Mohammad A. Hassonah, Ali Rodan, Abdel-Karim Al-Tamimi, J. Alsakran
{"title":"Churn Prediction: A Comparative Study Using KNN and Decision Trees","authors":"Mohammad A. Hassonah, Ali Rodan, Abdel-Karim Al-Tamimi, J. Alsakran","doi":"10.1109/ITT48889.2019.9075077","DOIUrl":"https://doi.org/10.1109/ITT48889.2019.9075077","url":null,"abstract":"Churn prediction represents one of the most important components of Customer Relationship Management (CRM). In the purpose of retaining customers and maintaining their satisfaction, researchers of many fields including business intelligence, marketing and information technology were motivated to investigate the best methods that deliver the best services for customers. Many machine learning algorithms had been implemented in the purpose of optimally predicting the possible churning customers and making the right decisions at the right moments. Researchers had conducted several studies on various types of algorithms and results were found very promising. In this paper, we are conducting a comparison study of the performance towards churn prediction between two of the most powerful machine learning algorithms which are Decision Tree and K-Nearest Neighbor algorithms. Results were quite interesting showing a quite large dissimilarity in many areas between the two algorithms.","PeriodicalId":112059,"journal":{"name":"2019 Sixth HCT Information Technology Trends (ITT)","volume":"36 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131436698","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Improving Shared Mobility with Mobile Technology: The Case of ekar in Dubai","authors":"M. A. Gilbert","doi":"10.1109/ITT48889.2019.9075125","DOIUrl":"https://doi.org/10.1109/ITT48889.2019.9075125","url":null,"abstract":"Dubai motorists spend an average of 80 hours stuck in rush-hour traffic annually, costing businesses billions of dollars in lost workhours. More than 570 cars per 1,000 people, a number projected to increase with the arrival of Expo 2020, fuels this congestion each day. Reducing individual car ownership is one solution to this challenge; carsharing services provide a proven pathway. Indeed, car-sharing service car2go demonstrated that each vehicle in their fleet removed up to 11 personal cars from the road. Embracing this option, in 2017 Dubai Roads and Transport Authority (RTA) launched a car-sharing service with two private firms: Udrive and ekar. Both firms offer a smartphone app and technology with which users can find, unlock, and rent cars at more than 45 locations across Dubai. The objective of this paper is to explore in case study format the strategy and technology of one of these providers, ekar, while evaluating the implications of blockchain functionality and internet of things features on the digital drivetrain of the carsharing service.","PeriodicalId":112059,"journal":{"name":"2019 Sixth HCT Information Technology Trends (ITT)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115167274","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mughees Ali, Z. Khan, Sana Mujeeb, Shahid Abbas, N. Javaid
{"title":"Short-Term Electricity Price and Load Forecasting using Enhanced Support Vector Machine and K-Nearest Neighbor","authors":"Mughees Ali, Z. Khan, Sana Mujeeb, Shahid Abbas, N. Javaid","doi":"10.1109/ITT48889.2019.9075063","DOIUrl":"https://doi.org/10.1109/ITT48889.2019.9075063","url":null,"abstract":"Accurate load and price forecasting is one of the crucial stage in Smart Grid (SG). An efficient load and price forecasting is required to minimize the large difference among power generation and consumption. Accurate selection and extraction of meaningful features from data are challenging. In this paper, New York Independent System Operator (NYISO) six months' load and price data is used for forecasting. Decision Tree (DT) is used for feature selection and Recursive Feature Elimination (REF) technique is used for feature extraction. REF technique is used to remove redundancy from selected features. After feature extraction, two classifiers are used for forecasting. One classifier is Support Vector Machine (SVM) and other classifier is K-Nearest Neighbor (KNN). These classifiers have different parameters with some default values. Week ahead load and price forecasting is performed in this work. Accuracy of modified SVM is 89.5984% and modified KNN is 89.8605% is achieved for load forecasting. For price, accuracy of modified SVM is 88.2740% and modified KNN is 85.5999%.","PeriodicalId":112059,"journal":{"name":"2019 Sixth HCT Information Technology Trends (ITT)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132212737","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Cluster-based Algorithm for Energy Optimization of Swarmed Robots using Swarm Intelligence","authors":"M. Al-Obaidy, Rula Al-Azawi","doi":"10.1109/ITT48889.2019.9075119","DOIUrl":"https://doi.org/10.1109/ITT48889.2019.9075119","url":null,"abstract":"This paper presents the design of an intelligent energy efficient algorithm which is based on Swarm Intelligence to increase the life time of swarmed Robots. This algorithm represents a further advancing stage to our previous work which was devoted to cluster Wireless Sensor Networks (WSNs) into independent clusters. Our Algorithm presented in this research is mainly designed to keep the optimum distribution of clustered mobile Robots while those Robots are directed as a swarm to achieve a given goal. The algorithm presented in this research is suitable for large scale mobile Robots and provides a robust and energy- efficient communication mechanism. We are using the Particle Swarm Optimization (PSO) technique to decrease the energy consumption for the entire swarms. One of the main strengths