检索结果-内蒙古大学图书馆

A General Framework for Clustering and Distribution Matching with Bandit Feedback

IEEE Transactions on Information Theory 2025年第3期71卷 2116-2139页

作者： Yavas, Recep Can Huang, Yuqi Tan, Vincent Y. F. Scarlett, Jonathan CNRS@CREATE DesCartes Program CREATE Tower 138602 Singapore National University of Singapore Department of Computer Science Queenstown119077 Singapore National University of Singapore School of Computing Department of Information Systems and Analytics Queenstown119077 Singapore National University of Singapore Department of Mathematics Department of Electrical and Computer Engineering Queenstown119077 Singapore Institute of Data Science National University of Singapore Department of Computer Science The Department of Mathematics Queenstown119077 Singapore

We develop a general framework for clustering and distribution matching problems with bandit feedback. We consider a K-armed bandit model where some subset of K arms is partitioned into M groups. Within each group, the random variable associated to each arm follows the same distribution on a finite alphabet. At each time step, the decision maker pulls an arm and observes its outcome from the random variable associated to that arm. Subsequent arm pulls depend on the history of arm pulls and their outcomes. The decision maker has no knowledge of the distributions of the arms or the underlying partitions. The task is to devise an online algorithm to learn the underlying partition of arms with the least number of arm pulls on average and with an error probability not exceeding a pre-determined value δ. Several existing problems fall under our general framework, including finding M pairs of arms, odd arm identification, and N-ary clustering of K arms belong to our general framework. We derive a non-asymptotic lower bound on the average number of arm pulls for any online algorithm with an error probability not exceeding δ. Furthermore, we develop a computationally-efficient online algorithm based on the Track-and-Stop method and Frank-Wolfe algorithm, and show that the average number of arm pulls of our algorithm asymptotically matches that of the lower bound. Our refined analysis also uncovers a novel bound on the speed at which the average number of arm pulls of our algorithm converges to the fundamental limit as δ vanishes. © 1963-2012 IEEE.

关键词： Random variables

来源：评论

学校读者我要写书评

暂无评论

Early Time Series Anomaly Prediction with Multi-Objective Optimization

引用

IEEE Transactions on Emerging Topics in Computational Intelligence 2025年第1期9卷 972-987页

作者： Chao, Ting-En Huang, Yu Dai, Hao Yen, Gary G. Tseng, Vincent S. National Yang Ming Chiao Tung University Institute of Information Management Hsinchu300093 Taiwan Oklahoma State University Department of Electrical and Computer Engineering StillwaterOK74078 United States National Yang Ming Chiao Tung University Department of Computer Science Hsinchu300093 Taiwan National Chung Hsing University Department of Management Information Systems Taichung402 Taiwan

Anomaly prediction, aiming to predict abnormal events before occurrence, plays a key role in significantly reducing costs and minimizing potential threats to mechanical devices. Monitoring machines using fixed-length time windows faces challenges in accommodating the varying characteristics of anomaly events. The lengthy and imbalanced sequence data associated with anomaly events further complicates the resolution of these challenges. Additionally, the inherent trade-off between accurate prediction and timely alarm is a crucial concern, posing difficulties in decision-making. This study puts forward a novel framework for early anomaly prediction, named early time series Anomaly Prediction with Neighbor Over-sampling and Multi-objective Optimization (APNOMO), pronounced as 'abnormal'. The framework employs three key techniques: 1) sliding windows that divide long input sequences into segments for prediction at proper intervals, 2) over-sampling and proposed neighbor over-sampling that handle imbalanced data in a novel way, and 3) multi-objective optimization that searches optimal thresholds to balance accurately prediction and timely alarm the abnormal. Experiments on a real-world dataset demonstrate APNOMO's superior performance over some state-of-the-art designs, with higher recall, F1 score, and more suitable earliness. It can predict anomalies 0.78-3.56 hours in advance, showcasing excellent early anomaly prediction capabilities for enabling predictive maintenance. © 2017 IEEE.

关键词： Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

Research on Tumor Images Segmentation based on Improved Convolutional Neural Network 24

Research on Tumor Images Segmentation based on Improved Conv...

