International Journal of Electrical and Computer Engineering Systems

From Reactive to Proactive: Automating IP Threat Intelligence in SIEM Systems for Cyber Threat Detection

Abeer Alhuzali — 2026-01-08

Digital transformation has provided more opportunities for cybercriminals and exposed organizations to sophisticated threats. Organizations should continuously evaluate their security measures and implement defensive actions to prevent attacks by cybercriminals. Security Information and Event Management (SIEM) systems, deployed within Security Operations Centers (SOCs), allow organizations to identify security risks and vulnerabilities, monitor unusual behavior, and automatically respond to security events. However, SIEM platforms require certain functional enhancements. For instance, security analysts often use external threat intelligence platforms to check suspicious IP addresses manually. This results in longer response times and a greater likelihood of human error. Hence, this paper proposes an integration framework that correlates the functionality of an external threat intelligence platform (AbuseIPDB) with a SIEM system (IBM QRadar) to automatically validate suspicious IP addresses without the need for manual checking. The goal of this integration is to increase the efficiency of threat analysis, incident response, and SIEM-based threat detection. Tests demonstrated that our proposed framework shortens the threat validation time by up to 97.7%, compared to manual processes. Additionally, our system reduces false positives by capitalizing on contextual threat intelligence, thus allowing SOC teams to prioritize critical alerts.

Enhanced Crop Yield through IoT-Based Soil Monitoring and Machine Learning Analysis for Rice and Sugarcane Cultivation

Deepthi Gorijavolu — 2026-01-08

Agriculture, a cornerstone of global economies, faces persistent challenges in efficient crop monitoring. This study introduces a groundbreaking IoT-based framework, integrated with a novel Deep Ensemble Learning (DEL) technique. The cuurent study objective is to enhance rice and sugarcane yield through monitoring soil parameters precisely. The framework employs an array of sensors, including moisture and pH sensors, to determine key soil properties: moisture content, pH level, Nutrient Retention Capability (NRC), and oxygen content. These parameters are crucial in assessing nutrient availability, Organic Carbon Content (OCC), soil texture, and root health. Data captured by sensors is transmitted via an Arduino kit to the cloud, where it undergoes analysis by advanced deep learning models, namely Bidirectional Long Short-Term Memory (Bi-LSTM). The ensemble of models ensures high accuracy in predicting soil parameter. The farmers acquires the processed data through a mobile application that offers actionable insights and facilitating real-time, automated agricultural interventions. Empirical results from field trials demonstrate a significant enhancement in soil parameter detection and monitoring accuracy.The application enables the IoT and DEL-based system in rice and sugarcane fields that enhances the crop yeild by 97% compared to traditional schemes. The study demonstrates the potential of integrating IoT and machine learning in agriculture paradigm shift towards the precision farming, and sets a new standard for sustainable, efficient agricultural practices.

A Novel Approach for Diabetes Mellitus Detection Using a Modified Binary Multi- Neighbourhood Artificial Bee Colony Algorithm with Mahalanobis-Based Feature Selection (MBMNABC-Ma) and an Optimized Decision Forest Framework

Gaurav Pradhan — 2026-01-12

Diabetes is a critical global health issue caused by high blood sugar (hyperglycemia), leading to complications like cardiovascular disease, blindness, neuropathy, and kidney failure. Machine learning (ML) algorithms improve both the accuracy and efficiency of medical diagnoses. This study applies a Modified Binary Multi-Neighbourhood Artificial Bee Colony with Mahalanobis- based (MBMNABC-Ma) for a feature selection algorithm, combined with diverse ML models for diabetes identification. Compared to the conventional Binary Multi-Neighbourhood Artificial Bee Colony (BMNABC), MBMNABC-Ma improves classification accuracy and reduces computational complexity. Five diabetes datasets were analyzed using a 70-30% holdout cross-validation. The MBMNABC- Ma model, trained on Optimal Decision Forest (ODF) with Random Forest Ensemble (RFE), demonstrated high effectiveness. It achieved 97.23% accuracy on the Merged Datasets (comprising 130 US and PIMA datasets), 97.93% on the Iranian Ministry of Health Dataset, 96.05% on the Questionnaire Dataset, 98.39% on the Hospital of Sylhet Dataset, and 80.98% on the PIMA Dataset, with high specificity and sensitivity scores across all cases.

