检索结果-内蒙古大学图书馆

Towards Non-Invasive Swallowing Assessment: An AI-Powered Interface for Swallowing Kinematic Analysis using High-Resolution Cervical Auscultation 46

Towards Non-Invasive Swallowing Assessment: An AI-Powered In...

引用

46th Annual International Conference of the IEEE engineering in Medicine and Biology Society, EMBC 2024

作者： Luo, Yuewen Anwar, Ayman Ren, Siyi Coyle, James L. Sejdic, Ervin University of Toronto Division of Engineering Science Faculty of Applied Science & Engineering TorontoON Canada University of Toronto Faculty of Applied Science & Engineering Department of Electrical and Computer Engineering TorontoON Canada University of Pittsburgh School of Health and Rehabilitation Sciences Department of Communication Science and Disorders PittsburghPA United States University of Toronto North York General Hospital Faculty of Applied Science & Engineering Department of Electrical and Computer Engineering TorontoON Canada

ISBN: (纸本)9798350371499

Swallowing is a pivotal physiological function for human sustenance and hydration. Dysfunctions, termed dysphagia, necessitate prompt and precise diagnosis. Videofluoroscopic swallowing studies (VFSS) remain the gold standard for swallowing assessment but pose accessibility and radiation exposure concerns. High-resolution cervical auscultation (HRCA) presents a non-invasive alternative with comparable accuracy. Yet, existing studies have only assessed HRCA in tandem with VFSS, without applying it to clinical settings. We propose an AI-enhanced PC software deploying HRCA for real-time bedside swallowing screening. This software proficiently detects abnormalities and precisely measures key kinematic events, including upper esophageal sphincter opening and laryngeal vestibule closure duration. The system was evaluated through two studies, encompassing a VFSS comparative analysis and a usability study. Our findings underscored the software's superior operational efficiency and diagnostic accuracy, positioning our HRCA-based system as a refined and pragmatic alternative for dysphagia assessment. © 2024 IEEE.

关键词： User centered design

来源：评论

学校读者我要写书评

暂无评论

Investigations and Time Estimation on Federated Learning for Future Internet of Vehicles

引用

IEEE Internet of Things Journal 2025年第11期12卷 17387-17398页

作者： Fukumoto, Shun Li, Ruidong Zeng, Kai Nan, Haihan Su, Zhou Kanazawa University Intelligent Computation and Network Laboratory Division of Electrical Information and Communication Engineering Kanazawa920-1192 Japan Kunming University of Science and Technology Faculty of Information Engineering Automation Kunming066000 China Kanazawa University Division of Electrical Information and Communication Engineering Kanazawa920-1192 Japan George Mason University Electrical and Computer Engineering Department FairfaxVA22030 United States Xi’an Jiaotong University School of Cyber Science and Engineering Xi’an710049 China

For future Internet of Vehicles (IoV), communications and computing will converge to provide services. Federated learning (FL), as one of the typical distributed computing technologies, needs to be integrated with IoV. For such integration, FL suffers from the straggler effect that the entire learning speed is lowered down, because of the existence of the devices, such as low-powered road side units and vehicles, taking more time to complete their tasks. Although the existing mechanisms reduce straggler effects by adopting asynchronous mechanisms and clustering mechanisms, they lack the detailed analysis of the reasons and the impacts of each cause, leading to inefficiencies in the design of algorithm. Additionally, most of the existing work only considered the impact of a single factor in computation, communication, or data distribution, which lacks comprehensive on research for causes of stragglers effects. The bottleneck is that it is laborious to observe the time delay precisely with the existing high-calculating evaluations. In this article, we elaborately explore the effects of computing power, communication capability, and data distributions on the straggler effects with carefully designing and conducting the extensive experiments. After investigations, we propose a novel learning completion time estimation formula for low computing capability devices with mini-batch stochastic gradient decent (SGD). We compare our proposed estimation formula with the one based on floating operation per second (FLOPs). Through the evaluations, our formula can demonstrate the improvement up to 72.4% at docker and 32.4% at Raspberry Pi device compared to the existing work. © 2014 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Interference Suppression and Jitter Elimination Ability-Based Adaption Tracking Guidance for Robotic Fishes

