An Integrated Lightweight Neural Network Design and FPGA-Accelerated Edge Computing for Chili Pepper Variety and Origin Identification via an E-Nose by Ziyu Guo, Yong Yin, Haolin Gu, Guihua Peng, Xueya Wang, Ju Chen, Jia Yan

“…The system uses the AIRSENSE PEN3 e-nose from Germany to collect gas data from thirteen different varieties of chili peppers and two specific varieties of chili peppers originating from seven different regions. …”
Get full text

Fault diagnosis method of mine hoist main bearing with small sample based on VAE-WGAN by Fan JIANG, Hongyan SONG, Xi SHEN, Zhencai ZHU, Shuman CHENG

“…In order to improve the feature extraction ability and fault diagnosis accuracy of fault diagnosis models, based on the lightweight convolutional neural network MobileNetV2, the convolutional block attention mechanism CBAM is integrated into the deep feature mapping of MobileNetV2, and an attention mechanism convolutional classification network CBAM-MobileNetV2 is constructed. …”
Get full text

GAT-Enhanced YOLOv8_L with Dilated Encoder for Multi-Scale Space Object Detection by Haifeng Zhang, Han Ai, Donglin Xue, Zeyu He, Haoran Zhu, Delian Liu, Jianzhong Cao, Chao Mei

“…The Dilated Encoder network is introduced to cover different-scale targets by differentiating receptive fields, and the feature weight allocation is optimized by combining it with a Convolutional Block Attention Module (CBAM). …”
Get full text

Semi-supervised gearbox fault diagnosis under variable working conditions based on masked contrastive learning by ZHANG Huiyun, ZUO Fangjun, LI Hang, YU Xi

“…Secondly, a dynamic convolutional neural network was employed to dynamically weight and aggregate the masked instances, enabling discriminative feature modeling of different masked instances. …”
Get full text

Time Series Forecasting Method Based on Multi-Scale Feature Fusion and Autoformer by Xiangkai Ma, Huaxiong Zhang

“…Based on multi-scale convolutional operations, a multi-scale feature fusion network is proposed, combined with date–time encoding to build the MD–Autoformer time series forecasting model, which enhances the model’s ability to capture information at different scales. …”
Get full text

CAPTCHA Recognition Method Based on CNN with Focal Loss by Zhong Wang, Peibei Shi

“…The traditional CAPTCHA recognition method has poor recognition ability and robustness to different types of verification codes. For this reason, the paper proposes a CAPTCHA recognition method based on convolutional neural network with focal loss function. …”
Get full text

A hierarchical reinforcement learning approach for energy‐aware service function chain dynamic deployment in IoT by Shuyi Wang, Haotong Cao, Longxiang Yang

“…The suggested method is tested in three typical complicated networks with different network parameters to show its suitability in different network scenarios.…”
Get full text

Synergizing BRDF correction and deep learning for enhanced crop classification in GF-1 WFV imagery by Yuanwei Chen, Yang Li, Runze Li, Chongzheng Guo, Jilin Li

“…First, a BRDF correction method based on normalized difference vegetation index (NDVI) and anisotropy flat index (AFX) is developed to normalize radiometric discrepancies. …”
Get full text

Automated liver segmentation from CT images using modified ResUNet by R.V. Manjunath, Yashaswini Gowda N, H.M. Manu

“…In this study we proposed an automatic system that utilizes convolutional layers to efficiently extract features while maintaining spatial information. …”
Get full text

Machine Learning Prediction of Storm‐Time High‐Latitude Ionospheric Irregularities From GNSS‐Derived ROTI Maps by Lei Liu, Y. Jade Morton, Yunxiang Liu

“…Abstract This study presents an image‐based convolutional long short‐term memory (convLSTM) machine learning algorithm to predict storm‐time ionospheric irregularities. …”
Get full text

KSC-Net: a biologically inspired spatio-temporal correlation network for video-based human action recognition by Hui Ma, Xuelian Ma

