检索结果-内蒙古大学图书馆

IEEE Transactions on artificial intelligence 2024年第2期5卷 698-708页

作者： Dutta, H Pallab Jyoti Bhuyan, M.K. Neog, Debanga Raj Macdorman, Karl F. Laskar, R.H. Department of Electronics and Electrical Engineering Indian Institute of Technology Assam Guwahati781039 India Department of Electronics and Electrical Engineering and Mehta Family School of Data Science and Artificial Intelligence Indian Institute of Technology Assam Guwahati781039 India Mehta Family School of Data Science and Artificial Intelligence Indian Institute ofTechnology Assam Guwahati781039 India School of Informatics and Computing Indiana University IN46202 United States Department of Electronics and Communication Engineering National Institute of Technology Assam Silchar788010 India

In this article, we propose a hand gesture-operated system as an AI application to relieve discomfort and restore function in hand and arm movements caused by injuries and nerve and muscle complications. The system trains patients with hand exercises, such as performing hand gestures accurately, traversing within specified bounds, and operating a hand gesture calculator. However, the system requires accurate hand gesture detection, which is impeded by background clutter and variations in illumination and in the hand's size and angle. To address this, we developed a robust hand detection module that uses a single-stage transformer deep network. The transformer network encodes global information and uses bipartite matching to reduce the frequency of spurious detections. It drives a regression head and a classification head to localize the hand gesture in a bounding box and assign it a class label. Hand keypoints are also detected to support drawing, path traversal, and calculator use. The approach is evaluated on two benchmark datasets: 1) OUHANDS and 2) NUS. The method yields 89.6% accuracy for OUHANDS and 100% for NUS. These results indicate that precise hand detection can support a robust system for rehabilitation through hand exercises. Our experiments confirm that the users' hand function progressively improved. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Contradicted in Reliable, Replicated in Unreliable: Dual-Source Reference for Fake News Early Detection 39

Contradicted in Reliable, Replicated in Unreliable: Dual-Sou...

引用

39th Annual AAAI Conference on artificial intelligence, AAAI 2025

作者： Feng, Yifan Li, Weimin Wang, Yue Wang, Jingchao Liu, Fangfang Han, Zhongming School of Computer Engineering and Science Shanghai University Shanghai200444 China School of Computer and Artificial Intelligence Beijing Technology and Business University Beijing100048 China

ISBN: (纸本)157735897X

Early detection of fake news is crucial to mitigate its negative impact. Current research in fake news detection often utilizes the difference between real and fake news regarding the support degree from reliable sources. However, it has overlooked their different semantic outlier degrees among unreliable source information during the same period. Since fake news often serves idea propaganda, unreliable sources usually publish a lot of information with the same propaganda idea during the same period, making it less likely to be a semantic outlier. To leverage this difference, we propose the Reliable-Unreliable Source Reference (RUSR) Fake News Early Detection Method. RUSR introduces the publication background for detected news, which consists of related news with common main objects of description and slightly earlier publication from both reliable and unreliable sources. Furthermore, we develop a strongly preference-driven support degree evaluation model and a two-hop semantic outlier degree evaluation model, which respectively mitigate the interference of news with weak validation effectiveness and the tightness degree of semantic cluster. The designed redistribution module and expanding range relative time encoding are adopted by both models, respectively optimizing early checkpoint of training and expressing the relevance of news implied by their release time gap. Finally, we present a multi-model mutual benefit and collaboration framework that enables the multi-model mutual benefit of generalization in training and multi-perspective prediction of news authenticity in inference. Experiments on our newly constructed dataset demonstrate the superiority of RUSR. Copyright © 2025, Association for the Advancement of artificial intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Temporal Dependency Modeling in Air Quality Index Prediction Using LSTM Networks 15th

Temporal Dependency Modeling in Air Quality Index Prediction...

