Theses for Computer Science

Permanent URI for this collection

https://bspace.buid.ac.ae/handle/1234/1099

Browse

Now showing 1 - 20 of 41

Smart Safe Cities Technology Architecture to Assure Citizens’ Happiness and Future Foresight to Achieve United Arab Emirates 100 Year Vision: Response Readiness, National Resilience and Future Accelerations
(The British University in Dubai (BUiD), 2017-07) AL HASSAN, MOHAMMAD KHALED
Smart cities have emerged quite rapidly across the globe, be it the Masdar City in partuclar Abu Dhabi the capital of UAE, or in London, or Washington irrespective of the economy being developed, developing or emerging. This is primarily given the usefulness of such cities to enable transparency and efficiency within the city functions. In this research, the focus on the ‘safety’ aspect within smart cities, bringing forth the implementations requirement to transform a smart city into safety city for UAE. The aim of this research is to build a conceptual framework to enable the transformation of smart city into SSC, supporting citizen happiness, future accelerations and sharing future governments. Over the years, various models and theories were proposed to enable organizations into smart organizations, with one such being the institutional theory. The theory has been utilized extensively, in collaboration with other theories such as the Lewin’s model of 3-stage or the barrier-driver model developed for e-governments. The case considered for this research was Abu Dhabi Government in UAE, with the research questions and objectives set out and achieved through the aid of a quantitative survey questionnaire. The sample selected for the research was public sector of Abu Dhabi. With a detailed review of the factors (internal and external) of smart cities and e-government (as the base), the study reviewed the benefits, barriers as well as risks that entail the transformation of smart cities to SSC within the context of UAE. Based on the findings of the data analysis, the conceptual framework developed was validated followed by a re-conceptualization to suit the Abu Dhabi Government. Recommendations were built to support the extension of the framework to smart city models in other countries to focus and build on the safety aspect, thus achieving citizen happiness and boost future development.
Information Technology Disaster Recovery Plan (IT DRP) Framework – A study on IT Continuity for Smart City in Abu Dhabi Smart Government
(The British University in Dubai (BUiD), 2017-07) AL HASSAN, LINDA KHALED MOHAMMED
The growth in urbanization in the world of today in unprecedented, supported with information technology to meet the growing demands of the humankind. Over the years, technology application in various fields of business has increased, with one such concept been seen in the form of smart cities. The heavy reliance on technology today has facilitated governments to improve public services and achieve satisfaction amongst its users. Similarly for businesses, it has boosted global communication, trade and development. However, the reliance on information technology has also increased the challenges with one such being disaster recovery. In this research study, the aim was to develop a IT DRP framework to support the Abu Dhabi Government in the initiatives of smart city services to assure its system and IT continuity. An extensive literature review was conducted to identify the key parameters that dictate the efficiency of an IT framework, and the challenges, barriers and risks that are involved in securing IT disaster recovery. Past literature in the area of smart cities and information technology had led to the identification of the gap of IT disaster recovery which is found missing. While a large extent of the literature deals with securing firms in the event of a natural disaster, however, no significant finding was made in terms of a well-developed IT disaster recovery framework. This applies especially in the area of public services such as those offered by Abu Dhabi Smart City. Also, given the focus of the past researchers on IT continuity for corporates, this research study design was framed to incorporate the case of Abu Dhabi Smart City. Based on the factors identified in the literature review, i.e. factors influencing smart city services and the components of IT disaster recovery, a conceptual framework was developed. The concept was reviewed and examined in light of the past literature in the area of IT disaster recovery and the challenges or barriers that restricted their application in smart city services. A quantitative method was adopted as the research design for data collection from experts, IT professionals and policy makers from Abu Dhabi Government, UAE as the sample. A detailed statistical analysis was conducted to identify the relationships between the key variables i.e. smart city services and IT DRP and how the framework can be implemented in case of an IT disaster to secure IT services continuity. Upon data analysis, the researcher was able to identify the core components of IT DRP and Smart city which were then conjoined together to formulate the revised framework. Post review of each individual factor, correlation testing and hypothesis testing was conducted that examined the relationship between smart city variables and IT DRP variables. The analysis revealed that all the components of IT DRP and Smart city are inter-connected. As per the findings from the responses of the IT personnel associated with smart city projects in Abu Dhabi Government and the analysis of data, distinct from data validation, some additional factors are discovered. Based on this, few changes are made to the framework which involves addition of new factors and removal of less dominant factors from the framework for smart city IT DRP. The new comprehensive framework for smart city IT DRP for smart government services was tested as well as evaluated for validity. It was found that the framework proposed with the subcomponents of IT DRP and Smart city have a strong relationship when integrated together. After conducting the research and drawing important conclusions, the researcher offers recommendations for policy makers as well as researchers. The government can adopt the proposed framework for analysis of the numerous external factors having the potential to impact the plans in one way or the other and to devise more intelligent plans and strategies accordingly. In case of academic researchers, his study suggests to investigate on how to identify and then manage the identified stakeholders effectively for better results. They can look into the details of how by keeping in view the specific needs of the public, government can formulate more effectual policies to administer such large ICT projects. They can explore the different techniques adopted by the government entities and how they determine the order in which they execute their different tasks. It is suggested that they should look into the several facets of this smart city project so as to make planning in compliance. It is also recommended that the organizations and government should constantly monitor their security systems to avoid any sort of data breach and keep them up to date.
