A Wide-range Power Supply Converter Design by CHEN Xiulin, WANG Fuguang, ZHANG Shunbiao

“…Inputand output current of the converter in steady state was analyzed, which showed the continuous current feature, in favour of improveconverter power density; and a kind of variable frequency control strategy and its realization method were presented, which solved thestability problem of the converter. …”
Get full text

MODERN METHODS OF AUTOMATIC RECTANGLE OBJECTS DETECTION by E. S. Matusevich, I. E. Kheidorov

“…Low-level and high-level feature extraction methods and algorithms for the image formation of a rectangular object were considered. …”
Get full text

Snow Leopard Infrared Camera Image Detection Method Based on Improved EfficientDet Model by DAI Tianhong, LIU Chao

“…Secondly, the Generative Adversarial Networks is used to transfer the domain of night infrared gray image, and the image prediction results before and after migration are fused to solve the problem of weak target recognition ability in infrared image.Finally, the attention mechanism is added to the backbone feature extraction network to refine the feature map to improve the visual significance of snow leopard in RGB and infrared images, and the improved feature fusion network structure to integrate more effective information. …”
Get full text

Face Recognition using Artificial Intelligent Techniques by Laheeb Ibrahim, Ibrahim Saleh

“…This research deals with the problem of face recognition. A novel approach is presented for both face feature extraction and recognition, first, we introduce Principal Component Analysis (PCA) for face feature extraction, Generalized Regression Artificial Neural network for face recognition. …”
Get full text

Mine underground object detection algorithm based on TTFNet and anchor-free by Song Zhen, Qing Xuwen, Zhou Meng, Men Yuting

“…First, CenterNet and TTFNet algorithms are introduced, then pooling is introduced into CSPNet basic structure to design a lightweight feature extraction network, at the same time optimizing the feature fusion way in the original algorithm, optimizing residual shrinkage network structure, and introducing it into object detection task. …”
Get full text

Safety belt wearing detection for electric aloft work based on EPSA-YOLOv5 by LI Yongfu, CHEN Libin, HUI Junwei, YUAN Runcong, CHAI Haokai

“…This method was based on EPSANet backbone feature extraction network, which reduced the number of parameters in the network while maintaining good feature extraction performance, and speeding up the model recognition speed. …”
Get full text

TIAR-SAR: An Oriented SAR Ship Detector Combining a Task Interaction Head Architecture with Composite Angle Regression by Yu Gu, Minding Fang, Dongliang Peng

“…This structure not only mitigates feature misalignment but also promotes feature interaction between regression and classification tasks, thereby enhancing prediction consistency. …”
Get full text

Ensembling Classical Machine Learning and Deep Learning Approaches for Morbidity Identification From Clinical Notes by Vivek Kumar, Diego Reforgiato Recupero, Daniele Riboni, Rim Helaoui

“…We have compared the outcomes of classical machine learning and deep learning approaches with the employed feature representation methods and feature selection methods. …”
Get full text

Deep learning-based automatic detection and grading of disk herniation in lumbar magnetic resonance images by Yan Guo, Xiaoxiang Huang, Wei Chen, Ichiro Nakamoto, Weiqing Zhuang, Hua Chen, Jie Feng, Jianfeng Wu

“…To address the difficulty of intervertebral disc feature extraction, the GS module was introduced into the backbone network, which enhances the feature learning ability for the key structures through the gradient splitting strategy, and the number of parameters was reduced by 2.1%. …”
Get full text

Multimodal multilevel attention for semi-supervised skeleton-based gesture recognition by Jinting Liu, Minggang Gan, Yuxuan He, Jia Guo, Kang Hu

“…To resolve this problem, we propose a novel multimodal multilevel attention network designed for semi-supervised learning. …”
Get full text

Nonlocal Hybrid Integro-Differential Equations Involving Atangana–Baleanu Fractional Operators by Saleh Alshammari, Mohammad Alshammari, Mohammed S. Abdo

“…In this study, we develop a theory for the nonlocal hybrid boundary value problem for the fractional integro-differential equations featuring Atangana–Baleanu derivatives. …”
Get full text

