SAGCN: Self-Attention Graph Convolutional Network for Human Pose Embedding by Zhongxiong Xu, Jiajun Hong, Yicong Yu, Chengzhu Lin, Linfei Yu, Meixian Xu

“…While traditional convolutional neural networks (CNNs) have advanced pose feature extraction, they struggle to model structural relationships and long-range dependencies between keypoints, and are less robust to occlusions. …”
Get full text

Transformer network for time series prediction via wavelet packet decomposition by Zhichao Wu, Aiye Shi, Yan Ping Tao

Get full text

Neuroevolutionary Convolutional Neural Network Design for Low-Resolution Face Recognition by Jhon I. Pilataxi, Juan P. Perez, Claudio A. Perez, Kevin W. Bowyer

“…The classifier and performance predictor are trained using the CNN architectures evaluated from previous generations, with the architecture encoding used as a feature vector. …”
Get full text

Human Activity Recognition Using Graph Structures and Deep Neural Networks by Abed Al Raoof K. Bsoul

“…This research presents a novel HAR system combining graph structures with deep neural networks to capture both spatial and temporal patterns in activities. …”
Get full text

Residual Network with Triple-Attention Mechanisms for Knee Osteoarthritis Severity Classification by Tian Hongyu, Cao Wenming, Ran Qiyu

“…To address this diagnostic bottleneck, we introduce Triplet Attention (TA) in Residual Network (ResNet) for KOA recognition. The architecture innovatively integrates cross-dimensional attention modules within residual blocks, enabling simultaneous modeling of channel-wise dependencies, spatial correlations, and hierarchical feature relation- ships. …”
Get full text

TCCU-Net: Transformer and CNN Collaborative Unmixing Network for Hyperspectral Image by Jianfeng Chen, Chen Yang, Lan Zhang, Linzi Yang, Lifeng Bian, Zijiang Luo, Jihong Wang

“…By fusing the outputs of these two encoders, the semantic gap between the encoder and decoder is bridged, resulting in improved feature mapping and unmixing outcomes. This article extensively evaluates TCCU-Net and seven hyperspectral unmixing methods on four datasets (Samson, Apex, Jasper Ridge, and Synthetic dataset). …”
Get full text

Cost Index Predictions for Construction Engineering Based on LSTM Neural Networks by Jiacheng Dong, Yuan Chen, Gang Guan

“…The recurrent neural network (RNN) belongs to a time series network, and the purpose of timeliness transfer calculation is achieved through the weight sharing of time steps. …”
Get full text

MSEA-Net: Multi-Scale and Edge-Aware Network for Weed Segmentation by Akram Syed, Baifan Chen, Adeel Ahmed Abbasi, Sharjeel Abid Butt, Xiaoqing Fang

“…To address these limitations, we propose the Multi-Scale and Edge-Aware Network (MSEA-Net), a lightweight and efficient deep learning framework designed to enhance segmentation accuracy while maintaining computational efficiency. …”
Get full text

SCITUNA: single-cell data integration tool using network alignment by Aissa Houdjedj, Yacine Marouf, Mekan Myradov, Süleyman Onur Doğan, Burak Onur Erten, Oznur Tastan, Cesim Erten, Hilal Kazan

“…Results We introduce a novel method for batch effect correction named SCITUNA, a Single-Cell data Integration Tool Using Network Alignment. We perform evaluations on 39 individual batches from four real datasets and a simulated dataset, which include both scRNA-seq and scATAC-seq datasets, spanning multiple organisms and tissues. …”
Get full text

Siamese network with change awareness for surface defect segmentation in complex backgrounds by Biyuan Liu, Sijie Luo, Huiyao Zhan, Yicheng Zhou, Zhou Huang, Huaixin Chen

“…Abstract Despite the significant advancements made by deep visual networks in detecting surface defects at a regional level, the challenge of achieving high-quality pixel-wise defect detection persists due to the varied appearances of defects and the limited availability of data. …”
Get full text

CNN–Transformer gated fusion network for medical image super-resolution by Juanjuan Qin, Jian Xiong, Zhantu Liang

“…The local branch uses the characteristic of dynamic convolution to adaptively adjust the convolution kernel parameters, which can enhance the feature extraction ability of convolutional neural network for multi-scale information and improve the detail restoration ability of the image without significantly increasing the network model size. …”
Get full text

STOCHASTIC APPROACH FOR EVALUATION OF RELIABILITY AND RESIDUAL LIFE OF TRANSPORT STRUCTURES by U. N. Rabtsau

“…In order to ensure maximum efficiency of investments in operation of transport network it is necessary exactly evaluate reliability and residual life of structures. …”
Get full text

SP-Pillars: An Efficient LiDAR 3D Objects Detection Framework With Multi-Scale Feature Perception and Optimization by Tingshuai Chen, Ye Yuan, Bingyang Yin, Yuanhong Liao

“…To address this challenge, this paper proposes a 3D object detection algorithm SP-Pillars that can effectively learn point cloud features. Firstly, a Pillar Feature Weighted Network (PFWNet) is proposed for processing point cloud information, which divides the point cloud into pillar structures and uses SPCV feature attention network to focus on its multi-level feature information. …”
Get full text

Improving cancer detection through computer-aided diagnosis: A comprehensive analysis of nonlinear and texture features in breast thermograms. by Hamed Khodadadi, Shima Nazem

“…The proposed method utilizes various machine learning algorithms, including Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Linear Discriminant Analysis (LDA), Pattern recognition Network (Pat net), and Fitting neural Network (Fit net), for classification. ten-fold cross-validation ensures robust performance evaluation. …”
Get full text

Transferable Deep Learning Models for Accurate Ankle Joint Moment Estimation during Gait Using Electromyography by Amged Elsheikh Abdelgadir Ali, Dai Owaki, Mitsuhiro Hayashibe

“…We verified and compared the performance of 1302 intrasubject models per subject on 597 steps from seven subjects using various architectures and feature sets. The best-performing intrasubject models were recurrent convolutional neural networks trained using signal energy features. …”
Get full text

Evaluation of high-standard public transport centres in the Slovak Republic by Horňák Marcel, Struhár Peter, Pšenka Tomáš

Get full text

Building consistency in explanations: Harmonizing CNN attributions for satellite-based land cover classification by Timo T. Stomberg, Lennart A. Reißner, Martin G. Schultz, Ribana Roscher

“…Attribution methods like Grad-CAM and occlusion sensitivity analysis are frequently used to identify how features contribute to predictions of neural networks. …”
Get full text

Evaluating impact of different factors on electric vehicle charging demand by Shakker Soheila, Esmi Nima, Shahbahrami Asadollah

“…Leveraging long short-term memory networks – effective in modeling time-series data – we evaluate the impact of contextual features on forecasting performance. …”
Get full text

An AI framework for counterattack detection and decision-making evaluation in football by Jiangyan Yang, Huanmin Ge, Yixiong Cui

“…Abstract This study proposes a performance analysis framework for evaluating counterattack decisions in football by utilizing deep learning techniques. …”
Get full text

Evaluating Lightweight Transformers With Local Explainability for Android Malware Detection by Fatima Bourebaa, Mohamed Benmohammed

Get full text