Rethinking feature representation and attention mechanisms in intelligent recognition of leaf pests and diseases in wheat by Yuhan Zhang, Dongsheng Liu

“…To address the above problems and needs, we rethink the feature representation and attention mechanism in intelligent recognition of wheat leaf diseases and pests, and propose a representation and recognition network (RReNet) based on the feature attention mechanism. RReNet captures key information more efficiently by focusing on complex pest and disease characteristics and fusing multi-semantic feature information. …”
Get full text

Autonomous Extraction Technology for Aquaculture Ponds in Complex Geological Environments Based on Multispectral Feature Fusion of Medium-Resolution Remote Sensing Imagery by Zunxun Liang, Fangxiong Wang, Jianfeng Zhu, Peng Li, Fuding Xie, Yifei Zhao

“…Experimental and comparative results reveal that the proposed MAFU-Net method achieves an F1 score of 90.67% and an intersection over union (IoU) of 83.93% on the CHN-LN4-ISAPS-9 dataset, outperforming advanced methods such as U-Net, DeepLabV3+, SegNet, PSPNet, SKNet, UPS-Net, and SegFormer. …”
Get full text

A multi-domain dual-stream network for hyperspectral unmixing by Jiwei Hu, Tianhao Wang, Qiwen Jin, Chengli Peng, Quan Liu

“…In this paper, we propose a novel multi-domain dual-stream network, called MdsNet, which enhances performance by incorporating high-rank spatial information to guide the unmixing process. …”
Get full text

Nonlocal and Local Feature-Coupled Self-Supervised Network for Hyperspectral Anomaly Detection by Degang Wang, Longfei Ren, Xu Sun, Lianru Gao, Jocelyn Chanussot

“…To this end, this article proposes a novel nonlocal and local feature-coupled self-supervised network (NL2Net) tailored for HAD. NL2Net employs a dual-branch architecture that integrates both local and nonlocal feature extraction. …”
Get full text

Application of Optimized Convolution Neural Network Model in Mural Segmentation by Zhiqiang Chen, Leelavathi Rajamanickam, Xiaodong Tian, Jianfang Cao

“…The obtained experimental results indicate that MC-DM improves the training accuracy by 1 percentage point compared with the conventional SegNet-based image segmentation model, and by 2 percentage points compared with the PspNet network-based image segmentation model. …”
Get full text

Underwater image enhancement via multiscale disentanglement strategy by Jiaquan Yan, Hao Hu, Yijian Wang, Muhammad Wasim Nawaz, Naveed Ur Rehman Junejo, Ente Guo, Huibin Feng

Get full text

An Approach for Detecting Tomato Under a Complicated Environment by Chen-Feng Long, Yu-Juan Yang, Hong-Mei Liu, Feng Su, Yang-Jun Deng

“…To address these challenges, this study proposes a tomato detection method based on Graph-CenterNet. The method employs Vision Graph Convolution (ViG) to replace traditional convolutions, thereby enhancing the flexibility of feature extraction, while reducing one downsampling layer to strengthen global information capture. …”
Get full text

SSMSFuse: A Spectral and Spatial Multiscale Coupling Fusion Model for Hyperspectral and Multispectral Image by Siyuan Liu, Yingchao Fan, Qi Hu, Bing Li, Yudong Zhang, Shuaiqi Liu

“…Spe-Net is constructed using self-attention, which can model the long-distance spectral dependencies of HSI to better extract spectral information from HSI. …”
Get full text

Bio-Inspired Hyperparameter Tuning of Federated Learning for Student Activity Recognition in Online Exam Environment by Ramu Shankarappa, Nandini Prasad, Ram Mohana Reddy Guddeti, Biju R. Mohan

Get full text

Ultra-sparse reconstruction for photoacoustic tomography: Sinogram domain prior-guided method exploiting enhanced score-based diffusion model by Zilong Li, Jiabin Lin, Yiguang Wang, Jiahong Li, Yubin Cao, Xuan Liu, Wenbo Wan, Qiegen Liu, Xianlin Song

