Proceedings of Fifth International Congress on Information and Communication Technology

Table of Contents

1. Frontmatter

2. Adaptive Cognitive Modeling of Electroconvulsive Treatment (ECT)

   S. Sahand Mohammadi Ziabari, Charlotte Gerritsen

   Abstract

   This paper presents a cognitive model on electroconvulsive treatment to reduce the stress level in body. The stress reduction is triggered by a cognitive electroconvulsive treatment that uses persistent manipulation of this treatment. The goal of this treatment is to decrease the strength between certain parts of the brain which are in charge of the stress. The proposed adaptive cognitive model aims to illustrate the effect of the therapy on different components of the brain. The model begins with a state of tough, powerful, and consistent stress within a post-traumatic disorder patient, and after following electroconvulsive treatment, the stress level starts to decrease from time to time according to each treatment session. The results show that, in the end, the disorder person will have a declined stress in contrast to not performing electroconvulsive treatment.

3. Digital Transformation in Swiss Hospitals: A Reference Modeling Approach

   Mike Krey

   Abstract

   Through various approaches such as the eHealth Switzerland 2.0 strategy, the Swiss healthcare system aims to digitally catch up with other industries and drive the industry into the digital future. To enable hospitals to transform their business model and prepare for the future, this paper presents an approach for the implementation of the digital transformation in Swiss hospitals. Thus, a metamodel consisting of nine elements was created as a base. The focus of the metamodel and the later reference model lay on the central activity elements, which are each embedded in a phase and are directly or indirectly connected to all the other elements in the metamodel. For the reference modeling, the metamodel serves as a structural template, while an existing roadmap from the literature on the digital transformation was used as a content-based starting point. The final reference model consists of 30 activities within six different phases.

4. Estimating Exceedance Probability in Air Pollution Time Series

   Giuseppina Albano, Michele La Rocca, Cira Perna

   Abstract

   In the last years, increasing attention has been paid to air pollution, due to its impact on human health and on the environment. Current EU legislation establishes fixed limits for some air components that have been shown to have adverse effects on human health. It is therefore important to identify regions where the probability of exceeding those limits is high. In this paper, we propose a bootstrap scheme to obtain the distribution of the considered air pollutant at a given time point. In particular, the proposed resampling scheme is based on the residuals of a semiparametric model which is able to incorporate some stylized facts usually observed in such kind of data, such as missing data, trends and conditional heteroscedasticity. The estimated bootstrap distribution is then used to estimate the probability that the air pollutant exceeds the fixed legal limits. An application to (\(PM_{10}\)) in Torino area in the North-Italian region Piemonte is shown.

5. Gemstone Merchandise Software

   Mohammed Nazik Zayan, Gayashini Shyanka Ratnayake

   Abstract

   Today, new and existing small-scaled gem merchants are finding it difficult to lead the business in a successful way due to poor decision-making, unpredictable market conditions, inexperience, and maintenance of client base. Therefore, it has urged the need of a solution focusing on helping to maintain and improve these areas leading to the profitability and success of small-scaled merchandise. This research focuses on analyzing the difficulties faced by small-scaled gem merchants relating to purchasing gemstones, adding and manipulating records, marketing and sales and to design and develop a software solution giving importance in helping to make corrective decisions leading to the profitability of the company such as purchasing a gemstone for the right price and adequate ways of reaching out to potential clients leading to marketing and sale of colored stones.

6. Factors Causing Stunting Among Under-Five Children in Bangladesh

   Dm. Mehedi Hasan Abid, Aminul Haque, Md. Kamrul Hossain

   Abstract

   Malnutrition is one of the major problems in developing countries including Bangladesh. Stunting is a chronic malnutrition, which indicates low height for age and interrupt the growth. The purpose of this research is to find out the factors associated with the malnutrition status and test the accuracy of the algorithms used to identify the factors. Data from Bangladesh Demographic Health Survey (BDHS), 2014, is used. Factors like demographic, socioeconomic, and environmental have differential influence on stunting. Based on analysis, about 36% of under-five children were suffering from stunting. Decision tree algorithm was applied to find the associated factors with stunting. It is found that mothers’ education, birth order number, and economic status were associated with stunting. Support vector machine (SVM) and artificial neural network (ANN) are also applied with the stunting dataset to test the accuracy. The accuracy of decision tree is 74%, SVM is 76%, and ANN is 73%.

