As the Internet of Things (IoT) expands rapidly and 5G networks become more widespread, the need for strong cybersecurity measures in IoT systems has become increasingly critical. Traditional security methods are no longer sufficient due to the shear volume, diversity, and limited processing capabilities of IoT devices. The high data transmission speeds of 5G networks further intensify the potential risks, making it essential to implement effective security measures. One of the major threats to IoT systems is Cross-Site Scripting (XSS) attacks. To address this issue, we introduce a new machine learning (ML) approach designed to detect and predict XSS attacks on IoT systems operating over 5G networks. By using ML classifiers, particularly the Random Forest classifier, our approach achieves a high classification accuracy of 99.89% in identifying XSS attacks. This research enhances IoT security by addressing the emerging challenges posed by 5G networks and XSS attacks, ensuring the safe operation of IoT devices within the 5G ecosystem through early detection and prevention of vulnerabilities.

This study presents a new comparative analysis of the cognitive control methods of HVAC systems that assess reinforcement learning (RL) and traditional proportional-integral-derivative (PID) control. Through extensive simulations in various building environments, we have shown that while the PID controller provides stability under predictable conditions, the RL-based control can improve energy efficiency and thermal comfort in dynamic environments by constantly adapting to environmental changes. Our framework integrates real-time sensor data with a scalable RL architecture, allowing autonomous optimization without the need for a precise system model. Key findings show that RL largely outperforms PID during disturbances such as occupancy increases and weather fluctuations, and that the preferably optimal solution balances energy savings and comfort. The study provides practical insight into the implementation of adaptive HVAC control and outlines the potential of RL to transform building energy management despite its higher computational requirements.

Wearable devices and deep learning methods for Human Activity Recognition (HAR) have attracted a lot of interest because they could change healthcare monitoring. This study presents a CNN-LSTM model to accurately and reliably detect human movements from smartphone sensor data. The proposed model takes advantage of both the strengths of Long Short-Term Memory (LSTM) networks for modeling time and Convolutional Neural Networks (CNNs) for extracting features from space. This enables determining how the input data change over time and space. This study examines whether this method can work and is practical in real-life healthcare settings, focused on uses such as watching patients from distance, caring for the elderly, and therapy. The proposed model was evaluated on publicly accessible standard datasets. Various architectural configurations and hyperparameters were examined to determine their performance. The proposed CNN-LSTM model performed well and has great potential for practical use in activity tracking and environment understanding systems.

Actual load balancing in parallel and distributed systems ruins a serious task due to workloads’ dynamic nature and resource availability. Existing scheduling procedures continually fail to regulate real-time alterations, leading to suboptimal performance and resource underutilization. Our study validates dynamic and effective load distribution by combining novel systems and optimization techniques to handle these issues. We utilize a comprehensive dynamic scheduling approach in this work to provide efficient load balancing in distributed and parallel systems. In this example, we start by using Round-Robin Allocation with Sunflower Whale Optimization (RRA-SWO) to perform an allocation procedure. The allocation step is followed by the Hybrid Ant Genetic Algorithm (HAGA), which is used to schedule tasks in parallel. The Least Response Time (LRT) technique for the Load Monitoring procedures will be developed once the job scheduling is complete. The Harmony Search Algorithm with Linear Regression (LR-HSA) is then used to do Distributed Computing-based Load Prediction and Adjustment. Alongside ongoing observation, this is carried out. Finally, we use the Least Recently Used (LRU) technique to do dynamic load balancing. Performance evaluations are using CloudSim and NetBeans 12.3, metrics like Packet Delivery Ratio at 98 (%), Average Response Time at 65 (s), Task Success Rate at 95 (%), Memory Utilization Rate at 80 (%), and Throughput at 97 (%) are all analyzed to validate our strategy.

Driver drowsiness is a major cause of road accidents worldwide, leading to thousands of injuries and fatalities each year. Detecting early signs of fatigue remains a critical challenge in road safety and intelligent transportation systems. This paper proposes a novel deep learning-based framework named SAFE-DRIVE-AI, designed to detect drowsiness in real-time by analyzing visual cues from the driver's eyes. The proposed framework integrates three components: A Convolutional Neural Network (CNN) to extract spatial features from eye images, a Long Short-Term Memory (LSTM) layer for capturing temporal patterns such as blink duration and frequency, and an Attention mechanism to enhance the model’s focus on the most relevant time steps. To validate the effectiveness of Deep Learning (DL) techniques, a comparative analysis was conducted using both traditional Machine Learning (ML) models (Logistic Regression, Decision Trees, Random Forest, and Support Vector Machines) and DL models (CNN, LSTM). The experimental results showed that the DL models significantly outperformed the ML ones in all metrics. The hybrid CNN+LSTM model achieved an accuracy of 97.3% and an F1-score of 96.8%, being the most accurate approach. SAFE-DRIVE-AI is designed for real-world deployment, with potential integration into edge devices, 5G-enabled systems, and real-time alert mechanisms. The proposed method offers a practical and intelligent solution for enhancing driver safety through proactive fatigue monitoring.