Skip to main content

Über dieses Buch

This book contains selected papers from the 8th International Conference on Information Science and Applications (ICISA 2017) and provides a snapshot of the latest issues encountered in technical convergence and convergences of security technology. It explores how information science is core to most current research, industrial and commercial activities and consists of contributions covering topics including Ubiquitous Computing, Networks and Information Systems, Multimedia and Visualization, Middleware and Operating Systems, Security and Privacy, Data Mining and Artificial Intelligence, Software Engineering, and Web Technology. The proceedings introduce the most recent information technology and ideas, applications and problems related to technology convergence, illustrated through case studies, and reviews converging existing security techniques. Through this volume, readers will gain an understanding of the current state-of-the-art information strategies and technologies of convergence security.The intended readerships are researchers in academia, industry and other research institutes focusing on information science and technology.



Ubiquitous Computing


Improving Performance and Energy Efficiency for OFDMA Systems Using Adaptive Antennas and CoMP

The research described in this paper shows how by combining CoMP with adaptable semi-smart antennas it is possible to improve the throughput of an OFDMA LTE system and at the same time reduce the power required for transmission; i.e. providing better performance at lower cost. Optimisation of antenna patterns is performed by a Genetic Algorithm to satisfy an objective function that considers throughput, number of UEs handled as well as power in the transmission. It is shown that the dominant effect is using the semi-smart antennas and that the results are not sensitive to small amounts of movement.

Yapeng Wang, Xu Yang, Laurie Cuthbert, Tiankui Zhang, Lin Xiao

Privacy in Location Based Services: Protection Strategies, Attack Models and Open Challenges

The increasing capabilities of position determination technologies (e.g., GPS) in mobile and hand held device facilitates the widespread use of Location Based Services (LBS). Although LBSs are providing enhanced functionalities and convenience of ubiquitous computing, they open up new vulnerabilities that can be exploited to target violation of security and privacy of users. For these applications to perform, location of the individual/user is required. Consequently they may pose a major privacy threat on its users. So for LBS applications to succeed, privacy and confidentiality are key issues. “Privacy protection” has become the buzz word now days for the users of location based services. This problem has gained a considerable attention among the researcher community also. A state-of-art survey of privacy in location based services containing details of all privacy protection schemes is presented. Further, attack models and their handling mechanism are discussed in comprehensive manner. Finally, some open challenges in the area of location privacy are also demonstrated.

Priti Jagwani, Saroj Kaushik

An Efficient and Low-Signaling Opportunistic Routing for Underwater Acoustic Sensor Networks

Underwater acoustic sensor network (UASN) has been considered as a promising technique for ocean engineering. However, existing problems like long propagation delay, multipath interference and low available bandwidth are important issues in UASN. Based on the analysis of the UASNs characteristics, we proposed a novel protocol, named DUOR (Depth-based Underwater Opportunistic Routing protocol), which directs a packet to the sonobuoy on the surface in an efficient and low-signaling method. The contribution of DUOR is twofold: (1) minimizing signaling costs; (2) solving “void area” and “the extremely long forwarding path”. Simulation results show that the proposed DUOR outperforms the existing Depth Based Routing (DBR).

Zhengyu Ma, Quansheng Guan, Fei Ji, Hua Yu, Fangjiong Chen

A Novel Mobile Online Vehicle Status Awareness Method Using Smartphone Sensors

In this paper, we proposed an efficient method with flexible framework for vehicle status awareness using smartphone sensors, so called Mobile Online Vehicle Status Awareness System (MOVSAS). The system deployed while users to put their smartphones in any position and at any direction. In our proposed framework, principal component analysis (PCA) algorithm is used to selected suitable features from set of combining features on time-base, power-based and frequency-based domain, which extracted from accelerometer sensor data. The classification model using Random Forest (RF), Naïve Bayes (NB), K-Nearest Neighbor (KNN), and Support Vector Machine (SVM) algorithms to deploy for awareness issues of vehicle status. The refining model is proposed using Artificial Neural Network (ANN) algorithm aim to improved accuracy prediction vehicle status results before. Training data sets, which are collected and the dynamic feedback also helping improved accuracy of system. A number of experiments are shown that the high accuracy of MOVSAS with vehicle kinds as bicycle, motorbike and car.

Dang-Nhac Lu, Thi-Thu-Trang Ngo, Duc-Nhan Nguyen, Thi-Hau Nguyen, Ha-Nam Nguyen

A Study on OPNET State Machine Model Based IoT Network Layer Test

Model based testing can enable automated test case generation for many kind of application. Even test code can be generated from the model by specialized tools. IoT protocols for network layer have many constraints for exhaustive or manual testing because of battery problem and large number of sensor nodes. To solve these testing constraints, this paper proposes an efficient State Machine based test case generation for IoT network layer by using OPNET simulation model and test case generation tool. The size of test suite is compared according to the size of State Machine model from OPNET.

Young-hwan Ham, Hyo-taeg Jung, Hyun-cheol Kim, Jin-wook Chung

A Secure Localization Algorithm Based on Confidence Constraint for Underwater Wireless Sensor Networks

This paper proposed a novel secure localization algorithm based on confidence constraint for Underwater Wireless Sensor Networks (UWSNs). In recent years, UWSNs have attracted a rapidly growing interest from ocean battlefield surveillance. As essential technology, secure localization is crucial to the location-based applications. However, the localization process has been restricted by the adverse battlefield environments, e.g. the confidence problem of reference nodes and information due to disturbances or attacks, which lead to obvious degradation of localization security and accuracy. To solve this issue, we transformed the secure localization into a confidence constraint satisfaction problem. Zero-sum game method has been utilized to deal with the confidence problem of reference information. Simulation results show that our algorithm is an effective and efficient approach to localization for UWSNs.

Xiaofeng Xu, Guangyuan Wang, Yongji Ren, Xiaolei Liu

Networks and Information Systems


Generating Time Series Simulation Dataset Derived from Dynamic Time-Varying Bayesian Network

Numerous network inference models have been developed for understanding genetic regulatory mechanisms such as gene transcription and protein synthesis. Dynamic Bayesian network effectively represent the causal relationship between genes and gene and protein. Modern approaches employ single multivariate gene expression data set to estimate time varying dynamic Bayesian network. However, evaluating inferred time varying network is infeasible due to the absence of known gold standards. In this paper, the simulation model for time series gene expression level under certain network structure is proposed. The network can be used for assessing inferred data which is estimated based on simulated gene expression data.

Garam Lee, Hyunjin Lee, Kyung-Ah Sohn

AMI-SIM: An NS-2 Based Simulator for Advanced Metering Infrastructure Network

One of the main components of the smart grid is advanced metering infrastructure, which is responsible for delivering, concentrating and analyzing energy usage data. For an advanced metering infrastructure should cover extensive area like a city or a province, if organizing systems and lines were inadvertently chosen or their structure were not properly configured, they would generate huge waste of various resource or cause great damage to system itself. That’s why the simulation tool for large scale advanced metering infrastructure network is needed. In this paper, we defined requirements of advanced metering infrastructure network simulator useful for choosing proper system spec in given advanced metering infrastructure network topology, and proposed simulator designed to follow these requirements. The core engine of simulator is NS-2 but original NS-2 was modified to match our goal of simulation. Several tests were performed to evaluate if the performance of a node properly have an effect on simulation result, and to evaluate accuracy of capability usage degree calculation performed by simulator. These tests show that proposed simulator is available for practical use.

Nam-Uk Kim, Tai-Myoung Chung

Beyond Map-Reduce: LATNODE – A New Programming Paradigm for Big Data Systems

The Compute Aggregate model used to model Map Reduce does not allow for dynamic node reordering once a job has started, assumes homogenous nodes and a balanced tree layout. We introduce heterogeneous nodes into the tree structure, thereby causing unbalanced trees. Finally, we present a new programming abstraction to allow for dynamic tree balancing.

Chai Yit Sheng, Phang Keat Keong

Indoor Positioning Solely Based on User’s Sight

Determination of the absolute geographical position has become every day routine, using the Global Positioning System (GPS), despite the prior existence of maps. However no equally universal solution has been developed for determining one’s location inside a building, which is an equally relevant problem statement, for which GPS cannot be used. Existing solutions usually involve additional infrastructure on the end of the location provider, such as beacon installations or particular configurations of wireless access points. These solutions are generally facilitated by additional native mobile applications on the client device, which connect to this infrastructure. We are aware of such solutions, but believe these to be lacking in simplicity. Our approach for indoor positioning alleviates the necessity for additional hardware by the provider, and software installation by the user. We propose to determine the user’s position inside a building using only a photo of the corridor visible to the user, uploading it to a local positioning server, accessible using a browser, which performs a classification of the photo based on a Neural Network approach. Our results prove the feasibility of our approach. One floor of the university’s building with partially very similar corridors has been learned by a deep convolutional neural network. A person lost in the building simply accesses the positioning server’s website and uploads a photo of his current line of sight. The server responds by generating and displaying a map of the building with the user’s current position and current direction.

Matthias Becker

Naming Convention Scheme for Role Based Access Control in Cloud Based ERP Platforms

Cloud computing users can use at the same time the same cloud service. So, there is a need for having an access control mechanism to ensure that each user cannot access any sensitive data of other users. Several access control models have been proposed for cloud computing. However, these models need to be efficient and scalable due to increased workload (e.g., users, policies, etc.) in the cloud. This paper presents a role based access control model (RBAC) for cloud computing based on naming convention (NC) concept. The WSLA specification language is used for SLAs specification. A naming convention role based access control (NC-RBAC) is presented by modifying the standard RBAC to support the NC. Then, the proposed framework is designed based on the NC-RBAC to offer a simplified designed for the system administration of security in a large institution where there are many users is challenging to control access to resources. The proposed framework is implemented and its efficiency and scalability are measured using an experiment study. The result shows that the proposed framework provides an efficient and scalable access control for cloud computing while provides an administrator with an efficient and simple search method for classifying the cloud users.

