Hyperspectral Image Classification With Re-Attention Agent Transformer and Multiscale Partial Convolution by Junding Sun, Hongyuan Zhang, Jianlong Wang, Haifeng Sima, Shuanggen Jin

“…Convolutional neural networks (CNNs) focus solely on extracting local features, lacking the ability to capture global spectral-spatial information. …”
Get full text

Multistep Prediction Model for Photovoltaic Power Generation Based on Time Convolution and DLinear by WANG Shuyu, LI Hao, MA Gang, YUAN Yubo, BU Qiangsheng, YE Zhigang

“…[Methods] This paper presents a multistep prediction model for photovoltaic power generation based on a temporal convolutional network （TCN） and DLinear combined model. …”
Get full text

Lightweight Sheep Face Recognition Model Combining Grouped Convolution and Parameter Fusion by Gaochao Liu, Lijun Kang, Yongqiang Dai

Get full text

Classification of maize seed hyperspectral images based on variable-depth convolutional kernels by Yating Hu, Hongchen Zhang, Hongchen Zhang, Changming Li, Qianfu Su, Wei Wang

“…However, conventional hyperspectral data processing approaches often fail to simultaneously capture both spectral and textural features effectively.MethodsTo overcome this limitation, we propose a novel convolutional neural network architecture with a variable-depth convolutional kernel structure (VD-CNN). …”
Get full text

Advanced Intelligent Data Hiding Using Video Stego and Convolutional Neural Networks by Inas Ali Abdulmunem, Eman S. Harba, Hind S. Harba

“…Steganography is a technique of concealing secret data within other quotidian files of the same or different types. Hiding data has been essential to digital information security. …”
Get full text

Application of the Algebraic Extension Method to the Construction of Orthogonal Bases for Partial Digital Convolutions by Aruzhan Kadyrzhan, Akhat Bakirov, Dina Shaltykova, Ibragim Suleimenov

“…Mathematical tools have been developed that are analogous to the tool that allows one to reduce the description of linear systems in terms of convolution operations to a description in terms of amplitude-frequency characteristics. …”
Get full text

Fully automated MRI-based convolutional neural network for noninvasive diagnosis of cirrhosis by Tianying Zheng, Yajing Zhu, Yidi Chen, Shengshi Mai, Lixin Xu, Hanyu Jiang, Ting Duan, Yuanan Wu, Yali Qu, Yinan Chen, Bin Song

“…Abstract Objectives To develop and externally validate a fully automated diagnostic convolutional neural network (CNN) model for cirrhosis based on liver MRI and serum biomarkers. …”
Get full text

Steganographer identification of JPEG image based on feature selection and graph convolutional representation by Qianqian ZHANG, Yi ZHANG, Hao LI, Yuanyuan MA, Xiangyang LUO

“…Aiming at the problem that the feature dimension of JPEG image steganalysis is too high, which leads to the complexity of distance calculation between users and a decrease in the identification performance of the steganographer, a method for steganographer recognition based on feature selection and graph convolutional representation was proposed.Firstly, the steganalysis features of the user’s images were extracted, and the feature subset with highseparability was selected.Then, the users were represented as a graph, and the features of users were obtained by training the graph convolutional neural network.Finally, because inter-class separability and intra-class aggregation were considered, the features of users that could capture the differences between users were learned.For steganographers who use JPEG steganography, such as nsF5, UED, J-UNIWARD, and so on, to embed secret information in images, the proposed method can reduce the feature dimensions and computing.The identification accuracy of various payloads can reach more than 80.4%, and it has an obvious advantage at the low payload.…”
Get full text

Steganographer identification of JPEG image based on feature selection and graph convolutional representation by Qianqian ZHANG, Yi ZHANG, Hao LI, Yuanyuan MA, Xiangyang LUO

“…Aiming at the problem that the feature dimension of JPEG image steganalysis is too high, which leads to the complexity of distance calculation between users and a decrease in the identification performance of the steganographer, a method for steganographer recognition based on feature selection and graph convolutional representation was proposed.Firstly, the steganalysis features of the user’s images were extracted, and the feature subset with highseparability was selected.Then, the users were represented as a graph, and the features of users were obtained by training the graph convolutional neural network.Finally, because inter-class separability and intra-class aggregation were considered, the features of users that could capture the differences between users were learned.For steganographers who use JPEG steganography, such as nsF5, UED, J-UNIWARD, and so on, to embed secret information in images, the proposed method can reduce the feature dimensions and computing.The identification accuracy of various payloads can reach more than 80.4%, and it has an obvious advantage at the low payload.…”
Get full text

An anti‐jamming method in multistatic radar system based on convolutional neural network by Jieyi Liu, Maoguo Gong, Mingyang Zhang, Hao Li, Shanshan Zhao