Framework for Minimizing Critical Information Infrastructure Threats from Insiders
(The British University in Dubai (BUiD), 2017-10) AL KATHEERI, AHMED OMAR
Malicious insiders are posing unique security challenges to organizations due to their knowledge, capabilities, and authorized access to information systems. Data theft and IT sabotage are two of the most recurring themes among crimes committed by malicious insiders. This research aims at investigating the scale and the scope of the risks from malicious insider’s activities and exploring the impact of such threats on business operations. The developed framework targets minimization of the insider threats through profiling the user activities using information from the log files of several components participating in these activities, like IDS, IPS, firewalls, network devices, sever hosts and workstations. Malicious activities potentially leave suspicious patterns and references to users which can be used to infer the main actor or actors and mitigate the threat before they actually occur. The analytical backbone of the framework can be build upon Actor Network Theory. Organizations need to implement a multi layered defensive approaches to combat insider risks; safeguarding sensitive business information from malicious insiders requires an effective security framework that can identify the malicious group members involved and predict their offensive intentions something like a black box. To open this black box and explore the intention of the insiders, the framework developed here relies on two different security technologies: Security Information Event Management (SIEM) and User Behavior Analytics (UBA). They allow extracting the data from different entity logs, analyzing and separating the malicious activities from non-malicious ones on the base of the User Security Profile (USP). On the other hand, the security engine must allow formulating different hypothesis, which have varying degree of flexibility to address the security requirements and have the ability to identify the main actor and the other participants using analyzed information. Organizations need to implement multi layered defensive approaches to combat insider risks; safeguarding sensitive business information from malicious insiders requires an effective security policy that communicates widely the consequences of stealing or leaking confidential information in an unauthorized manner. Secondly, logging and monitoring employee activity is essential in detecting and controlling system vulnerabilities. Thirdly, conducting periodic and consistent vulnerability assessments is critical to identify any gaps in security controls and to prevent insiders from exploiting them. And last, but certainly not least, taking extra caution when dealing with privileged users is important to proactively protect the information infrastructure from insider risks.
Predicting Mobile Game Success Using Data Analytics
(The British University in Dubai (BUiD), 2017-11) ALOMARI, KHALED MOHAMMAD
Since the advent of arcade games and the development of the Wireless Application Protocol (WAP) at the close of the millennium, the mobile game app industry has exploded; and subsequently has transformed the ideologies of mobile technology and software developers to forward thinking within the dimension of innovative mobile game development. After the first decade of the new millennium has passed, and even though billions of dollars in revenue have been realized from mobile game apps, there is still a gap in literature with regard to mobile game user behavior and methodologies for predicting the likely success of mobile game apps during the development phase. Game features and ARM strategies are analyzed and discussed as primary drivers of mobile game app success. This study addresses these challenges through data driven research of the mobile gaming application market, mobile gaming application features, user acquisition and retention trends, and monetization strategies using the CRISP-DM model for data mining in order to prove a successful method for predictions of mobile game application success. The attainment of the prediction of one mobile game app from a sample of 50 was accomplished by running a batch prediction for the game features dataset, and a separate batch prediction for the user behavior dataset. The lists were then integrated, a final list of games which appeared in both lists was generated for further comparison. According to the prediction model results for the dual datasets, the most successful mobile game app from the 50 game sample was Game of War-Fire Age; the most successful genre was Puzzles, and the most successful developer was EA Sports. Where success is described based on the best match with the results of the study. The most successful game predictions were extracted and compared to the predominating user behaviors for further analysis and implications. Significant outcomes for the comparisons included the predominance of the Social Networking features, Offers, and IAP 90% to 100% of the sample. A model of mobile game app success prediction based upon the game features values that are created proposed.
Relevance Feedback Optimization for Digital Forensic Investigations
(The British University in Dubai (BUiD), 2019) Hanadi, Al Suwaidi
Digital forensics deals with the use of tools and techniques to preserve, identify, extract, document, and interpret any data stored or transmitted using a digital system. It is usually used to help support or refute a theory, for the occurrence of an offense or crime, or it might indicate intent or alibi. There are many challenges when it comes to the forensics discipline of digital evidence, and the sheer amount of data found on modern digital devices is one of them. In today’s society, it became the norm for one individual to own multiple digital devices with large storage capacities. If that individual was part of a group of people accused of a certain crime, the end result would be a large amount of data, possibly in Terabytes. Furthermore, such data would usually need to be investigated for evidence in a limited window of time. Digital forensic laboratories that rely on traditional forensic tools usually lack the resources required to handle the size of data found on digital devices today. The work presented in this thesis can be seen as a step forward into enhancing digital forensics investigations by optimizing the investigator’s relevancy feedback. The study proposes a framework that integrates different text processing and mining techniques to assist the examiner reach useful information faster. The framework has been implemented and evaluated using a real world crime dataset of Arabic text. A Proof-of-Concept implementation was evaluated by experienced senior digital forensics examiners. The results showed a good improvement in the average recall-precision rates and a reduction of the required time to complete the tasks by 53% over the time spent using traditional tools.
Neural Machine Translation for Arabic Language
(The British University in Dubai (BUiD), 2019-07) Alkhatib, Manar
Translating the Arabic Language into other languages engenders multiple linguistic problems, as no two languages can match, either in the meaning given to the conforming symbols or in the ways in which such symbols are arranged in phrases and sentences. Lexical, syntactic and semantic problems arise when translating the meaning of Arabic words into English. Machine translation (MT) into morphologically rich languages (MRL) poses many challenges, from handling a complex and rich vocabulary, to designing adequate MT metrics that take morphology into consideration. The task of recognizing and generating paraphrases is an essential component in many Arabic natural language processing (NLP) applications. A well-established machine translation approach for automatically extracting paraphrases, leverages bilingual corpora to find the equivalent meaning of phrases in a single language, is performed by "pivoting" over a shared translation in another language. Neural machine translation has recently become a viable alternative approach to the more widely-used statistical machine translation. In this thesis, we revisit bilingual pivoting in the context of neural machine translation and present a paraphrasing model based mainly on neural networks. The thesis we present also, highlights the key challenges for Arabic language translation into English, and Arabic. Experimental results across datasets confirm that neural paraphrases significantly outperform those obtained with statistical machine translation, and indicate high similarity correlation between our model and human translation, making our model attractive for real-world deployment.
