Computational Intelligence最新文献

A Deformable Convolutional Neural Network for Video Super-Resolution 用于视频超分辨率的可变形卷积神经网络

IF 1.8 4区计算机科学

Computational Intelligence Pub Date : 2025-05-03 DOI: 10.1111/coin.70052

Xi Chen, Qi Zhang, Kai Liu, Yong Zhang

{"title":"A Deformable Convolutional Neural Network for Video Super-Resolution","authors":"Xi Chen, Qi Zhang, Kai Liu, Yong Zhang","doi":"10.1111/coin.70052","DOIUrl":"https://doi.org/10.1111/coin.70052","url":null,"abstract":"<div>\u0000 \u0000 <p>Convolutional Neural Networks used deep architectures to achieve deep feature extraction in video super-resolution. However, they suffered from challenges of rapid motion and complex scenes in video super-resolution. In this paper, we present a deformable convolutional neural network for video super-resolution (DVSRNet). DVSRNet mainly contains forward and backward feature propagation blocks (FPBs), feature enhancement blocks (FEBs), a feature fusion block (FFB), and a reconstruction block (RB). FPBs can leverage temporal sequence information to capture rich temporal dimensional information in video super-resolution. To restore detailed information, an optical flow technique guided a CNN to align the obtained structural information of different frames to reduce motion-induced blur and artifacts. To address deformable videos from motioned objects, two FEBs utilized deformable convolutions to adaptively correct misaligned objects to improve spatial continuity of videos. To improve reliability of obtained videos, an FFB is used to integrate relations of different video frames from forward and backward propagations. Finally, an RB via upsampling operations and a residual learning technique is used to construct high-quality videos. Experimental results demonstrate that our DVSRNet exhibits superior performance on multiple public datasets for video super-resolution. Its codes can be available at https://github.com/leyoukai/DVSRNet.</p>\u0000 </div>","PeriodicalId":55228,"journal":{"name":"Computational Intelligence","volume":"41 3","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143901086","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

RETRACTION 收缩

IF 1.8 4区计算机科学

Computational Intelligence Pub Date : 2025-05-02 DOI: 10.1111/coin.70054

引用次数: 0

RETRACTION 收缩

IF 1.8 4区计算机科学

Computational Intelligence Pub Date : 2025-05-02 DOI: 10.1111/coin.70056

引用次数: 0

RETRACTION 收缩

IF 1.8 4区计算机科学

Computational Intelligence Pub Date : 2025-05-02 DOI: 10.1111/coin.70055

引用次数: 0

RETRACTION 收缩

IF 1.8 4区计算机科学

Computational Intelligence Pub Date : 2025-05-02 DOI: 10.1111/coin.70058

引用次数: 0

Retraction 收缩

IF 1.8 4区计算机科学

Computational Intelligence Pub Date : 2025-05-02 DOI: 10.1111/coin.70057

引用次数: 0

Rethinking Correlation Filter Trackers for Small Unmanned Aircraft Systems 对小型无人机系统相关滤波跟踪器的再思考

IF 1.8 4区计算机科学

Computational Intelligence Pub Date : 2025-04-21 DOI: 10.1111/coin.70053

Wei Liu, Shuang Wu, Xin Yun, Youfa Liu

引用次数: 0

Safety Monitoring of Machine Learning Perception Functions: A Survey 机器学习感知功能的安全监控：调查

IF 1.8 4区计算机科学

Computational Intelligence Pub Date : 2025-04-20 DOI: 10.1111/coin.70032

Raul Sena Ferreira, Joris Guérin, Kevin Delmas, Jérémie Guiochet, Hélène Waeselynck

引用次数: 0

Vitamin D Analysis for Sustainable Healthcare in Inner London Borough 内伦敦区可持续医疗的维生素 D 分析

IF 1.8 4区计算机科学

Computational Intelligence Pub Date : 2025-04-16 DOI: 10.1111/coin.70050

Sandra Fernando, Viktor Sowinski-Mydlarz, Subeksha Shrestha, Sunila Maharjan, Duncan Stewart, Dee Bhakta, Gary McLean, Sarah Illingworth