Abed Alshreef, Lin Li, Wahid Rajeh

Multimedia and Visualization


Korean/Chinese Web-Based Font Editor Based on METAFONT for User Interaction

Font designers need to spend the same amount of time and efforts when designing a different style of an already designed outline font like italic, bold, and so forth. On the other hand, METAFONT expresses fonts by tracing the skeleton of characters with a pen. It can easily change the style of characters only by altering the shape of a pen. However, since the METAFONT is a programming language, it is difficult to be used by font designers who are not familiar with programming languages. In this paper, we propose a web-based font editor based on METAFONT, which can be used to easily edit Korean/Chinese fonts. It extracts parameters of characters based on their anatomy and applies them to modify fonts using GUI.

Minju Son, Gyeongjae Gwon, Jaeyeong Choi

A Highly Robust and Secure Digital Image Encryption Technique

Robust and secure image encryption requires primarily a very large key-space and immunity to differential attack. We report in this paper a new novel encryption technique using chaotic Logistic map, a support image, and a hyper-chaotic 4-D system. The support image, which is available both with the transmitter and the receiver, is utilized to enhance the robustness and security possible from the encryption algorithms based on chaotic Logistic map and Hyper-chaotic system. The support image is used in two different ways in two schemes that provide different levels of key-space enhancement and immunity to differential attacks. The final stage of the technique uses either one round or two rounds of pixel value diffusion with hyper-chaotic system. The results reported here are encouraging to defeat attacks attempted with high computing resources.

Md. Anwar Hussain, Popi Bora, Joyatri Bora

Saliency Based Object Detection and Enhancements in Static Images

Human visual system always focuses on the salient region of an image. From that region the salient features are obtained and can be collected by generating the saliency map. Natural statistics measures are used to measure the saliency from data collection of natural images. ICA filters are used to generate the saliency map that can blur the image. We have improved it by using different techniques like edge detection and morphological operations. By applying these algorithms we have successfully reduced the blur in images. That makes the salient objects more prominent by sharpening the edges. Proposed method is also compared with the state-of-the-art method like Achanta model.

Rehan Mehmood Yousaf, Saad Rehman, Hassan Dawood, Guo Ping, Zahid Mehmood, Shoaib Azam, Abdullah Aman Khan

A Center Symmetric Padding Method for Image Filtering

Padding the boundary is the first step in image filtering. If not appropriately handled, it often cause serious artifacts and losing information. In this paper an optimized boundary padding method is proposed to solve this problem. We analyze the pixel values near the boundary, calculate the gradient of the pixels, and pad the input image with a center symmetric padding method. Consequently, the details of the boundary will be preserved, and the number of unexpected noise will be suppressed as much as possible. We demonstrate that the center symmetric padding method is more effective than the traditional border handling methods in some computer vision applications.

Mengqin Li, Xiaopin Zhong

Implementing a Stereo Image Processing for Medical 3D Microscopes with Wireless HMD

Recently 3D scenes are used in medical fields. We developed a medical 3D microscope with a HMD. We mounted two cameras on the 3D microscope. Incoming images through an object lens of an optical microscope are projected on sensors of mounted cameras by using reflector mirrors. These are processed in a computer and sent to HMD by wireless communications. However, there is the problem about 3D imaging display. Two camera images are easily distorted due to the defect in the 3D microscope and the color of the images are also a little changed because of the color characteristics of the cameras. In this paper, we suggested the method to correct the geometric and color distortion of the stereo camera image and real time implementation of these methods using GPU. We used a wireless HMD for ease of use by doctors. This system would be helpful for doctors to operate more comfortably.

Cheolhwan Kim, Jiyoung Yoon, Yun-Jung Lee, Shihyun Ahn, Yongtaek Park

Design of OpenGL SC 2.0 Rendering Pipeline

OpenGL SC 2.0 is a newly specified 3D graphics standard, derived from the OpenGL ES 2.0, as its safety-critical profile. In this paper, we represent the high-level design scheme of the OpenGL SC 2.0 context and rendering system. We also show the detailed implementation strategy, for its step-by-step implementation works. These implementation schemes are the fundamental and theoretical frameworks for the OpenGL SC 2.0 system implementation. In near future, we will implement all the OpenGL SC 2.0 API functions and its theoretical background, from the OpenGL SC 2.0 system implementations.

Nakhoon Baek

Saliency Detection via Foreground and Background Seeds

In this paper, we come up with a bottom-up saliency algorithm that both consider the background and foreground cues. First, we compute the coarse saliency map by manifold ranking on a graph using partly image boundaries which consider as background prior. In this step, we just select left and top sides as background seeds. Second, bi-segment the preliminary saliency map to extract foreground information. Third, we utilize Markov absorption probabilities to highlight objects against the background. Results on public datasets show that our proposed method achieve fabulous performance.

Xiao Lin, Zhixun Yan, Linhua Jiang

Identification and Annotation of Hidden Object in Human Terahertz Image

Terahertz (THz) detection technology is a new security technology, it is play a significant role for social public security in the current situation. In this paper, we propose a new fast recognition algorithm for detection of suspicious objects according to the characteristics of human THz images. The algorithm consists of the following steps: (1), Smoothing and using gray stretch algorithm to enhance the terahertz images, (2), Distinguish the suspicious object connected and not connected to the background images. Here, THz images are classified by using our morphological classification algorithm, (3), Extracting a full human body contour by using our Bilateral Contour Tracking Comparison algorithm(BCTC). Finally, the computer can automatically identify and mark the hidden suspicious objects in Terahertz Image. Through a large number of experiments show that the new detection algorithm accuracy is reaching 92%. Our test results show that the new algorithm is quite effective for segmentation and extraction with human body contour and less time-cost.

Guiyang Yue, Zhihao Yu, Cong Liu, Hui Huang, Yiming Zhu, Linhua Jiang

Information Visualization for Mobile-Based Disability Test Applications

As part of the development of ICT convergence technologies for special education, we implemented a mobile-based disability test application. In this paper, we studied an information visualization method that uses a graph to optimize the display on the screen of mobile devices. The implemented application properly divides the screen of the mobile device, and the test scores obtained from the results of the disability test are displayed in a graph that can be moved left and right using the GraphView library. Test comments are also displayed in a table format that can be simultaneously moved up and down. This provides efficiency to users due to the large amount of data that can be represented.

Jongmun Jeong, Seungho Kim, Changsoon Kang, Mintae Hwang

Deep Convolutional Neural Networks for All-Day Pedestrian Detection

Pedestrian detection is a special topic in computer vision and plays a key role in intelligent vehicles and unmanned drive. Although recent pedestrian detect methods such as RPN_BF [1] have shown good performance from visible spectrum images at daytime, they have limited study for near-infrared image at nighttime. Unfortunately, when the traffic accident happened at night, the pedestrian is one of the most serious victims. Recently deep convolutional neural networks such as R-CNN/Faster R-CNN [2, 3] have shown excellent performance for object detection. In this paper, we investigate issues involving Faster R-CNN for construction of end-to-end all-day pedestrian detection system. We propose an effective baseline for pedestrian detection both on visible spectrum images and infrared images, using a same pre-train Faster R-CNN model. We comprehensively evaluate this method, the experiment results presenting competitive accuracy and acceptable running time.

Xingguo Zhang, Guoyue Chen, Kazuki Saruta, Yuki Terata

An Augmented Reality Learning System for Programming Concepts

Learning programming concepts through traditional learning method is challenging for novice programming students due to it lacks the characteristics to motivate students to further study on the particular content. This paper analyses the results of survey given to students enrolled in computing programmes at Sunway University in 2016. The survey focused on student involvement in learning using student engagement matrix. The overall findings states that students are only moderately engaged, hence we aim to enhance the interactivity and motivation of learning through the use of Augmented Reality (AR) technology in designing the learning system for programming concepts. Two basic of programming structures are implemented and evaluated by 20 novice programming students. 80% of students agreed that AR learning method is an effective method as it provides more fun, interest, provide basic understanding and good effect for students to learn programming.

Kelwin Seen Tiong Tan, Yunli Lee

Middleware and Operating Systems


Efficient vCore Based Container Deployment Algorithm for Improving Heterogeneous Hadoop YARN Performance

Hadoop has been widely utilized in processing a large-scale of data. Even though Hadoop-YARN has highly advanced processing performance, it still has performance limitations on heterogeneous environment. Its processing performance can be degraded when it is utilized in servers with different capabilities as well as the processes are scheduled for multiple users. To address this performance degradation problem caused by imbalanced load on heterogeneous environment, we propose an efficient vCore based container deployment algorithm that allocates the processing load for each container equally in order to minimize the deviation among processing task loads by controlling the number of vCores. The experiments show that our proposed method improved the performance on completion time by 18% on average.

SooKyung Lee, Min-Ho Bae, Jun-Ho Eum, Sangyoon Oh

A Real-Time Operating System Supporting Distributed Shared Memory for Embedded Control Systems

The paper presents a real-time operating system (RTOS) that supports distributed shared memory (DSM) for distributed embedded control systems. The RTOS provides a location-transparent environment, in which distributed software modules can exchange input and output values through the DSM. The RTOS is an extension to OSEK OS and it utilizes a real-time network called FlexRay. The consistency of the DSM is maintained according to the order of data transfer through FlexRay, not using inter-node synchronization. The worst case response time of the DSM is predictable if the FlexRay communication is well configured.

Yuji Tamura, Doan Truong Thi, Takahiro Chiba, Myungryun Yoo, Takanori Yokoyama

Security and Privacy


MBR Image Automation Analysis Techniques Utilizing Emulab

Virtual environment is frequently used for malware analysis. To hide their behavior, malware began to adopt virtual environment detection techniques. One of trickiest things when analyzing malware on real systems is that the operating system became unbootable due to the crash of partition and boot loader stored in the first sector of hard disk called the master boot record (MBR). It is quite time consuming to extract its MBR image from the crashed hard disk, so running malware on real system is usually considered as the last resort. In this research, we proposed a malware analysis system utilizing Emulab to extract crashed MBR images very easily.