An Omnichannel Digital Banking Platform For Smart City Services: UAE Case Study
(The British University in Dubai (BUiD), 2019-09) Al Nuaimi, Maitha
The main aim of the research is to examine the omnichannel digital banking platforms within the UAE and how banking sector in UAE is providing smart service for smart cities. Digital banking and financial technology are taking the world at the next level by storm and with constant advances in technology and developments in internet and mobile connectivity; the revolution of online banking is becoming a reality. The proposed study uses mixed research methods i.e. quantitative and qualitative, with key instruments being questionnaires, interviews, observation, and case design for data collection. Mixed research methods refer to the research approaches where the researcher collect and analyses the study data for quantitatively and qualitatively in the same study. This thesis addresses the proposed conceptual framework of the omnichannel banking that will fill the gap between the current digital banking services and customer need. Modelling and evaluating the omnichannel banking platform architecture design has been performed in chapter five, this chapter will further introduce simulation and automation software i.e. Arena, which will be used to demonstrate the facilities and capabilities of discrete event simulation tool (Arena Simulation 2019) by building the operational process of the omnichannel digital banking platform. Arena software is developed by Rockwell Automation, uses the SIMAN processor and simulation language on Microsoft Windows platforms. It provides an integrated environment for building simulation models for a wide variety of applications as well as provides enhancements in optimisation, animation, and modelling processes with big data. Through the analysis of the framework, the study highlighted the interoperation between system layers within the framework with diverse roles performed by a government department such as Abu Dhabi Globe Mark and Abu Dhabi Sandbox and others. This phenomenon of traditional banks being willing to work with and through FinTech companies has opened up an avenue through which the UAE government can unite its banking sector. The research proposed an alternative digital banking solution that delivers frictionless omnichannel banking experience and allows customers to enjoy a seamless, secure, smart lifestyle and personalised service across every touchpoint by smart device at any channel and anywhere in the UAE.
A Digital DNA Sequencing Engine for Ransomware Analysis using a Machine Learning Network
(The British University in Dubai (BUiD), 2020-02) KHAN, FIROZ
The research work proposes a novel detection mechanism for ransomware using machine learning approach using Digital DNA sequencing. The proposed work contains three significant phases: Preprocessing and Feature Selection, DNA Sequence Generation and Ransomware Detection. In the first phase, data preprocessing and feature selection technique is applied to the collected dataset. The preprocessing of data includes remove missing value records and remove columns that have a negligible impact. The feature selection uses Grey Wolf Optimisation and Binary Search algorithms for choosing the best features out of the dataset. In the DNA Sequence generation phase uses design constraints of DNA sequence and k-mer frequency vector. A newly collected dataset after feature selection is used to generate the DNA sequence. In the final phase, the new dataset is trained using active learning concept, and the test data is generated using a random DNA sequence method. The data is finally classified as either ransomware or goodware using the learning methodologies. The results are found to be promising and reconfirm the fact that the developed method has efficiently detected ransomware when compared to other methods. The thesis concludes by a discussion of future work to advance the proposed method and future directions of research on the use of Digital DNA sequencing engine for general malware detection.
Integration of Artificial Intelligence in E-Procurement of the Hospitality Industry: A Case Study in the UAE
(The British University in Dubai (BUiD), 2020-05) Mathew, Elezabeth
The hospitality industry is growing at an increasingly fast pace across the world which results in accumulating a large amount of data, including employee details, property details, purchase details, vendor details, and so on. The industry is yet to fully benefit from these big data by applying Machine Learning (ML) and Artificial Intelligence (AI). The data has not been investigated to the extent that such analysis can support decision-making or revenue/budget forecasting. The data analytics maturity model is used as the conceptual model for evaluating both data analytics and data governance in this research. In this paper, the author has explored the data and produced some useful visual reports, which are beneficial for top management, as the results provide additional information about the inventoried data by applying ML. Demand forecasting is done using deep learning techniques. Long short-term memory (LSTM) is used to find the demand forecasting of spend and quantity using time lags. The research proposes an extended framework for integrating AI within the e-procurement of the hospitality industry. The AI integrated technologies will enable stakeholders of the industry to be interoperable with all the providers and sub-providers to obtain information easily and efficiently to identify the best solution for their requirements. The proposed framework of integrating AI in the conceptual framework could be used by medium to large enterprises for interoperability, interconnectivity and to take optimum decisions. This paper has uses six ML methods to check the accuracy scoring of the predicted duration of purchase. The duration is predicted using feature variables, including recent purchases, frequency of purchases, spend per purchase, days between the last three purchases, and mean and standard deviation of the difference between purchase days. Logistic Regression, XGBoost, and Naïve Bayes models have proven to be useful for this kind of study where three different scenarios are drawn. Other major results of the research include an answer to what to buy when to buy and how much to buy using demand forecasting for the e-procurement in the hospitality industry. The novel LSTM time series algorithm proved to work best for demand forecasting. Various descriptive, diagnostic, predictive, and prescriptive analysis is done on the e-procurement data. The deep learning model developed can perform thousands of routine and, repetitive tasks within a fairly short period compared to what it would take for a human being without any compromise on the quality of work. Finally, an interview with a subject matter expert is done to evaluate the result and confirm the importance of the study. A survey is also conducted with people involved in the procurement process as part of triangulation. The survey revealed 92% of participants agreed that having an integrated e-procurement framework is very important for the hospitality industry. The integration of AI and ML in e-procurement will revolutionise the hospitality industry.