“…In this study, a discrimination method in a multistatic radar system based on the convolutional neural network is proposed. This proposal combines the advantages of multiple‐radar systems cooperative detection technology with the convolutional neural network, and effectively applies to the field of anti‐deception jamming, which takes full advantage of unknown information of echo data to obtain multi‐dimensional, comprehensive, complete and deep feature differences besides correlation, so as to achieve a better jamming discrimination effect. …”
Get full text

Risk assessment of thyroid nodules with a multi-instance convolutional neural network by Da Yu, Tingting Song, Yancheng Yu, Hebin Zhang, Feng Gao, Zirong Wang, Jiacheng Wang

“…However, existing AI-assisted methods often suffer from limited diagnostic performance.MethodsIn this study, we propose a novel multi-instance learning (MIL) convolutional neural network (CNN) model tailored for ultrasound-based thyroid cancer diagnosis. …”
Get full text

A Lightweight Deep Learning Model for Profiled SCA Based on Random Convolution Kernels by Yu Ou, Yongzhuang Wei, René Rodríguez-Aldama, Fengrong Zhang

“…In this article, a DL-SCA model is proposed by introducing a non-trained DL technique called random convolutional kernels, which allows us to extract the features of leakage like using a transformer model. …”
Get full text

Scaling convolutional neural networks achieves expert level seizure detection in neonatal EEG by Robert Hogan, Sean R. Mathieson, Aurel Luca, Soraia Ventura, Sean Griffin, Geraldine B. Boylan, John M. O’Toole

“…We have developed and validated a seizure detection model using retrospective EEG data from 332 neonates. A convolutional neural network was trained and tested on over 50,000 hours (n = 202) of annotated single-channel EEG containing 12,402 seizure events. …”
Get full text

Cross-device fault diagnosis method based on graph convolution and multi-sensor fusion by SUN Yuanshuai, KONG Fanqin, NIE Xiaoyin, XIE Gang

“…To address this problem, a cross-device fault diagnosis method based on graph convolution and multi-sensor fusion, convolutional domain graph convolution network (CDGCN) , was proposed. …”
Get full text

Brain-guided convolutional neural networks reveal task-specific representations in scene processing by Bruce C. Hansen, Michelle R. Greene, Henry A. S. Lewinsohn, Audrey E. Kris, Sophie Smyth, Binghui Tang

“…Here, we developed a novel brain-guided convolutional neural network (CNN) where each convolutional layer was separately guided by neural responses taken at different time points while observers performed a pre-cued object detection task or a scene affordance task on the same set of images. …”
Get full text

Ground-Based Remote Sensing Cloud Image Segmentation Using Convolution-MLP Network by Shuang Liu, Jiafeng Zhang, Zhong Zhang, Shuzhen Hu, Baihua Xiao

“…To this end, we propose the attention-guided MLPs module to highlight salient features and suppress irrelevant features from the spatial and channel aspects. Meanwhile, different from existing MLPs methods where the long-range dependencies are learned from one single scale, we propose the dilated MLPs (DMLPs) to learn long-range dependencies at different scales by sampling different channels of tokens. …”
Get full text

Bearing Fault Detection and Classification Based on Temporal Convolutions and LSTM Network in Induction Machine by Mohammad Hoseintabar Marzebali, Saeed Hasani Borzadaran, Hoda Mashayekhi, Valiollah Mashayekhi

“…Therefore, a proper condition monitoring method that can classify the type and the severity of electrical machine faults in different load levels is crucial to avoid unwanted downtime and loss of operation. …”
Get full text

Comparative exploration of deep convolutional neural networks using real-time endoscopy images by Subhashree Mohapatra, Pukhraj Singh Jeji, Girish Kumar Pati, Manohar Mishra, Tripti Swarnkar

“…Until now various deep convolutional neural networks are designed and trained for the purpose of classifying different medical conditions related to the domain of gastroenterology. …”
Get full text

The diagnostic value of convolutional neural networks in thyroid cancer detection using ultrasound images by Pei Zhang, Qijian Xu, Feng Jiang

“…ObjectiveTo extract and analyze the image features of two-dimensional ultrasound images and elastic images of four thyroid nodules by radiomics, and then further convolution processing to construct a prediction model for thyroid cancer. …”
Get full text

Fast and intelligent detection of concrete cracks based on sound signals and convolutional neural network by Chunlei Ge, Yue Qin, Yue Qin, Kaizhong Xie, Zubiao Lu

“…Finally, comparative experiments with different frame lengths, different models and different signal-to-noise ratios (SNR) are conducted using the improved CNN.ResultsThe results show that the model validation process has the least loss and highest accuracy when the input frame length is 1024. …”
Get full text