Emotion classification with multi‐modal physiological signals using multi‐attention‐based neural network by Chengsheng Zou, Zhen Deng, Bingwei He, Maosong Yan, Jie Wu, Zhaoju Zhu

“…However, emotion classification with physiological signals is still a challenging problem due to the diversity of emotion expression and the characteristic differences in different modal signals. …”
Get full text

An interactive ball training partner robot based on YOLOv5 by Zeng Yangji, Liu Zihong, Cai Yong, Guo Xingchen, Mo Jinlong

“…Compared with other algorithms based on feature matching and small target detection using gestures, the robot has higher detection speed and accuracy, which makes the robot more intelligent.…”
Get full text

Research on Calibration Algorithm of Camera and LiDAR for Transport Vehicles in Open-pit Mines by XU Yanghan, LIN Jun, KANG Gaoqiang, YOU Jun, YUE Wei, TONG Hao

“…In the intelligent driving system of transport vehicles in open-pit mines, the data fusion of camera and LiDAR plays a vital role in the detection, recognition and tracking of obstacles. Aiming at the problem of camera and LiDAR spatial coordinate unity, that is establishing the correspondence between 2D coordinate system of image and 3D coordinate system of point cloud, this paper proposes a camera and LiDAR calibration method based on chessboard calibration board. …”
Get full text

Bolt Anchorage Quality Levels Classification Method Based on HO‐VMD‐CNN‐BiLSTM by Fan Kesong, Zhang Can, Liu Shaowei, Feng Mengyin, Yan Ao, Fu Mengxiong, He Deyin, Nie Zhibin

“…ABSTRACT At present, ultrasonic guided wave nondestructive testing technology is widely used in the detection of bolt anchorage defects. Traditional detection methods are confronted with problems such as serious signal noise interference, low detection accuracy, and poor real‐time performance. …”
Get full text

EDPNet: A Transmission Line Ice-Thickness Recognition End-Side Network Based on Efficient Dynamic Perception by Yangyang Jiao, Yu Zhang, Yinke Dou, Liangliang Zhao, Qiang Liu

“…Compared with the baseline model, the maximum ice-thickness detection error is 4.2%, the model parameters are reduced by 86.1%, and the detection speed is increased by 74.6%. …”
Get full text

Interturn short circuit fault diagnosis method of direct-drive permanent magnet synchronous motor based on two-stage PNN by GAO Caixia, FENG Lingyun, DANG Jianjun

“…ObjectivesAccurate positioning of early faults is crucial for preventing the deterioration of motor system faults and formulating operation and maintenance strategies after faults.MethodsAiming at the problem that the inter-turn short-circuit fault diagnosis of multi-branch parallel direct-drive permanent magnet synchronous motor （MB-DDPMSM）， a novel method of inter-turn short-circuit fault detection and short-circuit coil automatic positioning based on two-stage PNN was proposed. …”
Get full text

Research on chaotic secure communication system based on all optical chaos injection double-loop electro-optical phase feedback loop by ZHOU Xuefang, WANG Fei, YANG Guowei, BI Meihua, XU Mengmeng, HU Miao

“…To solve the problem of large feedback gain coefficient required for delay feature hiding in existing chaotic secure laser communication systems, a chaotic secure communication system based on all optical chaos injection double-loop electro-optical phase feedback loop was designed. …”
Get full text

A Ship Detector Design Based on Deep Convolutional Neural Networks for Satellite Images by Ferhat Ucar, Deniz Korkmaz

“…The dissimilarity of results, enhanced dataset requirement, intricacyof the problem domain, general use of Synthetic Aperture Radar (SAR) images andproblems on generalizability are some topics of the issues related to shiptarget detection. …”
Get full text

Object Ontologies as a Priori Models for Logical-Probabilistic Machine Learning by D. N. Gavrilin, A.V. Mantsivoda

“…The combination of LPML and object ontologies is capable of solving the forecasting problems, the tasks of automated control, problem detection, decision making, and business process synthesis. …”
Get full text

CTAO sensitivity to axion-like particles by Schiavone Francesco, Di Venere Leonardo, Giordano Francesco

“…Axion-like particles (ALPs) are a common feature in several extensions of the StandardModel, arising, for example, as a solution to the strong CP problem in quantum chromodynamics, or as a prediction of string theories. …”
Get full text

Research on rolling bearing compound fault diagnosis based on AMOMCKD and convolutional neural network by Runfang Hao, Yunpeng Bai, Kun Yang, Yongqiang Cheng, Shengjun Chang

“…Finally, the kernel size of the CNN is optimized based on the length of the filtered periodic pulse signal, which enables the CNN to achieve deeper feature extraction and classification. Experimental results from two different datasets highlight that AMOMCKD-CNN outperforms other classical diagnostic methods under the same conditions, and it is more conducive to the detection of compound faults.…”
Get full text

Behavior Analysis of Students in Preschool Mathematics Teaching Based on Deep Learning by Guangning Qin

