Ensuring software reliability before public release is crucial, as most issues stem from human errors during development. Addressing these early through integrated testing resources can mitigate potential problems. This paper proposes an enhanced software fault prediction model using a meta-heuristic optimization technique. Our approach utilizes NASA’s datasets, incorporating data cleaning, feature dimensional reduction, and software fault prediction (SFP). The Extreme Learning Machine (ELM) parameters, such as weights and biases, were optimally determined using the improved particle swarm optimization (IMPSO) method. Model validation employed various metrics, including accuracy, sensitivity, specificity, F1 score, and MCC, through a 10 × 5 cross-validation. The model, named PCALDA+IMPSO-ELM, was tested on NASA datasets (CM1, KC2, KC3, MC1, and PC1), achieving prediction accuracies of 0.9696, 0.9836, 0.9482, 0.9799, and 0.9644, respectively. The findings demonstrate significant promise for the meta-heuristic optimization technique in software fault prediction with reduced feature sets, offering an effective method to enhance software reliability and anticipate fault-prone modules.

WSNs are integral to various applications, ranging from environmental monitoring to industrial automation. However, their vulnerability to malicious activities necessitates robust security measures. The proposed Ensemble Intrusion Detection System (ENS-IDS) leverages machine learning techniques to detect anomalies in the WSN data, identifying potential intrusions or security breaches. The system incorporates feature selection, model training, and real-time monitoring to enhance its accuracy and responsiveness. Evaluation metrics, including precision, recall, and F1 score, demonstrate the effectiveness of the ENS-IDS in mitigating security threats within the WSN environment. The presented ENS-IDS is evaluated on KDD and CICIDS2017 dataset and comparison on known classifiers such as SVM, random forest, extra tree, KNN, logistic regression, decision tree and ensemble classifiers such as XGBoost, CatBoost and LGBM. Our model ENS-IDS has given better accuracy, precision, recall and F1-score.

Research in the area of identifying the most influential users in social networks is currently regarded to be one of the most important areas of study. Through the examination of the most influential users on social networks, it is possible to analyze and, in some cases, manage the dissemination of information. A technique that is both quick and scalable is proposed in this research as a means of identifying the users with maximum diffusion capabilities in online social networks. This approach is suited for directed networks as well as undirected networks. The approach that has been suggested is comprised of four stages: (1) community detection, which involves the partial partitioning of the whole social network into communities that are connected to one another by the use of the Louvain algorithm; (2) the removal of communities that are not suitable; (3) selection of prominent nodes within the particular community; and (4) selection of the top k seed nodes. Experimental research was carried out on a number of datasets, each of which was of a different complexity. Using imperfect social networks, it has been demonstrated that the findings generate better outcomes for the diffusion of influence than the current related work models, and they do so with a much less amount of processing time being required.

Soft sensors offer an alternative approach for measuring process variables that cannot be directly obtained from hardware sensors, crucial for optimizing process outputs. This paper outlines a method for implementing an embedded soft sensor to estimate lactose concentration in a bioreactor using the MicroBlaze Soft Processor found in the Zynq SoC. The study focuses on employing the Extended Kalman Filter (EKF) algorithm for this purpose. The methodology involves designing a block using the MicroBlaze soft processor core in VIVADO, utilizing the Zybo board as the hardware platform. The embedded soft sensor is developed as a software application in C, configured to operate on the soft processor within the Zynq device. A comparative analysis is conducted among lactose output values obtained from simulation, hardware implementation, and true values derived from laboratory analysis. This approach underscores the efficacy of embedded soft sensors in enhancing process monitoring and optimization.

In this study, we propose a novel approach to enhance the security and efficiency of Vehicular Ad-Hoc Networks (VANETs) by integrating user authentication and cluster-based routing. The proposed method is divided into two segments. The first segment focuses on user authentication using a curve fitting technique, implemented via MATLAB simulation. Nodes are randomly deployed with geostationary coordinates and node keys. These nodes are clustered based on their geographical locations, and their legitimacy is verified using curve fitting. This ensures that only authenticated nodes participate in the network, thereby enhancing security and reliability. The second segment employs a modified Ad hoc On-Demand Distance Vector (AODV) protocol for routing, adapted to the clustered network structure. Route Requests (RREQs) are sent to Zone Heads (ZH) for validation and then forwarded to Cluster Heads (CH), where idle and execution costs are calculated based on buffer states and execution capacities. The proposed method also incorporates fog computing to enable localized data processing, reducing latency and improving scalability. The performance of the proposed method was evaluated through extensive simulations, measuring key metrics such as throughput, Packet Delivery Ratio (PDR), and latency. Results show that the proposed method achieves a throughput of 8367.141811 packets per second, a PDR of 0.83336875, and a latency of 6.606503751 seconds, outperforming state-of-the-art algorithms by significant margins. Specifically, the proposed method demonstrates a 7.5% improvement in throughput over Khudhair et al. and a 12.9% improvement over Ahmad et al. In terms of PDR, it shows an 8.8% increase over Khudhair et al. and a 7.1% increase over Ahmad et al. The latency reduction compared to these algorithms is 9.1% and 10.5%, respectively. These enhancements are attributed to the efficient clustering and authentication mechanisms, along with the integration of fog computing. The proposed method thus provides a comprehensive solution for secure and efficient VANET communication, paving the way for advanced intelligent transportation systems.

This work introduces a revolutionary YOLOv9 deep learning architecture-based method for facial emotion identification. Happy, Sad, Angry, Disgust, Natural, and Surprise are the six emotional classifications the research divides the 21,263 images into which the research divides. The model was trained on 88% of the dataset; 4% was used for testing and 8% for validation. The preprocessing operations were auto-orientation, zoom, rotation, and 416x416 pixel scaling. Training time was cut down significantly because the experiment was carried out with a T4 GPU from Kaggle. Five epochs later, the average mAP score of 0.85, average precision of 0.74, and average recall of 0.84 indicate encouraging emotional performance. At a mAP score of 0.98, the model showed exceptionally high accuracy in identifying disgust. With its reliable and effective approach to real-time emotion recognition in various applications, this work advances the field of affective computing.