Boosting Degradation Representation Learning for Blind Image Super-Resolution by YUAN Jiang, MA Ji, ZHOU Dengwen

“…In most convolutional neural networks-based super-resolution (SR) methods, the degradation assumptions are fixed and known (e.g., bicubic degradation). …”
Get full text

Drug-drug interaction prediction of traditional Chinese medicine based on graph attention networks by Bin Yang, Dan Song, Yadong Li, Jinglong Wang

“…Our approach leverages graph-based representations of chemical molecules and employs attention mechanism to extract deep structural features, enabling the effective prediction of TCMDDI by capturing spatial structural relationships among different compounds. Furthermore, we construct a comprehensive dataset encompassing three different categories of herbal ingredients, informed by traditional TCM principles. …”
Get full text

Multi-label Bird Species Classification Using Transfer Learning Network by Xue HAN, Jianxin PENG

“…The final dataset consists of 28 000 audio clips, each 5 s long, containing overlapping vocalizations of two or three bird species among 11 different species. Several pre-trained convolutional neural networks (CNNs), including InceptionV3, ResNet50, VGG16, and VGG19, were evaluated for extracting deep features from audio signals represented as mel spectrograms. …”
Get full text

Research on Surface Defects Classification for PET Preform by Fusing Multi-Scale Features by Chunmei Duan, Taochuan Zhang, Lei Han, Huilin Tan

“…Multi-scale features fusion combines features from different scales to produce more accurate and robust feature representations, which improve the accuracy, stability and adaptability of PET preform detection model. …”
Get full text

Progressive multi-scale multi-attention fusion for hyperspectral image classification by Hu Wang, Sixiang Quan, Jun Liu, Hai Xiao, Yingying Peng, Zhihui Wang, Huali Li

“…The complementary responsibilities of the three branches address the issue of feature loss in details and improve the network’s learning efficiency across feature maps of different scales. By cleverly extracting features from different branches multiple times, the fusion of multi-scale features is achieved, avoiding the limitations of single-scale feature representation. …”
Get full text

Effects of Automatic Hyperparameter Tuning on the Performance of Multi‐Variate Deep Learning‐Based Rainfall Nowcasting by Amirmasoud Amini, Mehri Dolatshahi, Reza Kerachian

“…This paper combines different convolutional, long short‐term memory (LSTM)‐based networks and NWPs using ensemble techniques (i.e., bagging, random forest, and adaboost methods) with automatic hyperparameter tuning for multi‐step rainfall nowcasting. …”
Get full text

Protein sequence classification using natural language processing techniques by Huma Perveen, Julie Weeds

“…Performance was tested using different amino acid ranges and sequence lengths with a focus on generalization across unseen evolutionary families. …”
Get full text

CNN‐based off‐angle iris segmentation and recognition by Ehsaneddin Jalilian, Mahmut Karakaya, Andreas Uhl

“…In this work, the general effect of different gaze angles on ocular biometrics is discussed, and the findings are then related to the CNN‐based off‐angle iris segmentation results and the subsequent recognition performance. …”
Get full text

Emotion Recognition from Speech in a Subject-Independent Approach by Andrzej Majkowski, Marcin Kołodziej

“…The effectiveness of recognizing seven and eight different emotions was analyzed. A range of acoustic features, including energy features, mel-cepstral features, zero-crossing rate, fundamental frequency, and spectral features, were utilized to analyze the emotions in speech. …”
Get full text

Real-Time Fault Diagnosis of Mooring Chain Jack Hydraulic System Based on Multi-Scale Feature Fusion Under Diverse Operating Conditions by Yujia Liu, Wenhua Li, Haoran Ye, Shanying Lin, Lei Hong

“…Under complex and dynamic marine operating conditions, different severity faults in the CJ hydraulic system display distinct time-scale characteristics. …”
Get full text

The effectiveness of a novel artificial intelligence (AI) model in detecting oral and dental diseases by Ravi Rathod, Saffa Dean, Christopher Sproat

“…Ninety different unseen images were selected and presented to the AI model to test the accuracy of disease detection. …”
Get full text

