Thaier Hamid

This paper presents a novel Intrusion Detection System (IDS) framework for securing Internet of Things (IoT) networks, leveraging advanced machine learning techniques. The proposed framework integrates Deep Neural Networks (DNNs) and Random Forest (RF) algorithms to enhance detection accuracy and robustness. Utilising the comprehensive CICIoT2023 dataset, the IDS model is rigorously trained and evaluated, demonstrating high efficacy in detecting and mitigating potential threats. However, the results also reveal shortcomings in detecting certain attack categories, such as command injection and SQL injection, indicating areas for further refinement. These findings contribute to the advancement of IoT security through the application of advanced machine learning techniques, while also highlighting the need for continued research to address identified shortcomings.

This paper investigates the use of ensemble learning techniques to enhance the security of Internet of Things (IoT) networks through advanced Intrusion Detection Systems (IDS). Utilizing the CICIoT2023 dataset, the study evaluates four ensemble methods: Ensemble Voting, Random Subspace, Bayesian Model Averaging, and Boosting. The results demonstrate that Random Subspace and Bayesian Model Averaging significantly improve detection accuracy and robustness against various attack types, highlighting their potential in real-world IoT security applications.

As retailers embrace the online shopping experience and technology advances, it is now also vital for retailers to pay attention to customer churn since it has a detrimental impact on the company's corporate development and reputation. To mitigate the negative effects of customer churn on grocery retail businesses, this study will look at how machine learning and deep learning churn prediction models are applied, as well as data analytical findings on customer retention. The implications of customer churn and how it impacts grocery businesses will be the subject of thorough research.
Furthermore, an analysis of previously gathered data sets will reveal significant discoveries, customer preferences, and behaviours related to Churn.
The study will examine how churn prediction affects a company's profitability, reputation, and operational efficiency.
Following the study of the dataset, a thorough framework will be suggested with the main goal of proactive churn control, thereby limiting its effects on the overall growth of the company.
This thesis aims to contribute to current efforts to improve corporate company growth by studying customer behavioural patterns most associated with churn and then suggesting solutions to the challenges.

Robotics is becoming more ubiquitous, and this technology has existed for almost a century and also keeps continuously evolving with better capabilities and advancements in an environment which includes both hardware and software. Nowadays, Robotics come in different shapes with different capabilities. These days, a robot can be small, and simple and still have increased performance and productivity. Additionally, this technology has become an essential component of daily life, and robotics automation usage cases have expanded from household utilities to medical, or space projects, defense, and education. Robotic functionalities are similar to computer systems running by a program that is defined to repeat tasks or operations. Moreover, they experience security problems that are comparable to those that computer systems have had for years. Hence, when robots are compromised, it immediately affects two different areas.: I. Physical elements may raise concern in three key aspects; integrity, confidentiality, and availability of the robot system’s operations and functions. It can also lead to attacks or hacks. I. Virtual security vulnerabilities can be found in provider platforms, misconfigurations, built-in weaknesses in robot systems, and risks in data communications channels. For instance, the WIFI connection may be designed with a poor encryption system. Therefore, both physical and virtual problems in robotics systems are part of cybersecurity in Robotics which is rapidly growing. In this case, the paper focuses on cybersecurity in Robotics and identifies security gaps, vulnerabilities, and risks.

Information communication technology (ICT) is constantly evolving, it is currently used in virtually every aspect of human life, such as financial transactions. Due to its ongoing development, the internet serves as the basis for all service platforms. Financial institutions are responding to the development of ICT by following suit in an effort to improve services and maintain existing technology. Similarly, worldwide cybercrime has increased, resulting in financial losses. As a result, information security has become a pressing concern for any institution tasked with providing adequate services. Developing complex security methods that address people, processes, and technology is required to strike a balance between the technical and behavioural components of information security. This qualitative study will examine how socio-organizational factors can enhance employees’ attitudes toward information security culture at any financial institution. To fulfil the above aim, a qualitative methodology is utilised. Interviews (prior and main) and document analysis (Review & Analysis of Internal Materials in the banking sector of Nigeria) will be used to collect data. The Quota Sampling method is used in recruiting participants for interviews. With the assistance of academic experts, fellow researchers, and information security professional experts, the interview questions will be pretested. The Thematic analysis will be utilised to deduce occurrences, patterns, and use of concepts. Based on the analysis of data gathered from 38 top management of a financial institution, the study concludes that improving information security culture in any institution requires strong leadership, accountability, education/awareness/training/experience, commitment & trust, monitoring & internal control (audits), process integration, technology, permissible/institutional pressure, societal pressure, personal beliefs, values, and attitudes. The study expands on ’behavioural information security’, a crucial area of study. It bridges the gap in research most especially in Africa as it expands knowledge of information security by critically exploring human factors in the form of employees in the financial sector of a cross-cultural country Nigeria. From a theoretical perspective, the study presents socio-organizational factors that can enhance employees’ attitudes toward information security culture. From a practical perspective, it is a study which provides guideline for better articulation, formation, and implementation of an organisation’s Information security laws, policies, and procedures as well as to create a framework which can aid top management in recruiting. The usefulness of this thesis is not limited to the financial institution of Nigeria/Africa.