Enhancing Cold-Start Recommendations with Content-Based Profiles and Latent Factor Models

Amritha P — 2026-01-19

Recommendation systems have become an important tool for enhancing personalized recommendations across various domains. However, these systems face challenges, including the cold start problem, data sparsity, etc. In this paper, we present a novel recommendation model that integrates content-based and collaborative approaches to overcome these challenges. The proposed model uses TF-IDF vectorization over multiple item attributes to compute content similarity scores, and the SVD collaborative model captures latent user-item interactions. To further strengthen user preferences, a time-aware exponential decay function is used to acquire the most recent user preferences during the construction of user profiles for content-based prediction. Finally, the rating prediction is generated through a weighted fusion of content and collaborative models. Compared to benchmark models, our approach reduces RMSE by 3.06% and MAE by 3.23%, demonstrating an improvement in prediction accuracy. Furthermore, our method shows stable performance, with only a slight increase in prediction error (MAE with 8% and RMSE with 1.5% with a hybrid weight of 0.5) under cold-start conditions, indicating that the proposed method maintains strong stability and robustness even in data sparsity scenarios.

Impact of Ammonia (NH3) on the Energy Production in Photovoltaic Panels

Diego Rigoberto Aguiar — 2026-01-21

The increase in energy demand, the fossil energy crisis, and the trend towards using renewable energies from sources such as the sun or wind have led to the rise in photovoltaic installations. Some of these installations are being installed on farms. While it is true that irradiation levels, location, and inclination of the panels are considered, the influence of certain gases such as ammonia (NH3), which is present in poultry, pig and dairy farms, is not considered. The present study is carried out in a poultry farm, through the implementation of two data acquisition devices that will be located in two scenarios, the first one exposed to NH3 levels and the other one free of the influence of this gas, the prototypes are equipped with a 100W panel to measure the power generated and determine if there is a difference in the energy production produced by the influence of ammonia. Data was obtained for ten consecutive days, in which it was determined that the power generated by the panel decreased in the scenario with ammonia compared to the prototype without of influence of this gas, proving that NH3 influences the decrease in power generated in the solar photovoltaic panel, obtaining average losses of 5%. It is concluded that ammonia (NH3) influences the efficiency of energy conversion in photovoltaic solar panels.

Fast and Accurate Design of BLDC Motors Using Bayesian Neural Networks

Son Nguyen Thanh — 2026-01-23

Brushless direct current (BLDC) motors are gaining popularity over traditional direct current (DC) motors due to their higher efficiency, compact size, and precise control capabilities. This study proposes a fast and accurate approach to BLDC motor design using a Bayesian neural network (BNN). The BNN, a specialized form of the multi-layer perceptron (MLP), offers strong resistance to overfitting and performs effectively with noisy or limited datasets, making it well-suited for complex motor design problems. In the proposed method, the BNN is applied within an inverse modeling framework to map desired motor performance parameters to the corresponding design variables. A dataset for an outer-rotor BLDC motor—containing both design parameters and the resulting output torque—is generated through finite element analysis (FEA). Finally, a demonstration of BLDC motor design using the BNN validates the effectiveness of the proposed approach.

A Secure Data Aggregation for Clustering Routing Protocols in Heterogenous Wireless Sensor Networks

Basim Abbod — 2026-01-26

The paper presents a broadly elaborated, secure, and energy-efficient data aggregation scheme of the heterogeneous wireless sensor networks (HWSNs). This is motivated by two consistent shortcomings of existing work: (i) clustering-based routing algorithms like LEACH, SEP, and FSEP are inadequate on balancing the energy usage when there is a disparity in the node capabilities, and (ii) most ECC-based security systems create too much computation overhead to extend network lifetime. To satisfy such gaps, the given framework integrates the Spider Monkey Optimization Routing Protocol (SMORP) with a compact cryptographic implementer including the Improved Elliptic Curve Cryptography (IECC) and El Gamal Digital Signature (ELGDS) scheme. SMORP gives maximum consideration to cluster forming and multi hop forwarding and the IECC-ELGDS module that provides all the above data confidentiality, authentication and data integrity at a lower cost of computation. As compared to the previous strategies, the combination of routing optimization and elliptic-curve-based secure aggregation facilitates energy efficiency and high-security assurance in the resource- constrained nodes. MATLAB models show that the offered framework can boost network life up to 27 percent, residual energy up to 32 percent, and get a 96 percent packet-delivery ratio relative to LEACH, SEP, and FSEP. Moreover, the IECC-ELGDS module will need less time in encryption/decryption by 22-35 percent in comparison with ECC-HE, IEKC and ECDH-RSA. These findings support the idea that the SMORP-IECC-ELGDS is a viable and fast architecture to secure aggregation in the real-life HWSN deployment.