in the presented algorithm is that the number of clusters within the swarm of Robots is not predefined, this gives more flexibility for the Robots' deployment in the swarm. Another strength is that the number of Robots assigned within each swarm is not necessary to be uniformly distributed as in other swarms, since in some applications constraints, the sensing Robots need to be deployed in different densities depending on the nature of the application.","PeriodicalId":112059,"journal":{"name":"2019 Sixth HCT Information Technology Trends (ITT)","volume":"151 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117342533","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Digital Simulation in the Virtual World: Its Effect in the Knowledge and Attitude of Students Towards Cybersecurity","authors":"Pedro Flores","doi":"10.1109/ITT48889.2019.9075068","DOIUrl":"https://doi.org/10.1109/ITT48889.2019.9075068","url":null,"abstract":"The search for alternative delivery modes to teaching has been one of the pressing concerns of numerous educational institutions. One key innovation to improve teaching and learning is e-learning which has undergone enormous improvements. From its focus on text-based environment, it has evolved into Virtual Learning Environments (VLEs) which provide more stimulating and immersive experiences among learners and educators. An example of VLEs is the virtual world which is an emerging educational platform among universities worldwide. One very interesting topic that can be taught using the virtual world is cybersecurity. Simulating cybersecurity in the virtual world may give a realistic experience to students which can be hardly achieved by classroom teaching. To date, there are quite a number of studies focused on cybersecurity awareness and cybersecurity behavior. But none has focused looking into the effect of digital simulation in the virtual world, as a new educational platform, in the cybersecurity attitude of the students. It is in this regard that this study has been conducted by designing simulation in the virtual world lessons that teaches the five aspects of cybersecurity namely; malware, phishing, social engineering, password usage and online scam, which are the most common cybersecurity issues. The study sought to examine the effect of this digital simulation design in the cybersecurity knowledge and attitude of the students. The result of the study ascertains that students exposed under simulation in the virtual world have a greater positive change in cybersecurity knowledge and attitude than their counterparts.","PeriodicalId":112059,"journal":{"name":"2019 Sixth HCT Information Technology Trends (ITT)","volume":"304 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115365612","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"SMART project management for SMART cities: Analyzing critical factors affecting trust among Virtual Project Teams","authors":"Sukhwant Kaur, Vishwesh Akre, M. Arif","doi":"10.1109/ITT48889.2019.9075131","DOIUrl":"https://doi.org/10.1109/ITT48889.2019.9075131","url":null,"abstract":"SMART cities suggest a domain that attracts an increasing scientific, political and economic attention. Smart Cities have been characterised and defined by a number of factors including sustainability, economic development and a high quality of life. Enhancing these factors can be achieved through infrastructure (physical capital), human capital, social capital and ICT infrastructure. It requires ambitious projects to transform entire urban areas through master planning and infrastructure development. This required SMART project management. In order to accomplish the goals of SMART project management, the construction industries have to rely on multi -disciplinary project teams having varied expertise. Majority of these companies have adopted virtual teams for their business activities. These virtual teams work at global level and face a number of challenges that can have an impact on team effectiveness. This research paper focuses on classification of smart cities and key challenges faced by the virtual project teams. Further to this, this paper reviews existing international literature to identify the variables affecting trust among virtual team members in construction sector of Middle East. The variables are then grouped together to form factors after understanding their definitions and commonalities among them. This research highlights the importance of these factors to project managers of smart city projects and it would be beneficial to Project Managers of Architectural/Engineering / Construction Companies as well as that of other sectors by facilitating them to know the actions required for better team collaboration in virtual teams. This may lead to greater team performance and individual learning.","PeriodicalId":112059,"journal":{"name":"2019 Sixth HCT Information Technology Trends (ITT)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126402361","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Nedaa Baker Al Barghuthi, Issam Hamdan, Saleh Al Suwaidi, Ahmed Lootah, Bader Al Amoudi, Omar Al Shamsi, Saeed Al Aryani
