International Journal of Computing, Intelligence and Security Research

HAZARDOUS WASTE MANAGEMENT THROUGH OBJECT DETECTION USING COMPUTER VISION

2025-03-28T08:38:22+00:00

The management of hazardous waste is a global challenge, with approximately 1.5 billion tons of municipal solid waste generated annually, projected to reach 2.2 billion tons by 2025. Developing nations, including Nigeria, face significant issues with improper waste disposal, contributing to severe environmental hazards. Nigeria alone generates 2.4 million tons of hazardous waste each year, much of which ends up in landfills, waterways, and incinerators. Among these, sanitary pads and baby diapers contain non-biodegradable compounds such as dioxins and furans, which persist in the environment for centuries and release toxic emissions when burned. This research presents an automated waste detection system using Faster R-CNN implemented in Detectron2. A dataset of 5,000 images was collected, pre-processed, and split into training 70%, validation 15%, and testing 15% sets. The Faster R-CNN X101, R100, and R50 models were trained and evaluated, with Faster R-CNN X101 achieving the highest accuracy of 98%. The results demonstrate the effectiveness of deep learning in sanitary waste classification and its potential for improving waste sorting and environmental sustainability.

Assessment of the Impact of Cybersecurity Legal Frameworks on the Telecommunications Sector in Nigeria

2025-03-19T12:47:41+00:00

The Nigerian telecommunications sector has witnessed huge implementation and evolution of various cybersecurity legal frameworks, driven by rapid technological advancements and the convergence of telecommunications and information technology (IT). This convergence has resulted in increased connectivity but proportionately heightened cybersecurity challenges. Despite the existence of these frameworks, no comprehensive impact assessment has been conducted to evaluate their effectiveness. This paper addressed this gap by assessing the impact of the cybersecurity legal frameworks on the telecommunications sector. The study developed an impact assessment model that computes the Cybersecurity Legal Framework Impact Index (CLFII), to measure the overall impact of these legal frameworks on the telecoms sector. Data were collected from 43 participants, and the results were analysed across five impact categories (IC₁-IC₅). The findings revealed that over 83% of respondents fell within the IC₃ range (0.41–0.61), while 16% scored in the IC₄ range (0.61–0.81). Two key metrics, Legal Framework Impact Assessment Metrics (LFIAMs), were identified to evaluate the frameworks’ impact on cybersecurity capabilities and collaborations. The results showed that while the legal frameworks have significant positive impact on collaborations (74% of participants scoring in the C₄ range), their impact on building cybersecurity capabilities was less substantial, with all participants scoring in the C₃ range. These findings highlight the need for enhancement of the capacity-building measures in Nigeria’s telecommunications sector.

Wireless sensor network Energy -Efficient clustering in wireless sensor network using a hybrid meta heuristic approach based on firefly optimization and genetic algorithm

2025-03-26T21:09:05+00:00

Wireless Sensor Networks (WSNs) are essential for applications such as military operations, healthcare, and environmental monitoring. However, a major challenge in WSNs is extending the network lifetime, which can be effectively managed through a cluster-based network organization. Choosing the best cluster head is essential since it has a direct impact on network performance. However, problems including early node depletion, unequal energy distribution, and shortened network longevity are frequently caused by the cluster head selection techniques now in use. These issues have not been resolved by conventional methods like Randomized Clustering and Fixed Cluster Head selection, underscoring the need for more effective approaches. This paper presents an optimized cluster head selection technique that combines Genetic Algorithm (GA) and Firefly Optimization (FFO) in a hybrid metaheuristic approach to overcome these difficulties. Cluster heads are first identified and their positions are updated using FFO. Then, GA employs fitness values to determine which cluster head is most effective for transmitting data to the base station. According to simulation data, the suggested algorithm, FOGA, improves network lifetime by 1% over FFO and 2% over GA, outperforming both FFO and GA. Compared to FFO and GA, energy usage is lower by 15% and 25%, respectively. These findings show that FOGA successfully increases network lifetime and energy efficiency.

