A Method of Image Restoration for Distortion of Object in Water-Air Cross-Media by Yuhe Gao, Jishen Jia, Lei Cai, Meng Zhou, Haojie Chai, Jinze Jia

“…To address these issues, this paper proposes a repair network to correct object image distortion in water-air cross-media. Firstly, convolutional combination performs feature extraction on water-air cross-media images, which retains the same features at the same scale and marks feature points with large differences. …”
Get full text

An improved ViT model for music genre classification based on mel spectrogram. by Pingping Wu, Weijie Gao, Yitao Chen, Fangfang Xu, Yanzhe Ji, Juan Tu, Han Lin

“…In this paper, an improved ViT model is proposed to extract more comprehensive music genre features from Mel spectrograms by leveraging the strengths of both convolutional neural networks and Transformers. Also, the paper incorporates a channel attention mechanism by amplifying differences between channels within the Mel spectrograms of individual music genres, thereby facilitating more precise classification. …”
Get full text

Knowledge Distillation‐Based Zero‐Shot Learning for Process Fault Diagnosis by Yi Liu, Jiajun Huang, Mingwei Jia

“…When an unknown fault arises, there exist differences between the information extracted by the teacher model and the student model. …”
Get full text

Mapping stains on flat roofs using semantic segmentation based on deep learning by Lara Monalisa Alves dos Santos, Leonardo Rabero Lescano, Gabriel Toshio Hirokawa Higa, Vanda Alice Garcia Zanoni, Lenildo Santos da Silva, Cesar Ivan Alvarez, Hemerson Pistori

“…During inspections of roofing systems, an inspector's field of vision differs from that of drones during overflights. As a result, traditional inspections might not always detect the presence and severity of stains, making maintenance on flat roofs a complex task. …”
Get full text

Automated Age Estimation from OPG Images and Patient Records Using Deep Feature Extraction and Modified Genetic–Random Forest by Gulfem Ozlu Ucan, Omar Abboosh Hussein Gwassi, Burak Kerem Apaydin, Bahadir Ucan

“…<b>Methods:</b> Two-Dimensional Deep Convolutional Neural Network (2D-DCNN) and One-Dimensional Deep Convolutional Neural Network (1D-DCNN) techniques were used to extract features from panoramic radiographs and patient records. …”
Get full text

A Novel Swin-Transformer with Multi-Source Information Fusion for Online Cross-Domain Bearing RUL Prediction by Zaimi Xie, Chunmei Mo, Baozhu Jia

“…The method uses a Bidirectional Long Short-Term Memory (Bi-LSTM) network to capture temporal features, which are transformed into 2D images using Gramian Angular Fields (GAF) for spatial feature extraction by a 2D Convolutional Neural Network (CNN). A self-attention mechanism further integrates multi-source features, while an adversarial Multi-Kernel Maximum Mean Discrepancy (MK-MMD) combined with a relational network mitigates feature distribution differences across domains. …”
Get full text

Multiscale implicit frequency selective network for single-image dehazing by Zhibo Wang, Jia Jia, Jeongik Min

“…As hazy and clear images considerably differ in high-frequency components, we introduce an implicit frequency selection module to amplify high-frequency components of features and generate candidate feature maps. …”
Get full text

Review of image classification based on deep learning by Fu SU, Qin LV, Renze LUO

“…In recent years,deep learning performed superior in the field of computer vision to traditional machine learning technology.Indeed,image classification issue drew great attention as a prominent research topic.For traditional image classification method,huge volume of image data was of difficulty to process and the requirements for the operation accuracy and speed of image classification could not be met.However,deep learning-based image classification method broke through the bottleneck and became the mainstream method to finish these classification tasks.The research significance and current development status of image classification was introduced in detail.Also,besides the structure,advantages and limitations of the convolutional neural networks,the most important deep learning methods,such as auto-encoders,deep belief networks and deep Boltzmann machines image classification were concretely analyzed.Furthermore,the differences and performance on common datasets of these methods were compared and analyzed.In the end,the shortcomings of deep learning methods in the field of image classification and the possible future research directions were discussed.…”
Get full text

Quantifying the non-isomorphism of global urban road networks using GNNs and graph kernels by Linfang Tian, Weixiong Rao, Kai Zhao, Huy T. Vo

“…Abstract A novel concept of quantifying graph non-isomorphism is introduced to measure structural differences between graphs, and thus overcoming the strict limitations of traditional graph isomorphism tests. …”
Get full text

ML‐UrineQuant: A machine learning program for identifying and quantifying mouse urine on absorbent paper by Warren G. Hill, Bryce MacIver, Gary A. Churchill, Mariana G. DeOliveira, Mark L. Zeidel, Marcelo Cicconet

