Publications

Network Intrusion Detection Systems (NIDSs) have emerged as a frontline defense against potential attacks in wireless Internet of Things (IoT) networks. However, existing machine learning methods follow an unstructured data processing patterns and can barely incorporate all information due to the network dynamicity as well as data imbalance. In this study, we propose Graph Isomorphism Network model based on Edge (GINE), an innovative graph-based algorithm tailored to pinpoint malicious network traffic within wireless IoT networks. Specifically, we initiate by presenting the wireless IoT network graph, capturing the global topological interactions of its edges. Subsequently, we design an edge representation learning algorithm, capable of encoding network data frames in a discerning pattern-aware manner. Moreover, we integrate a data interpolation module into the edges of our structured graph data targeting at data imbalance, which fosters a more balanced distribution across the various classes of edges. Our empirical analysis on select wireless IoT intrusion datasets shows GINE’s superiority, consistently outperforming state-of-the-art methods in classification metrics, including accuracy, F1-Score, False Alarm Rate, etc. Through a simulated wireless environment, we demonstrate GINE’s robust scalability, even in unpredictable wireless networks.

Vehicle routing, being a major concern of any industry with transportation requirements (manufacturing, supply-chain, travel and tourism, etc.), offers immense scope for research. Due consideration of this fact has motivated the development of the approach illustrated hereafter. In this article, a vehicle routing problem (VRP) with generalized fuzzy travel times, multiple depots, split delivery (including inter depot split), and heterogenous, capacitated, alternative fuel driven vehicles, is studied. A hybrid genetic algorithm (GA) is designed to produce efficient solutions. Since traditional methods are incapable of computing the expected values of such fuzzy variables, the technique of fuzzy simulation is incorporated in the GA. Five alternative fuel vehicles-electric, hybrid, diesel, biodiesel, and CNG, are evaluated vis-a-vis multiple criteria using fuzzy hierarchical technique for order preference by similarity to ideal solution (TOPSIS) and their respective scores are input in the hybrid GA for sustainable, apt, and low-cost assignment of vehicles to routes. The algorithm is run for multiple combinations of crossover and mutation probabilities, vehicle capacities, location instances, and number of generations. The experimental results substantiate the robustness of the proposed approach and suffice to project the strength of the computationally challenging model.

TOM (stands for Theoretically Objective Measurements of Software Development Projects) is a set of services that are in charge of helping developers or teams in the process of identifying anomilies within their software development process, and providing a list of preventive or corrective actions (aka CAPAS) that positively impact the process. and in this way to improve the quality of the final product and its development process. In order to get help from TOM, it is as simple as adding our bot (@0capa) to the list of collaborators in your repository, and with this our bot will automatically take care of obtaining different metrics from your repository, in order to suggest actions to take into account to that in your future updates the identified anomalies are not repeated. This paper presents the underlying research on this idea.