检索结果-内蒙古大学图书馆

High-Resolution NLP for Social Healthcare Networks: Text Classification through Integration of Causal Dilated Cosine Architecture Optimized by Weighted Leadership Navigator for Advanced Insights

High-Resolution NLP for Social Healthcare Networks: Text Cla...

引用

International Conference on ICT in Business Industry & Government (ICTBIG)

作者： K Karpagavadivu Senthilkumar Sakthivel M. Ramya Seeniappan Kaliappan R Maranan Nitheesh S Artificial Intelligence and Data Science Dr. N.G.P Institute of Technology Coimbatore Senior AI Cloud Architect Entergy Woodland Prairie Ln Conroe Texas Division of Research and Development Lovely Professional University Phagwara Punjab India Department of Mechanical Engineering KCG College of Technology Karapakkam Chennai Tamil Nadu India Department of Research and Innovation Saveetha School of Engineering SIMATS Chennai Tamil Nadu India Department of Mechatronics Engineering KCG College of Technology Karapakkam Chennai Tamil Nadu India

ISBN: (数字)9798331518981

ISBN: (纸本)9798331518998

The advancement in information technology has been on the increase in the recent past with the expansion of text data dissemination in the form of news, medical reports, product reviews, and social media posts among others, the increase in text data has made text mining and classification mandatory. In the last decade a lot of attempts have been undertaken to solve the text classification problems employing machine learning and deep learning approaches both supervised and unsupervised. In this context, our research proposes High-Resolution NLP for Social Healthcare Networks (HiN-TC), a state-of-the-art text classification approach. In our research, data cleaning and normalization are done using Min-Max with Zero-Mean Rescaling Normalization, feature selection is done using Echelon Adaptive Poplar Algorithm, and feature extraction is done using Bi-Consolidation Transformer that captures key patterns in the text. It is supposed to classify the data with good accuracy using Causal Dilated Cosine Architecture and we have optimized it using Precision-Weighted Leadership Navigator for improved performance. This framework is applied to the COVID-19 vaccination Twitter dataset to help get more superior understanding of social healthcare trends. Our methodology demonstrates significant performance improvements, achieving a 98.5% increase in classification accuracy, a 96.3% reduction in text processing time, and a 97.1% boost in scalability. These outcomes suggest the capability of the HiN-TC to deliver a more profound understanding of the social healthcare networks and suggest that the presented framework can be effective for the enhancement of the efficiency and accuracy in the computationally extensive range of the NLP methods and applications for the analysis of the large-scale unstructured text data in healthcare.

关键词： COVID-19 Leadership Accuracy Social networking (online) Navigation Text categorization Blogs Computer architecture Feature extraction Vaccines

来源：评论

学校读者我要写书评

暂无评论

Normal Vector Direction-based 3D LiDAR Point Cloud Planar Surface Removal for Object Cluster Minimization in Human Activity Monitoring System

Normal Vector Direction-based 3D LiDAR Point Cloud Planar Su...

引用

IEEE Instrumentation and Measurement technology Conference

作者： Nova Eka Budiyanta Eko Mulyanto Yuniarno Tsuyoshi Usagawa Mauridhi Hery Purnomo Dept. of Electrical Engineering Faculty of Intelligent Electrical and Informatics Technology (F-Electics) Institut Teknologi Sepuluh Nopember Surabaya Indonesia Dept. of Electrical Engineering Dept. of Computer Engineering Faculty of Intelligent Electrical and Informatics Technology (F-Electics) Institut Teknologi Sepuluh Nopember Surabaya Indonesia Department of Computer Science and Electrical Engineering Graduate School of Science and Technology Kumamoto University Kumamoto Japan Dept. of Electrical Engineering Dept. of Computer Engineering Faculty of Intelligent Electrical and Informatics Technology (F-Electics) Institut Teknologi Sepuluh Nopember University Center of Excellence on Artificial Intelligence for Healthcare and Society (UCE AIHeS) Surabaya Indonesia

