Skip to main content
main-content

Über dieses Buch

The three-volume set LNAI 7196, LNAI 7197 and LNAI 7198 constitutes the refereed proceedings of the 4th Asian Conference on Intelligent Information and Database Systems, ACIIDS 2012, held in Kaohsiung, Taiwan in March 2012.

The 161 revised papers presented were carefully reviewed and selected from more than 472 submissions. The papers included cover the following topics: intelligent database systems, data warehouses and data mining, natural language processing and computational linguistics, semantic Web, social networks and recommendation systems, collaborative systems and applications, e-bussiness and e-commerce systems, e-learning systems, information modeling and requirements engineering, information retrieval systems, intelligent agents and multi-agent systems, intelligent information systems, intelligent internet systems, intelligent optimization techniques, object-relational DBMS, ontologies and knowledge sharing, semi-structured and XML database systems, unified modeling language and unified processes, Web services and semantic Web, computer networks and communication systems.

Inhaltsverzeichnis

Frontmatter

Ubiquitous Decision Support with Bayesian Network and Computational Creativity

The Impact of Human Brand Image Appeal on Visual Attention and Purchase Intentions at an E-commerce Website

The purpose of this study was to examine how human brand image appeal affects visual attention using eye-tracker, a visual attention measuring apparatus, at an e-commerce website. Additionally, we examined the effect of human brand image appeal on purchase intention using a questionnaire method. We conducted an eye-tracker experiment, collected survey data, and conducted interviews with each participant using laptop and perfume products. After collecting 108 valid data, the human brand images were divided into three groups: high human brand image appeal group, low human brand image appeal group, and no human brand group. We applied MANOVA and t-tests to analyze the data. The results showed that the level of human brand image appeal has a significant influence on a consumer’s visual attention and purchase intention towards a product. Both visual attention (human brand and product AOI) and purchase intention are highest for the high image appeal group.

Young Wook Seo, Seong Wook Chae, Kun Chang Lee

Exploring Human Brands in Online Shopping: An Eye-Tracking Approach

Trust plays a critical role in facilitating transactions in the online shopping environment. Accordingly, various methods have been considered to enhance customer trust. Human branding has received increased attention and played a vital role in business in recent years because it has great impacts on our daily life and consumption. The purpose of this paper is to investigate the effect of applying human brands in an online shopping environment with an emphasis on product type and human brand attachment. The study combines the eye-tracking technique with a self-reported questionnaire to gain a deeper understanding of the effect of human branding in the online shopping process. The results showed that both the product type and level of human brand attachment have significant influences on a customer’s visual attention as well as perceived trust towards the product.

Seong Wook Chae, Young Wook Seo, Kun Chang Lee

Task Performance under Stressed and Non-stressed Conditions: Emphasis on Physiological Approaches

By using a physiological approach, we examined performance in the Minesweeper

R

game. In this experiment, we measured subjects’ Galvanic Skin Response (GSR) and electrocardiogram (ECG) during game play. We divided subjects into two groups, one of which was exposed to two types of manipulated stress. Additionally, a questionnaire was given to the subjects in order to measure perceived stress. We investigated how much stress each group endured by measuring physiological data and by administering the perceived stress scale (PSS). The results showed that there was no difference for multi-relational performance between the control group and the experimental group. For future studies of multi-relational performance under stress, we suggest that researchers should consider other factors that might influence stress and multi-relational performance.

Nam Yong Jo, Kun Chang Lee, Dae Sung Lee

Characteristics of Decision-Making for Different Levels of Product Involvement Depending on the Degree of Trust Transfer: A Comparison of Cognitive Decision-Making Criteria and Physiological Responses

This research verified the match rate between cognitive decision-making criteria and the physiological reaction on a website using Eye-Tracker, which measures a user’s visual attention. Specifically, we explored the match rate between cognitive decision-making and the physiological reaction depending on the degree of product involvement and the degree of trust transfer through an experiment and survey. The verification results show that, for the involvement of products (high/low involvement), the match rate between the fixation length and the cognitive criteria used in decision-making for the high involvement product was higher than that with the low involvement product, and the difference in the match rate was statistically significant. However, in the aspect of trust transfer, the difference in the match rate between the high and low trust transfer groups was not statistically significant.

Min Hee Hahn, Do Young Choi, Kun Chang Lee

A Comparison of Buying Decision Patterns by Product Involvement: An Eye-Tracking Approach

This research investigated whether buying the decision process differs by the level of product involvement. We analyzed visual attention based on the eye-tracking technique to explore the cognitive characteristics of buying decisions. More specifically, we observed visual attention of involvement by conducting experiments in a website environment. Through eye-tracking experiments, we applied physiological data in order to test our research hypotheses regarding the buying decision process and product involvement, measuring fixation length as visual attention. The results of the eye-tracking experiment showed that the decision process for high involvement products is more complicated than that for low involvement products.

Do Young Choi, Min Hee Hahn, Kun Chang Lee

The Influence of Team-Member Exchange on Self-reported Creativity in the Korean Information and Communication Technology (ICT) Industry

There have been some studies on the relationship between social exchange relationships and creativity in organizations, but researchers have little explored the effect of TMX (team-member exchange) and coworker behaviors on creativity. In this respect, we introduced into our research model TMX and coworker behaviors as social or contextual factors which might influence individual creativity within Korean ICT companies. Although CHS (Coworker helping and support) does not have a sufficient mediating effect on individual creativity, that factor is positively related to Individual creativity. On the other hand, FC (Feedback from Coworkers) does not influence individual creativity at all. However, we found that TMX directly and strongly influences individual creativity. Therefore, organizations should encourage employees to build a high level of social exchange relationships with coworkers.