Gibeom Song, Manhee Lee

Detection of DNS Tunneling in Mobile Networks Using Machine Learning

Lately, costly and threatening DNS tunnels on the mobile networks bypassing the mobile operator’s Policy and Charging Enforcement Function (PCEF), has shown the vulnerability of the mobile networks caused by the Domain Name System (DNS) which calls for protection solutions. Unfortunately there is currently no really adequate solution. This paper proposes to use machine learning techniques in the detection and mitigation of a DNS tunneling in mobile networks. Two machine learning techniques, namely One Class Support Vector Machine (OCSVM) and K-Means are experimented and the results prove that machine learning techniques could yield quite efficient detection solutions. The paper starts with a comprehensive introduction to DNS tunneling in mobile networks. Next the challenges in DNS tunneling detections are reviewed. The main part of the paper is the description of proposed DNS tunneling detection using machine learning.

Van Thuan Do, Paal Engelstad, Boning Feng, Thanh van Do

On the Security Analysis of Weak Cryptographic Primitive Based Key Derivation Function

A key derivation function is a function that generate one or more cryptographic keys from a private string together with some public information. The generated cryptographic key(s) must be indistinguishable from random binary strings of the same length. To date, there are designed of key derivation function proposals using cryptographic primitives such as hash functions, block ciphers and stream ciphers. The security of key derivation functions are based on the assumption that the underlying cryptographic primitives are secure from attacks. Unfortunately, the current works do not investigate the consequences for key derivation functions if the cryptographic primitives that are used to build the key derivation functions are broken. In this paper, we are confirmed by results of having the cryptographic primitives that are used to build the key derivation functions are broken, it allows the adversaries to distinguish the cryptographic key from the random binary string of the same length.

Chai Wen Chuah, Mustafa Mat Deris, Edward Dawson

On the Security of a Privacy Authentication Scheme Based on Cloud for Medical Environment

Recently, Chiou et al. proposed a secure authentication scheme which not only ensures message confidentiality and patient anonymity but also provides real telemedicine system implementation. However, in this paper, we found that Chiou et al.’s telemedicine scheme has some security weaknesses such as (1) it fails to protect the confidentiality of patient’s inspection report and doctor’s treatment record, (2) it fails to provide the property of unlinkability. The above-mentioned design flaws in Chiou et al.’s scheme may lead to privacy exposure and malicious outsider can link and discover the sensitive relationship between the patient and the doctor.

Chun-Ta Li, Dong-Her Shih, Chun-Cheng Wang

Physical Layer Security with Energy Harvesting in Single Hop Wireless Relaying System

In this paper, a single hop wireless relaying system, employing energy harvesting (EH) is proposed, where an information is transmitted from source to destination with the help of a relay in the presence of an eavesdropper. In this proposed system, source and relay utilizes EH technique for obtaining energy from a power beacon. The EH technique employed in this system is time switching EH technique. The secrecy performance of the proposed system is investigated for two cooperative schemes: decode-and-forward (DF), and amplify-and-forward (AF). The proposed system with EH technique provides improvement in secrecy rate, energy efficiency and power consumption as compared to that of the conventional scheme, as in the proposed system, nodes are powered up with EH technique, instead of using individual batteries. The secrecy rate of the proposed system with EH is higher than that of the conventional system by 8.89% for AF relay and by 9.83% for DF relay at a distance of 70 m between the relay and the eavesdropper. Also, it is shown by the resulting analysis that the AF relays have better secrecy rate than that of the DF relays in both proposed system and conventional system.

Poonam Jindal, Rupali Sinha

A System Design for the Measurement and Evaluation of the Communications Security Domain in ISO 27001:2013 Using an Ontology

This paper presents a system design using the design and linking semantic technology of ontologies by mapping the structure base and finding identical meanings of each text. The Wu and Palmer method and WordNet database were used for this purpose. The accuracy of the results of the concept are measured by using Recall, Precision, and F-Measure. Then, the proposed designed can be used to developed tools to qualify the security system for communications security domain under the standards of information security management for ISO 27001:2013. However, the cost of certification to organisations to meet international standards is considerable. Our intention was to demonstrate the ontology-based concept for organisations to be able to reduce their certification costs by waiving the requirement for an external consultant to evaluate their standards and policies.

Pongsak Sirisom, Janjira Payakpate, Winai Wongthai

Timing Side Channel Attack on Key Derivation Functions

A key derivation function is a function that generate one or more arbitrary length of cryptographic keys from a private string together with some public information. The generated cryptographic key(s) from this key derivation function proposals are generally indistinguishable from random binary strings of the same length based on formal mathematically proof. To date, there are designed of key derivation function proposals using cryptographic primitives such as hash functions, block ciphers and stream ciphers. However, there are limited security analysis of side channel attacks for the key derivation function proposals. This paper is to investigate the timing side channel attacks towards these three types of cryptographic primitives based key derivation function. Key derivation functions based on stream ciphers and block ciphers are input-dependent execution, the experiment results have shown that both key derivation functions proposals are vulnerable against timing side channel.

Chai Wen Chuah, Wen Wen Koh

A Security Aware Fuzzy Embedded ACO Based Routing Protocol (SAFACO) in VANETs

Intelligent vehicle technologies have been developed rapidly in recent year. Smart vehicles can exchange the essential information, such as the road and weather conditions, to guarantee the road safety. However, vehicles communicate with each other or the Road Side Unit (RSU) via wireless channel, which poses many challenges to fulfill the security requirements. In the data routing process, attackers can analyze, modify or drop the data packets to reveal the vehicles’ privacy or disturb the normal communication. In this paper, we devise a Security Aware Fuzzy embedded ACO routing algorithm (SAFACO) in VANETs, which combines digital signatures with fuzzy logic embedded ACO based routing protocol. After introducing the main structure of SAFACO, we also provide a detailed discussion of its security mechanism. The proposed secure communication scheme is able to provide the authentication, ensure the data consistency, preserve the privacy of vehicles, also to detect and isolate malicious vehicles.

Hang Zhang, Xi Wang, Dieter Hogrefe

Cryptanalysis of “An Efficient Searchable Encryption Against Keyword Guessing Attacks for Shareable Electronic Medical Records in Cloud-Based System”

Recently, Wu et al. proposed a secure channel free searchable encryption (SCF-PEKS) scheme which not only can guard against keyword guessing and record disclosure attacks but also can provide much better performance than other related scheme for shareable EMRs. However, in this paper, we demonstrated that Wu et al.’s SCF-PEKS scheme has some design flaws and security weaknesses such as (1) it fails to ensure the properties of message authentication and untraceability, (2) it fails to prevent the malicious outsider from forging a fake EMR as the sender, (3) it fails to prevent the privileged cloud insider from revealing sender’s secret keyword and sensitive record. The aforementioned security flaws in Wu et al.’s scheme may lead to privacy exposure and the receiver misled the contents of this fake record.

Chun-Ta Li, Cheng-Chi Lee, Chi-Yao Weng, Tsu-Yang Wu, Chien-Ming Chen

eDSDroid: A Hybrid Approach for Information Leak Detection in Android

Leaking personal information on mobile devices is a serious problem. Work on information leak detection for mobile devices, until now, mostly focus on action within a single application, while the coordinated action of several applications for the malicious purpose is becoming popular. This study proposes a hybrid approach that combines static and dynamic analysis to detect information leak as a result of the coordinated action of multiple applications. In this text, we call it inter-application malware. The analysis takes place in two stages. In the first stage, we use static analysis to determine the chains of sensitive actions on multiple applications. The chain of sensitive actions is the sequential user’s actions that may lead to information leakage. In the second stage, we validate whether the chain of sensitive actions indeed leaks user’s data by using the dynamic analysis. In fact, the applications in question are forced to execute after the chains of sensitive actions detected in the first stage. We monitor the sensitive actions to determine which actions make information leak. In order to do so, we modify the Android Emulator to trigger and monitor any action of any applications running on it. We have evaluated our tool, namely eDSDroid, on the famous Toyapps test case. The test result shows the correctness and effectiveness of our tool.

Hoang Tuan Ly, Tan Cam Nguyen, Van-Hau Pham

Detect Sensitive Data Leakage via Inter-application on Android by Using Static Analysis and Dynamic Analysis

Mobile malwares (especially spyware) target heavily Android operating system. Data is leaked if it exists a sensitive data flow (Data propagation from sensitive source to critical sink). Usually, a sensitive data flow is executed by a chain of actions. In most cases, sensitive data flows are begun and finished in the same application. However, there exist cases where these flows can pass to multi-applications by using inter-application communication. Standalone application analysis can not detect such data flows. Static analysis faces limitations when malware code is obfuscated. Besides, certain actions only take place when receiving input from user. It means that the information related to sensitive data flows is depended on the input data. Which is not available at analysis time when using static analysis technique. In this study, we propose uitHyDroid system that allows to detect sensitive data leakage via multi-applications by using hybrid analysis. uitHyDroid uses static analysis to collect sensitive data flows in each application. Meanwhile, dynamic analysis is used to capture inter-application communications. In this study, to evaluate our approach, we use the extended of DroidBench dataset and applications downloaded from GooglePlay. The experimental results show that almost of sensitive data leakages in the first dataset are correctly detected. Beside that, the proposed system detects several malwares in real-world applications.

Nguyen Tan Cam, Van-Hau Pham, Tuan Nguyen

Known Bid Attack on an Electronic Sealed-Bid Auction Scheme

In this paper, we cryptanalyze a receipt-free electronic sealed-bid auction scheme and show that it is forgeable under the known bid attack. Specifically, we show that a malicious sealer can forge the sealed-bid with non-negligible probability. Besides, we also propose a possible fix for the attack.