“…Notably, for in vivo data under 32 projections, the sinogram structural similarity improved by ∼21 % over U-Net, and the image structural similarity increased by ∼51 % and ∼84 % compared to U-Net and delay-and-sum methods, respectively. …”
Get full text

Contrastive learning-driven framework for neuron morphology classification by Yikang Jiang, Hao Tian, Quanbing Zhang

Get full text

Intracranial Aneurysm Segmentation with a Dual-Path Fusion Network by Ke Wang, Yong Zhang, Bin Fang

“…Our research introduces the innovative Dual-Path Fusion Network (DPF-Net), an advanced deep learning architecture crafted to refine IAs segmentation by adeptly incorporating detailed information. …”
Get full text

Pulmonary diseases accurate recognition using adaptive multiscale feature fusion in chest radiography by Mengran Zhou, Lipeng Gao, Kai Bian, Haonan Wang, Ning Wang, Yue Chen, Siyi Liu

Get full text

Efficient deep learning model for classifying lung cancer images using normalized stain agnostic feature method and FastAI-2 by Pranshu Saxena, Sanjay Kumar Singh, Mamoon Rashid, Sultan S. Alshamrani, Mrim M. Alnfiai

Get full text

Emotion Recognition Based on Handwriting Using Generative Adversarial Networks and Deep Learning by Hengnian Qi, Gang Zeng, Keke Jia, Chu Zhang, Xiaoping Wu, Mengxia Li, Qing Lang, Lingxuan Wang

Get full text

Data-Driven Prediction of Grape Leaf Chlorophyll Content Using Hyperspectral Imaging and Convolutional Neural Networks by Minglu Zeng, Xinghui Zhu, Ling Wan, Jian Xu, Luming Shen

Get full text

Optimizing Backbone Networks Through Hybrid–Modal Fusion: A New Strategy for Waste Classification by Houkui Zhou, Qifeng Ding, Chang Chen, Qinqin Liao, Qun Wang, Huimin Yu, Haoji Hu, Guangqun Zhang, Junguo Hu, Tao He

Get full text

Enhancing Medical X-Ray Image Classification with Neutrosophic Set Theory and Advanced Deep Learning Models by Walid Abdullah

“…NS theory introduces three domains: True (T), Indeterminate (I), and False (F) to manage image uncertainty and noise, allowing deep learning models to better interpret complex, ambiguous visual information. To evaluate the approach, five state-of-the-art deep learning models—MobileNet, ResNet50, VGG16, DenseNet121, and InceptionV3 are utilized, and their performance was evaluated on two different medical image datasets: Cervical spine injuries detection and chest disease classification. …”
Get full text

Bio-inspired swarm intelligence for enhanced real-time aerial tracking: integrating whale optimization and grey wolf optimizer algorithms by GaoFeng Han

“…Experimental results show that compared with mainstream models such as ConvNeXt, ResNet, EfficientNet, MobileNetV3, and DenseNet, WGWO improves target recognition accuracy to 0.92 and reduces the target loss rate to only 2.35% for uniformly moving targets. …”
Get full text

Extracting knowledge of preventive maintenance using data mining technique in interaction with production within textile industry by Shahram Fatemi

“…Using IBM SPSS Modeler 18, the most significant results of datamining calculations to extract knowledge are as follows, which are arranged based on main predictors of the research: predicting models of "strategy innovation in net with data code (A5)" with the prediction wight of 0.34; "technology innovation in net with data code (A1)" with the prediction wight of 0.30; "work environment innovation in net with data code (A3)" with the prediction wight of 0.16; Quality innovation in net with data code (A4)" with the prediction wight of 0.15; "employe  innovation in net with data code (A2)" with the prediction wight of 0.10 are utilized to accurately analyze preventive maintenance in interaction with production.…”
Get full text