The use of 3-Dimensional Light Detection and Ranging (3D LiDAR) point cloud as the alternative data to reduce privacy exposure in monitoring systems has been carried out in several studies. Unfortunately, various challenges in using point clouds intersect with the amount of data and computational costs. Several studies attempted to optimize the point cloud processing approach by segmenting the ground plane to get the object clusters separated. However, many unnecessary points can still burden the computation process. Since the ground plane mainly represents the horizontal planar plane on the x, y axis, this study tried to reduce the points on the vertical planar plane on the x, z and y, z axes with the x, y horizontal planar plane as well based on the surface normal vector direction of each point. The proposed approach has successfully reduced the raw point cloud by 79.29% removing the point cloud that indicates the planar surface of the three axes while maintaining the essential object of the monitoring system on the KITTI raw dataset. Therefore, the object cluster can be minimized, supporting the computational costs for further research in human activity monitoring systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Predicting the Availability of Supply Equipment at EV Charging Stations

Predicting the Availability of Supply Equipment at EV Chargi...

引用

IEEE Conference on Energy Internet and Energy System Integration (EI2)

作者： Chenxi Sun Haochen Sun Youwei Jia Xiaoying Tang Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China School of Science and Engineering The Chinese University of Hong Kong (Shenzhen) Shenzhen China School of Data Science The Chinese University of Hong Kong (Shenzhen) Shenzhen China Department of Electrical and Electronic Engineering Southern University of Science and Technology Shenzhen China

Understanding and characterizing Electric Vehicle (EV) users’ behavior at EV charging stations is beneficial for improving the operation efficiency of EV charging stations through smart scheduling. Recently, the fast development of EV charging infrastructure worldwide and the release of collected real EV charging dataset make it possible to learn from actual observations in practice. In this paper, we investigate the possibility of predicting the usage of electric vehicle supply equipment at EV charging stations using historical user data and weather data. We formulate the prediction problem as a time-series prediction problem. We evaluate and compare the performance of two popular neural network models against traditional methods for predicting the usage of Electric Vehicle Supply Equipment (EVSE) at charging stations using historical data. Experiments show that for workplace charging sites, these neural network models outperform baseline methods and are capable to predict the vacancies of EVSE with high accuracy.

关键词： Neural networks Memory management Employment Weather forecasting System integration Predictive models Charging stations

来源：评论

学校读者我要写书评

暂无评论

SIBW: A Swarm intelligence-Based Network Flow Watermarking Approach for Privacy Leakage Detection in Digital Healthcare Systems

引用

IEEE Journal of Biomedical and Health Informatics 2025年 PP卷 PP页

作者： Qiao, Sibo Guo, Qiang Shi, Fengdong Wang, Min Zhu, Haohao Khan, Fazlullah Rodrigues, Joel J.P.C. Lyu, Zhihan School of Software Tiangong University Tianjin300387 China School of Artificial Intelligence Tiangong University Tianjin300387 China National Demonstration Center for Experimental Engineering Training Education Tiangong University Tianjin300387 China School of Life Sciences Tiangong University Tianjin300387 China School of Control Sciences and Engineering Tiangong University Tianjin300387 China School of Computer Science Faculty of Science and Engineering University of Nottingham Ningbo China Zhejiang Ningbo315104 China Higher School of Technology Amazonas State University Amazonas Manaus69050-010 Brazil Department of Game Design Faculty of Arts Uppsala University Uppsala Sweden

The exponential growth of sensitive patient information and diagnostic records in digital healthcare systems has increased the complexity of data protection, while frequent medical data breaches severely compromise system security and reliability. Existing privacy protection techniques often lack robustness and real-time capabilities in high-noise, high-packet-loss, and dynamic network environments, limiting their effectiveness in detecting healthcare data leaks. To address these challenges, we propose a Swarm intelligence-Based Network Watermarking (SIBW) method for real-time privacy data leakage detection in digital healthcare systems. SIBW integrates fountain codes with outer error correction codes and employs a Multi-Phase Synergistic Swarm Optimization Algorithm (MPSSOA) to dynamically optimize encoding parameters, significantly enhancing the robustness and interference resistance of watermark detection. Additionally, a reliable synchronization sequence and lightweight embedding mechanism are designed to ensure adaptability to complex, dynamic networks. Experimental results demonstrate that SIBW achieves over 90% detection accuracy under high latency jitter and packet loss conditions, surpassing existing methods in both robustness and efficiency. With a compact design of only 3.7 MB, SIBW is particularly suited for rapid deployment in resource-constrained digital healthcare systems. © 2013 IEEE All rights reserved.