引用

5th International Symposium on Artificial Intelligence for Medicine Science, ISAIMS 2024

作者： Wan, Yajie Diao, Su Jiang, Gaozhe Song, Chaoda Department of Computer Science Brown University ProvidenceRI United States Department of Industrial & Systems Engineering Auburn University AuburnAL United States Institute of Operations Research and Analytics National University of Singapore Singapore Singapore School of Engineering Department of Computer and Data Sciences ClevelandOH United States

ISBN: (纸本)9798400717826

Tumors are one of the most common tumors in humans, and the main treatment at present is surgical removal. Preoperative planning of tumors usually requires a professional doctor to manually segment the images, but this process is limited by the doctor’s technical experience, which is time-consuming and labor-intensive. In addition, segmentation is extremely difficult due to the complexity and morphological diversity of tumor lesions. We propose a tumor image segmentation method based on improved Convolutional Neural Network (CNN). The model enhances the feature extraction ability by introducing a deep separable convolutional layer and batch normalization, while using dilated convolution to increase the receptive field, thereby improving the accuracy of segmentation. We also incorporated attention mechanisms into the model to focus more accurately on the tumor area and further optimize the segmentation effect. In order to verify the effectiveness of the model, we conducted experimental analysis on multiple publicly available medical imaging datasets. Experimental results show that the improved convolutional neural network significantly improves the accuracy and efficiency of segmentation compared with traditional methods in tumor image segmentation tasks. © 2024 Copyright held by the owner/author(s).

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Laser Scribed CNTs/PEEK/TPU Composites Film for High-Performance Stretchable Electrodes

引用

IEEE Sensors Journal 2025年第10期25卷 16666-16674页

作者： Jiang, Caiyun Tang, Lei Hou, Jian Ding, Guqiao Sheng, Bin University of Shanghai for Science and Technology College of Optical-Electrical and Computer Engineering Shanghai200093 China Shanghai Key Laboratory of Modern Optical Systems Engineering Research Center of Optical Instrument and System Shanghai200093 China Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences State Key Laboratory of Materials for Integrated Circuits Shanghai200050 China

In this article, an elastic composite material comprising carbon nanotubes (CNTs), polyether-ether-ketone (PEEK), and thermoplastic polyurethane (TPU) is presented, in which direct laser-induced graphitization was used to fabricate high-performance stretchable electrodes. The introduction of CNTs can enhance the conductivity and mechanical strength of the composites, thus improving the overall performance of the sensors. Flexible strain sensors with porous structures were prepared by appropriate encapsulation methods, which exhibited superior gauge factors (GFs) of 72, 367, and 972 in the 0%–30%, 30%–44%, and 44%–53% strain regions, respectively. Furthermore, it features a rapid response time (100 ms), excellent stability and durability, and is capable of detecting both large-scale human movement and monitoring of small physical signals. In addition, patterned laser-induced graphene interdigital electrodes (LIG-IDEs) were fabricated on composites using laser light. Highly sensitive humidity sensors were obtained using graphene oxide as the humidity-sensing material for respiratory monitoring and noncontact sensing. The thermoplastic properties of TPU allow the straight fiber to be thermoformed into highly stretchable helical electrode, which was of a helix index of 5 and with a high-quality factor (Q = 130) at 1250% strain. In conclusion, the preparation of LIG on stretchable composite films by direct laser scribing shows a promising approach for large-scale fabrication of wearable devices. © 2001-2012 IEEE.

关键词： Humidity sensors

来源：评论

学校读者我要写书评

暂无评论

Study of orography–MJO interaction and its impact on rainfall variability in West Sumatra

引用

Journal of Earth System Science 2025年第2期134卷 1-27页

作者： Satiadi, Didi Purwaningsih, Anis Harjupa, Wendi Saufina, Elfira Fathrio, Ibnu Trismidianto Rahmatia, Fahmi Pratama, Ridho Hashiguchi, Hiroyuki Shimomai, Toyoshi Research Center for Climate and Atmosphere National Research and Innovation Agency (BRIN) Bandung Indonesia Department of Computer Engineering School of Electrical Engineering Telkom University Bandung Indonesia Disaster Prevention Research Institute Kyoto University Kyoto Japan Research Institute for Sustainable Humanosphere Kyoto University Kyoto Japan Department of Electronic and Control Systems Engineering Shimane University Shimane Japan