Dae Sung Lee, Kun Chang Lee, Nam Yong Jo

Computational Intelligence

Semi-parametric Smoothing Regression Model Based on GA for Financial Time Series Forecasting

In this study, a novel Neural Network (NN) ensemble model using Projection Pursuit Regression (PPR) and Least Squares Support Vector Regression (LS–SVR) is developed for financial forecasting. In the process of ensemble modeling, the first stage some important economic factors are selected by the PPR technology as input feature for NN. In the second stage, the initial data set is divided into different training sets by used Bagging and Boosting technology. In the third stage, these training sets are input to the different individual NN models, and then various single NN predictors are produced based on diversity principle. In the fourth stage, the Partial Least Square (PLS) technology is used to choosing the appropriate number of neural network ensemble members. In the final stage, LS–SVR is used for ensemble of the NN to prediction purpose. For testing purposes, this study compare the new ensemble model’s performance with some existing neural network ensemble approaches in terms of the Shanghai Stock Exchange index. Experimental results reveal that the predictions using the proposed approach are consistently better than those obtained using the other methods presented in this study in terms of the same measurements.

Lingzhi Wang

Classification of Respiratory Abnormalities Using Adaptive Neuro Fuzzy Inference System

Spirometric evaluation of pulmonary function plays a critical role in the diagnosis, differentiation and management of respiratory disorders. In spirometry, there is a requirement that a large database is to be analyzed by the physician for effective investigation. Hence, there is a need for automated evaluation of spirometric parameters to diagnose respiratory abnormalities in order to ease the work of the physician. In this work, a neuro fuzzy based Adaptive Neuro Fuzzy Inference System (ANFIS), Multiple ANFIS and Complex valued ANFIS models are employed in classifying the spirometric data. Four different membership functions which include triangular, trapezoidal, Gaussian and Gbell are employed in these classification models. Results show that all the models are capable of classifying respiratory abnormalities. Also, it is observed that CANFIS model with Gaussian membership function performs better than other models and achieved higher accuracy. This study seems to be clinically relevant as this could be useful for mass screening of respiratory diseases.

Mythili Asaithambi, Sujatha C. Manoharan, Srinivasan Subramanian

An Ant Colony Optimization and Bayesian Network Structure Application for the Asymmetric Traveling Salesman Problem

The asymmetric traveling salesman problem (ATSP) is an NP-hard problem. The Bayesian network structure which describes conditional independence among subsets of variables is useful in reasoning uncertainty. The ATSP is formed as the Bayesian network structure and solved by the ant colony optimization (ACO) in this study. The proposed algorithm is tested in different sample size. The exam case is finding customer preference’s city sequence. Results show the proposed algorithm has a higher joint probability than random selected case. More applications such as the sequential decision, the variable ordering or the route planning can also implement.

Nai-Hua Chen

Expert Pruning Based on Genetic Algorithm in Regression Problems

Committee machines are a set of experts that their outputs are combined to improve the performance of the whole system which tend to grow into unnecessarily large size in most of the time. This can lead to extra memory usage, computational costs, and occasional decreases in effectiveness. Expert pruning is an intermediate technique to search for a good subset of all members before combining them. In this paper we studied an expert pruning method based on genetic algorithm to prune regression members. The proposed algorithm searches to find a best subset of experts by creating a logical weight for each member and chooses which member that the related weight is equal to one. The final weights for selected experts are calculated by genetic algorithm method. The results showed that MSE and R-square for the pruned CM are 0.148 and 0.9032 respectively that are reasonable rather than all experts separately.

S. A. Jafari, S. Mashohor, Abd. R. Ramli, M. Hamiruce Marhaban

A Hybrid CS/PSO Algorithm for Global Optimization

This paper presents the hybrid approach of two nature inspired metaheuristic algorithms; Cuckoo Search (CS) and Particle Swarm Optimization (PSO) for solving optimization problems. Cuckoo birds lay their own eggs to other host birds. If the host birds discover the alien birds, they will leave the nest or throw the egg away. Cuckoo birds migrate to the environments that reduce the chance of their eggs to be discovered by the host birds. In standard CS, cuckoo birds experience new places by the Lévy Flight. In the proposed hybrid algorithm, cuckoo birds are aware of each other positions and make use of swarm intelligence in PSO in order to reach to better solutions. Experimental results are examined with some standard benchmark functions and the results show a promising performance of this algorithm.

Amirhossein Ghodrati, Shahriar Lotfi

A Hybrid ICA/PSO Algorithm by Adding Independent Countries for Large Scale Global Optimization

This paper presents the hybrid approach of Imperialist Competitive Algorithm (ICA) and Particle Swarm Optimization (PSO) for global optimization. In standard ICA, there are only two types of countries: imperialists and colonies. In the proposed hybrid algorithm (ICA/PSO) we added another type of country, ‘

Independent’

. Independent countries do not fall into the category of empires, and are anti-imperialism. In addition, they are united and their shared goal is to get stronger in order to rescue colonies and help them join independent countries. These independent countries are aware of each other positions and make use of swarm intelligence in PSO for their own progress. Experimental results are examined with benchmark functions provided by CEC2010 Special Session on Large Scale Global Optimization (LSGO) and the results are compared with some previous LSGO algorithms, standard PSO and standard ICA.

Amirhossein Ghodrati, Mohammad V. Malakooti, Mansooreh Soleimani

The Modified Differential Evolution Algorithm (MDEA)

Differential evolution (DE) is arguably one of the most powerful stochastic real-parameter optimization algorithms. DE has drawn the attention of many researchers resulting in a lot of variants of the classical algorithm with improved performance. This paper presents a new modified differential evolution algorithm for minimizing continuous space. New differential evolution operators for realizing the approach are described, and its performance is compared with several variants of differential evolution algorithms. The proposed algorithm is basedon the idea of performing biased initial population. By means of an extensive testbed it is demonstrated that the new method converges faster and with more certainty than many other acclaimed differential evolution algorithms. The results indicate that the proposed algorithm is able to arrive at high quality solutions in a relatively short time limit: for the largest publicly known problem instance, a new best solution could be found.