{"title":"An Analytical View on Political Voting System using Blockchain Technology - UAE Case Study","authors":"Nedaa Baker Al Barghuthi, Issam Hamdan, Saleh Al Suwaidi, Ahmed Lootah, Bader Al Amoudi, Omar Al Shamsi, Saeed Al Aryani","doi":"10.1109/ITT48889.2019.9075074","DOIUrl":"https://doi.org/10.1109/ITT48889.2019.9075074","url":null,"abstract":"Voting is a pillar of modern society, but the traditional paper voting system is prone to fraud and failure. Votes can sometimes be miscounted or might be lost in transit. Besides, the electronic voting system has been active subject research for decades. However, the old traditional voting system lacks security and privacy features, which has been a challenge for a long time. As a solution, this paper is proposing a prototype blockchain-based electronic voting system for the United Arab Emirates (UAE) political election process. A blockchain system is a distributed decentralized, immutable database; that allows the data to be distributed and shared among all the participants in a network. Also, it has many advantages that can be applied in many use cases, such as electronic voting systems. Implementing the blockchain-based electronic voting system will minimize the costs of running an election while ensuring integrity. It has the potential to limit voter fraud while making the votes traceable and verifiable, preventing unauthorized activity, and fake votes by authenticating each voter in the system. The UAE has a blockchain initiative that seeks to have 50 percent paperless transactions in all its governmental processes by the end of 2021. This paper studied the effectiveness of adopting blockchain in the UAE political election.","PeriodicalId":112059,"journal":{"name":"2019 Sixth HCT Information Technology Trends (ITT)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124867936","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Omar Alamir, R. Raman, Amal Faisal Alhashimi, Fatima Ali Almoaber, Amna Humaid Alremeithi
{"title":"M-Blocks (Medical Blocks): A blockchain based approach for patient record management using IBM Hyperledger","authors":"Omar Alamir, R. Raman, Amal Faisal Alhashimi, Fatima Ali Almoaber, Amna Humaid Alremeithi","doi":"10.1109/ITT48889.2019.9075088","DOIUrl":"https://doi.org/10.1109/ITT48889.2019.9075088","url":null,"abstract":"The purpose of this research is to highlight the usage of blockchain technology for the maintaining the health records of the patients across visiting hospitals in a highly secured environment. A blockchain is a distributed ledger technology (DLT) in which the blockchain is separated into blocks that contain a list of digital records that are secured by using encryption technology (cryptography). The blockchain is a data structure that show the way the data are stored and logically joined together in a peer to peer (P2P) network. Sharing health records between the various hospitals is a vital and life-saving during emergency. This will greatly reduce the time needed for the physicians to prescribe and take preventive actions required as quickly as possible. This helps to attend the patients on-time and save their life during the emergency situations. MBlocks stands for medical blocks with sequence of blocks having the patient's information shared and stored across various entities in a secured Hyperledger environment.","PeriodicalId":112059,"journal":{"name":"2019 Sixth HCT Information Technology Trends (ITT)","volume":"294 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114953468","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Muhammad Usman, Zahoor Ali Khan, I. Khan, Sakeena Javaid, N. Javaid
{"title":"Data Analytics for Short Term Price and Load Forecasting in Smart Grids using Enhanced Recurrent Neural Network","authors":"Muhammad Usman, Zahoor Ali Khan, I. Khan, Sakeena Javaid, N. Javaid","doi":"10.1109/ITT48889.2019.9075065","DOIUrl":"https://doi.org/10.1109/ITT48889.2019.9075065","url":null,"abstract":"In this paper, an artificial neural network (ANN) based methodology is proposed to forecast electricity load and price. The performance of an ANN forecast model depends on appropriate input parameters. Parameter tuning of ANN is very important to increase the accuracy of electricity price and load prediction. This is done using mutual information and decision tree. After selecting best features for forecasting, these features are given to forecasting engine working on principles of recurrent neural network (RNN). For simulations, dataset is taken from national electricity market (NEM), Australia. Results show that the methodology has increased the accuracy of electricity load and price forecast. Whereas, the error rate of forecasting is lower than the other models for electricity load and price.","PeriodicalId":112059,"journal":{"name":"2019 Sixth HCT Information Technology Trends (ITT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130317593","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Smart IoT based Demand Variation Prediction Model","authors":"M. Naveed, M. Adnan, Israr Ahmed, Yasir Javed","doi":"10.1109/ITT48889.2019.9075066","DOIUrl":"https://doi.org/10.1109/ITT48889.2019.9075066","url":null,"abstract":"This paper addresses the inventory control problem to predict the demand variations in real-time. The work presents a novel solution using a reinforcement learning model that manages Internet of Things (IoT) devices for collaboration. The key focus is on the inventories with open orders. Such inventories require a solution that can predict variations based on short-term demand data. Demand variations are frequent and involve high degree of uncertainty. The inventory prediction and update in real-time is a challenging and non- trivial task. The accurate predictions of inventory variations play key role in reducing the overhead of inventory management. In this work, we explore a novel reinforcement model using inventory data of Grupo Bimbo and results show that reinforcement model performs better to identify demand based on short variations. The model learning is optimized using IoT devices.","PeriodicalId":112059,"journal":{"name":"2019 Sixth HCT Information Technology Trends (ITT)","volume":"147 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116501545","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}