7. Human Resources Information Systems and Their Impact on Employee Performance Assessment Strategy: A Practical Study on Jordan Telecom Company in the Hashemite Kingdom of Jordan

   Hisham O. Mbaidin

   Abstract

   The study aimed to identify the human resources information systems and their impact on the strategy of evaluating the performance of the employees of Jordan Telecom Company. The objectives of the study achieved through a questionnaire were developed for the purpose of data collection. The (SPSS.16.1) statistical software was used to analyze data. The most prominent results were: The level of importance of human resources information systems (the efficiency of human resources information systems, integration with other MIS, responsiveness) in Jordan Telecom was moderate in terms of respondents’ perceptions, as well as the impact of human resources information systems in the performance assessment strategy. Human resource systems accounted for 54% of the variation in the strategy of evaluating the performance of Jordan Telecom employees. In light of the achieved results, the study recommends, the most important of which is the development of human resources information system aimed at tracking the performance of employees to improve their performance and improvement, and recommended the development of human resources management policies, so as to contribute to the detection of the potential and potential of workers.

8. Measuring Complexity of Legislation. A Systems Engineering Approach

   Andres Kütt, Laura Kask

   Abstract

   Complexity management is a well-understood concept in systems engineering with strong theoretical and practical foundations. The complexity of legal systems, however, is mainly considered in trade or tax context and remains largely qualitative in nature. Since the ability to create, develop and follow law is crucial to functioning of a society, a quantitative method for assessing the complexity of a set of laws from both its creation and consumption perspective and development of that complexity over time would be beneficial. For example, such a measure could be used to assess the sustainability of a legal system, develop “complexity budgets” for legislative texts and quantitatively measure the impact of changes. In this paper, the authors utilise a complexity measure for engineering systems in the legal context of the Republic of Estonia. A specific measure of legal complexity is developed based on ideas from systems engineering and morphological analysis. It is then applied to time series of quarterly sets of Estonian legislation from 2002 to 2019. The research shows that systems engineering approach does yield meaningful results in the legal domain and that, assuming limited cognitive capabilities, the existing trend of complexity growth is not sustainable. Policy recommendations are presented to change the trend found.

9. A Multimodal Biometric System for Secure User Identification Based on Deep Learning

   Shefali Arora, M. P. S. Bhatia, Harshita Kukreja

   Abstract

   A multimodal biometric system utilizes more than one biometric modality of a person to relieve some of the shortcomings of a unimodal biometric system and improves its security. In this paper, we propose a novel deep learning approach for fusing the features extracted from the individual’s face and iris (left and right) to get a more secure biometric verification system. Firstly, we extract the facial and iris features separately using various convolutional neural network (CNN) models. Further, the feature vectors of the final CNN layers of both models are fused to achieve classification of individuals with improved performance. The proposed system is tested on the CASIA-Face V5 dataset for faces and IITD iris dataset for left and right irises. The results achieved prove the superiority of the proposed multimodal system. It is efficient, reliable, and robust as compared to unimodal biometric systems.

10. Distributed Modular Multiplication to Be Processed by a Network of Limited Resources Devices

    Menachem Domb

    Abstract

    Asymmetric cryptography algorithms, still considered the most robust tool available in the cryptography domain. It incorporates intensive modular exponentiation calculations, which entail considerable computing power, memory and storage space. Common IoT device is equipped with limited computing resources and so, for security purposes, it can execute symmetric and limited asymmetric cryptography. In most cases, IoT devices do not have the capacity required for executing massive modular multiplications of numbers of magnitude of 4 K bits and more. This leads to the lack of asymmetric cryptography in the IoT domain resulting with a reduction in security means to cope with the raising security challenges. The security problem increases as the number of IoT devices is expected to significantly grow soon. We propose a new implementation of asymmetric cryptography, which splits its heavy calculations into micro-processes, where each micro-process is distributed to an appropriate IoT device, connected to the network. The accepted result is transferred back to the distributing IoT. Once all the results are accumulated, a consolidation process is activated to generate the final calculation result, which then is fed into the cryptography process, to generate the Encrypted/Decrypted string, proving the ability to maintain asymmetric cryptography also at the IoT level without compromising security.