Fatemeh Ramezani, Shahriar Lotfi

Quad Countries Algorithm (QCA)

This paper introduces an improved evolutionary algorithm based onthe

Imperialist Competitive Algorithm

(ICA), called

Quad Countries Algorithm

(QCA). The Imperialist Competitive Algorithm is inspired by socio-political process of imperialistic competition in the real world and has shown its reliable performance in optimization problems. In the ICA, the countries are classified into two groups: Imperialists and Colonies. However, in the QCA, two other kinds of countries including Independent and Seeking Independence are added to the countries collection. In the ICA also the Imperialists’ positions are fixed, while in the QCA Imperialists may move. The proposed algorithm was tested by well-known benchmarks, and the compared results of the QCA with results of ICA, GA [12], PSO [12], PS-EA [12] and ABC [11] show that the QCA has better performance than all mentioned algorithms. Among them, the QCA, ABC and PSO have better performance respectively in 50%, 41.66% and 8.33% of all cases.

M. A. Soltani-Sarvestani, Shahriar Lotfi, Fatemeh Ramezani

Human Computer Interaction

An Aspectual Feature Module Based Adaptive Design Pattern for Autonomic Computing Systems

Adaptability in software is the main fascinating concern for which today’s software architects are really interested in providing the autonomic computing. Different programming paradigms have been introduced for enhancing the dynamic behavior of the programs. Few among them are the Aspect oriented programming (AOP) and Feature oriented programming (FOP) with both of them having the ability to modularize the crosscutting concerns, where the former is dependent on aspects, advice and lateral one on the collaboration design and refinements. In this paper we will propose a design pattern for Autonomic Computing System which is designed with Aspect-oriented design patterns we’ll also study about the amalgamation of the Feature-oriented and Aspect-oriented software development methodology and its usage in developing a self-reconfigurable adaptive system. In this paper we used the design patterns which will satisfy the properties of an autonomic system: For monitoring we used the Observer design pattern, Decision making we used Adaptation Detector design pattern, and for Reconfiguration we used Feature-oriented Aspect insertion using participant pattern. The main objective of the system is to provide self-reconfiguring behavior at run-time by inserting into the current existing code with an aspectual feature module code without interrupting the user and to provide transparency while accessing the system. The pattern is described using a java-like notation for the classes and interfaces. A simple UML class and Sequence diagrams are depicted.

Vishnuvardhan Mannava, T. Ramesh

Malay Anaphor and Antecedent Candidate Identification: A Proposed Solution

This paper discusses on Malay language anaphor and antecedent candidate determination using the knowledge-poor techniques. The process to determine the candidate for anaphor and antecedent is important because the usage of pronouns in a text is not always considered as an anaphor. Sometimes pronoun referred to something outside the context or does not refer to any situation in the text. Such a situation is also exhibited in the use of pronouns in Malay language. Therefore, certain rules must be issued to identify the antecedent and anaphor candidate. Pronoun usage in Malay language does indicate the gender of the person, but to distinguish the status of the person such as imperial family, honorable people and common people. Thus, generic rules that have been used by other languages cannot simply be adapted for Malay language. The proposed solution concerns with the distance of each candidate and location of the Subject-Verb-Object (SVO) used to determine the anaphor candidate. As such, syntactic information, semantic information and distance of anaphor-antecedent are seen important to determine the antecedent candidate.

Noorhuzaimi Karimah Mohd Noor, Shahrul Azman Noah, Mohd Juzaiddin Ab Aziz, Mohd Pouzi Hamzah

Ranking Semantic Associations between Two Entities – Extended Model

Semantic association is a set of relationships between two entities in knowledge base represented as graph paths consisting of a sequence of links. The number of relationships between entities in a knowledge base might be much greater than the number of entities. So, ranking the relationship paths is required to find the relevant relationships with respect to the user’s domain of interest. In some situations, user may expect the semantic relationships with respect to specific domain closer to any one of these entities. Consider the example for finding the semantic association between the person X and person Y. If the user has already known something about the person X such as person X may be associated with financial activities or scientific research etc., then the user wants to focus on finding and ranking the relationship between two persons in which the users’ context is closer to person X. In many of the existing systems, there is no consideration given into context closeness during ranking process. In this paper, we present an approach which allows the extraction of semantic associations between two entities depending on the choice of the user in which the context is closer to left or right entity. The average correlation coefficient between proposed ranking and human ranking is 0.70. We compare the results of our proposed method with other existing methods. It explains that the proposed ranking is highly correlated with human ranking. According to our experiments, the proposed system provides the highest precision rate in ranking the semantic association paths.

V. Viswanathan, Ilango Krishnamurthi

The Quantum of Language: A Metaphorical View of Mind Dimension

In this article, we are focusing on metaphor of mental states examining hidden dimension of the human mind and its interaction with a world. Our natural language research methodology were included constructing a database of metaphorical stimuli, randomly presenting these to participants, and tabulating FAE responses both by participant and by the stimulus, analyzed by frequency of semantic type. The project aimed to produce a new model of knowledge representation. Acquired data suggest that mind’s metaphoric self-reflection semantics closely correlate with entangled quantum particles and light binding phenomena. Created semantic network gave us a unique opportunity to visualize the probabilistic picture of mind itself within an interdisciplinary approach of cognitive and computational networking studies.

Svetlana Machova, Jana Kleckova

An Experimental Study to Explore Usability Problems of Interactive Voice Response Systems

While interactive voice response (IVR) systems employing touch tone interface (TTI) are popularly used these days, they are generally known for their inconvenience. This is not only because of the characteristics that TTI inherently has, but also because of lack of understanding of IVR system users. This study is aimed at contributing to capture an understanding of the users, which eventually leads to better system design. In particular, we have developed an IVR system simulator to enable efficient, flexible, and rich usability tests for IVR systems. This paper presents an experimental study on usability of IVR systems utilizing the simulator. In the experiment, 41 subjects performed three different tasks concerning phone charges using the simulator to identify various usability problems. The analytic results are hopefully a basis for user-centered IVR systems design.