“…First, a Dynamic Feature Filter (DF) is introduced to enhance sensitivity to salient motion by suppressing redundant visual signals through second-order temporal difference and Laplacian-based spatial filtering. This module mimics the edge-enhancing and motion-focusing mechanisms of human vision. …”
Get full text

Algorithm for Extraction of Reflection Waves in Single-Well Imaging Based on MC-ConvTasNet by Wanting Lin, Jiaqi Xu, Hengshan Hu

“…In the signal channels of the common-source gather, there exists a notable arrival time difference between direct waves and reflected waves. …”
Get full text

Ultrasound Localization of Nitinol Wire of Sub-Wavelength Dimension by D. R. DeVries, L. J. Olafsen, J. S. Olafsen, H. H. Nguyen, K. E. Schubert, S. Dayawansa, J. H. Huang

“…<italic>Results:</italic> For the full range of diameters traversing the phantom, the wires were localized successfully via visual inspection of both regular and difference ultrasound images. Similarly, two convolutional neural networks were trained, and both achieved an accuracy of over 95&#x0025;. …”
Get full text

WDM C-band four channel demultiplexer using cascaded multimode interference on SiN strip waveguide structure by Malka Dror

“…Our design was optimized using AI-enhanced RSoft-CAD simulations that combined the Beam Propagation Method (BPM) and Finite-Difference Time-Domain (FDTD) techniques, integrated with convolutional neural network (CNN) machine learning algorithms. …”
Get full text

An Investigation on Prediction of Infrastructure Asset Defect with CNN and ViT Algorithms by Nam Lethanh, Tu Anh Trinh, Mir Tahmid Hossain

“…The results confirm that the accuracies of both CNN and ViT models exceed 95% after 100 epochs of training, with no significant difference observed between them for binary classification. …”
Get full text

Linear-nonlinear cascades capture synaptic dynamics. by Julian Rossbroich, Daniel Trotter, John Beninger, Katalin Tóth, Richard Naud

“…Short-term synaptic dynamics differ markedly across connections and strongly regulate how action potentials communicate information. …”
Get full text

On the performance of non‐profiled side channel attacks based on deep learning techniques by Ngoc‐Tuan Do, Van‐Phuc Hoang, Van Sang Doan, Cong‐Kha Pham

“…This paper proposes and evaluates the applications of different DL techniques including the Convolutional Neural Network and the multilayer perceptron models for non‐profiled attacks on the AES‐128 encryption implementation. …”
Get full text

Exploring latent weight factors and global information for food-oriented cross-modal retrieval by Wenyu Zhao, Dong Zhou, Buqing Cao, Wei Liang, Nitin Sukhija

“…Though several studies are introduced to bridge this gap, they still suffer from two major limitations: 1) The simple embedding concatenation only can capture the simple interactions rather than complex interactions between different recipe components. 2) The image feature extraction based on convolutional neural networks only considers the local features and ignores the global features of an image, as well as the interactions between different extracted features. …”
Get full text

Method to generate cyber deception traffic based on adversarial sample by Yongjin HU, Yuanbo GUO, Jun MA, Han ZHANG, Xiuqing MAO

“…In order to prevent attacker traffic classification attacks,a method for generating deception traffic based on adversarial samples from the perspective of the defender was proposed.By adding perturbation to the normal network traffic,an adversarial sample of deception traffic was formed,so that an attacker could make a misclassification when implementing a traffic analysis attack based on a deep learning model,achieving deception effect by causing the attacker to consume time and energy.Several different methods for crafting perturbation were used to generate adversarial samples of deception traffic,and the LeNet-5 deep convolutional neural network was selected as a traffic classification model for attackers to deceive.The effectiveness of the proposed method is verified by experiments,which provides a new method for network traffic obfuscation and deception.…”
Get full text

Enhanced pedestrian trajectory prediction via overlapping field-of-view domains and integrated Kolmogorov-Arnold networks. by Hongxia Wang, Yang Liu, Zhenkai Nie

“…By rigorously dividing monocular and binocular overlapping visual regions and utilizing different influence factors, the model pedestrian interactions more realistically. …”
Get full text