Abstract: This study examines the impact of orography and the Madden–Julian Oscillation (MJO) on rainfall patterns in West Sumatra, Indonesia, using ERA5 reanalysis data. We analyzed variables such as precipitation, zonal and vertical winds, vertically integrated moisture convergence (VIMC), Froude number, lifting condensation level (LCL), level of free convection (LFC), level of non-buoyancy (LNB), convective available potential energy (CAPE), and convective inhibition (CINH), focusing on MJO phases 3 (MJO-3) and 4 (MJO-4). The ERA5 data was validated with observations from the Agam Observation Station, including data from the equatorial atmosphere radar, X-band Doppler Radar, optical rain gauge, microwave radiometer, and radiosonde. Our analysis, covering 22 years (2001–2022) of hourly data from five locations at varying elevations, reveals that topography significantly influences rainfall distribution, with windward slopes and mountain peaks receiving the most rainfall. This pattern closely aligns with VIMC, indicating that moisture convergence is a key driver of rainfall variability. MJO-3 significantly enhances rainfall by reducing zonal wind speeds, thereby increasing moisture convergence, while MJO-4 has a minimal impact, with increased zonal wind speeds limiting moisture convergence. The study concludes that VIMC patterns, influenced by wind dynamics, are central to understanding rainfall variability in West Sumatra’s mountainous terrain under different MJO phases. Research highlights: Orography strongly influences rainfall in West Sumatra, with the most precipitation on windward slopes and peaks, linked to vertically integrated moisture convergence (VIMC). MJO-3 boosts rainfall by reducing zonal wind speeds, which enhances moisture convergence and emphasizes wind dynamics in rainfall variability. MJO-4 has minimal impact on rainfall, as increased zonal winds restrict moisture convergence, leading to slight changes in precipitation. VIMC is crucial for under

关键词： MJO Orography rainfall topography West Sumatra

来源：评论

学校读者我要写书评

暂无评论

An improved and decentralized/distributed healthcare framework for disabled people through AI models

引用

Alexandria engineering Journal 2025年 125卷 441-448页

作者： Rathee, Geetanjali Garg, Sahil Kaddoum, Georges Alzanin, Samah M. Hassan, Mohammad Mehedi Department of Computer Science and Engineering Netaji Subhas University of Technology Dwarka Sector-3 New Delhi110078 India Electrical Engineering Department École de technologie supérieure MontréalQC H3C 1K3 Canada Centre for Research Impact & Outcome Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura140401 India Department of Computer Science College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz University Al-Kharj11942 Saudi Arabia Department of Information Systems College of Computer and Information Sciences King Saud University Riyadh11543 Saudi Arabia King Salman Center for Disability Research Riyadh11614 Saudi Arabia

Access to adequate healthcare is critical for everyone, but people with disabilities often face considerable challenges in receiving reliable and timely medical treatment. The Vision 2030 plan in Saudi Arabia intends to change the healthcare system by incorporating new technologies that increase accessibility, efficiency, and service delivery. However, current healthcare systems continue to suffer from delays, inefficient data processing, and accessibility concerns, especially for the visually impaired. This study proposes a more decentralized healthcare system that uses artificial intelligence (AI) and machine learning (ML) models to improve healthcare services for individuals with disabilities. The system achieves real-time data processing, reduces latency, and enhances decision-making accuracy by combining federated learning and zero-shot architectures. Furthermore, smart technologies such as the Internet of Things (IoT) and natural language processing (NLP) provide seamless data collection and analysis, allowing healthcare practitioners to provide prompt and personalized treatment. The suggested solution solves crucial issues such as inefficiencies in data processing, delays in obtaining medical information, and limits in current healthcare processes. This platform improves impaired people's freedom and mobility by delivering remote healthcare solutions using AI-powered diagnostics and real-time monitoring. This study contributes to a more inclusive and efficient healthcare system in Saudi Arabia by bridging the gap between technology and accessibility, which aligns with the Vision 2030 objective of providing fair healthcare services to everyone. © 2025 The Authors

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Ultimate Boundedness and Output Convergence of Prioritized Output Tracking Control Under Nonsmooth and Imperfect Feedback Linearization

引用

IEEE Transactions on Automatic Control 2025年

作者： An, Sang-Ik Lee, Dongheui Park, Gyunghoon University of Seoul School of Electrical and Computer Engineering Korea Republic of Tu Wien Autonomous Systems at Institute of Computer Technology Faculty of Electrical Engineering and Information Technology Austria Institute of Robotics and Mechatronics Germany

The concept of priority has been introduced to the robotic systems in 1980 s as an effort to overcome problems caused by singularity and it has attracted considerable attention from both the robotics and control societies. However, none of the previous works have successfully addressed two fundamental degenerate properties of singularity: nonsmoothness and imperfect inversion. This technical note proposes a prioritized output tracking control method that guarantees the ultimate boundedness and the convergence of higher priority outputs when the input-output feedback linearization becomes nonsmooth and imperfect by singularity. For that purpose, we firstly prioritize the input-output feedback linearization and discuss how two degenerate properties can occur when the system becomes singular. Then, we introduce the differential inclusion to deal with the nonsmooth internal dynamics and establish a condition using the upper Dini derivative for asymptotically stable zero dynamics. Also, we propose a strictly positive realness-based feedback gain design and find a condition related to an M-matrix in order to handle nonlinearities that appear in the imperfect feedback linearization. Finally, we combine these two results and show the ultimate boundedness and the output convergence. Additionally, we provide a motivational example with a planar four-link manipulator to illustrate the effectiveness and limitations of the proposed method. © 1963-2012 IEEE.