Telemedicine in Practice: A Sociotechnical Analysis in the United Arab Emirates (UAE)
(The British University in Dubai (BUiD), 2020-06) Abdool, Shaikha
Telemedicine technology means providing healthcare services by utilizing telecommunication tools without being physically in the same location. The technology is new in the region although it is not the case worldwide and there are gaps that need to be filled in related to it. This research aimed to conduct a thorough sociotechnical analysis of telemedicine in a realistic environment using a large sample of subjects. Mixed methodology was followed (quantitatively and qualitatively). The sample size was randomly drawn from the UAE population. The results were in the form of statistical outputs attained from a proven and well-known model and theory [Technology Acceptance Model (TAM) and Diffusion Of Innovations (DOI) Theory]. Analysis and findings indicated that UAE is ready for telemedicine with few enhancements to be made. This research can be said as the first one in the UAE and one of the few in the region that examined telemedicine based on sociotechnical analysis and at the same time applied TAM and DOI Theory on diverse categories of subjects. Also, several hypotheses were tested within the UAE context. Additionally, it would enable decision-makers and healthcare organizations to identify telemedicine's current status in the UAE, demand and acceptance level.
Transforming Towards Secure Global Trade for Customs Administrations Powered by Blockchain
(The British University in Dubai (BUiD), 2020-06) Abunqira, Hussam
As part of the international trade supply chain, Customs authorities act as the gatekeeper protecting the society and the economy. The trade supply chain involves several participants each performs its task based on the documents that are provided by the other participant in the trade supply chain. For instance, the customs officials process the customs declaration submitted by the broker and then send the results to the next participant. The customs authorities need to perform an accurate risk assessment to ensure that protection of society and trade are not impacted. The verification and risk assessment are costly processes. The isolation between the participants in the trade supply chain impacts the efficiency of the current international trade supply model. In this work, a blockchain-based solution with a plugin to empower the solution with risk assessment capabilities is proposed. To build this solution, a proof of concept (PoC) approach is followed using the IBM Hyperledger fabric and Python programming language. The participants of this international trade process are identified. Then, the detailed process, activities, assets, transactions that are performed by each participant are analyzed. After that, a solution architecture is designed followed by building the smart contracts and building the PoC. This computational model ensures secure transactions, traceable transactions, and an immutable data communication model for better coordination among the entities along the supply chain. To further enhance the blockchain solution, two models are proposed to provide Customs authority with online risk assessment capabilities; distributed risk assessment method and a hybrid risk assessment method that consists of distributed and centralized risk assessment processes. The real data used in this work was obtained from Dubai Customs and contains shipment declaration applications. This labelled data is used to evaluate two models. The first method reported significant results that can provide classification with 83% in terms of accuracy. While, the accuracy in the extended work for the first method achieved a higher accuracy of 92%. This work addresses important issues related to security and risk assessment and provide powerful methods that complement the risk assessments performed at the customs authority by providing feedback from the early stage of risk analysis. كجزء من سلسلة توريد التجارة الدولية، تعمل سلطات الجمارك بمثابة حارس يحمي المجتمع والاقتصاد. تتضمن سلسلة التوريد التجارية عدة مشاركين يؤدون كل منهم مهمته بناءً على المستندات التي يقدمها المشارك الآخر في سلسلة التوريد التجارية. على سبيل المثال، يقوم موظفو الجمارك بمعالجة البيان الجمركي المقدم من قبل الوسيط ومن ثم إرسال النتائج إلى المشارك التالي. تحتاج السلطات الجمركية إلى إجراء تقييم دقيق للمخاطر لضمان عدم التأثير على حماية المجتمع والتجارة. تعتبر عمليات التحقق وتقييم المخاطر عمليات مكلفة على السلطات الجمركية. تؤثر العزلة بين المشاركين في سلسلة الإمداد التجاري على كفاءة نموذج الإمداد التجاري الدولي الحالي. في هذا العمل، يُقترح حل بالاعتماد على تقنية البلوك تشين ع مع مكون إضافي لتمكين الحل بقدرات تقييم المخاطر. لبناء هذا الحل، يتم اتباع نهج الدليل والنموذج التجريبي للمفهوم باستخدام نسيج اي بي ام هيبرلدجر ولغة البرمجة بايثون. تم تحديد المشاركين في عملية التجارة الدولية هذه. بعد ذلك، يتم تحليل تفاصيل العمليات والأنشطة والأصول والمعاملات التي يقوم بها كل مشارك في السلسلة. بعد ذلك، يتم تصميم هندسة الحلول متبوعة ببناء العقود الذكية وبناء النموذج التجريبي. يضمن هذا الحل المعاملات الآمنة والمعاملات التي يمكن تتبعها ونموذج اتصال البيانات غير القابل للتغيير لتحسين التنسيق بين الكيانات على طول سلسلة التوريد. لزيادة تعزيز حل البلوك تشين، تم بناء نموذجان لتزويد السلطات الجمركية بقدرات تقييم المخاطر بشكل آني؛ طريقة تقييم المخاطر الموزعة وطريقة تقييم المخاطر المختلطة التي تتكون من عمليات تقييم المخاطر الموزعة والمركزية. يتم استخدام هذه البيانات لتقييم أداء النموذجين المقترحين في هذا العمل. حققت الطريقة الأولى نتائج مهمة يمكن أن توفر تصنيفًا بنسبة 83٪ من حيث الدقة في المتوسط. بينما حققت الطريقة الثانية نتائج أفضل بدقة وصلت إلى 92٪. يتناول هذا العمل قضايا مهمة تتعلق بالأمن وتقييم المخاطر ويوفر طرقًا قوية تكمل تقييمات المخاطر التي يتم إجراؤها في مصلحة الجمارك من خلال توفير التغذية المرتدة من المرحلة المبكرة لتحليل المخاطر.
