Lightweight visible damage detection algorithm for embedded systems applied to pipeline automation equipment by Jiale Xiao, Lei Xu, Changyun Li, Ling Tang, Guogang Gao

“…The backbone of the algorithm, CSPHet, employs efficient combinatorial convolution and heterogeneous kernel convolution, incorporates a lightweight convolutional structure SL in the neck of the network, enhances the nonlinear representation and feature processing capability through channel shuffling, utilizes the lightweight self-attention mechanism Detect_SA for prediction, and employs a multilayered GhostConv to improve the computational efficiency. …”
Get full text

New Label-Free DNA Nanosensor Based on Top-Gated Metal–Ferroelectric–Metal Graphene Nanoribbon on Insulator Field-Effect Transistor: A Quantum Simulation Study by Khalil Tamersit, Abdellah Kouzou, José Rodriguez, Mohamed Abdelrahem

“…It has been observed that the feature of ferroelectric-induced gate voltage amplification using the integrated MFM structure can significantly enhance the biosensor’s sensitivity to DNA molecules, whether in terms of threshold voltage shift or drain current variation. …”
Get full text

An Intelligent Fault Diagnosis Model for Rolling Bearings Based on IGTO-Optimized VMD and LSTM Networks by Xianglong Luo, Fengrong Yu, Jing Qian, Biao An, Nengpeng Duan

“…The IGTO algorithm is used to optimize the parameters of VMD and LSTM, enhancing signal decomposition and feature extraction. …”
Get full text

A Low Complexity Linear Precoding Method for Extremely Large-Scale MIMO Systems by Salah Berra, Abderrazak Benchabane, Sourav Chakraborty, Kazuki Maruta, Rui Dinis, Marko Beko

“…As a result, spatial non-stationary features emerge as users view just a section of the antenna array, known as the visibility regions (VRs). …”
Get full text

HP-YOLO: A Lightweight Real-Time Human Pose Estimation Method by Haiyan Tu, Zhengkun Qiu, Kang Yang, Xiaoyue Tan, Xiujuan Zheng

“…We designed an Enhanced Large Separated Kernel Attention (ELSKA) mechanism and integrated it into the backbone network, thereby improving the model’s effective receptive field and feature separation capabilities, which enhances keypoint detection accuracy in challenging environments. …”
Get full text

Machine Learning in the Design and Performance Prediction of Organic Framework Membranes: Methodologies, Applications, and Industrial Prospects by Tong Wu, Jiawei Zhang, Qinghao Yan, Jingxiang Wang, Hao Yang

“…Methodologically, ML workflows—spanning data construction, feature engineering, and model optimization—accelerate candidate screening, inverse design, and mechanistic interpretation, as demonstrated in gas separations and nascent liquid-phase applications. …”
Get full text

A Comparative Analysis of Convolutional Neural Network (CNN): MobileNetV2 and Xception for Butterfly Species Classification by Mehta Pradnyatama, Christy Atika Sari, Eko Hari Rachmawanto, Hussain Md Mehedul Islam

“…Despite minimal performance difference, MobileNetV2 offers significant computational efficiency advantages with 4.15M parameters compared to Xception's 25.27M, while Xception provides marginally better classification. …”
Get full text

DC-WUnet: An Underwater Ranging Signal Enhancement Network Optimized with Depthwise Separable Convolution and Conformer by Xiaosen Liu, Juan Li, Jingyao Zhang, Yajie Bai, Zhaowei Cui

“…The encoder incorporates the Conformer module and skip connections to enhance the network’s multiscale feature extraction capability. Meanwhile, the network introduces depthwise separable convolution to reduce the number of parameters and improve computational efficiency. …”
Get full text

Lightweight RT-DETR with Attentional Up-Downsampling Pyramid Network by Nan Li, Xiao Han, Xingguo Song, Xu Fang, Mengming Wu, Qiulin Yu

“…This lightweight, efficient design integrates YOLOv9’s ADown module, the RepNCSPELAN4 module, and custom attention-based AdaptiveGateUpsample and AdaptiveGateDownsample modules for enhanced multi-scale feature fusion, reducing weight and complexity while optimizing real-time detection. …”
Get full text

A YOLOv8n-T and ByteTrack-Based Dual-Area Tracking and Counting Method for Cucumber Flowers by Liyang Su, Shujuan Zhang, Hongtu Zhang, Xiangsen Meng, Xiongkui He