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

Demystifying the Role of Big data Analytics in IIoT-Based Connected Railways

Demystifying the Role of Big Data Analytics in IIoT-Based Co...

引用

Advancement in Electronics & Communication engineering (AECE), International Conference on

作者： Navya Gupta Bhawna Narwal Shivangi Batra Pooja Gera Pooja Bhati Department of Artificial Intelligence and Data Science Indira Gandhi Delhi Technical University for Women (IGDTUW) Delhi India Department of Information Technology Indira Gandhi Delhi Technical University for Women (IGDTUW) Delhi India Department of Mechanical and Automation Engineering Indira Gandhi Delhi Technical University for Women (IGDTUW) Delhi India

Recent advances in sensors, networks, and hardware/software platforms have facilitated the development of Industrial Internet of Things (IIoT) applications in railway transportation. Nevertheless, the limited coverage and battery life of IIoT devices remain significant hurdles in realizing realistic service implementations. Against this backdrop, this study aims to scrutinize the impact of Industry 4.0 and big data analytics on railway engineering, considering factors such as post-COVID requisites and the security and privacy of rail users. Additionally, the research investigates the application of these ideas in India, which presents a challenging environment, and examines potential avenues for future research.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cross-Store Next-Basket Recommendation

Cross-Store Next-Basket Recommendation

引用

IEEE International Conference on data Mining (ICDM)

作者： Liang-Chen Ma Ya Li Zi-Feng Mai Fei-Yao Liang Chang-Dong Wang Min Chen Mohsen Guizani School of Computer Science and Engineering Sun Yat-sen University Guangzhou China School of Electronics and Information Guangdong Polytechnic Normal University Guangzhou China Guangdong Provincial Key Laboratory of Intellectual Property and Big Data Guangzhou China School of Computer Science and Engineering South China University of Technology Guangzhou China Pazhou Laboratory Guangzhou China Machine Learning Department Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI) Abu Dhabi UAE

ISBN: (数字)9798331506681

ISBN: (纸本)9798331506698

Next-basket recommendation (NBR) infers a set of items that a user will interact with in the next basket. Existing methods often struggle with the data sparsity problem, particularly when the number of baskets is significantly large due to diverse user behaviors. Cross-domain recommendation (CDR) can effectively alleviate this problem in NBR by transferring knowledge across different domains. Nevertheless, these methods often rely on the similarities of overlapping users, which leads to the negative transfer problem and ignores the overlapping items that are general in real-world scenarios like chain stores. In this paper, we provide a clear symbolic definition of cross-store recommendation (CSR) and distinguish it from CDR. We also propose a novel CSNBR model for cross-store next-basket recommendation task. To fully model the transferable collaborative information between two stores, we learn the embeddings of users, baskets, and items by two intra-store bipartite graphs, and use an inter-store unified bipartite graph to transfer the previously learned knowledge. Furthermore, to alleviate the negative transfer problem, we propose to reconstruct the inter-store unified bipartite graph by utilizing user embeddings obtained from the transfer layer and the disentanglement layer. We also employ two sequence encoders to model the historical sequential information at basket-level and item-level. Extensive experiments conducted on real-world datasets demonstrate the effectiveness of the CSNBR model.

关键词： Neural networks Collaboration data models Bipartite graph data mining

来源：评论

学校读者我要写书评

暂无评论

Screening cognitive impairment in patients with atrial fibrillation: A deep learning model based on retinal fundus photographs