11. Novel Hidden Markov Scoring Algorithm for Fraudulent Impression Classification in Mobile Advertising

    Iroshan Aberathne, Chamila Walgampaya, Udara Rathnayake

    Abstract

    Excessive usage of smartphones and tablets have led to drastic increase of mobile ad fraud in recent years. The fraudulent users can be either human or automated scripts with the intention of making illegal revenue or exhausting the advertiser budget are being engaged with this multimillion industry. The ad fraud referred to any kind of activities that are generated by a fraudulent user is a huge threat to the existence of the online advertising ecosystem. The researchers have proposed various kinds of methodologies and tools in the context of ad fraud detection and prevention. However, the fraudulent users are smart enough to bypass the significant number of existing detection and prevention systems. The combat between fraud users and researchers or solution designers in this field never ends. Thus, the novel solution of ad fraud detection and prevention techniques is needed. The proposed approach of this study to address this problem is called hidden Markov scoring model—HMSM. The model calculates scores for each observe/emission variable of experimental data set towards the hidden states of target variable based on hidden Markov model so that fraud impression can be classified. The experimental results show that the significance of the proposed approach to classify the fraud and non-fraud impression.

12. Looking for Virtual Investors

    Ion Chiţescu, Mǎdǎlina Giurgescu, Titi Paraschiv

    Abstract

    This paper introduces a method of selecting the most probable future investment clients of a brokerage company on the capital market. The method consists in using the answers given by the virtual investors to a set of prescribed questions. Namely, the aforementioned answers are fusioned with a data mining procedure using the Choquet integrable. The scores thus obtained are classified using some preassigned thresholds, allowing to select the most probable future investment clients.

13. Scalability Analysis of Low-Power Wide Area Network Technology

    N. A. Abdul Latiff, I. S. Ismail, M. H. Yusoff, A. R. Salisa, J. A. Shukor

    Abstract

    Low-power wide area network is a new wireless communication technology designed for low-power consumption together with long-distance communications, and LoRa technology is one of the leading technology solutions. The long-range connection between end-nodes and gateway is achievable by LoRa devices due to star-based network topology and modulation techniques used in wireless communication of the technology. One of the main features of LoRa technology is the ability to scale. Modelling and simulation can interpret the actual network behaviour of LoRa technology as accurate as possible. This paper aims to investigate the performance of the low-power wide area network technology focusing on capability of the network to scale. We model the network system based on the behaviours of the communication between the end-node and gateway. The simulation to study the scalability was done based on several parameters, such as the number of end-nodes, application time and the number of channels used by the end-node. The results show that the amount of successfully received data signal at gateway increased as the application time and channel used increased.

14. Enhancement of Advanced Driver Assistance System (Adas) Using Machine Learning

    Santhosh Krishnarao, Hwang-Cheng Wang, Abhishek Sharma, Mazher Iqbal

    Abstract

    Most of the road accidents can be attributed to human errors. Advanced driver assistance system (ADAS) is an electronic system that guides a vehicle driver while driving. It is designed with a safe human-machine interface that is intended to increase vehicle safety and road safety. ADAS is developed to automate, adapt and enhance vehicle systems for safety and better driving. An increasing number of modern vehicles have ADAS such as collision avoidance, lane departure warning, automotive night vision, driver monitoring system, anti-lock braking system and automatic parking system. ADAS relies on input from multiple data sources like lidar, radar, and camera. This paper describes the implementation of ADAS using machine and deep learning algorithms. We implement a model which has a 360-degree camera (lens on two sides of 170 degrees each), lidar, ultrasonic sensor, and radar that provide the input for ADAS. We implement the ADAS by training this whole model using deep learning (advanced machine learning) by designing a neural network using Python in TensorFlow. Generative adversarial networks (GANs) are used in object detection when a hazed image (foggy, rainy, etc.) is detected. This reduces the sensor complexity and area in the vehicle. Results gained from the study and their implications are presented.

