Thesis (IT & Engineering)

Permanent URI for this community

https://bspace.buid.ac.ae/handle/1234/814

Browse

Now showing 1 - 20 of 51

A Decision Modelling Approach for Perceived and Engaged Immersive Visual Interactive Applications on the Metaverse
(The British University in Dubai (BUiD), 2024-09) IBRAHIM, SAMAR; Dr Mostafa Al Emran
Many researchers have developed and implemented various immersive visual interactive applications that incorporate visualization and interaction techniques, support the visual construct and enhance exploration in the Metaverse. Benchmarking these applications is critical due to the absence of an ideal model, particularly given their varied development criteria. The multiple evaluations, significance, and the data variability of these criteria among various applications present challenges that necessitate using specific multicriteria decision-making (MCDM) methods. This study introduces a new decision modelling approach that extends the fuzzy-weighted zero inconsistency (FWZIC) method with the new Interval-Valued Fermatean Neutrosophic fuzzy sets (IVFN) and combines it with the extended ranking method, Više kriterijumska Optimization I compromise Rešenje (VIKOR) and Gray relational analysis (GRA). The modelling approach benchmarks the most perceived immersive visual interactive applications using the extended VIKOR-GRA method based on a decision matrix of 18 criteria and 29 alternatives for the four visualization scenarios. The new extended IVFN-FWZIC method weighs the criteria for benchmarking the optimal applications based on experts’ judgments. The results illustrate the effectiveness of the modelling approach and indicate that "spatial" and “haptics” are the most significant criteria in evaluating immersive visual interactive applications. The robustness and reliability of the results were validated and evaluated using sensitivity analysis, comparative analysis, and a systematic ranking process. This study offers a vision for decision-makers and stakeholders, contributing to improving visualization and exploration of the Metaverse.
Analyzing and Simulating Traffic Collision Data to Recommend Policy for Autonomous Taxi Deployment in Dubai
(The British University in Dubai (BUiD), 2023-12) MAHBOOB, MOHAMED
The adoption of appropriate and suitable Autonomous vehicles regulations and guidelines is one of the main challenges that governments and transportation decision makers are facing nowadays. Appropriate guidelines to operate autonomous vehicles successfully and to maximize their benefits is crucial for safe and seamless deployment. This research focuses on analyzing the key safety benefits of deploying autonomous taxis for traffic collision avoidance. The research also suggests and recommends policies and guidance to accelerate appropriate and safe autonomous vehicles deployment. The research aims at supporting policy makers and governments with the recommendations for safer deployment of autonomous taxi. The Al Muraqabat area was selected for the simulation model as it had a high frequency of collisions. Statistical analysis of taxi traffic collision data was conducted to identify the human factors that contribute to traffic collisions. The statistical model was developed using the SPSS software. Ten reasons for traffic collisions were studied and 76% of the traffic collisions were due to three reasons that were associated with human factors. Experience, Age and fatigue were identified as main causes of traffic collision which are associated with human drivers. The outcome of the statistical model was used to build a traffic simulation model using the Vissim traffic simulation Software. Seven scenarios were simulated which included a baseline model and three autonomous driving behavior scenarios that were simulated on both 100% and 50% penetration levels. When autonomous scenarios were simulated, the lowest number of traffic collisions occurred for the case of 100% normal driving behavior (367) which was 21% lower than baseline scenario. Policy analysis was used to identify gaps in the current legislations and exploring best practice globally. The interview questions were formulated based on the outcome of statistical analysis, simulation and legislation gaps. The thematic analysis was used to identify the experts’ ideas and thoughts using Nvivo software. Experts suggested focused on engaging the government and providing incentives to the private sector. Restudying urban planning, dedicated autonomous vehicles centers and developing smart infrastructure were the main recommendations. Revising the traffic and developing autonomous vehicles standard are critical for safe deployment.
