Caritas University

Weeds today are among the factors contributing to low agricultural productivity. As the world’s population continues to grow, there is an urgent need to meet global food demand. Nigeria currently lacks sufficient crop production to feed its growing population, and weeds are among the core contributors to poor agricultural yield. This study conducts a comprehensive review of Deep Learning (DL) approaches to weed classification in precision agriculture, covering literature from 2018 to 2025, was carried out. We employed a mix of quantitative and qualitative methods in the course of this review paper. Our data source is centred on Scopus-indexed papers, published with Sensors, Electronics, and Agriculture in MDPI as well as IEEE, Thomson Reuters, and Springer. The study systematically reviewed and analysed machine learning (ML), DL, and instance segmentation techniques to identify the key technological and environmental barriers, such as data limitations, class imbalance, environmental variability, and model scalability issues that affect the effectiveness and efficiency of these models when deployed in real time. These findings show that while weed management models like the YOLO variants, ResNet, and Vision Transformers achieved high accuracy in training and testing, they are associated with several challenges in their real world-deployment, such as occlusion, small object detection, and environmental adaptability. Overall, this research provides recommended solutions to enhance model robustness, scalability, and efficiency. It further provides a summary of the current state and future directions for AI-driven weed management.

Background: In the current postmodern era, marriages are increasingly confronted by challenges stemming from digital integration. While social media serves as a modern technological tool for information and connectivity, its role as a determinant of marital stability remains a subject of critical inquiry. Objective: This research sought to investigate the influence of social media engagements on marital satisfaction among couples in Enugu state, Nigeria. The study specifically examined the impact of usage duration, content types, and message formats, while also considering the moderating role of spousal communication. Methodology: A survey-based descriptive design was adopted for the study. Using a multistage sampling technique, a sample size of 385 married couples was selected from the three senatorial districts of Enugu state. Data were collected through a structured four-point Likert scale questionnaire and analysed using simple percentages, mean deviation, and Chi-square statistical tools. Results: Findings revealed that respondents spend a moderate duration of one to two hours daily on social media, which positively influences marital satisfaction to a high extent. Prank and comedy were identified as the most consumed content types, contributing to emotional relief and marital enlightenment. Furthermore, text-based posts were found to be the most preferred message format. Hypothesis testing indicated that family income significantly predicts the impact of social media on marital satisfaction, whereas marriage duration does not. Conclusion: The study concludes that social media is an advantageous tool for marital satisfaction when used judiciously. Effective spousal communication and moderate online engagement help couples avert the negative consequences associated with social media addiction. It is recommended that couples maintain a balance between digital interactions and heart-to-heart discussions to foster long-term conjugal growth.

Machine learning and deep learning have become essential components of modern cybersecurity because of their ability to detect malicious activities, classify network traffic, identify malware, recognize phishing attempts, and support automated incident response. However, machine learning–based cybersecurity classifiers are vulnerable to adversarial attacks in which attackers deliberately manipulate data, features, model inputs, or training processes to cause misclassification or evade detection. This study systematically analyzes adversarial attacks against machine learning–based cybersecurity classifiers and proposes a comprehensive defense framework to improve their robustness and reliability. The study examines major attack categories, including evasion, data poisoning, model extraction, inference, backdoor, and adversarial example attacks. It also analyzes attack surfaces, threat models, and the consequences of adversarial manipulation in intrusion detection, malware detection, phishing classification, and other AI-enabled cybersecurity systems. The findings indicate that adversarial attacks can significantly reduce detection performance, increase false-negative and false-positive rates, manipulate decision boundaries, and undermine trust in automated security systems. A defense-in-depth framework is proposed, incorporating secure data management, adversarial training, robust feature engineering, model validation, ensemble learning, anomaly detection, explainable AI, continuous monitoring, human oversight, and regular security auditing. The study concludes that no single defense mechanism can provide complete protection against adversarial machine learning attacks. Therefore, resilient AI-based cybersecurity requires a layered approach that protects data, features, models, inference processes, and the entire machine learning lifecycle.

This study examined the political and economic factors driving the demolition of business premises in Enugu State, Nigeria, highlighting the tensions between state-led development initiatives and the interests of local business communities. Guided by Urban Political Economy Theory, this research aims to determine if urban renewal, modernization and gentrification accounted for the demolition of business premises in Enugu State, using a case study design and mixed methods approach combining documentary and focus group discussions.