引用

Heart Rhythm O2 2025年第5期6卷 678-686页

作者： Wang, Zhen Li, Mingxiao Xia, Peng Jiang, Chao Shen, Ting Ma, Jiaming Bai, Yu Zhang, Suhui Lai, Yiwei Li, Sitong Xu, Hui Xu, Yang Ma, Tong Ju, Lie He, Liu Dong, Li Sang, Caihua Long, Deyong Chen, Yuzhong Du, Xin Ge, Zongyuan Dong, Jianzeng Wei, Wen-Bin Ma, Changsheng Department of Cardiology Beijing Anzhen Hospital Capital Medical University Beijing China Engineering Research Center of Medical Devices for Cardiovascular Diseases Ministry of Education Capital Medical University Beijing China National Clinical Research Center for Cardiovascular Diseases Beijing China Beijing Airdoc Technology Co. Ltd. Beijing China Department of Electrical and Computer Systems Engineering Faculty of Engineering Monash University Clayton Australia Yale School of Medicine New Haven Connecticut United States School of Clinical Medicine Peking Union Medical College and Chinese Academy of Medical Science Beijing China Beijing Tongren Eye Center Beijing Key Laboratory of Intraocular Tumor Diagnosis and Treatment Beijing Ophthalmology & Visual Sciences Key Lab Medical Artificial Intelligence Research and Verification Key Laboratory of the Ministry of Industry and Information Technology Beijing Tongren Hospital Capital Medical University Beijing China Monash e-Research Center Monash University Clayton Australia

Background: Patients with atrial fibrillation (AF) have a higher risk of cognitive impairment (CI). However, complexity of CI diagnosis and lack of simple screening approaches limited early screening and intervention of CI in AF patients. Objective: Our study aimed to develop deep learning models based on fundus photographs for easy screening of CI in AF patients. Methods: From May 2021 to April 2023, patients who completed fundus examination and cognitive function evaluation in the Chinese Atrial Fibrillation Registry Study were included. The training and validation sets were randomly split at an 8:2 ratio. Participants from the Beijing Eye Study served as the external validation set. Different deep learning models were trained, and their CI detection ability was validated. Results: A total of 899 patients in the Chinese Atrial Fibrillation Registry Study were included. In the validation set, the vision-ensemble model based on fundus images alone had an area under the receiver-operating characteristic curve (AUROC) of 0.855 (95% confidence interval 0.816–0.894) for CI screening. The multimodal model (AUROC 0.861, 95% confidence interval 0.823–0.898), based on fundus photographs and 4 clinical variables, performed comparably to the vision-ensemble model. The AUROC of the vision-ensemble model for CI screening achieved 0.773 (95% confidence interval 0.709–0.837) in the external test set. In the saliency map, the vision-ensemble model focused on areas around retinal vessels and the optic disc. Conclusion: A vision-ensemble model based on fundus images might be practical for preliminary screening of CI in AF patients. © 2025 Heart Rhythm Society

关键词： artificial intelligence Atrial fibrillation Cognitive impairment Deep learning Fundus photography

来源：评论

学校读者我要写书评

暂无评论

Short-Term Electric Load Forecasting Via State-State Approach with a Mixture of Long-Lag Vector Autoregressive Models

SSRN

引用

SSRN 2023年

作者： Jeong, Dongyeon Park, Chiwoo Ko, Young Myoung Samsung Electronics 56 Seongchon-gil Seocho-gu Seoul06765 Korea Republic of Department of Industrial and Management Engineering Pohang University of Science and Technology Gyeongbuk Pohang37673 Korea Republic of Open Innovation Big Data Center Pohang University of Science and Technology Gyeongbuk Pohang37673 Korea Republic of Graduate School of Artificial Intelligence Pohang University of Science and Technology Gyeongbuk Pohang37673 Korea Republic of Department of Industrial and Manufacturing Engineering Florida State University TallahasseeFL32306 United States

This paper proposes a novel day-ahead electric load forecasting model for buildings and regions. We explore the problem that the daily load curves of electric load data in buildings and regions have periodicity and follow some patterns. We use long-lag terms of historical load data to capture periodicity and clustering to figure out daily load curve patterns. We propose a forecast model called a state-space model with a mixture of long-lag vector autoregressive models (SSM-MLVAR), which combines a state-space model and long-lag vector autoregressive models into a single model. The proposed model ensures feasibility by reducing the number of parameters of the long-lag vector autoregressive model. The state-space model alleviates forecasting errors that cannot be fine-tuned with the vector autoregressive model. With electric load data from a building and 10 regions, we compare the proposed model with existing forecasting methods such as persistence, multiple-output support vector machine (M-SVM), cluster model (CM), logistic mixture vector autoregressive model (LMVAR), Bayesian mixture density network (BayMDN), and variational mode decomposition with multiple wavelet decomposition network (VMD-mWDN). It turns out that the proposed model achieves significantly higher prediction accuracy than these models on the datasets. © 2023, The Authors. All rights reserved.