Hee-Cheol Kim

Using Eyetracking in a Mobile Applications Usability Testing

In this paper we present general problems of a mobile application usability testing by means of eyetracking. The motivation for considering this problem is the fact that eyetracking is still one of the most advanced usability testing tool. We achieved that by performing two eyetracking tests with the participation of users. We tested mobile application on smartphone and PC emulator, to find out which method gives the most valuable results. Both tests showed that eyetracking testing of mobile applications gives valuable results but to make it really efficient professional equipment designed for mobile eyetracking is required.

Piotr Chynał, Jerzy M. Szymański, Janusz Sobecki

An Approach for Improving Thai Text Entry on Touch Screen Mobile Devices Based on Bivariate Normal Distribution and Probabilistic Language Model

This paper presents an approach to improve the correctness for Thai text inputting via virtual keyboard on touch screen mobile phones. The proposed approach is to generate candidate character based on statistical model from bivariate analysis of pre-collected coordinate data and apply the character trigram model to each candidate character sequence. From user’s touch positions, a set of candidate characters with high position-based probability is generated. Then, the character trigram model is applied to each generated candidate characters sequence. For each character sequence, a probability is computed from the weighted combination of position-based and character trigram models. In the end, the character sequence with the highest probability is selected to be the most appropriate sequence. Experiments were conducted to compare the typing accuracy between an ordinary Thai virtual keyboard and our proposed algorithm using the same Thai keyboard layout. Results demonstrate that the proposed algorithm provides the improvement in the text entry accuracy in both character levels and word levels.

Thitiya Phanchaipetch, Cholwich Nattee

An Iterative Stemmer for Tamil Language

Stemming algorithm is a procedure that attempts to map all the derived forms of a word to a single root, the stem. It is widely used in various applications with the main motive of enhancing the recall factor. Apart from English, researches on developing stemmers for both the native and the regional languages are also being carried out. In this paper, we present a stemmer for Tamil, a Dravidian language. Our stemmer effectiveness is 84.32%.

Vivek Anandan Ramachandran, Ilango Krishnamurthi

Innovation in Cloud Computing Technology and Application

Implementation of Indoor Positioning Using Signal Strength from Infrastructures

Real time location system is not a brand new technology. The most typical approach is using global position system (GPS). However, GPS can only be used outdoors. It is unable to work completely indoors or in an environment with obstacles. Therefore, the development related to indoor position technology is quite important. In the system developed in this study, it makes use of Received Signal Strength Index value of low-power active RFID (Radio Frequency Identification) for movement detection. Besides, it adopts ZigBee wireless transmission technology as reference nodes for positioning detection. Information gathered by reference points is delivered to the server through the Internet. All positioning information is computed by the server. Positioning algorithm uses the average values of signals in its operation. The advantage is to compare many average values with the closing nodes in order to locate the closest position node for the mobile device and reduce the multi-path interference which is caused by other environmental factors. Positioning results can be accessed through the networked computer or mobile device with WiFi functionality. The experimental results are more stable than other positioning algorithms, and the installation of the system is more convenient.

Yuh-Chung Lin, Chin-Shiuh Shieh, Kun-Mu Tu, Jeng-Shyang Pan

Dual Migration for Improved Efficiency in Cloud Service

Wireless technologies enable users to retain their Internet access at anywhere and at anytime, without the tangling of wired cables. Users might want to keep enjoying their favor services when they are moving. However, the user mobility would causes longer and longer path to the serving server so that the QoS cannot be guaranteed. In order to maintain better QoS as a user moves, we proposed a novel and efficient cloud service architecture, named dual migration. The dual migration architecture keeps monitor the location of a user and migrates the contents what the user might need onto the closest server for the current location of the user. Therefore, the hop count of the path between a user and the corresponding server is short.

Wei Kuang Lai, Kai-Ting Yang, Yuh-Chung Lin, Chin-Shiuh Shieh

Integrating Bibliographical Data of Computer Science Publications from Online Digital Libraries

In this paper we proposed and developed a system to integrate the bibliographical data of publications in the computer science domain from various online sources into a unified database based on the focused crawling approach. In order to build this system, there are two phases to carry on. The first phase deals with importing bibliographic data from DBLP (Digital Bibliography and Library Project) into our database. The second phase the system will automatically crawl new publications from online digital libraries such as Microsoft Academic Search, ACM, IEEEXplore, CiteSeer and extract bibliographical information (one kind of publication metadata) to update, enrich the existing database, which have been built at the first phase. This system serves effectively in services relating to academic activities such as searching literatures, ranking publications, ranking experts, ranking conferences or journals, reviewing articles, identifying the research trends, mining the linking of articles, stating of the art for a specified research domain, and other related works base on these bibliographical data.

Tin Huynh, Hiep Luong, Kiem Hoang

Rural Residents’ Perceptions and Needs of Telecare in Taiwan

The purpose of this study was to explore rural residents’ perceptions and needs of a telecare system after they have used it. The samples were collected using structured questionnaires with face to face interviews between July 1 and September 30, 2009. Results from this exploratory study show that most elderly people have never heard or touched telecare systems before the study was conducted. However, the general perceptions of such systems include improvement of interacting with medical staffs, safety protection, convenient care, and one needed item of services in daily life. Especially, the mostly risk perception is privacy risk, that is, data confidentiality and individual privacy. Generally, most elderly residents evaluated their telecare experiences and perceptions as being positive. Besides, most elderly resident were willing to use the telecare system without fees. However, they felt risky about confidentiality and privacy toward this technology. To improve trustworthy perception of this novel technology, telecare providers should implement appropriate safeguards to protect patient health information exchanged in a telecare setting. Also, the physicians/nurses should take the time to communicate with the residents, especially in the form of education, about the benefits of technology. To optimize the effectiveness of this promising technique, more research on the relationship between residents’ (or patients’) perceptions and influences of technology will need to be conducted continually in future.