引用

15th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2023 and 14th World Congress on Nature and Biologically Inspired Computing, NaBIC 2023

作者： Dash, Yajnaseni Abraham, Ajith Kumar, Naween Purohit, Gayatri Mittal, Arnav Bagla, Aarav School of Artificial Intelligence Bennett University UP Greater Noida India School of Computer Science Engineering and Technology Bennett University UP Greater Noida India School of Artificial Intelligence Sai University Chennai India

ISBN: (纸本)9783031810824

The Air Quality Index (AQI) forecasting is a very significant area of research as it has an impact on worldwide ecosystems and human health. The close monitoring of AQI is necessary to develop different mitigation strategies. The present study investigated the efficacy of different techniques such as Linear Regression, Support Vector Regression, Random Forest, Gradient Boosting, and Long Short-Term Memory (LSTM) networks to forecast AQI patterns. After modeling the historical AQI climate data it is found that LSTM models can accurately predict AQI as these models can capture temporal dependencies. As per this study, LSTM models can be used to make predictions and to support policies for tackling related issues of the dynamism of Climate science. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Classifier-Ensemble-Based Surrogate-Assisted Evolutionary Algorithm for Distributed data-Driven Optimization

引用

IEEE Transactions on Evolutionary Computation 2025年第3期29卷 711-725页

作者： Guo, Xiao-Qi Wei, Feng-Feng Zhang, Jun Chen, Wei-Neng South China University of Technology School of Computer Science and Engineering Guangzhou510006 China South China University of Technology State Key Laboratory of Subtropical Building of Big Data and Computational Intelligence Guangzhou510006 China Hanyang University ERICA School of Electrical and Engineering Ansan15588 Korea Republic of Nankai University College of Artificial Intelligence Tianjin300071 China

Surrogate-assisted evolutionary algorithms (SAEAs) have achieved effective performance in solving complex data-driven optimization problems. In the Internet of Things environment, the data of many problems are collected and processed in distributed network nodes and cannot be transmitted. As each local node can only access and build surrogate models based on partial data, local models are usually not accurate and even conflicting. To address these challenges, this article proposes a classifier-ensemble-based surrogate-assisted evolutionary algorithm (CESAEA) with the following features. First, the local nodes in CESAEA train classifiers as surrogate models based on their own data to classify candidates into several levels according to their fitness quality. The classifiers are less sensitive to the partial and biased data than regression models in local nodes. Second, the central node in CESAEA ensembles the local surrogates to form a global classifier with a relaxation condition to guide the evolutionary optimizer to generate promising candidates. The relaxation condition helps to overcome the problem of local model inconsistency. Overall, CESAEA is composed of local classifier construction, global classifier ensemble, classifier-assisted evolutionary optimization and local regression-assisted selection. As only classifiers are allowed to transmit from local nodes to the central node, the mapping relationship between decision vector and objective is hidden and thus data privacy is protected. The experimental results on benchmark functions as well as distributed feature selection problems verify the effectiveness of CESAEA compared to several state-of-the-art approaches. © 1997-2012 IEEE.

关键词： Linear programming

来源：评论

学校读者我要写书评

暂无评论

Enhancing Weather Forecast Accuracy Using Deep Learning Models 15th

Enhancing Weather Forecast Accuracy Using Deep Learning Mode...

引用

15th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2023 and 14th World Congress on Nature and Biologically Inspired Computing, NaBIC 2023

作者： Kumar, Naween Dash, Yajnaseni Abraham, Ajith Ahmad, Shaik Irfan Saifullah, Shaik School of Computer Science Engineering and Technology Bennett University UP Greater Noida India School of Artificial Intelligence Bennett University UP Greater Noida India School of Artificial Intelligence Sai University Chennai India

ISBN: (纸本)9783031810824

The weather has a significant impact on a wide range of businesses and daily activities, including transportation, agriculture, and disaster relief. Planning for risk mitigation, allocating resources, and making every decision depends on accurate and precise weather pattern forecasts. In recent years, deep learning algorithms have become effective tools in improving the accuracy of weather forecasting. The model uses neural networks to uncover complex patterns from weather data. This study presents the use of deep learning models to predict climate change. This article highlights the shortcomings of traditional methods and the benefits of using deep learning, laying the foundation for our study of how deep learning can improve the accuracy of weather forecasting. Recurrent neural networks (RNN) and Convolutional neural networks (CNN) were used to predict weather patterns. The results indicate that RNN produces accurate results. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