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
Courtyards as passive design solution for school buildings in hot areas: UAE as a case study
(The British University in Dubai (BUiD), 2018-06) SALAMEH, MUNA MAHMOUD
The global concentration on green efficient schools is growing as schools represent a considerable sector in the built environment, which consumes a lot of energy to provide a standard level of thermal comfort for students. In the UAE, both private and public-school buildings are assumed to be a high energy consumption sector, in addition to universities, banks and shopping malls. Moreover, the energy consumption in schools seems to be encouraged rather than controlled, thus there is the potential for reducing the sector’s energy consumption. Traditional architecture adopted the courtyard design as a distinct form to create the core of houses and moderate the thermal conditions for the surrounding spaces, especially in hot climates. In most of the previous studies on the subject, courtyards were found to be related to houses or buildings in general, rather than educational institutions specifically, such as schools. This research aims to investigate the integration of a well-designed courtyard as a passive design strategy in buildings in the UAE to reduce the energy consumption required for cooling. In addition, the improvements in the thermal comfort conditions within the courtyards should translate to a more comfortable outdoor space for the students. This research adopted a qualitative approach based on case studies and computer simulations. The case studies were five present public schools’ buildings with different plan templates and different courtyard configurations; the schools are models 586, 596, KAT, UPA1 and finally UPA-fin. The computer analysis in this research was based on two software programs: ENVI-met software to evaluate changes in the schools’ microclimates due to the presence of courtyards and IESve software to calculate the energy consumption of the school buildings due to the changes of the microclimates affected by the courtyards. The thermal effect of the courtyards on the school buildings was investigated through two stages. The first stage discussed the orientation of the courtyard. The second stage investigated a range of courtyard configurations and designs through five phases, each focused on one of five relevant parameters which are: courtyard’s shape factor ratio (W/L ratio), courtyard’s area to built-up area (CA/BA ratio), courtyard’s outline shape, courtyard’s height (number of floors) and finally courtyard’s vegetation. There was third stage in this research that investigated the cooling loads for schools (case studies) in relation to the orientation and the design strategies. The cooling plant sensible load was investigated the beginning on specific dates and then it was investigated for the whole academic year. The outcomes of the research investigations concluded that the design and the properties of the courtyards can affect the indoor temperature of the school building, thus the cooling load. Moreover, the results of the computer simulation revealed that the school UPA-fin was the best school case with the optimum courtyards after adopting the following strategies 1- orientation to the north , 2-CA/BA ratio 20%, 3-square outline for the courtyards, 4-additional third floor on the east mass mainly 5- integrating vegetation in the courtyards, succeeded in reducing the Tin to 1.9 ˚C on 21st of September and 1.7 ˚C on 21st of March and that managed to reduce the cooling load by 19% on 21st of September and 27% on 21st of March compared to the basic UPA-fin to the north in phase one . The investigation of the annual cooling load after adopting only four strategies that included 1- orientation, 2-CA/BA ratio 20%, 3-square outline for the courtyards, 4-additional third floor on the east mass mainly and excluding the integration of vegetation, succeeded in reducing the cooling load by 16.5%compared to phase one UPA-fin basic to the north. The results showed that the optimum courtyard had the best predicted mean vote (PMV) performance also, as on 21st of September the max PMV reading for the poorest case of stage two equaled 4.35, which covered 48% of the courtyard’s area, while the max PMV reading for the best case of stage two (phase five) equaled 3.15 and covered 1.5% of the courtyard’s area with a reduction of about 1.2 on the PMV scale. On the other hand, on the 21st of March the max PMV reading for the poorest case of stage two equaled 3.0 and covered 48% of the courtyard’s area; while the max PMV reading for the best case equaled 1.9 and covered 1.5% of the courtyard’s area, with a reduction of about 1.1 according to the PMV scale. The research results revealed that the optimal design of the courtyard can reduce the temperature of the inner spaces of the school, thus it can reduce the cooling load for the school building in general. Moreover, it can improve the thermal comfort for the outdoor areas. The findings of this study will be important for architects, sustainable developers, educational developers, economic consultants and green buildings designers in UAE and in areas with similar climate to help them in designing green schools.
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.