Bi-Kun Chuang, Chung-Hung Tsai

Renewable Energy and Power Management in Smart Transportation

This paper designs a heuristic-based charging scheduler capable of integrating renewable energy for electric vehicles, aiming at reducing power load induced from the large deployment of electric vehicles. Based on the power consumption profile as well as the preemptive charging task model which includes the time constraint on the completion time, a charging schedule is generated as a

M

×

N

allocation table, where

M

is the number of time slots and

N

is the number of tasks. Basically, it assigns the task operation to those slots having the smallest power load until the last task allocation, further taking different allocation orders according to slack, operation length, and per-slot power demand. Finally, the peaking task of the peaking slot is iteratively picked to supply renewable energy stored in the battery device. The performance measurement result shows that our scheme can reduce the peak load by up to 37.3 % compared with the

Earliest

allocation scheme for the given amount of available renewable energy.

Junghoon Lee, Hye-Jin Kim, Gyung-Leen Park

A Cloud Computing Implementation of XML Indexing Method Using Hadoop

With the increasing of data at an incredible rate, the development of cloud computing technologies is of critical importance to the advances of researches. The Apache Hadoop has become a widely used open source cloud computing framework that provides a distributed file system for large scale data processing. In this paper, we present a cloud computing implementation of an XML indexing method called NCIM (Node Clustering Indexing Method), which was developed by our research team, for indexing and querying a large number of big XML documents using MapReduce. The experimental results show that NCIM is suitable for cloud computing environment. The throughput of 1200 queries per second for huge amount of queries using a 15-node cluster signifies the potential applications of NCIM to the fast query processing of enormous Internet documents.

Wen-Chiao Hsu, I-En Liao, Hsiao-Chen Shih

Constraint-Based Charging Scheduler Design for Electric Vehicles

This paper proposes an efficient charging scheduler for electric vehicles and measures its performance, aiming at reducing peak power consumption while satisfying the diverse constraints specified in each charging request. Upon the arrival of a charging request via the underlying vehicle network, the scheduler builds the feasible schedule based on the activation time, the deadline, and the power load profile of each charging task, which is practically nonpreemptive. During the search space expansion of a backtracking algorithm, each step checks the constraint imposed on peak load, completion time, number of chargers, and precedence relation between tasks to prune unnecessary branches. The performance measurement result obtained from the prototype implementation reveals that the proposed scheme reduces the execution time by 80 %, achieves the peak load reduction by 11 %, and improves the schedulability by 5 %, compared with uncoordinated and list scheduling schemes for the given parameter set.

Hye-Jin Kim, Junghoon Lee, Gyung-Leen Park

Modular Arithmetic and Fast Algorithm Designed for Modern Computer Security Applications

Modular arithmetic plays very crucial role for public key cryptosystems, such as the public key cryptosystem, the key distribution scheme, and the key exchange scheme. Modular exponentiation is a common operation used by several public-key cryptosystems, such as the RSA encryption scheme and the Diffie-Hellman key exchange scheme. In this paper, we have proposed a new method to fast evaluate modular exponentiation, which combines the complement recoding method and canonical recoding technique.

Chia-Long Wu

Innovative Computing Technology

An Efficient Information System Generator

We developed a new customized software tool for automatically generating a complete Java program based on the values or parameters inputted by the user. We call it an efficient Information System Generator or ISG for short. It is efficient in terms of the processor usage and the development time. We illustrate how it can be used by building a system for keeping track of student’s scores that can be used by any faculty member who teaches multiple courses at a university or a college. It can also be used for generating e-commerce web sites.

Ling-Hua Chang, Sanjiv Behl

A Temporal Data Model for Intelligent Synchronized Multimedia Integration

This paper aims to develop a generic temporal data model and to design the relevant mining for multimedia applications. We develop a data model as efficient computation model to unify time-varying events and objects. Several computation algorithms and operation tables which include a set of complete temporal logics are proposed. The combined temporal data model is generalized by composing point and interval algebra with qualitative and quantitative functions. The temporal data model is extended to spatial projection representations. Also we apply the result of computation models to multimedia data for synchronized integration applications. This data model framework can handle semantics of the solutions for knowledge querying and can compose the temporal semantics among multimedia objects over the web.

Anthony Y. Chang

Novel Blind Video Forgery Detection Using Markov Models on Motion Residue

In this paper we present a novel blind video forgery detection method by applying Markov models to motion in videos. Motion is an important aspect of video forgery detection as it effects forgery detection in videos. Most of the current video forgery detection algorithms do not consider motion in their approach. Motion is usually captured from motion vectors and prediction error frame. However capturing motion for I-frame is computationally expensive, so in this paper we extract the motion information by applying collusion on successive frames. First a base frame is obtained by applying collusion on successive frames and the difference between actual and estimate gives information about motion. Then we apply Markov models on this motion residue and apply pattern recognition on this. We used Support Vector Machines (SVMs) in our experiment. We obtained an accuracy of 87% even for reduced feature set.

Kesav Kancherla, Srinivas Mukkamala

Sports Video Classification Using Bag of Words Model

We propose a novel approach classify different sports videos given their groups. First, the SURF descriptors in each key frames are extracted. Then they are used to form the visual word vocabulary (codebook) by using K-Means clustering algorithm. After that, the histogram of these visual words are computed and considered as a feature vector. Finally, we use SVM to train each classifier for each category. The classification result of the video is the production of the scores output from all of the key frames. An extensive experiment is performed on a diverse and challenging dataset of 600 sports video clips downloaded from Youtube with a total of more than 6000 minutes in length for 10 different kinds of sports.