An Ensemble Based Deep Learning Architecture for Fish Disease Detection and Classification

2025-05-02T06:25:16+00:00

Fish diseases pose a major threat to aquaculture, leading to significant economic and ecological consequences. Fish diseases are a serious problem in aquaculture, causing economic losses and harming the environment. This study presents an ensemble deep learning model that combines ResNet50 and EfficientNetB0 to accurately detect and classify fish diseases from images. A total of 1,747 images were collected and grouped into seven classes, including different types of bacterial, fungal, viral, parasitic diseases, and healthy fish. Several preprocessing steps were used to improve image quality and help the model perform better. The ensemble model uses the strengths of both networks, along with global average pooling and dense layers, to make predictions. The model performed very well, achieving 98.5% accuracy, 98% precision, 97.9% recall, and a 97.8% F1-score. The confusion matrix, training and validation accuracy, and training and validation loss show that the model is reliable and works well across different disease types. These results suggest the model can be used in real-time systems to monitor fish health, reduce disease-related losses, and support food security. This study shows that using ensemble deep learning can be a powerful, accurate, and practical solution for managing fish diseases in aquaculture, which can significantly benefit aquaculture productivity, sustainability, and food security.

An enhanced garbage image classification using deep learning Techniques.

2025-05-16T20:44:29+00:00

The increasing volume of waste generated globally has necessitated the development of efficient waste management systems. Traditional methods of waste sorting are labor-intensive, time-consuming, and prone to human error. In this research a deep learning-based approach for automated garbage image classification was developed, focusing on six distinct categories: metal, paper, organic, battery, plastic and glass. Leveraging convolutional neural networks (CNNs), the system aims to accurately classify waste materials from images, thereby facilitating efficient recycling and waste management processes. The dataset used for training and evaluation consists of labeled images of various waste types, preprocessed and augmented to enhance model performance. Experimental results demonstrate the effectiveness of the proposed model in achieving high classification accuracy, highlighting its potential for real-world deployment in smart waste management systems. This research contributes to the growing field of environmental sustainability by providing a scalable and automated solution for waste classification.

Optimizing Task Scheduling in Cloud Computing: Development of a Refined Round Robin Algorithm with Dynamic Time Quantum Adjustment

2025-02-14T12:47:08+00:00

Cloud computing has transformed the landscape of modern computing by providing scalable and on-demand access to computational resources. Efficient task scheduling is a critical aspect of cloud computing, directly impacting system performance and resource utilization. The conventional Round Robin algorithm, while commonly used, suffers from limitations such as fixed time quantum and inability to adapt to varying task priorities, leading to suboptimal scheduling outcomes. This research addresses these limitations by developing a Refined Round Robin Algorithm (RRRA) that introduces a dynamic time quantum adjustment mechanism based on task priority and system load conditions. The proposed algorithm calculates the time quantum dynamically using a formula that incorporates an initial time quantum, a system-determined constant, and the task's priority level. The study evaluates the performance of the RRRA in a simulated cloud computing environment using MATLAB, with three scenarios representing different task arrival and priority conditions. Key performance metrics, including waiting time, turnaround time, throughput, and the number of context switches, were analyzed and compared with traditional scheduling algorithms, such as the Standard Round Robin, Round Robin with Adaptive Priority Scheduling (RRAPS), and Dynamic Round-Robin Heuristic Algorithm (DRRHA). The results demonstrate that the Refined Round Robin Algorithm significantly improves scheduling efficiency, particularly in reducing waiting time and context switches while enhancing system throughput. The findings suggest that the RRRA can serve as an effective scheduling solution in cloud environments, providing a balanced approach to task prioritization and dynamic resource allocation.

Operational Integration of Cyber Threat Intelligence in Modern Security Operations Centers: A Design Science Approach

2025-09-26T07:19:38+00:00

The escalating volume, velocity, and sophistication of cyber threats necessitate the strategic integration of Cyber Threat Intelligence (CTI) into Security Operations Centers (SOCs). While CTI offers the potential to significantly enhance situational awareness, improve threat detection, and enable a proactive defense posture, its operational integration within SOC workflows often remains inconsistent and underdeveloped. This research employs a design science methodology to investigate the current state of CTI utilization in SOCs, identifying the critical technical and organizational challenges that impede its full adoption. We evaluate the efficacy of existing CTI platforms and standards, leading to the design of a novel framework for systematically embedding CTI into SOC operations with a focus on automation, contextual enrichment, and intelligent orchestration. The framework's utility is validated in a controlled SOC environment using a combination of real-world and synthetic threat intelligence. The evaluation, based on technical performance metrics and qualitative analyst feedback, demonstrates that a structured approach to CTI integration can significantly improve detection efficacy while reducing Mean Time to Detect (MTTD), Mean Time to Respond (MTTR), and triage time which can substantially enhance threat prioritization and decision-making. This paper culminates in the proposal of a CTI Operationalization Maturity Model, providing a structured roadmap and actionable guidance for organizations seeking to substantially enhance threat prioritization and decision-making.