关键词： Feedback linearization

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Blockchain Framework for Secure, Scalable, and Energy-Efficient Digital Identity Management with Token-based Selective Disclosure 3

A Hybrid Blockchain Framework for Secure, Scalable, and Ener...

引用

3rd International Conference on Electronics and Renewable systems, ICEARS 2025

作者： Velmurugan, M. Shinzeer, C.K. Maya, G. Ramya, R. Kanimozhi, R. Lathif, Syed Ismail Abdul Vel Tech Rangarajan Dr Sagunthala R&d Institute of Science And Technology Department Of Computer Science & Engineering Chennai600 062 India Lovely Professional University Department of School of Computer Applications Punjab Phagwara144411 India Srm Institute of Science and Technology Faculty of Management Kattankulathur603 203 India K.Ramakrishnan College of Engineering Department of Electronics and Communication Engineering Samayapuram621112 India Muthayammal Engineering College Computer Science and Engineering Rasipuram637408 India Srm Institute of Science and Technology Department of Data Science and Business Systems Chennai603203 India

ISBN: (纸本)9798331509675

Data breaches, identity theft, and the lack of user control within traditional digital identity management systems, it begs a more secure and decentralized alternative. In this study we propose a blockchain based digital identity management framework that implements privacy, security and transparency by employing distributed ledger technology. To provide tamper proof identity storage and automated verification, the proposed model uses cryptographic hashing and smart contracts. The use of a novel token-based access mechanism enables users to safely share their identity data with third parties, while keeping sensitive information out of sight. Security metrics are enhanced by 30% for data integrity with 45% reduction in unauthorized access attempts all through simulations. The framework also achieves improved efficiency reducing identity verification time by 40 percent compared to traditional systems. It offers a promising approach to address important vulnerabilities in centralized identity management in line with the development of marketable and user-friendly digital identity solutions. © 2025 IEEE.

关键词： Data integrity

来源：评论

学校读者我要写书评

暂无评论

Time-Series RF-EMF Predictions for Exposure Assessments Using Machine Learning Techniques

Time-Series RF-EMF Predictions for Exposure Assessments Usin...

引用

European Conference on Antennas and Propagation, EuCAP

作者： Nektarios Moraitis Konstantina S. Nikita School of Electrical and Computer Engineering National Technical University of Athens and Institute of Communication and Computer Systems Athens Greece

ISBN: (数字)9788831299107

ISBN: (纸本)9798350366327

This paper performs time-series forecasts for radio-frequency electromagnetic field (RF-EMF) exposure assessments, leveraging machine learning (ML) methods. More specifically, a deep bidirectional long short-term memory (BiLSTM) network is proposed, which is trained and tested on long-term electric field time-series data collected by a monitoring station at frequencies between 100 kHz and 7 GHz. The adopted ML network performs very well during the testing phase delivering quite accurate time-series forecasts for unknown inputs. Finally, future electric field sequences are forecasted where the encountered electric field periodic patterns, which are correlated with the daily life, remain consistent.

关键词： Radio frequency Time-frequency analysis Accuracy Bidirectional long short term memory Europe Machine learning Predictive models Electric fields Monitoring Testing

来源：评论

学校读者我要写书评

暂无评论

Indoor Corridor Channel Measurements and Characterization in the Upper Mid-Band

Indoor Corridor Channel Measurements and Characterization in...

引用

European Conference on Antennas and Propagation, EuCAP

作者： Nektarios Moraitis Alexandros Rogaris Ileana Popescu Konstantina S. Nikita School of Electrical and Computer Engineering National Technical University of Athens and Institute of Communication and Computer Systems Athens Greece

ISBN: (数字)9788831299107

ISBN: (纸本)9798350366327

This paper presents a preliminary characterization of the indoor channel in the upper mid-band. Narrowband measurements are launched in corridors taking into consideration line-of-sight (LOS) and non-line-of-sight (NLOS) propagation scenarios at diverse frequencies between 7 and 20 GHz. The path loss, the shadow fading, and the K-factor properties of the channel are measured and assessed. According to the results, the measured path loss can be accurately forecasted by the Close-In (CI) empirical model. Simple linear relationships are delivered, tailored to characterize the path loss exponent, the shadow fading and the K-factor variation versus frequency. The latter parameter degrades linearly versus frequency exhibiting negative values in NLOS scenarios and at frequencies above 8 GHz.

关键词： Measurement uncertainty Line-of-sight propagation Europe Rayleigh channels Predictive models Antennas and propagation Loss measurement Frequency diversity Frequency measurement Narrowband

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：