Data Analytics: Adaptive Network-based Fuzzy Inference System for prediction of computer science graduates’ employability
(The British University in Dubai (BUiD), 2020-09) Khadragy, Saada
The increased amount of data generated in the world of today in all fields is considered to be an indicator for future predictions. In recent decades, in any field and as a result of developments in information technology, a huge amount of data has been provided from the educational field, by which students’ Employability Prediction has become a main concern for higher education institutions. The question of employability has become a critical consideration not only for graduates but for the educational institutions themselves. This research study compares a number of classifiers to determine the effective classifier that accurately and efficiently categorizes CS and IT graduates into employed, unemployed, or other, and predict the future employability of CS and IT students in Jordan. For this purpose, an Adaptive Network Fuzzy Inference System (ANFIS) is applied in this research study. The data of 1095 CS and IT graduates was obtained from three universities in Jordan. This data was collected through a set of tracer studies that were carried out by these universities. ANFIS, Decision Tree, SVM, MLP, and Naïve Bayes classifiers were applied in order to find the classifier with the highest accuracy and efficiency. The final outcomes showed that ANFIS has the highest accuracy, with a percentage of 94% accuracy for its predictions. A set of recommendations is presented by the researcher according to the most effective factors that influence the CS and IT employment market in the Middle East. The researcher suggests for the ministries of higher education to focus on developing the CS and IT students’ programming skills and communication skills, which emerged as essential for increasing CS and IT students’ employment prospects. affecting the employment market for CS and IT.
Towards Building a Secure Blockchain-Based Architecture for Internet of Things (IoT)
(The British University in Dubai (BUiD), 2020-10) Pavithran, Deepa
IoT (Internet of Things) devices usually generate a large amount of data shared with a centralized cloud to provide various services. Traditional IoT architecture is heavily centralized, where data stored in a cloud environment, is prone to several kinds of threats. Blockchain is a very promising technology that spans many use-cases other than cryptocurrencies. For example, its implementation in the Internet of Things based networks (IoT) is still unclear and demands further research. The traditional adoption of the blockchain protocol for Bitcoin is common but it cannot be used for IoT because Bitcoin is a payment system, whereas the IoT eco-system has a different architecture. Implementing blockchain for IoT may still impose a variety of challenges. In this thesis, we proposed an architecture for the use of blockchain in event-driven IoT. In particular, we identified the key components along with their design considerations and challenges to consider while creating the blockchain architecture for IoT. We also defined gaps that hinder creating a secure blockchain framework for IoT. Various literatures have proposed blockchain architectures for IoT; however, most of them are applicable to use-cases related to smart homes and healthcare. In addition, we identified that the existing architectures have additional overhead of key management. Hence, we proposed a privacy-preserving blockchain architecture for Traffic Speed radars using Hierarchical Identity Based Encryption (HIBE). The proposed architecture uses edge and cloudlet computing paradigm as well as HIBE to preserve privacy. The performance of the proposed architecture is evaluated by conducting extensive experiments. We created the blockchain network using Ethereum and evaluated the system performance. Network performance was evaluated by simulating the network using Contiki OS. Finally, we analyzed the security of the scheme through theoretical analysis and threat-modelling tool that considers the existence of a malicious adversary.
Toward National Unified Medical Records (NUMR) and the Application of Nationwide Disease Registry
(The British University in Dubai (BUiD), 2021-01) Harbi, Alya
Technology in healthcare has evolved, however, till this date many healthcare providers find it difficult to provide their services as intended as a result of fragmented systems and scattered data. The challenges are noticeable especially with the rapid population growth which demanded software engineering and state of art solution to be able to handle different constraints. Although couple of countries started to implement nationwide electronic systems that are interoperable, none have completely finalized the program yet. United Arab Emirates (UAE) started toward this initiative to integrate the different systems in healthcare whether public or private. In addition to that, managing the burden of diseases is becoming uncontrollable and National Unified Medical Record (NUMR) is a starting point toward proper management to raise the healthcare quality and cut the cost. The aim of this study is to set new directions toward establishing NUMR and its applications of nationwide disease registry and assess the current situations and needs to be able to establish a proper mechanism and standards for UAE and other countries to benefits from, as well as study the application of disease registry and how we can utilize the concept of data mining, and business intelligence for better nationwide population management. Having NUMR will facilitate having proper nationwide disease registry that would enable analytics and prediction for better management. This study will bring great benefits for all countries that are going toward nationwide and interoperable healthcare platform. Moreover, it should be mentioned that there are limited nationwide disease registries worldwide especially for cardiology and diabetes, making it difficult to strategize the prevention programs in these field. Hence, it is very crucial to study the standards and mechanisms with respect to this field in order to provide lessons learned from other countries having a similar direction. The future of implementation of NUMR in UAE is promising. Our findings offer beneficial guidelines for consideration in implementing NUMR system across UAE and also help in the drive to improve healthcare systems nationally.