Inertial-relaxed splitting for composite monotone inclusions by Oré, Ernesto, Mahey, Philippe, Ocaña, Eladio

“…A unified setting is formalized and applied to different average maps whose corresponding fixed points are related to the solutions of the inclusion problem associated with our extended model. An interesting feature of the resulting algorithms we have designed is that they present two distinct versions with a Gauss–Seidel or a Jacobi flavor, extending in that sense former proximal ADMM methods, both including inertial and relaxation parameters. …”
Get full text

Rolling Bearing Remaining Useful Life Prognosis Method based on Improved CHSMM by Zhu Shuo, Bai Ruilin, Ji Feng

“…The feature vectors of the time and time frequency domain are extracted from the vibration signal of bearing and then the PCA algorithm is used to reduce the dimension of the feature vectors. …”
Get full text

Blotch Detection in Archive Films Based on Visual Saliency Map by Yildiz Aydin, Bekir Dizdaroğlu

“…Degradations frequently occur in archive films that symbolize the historical and cultural heritage of a nation. In this study, the problem of detection blotches commonly encountered in archive films is handled. …”
Get full text

Gearbox Fault Diagnosis Based on the LMD Cloud Model and PSO-KELM by Zhao Xiaohui, Tan Qi, Hu Sheng, Yang Wenbin, Huan Kaixuan, Zhang Zhijie

“…The characteristics of non-smoothness and uncertainty of gearbox fault vibration signal lead to the low accuracy of gearbox fault diagnosis. To address this problem, a gearbox fault diagnosis method based on local mean decomposition (LMD) cloud model feature extraction combined with particle swarm optimization (PSO) kernel extreme learning machine (KELM) is proposed. …”
Get full text

Research on fault diagnosis of amorphous alloy transformers by using vibration signals and a PSO-optimized full-process WPT-SVM model by Daosheng Liu, Wentao Yang, Longsheng Liu, Zhe Zhao

“…The PSO algorithm is used to optimize the number of WPT decomposition layers, wavelet basis functions, SVM kernel parameters g and penalty parameters c to enhance the accuracy of feature extraction and classification. Additionally, principal component analysis (PCA) reduces the dimensionality of the redundant frequency band energy after WPT feature extraction, minimizing data redundancy. …”
Get full text

Fault Extraction of Wind Turbine Rolling Bearings Using FDEO and the Improved ACYCBD by Gong Yongli, Peng Dikang, Feng Tao, Liu Yibing

“…Finally, for the purpose of addressing the problem such as multiple vibration components existing in a vibration signal collected from wind turbines, which may mask the vibration component of interest, the improved ACYCBD is then used to extract the fault feature. …”
Get full text

Passive forensic based on spatio-temporal localization of video object removal tampering by Linqiang CHEN, Quanxin YANG, Lifeng YUAN, Ye YAO, Zhen ZHANG, Guohua WU

“…To address the problem of identification of authenticity and integrity of video content and the location of video tampering area,a deep learning detection algorithm based on video noise flow was proposed.Firstly,based on SRM (spatial rich model) and C3D (3D convolution) neural network,a feature extractor,a frame discriminator and a RPN (region proposal network) based spatial locator were constructed.Secondly,the feature extractor was combined with the frame discriminator and the spatial locator respectively,and then two neural networks were built.Finally,two kinds of deep learning models were trained by the enhanced data,which were used to locate the tampered area in temporal domain and spatial domain respectively.The test results show that the accuracy of temporal-domain location is increased to 98.5%,and the average intersection over union of spatial localization and tamper area labeling is 49%,which can effectively locate the tamper area in temporal domain and spatial domain.…”
Get full text

Neural network technology for processing of signals from technical objects control means by A. A. Doudkin, Y. Y. Marushko

“…The paper presents a technology based on an ensemble of neural networks that solves the problem of predicting a multidimensional time series of telemetry data. …”
Get full text

Real-time Diagnosis and Prediction of Grounding Insulation Fault inTrain Power Supply System by QIN Fangfang, ZHENG Caihui, LI Xueming, LI Peng

“…In order to solve the problem of fault location and real-time evaluation of fault development trend, it proposed a real-time diagnosis and prediction method based on signal feature pattern recognition. …”
Get full text