引用

IEEE/CAA Journal of Automatica Sinica 2025年第1期12卷 126-137页

作者： Dongfang Li Jie Huang Rob Law Xin Xu Limin Zhu Edmond Q.Wu IEEE the School of Electrical Engineering and Automation Fuzhou University the Key Laboratory of System Control and Information Processing Ministry of Education the School of Electrical Engineering and Automation Fuzhou University 5G+Industrial Internet Institute Fuzhou University the University of Macau the College of Mechatronics and Automation National University of Defense Technology the School of Mechanical Engineering Shanghai Jiao Tong University the Department of Computer Science and Engineering Shanghai Jiao Tong University

This work presents an adaptive tracking guidance method for robotic fishes. The scheme enables robots to suppress external interference and eliminate motion jitter. An adaptive integral surge line-of-sight guidance rule is designed to eliminate dynamics interference and sideslip issues. Limited-time yaw and surge speed observers are reported to fit disturbance variables in the model. The approximation values can compensate for the system's control input and improve the robots' tracking ***, this work develops a terminal sliding mode controller and third-order differential processor to determine the rotational torque and reduce the robots' run jitter. Then, Lyapunov's theory proves the uniform ultimate boundedness of the proposed method. Simulation and physical experiments confirm that the technology improves the tracking error convergence speed and stability of robotic fishes.

关键词： Adaptive integral surge line-of-sight approximation robotic fish speed observer

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Integrated Method for Healthcare Data Classification with Incompleteness

引用

computers, Materials & Continua 2024年第11期81卷 3125-3145页

作者： Sonia Goel Meena Tushir Jyoti Arora Tripti Sharma Deepali Gupta Ali Nauman Ghulam Muhammad Electrical and Electronics Engineering(EEE)Department Maharaja Surajmal Institute of TechnologyNew-Delhi110058India Information Technology(IT)Department Maharaja Surajmal Institute of TechnologyNew-Delhi110058India Chitkara University Institute of Engineering and Technology Chitkara UniversityRajpuraPunjab140401India Department of Computer Science and Engineering Yeungnam UniversityGyeongsan-si38541Republic of Korea Department of Computer Engineering College of Computer and Information SciencesKing Saud UniversityRiyadh11421Saudi Arabia

In numerous real-world healthcare applications,handling incomplete medical data poses significant challenges for missing value imputation and subsequent clustering or classification *** approaches often rely on statistical methods for imputation,which may yield suboptimal results and be computationally *** paper aims to integrate imputation and clustering techniques to enhance the classification of incomplete medical data with improved *** classification methods are ill-suited for incomplete medical *** enhance efficiency without compromising accuracy,this paper introduces a novel approach that combines imputation and clustering for the classification of incomplete ***,the linear interpolation imputation method alongside an iterative Fuzzy c-means clustering method is applied and followed by a classification *** effectiveness of the proposed approach is evaluated using multiple performance metrics,including accuracy,precision,specificity,and *** encouraging results demonstrate that our proposed method surpasses classical approaches across various performance criteria.

关键词： Incomplete data nearest neighbor linear interpolation imputation clustering classification

来源：评论

学校读者我要写书评

暂无评论

HyperBrain: Anomaly Detection for Temporal Hypergraph Brain Networks 7th

HyperBrain: Anomaly Detection for Temporal Hypergraph Brain...