Kin-Woon Yeow, Swee-Huay Heng, Syh-Yuan Tan

Perceptual 3D Watermarking Using Mesh Saliency

In this paper, we introduce a novel blind 3D mesh watermarking method which focuses on preserving the appearance of the watermarked model. Despite the high transparency achieved by existing 3D watermarking schemes, we observe that only a small amount of geometric error can bring a significant impact to appearance of 3D models, especially in visually important regions. We integrate this human perceptual importance, called saliency, to control the distortions on surfaces. Our method enhances the imperceptibility while maintaining the efficiency of processing spatial information by conjugating spatial and spectral regions. We use the vertex norm distribution and solve the quadratic error minimization problem to insert watermark bits. Experimental results demonstrate that our method performs well for perceived visual quality and also robustness against various geometric attacks.

Jeongho Son, Dongkyu Kim, Hak-Yeol Choi, Han-Ul Jang, Sunghee Choi

Perceptual Watermarking for Stereoscopic 3D Image Based on Visual Discomfort

As 3D content including images and videos has been common and popular, the demand for copyright protection has been increased. To protect the copyright of 3D content, 3D image watermarking schemes have been proposed. Given that visual discomfort can occur in 3D content during the watermark embedding process due to binocular mismatch, unlike in 2D content, 3D watermarking schemes should consider visual discomfort because it can decrease the performance of the human vision system (HVS). In this paper, a perceptual watermarking scheme for stereoscopic 3D images considering the issue of visual discomfort is introduced. The proposed scheme analyses the factors that cause visual discomfort during the watermark embedding process. In order to minimize visual discomfort and prevent quality degradation, perceptual masking using an occluded map and a defocused map is applied. Experimental results show that the proposed scheme offers low visual discomfort while preserving the robustness against attacks.

Sang-Keun Ji, Ji-Hyeon Kang, Heung-Kyu Lee

Fingerprint Spoof Detection Using Contrast Enhancement and Convolutional Neural Networks

Recently, as biometric technology grows rapidly, the importance of fingerprint spoof detection technique is emerging. In this paper, we propose a technique to detect forged fingerprints using contrast enhancement and Convolutional Neural Networks (CNNs). The proposed method detects the fingerprint spoof by performing contrast enhancement to improve the recognition rate of the fingerprint image, judging whether the sub-block of fingerprint image is falsified through CNNs composed of 6 weight layers and totalizing the result. Our fingerprint spoof detector has a high accuracy of 99.8% on average and has high accuracy even after experimenting with one detector in all datasets.

Han-Ul Jang, Hak-Yeol Choi, Dongkyu Kim, Jeongho Son, Heung-Kyu Lee

Content Recapture Detection Based on Convolutional Neural Networks

Detecting recaptured images has been considered as an important issue. The previous techniques tried to make hand-crafted features represent the statistical characteristics of the recaptured images. Different to the existing methods, the proposed method solves the recapturing detection problem based on a deep learning technique which shows high performance for various applications in recent image processing. Specifically, we propose a recaptured image classification scheme based on a convolutional neural networks (CNNs). To our best knowledge, this is the first work of applying CNNs into the recaptured image detection. For reliable performance evaltuation, we used high-quality database for training and testing. The experimental results show high performance compared to the state-of-the-art methods.

Hak-Yeol Choi, Han-Ul Jang, Jeongho Son, Dongkyu Kim, Heung-Kyu Lee

Secret Sharing Deniable Encryption Technique

Deniable Encryption was introduced to ensure that the sender and/or receiver in the communication able to create and encrypt fake messages into different ciphertexts to protect the real messages from a coercing adversary. Numerous past works have been proposed to cater the issues of coercible communication. To date, only Bi-Deniable Encryption has catered the issue of sender and receiver coercion. However there can be more than one receiver in a communication at a time. Multi-Party Computation addresses the problem of dishonest users that can be corrupted by the adversary. In some cases, Deniable Encryption may fails due to the coercer already know that it is applied in the communication protocol. A new deniability technique is needed to solve these problems. This research proposed Secret Sharing Deniable Encryption Technique. Secret Sharing technique is used to hide the secret key by creating shares and distributed among users.

Mohsen Mohamad Hata, Fakariah Hani Mohd Ali, Syed Ahmad Aljunid

Improved 3D Mesh Steganalysis Using Homogeneous Kernel Map

Steganalysis targets to detect the existence of hidden information in a given content. In this paper we propose to use a local feature set which is designed to enhance discrimination of features obtained from a cover and a stego mesh. The proposed feature captures the fine deformation of the 3D mesh surface induced by a steganography or watermarking method. In our 3D steganalysis approach, in addition, we apply the homogeneous kernel map to the local feature set, which make it possible to bring much more discrimination via non-linear mapping. The proposed feature set and its combination with the homogeneous feature map have shown good performance on two different steganography and watermarking algorithm with a well known and widely used 3D mesh database through repeated experiments.

Dongkyu Kim, Han-Ul Jang, Hak-Yeol Choi, Jeongho Son, In-Jae Yu, Heung-Kyu Lee

From Sealed-Bid Electronic Auction to Electronic Cheque

In this paper, we establish a relation between sealed-bid e-auction and e-cheque by proposing a transformation technique which transforms a secure sealed-bid e-auction into a secure e-cheque scheme. Although the application scenario differs, we notice that the scheme structure and fundamental security properties in both schemes are similar, namely, unforgeability, anonymity and indistinguishability. As a proof of concept, we apply the transformation technique on the classic Sakurai and Miyazaki sealed-bid e-auction scheme and obtain a secure e-cheque scheme.

Kin-Woon Yeow, Swee-Huay Heng, Syh-Yuan Tan

Enhanced Database Security Using Homomorphic Encryption

When sensitive data is stored on publicly available areas, privacy of that data becomes a concern. Organizations may wish to move data to public servers so the data is more accessible by their employees or consumers. It is important that this data be encrypted to ensure it remains confidential and secure. When this data is encrypted, it becomes difficult or impossible to perform calculations on a publicly stored database. A solution to this is homomorphic encryption, which allows an unlimited number of computations on encrypted data. This project analyzes an N-tier rotation scheme which allows an unlimited number of addition and subtractions of encrypted data, along with an unlimited number of scalar multiplications and divisions. This scheme is inspired by a combination lock and features multiple levels of security depth. The result of the proposed algorithm is a fast encryption scheme which allows data to be manipulated post encryption.

Connor Røset, Van Warren, Chia-Chu Chiang

k-Depth Mimicry Attack to Secretly Embed Shellcode into PDF Files

This paper revisits the shellcode embedding problem for PDF files. We found that a popularly used shellcode embedding technique called reverse mimicry attack has not been shown to be effective against well-trained state-of-the-art detectors. To overcome the limitation of the reverse mimicry method against existing shellcode detectors, we extend the idea of reverse mimicry attack to a more generalized one by applying the k-depth mimicry method to PDF files. We implement a proof-of-concept tool for the k-depth mimicry attack and show its feasibility by generating shellcode-embedded PDF files to evade the best known shellcode detector (PDFrate) with three classifiers. The experimental results show that all tested classifiers failed to effectively detect the shellcode embedded by the k-depth mimicry method when $$k \ge 20$$.

Jaewoo Park, Hyoungshick Kim

Reconstruction of Task Lists from Android Applications

The popularity of Android devices has made Android apps attractive targets for attackers. Some static checkers have been proposed to check whether an Android app is vulnerable to privacy leakage and other attacks. However, these checkers model the control flows in the app following the ICC events, ignoring the intrinsic purpose of users’ interaction with mobile devices. In fact, users carry out various tasks using mobile apps, e.g. online shopping. An Android task consists of one or more Activities, which are organized in the back stack of the task. By extracting the task lists among Activities in Android apps, we can capture all control flow transitions between them, including those bring by ICC events and back button events. We design and implement a system, which leverages the combination of static and dynamic analysis to extract the task lists. Our system can be used to detect task related attacks and help static checkers construct more complete call graphs.

Xingmin Cui, Ruiyi He, Lucas C. K. Hui, S. M. Yiu, Gang Zhou, Eric Ke Wang

Design and Evaluation of Chaotic Iterations Based Keyed Hash Function

Investigating how to construct a secure hash algorithm needs in-depth study, as various existing hash functions like the MD5 algorithm have recently exposed their security flaws. At the same time, hash function based on chaotic theory has become an emerging research in the field of nonlinear information security. As an extension of our previous research works, a new chaotic iterations keyed hash function is proposed in this article. Chaotic iterations are used both to construct strategies with pseudorandom number generator and to calculate new hash values using classical hash functions. It is shown that, by doing so, it is possible to apply a kind of post-treatment on existing hash algorithms, which preserves their security properties while adding Devaney’s chaos. Security performance analysis of such a post-treatment are finally provided.

Zhuosheng Lin, Christophe Guyeux, Simin Yu, Qianxue Wang

Data Mining and Artificial Intelligence


Intellectual Overall Evaluation of Power Quality Including System Cost

This paper presents a new methodology to evaluate power quality for a distribution system. Instead traditional evaluation methodology can evaluate a certain face of power quality, such as SAIFI and SAIDI for reliability, SARFI for voltage sag/swell, and THD for harmonics, by using IEEE Standard Indices, newly present evaluation methodology can overall evaluate for power quality items, maintenance cost, and system losses. This methodology uses AHP model and newly developed Ideal AHP. First, AHP model was employed and implemented for power quality overall evaluation. Second, Ideal AHP was developed to overcome different unit problems of power quality. This paper applied the method for a distribution system, and showed the process of the method, and obtained overall evaluation of the system.