Artificial Intelligence Frameworks for Sentiment Variations’ Reasoning and Emerging Topic Detection
(The British University in Dubai (BUiD), 2021-07) ALATTAR, FUAD ABDELWAHAB ABDELQADER
Utilizing Sentiment Analysis techniques to monitor public opinions on social media has been an essential yet challenging task in the field of Artificial Intelligence (AI). Many studies were conducted during the last two decades to help users tracking public sentiments about entities, products, events, or other targets. However, these techniques focus on extracting overall positive/negative/neutral polarity of texts without identifying the main reasons for extracted sentiments. This thesis contributes to the very few studies that took one step ahead by developing novel models to understand what causes sentiment changes over time. Obviously, identifying main reasons for public reactions is valuable to decision-makers so that they can take necessary actions in a timely manner. To develop our approach, we first examined existing Sentiment Reason Mining methods to identify their limitations, then we introduced our Filtered Latent Dirichlet Allocation (Filtered-LDA) Model that overcomes major deficiencies of base methods. This model can be used for multiple applications, including detection of new research trends from large sets of scientific papers, discovery of hot topics on social media, comparison of customer reviews for two products to identify their strong/weak aspects, and our focus topic of interpreting public sentiment variations. The Filtered-LDA Model utilizes a novel Emerging Topic Detection technique for which we developed multiple AI frameworks. It emulates human approach for discovering new topics from a large set of documents. A human would first skim through all old and new documents to isolate the new ones that may contain Emerging Topics. These clustered documents are then analyzed to identify the high-frequency emerging topics. With this simple method, the impact of clustering errors is significantly reduced as the wrongly clustered documents do not usually contain main keywords of high-frequency emerging topics. Furthermore, the new frameworks introduce measures to genuinely reduce chances of detecting old topics and visualize candidate reasons online. Given that some social media platforms, like twitter, use short-text documents, we first compared accuracies of state-of-the-art Sentiment Analysis classifiers to select the best performer for short-texts. Subsequently, the selected classifier is applied on a real-life large Twitter dataset, which includes around two million tweets, to extract positive/negative/neutral sentiments. The Filtered-LDA Model is tested first on a Ground Truth dataset to validate that it outperforms baseline models, then it is finally applied on the large Twitter dataset to automatically conclude main reasons for sentiment variations
Using Mobile Technology for Coordinating Educational Plans and Supporting Decision Making Through Reinforcement Learning in Inclusive Settings
(The British University in Dubai (BUiD), 2021-07) Siyam, Nur
Learners with special education needs and disabilities (SEND) require attention from a large set of a care team that includes parents, teachers, specialists, therapists, and doctors. Good coordination among these stakeholders leads to increased behavioural and academic progress for the learners. However, achieving good coordination in such setting is a challenging task. This is due to the different tasks each stakeholder is attempting, the different backgrounds of the stakeholders, and the lack of face-to-face interaction among them. I call this the intervention coordination problem (ICP). Furthermore, learners with SEND, and specially learners with autism spectrum disorder (ASD), usually show little interest in academic activities and may display disruptive behaviour when assigned certain tasks. Research indicates that selecting a good motivational variable during interventions improves behavioural and academic performance. I refer to this problem as the motivator selection problem (MSP). This work aims to exploit mobile and artificial intelligence (AI) technologies in order to address the above two problems. Toward this aim, this study follows a design science research approach to develop the IEP-Connect app. This mobile app uses the Individualized Education Program (IEP) as the foundation for coordinating the efforts and supporting the decision-making process of the different personnel who are involved in the IEP of a child with special needs. The proposed work presents four significant contributions, namely identifying the key design principles to inform the design of a coordination mobile app for special education, developing and implementing the IEP-Connect mobile app, modelling the selection of a motivator as a Markov Decision Process (MDP), and proposing a Reinforcement Learning (RL) framework to recommend a motivator to be used with students with SEND in a given learning setting. To evaluate the effectiveness of the proposed mobile app and RL framework, a series of studies based on participatory design research, mixed-methods usability evaluation, and pre-test/post-test quasi-experimental research methodology were conducted. The evaluation of the app focused on students with ASD as their learning requires sharing information from different distributed sources. Results from the usability questionnaires, interviews, and log data revealed that the app has good usability and that participants were satisfied with the use of the app for recording and sharing IEP information. Moreover, evaluations and data analysis have shown the validity of the proposed RL framework through improving the intervention effectiveness and users’ satisfaction. The implementation of this work provides insights into the future development of technology tools that facilitate information sharing between special education teachers and other stakeholders involved in the intervention of children with special education needs. Moreover, this work expands the interdisciplinary research of machine learning and special education by presenting promising preliminary results for therapy decision-making support.
Customs Trade Facilitation and Compliance for Ecommerce using Blockchain and Data Mining
(The British University in Dubai (BUiD), 2021-07) Alqaryouti, Omar
Electronic commerce (ecommerce) has penetrated every society, organization, business and household and changed consumers’ habits. It enabled businesses in some nations to trade beyond local borders and reach global proportions. This led to the explosive growth in demands for ecommerce platforms over the last few years and the increased popularity in cross-border trade interactions. The popularity became more evident in times of crisis such as COVID-19 for critical food and medical supplies and products. However, it was disrupted in other markets due to societies going on lockdown, which were further accentuated by borders being shut down. Ecommerce cross-border trade is impacted by regulations of each country. The challenges facing global trade and Customs administrations in particular cover many dimensions. Customs being tasked with protecting society and the smooth trade flow can no longer rely on traditional practices. A coordinated and consorted effort is required to disrupt illegitimate activities and support the mission of Customs. This work first aims to determine factors that drive the adoption of Blockchain technology. Blockchain is characterized for providing visibility, integrity, provenance and immutability across participants through the shared ledger capabilities. Therefore, blockchain technology is used in this study to build a framework to enhance trade facilitation and increase compliance while eliminating risks. This framework will provide advance access to information from various sources and will enable real-time discovery of risks. Accordingly, two off-chain clustering algorithms are proposed to determine value manipulation in ecommerce transactions and increase the efficiency of Customs Audit process. The Software Development Life Cycle (SDLC) methodology is adopted to build the framework. An integrated web application is developed to mock up the end-to-end process in ecommerce. Additionally, the Cross Industry Standard Process for Data Mining (CRISP-DM) methodology is employed for modelling the two proposed clustering algorithms to identify transactional risks. The usability of the proposed framework is evaluated using the System Usability Scale (SUS) resulting in overall high acceptability levels across all users. Furthermore, accuracy measures are used to evaluate performance of the proposed clustering algorithms, reaching 86% for valuation assessment and 87% for risk identification in customs audit. The proposed framework will revolutionize the way trade supply chain is handled. It will create a shift from reactive limited visibility to proactive full visibility mode and properly manage various scenarios such as the current health hurdles and any future challenges lurching around.
