PRO-BiGRU: Performance Evaluation Index System for Hardware and Software Resource Sharing Based on Cloud Computing by Nan Wang

“…To achieve this, we propose an enhanced performance evaluation method by integrating the Poor-Rich Optimization (PRO) algorithm with the Bidirectional Gated Recurrent Unit (BiGRU) network. …”
Get full text

Bringing Intelligence to SAR Missions: A Comprehensive Dataset and Evaluation of YOLO for Human Detection in TIR Images by Mostafa Rizk, Israa Bayad

Get full text

Revolutionizing climbing perch disease management: AI-Driven solutions for sustainable aquaculture by Kosit Sriputhorn, Rapeepan Pitakaso, Surasak Matitopanum, Peerawat Luesak, Surajet Khonjun, Rungwasun Kraiklang, Chakat Chueadee, Sarayut Gonwirat

“…This system uniquely combines non-population based differential evolution algorithms for optimizing the mix of image augmentation techniques, with population-based algorithms for integrating image segmentation and convolutional neural network (CNN) architectures. …”
Get full text

Blasting vibration velocity prediction of open pit mines based on GRA-EPSO-SVM model by Pengfei ZHANG, Yong YUAN, Yunhua HE, Shaojun DAI, Jiazhen LI, Xuehai CHI, Wei LI, Xue SUN, Jiao ZHANG, Runcai BAI, Honglu FEI

“…In the scene of coal and rock interbedded blasting in open-pit mine, aiming at the problems that the existing prediction methods of blasting vibration peak value are difficult to achieve ideal prediction results, resulting in unreasonable design of blasting parameters and initiation network, a prediction model of blasting vibration peak value based on integrated particle swarm optimization support vector machine algorithm (GRA-EPSO-SVM) with grey correlation degree feature selection is proposed. …”
Get full text

Evading control flow graph based GNN malware detectors via active opcode insertion method with maliciousness preserving by Hao Peng, Zehao Yu, Dandan Zhao, Zhiguo Ding, Jieshuai Yang, Bo Zhang, Jianming Han, Xuhong Zhang, Shouling Ji, Ming Zhong

“…Existing function-preserving adversarial attacks fall short of effectively modifying portable executable (PE) malware control flow graphs (CFGs), thereby failing to bypass the graph neural network (GNN) models that utilize CFGs for detection. …”
Get full text

Research on Multi-Scale Point Cloud Completion Method Based on Local Neighborhood Dynamic Fusion by Yalun Liu, Jiantao Sun, Ling Zhao

“…Finally, when designing the decoder, inspired by the concept of generative adversarial networks (GANs), an attention discriminator designed in series with a feature extraction layer and an attention layer is added to further optimize the completion performance of the network. …”
Get full text

Study of In-Vehicle Ethernet Message Scheduling Based on the Adaptive Frame Segmentation Algorithm by Jiaoyue Chen, Yujing Wu, Yihu Xu, Kaihang Zhang, Yinan Xu

“…With the rapid development of intelligent driving technology, in-vehicle bus networks face increasingly stringent requirements for real-time performance and data transmission. …”
Get full text

YOLO-LSD: A Lightweight Object Detection Model for Small Targets at Long Distances to Secure Pedestrian Safety by Ming-An Chung, Sung-Yun Chai, Ming-Chun Hsieh, Chia-Wei Lin, Kai-Xiang Chen, Shang-Jui Huang, Jun-Hao Zhang

“…The C3C2 module optimizes the network structure by reducing redundant operations, making it more suitable for real-time deployment on embedded devices. …”
Get full text

Performance Evaluation of YOLOv11 and YOLOv12 Deep Learning Architectures for Automated Detection and Classification of Immature Macauba (<i>Acrocomia aculeata</i>) Fruits by David Ribeiro, Dennis Tavares, Eduardo Tiradentes, Fabio Santos, Demostenes Rodriguez

Get full text

Attention-Enhanced Hybrid Automatic Modulation Classification for Advanced Wireless Communication Systems: A Deep Learning-Transformer Framework by Sam Ansari, Khawla A. Alnajjar, Sohaib Majzoub, Eqab Almajali, Anwar Jarndal, Talal Bonny, Abir Hussain, Soliman Mahmoud

“…The proposed framework is rigorously compared against six representative models&#x2014;recurrent neural networks (RNN), long short-term memory (LSTM), gated recurrent units (GRU), convolutional neural networks-transformer graph neural network (CTGNet), MobileViT, and DeepsigNet&#x2014;across multiple evaluation criteria. …”
Get full text