Developing interest for transfer work from home associations needs to permit numbers of specialists to get to confidential organizations on the business' nearby web. This leads to greater expenses to authorize the homeworker admittance to the association's assets secretly and safely through assigned gadgets and administration. The primary purpose of additionally supports the association execution with various administrations for telecommuters.
SASE utilizes Zero Trust Engineering as its spine, without confiding in any gadget or client, yet validate and approve at each solicitation. The main purpose to apply designated spot capabilities such as Secure Web Passage and Cloud Access Security Representative to additionally uphold the security of the association's resources that may not be trusted in the cloud. Toward this paper's end, we will comprehend how those strategies referenced for doing the work on secure systems for work with associations' system associations and security. We conduct a systematic literature review of security challenges of cloud computing. In addition to security issues, the benefits of cloud computing security were also studied. Whenever a website is hacked by an attacker, businesses and organizations lose their valuable data. Thus, we choose the best platform to organize and secure the data online in a valuable way. The main point of attack in the website is the use of weak passwords and sharing authentication to other users.

It has become mandatory for traditional cities to be converted into smart cities for the benefit of giving citizens a better lifestyle. The large amounts of people migrating towards smart cities has increased the requirements of a sustainable smart city with the assistance of cloud-based Internet of Things (IoT) devices such as active sensors and smartphones. When implementing these cloud applications that are IoT-based, there are several challenges including security and privacy of data in the devices, and satisfaction with the smart services provided. Previous research done revealed that the primary challenge was privacy and security, while current research emphasizes on the security of the smart devices, and the awareness and satisfaction of customers with them. In this paper, we used a qualitative and quantitative approach to attain sustainability. Under the qualitative analysis, we proposed a 5-Layer Smart City framework based on IoT, making use of various technologies such as fog computing, Artificial Intelligence, edge computing, Machine Learning, actuators, cloud computing, Deep Learning, sensors, etc. In the quantitative analysis, we carried out a smart city survey to gather knowledge about the citizens’ level of satisfaction and awareness. The study was carried out on a minimal scale because of limited resources and time; however, it still provides a possible solution to the issues encountered.

Mother, who gives birth, usually face a mood disorder called postpartum or postnatal depression. It appears immediately after the third week of the baby's birth. However, during the first year of delivery, women can suffer anytime with this situation, and it could lead to a couple of years after birth. Few men as a father can face this condition. If it is not monitored immediately, it triggers severe and permanent disorders such as anger issues, isolation, stress, or anxiety. A significant increase has been observed in postpartum depression incidents with harmful consequences on children as well as parents regarding their physical and emotional well-being. This research paper analysed the literature to evaluate the psychotherapies that can be followed as self-help. We also evaluated automated psychotherapy systems and meta-analysed mobile applications that are available online to cope with postpartum depression. We discussed the acceptability of a therapeutic mobile application for reducing depression during parenting and postpartum period, for the patients themselves. Finally, a combination of cognitive behavioural therapy and interpersonal psychotherapy, an algorithm; we proposed in this paper as a base to develop the mobile application that can help control and reduce depression during a postpartum situation.

The academic efficiency and knowledge retention of students can be improved by practicing active recall testing and implementing spaced repetition techniques. The process of trying to recall information previously learned with the aim of increasing the chance of committing the information to long-term memory is called active recall. Spaced repetition is a technique which can help students to memorize and learn information by outspreading reviews of the topics over larger range of time revising the same topic multiple times in a single session.
A qualitative method has been followed in this paper which takes a grounded theory approach while evaluating literature on different memory models, memory creation and retrieval processes. Based on the literature review, an algorithm has been proposed with the aim of improving learning effectiveness by leveraging spaced repetition techniques.