A Cybersecurity Skills Performance Dashboard (CSPD): The Use of a Technical Gamification Simulation Platform (TGSP) to Address Cybersecurity Skills Gap in the UAE
(The British University in Dubai (BUiD), 2021-10) BAZARGAN, FATMA AHMAD
Cybersecurity capacity building has been one of the main pillars of the UAE cybersecurity strategy to shorten the cybersecurity skills gap in the UAE. There have been several capacity building initiatives introduced by the UAE government to upscale the hands-on technical skills amongst cybersecurity professionals in the UAE. However, there has not been any mechanism nor a platform in place to either measure the scale of the skills gap that currently exist and needs to be addressed nor any measurement tool to provide visibility into the effectiveness of the capacity building initiatives introduced. Furthermore, there have been a plethora of undergraduate cybersecurity academic degree programs taught in various recognized educational institutions across the UAE. However, the shortage of cybersecurity practitioners globally and locally has never been more acute. Hence, there is a crucial need to introduce a UAE nation-wide cybersecurity skills performance dashboard that shall provide the required visibility into the scale of the skills gap that currently exists, hands-on technical skills that is currently available, and those skills that need to be developed and trained. The Cybersecurity Skills Performance Dashboard (CSPD) shall provide the true measurement of the current existent skills gap shortage in the UAE to enable the concerned entities to introduce the needed capacity building initiatives to shorten the skills gap. In addition, there is a heightened need to introduce new ways of instructing cybersecurity academic program to upscale the hands-on technical cybersecurity skills amongst university undergraduate students and thus improve a variety of technical skills such as digital forensics, incident response, reverse engineering, cryptography, penetration testing, and many more. This research study aims to design and develop the Cybersecurity Skills Performance Dashboard (CSPD) as a measurement tool for capacity building of cybersecurity professionals. It records and provides a true assessment of the upscale of hands-on technical cybersecurity skills of cybersecurity professionals. This is fulfilled through the introduction of new ways to the current traditional academic teaching model through the use of the Technical Gamification Simulation Platform (TGSP) to shorten the cybersecurity skills gap problem in the United Arab Emirates. Integrating the TGSP within the fabric of the undergraduate cybersecurity academic programs will produce market-ready professionals to fill in the active cybersecurity job postings in the United Arab Emirates or globally. This study employs a qualitative grounded theory research design to understand and explore how the use of the technical gamification simulation platform will enhance the hands-on technical skills amongst undergraduate students. Purposeful sampling was used to mindfully select the sample for this research work from a pool of 3rd and 4th-year undergraduate students majoring in cybersecurity from various renowned universities across the United Arab Emirates. This research work that applied to the selected participants consisted of three phases: assess, train, and perform. The data was collected from all the three phases. The first phase, the assessment phase, was in the form of responses to one-on-one interview questions. The second phase, which was the training phase, was in the form of results collected from the cybersecurity skills performance dashboard that was designed and developed by the researcher. Finally, the performance phase involved results that were in the form of responses to the post-training survey questionnaire by the participants in the study. Analysis and findings indicated that the undergraduate students found the technical gamification simulation platform an invaluable tool to upscale their hands-on technical skills because it provided them with a simulated real-world environment whilst using real-world tools to complete the technical scenario in a structured manner. This research work is considered to be the first to be conducted in the United Arab Emirates that examined providing undergraduate students majoring in cybersecurity with access to the technical gamification simulation platform for a duration of 8-weeks. Also, it was able to draw invaluable information on the effectiveness of introducing the training platform alongside the academic curriculum to upscale the hands-on technical skills. Several research questions were tested as part of this research work within the U.A.E. context. Finally, this thesis delivers the design and development of the cybersecurity skills performance dashboard (CSPD) as a measurement tool for capacity building of cybersecurity professionals and a contribution to this research study. The CSPD captures and displays the scores of the students as they complete a given technical scenario or challenge in the technical gamification simulation platform. Hence, the dashboard provides a true assessment of the cybersecurity undergraduate’s technical hands-on skills. The CSPD provides the required means to various entities (i.e., government entities, private sector, business owners, etc.) to approach the cybersecurity professional based on the skills they most need through the use of CSPD. The beneficiaries of this dashboard include entities in the UAE and worldwide. In addition, the dashboard can be used as a reference by the U.A.E. cybersecurity policymakers to understand the cybersecurity skills that are widely available in the United Arab Emirates and the skills that further need to be trained and developed. Hence, being able to tailor the capacity building campaigns on factual data. Also, the dashboard can act as a nationwide cybersecurity skills performance database/repository in the United Arab Emirates to understand the current availability of cybersecurity professionals and talents. Although the dashboard in this research work is applied to the field of cybersecurity. However, it can be generalized and applied to any other field of expertise to gain invaluable insights into the skills gap.