“…Through convolution and self-attention mechanism, multi-scale feature fusion is enhanced. Adding a small target detection layer and extracting local features from larger-sized feature maps significantly improves the ability to recognize the behaviors of students in the back row. …”
Get full text

Histopathological Image Analysis Using Deep Learning Framework by Sudha Rani Vupulluri, Jogendra Kumar Munagala

“…Graph-segmented images retrieve relevant features. Using recursive feature removal, breast cancer photographs are categorized. …”
Get full text

Blockchain covert communication scheme based on the cover of normal transactions by Pengkun JIANG, Wenyin ZHANG, Jiuru WANG, Shanyun HUANG, Wanshui SONG

“…With the development of computer technology, the situation of modern network attack and defense is becoming increasingly severe, and the problem of secure transmission of secret information needs to be solved urgently.Covert communication technology embeds secret information into the carrier and transmits the information safely through the covert channel.However, the traditional covert channels face the challenges of data damaging, attack, detection and so on, which cannot meet the higher security requirements.As a public data platform, blockchain can embed secret information under the cover of a large number of transactions.With its tamper proof, anonymity, decentralization and other characteristics, blockchain can well solve the problems of traditional covert channels and achieve secure covert communication.However, the existing blockchain covert communication schemes are limited by low communication efficiency and poor security.How to improve safety and efficiency of covert communication is a research focus of blockchain covert communication.Motivated by this issue, a blockchain covert communication scheme based on the cover of normal transactions was proposed.The hash algorithm was used to build a transmission-free password table to embed secret information without changing any transaction data.Using the elliptic curve feature, transactions with hidden information can be quickly screened out from a large number of transactions, to extract secret information quickly.This scheme improves the security and efficiency of covert communication and has strong portability.Theoretical analysis shows that attackers cannot distinguish between ordinary transactions and special transactions.This scheme has high anti-detection and scalability.Besides, the experimental results of the bitcoin test network show the high efficiency of this scheme.…”
Get full text

Application of EEG Signal Recognition Method Based on Duffing Equation in Psychological Stress Analysis by Min Chai, Lei Ba

“…At present, the use of the Duffing equation to detect weak unknown signals is to select a set of fixed parameters. …”
Get full text

Rapid acquisition and surface defects recognition based on panoramic image of small-section hydraulic tunnel by Haoyu Wang, Jichen Xie, Jinyang Fu, Cong Zhang, Dingping Chen, Zhiheng Zhu, Xuesen Zhang

“…The proposed YOLOv5-DECA has great detection performance for targets with variable shapes and can solve the problem of classification imbalance in surface defects. …”
Get full text

Toward Inclusive Smart Cities: Sound-Based Vehicle Diagnostics, Emergency Signal Recognition, and Beyond by Amr Rashed, Yousry Abdulazeem, Tamer Ahmed Farrag, Amna Bamaqa, Malik Almaliki, Mahmoud Badawy, Mostafa A. Elhosseini

“…Evaluations using both compact (52 features) and expanded (126 features) representations show that several classes (e.g., Engine Misfire, Fuel Pump Cartridge Fault, Radiator Fan Failure) achieve near-perfect accuracy, though acoustically similar classes like Universal Joint Failure, Knocking, and Pre-ignition Problem remain challenging. …”
Get full text

An Insight on the Timely Diagnosis of Diabetic Retinopathy Using Traditional and AI-Driven Approaches by Malaika Asif, Fasih Ur Rehman, Zoya Rashid, Altaf Hussain, Alina Mirza, Waqar Shahid Qureshi

“…Artificial intelligence is transforming the detection of diabetic retinopathy, moving away from traditional machine learning models that rely on manually created features to deep learning methods that allow for automatic feature extraction from retinal images. …”
Get full text

Advancing e-waste classification with customizable YOLO based deep learning models by P. Akhil Rajeev, Vivek Dharewa, D. Lakshmi, G. Vishnuvarthanan, Jayant Giri, T. Sathish, Mubarak Alrashoud

“…The ‘You Only Look Once’ (YOLO) methodology underpins our research, highlighting the distinctive architectural features of each model, including the CSPDarknet53 backbone, PANet, and advanced anchor-free detection. …”
Get full text

WCS-YOLOv8s: an improved YOLOv8s model for target identification and localization throughout the strawberry growth process by Sheng Gao, Sheng Gao, Gongpei Cui, Qiaohua Wang

“…Additionally, the neck network is enhanced by incorporating the CGFM module, which employs a multi-head self-attention mechanism to fuse diverse feature information and improve the network’s feature fusion performance.Results and discussionThe model’s Precision (P), Recall (R), HYPERLINK "mailto:mAP@0.5" mAP@0.5, and mAP@0.5:0.95 of detection were 83.4%, 86.7%, 87.53%, and 60.48%, respectively, and the detection speed was 45.9 FPS(21.8 ms/per image, which significantly improved on the detection accuracy and generalization ability of with the YOLOv8s benchmark model. …”
Get full text