LDAM: A lightweight dual attention module for optimizing automotive malware classification by Jiahui Chen, Mingrui Wu, Huiwu Huang

Get full text

Dynamic Relevance-Weighting-Based Width-Adaptive Auto-Encoder by Malak Almejalli, Ouiem Bchir, Mohamed Maher Ben Ismail

“…Unlike traditional autoencoders with fixed architectures, the proposed method introduces a dynamic relevance weighting mechanism that assigns adaptive importance to each node in the hidden layer. This distinctive feature enables the simultaneous learning of both the model parameters and its structure. …”
Get full text

Application of Improved Multi-Fractal Trend Removing Wave Model in the Analysis of Multi-Fractal Characteristics of Harmonic Signals by Jiebin Wen

“…In the analysis of even harmonics, the computational efficiency, resource consumption, stability, and parameter sensitivity of the research method were 96.6%, 31.2%, 93.7%, and 98.7%. …”
Get full text

A Dynamic Prediction Method for Rolling Bearings Residual Life via Multi-Stage Exponential Model by Xueyan Ye, Suhua Qiao, Chen Sun, Yinjun Wang

“…This method entails the computation of multiple signal characteristics from sample data to depict the bearing degradation process comprehensively. …”
Get full text

STar-DETR: A Lightweight Real-Time Detection Transformer for Space Targets in Optical Sensor Systems by Yao Xiao, Yang Guo, Qinghao Pang, Xu Yang, Zhengxu Zhao, Xianlong Yin

“…First, the improved MobileNetv4 (IMNv4) backbone network is developed to significantly reduce the model’s parameters and computational complexity. Second, group shuffle convolution (GSConv) is incorporated into the efficient hybrid encoder, which reduces convolution parameters while facilitating information exchange between channels. …”
Get full text

An Experimental Study of the Gemination in Arabic Language by Kamel FERRAT, Mhania GUERTI

“…To extract the feature characteristics, we have carried out an acoustic analysis by computing the values of frequency formants, energy and durations of the consonants and subsequent vowels in the various [VCV] and [VCgV] utterances (Cg: geminate consonant). …”
Get full text

Balancing complexity and accuracy for defect detection on filters with an improved RT-DETR by Maoyuan Zhang, Xiaojuan Wei, Guojun Liu, Mengxu Chen, Chunxia Zhao, Yingxiao Liu, Zhikang Bao, Yunfeng Guo, Run An, Pengcheng Zhao

“…Furthermore, the model reduces parameter count by 6.9% and computational load by 13.1%, demonstrating its improved efficiency. …”
Get full text

Semantic Segmentation Method for High-Resolution Tomato Seedling Point Clouds Based on Sparse Convolution by Shizhao Li, Zhichao Yan, Boxiang Ma, Shaoru Guo, Hongxia Song

Get full text

Using lightweight method to detect landslide from satellite imagery by Jinchi Dai, Xiaoai Dai, Renyuan Zhang, JiaXin Ma, Wenyu Li, Heng Lu, Weile Li, Shuneng Liang, Tangrui Dai, Yunfeng Shan, Donghui Zhang, Lei Zhao

“…Increasingly general-purpose detection models are being deployed for these complex and dynamic tasks involving features that are difficult to characterize. However, these models are computationally expensive and memory-hungry, while the accuracy and detection efficiency remain wanting. …”
Get full text

Dataset of SCAPS-1D simulated halide perovskite solar cells with SHAP and machine learning-based PCE optimizationZenodo by Ivan E. Novoselov, Alexander M. Gvozdev, Andrey A. Smirnov, Ivan S. Zhidkov

“…The structured dataset supports a reproducible simulation environment and is designed to facilitate further research in computational materials science and renewable energy. …”
Get full text

Novel channel attention-based filter pruning methods for low-complexity semantic segmentation models by Md. Bipul Hossain, Na Gong, Mohamed Shaban

“…This is realized by recognizing the contextual importance of the feature maps in each layer of the models and the significance of each filter to the final model performance. …”
Get full text

