The Internet of Things is being used far more frequently. Malicious attacks are on the rise in tandem with the growth of technology such as smart devices, smart homes, and other forms of automation. Taking care of network security is crucial. An effective network intrusion detection system is essential for defending Internet of Things devices against malware. It consists of feature selection, classification, and dimensionality reduction. Principal component analysis (PCA) is used to reduce dimensionality, and ant colony optimization (ACO) is used to choose features. Following that, the Extreme Gradient Boost Algorithm (XG-Boost) is used to carry out the classification. Python is used to implement the benchmarked intrusion detection NSL-KDD dataset on Colaboratory. The system outperformed the current intrusion detection system with 99.27 % accuracy, 99.6% precision, 98.8% recall, and 99.2% F1-score. Based on testing results, the system seems to be robust when evaluating several performance criteria.

Identifying influential nodes is vital for addressing the task of influence maximization in complex networks. Traditional methods typically assess a node’s influence using centrality measures that focus solely on network topology. However, a node’s influence is also affected by other factors, such as temporal activity and infection rates. Machine learning (ML) models offer a more nuanced approach by integrating multiple factors to assess a node’s influence potential. However, these ML models often classify nodes as either influential or not, without evaluating how well they propagate influence. To address these limitations, we have reformulated the problem of assessing node’s influence potential as a regression chore and developed the BO-CBoost model. Our model firstly generates a feature vector for every node reliant on both structural and temporal aspects of a node along with the infection rate. This feature vector is then used for model building and testing. We compared BO-CBoost against benchmark models like decision trees and linear regression, as well as state-of-art models such as LightGBM and XGBoost. Experiments conducted on three diverse real-world networks showed that BO-CBoost outperforms the baseline models. It achieved the most precise influence spread predictions, with a minimum average mean squared error of 0.056 and the lowest average absolute error of 0.118. Thus, BO-CBoost proved to be a more effective tool for predicting influence potential of nodes in complex networks.

Software Effort Estimation (SEE) is a technique for properly anticipating staff during the development of a project. Software development process is complicated and the most critical step is estimating the staff effort required for the projects. Correctly identifying the precise quantity of effort required in the initial phases of development can be problematic. Researchers have developed many machine learning and deep learning algorithms to improve the accuracy. A hybrid model PSO (Particle swarm optimisation)-based artificial neural network (ANN) model for software effort estimating (SEE) is presented and has demonstrated to outperform traditional methods. This model was evaluated using several datasets, including China, Albrecht, Kitchenham, Desharnais, Maxwell, Kemerer and Cocomo81. The machine learning algorithms Bagging, Boosting Averaging, weighted Averaging, Stacking using RF specify algorithm, are widely used in real word applications for software development. Our experiments demonstrate that the hybrid ANN-PSO model outperforms the traditional machine learning algorithm in regards to accuracy, precision, and recall. The ANN-PSO hybrid model achieves an average accuracy compared to the ML algorithm. The results of this study highlight the potential of hybrid deep learning models in tackling complex problems, particularly those involving large datasets and high-dimensional feature spaces. The hybrid ANN-optimized PSO has shown exceptional accuracy, with consistently elevated R2-squared (R 2) values across several datasets. Furthermore, the model shows performance metrics RMSE and MAE values, implying reliable predictions. These results support the effectiveness and utility of the paradigm. The low MAE of the model indicates that it may predict software development task requirements with reasonable accuracy. Given these remarkable outcomes, the hybrid PSO-optimized ANNs model will surely be important in software development.

Software defect prediction is greatly hampered by class imbalance, which frequently results in predictions that are biassed in favor of the majority class and inadequate identification of defective instances. This work assesses the usefulness of ensemble techniques in enhancing fault prediction accuracy and looks into how class imbalance affects the prediction performance of different machine learning classifiers. Group techniques like AdaBoost, GBoost, Stacking, and Voting were combined with four base classifiers: BNB, GNB, Random Forest, and SVM. With distinct assessments for defective (Class 1) and non-defective (Class 0) classes, the accuracy, precision, recall, and F1-score were used to compare the performance of these models. The research was carried out in two stages: first, ensemble approaches were tested on datasets that were unbalanced, and then PCA was integrated for feature reduction. According to the results, the Voting ensemble method worked better than the other approaches, regularly providing both classes with balanced recall and precision. Upon applying PCA, the Voting+PCA model exhibited noteworthy enhancements in all datasets (CM1, PC1, KC1, KC2), attaining superior accuracy and optimized metrics particular to each class. Interestingly, the Voting+PCA model performed better on all datasets and achieved accuracies of up to 98.20% for PC1. According to the results, combining PCA with ensemble models—in this case, the Voting method—improves predictive performance even when there is a class imbalance, making it a reliable strategy for predicting software defects.

This paper offers a comprehensive assessment of advanced cybersecurity attacks, their prevention, and future directions in the field. It aims to provide an overview of some of the most significant cyber-attacks on critical facilities that have occurred over the past 20 years. This paper aims to study various types of cyber-attacks, their effects, vulnerabilities, and the attackers and victims involved. The research identifies five major categories of attacks: web attacks, malware attacks, active attacks, passive attacks and cryptographic attacks. Each category is further divided into distinct types of cyber-attacks, which are described in terms of their proposals, evaluation parameters, characteristics and methodologies used. A summary of these attacks across various parameters is tabulated in this paper to facilitate detailed analysis. Additionally, the paper examines several cutting-edge solutions and preventive measures and reviews research gaps and limitations associated with various cyber-attacks. This study is significant as it provides researchers with a thorough review to better understand different cyber-attacks and recent developments in the field of cybersecurity.

Social media platforms are integral to shaping public discourse and facilitating the rapid dissemination of both positive and negative information within the contemporary digital landscape. However, the detection and management of abusive content on these platforms present significant challenges, as such content has the potential to incite social unrest and perpetuate hate. In response to this pressing issue, our study introduces an advanced DistilBERT model specifically designed for the efficient identification of abusive text. By leveraging the compact yet powerful BERT architecture, our model adeptly captures subtle contextual nuances, thereby enhancing predictive accuracy. A pivotal component of our methodology is the rigorous preprocessing of the dataset, which includes the removal of redundant or duplicate samples to ensure dataset integrity and mitigate biases that could compromise the model’s ability to generalize from unique instances. The DistilBERT model exhibits exceptional performance, achieving near-perfect scores in accuracy, precision, recall, and F1-score, significantly surpassing existing state-of-the-art and baseline methodologies. These findings underscore the model’s robustness and its potential as an effective instrument for monitoring and mitigating online abuse. By proposing a scalable solution that incorporates comprehensive data preprocessing, this research contributes to advancing the field of abusive content detection and aims to promote safer and more inclusive online communities.