Published Papers

Machine learning algorithms are employed on a football data set to forecast whether a shot results in a goal. Results from existing models are improved upon by employing various additional algorithms. At the initial stage, the study gathered data from an existing Kaggle article published online by Usama Waheed. The data set includes data from various leagues and their matches. The research analysed shot events, filtered out non-relevant events, and created features based on shot coordinates, angles, player skill, and shot type. Nine machine learning algorithms were implemented: logistic regression, XGBoost, random forests, support vector machines, k-nearest neighbours, decision trees, LightGBM, CatBoost, and artificial neural networks. The research also focused on removing the redundancy, optimizing performance on imbalanced datasets, and fine-tuning model hyperparameters by employing nested cross-validation. Lastly, the models were evaluated on accuracy, precision, recall, and training time metrics. The results revealed insights into the strengths and weaknesses of each model in predicting goals, with specific emphasis on areas of improvement for shot-based football analytics. Decision trees produced the most accurate predictions on the test set.

This paper investigates the extent to which the use of generative AI (Artificial Intelligence) poses ethical dilemmas in political campaigns. By reviewing the newest literature on the topic, this paper examines the problems associated with the creation of ethics guidelines on AI-generated content (AIGC) use. In pre-existing guidelines, certain vocabulary such as “transparency,” “dignity,” and “freedom & autonomy” were most frequently repeated. This shows not just how prevalent these ethical issues are but also that proposed guidelines can become repetitive whilst AI's ethical dilemmas still have to be dealt with. With the analysis of case studies in France, India, and the US (United States) we can see the impacts of AIGC on political elections within countries with diverse levels of AIGC regulation. France and India have looser regulations on AIGC - but the US, whilst lacking regulation in some states, has adopted the strictest measures in others. In the absence of harmonized legislation, international ethical guidelines have a key place in the discussion. This paper addresses the possibilities of incorporating AI systems that flag negative and unethical social media posts. The paper suggests a direction for private and public institutions to integrate new beneficial AI-based countermeasures in future political campaigns to mitigate harm. By combining these measures with bringing more attention to the creation of guidelines surrounding AIGC, ethical dilemmas can be lessened.

In this work, a review is conducted on the aerodynamic behaviour of the 2010 McLaren Mercedes rear-wing. The behaviour and effect of different sub-components on the wing are explained alongside how that contributes to the overall performance of the car. A particular focus of this review is on certain innovative systems utilised by the team in 2010 (such as the F-duct, wingtip Louvres and vents). Additionally, Autodesk CFD is used to qualitatively support observations about airflow around McLaren’s wing components, and the aerodynamic impact of changing wing parameters (e.g. angle of attack). The review validates how differing curvature on either side of the wing causes a pressure differential that produces downforce. Overall, the wing structure of the MP4-25 achieved one of the most effective downforce distributions of 2010 – additional downforce controlling systems such as the F-duct allowed McLaren to gain a competitive advantage by varying aerodynamic parameters to a greater extent than competitors

The purpose of this paper is to examine how social media and influencers are impacting food safety and standards in India. I have looked at a category of food supplements earlier marketed as ‘health beverages’, and how the issue of sugar content in these was flagged off via social media, eventually leading to a change in corporate behavior

This paper offers a comprehensive analysis of bank runs, tracing their evolution from the Great Depression to the COVID-19 pandemic. It explores the fundamental concept of bank runs, their shifting causes and consequences over the past century, and the role of public psychology in exacerbating these events. The paper highlights how the general public’s reactions can significantly influence the course of a bank run, noting how panic triggered by news of a bank run can rapidly escalate, causing individuals to rush to withdraw their funds and potentially creating widespread chaos and distress. Furthermore, the paper examines how policy adjustments and new implementations address public psychology and attempt to mitigate the risk of bank runs. It includes detailed assessments of the evolution of the FDIC and capital controls in response to various financial crises. Overall, the paper provides a focused analysis of the historical context and policy responses, evaluating them in relation to different financial crises over time.

This paper assesses whether climate change has an effect on mangrove forests using the Google Earth Engine (GEE) computing platform. Applying the 35+ year quasi-global rainfall CHIRPS dataset with the GEE platform provided the Precipitation and Evapotranspiration data. This data can be used to correlate with the climate variables, CO2 emissions and Temperature. 

This paper aims to analyse the correlation between Precipitation and Evapotranspiration with the climate variables to assess the climate change effect on the Al Zorah Natural Reserves mangrove in the UAE.