Buhm Lee, Dohee Sohn, Kyoung Min Kim

A Data-Driven Decision Making with Big Data Analysis on DNS Log

Domain Name System (DNS) log has been considered as a great source of valuable information for the decision making on government policy or business strategy because querying DNS is the first step of all Internet activities. Due to the size of DNS log, Hadoop is considered as a prominent solution, but the geographical dispersal of DNS log hinders to adopt it in an ordinary way. Hadoop assumes all data source should be located on a single Hadoop File System (HDFS), but DNS log is stored on DNS servers dispersed all over the world. To resolve this issue, a new method named “Localized Analysis & Merge (LAM)” is proposed in this paper. The proposed method enables Hadoop to analyze DNS log on the dispersed DNS servers and it reduced the whole processing time dramatically. Also, the LAM method showed that DNS log can be used to extract a lot of valuable information such as a malware detection, the access frequency over countries, etc.

Euihyun Jung

A Case-Based Approach to Colorectal Cancer Detection

Colorectal cancer is one of the most common malignancies in developed countries. Although it is not well known what causes this type of cancer, studies have showed that there are certain risk factors associated that may increase the likelihood of developing such malignancy. These factors comprise, among others, individual’s age, lifestyle habits, personal disease history, and genetic syndromes. Despite its high mortality, colorectal cancer may be prevented with an early diagnosis. Thus, this work aims at the development of Artificial Intelligence based decision support system to assess the risk of developing colorectal cancer. The framework is built on top of a Logic Programming approach to Knowledge Representation and Reasoning, complemented with a Case-based approach to computing that caters for the handling of incomplete, unknown, or even self-contradictory data, information or knowledge.

Pedro Morgado, Henrique Vicente, António Abelha, José Machado, João Neves, José Neves

Multi-Modes Cascade SVMs: Fast Support Vector Machines in Distributed System

Machine learning is one field of Artificial Intelligence (AI) to help machines solve problems. Support Vector Machines (SVMs) are classic methods in machine learning field and are also used in many other AI fields. However, the model training is very time-consuming when meeting large scale data sets. Some efforts have been devoted to develop it for distributed memory clusters. Their bottleneck is the training phase, where the structure is immobile. In this paper, we propose Multi-Modes Cascade SVMs (MMCascadeSVMs) to adaptively reshape the structure. MMCascadeSVMs employs analytical hierarchy process to qualitatively analyse the similarity between adjacent hierarchies. Furthermore, MMCascadeSVMs leverages a two-stage algorithm: the first stage is to compute the similarity between two adjacent models, and the similarity is built for halting criterion. The second stage is to predict new samples based on multi models. MMCascadeSVMs can modify the structure of SVMs in distributed systems and reduce training time. Experiments show that our approach significantly reduces the total computation cost.

Lijuan Cui, Changjian Wang, Wanli Li, Ludan Tan, Yuxing Peng

Deep Learning Based Recommendation: A Survey

Due to the great success, deep learning gains much attentions in the research field of recommendation. In this paper, we review the deep learning based recommendation approaches and propose a classification framework, by which the deep learning based recommendation approaches are divided according to the input and output of the approaches. We also give the possible research directions in the future.

Juntao Liu, Caihua Wu

Towards Collaborative Data Analytics for Smart Buildings

Smart buildings are buildings equipped with the latest technological and architectural solutions, controlled by Building Management Systems (BMS), operating in fulfillment of the typical goals of increasing occupants’ comfort and reducing buildings’ energy consumption. We witness a slow, but steadily increasing trend in the number of buildings that become smart. The increase in availability and the decrease in prices of sensors and meters, have made them almost standard elements in buildings; both in newly built and existing ones. Sensors and meters enable growing collections of data from buildings that is available for further analytics to support meeting BMS’ performance goals. For a single building to benefit from this data-based analytics, it will take a long time. Collaboration of BMS in their data analytics processes can significantly shorten this time period. This paper makes two contributions: one, a careful examination of the potential of buildings for collaborative data analytics; and two, description of models for collaborative data analytics.

Sanja Lazarova-Molnar, Nader Mohamed

English and Malay Cross-lingual Sentiment Lexicon Acquisition and Analysis

Sentiment analysis finds opinions, sentiments or emotions in user-generated contents. Most efforts are focusing on the English language, for which a large amount of sources and tools for sentiment analysis are available. The objective of this paper is to introduce a cross-lingual sentiment lexicon acquisition method for the Malay and English languages and further being test on a set of news test collections. Several part of speech tags are being experimented using the Word Score Summation technique in order to classify the sentiment of the news articles. This method records up to 50% as experimental accuracy result and works better for verbs and negations in both the English and Malay news articles.

Nurul Amelina Nasharuddin, Muhamad Taufik Abdullah, Azreen Azman, Rabiah Abdul Kadir

A Novel Natural Language Processing (NLP) Approach to Automatically Generate Conceptual Class Model from Initial Software Requirements

Conceptual class model is an essential design artifact of Software Development Life Cycle (SDLC). The involvement of several resources and additional time is required to generate the class model from early software requirements. On the other hand, Natural Language Processing (NLP) is a knowledge discovery approach to automatically extract elements of concern from initial plain text documents. Consequently, it is frequently utilized to generate various SDLC artifacts like class model from the early software requirements. However, it is usually required to perform few manual processing on textual requirements before applying NLP techniques that makes the whole process semi-automatic. This article presents a novel fully automated NLP approach to generate conceptual class model from initial software requirements. As a part of research, Automated Requirements 2 Design Transformation (AR2DT) tool is developed. The validation is performed through three benchmark case studies. The experimental results prove that the proposed NLP approach is fully automated and considerably improved as compared to the other state-of-the-art approaches.

Mudassar Adeel Ahmed, Wasi Haider Butt, Imran Ahsan, Muhammad Waseem Anwar, Muhammad Latif, Farooque Azam

The Applications of Natural Language Processing (NLP) for Software Requirement Engineering - A Systematic Literature Review

Natural Language Processing (NLP) is a well-known technique of artificial intelligence to extract the elements of concerns from raw plain text information. It can be utilized to process the early software requirements in order to achieve the goals like requirement prioritization and classification (functional and non-functional). To the best of our knowledge, no research work is available yet to examine and summarize the utilization of NLP in the domain of Software Requirement Engineering (SRE). Therefore, in this paper, we investigate the applications of NLP in the context of SRE. A Systematic Literature Review (SLR) is carried out to select 27 studies published during 2002–2016. Consequently, 6 NLP techniques and 14 existing tools are identified. Furthermore, 9 tools and 2 algorithms, proposed by the researchers, are presented. It has been concluded that the NLP techniques and tools are highly supportive to accelerate the SRE process. However, some manual operations are still required on initial plain text software requirements before applying the desired NLP techniques.

Farhana Nazir, Wasi Haider Butt, Muhammad Waseem Anwar, Muazzam A. Khan Khattak

Smart Fetal Monitoring

Fetal movement is an important index of fetal well-being. The absence or a reduction in fetal movement is a symptom or an alarming sign of fetal compromise or even death. The timely detection of abnormalities in fetal movement is vital to reduce the incidence of fetal loss, perinatal morbidity and maternal distress. This paper presents a smart fetal monitoring system to detect fetal movement and monitor movement pattern safely and reliably by using a new fabric sensor belt. The monitoring belt is wearable, non-intrusive, radiation free and washable. The new algorithms are robust for automated analysis, detection and assessment of fetal condition, which include effective noise removal, feature extraction, time sequence data analysis and decision support. Both the design of fabric sensor and functionality implementation of the belt are original and unique. The results of preliminary clinical trials demonstrate the feasibility of our prototype. There are no such similar products available in the market.

Jane You, Qin Li, Zhenhua Guo, Ruohan Zhao

A Network-Based Approach on Big Data for the Comorbidities of Urticaria

This study investigates the network properties of urticaria comorbidity. Comorbidities are the presence of one or more additional disorders or diseases that co-occur with a primary disease or disorder. The purpose of this study is to identify diseases that co-occur with urticaria. Research data was collected from 1,154,534 urticaria outpatient department medical records out of 163,141,270 outpatient department medical records from 1997 to 2010 in Taiwan. Through the phenotypic disease network (PDN), this study has identified the diseases that are associated with urticaria. It has been discovered that the PDN has a complex structure where some diseases are highly connected while others are barely connected at all. While not conclusive, these findings can explain that the more connected the diseases are, the higher the mortality rate is, as patients developing highly connected diseases are more likely to be diagnosed at an advanced stage of the disease, which can be reached through multiple paths in the PDN.

Yi-Horng Lai, Chih-Chiang Ho, Piao-Yi Chiou

Application of Automated Theorem-Proving to Philosophical Thought: Spinoza’s Ethics

We have applied the automatic theorem-prover Prover9 to prove first eleven theorems of Part 1 of Benedict de Spinoza’s Ethics. We have used a previous formalization of that segment developed by Blum and Malinovich. We have found Prover9 to be very efficient, providing proofs in tens of miliseconds. It appears that the only, but fundamental, limitation for testing philosophical reasoning is related to the difficulty of unique formalization.

Maciej Janowicz, Luiza Ochnio, Leszek J. Chmielewski, Arkadiusz Orłowski

Improving the B+-Tree Construction for Transaction Log Data in Bank System Using Hadoop

In Socialist Republic of Vietnam, applying the Big data to process any kind of data is still a challenge, especially in the banking sector. Until now, there is only one bank applied Big data to develop a data warehouse system has focused, consistent, can provide invaluable support to executives make immediate decisions, as well as planning long-term strategies, however, it still not able to solve any specific problem. Nowadays, from the fact large amounts of traditional data are still increasing significantly, if B-tree is considered as the standard data structure that manage and organize this kind of data, B+-tree is the most well-known variation of B-tree that is very suitable for applying bulk loading technique in case of data is available. However, it usually takes a lot of time to construct a B+-tree for a huge volume of data. In this paper, we propose a parallel B+-Tree construction scheme based on a Hadoop framework for Transaction log data. The proposed scheme divides the data into partitions, builds local B+-trees in parallel, and merges them to construct a B+-tree that covers the whole data set. While generating the partitions, it considers the data distribution so that each partitions have nearly equal amounts of data. Therefore the proposed scheme gives an efficient index structure while reducing the construction time.