Cyberbullying Detection in Arabic Text using Deep Learning
(The British University in Dubai (BUiD), 2023-03) ALBAYARI, REEM RAMADAN SA’ID; Professor Sherief Abdallah
In the new era of digital communications, cyberbullying is a significant concern for society. Cyberbullying involves the use of communication technology and data, including messages, photographs, and videos, to undertake aggressive negative actions to harm others. This practice has spread substantially due to rapid technological development and has gained significant attention in several domains involving data exchange, such as e-commerce, digital marketing, social media platforms, and others. Cyberbullying can negatively impact stakeholders, and can vary from psychological to pathological, such as self-isolation, depression, and anxiety potentially leading to suicide. Hence, detecting any act of cyberbullying in an automated manner will be helpful for stakeholders to prevent any unfortunate results from the victim’s perspective. If conducted automatically, rather than relying on human moderators, the process will be faster, enabling the early detection of cyberbullying before severe harm is caused. Data-driven approaches, such as machine learning (ML), particularly deep learning (DL), have shown promising results. DL approaches provide highly accurate predictive models for detecting cyberbullying. The first contribution of this thesis is conducting an in-depth meta-analysis of existing evaluation methods, classification techniques, and datasets related to ML for cyberbullying problems. The meta-analysis shows that ML approaches, particularly DL, have not been extensively studied for the Arabic text classification of cyberbullying. A potential reason for this research gap is the lack of Arabic-language repositories focusing on cyberbullying despite the large amount of Arabic text that can be extracted from Arabic social media platforms besides e-commerce and mobile applications. Consequently, I have designed and built a new Arabic text repository, the largest available, that can serve me and others in investigating various classifiers to deal with the issue of detecting cyberbullying. This repository contains 200,000 comments, 46,898 of which were annotated by three human annotators. First, the comments were classified as (positive/negative/neutral), and then the negative comments were further classified into two categories based on their level of negativity (toxic, bullying). The dialect for each comment was also added. This gives the dataset an advantage since it can be used for other purposes such as sentiment analysis and dialect identification, not just for cyberbullying detection. For the dataset to be regarded as a benchmark, Fleiss’s Kappa metric was adopted to measure the inter-annotator agreement (IAA), and the results show that the total Fleiss Kappa coefficient is = 0.869 with a p-value of 10-3, indicating near-perfect agreement among the three annotators. The application of DL to cyberbullying detection problems within Arabic text classification can be considered a novel approach due to the complexity of the problem and the tedious process involved, besides the scarcity of relevant research studies. Therefore, this study aims to evaluate several versions of Recurrent Neural Networks (RNNs) and Feedforward Neural Networks (FNNs) for detecting cyberbullying in the Arabic language. Although these algorithms are widely used in text classification and outperform the performance of classical classifiers, many have been extensively investigated in other domains such as sentiment analysis and dialect identification, as well as cyberbullying detection in English text. Hence, a comprehensive study focusing on Arabic cyberbullying can fill this gap in research. In this study, I conduct a performance evaluation and comparison for various DL algorithms (LSTM, GRU, LSTM-ATT, CNN-BLSTM, CNN-LSTM, CNN-BILSTM-LSTM, and LSTM-TCN) on different datasets of Arabic cyberbullying to obtain more precise and dependable findings. As a result of the models’ evaluation, a hybrid DL model is proposed that combines the best characteristics of the baseline models CNN, BLSTM and GRU for identifying cyberbullying. The proposed hybrid model improves the accuracy of all the studied datasets and can be integrated into different social media sites to automatically detect cyberbullying from Arabic social media posts. It has the potential to significantly reduce cyberbullying. Other results, related implications, and limitations, along with future research are also clarified and discussed.
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.
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.