15. Blockchain Applications in Logistics and Supply Chain Management: Problems and Prospects

    Yulia A. Morozova

    Abstract

    The growing interest and expectations from the blockchain applications attract many analysts to this issue. In what spheres of logistics and supply chain management blockchain is appropriate? What blockchain software solutions are available to companies now? This paper investigates the basic functionality of the existing software solutions on the market and the comparative analysis of blockchain platforms used for developing the solutions for logistics is also carried out. The main trends of blockchain applications are identified, based on the analysis of the project experience on the use of blockchain, in logistics and supply chain management, in different countries. The problems, limitations and conditions of blockchain implementation are also determined.

16. Augmented Reality Storytelling Teachers and Preschool Children Experience

    Faiz bin Meor Othman, Wan Adilah Wan Adnan, Zan Azma Nasruddin

    Abstract

    This study aims to use AR technology to develop an AR-based learning of a digital storybook for preschool children aged 6 years old as to motivate their reading. This application will show digital storytelling based on book titled “The Three Bears” by Emma Bailey focusing on pages 4 and 5. User testing with both teachers and preschool children was conducted to examine the potential of the AR approach in motivating them learning by using both qualitative and quantitative interview in order to measure their learning experience. The findings indicate that the AR-based storybook approach does affect their enjoyment, engagement and motivation. A suggestion for further research is to embed elements of surprise to prevent boredom in an AR-based storybook to preschool children to increase their engagement in reading.

17. TSP Algorithm for Optimum Path Formulation of AUV for Data Collection in Underwater Acoustic Sensor Network

    S. Ansa Shermin, Aditya Malhotra, Sarang Dhongdi

    Abstract

    Underwater acoustic sensor network (UASN) marks a new era in ocean exploration, enabling various scientific, military and commercial applications. This paper describes one of the scientific applications named coral reef monitoring in a desired region of interest in the Arabian Sea. The events of coral bleaching that leads to massive destruction of coral reef is a current alarm faced by most of the buildups. UASN can be deployed to monitor the environmental parameters of various such regions. In this paper, a number of nodes are deployed in the form of clusters at various regions. An autonomous underwater vehicle (AUV) is used to collect data by visiting the clusters/cluster-heads periodically. Travelling salesman problem (TSP) is used to find optimum tour for the AUV in the data collection phase. The application of TSP in data gathering helps the data collection by forming minimal tour for the vehicle. This paper provides the implementation of protocol stack along with detailed results and analysis using an underwater network simulator (UnetSim).

18. Preprocessing Improves CNN and LSTM in Aspect-Based Sentiment Analysis for Vietnamese

    Duy Nguyen Ngoc, Tuoi Phan Thi, Phuc Do

    Abstract

    The deep learning method has achieved particularly good results in many application fields, such as computer vision, image processing, voice recognition, and signal processing. Recently, this method has also been used in the field of natural language processing and has achieved impressive results. In this field, the problem of categorizing subjective opinions which is an individual’s thinking or judgment of a product or an event or a cultural and social issue. Subjective opinions have received attention from many producers and businesses who are interested in exploiting the opinions of the community and scientists. This paper experiments with the deep learning model convolution neural network (CNN), long short-term memory (LSTM), and the boxed model of CNN and LSTM. Training data sets comprise reviews of cars in Vietnamese. Cars are objects with a significant number of specifications that are provided in user reviews. The Vietnamese opinion set is preprocessed according to the method of aspect analysis based on an ontology of semantic and sentimental approaches. A Vietnamese corpus experiment with CNN, LSTM, and CNN + LSTM models are used to evaluate the effectiveness of the data preprocessing method that was used in this paper. To assess the validity of the test models with the Vietnamese opinion set, the paper also tests the sentiment classification with the English Sentence Collection Stanford Sentiment Treebank (SST).