“…Abstract The void spot assay has gained popularity as a way of assessing functional bladder voiding parameters in mice, but analyzing the size and distribution of urine spot patterns on filter paper with software remains problematic due to inter‐laboratory differences in image contrast and resolution quality and non‐void artifacts. …”
Get full text

Surface anomaly detection on island-based PV panels using edge neural networks by ZHANG Yinxian, ZHANG Zhanyao, ZHANG Xiya

“…Surface anomaly detection on photovoltaic （PV） panels is crucial for their operation and maintenance， especially in island environments where challenges such as small anomaly sizes and minimal color differences are prevalent. Due to the poor accuracy and low efficiency of existing detection methods， the paper proposes a surface anomaly detection method for island-based PV panels using edge neural networks. …”
Get full text

KANDiff: Kolmogorov–Arnold Network and Diffusion Model-Based Network for Hyperspectral and Multispectral Image Fusion by Wei Li, Lu Li, Man Peng, Ran Tao

“…To address these problems, we propose a new model, KanDiff, for hyperspectral and multispectral image fusion. To address the differences in modal information between multispectral and hyperspectral images, KANDiff incorporates Kolmogorov–Arnold Networks (KAN) to guide the inputs. …”
Get full text

RESEARCH ON CARBIDES IN M50 BEARING STEEL BASED ON MASK R-CNN DEEP LEARNING MODEL by SUN Ruiming, LI Shuxin, LU Siyuan, JIN Yongsheng, XIAO Huahai

“…Under the scanning electron microscopy (SEM), they exhibit significant differences in the shape, size, and distribution. Some carbides have larger sizes and uneven distribution. …”
Get full text

EFINet: Efficient Feature Interaction Network for Real-Time RGB-D Semantic Segmentation by Zhe Yang, Baozhong Mu, Mingxun Wang, Xin Wang, Jie Xu, Baolu Yang, Cheng Yang, Hong Li, Rongqi Lv

“…It requires models to balance computational cost and performance by employing more efficient mechanisms to effectively recognize differences in RGB-D multimodal information, retain complementary information, and reduce redundancies. …”
Get full text

Enabling Automated Device Size Selection for Transcatheter Aortic Valve Implantation by Patricio Astudillo, Peter Mortier, Johan Bosmans, Ole De Backer, Peter de Jaegere, Matthieu De Beule, Joni Dambre

“…The method was validated against an interoperator variability study of the same 118 patients. The differences between the manually obtained aortic annulus measurements and the automatic predictions were similar to the differences between two independent observers (paired diff. of 3.3 ± 16.8 mm2 vs. 1.3 ± 21.1 mm2 for the area and a paired diff. of 0.6 ± 1.7 mm vs. 0.2 ± 2.5 mm for the perimeter). …”
Get full text

DOA Estimation Based on CNNs Embedded With Mamba by Zhang Ziyan, Yi Shichao, Wang Chengyi

“…The convolutional neural networks (CNN) have been proved to be more efficient in Direction of Arrival (DOA) estimation of underwater acoustic array signals. …”
Get full text

The role of learned song in the evolution and speciation of Eastern and Spotted towhees. by Ximena León Du'Mottuchi, Nicole Creanza

“…Here, we quantify 16 song features to analyze geographic variation in Spotted and Eastern towhee songs and assess species-level differences. We then use several machine learning models to measure how accurately their songs can be classified by species. …”
Get full text

Leveraging two-dimensional pre-trained vision transformers for three-dimensional model generation via masked autoencoders by Muhammad Sajid, Kaleem Razzaq Malik, Ateeq Ur Rehman, Tauqeer Safdar Malik, Masoud Alajmi, Ali Haider Khan, Amir Haider, Seada Hussen

“…In vision, attention is used in conjunction with convolutional networks or to replace individual convolutional network elements while preserving the overall network design. …”
Get full text

Comparative Anatomical, Histological, and Histochemical Study of the Duodenum between Common Moorhen (Gallinula chloropus) and Domestic Fowl (Gallus domesticus) by Eman Jassem, Adel Hussein, Alaa Sawad

“…The results of statistical analysis revealed significant differences at level P&lt;0.05 in the thickness of (tunica mucosa, crypts, tunica sub mucosa, and tunica muscularis) between two birds. …”
Get full text

Accurate and Data‐Efficient Micro X‐ray Diffraction Phase Identification Using Multitask Learning: Application to Hydrothermal Fluids by Yanfei Li, Juejing Liu, Xiaodong Zhao, Wenjun Liu, Tong Geng, Ang Li, Xin Zhang

“…Most significantly, MTL models tuned to analyze raw and unmasked XRD patterns achieve close performance to models analyzing preprocessed data, with minimal accuracy differences. This work indicates that advanced deep learning architectures like MTL can automate arduous data handling tasks, streamline the analysis of distorted XRD patterns, and reduce the reliance on labor‐intensive experimental datasets.…”
Get full text