Wayne Goodridge

Kwasi Edward, Wayne Goodridge, Koffka Khan et al.

Context: Stock Android exposes Wi-Fi Direct peer-to-peer APIs, but it does not provide application-transparent communication across multiple Wi-Fi Direct groups. For developers working on non-rooted devices, the main obstacle is architectural: interface-specific transport contexts, relay roles, and forwarding state must be coordinated entirely at application level. Objectives: This paper investigates whether multi-group Wi-Fi Direct communication can be realized as a stock-Android software architecture while preserving forwarding-state consistency and remaining compatible with Android 11 devices without rooting or operating-system modification. Methods: We design SWARNET, a layered artifact composed of a Flutter application layer, a Kotlin native networking layer, interface-bound P2P and legacy-Wi-Fi sockets, relay-state management, and subscription-based forwarding tables. We evaluate the implemented artifact on five stock Samsung Galaxy A10s smartphones across four single-group and multi-group scenarios using archived throughput and packet-loss measurements. Results: The artifact remained operational in all four scenarios. Peak receiver throughput observed from the archived curves was approximately 19.7~Mbit/s in 2d1g, 17.9~Mbit/s in 3d1g, 16.1~Mbit/s in 4d2g, and 16.0~Mbit/s in 5d3g. Packet loss increased with forwarding complexity, reaching about 19--20\% only in the highest-load region of the three-group case. Conclusion: The contribution is an implementable software architecture and a feasibility study showing that stock-Android multi-group Wi-Fi Direct communication can be engineered at application level on non-rooted devices. The results support architectural feasibility in a small static testbed; they do not establish broad resilience, scalability, or deployment readiness.

Koffka Khan, Wayne Goodridge

This study addresses a critical gap in the literature regarding the use of Swarm Intelligence Optimization (SI) algorithms for client selection in Federated Learning (FL), with a focus on cybersecurity applications. Existing research primarily explores optimization techniques for centralized machine learning, leaving the unique challenges of client diveristy, non-IID data distributions, and adversarial noise in decentralized FL largely unexamined. To bridge this gap, we evaluate nine SI algorithms-Grey Wolf Optimization (GWO), Particle Swarm Optimization (PSO), Cuckoo Search, Bat Algorithm, Bee Colony, Ant Colony Optimization, Fish Swarm, Glow Worm, and Intelligent Water Droplet-across four experimental scenarios: fixed client participation, dynamic participation patterns, hetergeneous non-IID data distributions, and adversarial noise conditions. Results indicate that GWO exhibits superior adaptability and robustness, achieving the highest accuracy, recall and F1-scoress across all configurations, while PSO and Cuckoo Search also demonstrate strong performance. These findings underscore the potential of SI algorithms to address decentralized and adversarial FL challenges, offereing scalable and resilient solutions for cybersecurity applications, including intrusion detection in IoT and large-scale networks.

Nikita Louison, Wayne Goodridge, Koffka Khan

Existing Sign Language Learning applications focus on the demonstration of the sign in the hope that the student will copy a sign correctly. In these cases, only a teacher can confirm that the sign was completed correctly, by reviewing a video captured manually. Sign Language Translation is a widely explored field in visual recognition. This paper seeks to explore the algorithms that will allow for real-time, video sign translation, and grading of sign language accuracy for new sign language users. This required algorithms capable of recognizing and processing spatial and temporal features. The aim of this paper is to evaluate and identify the best neural network algorithm that can facilitate a sign language tuition system of this nature. Modern popular algorithms including CNN and 3DCNN are compared on a dataset not yet explored, Trinidad and Tobago Sign Language as well as an American Sign Language dataset. The 3DCNN algorithm was found to be the best performing neural network algorithm from these systems with 91% accuracy in the TTSL dataset and 83% accuracy in the ASL dataset.

Andrew Rudder, Wayne Goodridge, Shareeda Mohammed

In this paper, we propose a reversible data hiding method in the spatial domain for compressed grayscale images. The proposed method embeds secret bits into a compressed thumbnail of the original image by using a novel interpolation method and the Neighbour Mean Interpolation (NMI) technique as scaling up to the original image occurs. Experimental results presented in this paper show that the proposed method has significantly improved embedding capacities over the approach proposed by Jung and Yoo.