A Decision Modelling Approach for Security Modules of Delegation Methods in Mobile Cloud Computing using Probabilistic Interval Neutrosophic Hesitant Fuzzy Set
(The British University in Dubai (BUiD), 2023-03) AL HANTOOBI, SENDEYAH
Mobile Cloud Computing (MCC) has become a pervasive technology that offers on-demand, flexible, and scalable computing resources to mobile devices. However, the security issues associated with MCC have become a major concern for users and organizations, leading to the development of various Security Modules. These modules typically use delegation methods that involve the transfer of data or operations from mobile devices to the cloud to perform the task at the best performance and security levels. Despite extensive attempts to design secure security modules of delegation in Mobile Cloud Computing (MCC), none of the existing modules possess all the necessary development attributes. Our analysis indicates that previous studies have not used security development attributes as evaluation criteria to compare and assess the available Security modules of delegation methods in MCC. However, Modeling these modules is critical and poses significant challenges in selecting the most secure security module. du to multicriteria, importance of data and data variation. To address this issue, this study proposes a Decision Modelling Approach for Security Modules of Delegation Methods in Mobile Cloud Computing using multi-criteria decision-making (MCDM) methods. The proposed approach involves the integration of Evaluation based on Distance from Average Solution (EDAS) method with fuzzy weighted with zero inconsistency (FWZIC) under Probabilistic Interval Neutrosophic Hesitant Fuzzy Set (PINHFS) environment. . The framework presented in this study involves two primary stages : the construction of decision matrices for Security Modules of delegation methods in MCC and the application of the PINHFS-FWZIC method to determine the weight of the security evaluation criteria. The EDAS method is then employed to modeling the Security Modules of delegation methods in MCC based on the formulated decision matrices and criteria weight. The validation and evaluation of the proposed framework were conducted through model validation and decision evaluation procedures. Model validation involved sensitivity analysis and systematic ranking procedures . The benchmarking checklist was used to compare the results of the proposed framework with the existing approaches. Based on the findings, it can be concluded that the proposed framework can efficiently weight the security criteria and successfully rank Security Modules of delegation methods in MCC. The PINHFS-FWZIC method effectively handled the uncertainty and hesitancy of the decision-makers in assigning weights to the evaluation criteria. Overall, the proposed framework provides a useful benchmark for evaluating other Security Modules of delegation methods in MCC. It can aid decision-makers in selecting the most secure MCC delegation method system by providing a comprehensive evaluation and Modeling of the available Security Modules.
Detection of Depression in Arabic Social Media: A Comparison of Traditional and Modern Machine Learning Algorithms
(The British University in Dubai (BUiD), 2023-12) ALSHEHHI, OMAR KHALID HAMAD; Professor Sherief Abdallah
This study aims to address the research gap in detecting depression from Arabic tweets using the PHQ-9 scale as a framework. The dataset collected was a set of 200,000 tweets from around 20,000 users. A team of psychologists and assistants used a user-based approach to label users as either depressed or not. The data labelling and annotation process involved a user-based evaluation of the tweets to label users as either depressed or not, based on the two target variables of depressed_binary and depressed_multi. Users with scores between 0 and 6 were categorized as not depressed in the depressed_binary variable, while those with scores above six were classified as depressed. For the depressed_multi variable, users with scores ranging from 0 to 2 were labelled as not depressed, scores from 3 to 6 indicated mild depression, scores from 7 to 9 indicated moderate depression and scores of 10 or above represented high depression. Four machine learning models were employed in this study: HGB (Histogram Gradient Boost), GRU (Gated Recurrent Units), LSTM (Long Short-Term Memory), and SVM (Support Vector Machines). The findings revealed that the older models exhibited strong performance in binary classification, while the new models demonstrated competitive results. Future research should focus on exploring and developing newer deep learning models, such as HGB and GRU models, to enhance the accuracy and performance of depression detection in Arabic tweets. Future studies should also investigate strategies to account for the influence of different Arabic dialects and incorporate Arabic colloquialisms in depression detection models.
Developing a Digital Trust Framework between Government and Private Sector in the Financial Sector
(The British University in Dubai (BUiD), 2023-07) AL SHAMSI, SUAAD SALEM YOUSEF; Professor Sherief Abdallah
COVID-19 accelerated the transformation to a digital society. It created a necessity for an ecosystem trusted by all parties to avail services, which requires identity to be verified and information to be exchanged. The trusted digital identity of individuals and organizations is a fundamental block in such an ecosystem. Services in critical domains such as finance, health and travel heavily rely on identity verification. This process is known as “Know Your Customer” (KYC). Despite the need for a digital service offering, regulators mandate the physical verification of individuals and their documents. This process is usually lengthy, inefficient, costly and inconvenient to the customer. It mandates the customer to visit each service provider at least once to conduct customer identification and verification prior to availing the service or obtaining digital credentials. Regulators requirements need to be identified and addressed in a digital mean which is accepted and trusted by all involved parties, service providers, customers, and document issuers, in order to transform KYC process to a digital process which is trusted and efficient. The physical identity of individuals must be mapped to a digital identity that can be trusted and verified by all service providers. The physical documents of individuals representing their identity or any claim they make about themselves or their ownership must be transformed into trusted and verifiable digital credentials. This would enable an end to end digital service offering without the need for customer to physically visit service providers for customer identification and verification. This paper develop a Digital Trust Framework between the government and private sector in the United Arab Emirates (UAE) that aims to enable service providers to offer an end to end digital service through the development of a unified trusted digital identity and credentials that eliminate the need for the initial physical identification and verification, and imporve the continuous KYC monitoring of the customer therefore improving the efficiency and the user experience, reducing the cost, and increasing the transparency of the KYC processes. The framework uses decentralized identity and verifiable credentials (VCs) as a layer on top of blockchain technology to address the challenges faced in KYC processes while adopting Privacy-by-Design principles. Hence, this research paper follows a design science research methodology (DSRM) as research method to develop the framework. The focus is on the financial sector in the UAE. The DSRM research method integrates existing theoretical knowledge and insights from industry practitioners obtained through semi-structured expert interviews. The proposed framework to imporve the KYC process was successfully implemented as prototype system and it was evaluated through a case study evaluation with real users to verify its feasibility. The results of the demonstration were used to evaluate the prototype system through different performance metrics. The results of the evaluation showed satisfactory performance across various metrics indicating the system stability and reliability.