Creative design of digital media art based on computer visual aids by Luo Kun, Tao Ran

“…The evaluation shows that the work receives high scores in clarity, color accuracy, style coherence, and innovation (the average score is close to 9 points). Audience feedback shows that the model performs well in enhancing immersive experience, emotional resonance, and interactive satisfaction, whereas technical acceptance also highlights room for optimization. …”
Get full text

Multi-Modal Federated Learning Over Cell-Free Massive MIMO Systems for Activity Recognition by Seyed Mohammad Sheikholeslami, Pai Chet Ng, Jamshid Abouei, Konstantinos N. Plataniotis

“…This paper addresses the problem of Multi-modal Federated Learning (MFL) over resource-limited Cell-Free massive MIMO (CF-mMIMO) networks for the application of Human Activity Recognition (HAR). …”
Get full text

G2Grad-CAMRL: An Object Detection and Interpretation Model Based on Gradient-Weighted Class Activation Mapping and Reinforcement Learning in Remote Sensing Images by Shoulin Yin, Liguo Wang, Muhammad Shafiq, Lin Teng, Asif Ali Laghari, Muhammad Faizan Khan

“…The reinforcement learning method is used to optimize the generated region generation network. At the same time, we improve the reward function of reinforcement learning to improve the effectiveness of the region generation network. …”
Get full text

Integrating direct observation and environmental DNA data to enhance species distribution models in riverine environments by Luca Carraro

“…These results will contribute to designing efficient strategies for integrated biomonitoring in river networks.…”
Get full text

Deformation Monitoring of Truss Structure Bridge With Time-Series InSAR Analysis by Chuanxu Sun, Gen Li, Zihan Hu, Yifan Wang, Zehua Dong, Tao Zeng

“…In order to solve these problems, an improved PSI method is proposed in this article, which is first to carry out preliminary elevation measurement by a small temporal baseline, use the preliminary elevation results to PS-arcs construction based on 3-D spatial network, and utilize the optimal model coherence coefficient adaptive selection based on constant false alarm rate to carry out the parameter estimation so as to realize the accurate monitoring of deformation of large-span steel truss structure bridges. …”
Get full text

Design of an efficient multi-objective recognition approach for 8-ball billiards vision system by Jiaying Gao, Qiuyang He, Hong Gao, Zhixin Zhan, Zhe Wu

“…In order to improve the quality of CNN training: the colour segmentation and morphologic operation are applied for the segmented ball image pre-processing; the training set images are rotated for augmentation; pre-training stage is introduced in for optimizing the initial weight matrices. The calibrated image blocks are imported to the network for training. …”
Get full text

A Near-Infrared Imaging System for Robotic Venous Blood Collection by Zhikang Yang, Mao Shi, Yassine Gharbi, Qian Qi, Huan Shen, Gaojian Tao, Wu Xu, Wenqi Lyu, Aihong Ji

“…Results show that, compared to U-Net, the BYOL+U-Net+ResNet18 method achieves an 8.31% reduction in Binary Cross-Entropy (BCE), a 5.50% reduction in Hausdorff Distance (HD), a 15.95% increase in Intersection over Union (IoU), and a 9.20% increase in the Dice coefficient (Dice), indicating improved image segmentation quality. The average error of the optimized AD-Census stereo matching algorithm is reduced by 25.69%, and the improvement of the image stereo matching performance is more obvious. …”
Get full text

Improving Audio Recognition With Randomized Area Ratio Patch Masking: A Data Augmentation Perspective by Weichun Wong, Yachun Li, Shihan Li

“…The results show that RARPM achieves a mean average precision (mAP) of 0.385, surpassing the baseline SpecAugment&#x2019;s mAP of 0.366. …”
Get full text

A target detection model HR-YOLO for advanced driver assistance systems in foggy conditions by Yao Zhang, Na Jia

“…To enhance detection performance under complex meteorological conditions, several critical modules have been optimized. First, the Efficient High-Precision Defogging Network (EHPD-Net) is introduced to strengthen feature extraction. …”
Get full text

Technology for Improving the Accuracy of Predicting the Position and Speed of Human Movement Based on Machine Learning Models by Artem Obukhov, Denis Dedov, Andrey Volkov, Maksim Rybachok

“…Prediction of the person’s position (based on 10 previous frames) is performed using the DT model, which is optimal in terms of accuracy and computation time relative to other options. …”
Get full text