Cross-Subject Emotion Recognition with CT-ELCAN: Leveraging Cross-Modal Transformer and Enhanced Learning-Classify Adversarial Network by Ping Li, Ao Li, Xinhui Li, Zhao Lv

“…By combining a cross-modal Transformer with ELCAN, a feature alignment module using adversarial training, CT-ELCAN learns modality- and subject-invariant emotional representations. …”
Get full text

A Framework for Predicting Winter Wheat Yield in Northern China with Triple Cross-Attention and Multi-Source Data Fusion by Shuyan Pan, Liqun Liu

“…This framework consists of three modules: a multi-source data processing module, a multi-source feature fusion module, and a yield prediction module. …”
Get full text

Analyzing Patient Complaints in Web-Based Reviews of Private Hospitals in Selangor, Malaysia, Using Large Language Model–Assisted Content Analysis: Mixed Methods Study by Muhammad Hafiz Sulaiman, Nora Muda, Fatimah Abdul Razak

“…The factors identified follow a global pattern of issues identified from the literature. …”
Get full text

AFHNet: Attention-Free Hybrid Network for Salient Object Detection in Underwater Images by Qian Tang, Zhen Wang, Xuqi Wang, Shan-Wen Zhang

“…However, traditional machine vision and deep learning approaches face notable challenges in complex underwater environments due to issues such as light attenuation, scattering, motion blur, color distortion, noise, low contrast, and multipath effects, which severely affect detection accuracy. …”
Get full text

Edge Computing-Based Video Action Recognition Method and Its Application in Online Physical Education Teaching by Jinzhu Han, Jinjin Zhao, Yan Yue, Xinrui Che

“…To address the above issues, this paper proposes a lightweight video recognition method, named the lightweight video ViT (LWV-ViT) network. …”
Get full text

The Impact of Integrating Shallow and Deep Information on Knowledge Distillation by Yilin Miao, Yuhong Tang, Huangliang Ren, Jianjun Li

“…However, our experimental findings reveal that the ResNet model falls short in extracting shallow information from images, which in turn affects the performance of the corresponding student model. To address these issues, we propose a shallow feature extraction module (SFEM) that enriches the receptive field of images through dilated convolutions and captures information at different scales, while reducing parameter counts and optimizing computational resources. …”
Get full text

A multi-scale rotated ship targets detection network for remote sensing images in complex scenarios by Siyu Li, Fei Yan, Yunqing Liu, Yuzhuo Shen, Lan Liu, Ke Wang

“…The limited feature information of small-scale targets and their random orientation angles often result in missed and false detections. To address these issues, this paper proposes a Multi-Scale Rotated Detection Network (MSRO-Net) for detecting rotated ship targets in remote sensing images. …”
Get full text

Product family modeling technology for customized cosmetic packaging design based on basic-element theory by Tao Chen, Ding-Bang Luh, Jinguang Wang

“…These issues are especially noticeable in the domain of cosmetic packaging design. …”
Get full text

MRIE: Enhanced Rainfall Intensity Estimation With Two-Stage Multimodal Deep Learning by Jin Li, Wentao Hu, Zhigang Zhou

“…However, the reliability of existing methods in practical applications is relatively low due to certain deficiencies in data processing and noise resistance. To address these issues, MRIE is proposed, a two-stage multimodal framework that integrates data from environmental sensors and audio recordings to improve estimation accuracy. …”
Get full text

Steel Surface Defect Detection Algorithm Based on Improved YOLOv8 Modeling by Miao Peng, Sue Bai, Yang Lu

“…Second, the weighted fusion splicing module, Concat_BiFPN, is used in the neck network to facilitate multi-scale feature detection and fusion. …”
Get full text

Industrial Control Systems (ICS) cyber prediction model by Joana Katina, Tomas Plėta, Romualdas Petkevičius, Lina Lelešienė

“…Acceleration of scientific and technical progress, speeding up of technological changes, IT process globalisation and integration of OT processes invoked new challenges in preparing cyber strategies. Issues with adapting strategy for a particular specificity, region and specific cyber-attacks are not applicable. …”
Get full text

Advancing construction safety: YOLOv8-CGS helmet detection model. by Zhihui Wu, Xiaojia Lei, Munish Kumar

“…However, traditional object detection methods often face numerous challenges in complex construction environments, such as low light, occlusion, and the diverse shapes of helmets. To address these issues, we propose an improved helmet detection model, YOLOv8-CGS, which is based on the YOLOv8 architecture and integrates optimization modules such as CBAM (Convolutional Block Attention Module), GAM (Global Attention Mechanism), and SLOU (Smooth Labeling Loss Function). …”
Get full text

Maize quality detection based on MConv-SwinT high-precision model. by Ning Zhang, Yuanqi Chen, Enxu Zhang, Ziyang Liu, Jie Yue

“…The traditional method of corn quality detection relies heavily on the subjective judgment of inspectors and suffers from a high error rate. To address these issues, this study employs the Swin Transformer as an enhanced base model, integrating machine vision and deep learning techniques for corn quality assessment. …”
Get full text

Development of metacognition-based mathematics learning devices with heuristic strategies on sequences and series by Nadita Lerian Rosendra, Y. Yarman, Edwin Musdi, I Made Arnawa

“…Enhancing pupils' capacity to resolve mathematical issues is the aim. Students in SMAN 1 Lengayang's grade X, or Phase E, participated in this study. …”
Get full text

Bi-Modal Bi-Task Emotion Recognition Based on Transformer Architecture by Yu Song, Qi Zhou

“…Additionally, single-task models lack generalization and fail to fully utilize relevant information. To address these issues, this paper proposes a new bi-modal bi-task emotion recognition model. …”
Get full text

An Effective Parameter Analysis for Sending-or-Not-Sending Quantum Key Distribution with Untrusted Light Sources by Jiajian Huang, Weigang Li, Yucheng Qiao

“…However, the TF protocol still faces several security issues in real-world environments. To address the issue of untrusted sources, one effective solution is to introduce a light-source monitoring module into the system. …”
Get full text

Study on the Balise Antenna Interference Problem on Nanjing Metro Line 7 by HE Yuqin, XIE Wei

“…Method The signal equipment restart failure encountered by the balise transmission module (BTM) on Nanjing Metro Line 7 during the commissioning stage is taken as the research object. …”
Get full text

An improved YOLOv5n algorithm for detecting surface defects in industrial components by Jia-Hui Tian, Xue-Feng Feng, Feng Li, Qing-Long Xian, Zhen-Hong Jia, Jie-Liang Liu

“…Abstract Due to the small defect areas and indistinct features on industrial components, detecting surface defects with high accuracy remains challenging, often leading to false detections. To address these issues, this paper proposes an improved YOLOv5n algorithm for industrial surface defect detection. …”
Get full text

Study on Few-Shot Object Detection Approach Based on Improved RPN and Feature Aggregation by Qiyu Pan, Keyi Fu, Gaocai Wang

“…Simultaneously, we introduce an attention-based Feature Aggregation Module (AFM) in Region of Interest (RoI) Align to aggregate feature information from different levels, obtaining more comprehensive information and feature representation to address the issue of missing feature information due to scale differences. …”
Get full text

A Comparative Analysis of Self-Rectifying Turbines for the Mutriku Oscillating Water Column Energy Plant by Erlantz Otaola, Aitor J. Garrido, Jon Lekube, Izaskun Garrido

“…However, the most widely used turbine comprising its power take-off (PTO) module, the Wells turbine, presents some drawbacks that require special attention. …”
Get full text