Developing an Urban Resilience Index for Ajman City
(The British University in Dubai (BUiD), 2023-06) ALSHAMSI, ALYA; Professor Bassam Abu-Hijleh
Land-use change and worldwide environmental degradation are both accelerated by urbanisation. With global urbanisation accelerating, new regulations are needed to protect urban ecosystems, species, and the services they offer, ensuring more viable, adaptable, and liveable cities. The increase in the research of sustainable development has enhanced the awareness and attention of various global sectors such as developers and policymakers regarding advanced sustainable cities, along with the associated impact of sustainability in terms of the urban transformation. Ajman, one of the seven emirates that make up the UAE, has begun to establish plans, policies, and initiatives for this aim in collaboration with the other governmental agencies. Ajman has faced more obstacles as a result of the Emirate’s growing population, improved social conditions, way of life, and industrial revolution. These difficulties line up with the national and international aims and strategies that focus on pressing environmental, social, and economic problems. As a result, Ajman Municipality has made it a priority to integrate sustainability into all facets of daily life, and considers it to be essential to both its vision and goals. This research is intended to develop an urban resilience index (URI) for Ajman city to support future planning. The primary objective was to develop a tool for measuring and quantifying the resilience of an area, in order to assist policymakers and urban planners in determining whether a development project will be instrumental in enhancing city-level resilience. The proposed URI is based on data collected from a range of indicators spanning a number of key URI component indices. The dimensions over which the indices are distributed were identified through a critical literature review, while keeping Ajman’s local context in mind. The methodology for the current research was the primary qualitative approach, which was collected by conducting interviews. Ajman’s URI, according to the stakeholder feedback, should include institutional, infrastructural, social, and economic factors. The stakeholders also pointed out that the primary urban indicators that should be included in Ajman’s URI are the ecological environment’s quality, environmental policies, land use, public service amenities, disaster response and reduction framework, and critical city infrastructure. One of the issues raised was that the population of urban areas has grown significantly in recent years, and is expected to grow even further. Therefore, planners cannot find a balance between measures that can be better implemented to make urban systems, cities, and their people more resilient to problems. A 17-item universal resilience indicator composite was developed and found to be effective in assisting policymakers with the planning and assessment of a resilient future Ajman. The proposed URI can provide comprehensive information on urban resilience to climate change for municipal planners in cities. It allows for comprehensive city comparisons, which aids in the qualitative evaluation of areas of strength and weakness. It also allows one to look into the relationships between the total URI and other aspects of urban climate change resistance. Thus, the URI can be used to assess individual components of urban resilience and their associated indicators, as well as broad indicators of urban climate change resilience.
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.