Dinh Duong, Thang Ba Dinh, Tien Dinh, Duc Duong

Self Health Diagnosis System with Korean Traditional Medicine Using Fuzzy ART and Fuzzy Inference Rules

Korean traditional medicine has obtained more attention from the public and IT service industry especially after ’Dong-eui-bo-gam’ was registered to UNESCO Memory of the World. However, there are many obstacles in developing and commercializing an on-line self-diagnosis system by Korean traditional medicine. From the service point of view, since people are accustomed to the westernized style of diagnosis (symptom-disease pair), it is not easy to understand what traditional Korean medicine diagnoses and how one can react. Technically speaking, we need a special symptom-disease database because Korean traditional medicine has been built upon the innate characteristics of Korean people’s body. Thus, in this paper, we propose a self-diagnosis system of Korean traditional medicine based on Korean Standard Causes of Death Disease Classification Index (KCD) and fuzzy ART/inference method. Since this is for self-diagnosis, our system has graphical user-friendly interface that accepts symptoms of user from a certain part of body where the user feels inconvenient. Then, fuzzy ART algorithm and fuzzy inference engine picks up five most probable diseases with their causes and treatments extracted from Korean traditional medicine books. The power of our system comes from a fuzzy inference module combined with fuzzy ART algorithm that helps classifying related disease from database with accuracy. Our system is verified by field experts of Korean traditional medicine in collecting symptom-disease-treatments relationships and performance evaluation of experiment results.

Kwang-Baek Kim, Jin-Whan Kim

Real-Time Remote ECG Signal Monitor and Emergency Warning/Positioning System on Cellular Phone

This paper implements a remote real-time health care system mainly based on electrocardiogram (ECG), body temperature, pulse-based real-time monitoring. A cellular phone with Android O.S. and global positioning system (GPS) is adopted as the platform for this system. The monitor of electrocardiogram (ECG) is performed by a statistical model, Hidden Markov model (HMM), to immediately determine the status of the patient’s body. Besides, an automatic warning and positioning system is designed so that the patients can receive timely rescue. Also, a suggestion, if necessary, for finding the closest hospital will be given by this system. In this system, a device for measuring ECG signal is attached on a patient’s body and remotely transfers the ECG data to cellular phone through Bluetooth device. The ECG data are then transferred to and stored in the server through internet. All the data in the sever for a patient are used to train and update the HMM model in the cellular phone to get a more precise prediction of the patient’s health. Experiments in this paper show that the implemented system works well and is helpful to people’s health care.

Shih-Hao Liou, Yi-Heng Wu, Yi-Shun Syu, Yi-Lan Gong, Hung-Chin chen, Shing-Tai Pan

Reliability Sequential Sampling Test Based on Exponential Lifetime Distributions under Fuzzy Environment

In the areas of reliability analysis, the applications of life testing play a great important role. Under the deterministic circumstances, production reliability acceptance test (PRAT) for reliability sequential-sampling test (RSST) possesses high reliability and economic values in various fields. However, the past literatures showed that some of these uncertainties during the sampling inspection originate from trend, season, cyclic, or random variations; others come from improper operations. Hence, under these factors effect, the RSST may generate a vague value. In order to deal with uncertainty happened; this paper applies the triangular fuzzy number (TFN) are used to express the fuzzy phenomenon of the reliability sampling inspection’s parameters. Also, both the centroid and the signed distance approaches are used for defuzzification. To compare these estimates of the reliability sequential-sampling plan in the fuzzy sense, the better defuzzification method is generated.

Tien-Tsai Huang, Chien-Ming Huang, Kevin Kuan-Shun Chiu

Adaptive Performance for VVoIP Implementation in Cloud Computing Environment

In this paper we have implemented a real-time video/voice over IP (VVoIP) applications on a Hadoop cloud computing system and it is denoted CLC-IHU. It really outperforms the previous VVoIP using P2P connection (called SCTP-IHU) due to the easy-to-use and high-performance on video phone call. User does not need to know what is a real IP and web interface achieves interaction by adopt TCP instead of PR-SCTP so taht CLC-IHU scheme reduces computation load and power consumption dramatically at thin clients. We employed adaptive network-based fuzzy inference system (ANFIS) to tune key factors appropriately for adapting handoff and analyzing network traffic at any time. As a result it takes about 1.631 sec for the seamless handoff between base stations under mobile wireless network. In access control for preventing illegal intrusions from the outside of the cloud, the rapid facial recognition and fingerprint identification via cloud computing has been done successfully within 2.2 seconds to identify the subject exactly.

Bao Rong Chang, Hsiu-Fen Tsai, Zih-Yao Lin, Chi-Ming Chen, Chien-Feng Huang

Intelligent Service

Intelligence Decision Trading Systems for Stock Index

This paper introduces an intelligent decision-making model, based on the application of Fuzzy Logic and Neurofuzzy system (NFs) technology. Our proposed system can decide a trading strategy for each day and produce a high profit for each stock. Our decision-making model is used to capture the knowledge in technical indicators for making decisions such as buy, hold and sell. Moreover, we compared with 3 our proposed scenario of Intelligence Trading System model. Finally, the experimental results have shown higher profits than the Neural Network (NN) and “Buy & Hold” models for each stock index. And, some models which were including volume indicator and predicted close price on next day have profit batter than other models. The results are very encouraging and can be implemented in a Decision- Trading System during the trading day.

Monruthai Radeerom, Hataitep Wongsuwarn, M. L. Kulthon Kasemsan

Anomaly Detection System Based on Service Oriented Architecture

The problem of the network security has been taken up since eighties and has been developed up to present day. A major problem of an automatic intrusion detection is that, it is difficult to make a difference between a normal and an abnormal user behaviour. We propose the framework of a distributed anomaly detection system based on Service Oriented Architecture (SOA). The main idea of SOA is to treat applications, systems and processes as encapsulated components, which are called services. These services are represented by input and output parameters and the semantic description of their functionalities. We assume that all the functionalities of our system are delivered by the Web services.

