DEPARTMENT OF PHYSICAL SCIENCE

The security and reliability of cloud computing environments face significant threats from the escalating frequency and sophistication of Distributed Denial of Service (DDOS) attacks, which cause substantial financial losses and service disruptions while often serving as entry points for further system compromise. This research addresses this critical challenge by developing and evaluating deep learning-based detection models using two contemporary datasets: CICDDOS2019 (254,797 normal and 51,404 attack instances with 78 features) and IDS_ISCX_2012. To mitigate class imbalance, a balanced subset of 50,000 instances per class was created through random under-sampling, with optimal feature selection performed using the K-best method. Two advanced recurrent neural network architectures were implemented and compared: Bidirectional Long Short-Term Memory (BI-LSTM) and Gated Recurrent Unit (GRU), both enhanced with temporal attention mechanisms to focus on critical attack patterns within sequential network traffic. Experimental results demonstrated that GRU outperformed BI-LSTM across both datasets, achieving accuracies of 0.93 and 0.65 on IDS_ISCX_2012 and CICDDOS2019 respectively, compared to BI-LSTM's 0.91 and 0.61. The GRU model's simplified architecture proved more computationally efficient while effectively addressing the vanishing gradient problem common in recurrent networks. This study successfully establishes a robust framework for DDOS attack detection in cloud environments, contributing to enhanced network security through improved accuracy, reduced false positives, and practical implement ability for real-time threat mitigation

The advent of digital technology has catalysed the transformation of various industries, including public transportation, through the implementation of electronic ticketing (eticketing)management systems. This study delves into the historical evolution, motivations, challenges,and benefits that underlie the development and adoption of e-ticketing systems. The historical context reveals a departure from traditional paper-based ticketing towards the digital realm, driven by technological advancements and the need for enhanced efficiency, accuracy, and convenience. Motivations for e-ticketing encompass the desire to
provide drivers with a seamless and user-friendly ticketing experience while optimizing operational processesfor transportation authorities. However, challenges arise in bridging the digital divide, ensuring data security, establishing robust technological infrastructure, promoting user adoption, and facilitating integration with existing systems Through an in-depth analysis of the historical context, motivations, challenges, and benefits, this study offers a comprehensive understanding of the role that e-ticketing management systems play in reshaping modern transportation landscapes.

Machine learning has emerged as a transformative technology with a profound impact on various industries. In this course of study, this abstract provides an overview of ML, its significance, limitations, types of ML we have. Machine Learning: This refers to the exploration of computer programs that utilize algorithm and statistical model to acquire knowledge by identifying patterns and making inferences all without explicit programming. Some of the significance of Machine Learning includes its contribution to technological advancement in various industries, it equips individual with skills to automate processes and streamline operations and it also enables automation of repetitive tasks which enhance efficiency and productivity. There are challenges or limitations associated with ML, some of which includes: Data dependency, Interpretability and Transparency, Overfitting and Generalization, Domain-specific expertise and Lack of casual understanding. The types of Machine Learning are: Supervised Learning, Unsupervised Learning, Semi-supervised Learning and Reinforcement Learning.

Alkyd resins are products of poly condensation reaction between polybasic acid and
polyhydric alcohol modified with fatty acid or drying oil. Oil modified alkyd resins
are used as binders in surface coatings. It is estimated that alkyd resins contribute
about 70% to the conventional binders used in surface coatings today. Rubber seed
oil is a renewable raw material. Rubber seeds were collected from Rubber Research
Institute of Nigeria (RRIN), Iyanomo, Benin city and its oil was extracted by
soxhlet extraction process. The oil obtained was used in the preparation and
synthesis of alkyd resin. Monoglycerides were obtained from alcoholysis process
where RSO was reacted with glycerol at very high temperature in presence of a
catalyst. The resulting mixture was then reacted with phthalic anhydride of which
xylene was introduced in the reaction acting as an azeotropic solvent in order to
obtain the water of condensation. Rubber seed oil (RSO) and rubber seed oil alkyd
resin (RSOAR) were characterized by the determination of physico-chemical
properties. The values for RSO and RSOAR were found to be; Specific gravity
0.906 and 0.940, Density 0.903 and 0.937 (kg/m^3), Acid value 11.42 and 7.54 (mg
KOH/g), Peroxide value 1.85 and 1.49 (meq/kg), Iodine value 130.36 and 83.23
(gI2/100g), Saponification value 186.88 and 210.62 (mgKOH/g) respectively. The
performance characteristics of RSO was studied in terms of set to touch, surface dry
and dry through and resistance to chemicals and compared with commercial resin. The results revealed that alkyd resin formulated by RSO dried faster than that of
commercial resin and also had high resistance to water, salt and sulphuric acid
solutions.