Digital Forensics Framework for Investigating Hyperledger Fabric Blockchain Networks
(The British University in Dubai (BUiD), 2022-03) AL BARGHUTHI, NEDAA BAKER JAMIL
Industry leaders worldwide are adopting a new initiative to replace all paper transactions with digital ones and adopt them on blockchain platforms. Many pilot projects rely on private blockchain platforms such as the Hyperledger Fabric platform, whether at the government or private sector level. The increasing rise of this type of platform has led to the new research approach in digital forensics. There is a lack of research papers dealing with digital forensic techniques within the Hyperledger platform. This research fills the gap in the literature and provides guidelines for investigating the blockchain network. It also provides an approach for digital forensic investigators to examine the layers and associated components of Hyperledger Fabric, involving either criminal incidents, violations or abuse. This prototype retrieves relative evidence and contributes a valuable model to the current state of research. This research focuses on four objectives. proposing a prototype for network traffic investigations and retrieving all possible clues from the Hyperledger Blockchain. In addition, the research developed data mining methods and techniques to analyse the BC components. These techniques use a deployed Python-based Forensics Extractor Tool to automate the process. Furthermore, the criminological method was introduced and offered a novel and a law enforcement approach to investigate legal criminal cases in HLF BC networks. These objectives follow an adequate assessment of the characteristics of the main network components and examine in-depth network traffic. As a result, this research overcomes these challenges by working on flexible and reliable digital investigations. The numerical data extracted from the proposed framework has been verified and validated using various samples to test this framework. Accordingly, all research hypotheses were fulfilled during the research study. The outcome of the research is promising. and excellent results were illustrated. Moreover. this proposed prototype serves as a general framework for in-depth monitoring and analysis of the Hyperledger Blockchain network.
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.
Enhancing Arabic Offensive Tweet Classification: An Ensemble Approach Integrating AraBERT, Neural Networks, and LSTM Models
(The British University in Dubai (BUiD), 2023-10) WAHDAN, AHLAM MOHAMMAD; Professor Khaled Shaalan; Dr Mostafa AL-Emran
This thesis addresses the crucial research problem of accurate detection and moderation of offensive language in Arabic text, considering the intricacies posed by the language's complex morphology, dialectal variations, orthographic ambiguity, orthographic noise, limited linguistic resources, and the necessity for comprehensive coverage of offensive language expressions. The research objectives are delineated through four key research questions. Firstly, the study aims to identify the existing research gaps in Arabic Text Classification (ATC) through an extensive and rigorous systematic literature review. The study adopts a scholarly and formal approach, aiming to identify the specific areas within ATC research that lack comprehensive exploration or exhibit inadequacies in existing knowledge. This endeavor is grounded in the rigorous analysis and synthesis of relevant academic literature, ensuring a meticulous examination of the current state of research in ATC. Secondly, it investigates the effects of employing novel pre-processing methods on the performance of Arabic Text Classification. Thirdly, the research endeavors to determine the most effective model for enhancing the accuracy of Arabic offensive text classification by introducing a novel approach using pre-trained models; AraBERT model in conjunction with fully connected neural networks (NN) and long short-term memory (LSTM) networks. Finally, the study evaluates the proposed model's ability to classify Arabic offensive text effectively. The research methodology consists of two integral parts, comprising dataset description, the proposed framework. The dataset description provides insights into the two datasets utilized, namely OSACT and SEMEval. The framework elucidates the proposed model, which leverages a combination of pretrained models and neural networks, thereby achieving a high level of effectiveness in classifying Arabic offensive text. The model's performance is meticulously assessed using various evaluation metrics, including accuracy and F1-macro score, and is compared against other classifier models. The research findings demonstrate the superiority of the proposed model over the baseline AraBERT model, with the proposed model achieving an accuracy of 0.870 compared to the baseline accuracy of 0.820, along with an F1-score of 0.853 compared to the baseline's 0.800. This emphasizes the model's exceptional capacity to accurately identify offensive content in Arabic text. The implications of this research extend to diverse domains and stakeholders, encompassing decision makers, developers, and policy makers. The insights garnered from the study can be instrumental in making informed decisions pertaining to the integration of Arabic text classification systems in various operational settings. By comprehending the proposed model's performance and efficacy, decision makers can assess its potential impact on optimizing processes such as information retrieval, content filtering, and sentiment analysis in Arabic text. In conclusion, this thesis contributes significantly to the existing literature by addressing the complexities associated with offensive language identification in Arabic text and introducing an innovative approach that integrates pretrained models with deep learning techniques and neural networks. The demonstrated effectiveness and superior performance of the proposed model underscore its potential for practical implementation in real-world scenarios, thereby bolstering the field of Arabic offensive text classification.