Grzegorz Kołaczek, Agnieszka Prusiewicz

Efficient Data Update for Location-Based Recommendation Systems

Location-based recommendation systems are obtaining interests from the business and research communities. However, the efficiency of the update on the recommendation models is one of the most important issues. In this paper, we propose an efficient approach to update a recommendation model, User-centered collaborative location and activity filtering (UCLAF). The computational complexity of the model building is analyzed in details. Subsequently, our approach to update the models only the necessary parts is presented. As a result, the recommendation models obtained from our approach is exactly the same as the traditional re-calculation approach. The experiments have been conducted to evaluate our proposed approach. From the results, it is found that our proposed approach is highly efficient.

Narin Jantaraprapa, Juggapong Natwichai

Combining Topic Model and Co-author Network for KAKEN and DBLP Linking

The Web of Data is based on two simple ideas: to employ the RDF data model to public structured data on the Web and to set explicit RDF links to interlink data items within different data sources. In this paper, we describe our experience in building a system of link discovery between KAKEN, a database provides the latest information of research projects in Japan, and the DBLP Computer Science Bibliography. Using these links one can navigate from the information of a computer scientist in KAKEN to his publications in the DBLP database. Our problem of linkage between KAKE researchers and DBLP authors is name disambiguation. We proposed combining LDA based topic model and co-author network approach to improve linkage accuracy.

Duy-Hoang Tran, Hideaki Takeda, Kei Kurakawa, Minh-Triet Tran

PLR: A Benchmark for Probabilistic Data Stream Management Systems

Inherent imprecision of data streams in many applications leads to need for real-time uncertainty management. The new emerging Probabilistic Data Stream Management Systems (PDSMSs) are being developed to handle uncertainties of data streams in real-time. Many approaches have been proposed so far but there is no way to compare them regarding precision and efficiency. This problem motivated us to design an evaluation framework to compare performance and accuracy of PDSMSs with each other and also with probabilistic databases. In this paper, after a brief introduction to PDSMSs, we describe requirements and challenges for designing a PDSMS benchmark. Then, we present different parts of our framework including probabilistic data stream generator, queries, and result evaluator. Furthermore, we focus on implementation aspects and use our framework to evaluate effects of floating precision in our PDSMS prototype.

Armita Karachi, Mohammad G. Dezfuli, Mostafa S. Haghjoo

Mining Same-Taste Users with Common Preference Patterns for Ubiquitous Exhibition Navigation

In a ubiquitous exhibition, an intelligent navigation service that can provide booths’ information, recommend interesting booths and plan touring path is required for both visitors and vendors. The preference mining module is the kernel. This paper proposes a group-based user preference pattern mining method, which can be implemented as a preference mining module in this service. When the visiting traces that imply the preference of users are recorded, the method discovers user preference patterns with high representativeness and high discrimination from the historical visiting logs. According to the discovered model, collaborative recommendation can be accomplished, and then the intelligent navigation service can plan personalized touring path based on the recommendation lists. For demonstrating the performance of the proposed method, we engage some experiments, and then indicate the characteristics of the proposed method.

Shin-Yi Wu, Li-Chen Cheng

Publication Venue Recommendation Using Author Network’s Publication History

Selecting a good conference or journal in which to publish a new article is very important to many researchers and scholars. The choice of publication venue is usually based on the author’s existing knowledge of publication venues in their research domain or the match of the conference topics with their paper content. They may not be aware of new or other more appropriate conference venues to which their paper could be submitted. A traditional way to recommend a conference to a researcher is by analyzing her paper and comparing it to the topics of different conferences using content-based analysis. However, this approach can make errors due to mismatches caused by ambiguity in text comparisons. In this paper, we present a new approach allowing researchers to automatically find appropriate publication venues for their research paper by exploring author’s network of related co-authors and other researchers in the same domain. This work is a part of our social network based recommendation research for research publications venues and interesting hot-topic researches. Experiments with a set of ACM SIG conferences show that our new approach outperforms the content-based approach and provides accurate recommendation. This works also demonstrates the feasibility of our ongoing approach aimed at using social network analysis of researchers and experts in the relevant research domains for a variety of recommendation tasks.

Hiep Luong, Tin Huynh, Susan Gauch, Loc Do, Kiem Hoang

A Query Language for WordNet-Like Lexical Databases

WordNet-like lexical databases are used in many natural language processing tasks, such as word sense disambiguation, information extraction and sentiment analysis. The paper discusses the problem of querying such databases. The types of queries specific to WordNet-like databases are analyzed and previous approaches that were undertaken to query wordnets are discussed. A query language which incorporates data types and syntactic constructs based on concepts that form the core of a WordNet-like database (synsets, word senses, semantic relations, etc.) is proposed as a new solution to the problem of querying wordnets.

Marek Kubis

Intelligent Signal Processing and Application

Reversible Data Hiding with Hierarchical Relationships

In this paper, we propose a new method for reversible data hiding by employing the hierarchical relationships of original images. Considering the ease of implementation and the little overhead needed for decoding, we employ the histogram-based scheme with extensions for reversible data hiding. By utilizing the hierarchical structure and corresponding histograms of difference values, global and local characteristics of original images can be utilized for hiding more capacity with acceptable quality of output image. With our method, better performances can be obtained in enhanced image quality, embedding capacity, and comparable amount of side information. More importantly, the reversibility of our method is guaranteed, meaning that original image and hidden message can both be perfectly recovered at the decoder. Simulation results demonstrate that proposed method in this paper outperforms those in conventional histogram-based algorithms.