DCA-Net: data-Driven Collaborative Assistance Network for Semi-supervised Medical Segmentation

DCA-Net: Data-Driven Collaborative Assistance Network for Se...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Chen, Yuhan Wang, Chunshi Zhao, Bin Guilin University of Electronic Technology School of Computer Science and Information Security China Guilin University of Electronic Technology School of Artificial Intelligence China

ISBN: (纸本)9798350386226

In this paper, we focus on the empirical alignment challenge between labeled and unlabeled data in semi-supervised medical image segmentation. When labeled and unlabeled data are poorly aligned, the network struggles to fully leverage knowledge from the labeled data. To address this, we propose an efficient and streamlined approach called "DCA-Net,"which integrates a frequency-domain data augmentation module Style Transfer Module (STM) and Bidirectional Copy-Paste (BCP) to effectively reduce the distribution gap between labeled and unlabeled data. Additionally, we combine knowledge distillation with semi-supervised learning to encourage deeper feature learning and more stable model behavior. Experiments with DCA-Net on the LA and ACDC datasets achieve state-of-the-art (SOTA) results. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Improving Stock Index Prediction Based on Financial Sentiment Analysis and Time Series Models 8

Improving Stock Index Prediction Based on Financial Sentimen...

引用

8th International Conference on Communications and Future Internet, ICCFI 2024

作者： Yang, Licheng Liu, Yinhong Li, Zeming Qi, Boyuan Feng, Jingyi School of Artificial Intelligence Nanjing University Nanjing China School of Intelligence Science and Technology Nanjing University Suzhou China Xuteli School Beijing Institute of Technology Beijing China Computer School Beijing Information Science and Technology University Beijing China

ISBN: (纸本)9798350389050

Stock market prediction remains one of the most challenging tasks due to the complex interactions of multiple factors. In this study, we propose a novel stock index prediction method based on financial sentiment analysis and multivariate time series models, to maximize the use of prior information in stock market for better predictive performance. Specifically, a CoEmoBERT model is proposed to achieve better sentiment classification accuracy and f1-score of stock-related tweets on StockEmotions dataset than single language model. Through vector concatenation, we then combine historical stock market index(S&P 500) data from Yahoo Finance with the sentiment labels and comment texts into a series of vectors as model inputs. Finally, leveraging long short-term memory (LSTM) networks, we achieve stock market index predictions with a mean squared error (MSE) of 0.80 ×10-3. This represents a 3.62% improvement in performance over similar index predictions conducted using the StockE motions dataset. Our data and codes are available at https://***/yhliu04/CoEmoBERT_OneHotLSTM © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Cloud-Enhanced Machine Learning: Exploring the Synergy for Intelligent Automation and Optimization 15th

Cloud-Enhanced Machine Learning: Exploring the Synergy for I...

引用

15th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2023 and 14th World Congress on Nature and Biologically Inspired Computing, NaBIC 2023

作者： Kumar, Naween Dash, Yajnaseni Abraham, Ajith Choudhary, Rakesh Kumar Pandey, Shriyansh School of Computer Science Engineering and Technology Bennett University UP Greater Noida India School of Artificial Intelligence Bennett University UP Greater Noida India School of Artificial Intelligence Sai University Chennai India

ISBN: (纸本)9783031810855

The convergence of cloud computing and machine learning (ML) is evolving in the new era of technological innovation. This paper elaborates on the symbiotic relationship between these two fields, highlighting how cloud infrastructure enables scalable, flexible, and cost-efficient ML development and deployment. At the same time, ML enhances cloud services through intelligent automation, optimization, and data-driven insights. This study of synergy presents transformative and revolutionizing opportunities in the industry and opens doors to evolved ML models with the help of cloud environments. Additionally, the paper mentions best practices, challenges, and future trends in integrating ML and cloud technologies, providing a comprehensive guide for students, professionals, and researchers. Also, the pre-existing research on the subject has been reviewed thoroughly and summarized, making this study a guide for researchers. Through performance analyses, we illustrate the practical benefits and certain pitfalls of this integration, highlighting valuable insights for leveraging the full potential of ML and cloud synergy. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Intelligent computing