Cong Viet-Ngu Huynh, Jongmin Kim, Jun-Ho Huh

Calculate Deep Convolution NeurAl Network on Cell Unit

We introduce CACU, a new deep learning algorithm framework for CNN which using binary method to reduce the consumptions in convolution calculating. CACU introduces bit data flow to fit the CPU platform. Using binary-weights and xnor methods to speed-up the convolution’s computation on CPU device. GPU is also supported in CACU. CUDA version is implemented for accelerating large scale models’ training and inference. CACU is a C++ library with no dependencies except Boost. CACU is not only developed for the CNN’s usage in application, it’s helpful for researchers to take an inner investigation of bit method in CNN. It’s a fully open-source platform which is available on GitHub.

Haofang Lu, Ying Zhou, Zi-Ke Zhang

Stepwise Structure Learning Using Probabilistic Pruning for Bayesian Networks: Improving Efficiency and Comparing Characteristics

This paper evaluates a structure learning method for Bayesian networks called Stepwise Structure Learning with Probabilistic pruning (SSL-Pro). Probabilistic pruning allows this method to obtain appropriate network structures while reducing computational time for structure learning. Computer experiments were conducted to investigate the characteristics of the SSL-Pro. Results showed that the SSL-Pro generally provided favorable performance, and revealed several parameter-setting guidelines to ensure reasonable learning.

Godai Azuma, Daisuke Kitakoshi, Masato Suzuki

Differential-Weighted Global Optimum of BP Neural Network on Image Classification

This paper investigates the problem of image classification with limited or no annotations, but abundant unlabelled data. We propose the DBP (Differential-weighted Global Optimum of BP Neural Network) to make the performance of the BP Neural Network to become more stable. In details, the optimal weights will be saved as potential global optimum during the process of iteration and then we combine the BP Neural Network with the potential global weights to adjust parameters in the backward feedback process for the first time. As the model has fallen into local optimization, we replace the present parameters with the potential global optimal weights to optimize our model. Besides, we consider EP, CNN, SIFT image features and conduct several experiments on eight standard datasets. The results show that DBP mostly outperforms other supervised and semi-supervised learning methods in the state of the art.

Lin Ma, Xiao Lin, Linhua Jiang

Classification Model for Skin Lesion Image

The problem of image classification mostly focuses on feature extraction which depends on image data. However, the famous feature is extracted from images using Gray Level Co-occurrence matrix (GLCM) in order to cover all feature, which are range differently. The problem is less accuracy when it is inputted into classification model. This idea of paper is proposed for feature normalization 2 types called local-normalization and global-normalization from all feature extraction using GLCM in preprocessing of classification method. These feature values extracted from GLCM are transformed to proper normalization and given input classification model as Back Propagation in Multi-layer perceptron and Multi-Class support vector machine methods (polynomial and RBF) to compare these classification models. The skin disease image classification which occurs from skin lesions has divided into four classes: Tinea Corporis, Pityriasis Versicolor, Molluscum Contagiosum and Herpes Zoster. The experimental results are shown comparison between non-normalization and normalization within the same class called local-normalization and all classes called global-normalization. The accuracy of MLP with normalization by min-max normalization with local-normalization is highest to 92%. The methods of polynomial-SVM and RBF-SVM are given accuracy as 85% and 81% respectively. Whereas, the accuracy of classification model with non-normalization, and global-normalization are given average of accuracy as only 35% approximately.

Nontachai Danpakdee, Wararat Songpan

Software Engineering


Generation of Use Cases for Requirements Elicitation by Stakeholders

Use case diagrams and scenarios are often used in the requirements elicitation phase in software development. It is difficult for developers to create them based on appropriate stakeholders’ requirements. Meanwhile, stakeholders can survey existing applications to find functions and interactions that are similar to their requirements. This paper proposes a method to generate the bases of use case diagrams from the operation histories of existing applications. Operation histories are divided into operations of individual windows, and the entire window-switching sequence in an existing application is represented as a directed graph. Then the directed graphs are analyzed to extract the window-switching sequences that correspond to use cases. Finally, use case diagrams are generated.

Junko Shirogane

Smart Learner-Centric Learning Systems

This paper is concerned with knowledge delivery in learning systems. A learning system is a system through which learners can obtain knowledge. Providers deliver the knowledge in the way they decide is most appropriate. With the wide popularity of e-learning, learners can obtain knowledge from any source in any location in the world. On the other hand, each learner has his/her own learning style(s). But current learning systems are provider oriented. We believe that this is not sufficient. Hence, this paper introduces a smart learner-centric architecture. Smart in the sense that it allows the learner to decide the source of the knowledge he/she is requiring depending on his/her preferred learning style(s). Learner-centric is in the sense that knowledge providers publish their knowledge in a rich definition that specifies the used learning style(s). The architecture allows knowledge requesters to control the source of the knowledge and the learning style used to deliver the knowledge. The proposed architecture is an extension of traditional service-oriented architectures. It extends the definition of traditional service by adding context.

Naseem Ibrahim, Ismail I. K. Al Ani

Prioritized Process Test: More Efficiency in Testing of Business Processes and Workflows

Testing business processes and workflows in information systems, while aiming to cover all possible paths, requires high efforts demanding considerable costs. In this paper, we propose an algorithm generating a path-based test cases from the system model, based on weighted directed graph. The approach brings an alternative to the currently established test requirements concept. The algorithm reflects various levels of priorities of particular functions in the tested system, previously defined by the test designer. When compared to simulated naive approaches based on reverse reduction of test set, our proposed algorithm produces more efficient test cases in terms of number of the total test steps, whilst keeping the same level of test coverage of the priority functions of the tested system.

Miroslav Bures, Tomas Cerny, Matej Klima

Static Testing Using Different Types of CRUD Matrices

Static testing leads to early detection of defects throughout a project software development. This results in reduced costs and risks in the development process. Various types of static tests can be performed. In this paper, we propose extensions to contemporary static testing techniques based on CRUD matrices. In particular, we consider cross-verification between various types of CRUD matrices made by different parties at different stages of the project. This leads into extended the verification consistency of a CRUD matrix. In our evaluation, proposed techniques lead to significantly more consistent test Data Cycle Test cases, when involving our static testing techniques. Moreover, our results indicate positive impact on lowering the number of defects that usually remain undetected under the system test.

Miroslav Bures, Tomas Cerny

Extracting Test Cases with Message-Sequence Diagram for Validating the Photovoltaic Energy Integrated Monitoring System

Recently, in the photovoltaic energy integrated monitoring software system, it has more complex, and accordingly may be possible to occur more errors. In this industrial services, a small error can lead to a huge accident to make the power failures. To completely build this system, it should verify whether it is or not stability of software through measuring the full coverage with generating test cases in detail level based on a message sequence model. In this paper, we apply to verify a system stability of this monitoring system with our previous research such as the automatic test case generation based on UML 2.4.1 message-sequence diagram via cause-effect diagram. With this, we extract automatically test cases on coverage.

Woo Sung Jang, Bo Kyung Park, Hyun Seung Son, Byung Kook Jeon, R. Young Chul Kim

Automatic Test Case Generation with State Diagram for Validating the Solar Integrated System

For safe software development on the solar integrated monitoring system, it is very important how to identify safe behaviors of the system behaviors. Therefore, it needs to test the system behaviors after the software development. To solve this problem, the existing studies have proposed the use case based test coverage analysis at all software development stages [1]. With this method, we identify the test cases based on priority of the system behaviors. In this paper, we proposes automatic test case extraction method based on state diagram among the use case-based test coverage extraction methods. That is, we can use state diagram for a system behaviors with which generates test cases to validate the system. We show an applicative case on the system behaviors of a solar integrated system with this approach.

Bo Kyung Park, Woo Sung Jang, Hyun Seung Son, Keunsang Yi, R. Young Chul Kim

Comparison of Software Complexity Metrics in Measuring the Complexity of Event Sequences

One of the main challenges in software development is the complex structure of a system. The software development for event sequences is complex. It is a challenge to define a complexity metric for event sequences application. Lack of knowledge in complexity metric can lead to issues such as rises in software cost and delays in project timing. Numerous complexity metrics have been proposed and published, such as information flow complexity, lines of code, function points, and unique complexity metric. However, in the context of the event sequences, most of the research focuses on measuring web graphs, measuring the web traffic and how the complexity of the web impacts the customer. In this paper, the researchers studied and compared five different software complexity metrics. This paper describes the on-going research that addresses the issue to produce a unique weight to prioritise event sequences test cases.

Johanna Ahmad, Salmi Baharom

Implementation of Ceph Storage with Big Data for Performance Comparison

High Available share storage becomes one of the important resource information to expand our system especially for Big Data implementation system. To consider the world demand of reduce high risk data corrupt and improve the reading and writing storage performance, through our research we mainly apply Ceph storage with Big Data Performance testing in order to solve the best reading and write speed performance and data backup. This system is started from Hadoop operations. The data is stored in the Hadoop Distributed File System (HDFS) and copied to Alluxio MEM space. The data through Map Reduce processing (Mapping – Sorting – Filtering – Reducing) got the result and the output will be stored in to Alluxio MEM space. For the first experimental, we use S3 API and Rados Gateway of Ceph components as a bridge between Alluxio and Object Storage Daemon (OSDs). The second experimental is the same like first environment, but the output of Map Reduce will be directly connect to Object Storage Daemon using Ceph File System (CephFS). The data is more safety in the Ceph than in the Alluxio MEM only, because OSDs can back up the data with object storage levels. We also can use S3 browser (GUI) to maintenance the OSD’s data, e.g.: grant access, keep folder, create user account, move data location etc. The last one, we use Inkscope to monitor all system, if there is any problem the system will respond the error or giving warning alerts to the user.

