Most of researches on wireless sensor network (WSN) are focused on how to reduce energy consumption to increase the network lifetime. There are few researches solving the problem of energy optimization ensuring delay constraint. Whereas, the delay is important factor for applications that require delay‐sensitive data. Several works have been published to balance the energy consumption and delay. They achieved many different results but each proposal has certain limitations. Some proposals have high computational and messaging complexity. Some others have not found the optimal solution. In this study, we investigate in finding solution to improve the energy efficiency of sensor nodes satisfying end‐to‐end delay to transmit data from sensor nodes to sink in multi‐hop WSNs. Based on Lagrange relaxation method, we propose an aggregate cost function between energy consumption and delay as well as an efficient method to find the optimal multiplier for that objective function. We provide two algorithms to find paths with least energy consumption while maintaining end‐to‐end delay requirement from any sensor node to sink. Besides analyzing the complexity and convergence of the algorithm, the simulation results also show that the proposed algorithm achieved good balance between energy consumption and delay compared with the previous proposals.

In recent years, early detection and warning of fires have posed a significant challenge to environmental protection and human safety. Deep learning models such as Faster R-CNN (Faster Region based Convolutional Neural Network), YOLO (You Only Look Once), and their variants have demonstrated superiority in quickly detecting objects from images and videos, creating new opportunities to enhance automatic and efficient fire detection. The YOLO model, especially newer versions like YOLOv10, stands out for its fast processing capability, making it suitable for low-latency applications. However, when applied to real-world datasets, the accuracy of fire prediction is still not high. This study improves the accuracy of YOLOv10 for real-time applications through model fine-tuning techniques and data augmentation. The core work of the research involves creating a diverse fire image dataset specifically suited for fire detection applications in buildings and factories, freezing the initial layers of the model to retain general features learned from the dataset by applying the Squeeze and Excitation attention mechanism and employing the Stochastic Gradient Descent (SGD) with a momentum optimization algorithm to enhance accuracy while ensuring real-time fire detection. Experimental results demonstrate the effectiveness of the proposed fire prediction approach, where the YOLOv10 small model exhibits the best balance compared to other YOLO family models such as nano, medium, and balanced. Additionally, the study provides an experimental evaluation to highlight the effectiveness of model fine-tuning compared to the YOLOv10 baseline, YOLOv8 and Faster R-CNN based on two criteria: accuracy and prediction time.

Wireless sensor network (WSN) is composed of a large number of sensor nodes densely deployed in inhospitable physical environments. Due to limitations of sensor nodes in terms of memory, energy and computational capacities, the most important issue for designing sensor network protocols is energy efficiency. Although energy efficiency is a major concern in WSNs, it often suffers from the addition network delay. In this work, we first propose an energy and delay efficient hierarchical clustering scheme called BHC (Bruijn Hierarchical Clustering) for WSNs. It allows data transmission from sensor nodes to the base station (BS) in the form of multi-hop, multi-path and ensure energy efficiency and reasonable delay. Next, we provide data distribution algorithms from the sensor nodes to BS as quickly as possible and the most energy efficient. To evaluate the appropriateness of our proposal, we analyze the simulation results against another protocol in terms of communication overhead, total amount of energy dissipated in system and network delay using ns-2 network simulator.

With the rapid growth of online transactions, phishing attacks have become increasingly unpredictable, particularly those involving malicious Uniform Resource Locators (URLs). Currently, few studies have effectively combined manual and semantic features within a unified framework to both fully utilize the structural information and capture the deep context dependence of the character string. To address this gap, this study proposes a deep attention-based approach for phishing URL detection. Our approach first relies on the importance of manual features and the Bidirectional Encoder Representations from Transformers (BERT) model to extract semantic feature vectors. Subsequently, a hybrid deep learning architecture comprising Bidirectional Long Short-Term Memory (BiLSTM) layers, an attention mechanism, and fully connected dense networks is employed to classify URLs as either phishing or legitimate. Experimental results demonstrate that our proposed model achieves a high classification accuracy of 96.77%, while ablation analysis highlights the individual contributions of key components, including BERT embeddings, attention mechanism, LSTM layers, and feature types, to overall model performance. Finally, by training on a Kaggle benchmark dataset and testing on real-world phishing samples, the study confirms the model's strong generalization capability in detecting emerging phishing threats.