来源：评论

学校读者我要写书评

暂无评论

A Domain Generalization and Residual Network-Based Emotion Recognition from Physiological Signals

引用

Cyborg and Bionic Systems 2024年第1期5卷 709-720页

作者： Junnan Li Jiang Li Xiaoping Wang Xin Zhan Zhigang Zeng School of Artificial Intelligence and Automation Huazhong University of Science and TechnologyWuhan 430074China Hubei Key Laboratory of Brain-inspired Intelligent Systems Huazhong University of Science and TechnologyWuhan 430074China Key Laboratory of Image Processing and Intelligent Control(Huazhong University of Science and Technology) Ministry of EducationWuhan 430074China Institute of Artificial Intelligence Huazhong University of Science and TechnologyWuhan 430074China

Emotion recognition from physiological signals(ERPS)has drawn tremendous attention and can be potentially applied to numerous *** physiological signals are nonstationary time series with high sampling frequency,it is challenging to directly extract features from ***,there are 2 major challenges in ERPS:(a)how to adequately capture the correlations between physiological signals at different times and between different types of physiological signals and(b)how to effectively minimize the negative effect caused by temporal covariate shift(TCS).To tackle these problems,we propose a domain generalization and residual network-based approach for emotion recognition from physiological signals(DGR-ERPS).We first pre-extract time-and frequency-domain features from the original time series to compose a new time ***,in order to fully extract the correlation information of different physiological signals,these time series are converted into 3D image data to serve as input for a residual-based feature encoder(RBFE).In addition,we introduce a domain generalization-based technique to mitigate the issue posed by *** have conducted extensive experiments on 2 real-world datasets,and the results indicate that our DGR-ERPS achieves superior performance under both TCS and non-TCS scenarios.

关键词： physiological signals effectively minimize n capture correlations domain generalization residual network emotion recognition extract features emotion recognition physiological signals erps

来源：评论

学校读者我要写书评

暂无评论

M3 Bench: Benchmarking Whole-Body Motion Generation for Mobile Manipulation in 3D Scenes

引用

IEEE Robotics and Automation Letters 2025年第7期10卷 7286-7293页

作者： Zhang, Zeyu Yan, Sixu Han, Muzhi Wang, Zaijin Wang, Xinggang Zhu, Song-Chun Liu, Hangxin State Key Laboratory of General Artificial Intelligence Beijing100080 China Huazhong University of Science and Technology School of Electronic Information and Communications Wuhan430079 China Statistics Department Los AngelesCA90095 United States Peking University School of Artificial Intelligence Institute for Artificial Intelligence Beijing100871 China

We propose M3 Bench, a new benchmark for whole-body motion generation in mobile manipulation tasks. Given a 3D scene context, M3 Bench requires an embodied agent to reason about its configuration, environmental constraints, and task objectives to generate coordinated whole-body motion trajectories for object rearrangement. M3 Bench features 30,000 object rearrangement tasks across 119 diverse scenes, providing expert demonstrations generated by our newly developed M3 BenchMaker, an automatic data generation tool that produces whole-body motion trajectories from high-level task instructions using only basic scene and robot information. Our benchmark includes various task splits to evaluate generalization across different dimensions and leverages realistic physics simulation for trajectory assessment. Extensive evaluation analysis reveals that state-of-the-art models struggle with coordinating base-arm motion while adhering to environmental and task-specific constraints, underscoring the need for new models to bridge this gap. By releasing M3 Bench and M3 BenchMaker at https://***/papers/m3bench, we aim to advance robotics research toward more adaptive and capable mobile manipulation in diverse, real-world environments. © 2016 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：