Solution of clusterization problem by graph optimization methods by I.V. Konnov, O.A. Kashina, E.I. Gilmanova

“…The rapid growth in the volume of processed information that takes place nowadays determines the urgency of the development of methods for reducing the dimension of computational problems. One of the approaches to reducing the dimensionality of data is their clustering, i.e., uniting into maximally homogeneous groups. …”
Get full text

An AI-Based Horticultural Plant Fruit Visual Detection Algorithm for Apple Fruits by Bin Yan, Xiameng Li, Rongshan Yan

“…The Depthwise Separable Convolution (DWConv) module has many advantages: (1) It has high computational efficiency, reducing the number of parameters and calculations in the model; (2) It makes the model lightweight and easy to deploy in hardware; (3) DWConv can be combined with other modules to enhance the multi-scale feature extraction capability of the detection network and improve the ability to capture multi-scale information; (4) It balances the detection accuracy and speed of the model; (5) DWConv can flexibly adapt to different network structures. …”
Get full text

Mamba-YOLO-ML: A State-Space Model-Based Approach for Mulberry Leaf Disease Detection by Chang Yuan, Shicheng Li, Ke Wang, Qinghua Liu, Wentao Li, Weiguo Zhao, Guangyou Guo, Lai Wei

“…Traditional detection methods relying on chemical pesticides and manual observation prove inefficient and unsustainable. Although computer vision and deep learning technologies offer new solutions, existing models exhibit limitations in natural environments, including low recognition rates for small targets, insufficient computational efficiency, poor adaptability to occlusions, and inability to accurately identify structural features such as leaf veins. …”
Get full text

LiteMP-VTON: A Knowledge-Distilled Diffusion Model for Realistic and Efficient Virtual Try-On by Shufang Zhang, Lei Wang, Wenxin Ding

“…Despite their advantages, the substantial number of parameters and intensive computational requirements pose significant barriers to deployment on low-resource platforms. …”
Get full text

Detection of SAR Image Multiscale Ship Targets in Complex Inshore Scenes Based on Improved YOLOv5 by Zhixu Wang, Guangyu Hou, Zhihui Xin, Guisheng Liao, Penghui Huang, Yonghang Tai

“…Finally, to reduce the number of parameters and computational cost during model training, the normal convolution in the neck part is replaced with Ghost convolution. …”
Get full text

Direction-Aware Lightweight Framework for Traditional Mongolian Document Layout Analysis by Chenyang Zhou, Monghjaya Ha, Licheng Wu

“…Existing methods often struggle with the directional nature of traditional Mongolian text and require substantial computational resources. In this paper, we propose a direction-aware lightweight framework that effectively addresses these challenges. …”
Get full text

LSENet: A Lightweight Spectral Enhancement Network for High-Quality Speech Processing on Resource-Constrained Platforms by Hyeong Il Koh, Sungdae Na, Myoung Nam Kim

“…Although recent deep-learning-based speech enhancement (SE) methods significantly outperform traditional approaches, their computational demands often scale proportionally with their performance. …”
Get full text

PS-SLAM: A Visual SLAM for Semantic Mapping in Dynamic Outdoor Environment Using Panoptic Segmentation by Gang Li, Jinxiang Cai, Chen Huang, Hao Luo, Jian Yu

“…In addition, we use a stereo matching model to generate disparity images and compute depth information based on camera parameters. …”
Get full text

Fault Diagnosis Method of Rolling Bearing Based on 1D Multi-Channel Improved Convolutional Neural Network in Noisy Environment by Huijuan Guo, Dongzhi Ping, Lijun Wang, Weijie Zhang, Junfeng Wu, Xiao Ma, Qiang Xu, Zhongyu Lu

“…By introducing BiLSTM, an attention mechanism and a local sparse structure of a two-channel Convolutional Neural Network, the feature information of the noisy timing signal is fully extracted at different scales while reducing the computational parameters. …”
Get full text