Article Per Year (5 Year)
p-Index From 2020 - 2025
0.444
P-Index
This Author published in this journals
All Journal Journal of Applied Data Sciences Journal of Current Research in Blockchain
Harley, Charis
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
How Effective are Different Machine Learning Algorithms in Predicting Legal Outcomes in South Africa? Khosa, Joe; Mashao, Daniel; Olanipekun, Ayorinde; Harley, Charis
Journal of Applied Data Sciences Vol 5, No 4: DECEMBER 2024
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v5i4.215

Abstract

This study examines the effectiveness of different machine learning algorithms in predicting legal outcomes in South Africa's Judiciary system. Considering the advancement of artificial intelligence in the legal sector, this research aims to assess the effectiveness of various machine learning algorithms within the legal domain. Text classification is done using machine learning algorithms, including Logistic Regression, Random Forest, and K-Nearest Neighbours, with datasets obtained from a state legal firm in South Africa. The datasets undergo diligent data cleansing and pre-processing methods, encompassing tokenization and lemmatization techniques. This study evaluates these models' applications through accuracy metrics. The findings demonstrate that the Logistic Regression model attained an accuracy rate of 75.05%, whereas the Random Forest algorithm achieved an accuracy rate of 75.08%. On the other hand, the K-Nearest Neighbours algorithm exhibited no optimal performance, as evidenced by its accuracy rate of 62.76%. This study provides valuable insights for legal professionals by addressing a specific research question about the successful application of machine learning in South Africa's legal sector. The results indicate the possibility of using machine learning to predict the outcomes of criminal legal cases. Additionally, this study highlights the significance of responsibly and ethically implementing machine learning within the legal field. The results of this study enhance our comprehension of the prediction of legal outcomes, establishing a foundation for future investigations in this dynamic area of study. A limitation of this study is that the data was obtained from a single law firm in South Africa.
Cyber Attack Pattern Analysis Based on Geo-location and Time: A Case Study of Firewall and IDS/IPS Logs Mashao, Daniel; Harley, Charis
Journal of Current Research in Blockchain Vol. 2 No. 1 (2025): Regular Issue March
Publisher : Bright Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jcrb.v2i1.26

Abstract

Cyber attacks are a growing concern for organizations worldwide, requiring continuous monitoring and analysis to detect patterns and anticipate future threats. This study explores the temporal and geographical patterns of cyber attacks using log data from firewall and IDS/IPS systems, with a focus on understanding attack trends based on severity levels and monthly variations. The analysis revealed an almost even distribution of attacks, with 13,183 low severity, 13,435 medium severity, and 13,382 high severity incidents. This emphasizes the need for holistic defense strategies that address all levels of threats. Through time-series analysis, including the ARIMA model, we forecasted future attack trends, highlighting the consistency of cyber threats over time and identifying potential periods of increased activity. The monthly trend analysis showed fluctuations, with a notable peak of 906 attacks in March 2020 and a decrease to 825 attacks in April 2020, suggesting the influence of external factors such as global events. The ARIMA model provided accurate forecasts, indicating a steady rate of future attacks and underscoring the importance of continuous vigilance. While the ARIMA model captured linear trends effectively, future work should explore non-linear models, such as Long Short-Term Memory (LSTM) networks, to uncover deeper, more complex patterns in the data. This research provides critical insights into the nature of cyber attacks, offering organizations a data-driven approach to improving their cybersecurity measures. Future studies should focus on enhancing forecasting models and integrating real-time data to better anticipate emerging threats.
Co-Authors Khosa, Joe Mashao, Daniel Olanipekun, Ayorinde