Chao-Tung Yang, Cai-Jin Chen, Tzu-Yang Chen

Web Technology


Predicting Engaging Content for Increasing Organic Reach on Facebook

Over the past few years, many people have been concerned about declines in organic reach for their Facebook Pages. This has been a pain for many businesses, especially those small businesses and startup. Organic reach refers to how many people you can reach for free on Facebook by posting to your page. The declined organic reach results from some key changes to improve how News Feed chooses content. News Feed is aimed at becoming more engaging, even as the amount of content being shared on Facebook continues to grow. This paper presents a technique to increase Facebook organic reach. The method investigates some promising factors to predict the engaging content posting on business Pages, so that the post would gain exposure in News Feed of the liking users on Facebook. The proposed approach provides the alternative for businesses to increase the organic reach without more expense on advertising posted on Facebook Pages.

Natthaphong Phuntusil, Yachai Limpiyakorn

Learning Performance Evaluation in eLearning with the Web-Based Assessment

With the prevalence of Internet, eLearning provides a platform for education that enables students to take classes online. While eLearning provides a flexible learning environment, it also has drawbacks. This research investigated the potential benefit of the proposed method in an informal formative web-based assessment. The data were collected from college students in three separated groups. The statistical analyses showed mixed results. Some possible reasons were discussed along with other methods that could be further explored in the future.

Cheng-Ying Yang, Tsai-Yuan Chung, Min-Shiang Hwang, Cheng-Yi Li, Jenq-Foung JF Yao

Improving Teaching and Learning in Southeast Asian Secondary Schools with the Use of Culturally Motivated Web and Mobile Technology

Improving and stimulating teaching and learning are an interesting topic among educational researchers. As technology advances and with mobile technology and the Internet being used widely, it has become a vital tool for knowledge gathering and information sharing. It can foster new directives for teachers and stimulate the minds of learners, improving learning outcomes. However, the process of this triangulation of interaction has been overlooked in the Southeastern Asian region and requires an in-depth study into its culturally diverse background to identify its core problems and benefits. We propose Student Motivated Integrated Learning & Education with culture (SMiLE c) model in order to integrate education with web and mobile technology with an emphasis on Asian learning culture to promote active learning reduce overall costs and improves student learning outcome. We illustrate how this model can be implemented in Southeast Asian schools to improve teaching to suit students’ learning style during lessons through an alert system and motivates student to participate in discussions which can be used by the institution to identify student’s skill set early in the learning process.

Sithira Vadivel, Insu Song, Abhishek Singh Bhati

Game-Based Learning to Teach Assertive Communication ClickTalk for Enhancing Team Play

The rise of the computer as an “entertainment medium” has been achieved today only through computer games. But computer or video games have the potential and capability to function as “mediums of education” too. Can game-based learning provide learning experience and yet there is fun in changing behavior (assertive communication) for the individual? Game-based learning has been used to teach various skills to people with quite encouraging results. In this paper, a study was carried out to confirm the hypothesis that game-based learning can be a good platform to teach assertive communication delivering learning and fun because of its benefits and encouraging results from other research. A high-fidelity game-based learning prototype, ClickTalk was created for this purpose and it was evaluated with some interesting results.

Bah Tee Eng

Cloud Storage Federation as a Service Reference Architecture

Cloud storage is one of the leading technologies to address todays data storage demand. However, facing Big Data storage challenge relying on a single cloud storage provider is almost impossible. Cloud storage federation model provides the integration of multiples cloud storage providers into a single virtual storage pool, eliminating the dependency on a single provider and decreasing vendor lock-in problem. Moreover, federating multiple cloud storage providers improve data availability, storage scalability and data processing performance. In this paper, we propose a reference architecture for Cloud Storage Federation Service implementation. Moreover, a demo cloud storage federation service implementation is presented.

Rene Ivan Heinsen, Cindy Pamela Lopez, Tri D. T. Nguyen, Eui-Nam Huh

Internet of Things


A Study on the IoT Framework Design for Ginseng Cultivation

The Republic of Korea’s ginsengs are a high-priced special produce cultivated since the Koryo Dynasty (AD 918–1392) in the Middle Ages. Their efficacy has been studied for a long time and published in both domestic and foreign papers of internal medicines. Several Korean pharmaceutical companies are producing the immune enhancers with them and some of them are waiting for the FDA’s approval while conducting clinical trials, during which their excellent efficacy has been proven. Having the cultivation period of 3 to 6 years, ginseng farmers can draw a high income if they keep an adequate growing condition for these expensive produce favored by many Koreans and foreigners. Thus, by grafting the IoT technology onto the ginseng growing conditions, the farmers will be able to increase their outputs and incomes, as well as increasing the competitiveness of the Korean ginseng. Such a method can also contribute to the reduction of labor force which is one of the serious problems in the agricultural sector where the population is continuously declining. While this study focuses on the designing of an IoT framework considering the characteristics in ginseng cultivation conditions, the results can be standardized and used for the other special produce that require a long-term cultivation period.

Kyung-Gyun Lim, Chang-Geun Kim

An IPS Evaluation Framework for Measuring the Effectiveness and Efficiency of Indoor Positioning Solutions

The indoor positioning system (IPS) has been attracting great attention from researchers, thanks to the rapid adoption of smartphone technologies. Although there are many IPS proposed in the past decade that claimed to have good performance, all of them use their own method to evaluate and compare the accuracy of the proposed solution. During the evaluation phase, the method of gathering ground truth data (original position) is often not well described. As such, it is very difficult for other researchers to reproduce the work and improve on the existing methods. In this paper, we proposed a simple to implement framework to facilitate the process of evaluating IPS accuracy. Under this framework, the IPS position coordinates and ground truth are sent to the server using REST protocol when the phone reads an event triggered from tags scan placed on a fix position. We evaluated an existing well-known IPS technique, the Pedestrian Dead Reckoning (PDR) technique using our IPS evaluation framework. From our experiments, we showed that in addition to measuring the accuracy of IPS, the proposed solution can also measure the IPS accuracy deviation over time. Instead of relying on precision and recall, the framework also includes visualization tool for researchers to observe the overall accuracy of an IPS.

Jacqueline Lee Fang Ang, Wai Kong Lee, Boon Yaik Ooi, Thomas Wei Min Ooi

An IoT-Based Virtual Addressing Framework for Intelligent Delivery Logistics

The Internet of Things (IoT) has been one of the influential paradigms in the development of logistics transport functions. The introduction of IoT in logistics has impacted application areas such as capacity sensing, planning, route optimization, and energy management. However, most works presented so far assume the existence of physical addresses for all applications. This paper, as a result, deals with the logistics delivery inefficiency represented by the lack of physical addresses that is common developing countries. We adopt an IoT approach to propose a virtual addressing framework for tracking, monitoring, and managing package deliveries efficiently. The framework consists of a node network that provides address information virtually to enable better deliveries.

Omar Hiari, Dhiah el Diehn I. Abou-Tair, Ismail Abushaikha

Context-Aware Security Using Internet of Things Devices

Current trends aim to extend software applications with context-awareness. Nowadays, there are already various approaches enabling security based on context, unfortunately there have limitations. However, the challenging topic is how to obtain as much context information about user as possible. Current progress in Internet of Things domain could be leveraged to obtain more context data. We propose a method to formalize context based on Internet of Things devices and use it for application context-aware security. Our approach is based on composition of a tree topology correlating to the user’s devices for recurring situations. Based on changes in the tree we determine unusual behavior, trigger events or invoke specific actions.

Michal Trnka, Martin Tomasek, Tomas Cerny

An Energy-Efficient Transmission Framework for IoT Monitoring Systems in Precision Agriculture

Internet of Thing (IoT) technology has enabled efficient crop monitoring to support decision making in precision agriculture. The monitoring system collects environmental data in fields. A major challenge in the monitoring system is limited energy power of IoT sensor nodes. Consequently, we propose an energy-efficient transmission framework for IoT sensors in the monitoring system. Our proposed framework allows the sensor nodes adaptively collecting the data upon the environmental change. Furthermore, we propose an energy-efficient transmission algorithm for the proposed framework. The objective is to minimize the energy power at the sensor nodes while guaranteeing the transmission rate. A data-driven algorithm based on a greedy method is used to solve the problem with low complexity. We compare the performance of our algorithm with two traditional transmission protocols, called SPIN and ESPIN, through an experiment. From the results, our algorithm can provide better energy efficiency about 81.53% than SPIN and 36.84% than ESPIN.

Peerapak Lerdsuwan, Phond Phunchongharn

Piezoelectric Voltage Monitoring System Using Smartphone

This paper proposed to develop the voltage monitoring for piezoelectric system. The piezoelectric wireless monitoring system will enable voltage monitoring by utilizing a smartphone, piezoelectric sensor and Bluetooth to a device that installed with designated application. The Bluetooth system is the method used to connect the piezoelectric sensor and the smartphone. Thus, this research is aimed to monitor the voltage produced by the piezoelectric system wirelessly. The produced data can be monitored in real time as well as being extracted in excel data format for recording purpose. In the previous research, the piezoelectric were embedded in army boots for energy scavenging purpose to charge hand phone. Monitoring the voltage output utilizing multimeter not feasible at all, hence this research solves the challenges of monitoring the piezoelectric voltage output.

Nazatul Shiema Moh Nazar, Suresh Thanakodi, Azizi Miskon, Siti Nooraya Mohd Tawil, Muhammad Syafiq Najmi Mazlan

A System for Classroom Environment Monitoring Using the Internet of Things and Cloud Computing

A classroom environment monitoring system was developed as a demonstration to Computer Science and Information Technology undergraduate students to enhance their learning experience. Monitoring and controlling the classroom environment, including the lighting and temperature levels in real-time was the primary functionality of the system. Using data on the optimal light and temperature setting, the demonstration system was able to monitor and assess the environment to ensure the comfort of the students. The system demonstrated to the students the concepts and practices of the Internet of Things (IoT) and cloud computing can be beneficially applied and to provide services in specific application areas, this time in education, with simple system design and implementation. While such an application is not new in concept or implementation, the important features of similar systems discussed in previous systems related to the classroom environment monitoring were identified and analysed, and the best and most important features incorporated in our system, together with our own ideas, to provide the students with a significant learning experience based on a real application, which we implemented and presented as a prototype. The attributes of our system are discussed, and the success in providing a good learning experience for the students are discussed. We suggest that argue that more research is needed on this topic, and encourage other researchers to participate in the topic.

