A lightweight personnel detection method for underground coal mines by Shuai WANG, Wei YANG, Yuxiang LI, Jiaqi WU, Wei YANG

“…Secondly, the weighted multiscale feature fusion module (Weighted multiscale feature fusion moule) introduces learnable weights to give different attention to the feature layer. …”
Get full text

Improved UAV Target Detection Model for RT-DETR by Yong He, Yufan Pang, Guolin Ou, Renfeng Xiao, Yifan Tang

“…On the VisDrone2019 dataset, the mAP0.5 of the enhanced model demonstrates a 3.5% improvement, accompanied by a 6.1% and 2.9% reduction in parameters and computations, respectively. The efficacy of these enhancements is substantiated by the model’s superior performance in comparison to other target detection models at equivalent levels.…”
Get full text

A CT-based machine learning model for using clinical-radiomics to predict malignant cerebral edema after stroke: a two-center study by Lingfeng Zhang, Gang Xie, Yue Zhang, Yue Zhang, Junlin Li, Junlin Li, Wuli Tang, Wuli Tang, Ling Yang, Ling Yang, Kang Li

“…The radiomics features linked to MCE were pinpointed through a consistency test, Student’s t test and the least absolute shrinkage and selection operator (LASSO) method for selecting features. …”
Get full text

Ranking Assisted Unsupervised Morphological Disambiguation of Turkish by Hayri Volkan Agun, Ozkan Aslan

Get full text

An enhanced alpha evolution moss growth optimizer for prognostic prediction in spontaneous intracerebral hemorrhage by Lingxian Hou, Yongsheng Wang, Xiuqi Lin, Chengye Li, Huangrong Guo, Congcong Jin, Yi Chen, Huiling Chen, Jing Ji, Wenzong Zhu

Get full text

Lightweight pose estimation spatial-temporal enhanced graph convolutional model for miner behavior recognition by WANG Jianfang, DUAN Siyuan, PAN Hongguang, JING Ningbo

“…MEST-GCN improved upon the spatial-temporal graph convolutional network (ST-GCN) by removing redundant layers to simplify the model structure and reduce the number of parameters. It also introduced a multi-dimensional feature fusion attention module (M2FA). …”
Get full text

EnsembleXAI-Motor: A Lightweight Framework for Fault Classification in Electric Vehicle Drive Motors Using Feature Selection, Ensemble Learning, and Explainable AI by Md. Ehsanul Haque, Mahe Zabin, Jia Uddin

“…A lightweight framework for fault diagnosis in EV drive motors is presented with the aid of Recursive Feature Elimination with Cross-Validation (RFE-CV), parameter optimization, and in-depth preprocessing. …”
Get full text

A Method of Word Sense Disambiguation with Recurrent Netural Networks by ZHANG Chunxiang, ZHOU Xuesong, GAO Xueyao

Get full text

Understanding user experience for mobile applications: a systematic literature review by Guoying Lu, Siyuan Qu, Yining Chen

“…We developed the Scenarios, Themes, Features, and Methodologies framework to examine both the theoretical and practical applications across multiple dimensions. …”
Get full text

Development and calibration of roundabout safety performance functions using machine learning: a case study from Amman, Jordan by Diana Al-Nabulsi, Aya Hassouneh

Get full text

DAMI-YOLOv8l: A multi-scale detection framework for light-trapping insect pest monitoring by Xiao Chen, Xinting Yang, Huan Hu, Tianjun Li, Zijie Zhou, Wenyong Li

“…The DMC module improves multi-scale feature extraction to enable the effective capture and merging of features across different detection scales while reducing network parameters. …”
Get full text

Implementation of Chernobyl disaster optimizer based feature selection approach to predict software defects [version 2; peer review: 2 approved, 1 not approved] by Himansu Das, Ajay Kumar Jena, Kunal Anand

Get full text

LSANet: Lightweight Super Resolution via Large Separable Kernel Attention for Edge Remote Sensing by Tingting Yong, Xiaofang Liu

“…The core of LSANet is the large separable kernel attention mechanism, which efficiently expands the receptive field while retaining low computational overhead. By integrating this mechanism into an enhanced residual feature distillation module, the network captures long-range dependencies more effectively than traditional shallow residual blocks. …”
Get full text

A Pipeline for Multivariate Time Series Forecasting of Gas Consumption in Pelletization Process by Thadeu Pezzin Melo, Jefferson Andrade, Karin Satie Komati

“…In step (iii), twelve features were identified as the most relevant based on the Random Forest importance index. …”
Get full text

A Lightweight Semantic Segmentation Model for Underwater Images Based on DeepLabv3+ by Chongjing Xiao, Zhiyu Zhou, Yanjun Hu

“…The framework employs MobileOne-S0 as the lightweight backbone for feature extraction, integrates Simple, Parameter-Free Attention Module (SimAM) into deep feature layers, replaces global average pooling in the Atrous Spatial Pyramid Pooling (ASPP) module with strip pooling, and adopts a content-guided attention (CGA)-based mixup fusion scheme to effectively combine high-level and low-level features while minimizing parameter redundancy. …”
Get full text

False-Alarm-Controllable Detection of Marine Small Targets via Improved Concave Hull Classifier by Sainan Shi, Jiajun Wang, Jie Wang, Tao Li

“…On the other hand, in 3D feature space, an improved concave hull classifier is developed to further shrink the decision region, where a fast two-stage parameter search is designed for low computational cost and accurate control of false alarm rate. …”
Get full text

Deep learning to evaluate seismic-induced soil liquefaction and modified transfer learning between various data sources by Hongwei Guo, Chao Zhang, Hongyuan Fang, Timon Rabczuk, Xiaoying Zhuang

Get full text

The value of machine learning based on spectral CT quantitative parameters in the distinguishing benign from malignant thyroid micro-nodules by Zuhua Song, Qian Liu, Jie Huang, Dan Zhang, Jiayi Yu, Bi Zhou, Jiang Ma, Ya Zou, Yuwei Chen, Zhuoyue Tang

“…Four typical radiological features and 19 DLCT quantitative parameters in the arterial phase and venous phase were measured. …”
Get full text

A lightweight multi-path convolutional neural network architecture using optimal features selection for multiclass classification of brain tumor using magnetic resonance images by Amreen Batool, Yung-Cheol Byun

“…Pre-trained models like AlexNet, Residual Networks (ResNet), and Inception V3 are effective but has high computational costs due to trainable parameters. Therefore, a lightweight Multi -path Convolutional Neural Network (M-CNN) is introduced to extract features using varying convolutional filters at each convolutional layer. …”
Get full text

Research on scenario recognition for THz channels based on mRMR-GA by HAO Xinyu, LIAO Xi, WANG Yang, LIN Feng, LUO Jiao, ZHANG Jie

“…To address the challenges of excessive feature parameter redundancy and insufficient scene correlation in terahertz (THz) channel scenario recognition, a recognition algorithm integrating the minimal redundancy maximal relevance (mRMR) criterion with genetic algorithm (GA) optimization was constructed based on feature selection theory and evolutionary computation principles. …”
Get full text