Hsiang-Cheh Huang, Kai-Yi Huang, Feng-Cheng Chang

Effect of Density of Measurement Points Collected from a Multibeam Echosounder on the Accuracy of a Digital Terrain Model

Digital terrain models (DTMs), finding a wide range of applications in the exploration of water areas, are mainly created on the basis of bathymetric data from a multibeam echosounder. The estimation of DTM accuracy dependent on the choice of the survey parameters is difficult due to the lack of reference surface. These authors have developed the methodology of simulation called

virtual survey

, which enables examining how various parameters of the echosounder, survey and DTM construction algorithms affect the errors of the created models. They are aimed at precise estimation of the model accuracy and the optimization of depth measurement work. The article includes the results of the examination of the effect of parameters determining the density of measurement points on the accuracy of the obtained GRID model. It has been proved that a significant reduction of recorded data density leads to only a slight increase in the modeling error, which makes the bathymetric survey much more cost-effective.

Wojciech Maleika, Michal Palczynski, Dariusz Frejlichowski

Interpolation Methods and the Accuracy of Bathymetric Seabed Models Based on Multibeam Echosounder Data

In order to make reliable sea bottom visualizations and analyses, accurate bathymetric models are necessary. The authors analyzed the process of GRID model creation using multibeam echosounder data and pointed interpolation methods as important sources of models’ errors. In order to assess the accuracy of the model, the simulation technique named

virtual survey

was applied. A wide range of interpolation methods was examined. The results show significant differences between these methods in terms of accuracy and effectiveness. The choice of the best interpolation methods for various cases is suggested.

Wojciech Maleika, Michal Palczynski, Dariusz Frejlichowski

Quantitative Measurement for Pathological Change of Pulley Tissue from Microscopic Images via Color-Based Segmentation

Measurement of pathological change in pulley tissue is an important index for trigger finger disease. However, the current measurement process is mostly based on manual estimation which is subjective and time-consuming. We hence propose an automatic method for quantitatively measuring the pathological change of pulley tissue from microscopic images. We first apply the color normalization to normalize all the acquired images. Then we use a three-stepped color segmentation process to extract the areas of diseased tissues. On the other hand, we also apply an active double thresholding scheme to segment the nuclei and extract shape features of nucleus. At last, the ratio of abnormal tissue area and the ratio of abnormal nuclei are calculated as the indices for the evaluation of trigger finger disease. The result showed good correlation between the expert judgments and the measured parameters.

Yung-Chun Liu, Hui-Hsuan Shih, Tai-Hua Yang, Hsiao-Bai Yang, Dee-Shan Yang, Yung-Nien Sun

Quantitative Measurement of Nerve Cells and Myelin Sheaths from Microscopic Images via Two-Staged Segmentation

Cell morphology measurement is important in evaluating the injury level of nervous system. However, current measurement process is mostly achieved by manual estimation which is subjective and time-consuming. We hence propose a two-stage method to automatically segment axons and myelin sheaths from microscopic images for measuring the cell morphology quantitatively. First, an automatic thresholding method is used to obtain axon candidates and then geometric and image properties are used to assure the axon regions. Second, the outer contour of myelin sheath is segmented using the active contour model with the obtained axon contour as the initial solution. Then, the desired morphological parameters can be readily measured. In the experiments, we used seven nerve images for accuracy validation and achieved very small contour distance errors (less than 0.5

μ

m with nerve diameter around 8

μ

m in average). Overall, the proposed method is found efficient and useful in nerve parameter evaluation.

Yung-Chun Liu, Chih-Kai Chen, Hsin-Chen Chen, Syu-Huai Hong, Cheng-Chang Yang, I-Ming Jou, Yung-Nien Sun

Segmentation and Visualization of Tubular Structures in Computed Tomography Angiography

The new contribution of this article is description of filtering algorithm for detecting tubular structures (veins / arteries) in three-dimensional images. An algorithm incorporate the Frangi’s filtration with additional neighborhood analysis filter that eliminates local noises that often remains after that algorithm. The sensitivity of the method is steered by two algorithm’s parameters that might be visualized in 3D plot. Changing of those parameters does not require recalculation of filtration results. Also the concepts of those parameters are more intuitive to the potential user then the three scalable eigenvalues - based Frangi’s parameters. The whole solution was tested on real volumetric CTA data.

Tomasz Hachaj, Marek R. Ogiela

Incorporating Hierarchical Information into the Matrix Factorization Model for Collaborative Filtering

Matrix factorization (MF) is one of the well-known methods in collaborative filtering to build accurate and efficient recommender systems. While in all the previous studies about MF items are considered to be of the same type, in some applications, items are divided into different groups, related to each other in a defined hierarchy (e.g. artists, albums and tracks). This paper proposes Hierarchical Matrix Factorization (HMF), a method that incorporates such relations into MF, to model the item vectors. This method is applicable in the situations that item groups form a general-to-specific hierarchy with child-to-parent (many-to-one or many-to-many) relationship between successive layers. This study evaluates the accuracy of the proposed method in comparison to basic MF on the Yahoo! Music dataset by examining three different hierarchical models. The results in all the cases demonstrate the superiority of HMF. In addition to the effectiveness of HMF in improving the prediction accuracy in the mentioned scenarios, this model is very efficient and scalable. Furthermore, it can be readily integrated with the other variations of MF.

Ali Mashhoori, Sattar Hashemi

Optical Flow-Based Bird Tracking and Counting for Congregating Flocks

Bird flock counting is not deeply studied yet, but there are applications of bird flock counting that would provide benefits to different parties, such as the population estimation of swiftlets for swiftlet farmers and migratory raptors for ornithologists. The methodology involved two stages: 1. segmentation phase to segment the birds out from the video and; 2. tracking phase to track the birds using optical flow and count them. The raptor flocks are used in this paper because they are bigger and easier to be filmed at congregation sites during migration. The experimental results show an average hit rate of 88.1% for video of 500 × 400 but only achieve 6.17 fps while the video of 320 × 200 had a lower hit rate of 73.3% but achieving 16.98 fps. Both are not capable of achieving real-time processing but show possibility of tracking and counting a flock of flying birds.

Jing Yi Tou, Chen Chuan Toh

Backmatter

Weitere Informationen

Premium Partner

    Bildnachweise