“…The YOLOv8n-T incorporates a Coordinate Attention (CA) mechanism and lightweight modules while optimizing the loss function, thereby improving floral feature extraction capabilities and reducing computational complexity. …”
Get full text

Establishment and Test Effect of Artificial Intelligence Optimization Model Based on Convolutional Neural Network by Chunrong Zhou, Zhenghong Jiang

“…Convolutional neural networks (CNNs) are often used in tasks involving vision processing, and unclear images can hinder the performance of convolutional neural networks and increase its computational time. Furthermore, artificial intelligence (AI) and machine learning (ML) are related technologies, which are considered a branch of computer science, which are used to simulate and enhance human intelligence. …”
Get full text

Enhanced SVM-based model for predicting cyberspace vulnerabilities: Analyzing the role of user group dynamics and capital influx. by Yicheng Long

“…A standardized data preprocessing pipeline is constructed, including redundancy elimination, feature selection, and sample balancing, to ensure data representativeness and compatibility. …”
Get full text

Efficient Building Roof Type Classification: A Domain-Specific Self-Supervised Approach by G. Mutreja, K. Bittner

“…We propose a novel framework that incorporates a Convolutional Block Attention Module (CBAM) to enhance the feature extraction capabilities of EfficientNet. Furthermore, we explore the benefits of pretraining on a domain-specific dataset, the Aerial Image Dataset (AID), compared to ImageNet pretraining. …”
Get full text

LE-YOLOv5: A Lightweight and Efficient Neural Network for Steel Surface Defect Detection by Chengshun Zhu, Yong Sun, Hongji Zhang, Shilong Yuan, Hui Zhang

“…Therefore, based on the industrial scenario of low computational force, this study proposed a lightweight and efficient defect detector called LE-YOLOv5. …”
Get full text

A proximal policy optimization based deep reinforcement learning framework for tracking control of a flexible robotic manipulator by Joshi Kumar V, Vinodh Kumar Elumalai

“…The experimental validation on robotic manipulator system through hardware in loop (HIL) testing substantiates that the proposed framework offers faster convergence and better vibration suppression feature compared to the state-of-the-art policy gradient technique and actor-critic technique.…”
Get full text

A Novel Privacy Framework for Satellite Images Based on Theory of Chaos and Chess Pieces Castle and King by Nayef Alqahtani

“…Plaintext sensitivity –a necessary feature to foil the potential differential attacks, has been achieved by taking the SHA-256 hash codes of given images. …”
Get full text

RepVGG-MEM: A Lightweight Model for Garbage Classification Achieving a Balance Between Accuracy and Speed by Qiuxin Si, Sang Ik Han

“…The backbone of this model is derived from the lightweight RepVGG architecture, augmented by the integration of a multi-scale convolutional attention module to enhance high-quality feature extraction. Experimental results demonstrate that the RepVGG-MEM model outperforms its counterparts, achieving an accuracy of 93.26%, with a parameter count of 7.2 million and a floating-point operations (FLOPs) of 1.41 billion. …”
Get full text

SBCS-Net: Sparse Bayesian and Deep Learning Framework for Compressed Sensing in Sensor Networks by Xianwei Gao, Xiang Yao, Bi Chen, Honghao Zhang

“…The core of SBCS-Net is to optimize key SBL parameters through end-to-end learning. This can adaptively improve signal sparsity and probabilistically process measurement noise, while fully leveraging the powerful feature extraction and global context modeling capabilities of deep learning modules. …”
Get full text

Guiding a supersonic controlled object in a multi-position air basing radar by V. E. Markevich, V. V. Legkostup

“…The given guidance algorithms are a generalization of the method of proportional navigation widely used in practice and its modifications. A distinctive feature of the synthesized algorithms is the natural accounting for the nonlinear, multidimensional, and multiply connected structure of the control object, as well as the parameters of unsteady perturbations (acceleration of gravity, projections of the longitudinal acceleration of the object and acceleration of the target’s maneuver) that act in the guidance process.The unified kinematic differential equations that describe the dynamics of the control object, are obtained, and they can be used to synthesize a controller that operates according to switched or smoothly matched non-stationary optimality criteria (target functions, target integral manifolds). …”
Get full text

Broiler Behavior Detection and Tracking Method Based on Lightweight Transformer by Haixia Qi, Zihong Chen, Guangsheng Liang, Riyao Chen, Jinzhuo Jiang, Xiwen Luo

“…In addition, we propose a new cross-scale feature fusion network to optimize the neck network of the original model. …”
Get full text