Wuttipong Runathong, Winai Wongthai, Sutthiwat Panithansuwan

4th Convergence of Healthcare and Information Technology


Research on Design of End Site Architecture to Connect LHCONE in KREONET

As the large hadron collider (LHC) community has requested a high-performance network for the transmission of massive physics data, the large hadron collider optical private network (LHCOPN) and the large hadron collider open network environment (LHCONE) have provided a support internationally. For the LHC research groups in the Republic of Korea as well, the connection with LHCOPN and LHCONE has been necessary. Therefore, this study attempted to briefly review the LHCONE linked to the backbone of the Korea Research Environment Open NETwork (KREONET) and propose basic site architecture to accept the LHC community.

Chanjin Park, Wonhyuk Lee, Kuinam J. Kim, Hyuncheol Kim

A Study of Children Play Educational Environment Based on u-Healthcare System

The objective of this study is to discuss the application of u-Healthcare System to play educational environments and its effects. It is expected that this application will contribute to addressing various problems among Korean children such as negative habitual behaviors, pressures in the education system, etc. In addition, positive effects are expected in terms of the changing meaning of wellness, educational aspects, and psychological aspects of leisure play for children. To this end, IT-based data collection and analysis was conducted on changes in behaviors and emotions among children during their physical play activities: Specifically, the brainwave bio information collecting technology and physical activity information collecting technology are utilized so that teachers can monitor them easily. It is expected that this method will contribute to the establishment of a new child play environment as well as physical, mental, and social health of children.

Minkyu Kim, Soojung Park, Byungkwon Park

Virtual Resources Allocation Scheme in ICT Converged Networks

NFV enhancing the infrastructure agility, thus network operators and service providers are able to program their own network functions (e.g., gateways, routers, load balancers) on vendor-independent hardware substrate. One of the main challenges for the deployment of NFV is the efficient resource (e.g. virtual network function (VNF)) allocation of demanded network services in NFV-based network infrastructures. However, the effective mapping and scheduling of VNFs are essential to successfully provide NFV services. In this paper, we proposed revised online (dynamic) virtual network function allocation scheme to cope with successive network service (NS) requests. Unlike previous research on resource allocation, we assumed that each virtual node processes one or more functions at a time using multiprocessing technologies as in the real environment.

Hyuncheol Kim

Enhanced Metadata Creation and Utilization for Personalized IPTV Service

Metadata is the clue to connecting videos and individual users. For a successful personalization, collecting more detailed and concrete metadata is important. This paper proposes a method to create and utilize metadata more precisely as a result of research on how to do the personalization better. For that, we propose a way to consume and utilizing a video in a series of segmented images so that can get the user’s taste on specific sections or points of the video. Proposed method is implemented on the web site and the effectiveness of proposed method is revealed by comparing the site stay time and number of video usage per session between new visitors and returning visitors.

Hyojin Park, Kireem Han, Jinhong Yang, Jun Kyun Choi

A Study of Teaching Plan for the Physical Activity Using ICT

Possibility of using ICT to the education of physical activities is becoming a reality due to the increased interest in the field of physical activities that applied technologies such as motion recognition or virtual reality. This study sought to present the possibility of using ICT and education model for the education on the physical activities. Education of physical activities faces a number of limitations. In particular, share of the time and space limitations is high. Virtual reality can be cited as the ICT technology that can complement these limitations. Sports virtual reality system that enables sports experience service with high sense of immersion since sports and fun elements get mixed together is likely to be used for the education of physical activities since it is possible to complement the fun element while complementing the time and space, and environment limitations. When physical activity task is delivered, the following process is performed in order; searching for information via web or VOD, setting up the strategy for learning sports techniques, executing virtual reality simulation and evaluating the accuracy level of motions, carrying out physical activities by using related virtual reality sports program, feedback. The teaching strategy by applying virtual reality technology will be effective for learning exercise function.

Seung Ae Kang

Design and Implementation of Headend Servers for Downloadable CAS

This paper presents the design and implementation of headend servers for a downloadable conditional access system (DCAS) that can securely transmit CA code via a broadband channel. To design DCAS headend server, we define core functions to be performed in the headend and categorize them into four sections such as authentication, provisioning, personalization and key management. In order to verify the stability and effectiveness of the implemented headend servers, we construct a testbed using them and a legacy cable headend system in a laboratory. The experimental results show that the DCAS headend servers are well designed.

Soonchoul Kim, Hyuncheol Kim, Jinwook Chung

A Method of Modeling of Basic Big Data Analysis for Korean Medical Tourism: A Machine Learning Approach Using Apriori Algorithm

The Republic of Korea (ROK) has emerged as a country of superior medical tourism in the last decade among the people of China, Japan, Southeast Asia, Russia and the Middle East for the plastic surgery or others requiring precision skills. Although the ROK’s medical tourism industry grew quantitatively in its revenue and the number of visitors, the report from the 2015 World Economic Forum concerning the competitiveness of ROK’s tourism including the medical tourism showed that its rank had dropped to 29th position, a drop of 4 places from 25th in 2013. Thus, it is about time to improve the situation by investigating the actual conditions of tours taken by the foreign tourists to establish new strategy, which is the main contribution of this research. As a research method, a big data analysis has been performed on the basis of machine learning and using R-studio. During the analysis process, there were some relevant regularities which were difficult to be found in the big data and based on these findings, we have attempted to find the solutions for the bad images that foreign visitors had shared in common. The result of the big data analysis showed that the their purpose of visit was different from each other depending on the age groups and the details of their experience of inconvenience varied as well.

Jun-Ho Huh, Han-Byul Kim, Jinmo Kim

The Study of Application Development on Elderly Customized Exercise for Active Aging

The purpose of this study is to examine the current status and problems pertaining to the applications on the Korean elderly’s exercise in the Korean android market using smart phone, for the development of the exercise program application customized for the elderly and to provide services. Moreover, improvement measures are analyzed to provide the base data to provide resourceful information to the elderly, leaders, trainees interested in the elderly and institutions and to develop customized elderly exercise application for the Active Aging. When the elderly exercise applications in Korea were examined, there is only one exercise program with standardized contents. Only the program called the “Health Ewha” present convergence of food, nursing and sports, but this application cannot be searched easily with keyword. Thus, this study planned customized elderly exercise for Active Aging, and this is the base data for developing application that can input information, measuring current state (exercise strength level setting, physical strength via heart rate measurement), and customized exercise program (cardio, muscular strength, flexibility, equilibrium, and coordination exercise for healthy elderly and exercise by disease).

YoungHee Cho, SeungAe Kang, SooHyun Kim, SunYoung Kang

Improving Jaccard Index for Measuring Similarity in Collaborative Filtering

In collaborative filtering-based recommender systems, items are recommended by consulting ratings of similar users. However, if the number of ratings to compute similarity is not sufficient, the system may produce unreliable recommendations. Since this data sparsity problem is critical in collaborative filtering, many researchers have made efforts to develop new similarity metrics taking care of this problem. Jaccard index has also been a useful tool when combined with existing similarity measures to handle data sparsity problem. This paper proposes a novel improvement of Jaccard index that reflects the frequency of ratings assigned by users as well as the number of items co-rated by users. Performance of the proposed index is evaluated through extensive experiments to find that the proposed significantly outperforms Jaccard index especially in a dense dataset and that its combination with a previous similarity measure is superior to existing measures in terms of both prediction and recommendation qualities.

Soojung Lee

Temperature Recorder System

A temperature recorder system is based on the changes of the patients’ temperature over a fixed time that uses the advantages of a smartphone. This paper proposes a wirelessly controlled system to achieve reliability and mobility of the user. The wireless system was achieved by utilizing a smartphone, PIC Controller and Bluetooth to a device that’s been installed with the temperature sensors. This system can be used for medical purpose to monitor and record 24/7 of the patient’s temperature consistently which can systematically save manpower, time and lives.

Suresh Thanakodi, Nazatul Shiema Moh Nazar, Azizi Miskon, Ahmad Mujahid Ahmad Zaidi, Muhammad Syafiq Najmi Mazlan

7th International Workshop on ICT Convergence


The Emergence of ICTs for Knowledge Sharing Based on Research in Indonesia

This paper presents organizations in applying ICTs (Information, Communication, and Technologies) contribution for supporting knowledge activities, in order to gain organizational competitiveness. Through ICT, knowledge workers in different fields are empowered to contribute and share their knowledge effectively and efficiently. In Knowledge Sharing (KS), organization must focus on results of research in the development of Knowledge Management System features, adoption, and use of ICTs itself. Creating a knowledge repository and providing best practices via ICTs tools enable the starting of knowledge sharing application. The study found that the features to support mechanism, content, and process of KS are mostly applied based on identification of knowledge from structural and functional areas. Moreover, it needs to share in perspective as well as an important asset that must be managed efficiently for organizational success.

Siti Rohajawati, Boy Iskandar Pasaribu, Gun Gun Gumilar, Hilda Rizanti Putri

Quality of Transformation of Knowledge as Part of Knowledge Management System

(Research in Private University in Jakarta)

The main activity in education is the transfer of knowledge from educators with learners and among learners themselves. The knowledge can be in the form of explicit or implicit. On the other hand, the implementation of Knowledge Management conducted in almost all business and social activities, including in the field of education. This study aimed to get an idea of the condition of the implementation of the transformation of knowledge and develop knowledge management model of private university in Jakarta. Data were analyzed using descriptive tool “Radar”.

Dyah Budiastuti, Harjanto Prabowo


Weitere Informationen