Feature Coding and Graph via Transformer: Different Granularities Classification for Aircraft by Jianghao Rao, Senlin Qin, Zongyan An, Jianlin Zhang, Qiliang Bao, Zhenming Peng

“…Thanks to the ever-evolving nature of the convolutional neural network (CNN), it has become easier to distinguish and recognize different types of aircraft. …”
Get full text

Structural differences between human and mouse neurons and their implementation in generative AIs by Rino Saiga, Kaede Shiga, Yo Maruta, Chie Inomoto, Hiroshi Kajiwara, Naoya Nakamura, Yu Kakimoto, Yoshiro Yamamoto, Masahiro Yasutake, Masayuki Uesugi, Akihisa Takeuchi, Kentaro Uesugi, Yasuko Terada, Yoshio Suzuki, Viktor Nikitin, Vincent De Andrade, Francesco De Carlo, Yuichi Yamashita, Masanari Itokawa, Soichiro Ide, Kazutaka Ikeda, Ryuta Mizutani

“…Abstract Mouse and human brains have different functions that depend on their neuronal networks. …”
Get full text

Double-path multiscale adaptive compressed sensing network for electronic data by Lubin Yu, Yongsheng Huang, Yiqiang Cheng, Qiliang Du, Zhenwei Zhou, Lianfang Tian, Shilie He, Honghui Liu

“…Then, the secondary reconstruction module uses the adaptive dilated convolution residual module to adaptively adjust the size of the convolution kernel to ensure the high-quality reconstruction of different signals and combines it with the tree-like structure residual block for enhanced reconstruction. …”
Get full text

Dual conditional GAN based on external attention for semantic image synthesis by Gang Liu, Qijun Zhou, Xiaoxiao Xie, Qingchen Yu

“…The graph attention (GAT) is added to the generator to strengthen the relationship between different categories in the generated image. A graph convolutional segmentation network (GSeg) is designed to learn information for each category. …”
Get full text

A steel surface defect detection method based on improved RetinaNet by Zhanglin Yang, Yu Liu

“…Firstly, deformable convolutions are integrated into the ResNet backbone for feature extraction, allowing the convolutional kernels to adaptively adjust their shapes when confronted with defects of varying shapes, thereby capturing defect regions more accurately. …”
Get full text

A Rotation Target Detection Network Based on Multi-Kernel Interaction and Hierarchical Expansion by Qi Wang, Guanghu Xu, Donglin Jing

Get full text

METRIC: Multiple preferences learning with refined item attributes for multimodal recommendation by Yunfei Zhao, Jie Guo, Longyu Wen, Letian Wang

Get full text

YOLO-LSM: A Lightweight UAV Target Detection Algorithm Based on Shallow and Multiscale Information Learning by Chenxing Wu, Changlong Cai, Feng Xiao, Jiahao Wang, Yulin Guo, Longhui Ma

“…Second, a Multiscale Lightweight Convolution (MLConv) is designed, and a lightweight feature extraction module, MLCSP, is constructed to enhance the extraction of detailed information. …”
Get full text

Jordanian banknote data recognition: A CNN-based approach with attention mechanism by Ahmad Nasayreh, Ameera S. Jaradat, Hasan Gharaibeh, Waed Dawaghreh, Rabia Mehamad Al Mamlook, Yaqeen Alqudah, Qais Al-Na'amneh, Mohammad Sh. Daoud, Hazem Migdady, Laith Abualigah

“…The suggested approach collaborates deep learning through a convolutional neural network (CNN) and another attention mechanism which contributes to focusing on features of importance while avoiding features of less importance. …”
Get full text

Partial-Net: A Method for Data Gaps Reconstruction on Mars Images by Depei Gu, Dingruibo Miao, Jianguo Yan, Zhigang Tu, Jean-Pierre Barriot

“…Recently, many restoration works are based on the standard convolutions, in which the raw features of noise or wrong initialization values of gaps at the encoder will be propagated to the decoder level. …”
Get full text