关键词： Vector spaces

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Performance of Spatial and Frequency Domain Interpolation Techniques for Image Super-Resolution

Analyzing the Performance of Spatial and Frequency Domain In...

引用

International Conference on Computing and Networking technology (ICCNT)

作者： Lakshya Swarup P. Sharmila Kanika Seth Supriya Rai Suvarna R. Bhagwat G. Ravivarman Centre of Research Impact and Outcome Chitkara University Rajpura Punjab India Department of Science and Humanities Prince Shri Venkateshwara Padmavathy Engineering College Chennai India Chitkara Centre for Research and Development Chitkara University Himachal Pradesh India School of Mangement UG JAIN (Deemed to be University) Bangalore Karnataka India Department of Artificial Intelligence & Data Science Vishwakarma Institute of Information Technology Pune India Department of Electrical and Electronics Engineering Karpagam Academy of Higher Education Coimbatore India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

This paper examines the overall performance of two interpolation techniques, spatial and frequency area interpolation, for photo exquisite-decision. Those strategies are evaluated by evaluating the foundation mean squared distinction (RMSD) and top signal-to-noise ratio (PSNR). It’s miles proven that the frequency domain approach outperforms the spatial domain method in phrases of RMSD and PSNR metrics. The frequency area technique is characterized by using one-dimensional prediction clear-out and bicubic interpolation in the frequency domain. The spatial domain technique plays bicubic interpolation inside the spatial area with a view to up-sample the distorted photo. The experimentally carried out test photos are used to achieve the outcomes. The paper supplied reliability for the implementation of the frequency area technique in photograph brilliant-resolution applications.

关键词： Measurement Interpolation Accuracy Frequency-domain analysis Superresolution Reliability Spatial resolution Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Graph Dimension Attention Networks for Enterprise Credit Assessment

arXiv

引用

arXiv 2024年

作者： Wei, Shaopeng Egressy, Béni Chen, Xingyan Zhao, Yu Zhuang, Fuzhen Wattenhofer, Roger Kou, Gang School of Business Guangxi University China Information Technology and Electrical Engineering Department ETH Zürich Switzerland Fintech Innovation Center Financial Intelligence and Financial Engineering Key Laboratory of Sichuan Province Institute of Digital Economy and Interdisciplinary Science Innovation Southwestern University of Finance and Economics China Institute of Artificial Intelligence Beihang University Beijing China Zhongguancun Laboratory Beijing China School of Business Administration Faculty of Business Administration Southwestern University of Finance and Economics China

Enterprise credit assessment is critical for evaluating financial risk, and Graph Neural Networks (GNNs), with their advanced capability to model inter-entity relationships, are a natural tool to get a deeper understanding of these financial networks. However, existing GNN-based methodologies predominantly emphasize entity-level attention mechanisms for contagion risk aggregation, often overlooking the heterogeneous importance of different feature dimensions, thus falling short in adequately modeling credit risk levels. To address this issue, we propose a novel architecture named Graph Dimension Attention Network (GDAN), which incorporates a dimension-level attention mechanism to capture fine-grained risk-related characteristics. Furthermore, we explore the interpretability of the GNN-based method in financial scenarios and propose a simple but effective data-centric explainer for GDAN, called GDAN-DistShift. DistShift provides edge-level interpretability by quantifying distribution shifts during the message-passing process. Moreover, we collected a real-world, multi-source Enterprise Credit Assessment dataset (ECAD) and have made it accessible to the research community since high-quality datasets are lacking in this field. Extensive experiments conducted on ECAD demonstrate the effectiveness of our methods. In addition, we ran GDAN on the well-known datasets SMEsD and DBLP, also with excellent results. © 2024, CC BY.

关键词： Graph neural networks

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：