{"title":"Vitamin D Analysis for Sustainable Healthcare in Inner London Borough","authors":"Sandra Fernando, Viktor Sowinski-Mydlarz, Subeksha Shrestha, Sunila Maharjan, Duncan Stewart, Dee Bhakta, Gary McLean, Sarah Illingworth","doi":"10.1111/coin.70050","DOIUrl":"https://doi.org/10.1111/coin.70050","url":null,"abstract":"<p>Vitamin D is vital for bone health, immune system support, and muscle function. Deficiency in Vitamin D is widespread, with up to 65% of individuals in certain populations, including Black students at London Metropolitan University, UK, being affected. This study focuses on the need for a deeper understanding of Vitamin D prescription patterns, specifically within an inner London borough, using advanced data analytics. Previous analysis, such as ones conducted by \u0000OpenPrescribing.net, has investigated NHS prescription data but lacked a focused examination on Vitamin D. Our study introduces a novel computational approach, integrating NHS datasets from 2013 to 2023. We developed a web-hosted dashboard using Python, Flask, Cesium, PowerBI, and libraries such as Pandas, Scikit-learn to provide real-time data visualization and predictive analytics. Our methodology involved API-driven ingestion of large-scale data, focusing on Vitamin D prescriptions in a borough, and mapping this against patient numbers. We used feature manipulation and model training to gain insights into prescription counts, dosages, medication types, and formulations. This interactive platform supports dynamic reporting through PowerBI and Cesium. Our findings reveal significant variations in prescription patterns among GP surgeries influenced by socioeconomic factors. This interdisciplinary project, in future collaboration with local GP federations, United Kingdom, enhances computational health data analysis and aims to inform better prescription practices and healthcare policies, ultimately improving policy practice and public health outcomes.</p>","PeriodicalId":55228,"journal":{"name":"Computational Intelligence","volume":"41 2","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/coin.70050","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143836340","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Convolutional Attention-Based Bidirectional Recurrent Neural Network for Human Action Recognition 基于卷积注意的人类动作识别双向递归神经网络

IF 1.8 4区计算机科学

Computational Intelligence Pub Date : 2025-04-15 DOI: 10.1111/coin.70049

Aditya Mahamkali, Manvitha Gali, Soumya Ranjan Jena, Velagapudi Sreenivas

{"title":"Convolutional Attention-Based Bidirectional Recurrent Neural Network for Human Action Recognition","authors":"Aditya Mahamkali, Manvitha Gali, Soumya Ranjan Jena, Velagapudi Sreenivas","doi":"10.1111/coin.70049","DOIUrl":"https://doi.org/10.1111/coin.70049","url":null,"abstract":"<div>\u0000 \u0000 <p>Human activity recognition (HAR) technology plays a major role in today's world and is used in detecting human actions and poses in real-time. In the past, researchers employed statistical machine learning methods to build and extract attributes of various movements manually. However, typical techniques are becoming increasingly ineffective in the face of exponentially increasing waveform data that lacks unambiguous principles. With the advancement of deep learning technology, manual feature extraction is no longer required, and performance on challenging human activity recognition problems can be improved. However, various deep learning models have problems such as time consumption, inaccuracy, and the vanishing gradient problem. Therefore, to solve these problems, the proposed study used a deep convolutional attention-based bidirectional recurrent neural network to detect human activities in the provided samples. The input images are first pre-processed using an adaptive bilateral filtering approach to improve their quality and remove image noise. Then, the crucial features are recovered using the convolutional neural network (CNN) based encoder-decoder model. Finally, a deep convolutional attention-based bidirectional recurrent neural network is used to identify human activities. The model recognizes human actions with higher effectiveness and lower latency. The human behaviors are identified using the HMDB51 dataset. The proposed model acquired the highest accuracy of 95.46%, which is 10.51% superior to multi-layer perceptron (MLP), 6.99% superior to CNN, 12.76% superior to long short-term memory (LSTM), 5.59% superior to Bidirectional LSTM (BiLSTM), and 4.82% superior to CNN-LSTM, respectively.</p>\u0000 </div>","PeriodicalId":55228,"journal":{"name":"Computational Intelligence","volume":"41 2","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143835766","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0