Mechanical Fault Diagnosis Method of a Disconnector Based on Improved Dung Beetle Optimizer–Multivariate Variational Mode Decomposition and Convolutional Neural Network–Bidirection... by Chi Zhang, Hongzhong Ma, Wei Sun

“…Finally, this matrix was input to convolutional neural network–bidirectional long short-term memory for fault classification. …”
Get full text

A computational framework for processing time-series of earth observation data based on discrete convolution: global-scale historical Landsat cloud-free aggregates at 30 m spatial... by Davide Consoli, Leandro Parente, Rolf Simoes, Murat Şahin, Xuemeng Tian, Martijn Witjes, Lindsey Sloat, Tomislav Hengl

“…The quality of the result was assessed using a benchmark dataset derived from the aggregated product and comparing different imputation strategies. The resulting reconstructed images can be used as input for machine learning models or to map biophysical indices. …”
Get full text

An Adaptive Spatio-Temporal Traffic Flow Prediction Using Self-Attention and Multi-Graph Networks by Basma Alsehaimi, Ohoud Alzamzami, Nahed Alowidi, Manar Ali

“…The ASTAM employs multi-temporal gated convolution with multi-scale temporal input segments to model complex non-linear temporal correlations. …”
Get full text

Rolling Bearing Fault Diagnosis Based on Recurrence Plot by Zheming Chen, Bin Xu, Zhong Zhang

“…For the prediction model, the traditional convolutional neural network is enhanced by integrating bidirectional gated recurrent unit and multi-head attention mechanism, allowing it to capture temporal features alongside the spatial features typically extracted by convolutional neural network. …”
Get full text

A Dual-Attentive Multimodal Fusion Method for Fault Diagnosis Under Varying Working Conditions by Yan Chu, Leqi Zhu, Mingfeng Lu

Get full text

Recurrent neural network based turbo decoding algorithms for different code rates by Shridhar B. Devamane, Rajeshwari L. Itagi

“…BER performance of both is compared with that of a convolutional Viterbi decoder in awgn channel. Both the structures are studied for different input data-lengths and code rates.…”
Get full text

Fault Diagnosis for Rolling Bearings Under Complex Working Conditions Based on Domain-Conditioned Adaptation by Xu Zhang, Gaoquan Gu

“…The approach first constructs a multi-scale self-calibrating convolutional neural network to aggregate input signals across different scales, adaptively establishing long-range spatial and inter-channel dependencies at each spatial location, thereby enhancing feature modeling under noisy conditions. …”
Get full text

High-Precision and Low-Complexity Silicon Waveguide-Integrated Temperature Sensor System by Zhiming Zhang, Haole Kong, Yi Li

“…To achieve precise temperature demodulation, this paper employed a convolutional neural network (CNN) for nonlinear fitting. …”
Get full text

Reconstruction of concrete morphology using deep learning by Ondřej Šperl, Jan Sýkora

Get full text

A novel chaotic interleaving algorithm for mobile wireless channels by Xianping WANG, Hui CAO

“…Interleaving technique is an efficient technique to resist serious burst errors over mobile wireless fading channels.To resist 2 dimensionality burst errors effectively,a novel chaotic interleaving algorithm based on Baker map was proposed.In the proposed scheme,the binary source sequence was converted to the data matrix,and then the data matrix was dispersed randomly by using the chaotic Baker map approach,in order to realize the function of transforming 2 dimensionality long bust error into the short 1 dimensionality short bust error after de-interleaving.In additional,the proposed algorithm was combined with the convolution code based on Viterbi decoding,and was applied into the scenario of convolutional codes (2,1,3) and the scenario of (2,1,7) separately for a performance comparison.The simulation results show that the performance of the proposed algorithm outperforms better than the traditional algorithms under image transmission over mobile wireless channel.Moreover,the anti-fading capability of the proposed algorithm grows as the packet length increases,while reducing the complexity significantly.Finally,the chaotic interleaver can also enhance every transmitted packet's security with different secret keys.…”
Get full text