Time series prediction based on the variable weight combination of the T-GCN-Luong attention and GRU models by Yushu Guo, Jiacheng Huang, Xuchu Jiang

“…The model uses the T-GCN model to capture spatiotemporal features while introducing Luong attention to weight the inputs at different time steps to improve the prediction accuracy and further reduce the prediction error by fusing the outputs of the T-GCN-Luong attention and GRU models through the variable weight combination method. …”
Get full text

Benchmarking Deep Learning for Wetland Mapping in Denmark Using Remote Sensing Data by Muhammad Rizwan Asif

“…While remote sensing combined with deep learning (DL) offers a promising solution, inconsistencies in wetland classification systems—where different regions define wetland types based on their policy frameworks and conservation priorities—limit the applicability of these models. …”
Get full text

Evaluating Wind Speed Forecasting Models: A Comparative Study of CNN, DAN2, Random Forest and XGBOOST in Diverse South African Weather Conditions by Fhulufhelo Walter Mugware, Caston Sigauke, Thakhani Ravele

“…This research compares the effectiveness of Dynamic Architecture for Artificial Neural Networks (DAN2), convolutional neural networks (CNN), random forest and XGBOOST in predicting wind speed across three locations in South Africa, characterised by different weather patterns. …”
Get full text

Landslide Segmentation in High-Resolution Remote Sensing Images: The Van–UPerAttnSeg Framework with Multi-Scale Feature Enhancement by Chang Li, Quan Zou, Guoqing Li, Wenyang Yu

“…Then, it adopts an encoder–decoder structure, where the encoder is a visual attention network (Van) that focuses on extracting discriminative features of different scales from landslide images. The decoder consists of a pyramid pooling module (PPM) and feature pyramid network (FPN), combined with a convolutional block attention module (CBAM) module. …”
Get full text

Obstacle inversion based on the self-healing property of structured light by Shuailing Wang, Zhe Zhao, Mingjian Cheng, Jingping Xu, Yaping Yang

“…Firstly, we investigated the impact of obstacles of varying sizes and shapes on PVB at different stages of propagation, leading to a key conclusion the self-healing process of PVB can be divided into two parts: the self-healing of the obstructed region and the damage in the unstructured region. …”
Get full text

Study on the quantitative analysis of Tilianin based on Raman spectroscopy combined with deep learning. by Wen Jiang, Wei Liu, Xiaotong Xin, Wei Zhang, Junhui Chen, Jieyu Liu, Yanqi Ma, Cheng Chen, Xiaomei Pan

“…The structure of this model not only focuses on the deep and shallow features of the spectrum, but also the information between different channels, and the self-attention mechanism further extracts the features and outputs the predicted values of Tilianin concentration through the fully connected layer. …”
Get full text

Untrained perceptual loss for image denoising of line-like structures in MR images. by Elisabeth Pfaehler, Daniel Pflugfelder, Hanno Scharr

“…The uPL network's initialization is not important (e.g. for MR root images SSIM differences of 0.01 occur across initializations, while network depth and pooling operations impact denoising performance slightly more (SSIM of 0.83 for 5 convolutional layers and kernel size 3 vs. 0.86 for 5 convolutional layers and kernel size 5 for the root dataset). …”
Get full text

Enhanced prediction of heat transfer in jet impingement cooling using an artificial intelligence: A case study by Mehmet Berkant Özel, Ufuk Durmaz, Muhammed Ali Nur Öz, Ahmet Ümit Tepe, Cemil Öz, Ünal Uysal, Orhan Yalçinkaya, Ali Cemal Beni̇m, Norah Alomayrah, M.S. Al-Buriahi

“…Jet impingement cooling was examined with four different Reynolds numbers (16250, 21700, 27100, 36250) and six dimensionless gaps between the jet and the target surface (G/D = 1, 2, 3, 4, 5, and 6). …”
Get full text

Feature Selection-Based Hierarchical Deep Network for Image Classification by Guiqing He, Jiaqi Ji, Haixi Zhang, Yuelei Xu, Jianping Fan

“…In this paper, a novel hierarchical deep network is proposed to combine the deep convolutional neural network and the feature selection-based tree classifier efficiently for image classification. …”
Get full text