Browse
Recent Submissions
Now showing 1 - 5 of 14
- ItemA Feature Dynamic Enhancement and Global Collaboration Guidance Network for Remote Sensing Image Compression(Radioengineering Society, 2025-06) Fang, Q. Z.; Gu, S. B.; Wang, J. G.; Zhang, L. L.Deep learning-based remote sensing image compression methods show great potential, but traditional convolutional networks mainly focus on local feature extraction and show obvious limitations in dynamic feature learning and global context modeling. Remote sensing images contain multiscale local features and global low-frequency information, which are challenging to extract and fuse efficiently. To address this, we propose a Feature Dynamic Enhancement and Global Collaboration Guidance Network (FDEGCNet). First, we propose an Omni-Dimensional Attention Model (ODAM), which dynamically captures the key salient features in the image content by adaptively adjusting the feature extraction strategy to enhance the modelâ s sensitivity to key information. Second, a Hyperprior Efficient Attention Model (HEAM) is designed to combine multi-directional convolution and pooling operations to efficiently capture cross-dimensional contextual information and facilitate the interaction and fusion of multi-scale features. Finally, the Multi-Kernel Convolutional Attention Model (MCAM) integrates global branching to extract frequency domain context and enhance local feature representation through multi-scale convolutions. The experimental results show that FDEGCNet achieves significant improvement and maintains low computational complexity regarding image quality evaluation metrics (PSNR, MSSSIM, LPIPS, and VIFp) compared to the advanced compression models. Code is available at https://github.com/shiboGu12/FDEGCNet
- ItemPerformance Analysis of Relay Model-based Energy Harvesting in CR-WBAN(Radioengineering Society, 2025-06) Srinivasan, S. N.; Suresh Kumar, P.; Duraisamy, S.An emerging technique was introduced to extend the network lifetime of energy-limited relay nodes in wireless networks. In this paper, the spectral and energy efficiency of Wireless Body Area Networks (WBAN) is investigated. A novel Relay model-based WBAN with Energy Harvesting for enhancing spectrum utilization using Cognitive Radio (CR) technology. This approach involves the surrounding of RF signals, allowing the nodes to gather energy and process data within a WBAN, specifically for medical monitoring purposes enabling the coexistence of diverse implanted devices while maintaining their QoS. It facilitates the simultaneous operation of distinct sensor nodes for primary and secondary networks in on-body CR-WBAN, categorizing nodes based on medical and non-medical applications. The proposed protocols designed for energy harvesting notably Time Switching System (TSS) and Power-Splitting System (PSS) are utilized to enable the cooperation of secondary nodes with the primary network, allowing them to access the spectrum in exchange. The numerical analysis of proposed overlay CR-WBAN in aspects of outage probability, coverage analysis, throughput analysis, and energy efficiency performances considering a delay-limited scenario are examined. The numerical simulations confirm the validity of all the developed theoretical analyses and underscore the efficacy of the considered scheme by verifying using Monte Carlo simulations.
- ItemComparative Analysis of Input Image Characteristics in Convolutional Neural Network-based Signature Detection(Radioengineering Society, 2025-06) Adamec, M.; Turcanik, M.The detection of malware represents a primary concern in contemporary computer security and is therefore imperative for the protection of systems and data integrity. This research presents an innovative approach to comparing diverse input image formats with the objective of identifying the optimal methodology for detecting specific malware-related signatures using convolutional neural networks (CNN), which have been specifically developed by the authors for this purpose. Subsequently, machine code instructions are generated and then converted into four distinct image format options. The four image formats, namely 1xN fixed, 1xN scalable, NxN fixed, and NxN scalable, are subsequently employed for the training of the CNN. The study assesses the formats in question in terms of training time, accuracy, and computational complexity. The results demonstrate that the NxN scalable format exhibits the highest accuracy with accelerated training times in comparison to other formats. Furthermore, the scalable format necessitates only 25% of the original pixel count for a 96% classification success rate. The utilization of the NxN scalable format for machine code instruction representation results in enhanced accuracy, accelerated training, and a considerable reduction in pixel usage, indicating a promising avenue for optimizing the efficiency of malware detection.
- ItemEnhancing WSN Lifespan Based on Efficient-Energy Management Approach for Cluster Head Selection in IoT Application(Radioengineering Society, 2025-06) Mehra, B.; Datar, A.Wireless sensor networks (WSNs) are one of the most important components in the connected world i.e. Internet of Things (IoT). WSN is a network of distributed sensor nodes that communicate wirelessly to transmit and receive real-time data. These sensor nodes play a crucial role in monitoring various environments, enabling smarter decision-making and improving efficiency across numerous applications. This paper presents an energy-efficient protocol based on low energy adaptive clustering hierarchy (LEACH) for improving the lifetime of WSN. The proposed method modifies the basic LEACH protocol and incorporates the factors of residual energy of the network, number of neighbor nodes, average energy of the network, and threshold distance between the nodes and base station. The proposed work compares the result with the existing methods and has shown the improvement in the network performance parameter metrics. The simulation results show an improvement in the network lifetime due to better energy management, thus increasing the number of data packet transfers.The proposed method has shown improvement by 13% over the first dead (FD) node of EEBC-LEACH, 5% improvement over half dead (HD) node of PEGASIS, and 3% improvement over all dead (AD) nodes of FBCR-LEACH.
- ItemAn Effective Routing Algorithm to Minimize the UAV Routing Time and Extend the Network Lifetime in Clustered IoT Network(Radioengineering Society, 2025-06) Zafor, H.; Sheikh, T. A.; Mazumdar, N.; Nag, A.Recently, unmanned aerial vehicles (UAVs) have become more popular due to their ease of adaptability and capability to carry out a variety of activities, including the delivery of services, monitoring and surveillance in military and civilian contexts. One of the most significant challenges in UAV operation is ensuring maximum network lifetime and management of their limited battery life. To solve these problems, we have proposed an effective routing algorithm that finds the best route to minimize UAV routing time and extend network lifetime. This is performed using the Ant Colony Optimization with Local Search (ACO-LS) algorithm for data collection from the clustered IoT network by UAV to ensure maximum network lifetime. It solved the routing problem in the minimum time in the presence of multiple charging stations and optimized the routing path. The simulation was carried out using various performance metrics: network lifetime (NT), energy consumption (EC), number of alive nodes (NAN), and packet delivery percentage (PDP). These parameters were compared with some existing algorithms such as Ant Colony Optimization (ACO), Particle Swarm Optimization (PSO), and Genetic Algorithm (GA) and found that our proposed algorithm performs better in terms of higher NT, less EC, more NAN, and higher PDP than the existing algorithms ACO, PSO, and GA.
- «
- 1 (current)
- 2
- 3
- »