Towards the development of an integrated model for examining the determinants affecting the use of Queue Management Solutions in Healthcare
(The British University in Dubai (BUiD), 2021-10) ALQUDAH, ADI AHMAD ALI
Over the years, long queues were recognized as a common problem in the healthcare domain, and it is significant to manage them for patients' safety and overall satisfaction. Prolonged queues in healthcare organizations can produce high levels of distraction for the employees instead of focusing on their original activities. As a solution, queue management technologies became more popular in healthcare organizations to solve queue issues, gather data, and generate statistical reports for the current and future flow trends. The adoption of new technologies in healthcare has been turned into a must rather than a luxury due to the rapid changes of technology advancements and people's needs. In general, the success of technology adoption in healthcare relies on the behavior of end-users towards accepting and using the technology. Queue management solutions (QMS) face resistance from users, and their acceptance is not assured. A quick review of the literature showed a lack of studies that discuss the acceptance of QMS. Therefore, this research has three main objectives. First, conducting a systematic review to address the research gaps in the existing literature and understand the extensively utilized acceptance models in healthcare and their related constructs. The systematic review included empirical studies published between January 2010 and December 2019 on the topic of technology acceptance in healthcare. A total of 1,768 studies have been reviewed, and 142 studies were found eligible and considered in the analysis. Through the analysis, the technology acceptance model (TAM) and the Unified theory of acceptance and use of technology (UTAUT) have been recognized as the prevailing models in technology acceptance in healthcare. Additionally, 11 factors from various acceptance models were found extensively investigated to understand and analyze the technology acceptance in the healthcare domain. These factors include Performance Expectancy, Effort Expectancy, Social Influence, Facilitating Conditions, Attitude Towards, Behavioral Intention, Use Behavior, Computer Anxiety, Computer Self-Efficacy, Innovativeness, and Trust. In line with the gaps found in the literature, this research has presented a case study for the currently implemented queue management solution (QMS) in the out-patient department (OPD) in a healthcare organization in UAE. The research discussed the suggested business and technical optimizations that include integrating the QMS with the electronic medical records solution (EMR). The integration was achieved using Health Level Seven (HL7) integration standards, including the exchange of custom-designed XML and HL7 messages. The goal of the integration was to implement a novel tool for patient’s self-check-in and enhance the ease of use and usefulness of QMS. As a pilot implementation, the feasibility of the newly implemented tool was assessed through a simulation experiment in the internal medicine clinic over two different weeks (control and intervention). A total of 127 appointments were identified as eligible and included in the study. The patient’s journey was split into five stages: identification, wait to triage, triage process, wait to treatment, and treatment process. The results revealed that the new tool is beneficial, and the median times to finish the processes within the patient’s journey have significantly decreased. To evaluate the use of the enhanced QMS, this research develops an integrated model based on the integration of various constructs extracted from different theoretical models, including the UTAUT, TAM, and social cognitive theory (SCT) along with trust and innovativeness as external factors. The model was empirically validated using the partial least squares-structural equation modelling (PLS-SEM) approach based on data collected through a questionnaire survey from 242 healthcare professionals. In brief, the results exposed that the suggested model can be helpful to explore the acceptance of information technologies in healthcare. The model has explained 66.5% of the total variance in the behavioral intention to use the enhanced QMS, along with 59.3% of the total variance for the actual use of the enhanced QMS. The results indicated that innovativeness and computer self-efficacy factors have a positive significant influence on the effort expectancy of professionals to use QMS. The computer anxiety factor has a negative significant influence on the effort expectancy to use QMS. Besides, trust and computer self-efficacy factors have a positive significant influence on the performance expectancy when using QMS. Other results, related implications, limitations, along with future research were also clarified and discussed.
Dynamic Cyber Resilience of Interdependent Critical Information Infrastructures
(The British University in Dubai (BUiD), 2021-12) JUMA, MAZEN GHAZI
We are becoming progressively reliant on the Critical Information Infrastructures (CIIs) to provide essential services in our daily lives, such as telecommunications, energy facilities, financial systems, and power grids. These interdependent infrastructures form one coupled heterogeneous network that qualifies them to deliver new cyber roles and crucial tasks not achievable before in numerous domains worldwide. The CIIs have to deal with sophisticated cyber risks resulting from cyber vulnerabilities of their scale-free topology targeted by different cyber threats like concurrent and consecutive cyberattacks to the expected failure cause of the single hub nodes in their decentralized structures lead to cascading and escalating cyber failures that interrupt the vital services and considerable losses in modern societies with vast negative impacts on the economy and national security. Therefore, the research community has attempted over the last decade to pay attention to address the cyber protection gaps of CIIs in many studies by enhancing the existing standard solutions based on cyber trustfulness engineering, for example, distance-vector, link-state, and path-rule solutions, or developing new ones, but still missing one comprehensive technology solution. The required solution has to bridge the current literature gaps by shifting the paradigm of cyber CIIs protection properly towards dynamic cyber resilience to balance proactive and reactive perspectives at theoretical and empirical levels. Besides, it also needs to understand, analyze, evaluate, and optimize the set of dynamic cyber resilience capabilities consisting of withstanding, mitigation, recovery, and normalization. These capabilities support the various states of the typical cycle of dynamic cyber resilience, including threshold, bottom, and equilibrium states to increase CIIs robustness against cyberattacks, absorb frequent cyber disturbances that occurred, recover quickly from cyber failures, and re-establish their acceptable performance levels within appropriate timeframe. This thesis presents the novel proposed solution of dynamic cyber resilience using cyber zero-trust engineering for the first time to cope with highlighted shortcomings of the standard solutions, overcome the single hub node failure and enhance dynamic cyber resilience capabilities of interdependent CII networks against concurrent and consecutive cyberattacks to deliver their core services continuously. The research goal of this thesis was accomplished by an iterative four-objective cycle through two phases: primary and optimization. In the primary phase, the novel conceptual framework of the proposed solution was developed based on four fundamental concepts: decentralized registry, delegated peers, consensus rules, and dynamic routing. The technology stack of the proposed solution was also implemented with four algorithms and eight protocols. The evaluation results of the proposed solution were compared to the results of standard solutions under different cyberattack scenarios using quantitative research methods involving computing simulations, emulation experiments, and analytical modeling. The optimization phase improved the conceptual framework by adding three new fundamental concepts: hubs coupling, encrypted transmission, and end-to-end service quality. The technology stack was also enhanced with three new algorithms and five protocols. The proposed solution was optimized using the iterative four-objective cycle based on previous primary phase results. Lastly, all results in both phases were analyzed and discussed, and the final findings of the thesis were interpreted. However, it can be concluded that the proposed solution failed to compete with other standard solutions in terms of dynamic cyber resilience capabilities and total resilience measurements during the primary phase. Nevertheless, the optimized solution achieved the optimal results compared to the standard solutions. Finally, study limitations and recommendations for future works represented the research outcomes and contributions.

Browse

Browsing Theses for Computer Science by Issue Date

Results Per Page

Sort Options