Evaluation of LEED Interior Design Environment to Improve the Indoor Environmental Quality Through Enhancing Lighting Parameters of UAE Campus Buildings
(The British University in Dubai (BUiD), 2023-11) HASHAYKEH, HANAN A.; Dr Hanan Taleb
This study investigates the integration of interior artificial lighting, daylight, and quality views, all of which fall under Indoor Environmental Quality (IEQ), a key LEED (ID+C) credit in interior design environments. The research focuses on a campus building in the UAE, specifically the British University in Dubai. Effective design of these variables can enhance visual comfort and improve the building's indoor environment, including lighting quality and user performance. The methodology combines online surveys, field measurements, and computer simulations using DIALux EVO 11. It also considers human factors among students and staff through a mixed-method approach to validate findings and correlate data. The study aims to connect objective and subjective assessments of environmental factors in both daylight and artificial lighting, including lux value, uniformity ratio, glare, and daylight factor, according to EN 12464-1 (2021) standards. Field measurements validate outcomes from the base model in the software. The research offers practical insights into enhancing IEQ in campus buildings through various lighting strategies and scenarios. It analyzes different spaces based on LEED classifications, such as auditoriums, classrooms, libraries, and administration areas. The key findings emphasize the need to balance lighting parameters and conditions to achieve optimal results. The results show improved lighting conditions, enhanced lux values, glare reduction, and balanced light distribution across various spaces, benefiting user experience and performance. For instance, in the corridor areas, the lux value met the target value, ensuring the desired lighting quality. In other locations, such as the auditorium and classroom FF-111, lux values significantly exceeded the target levels, with values reaching 527lx and 602lx, respectively, greatly enhancing overall lighting conditions. The study's actionable insights cater to designers, architects, and stakeholders involved in campus building projects in the UAE. By integrating sustainable standards, this research promotes environmentally sustainable indoor environments that prioritize occupant well-being and enhance the quality of educational spaces.
Examining the Factors affecting the sustainability of blockchain technology in higher education using a hybrid SEM-ANN approach
(The British University in Dubai (BUiD), 2022-10) AL SHAMSI, MOHAMMED SALEM MATAR
Blockchain technology has received considerable attention during the last few years. Blockchain technology permits the creation of a distributed record of a decentralized digital event in which data and related transactions are not controlled by a third party. However, little is known concerning what aﬀects their sustainable use for educational purposes. Consequently, there are three primary goals for this research. A systematic review is conducted to address the research gaps in the literature on Blockchain adoption from the lens of information system (IS) models and theories. The systematic review included empirical studies published between January 2010 and December 2021 on the topic of blockchain adoption. Among the 918 articles, 30 articles were critically analyzed based on the inclusion criteria. This research, therefore, develops a theoretical model based on extracting constructs from the protection motivation theory (PMT) and expectation conﬁrmation model (ECM) to understand the sustainable use of blockchain in higher education. The developed model was then tested based on data collected through an online survey from 374 university students in the UAE who used blockchain technology for educational purposes. The model was empirically validated using a hybrid structural equation modelling-artiﬁcial neural network (SEM-ANN) approach. The hypotheses testing results reinforced most of the suggested hypotheses in the developed model. The sensitivity analysis results for model 1 revealed that satisfaction has the most considerable eﬀect on the sustainable use of blockchain technology with 100% normalized importance, followed by perceived usefulness (58.8%), perceived severity (12.1%), and response cost (9.2%). Besides, the sensitivity analysis for model 2 showed that perceived usefulness has the most considerable effect on the sustainable use of blockchain technology with 100% normalized importance. However, expectation confirmation has 29.2%. Theoretically, integrating the PMT and ECM will add significant value to the validation of the two theories in general and the blockchain in specific. Practically, understanding the impact of security factors would assist in understanding the effect of security incidents on the sustainable use of technology in higher educational institutions. In addition, governments, academia, businesses, and individuals often tend to share resources over a distributed ledger secured by means of cryptography. Blockchain technology also helps in facilitating the traceable, secure, and verifiable exchange of educational data across institutions effectively. Methodologically, the use of SEM-ANN in validating such theoretical models is rarely used, and hence, it would add value to the existing literature by measuring the non-linear relationships among the factors.
Examining the factors affecting users’ cybersecurity behaviour in mobile payment contactless technologies: A hybrid SEM-ANN approach
(The British University in Dubai (BUiD), 2022-12) ZAINAL, HANA YOUSUF
Modern businesses have adopted a plethora of advancements due to the emergence of digital transformation where the recent lifestyle requires to have a robust platform to process all the communication in an effective and secure way. Advanced technologies adopted by the society purely concentrated on the software and cybersecurity enhancements from the software perspective ignoring the fact that a human behaviour can be the most major and severe threat for these advanced technologies. The adoption of any new technology in the society has been turned into a must rather than a complimentary due to the rapid growth of the technology advancements and people curiosity to investigate new trends. Technology adoption depends on the behaviour of the end users in dealing with the technology. Mobile payment contactless technologies are one of the fast-growing technologies specially after the appearance of the COVID-19 where all the payments and transactions are performed using RFID (Radio-Frequency Identification) or NFC (Near Field Communication) techniques. The individual’s cybersecurity behaviour is a major concern in these technologies. A quick review of literature showed that none of the studies discussed the individual’s cybersecurity behaviour toward this technology. Therefore, this research has three main objectives. First, conducting a systematic of systematic reviews on cybersecurity through a multidisciplinary perspective to address the research gaps in the existing literature of human cybersecurity behaviour. The systematic review of systematic review included empirical studies published between January 2015 and February 2022 on the topic of cybersecurity. A total of 794 studies have been reviewed, and 60 studies were found qualified and considered in the analysis. Through the analysis, little attention has been paid to cybersecurity behaviour in general and mobile payment contactless technologies in specific. Moreover, the existing literature discussed the utilization of mobile payment contactless technologies in terms of adoption and use in a certain criteria or environment and do not measure or explore the cybersecurity behaviour towards this technology. To bridge this literature gap, this research builds an integrated theoretical model by combining factors from the Protection Motivation Theory (PMT), Technology Threat Avoidance Theory (TTAT), Theory of Planned Behaviour (TPB), along with cybersecurity awareness to measure the cybersecurity behaviour in mobile payment contactless technologies. The model was then empirically validated using a hybrid Structural Equation Modelling-Artificial Neural Network (SEM-ANN) approach based on data collected through questionnaire surveys from mobile payment contactless technologies users in the UAE. The results indicated that the attitude, subjective norm, cybersecurity awareness, perceived behavioural control and response efficacy have a significant influence on cybersecurity behaviour. On the other side, the results indicated that perceived threat, response cost, and self-efficacy have insignificant influence on cybersecurity behaviour. The model explained 53% of the total variance in cybersecurity behaviour. Additionally, the ANN results showed that cybersecurity awareness is the most important factor affecting cybersecurity behaviour, with a normalized importance of 100%. Theoretical contributions, practical implications, and limitations and future research were also discussed.
Examining the Factors Influencing Autonomous Vehicle Use and its Impact on Environmental Sustainability in UAE using a Hybrid SEM-ANN Approach
(The British University in Dubai (BUiD), 2024-05) AL MANSOORI, SAEED HUSSAIN ALI; Dr Mostafa Al-Emran,
Over the past few years, the evolution of transportation towards autonomous vehicles has attracted substantial interest, signifying a transformative shift in the realm of mobility. Nevertheless, AVs adoption is a complex process, influenced by cutting-edge technological advancements, societal acceptance, regulatory frameworks, and potential environmental impacts, all of which are critical in shaping their integration into modern transportation systems. To address the gap in the existing research of this domain, a comprehensive systematic review was conducted, focusing on AVs adoption through the lens of various information system (IS) models and theoretical frameworks. The systematic review analysed empirical studies published in the timeframe from January 2013 to January 2023, focusing on AVs adoption. Out of 3,532 articles, 71 were shortlisted for in-depth analysis according to specific inclusion criteria. In addition, this study constructs a novel theoretical model based on the integration of the Protection Motivation Theory (PMT), the Behavioural Reasoning Theory (BRT), and the updated IS success model variables to investigate the factors influencing AVs adoption and its impact on environmental sustainability. Subsequently, the proposed model was validated using data obtained from an online survey involving 495 individuals in the UAE, who either own or have had experience using AVs. The proposed model underwent empirical validation by applying a hybrid Structural Equation Modelling-Artificial Neural Network (SEM-ANN). The results of hypothesis testing provided strong support for the majority of the hypotheses derived from the proposed model (i.e., out of 12 hypotheses, 9 were supported).

Browse

Browsing Thesis (IT & Engineering) by Title

Results Per Page

Sort Options