引用

7th International Workshop on Machine Learning in Clinical Neuroimaging, MLCN 2024, Held in Conjunction with 27th International Conference on Medical Image Computing and computer-Assisted Intervention, MICCAI 2024

作者： Sadeghian, Sadaf Li, Xiaoxiao Seltzer, Margo Department of Computer Science University of British Columbia Vancouver Canada Department of Electrical and Computer Engineering University of British Columbia Vancouver Canada Vector Institute Toronto Canada

ISBN: (纸本)9783031787607

Identifying unusual brain activity is a crucial task in neuroscience research, as it aids in the early detection of brain disorders. It is common to represent brain networks as graphs, and researchers have developed various graph-based machine learning methods for analyzing them. However, the majority of existing graph learning tools for the brain face a combination of the following three key limitations. First, they focus only on pairwise correlations between regions of the brain, limiting their ability to capture synchronized activity among larger groups of regions. Second, they model the brain network as a static network, overlooking the temporal changes in the brain. Third, most are designed only for classifying brain networks as healthy or disordered, lacking the ability to identify abnormal brain activity patterns linked to biomarkers associated with disorders. To address these issues, we present HyperBrain, an unsupervised anomaly detection framework for temporal hypergraph brain networks. HyperBrain models fMRI time series data as temporal hypergraphs capturing dynamic higher-order interactions. It then uses a novel customized temporal walk (BrainWalk) and neural encodings to detect abnormal co-activations among brain regions. We evaluate the performance of HyperBrain in both synthetic and real-world settings for Autism Spectrum Disorder and Attention Deficit Hyperactivity Disorder (ADHD). HyperBrain outperforms all other baselines on detecting abnormal co-activations in brain networks. Furthermore, results obtained from HyperBrain are consistent with clinical research on these brain disorders. Our findings suggest that learning temporal and higher-order connections in the brain provides a promising approach to uncover intricate connectivity patterns in brain networks, offering improved diagnosis. Our code is available at: https://***/ubc-systopia/HyperBrain. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Tea Leaf Disease Identification using Improved Convolution Neural Network

Tea Leaf Disease Identification using Improved Convolution N...

引用

2023 International Conference on Digital Applications, Transformation and Economy, ICDATE 2023

作者： Thangaraj, Rajasekaran Vadivel, Balasubramaniam Aravind, T. Chandhru, L. Harish, K. Eswaran, Sivaraman Kpr Institute of Engineering and Technology Department of Computer Science and Engineering Coimbatore India Curtin University Malaysia Department of Electrical and Computer Engineering Miri Malaysia

ISBN: (纸本)9798350310689

Plant diseases are a significant concern for the agricultural industry, as they can reduce crop yields and cause economic losses. Tea is a popular and widely consumed beverage in India, and the tea crop can be affected by different leaf diseases. Early detection of the diseases is essential to prevent the spread of other crops and minimize production losses. Traditional methods of detecting leaf diseases involve manually interpreting the images, which can be time-consuming and laborious. To address this, artificial intelligence techniques, specifically deep learning models are used for more accurate and efficient detection of tea leaf disease. This study compares the performance of several deep learning models including ResNet50, Resnet50-RS, ResNetlOl-V2, and Modified-ResNet50-V2 (M-RN50V2) and finds that the M-RN50V2 model has the highest accuracy at 90.S4%. Overall, this work aims to promote sustainable agriculture by leveraging cutting-edge technology for disease classification. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Development of IoT based Smart Campus using STM32 15

Development of IoT based Smart Campus using STM32

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Raju, Leo Thirunavukkarasu, K. SSN College of Engineering Department of Electrical and Electronics Engineering Chennai India Thanthai Periyar Govt Institute of Technology Department of Computer Science and Engineering Vellore India

ISBN: (纸本)9798331300579

Over the past few decades, energy has been used mindlessly leading to many problems like reduction in supply, high power rates, increased carbon footprint, etc. Smart campuses, home automation, smart grid, etc. make living comfortable and economical. It optimizes energy consumption and is quite simple to operate too. This project proposes Internet of Things (IoT) based automation for smart car parking inside the campus, thus converting existing campus into smart campus. In this work, we have developed a prototype for smart campus using STM32 microcontroller. This microcontroller has better features compared to other contemporary microcontrollers. This prototype includes a smart car parking system which reduces traffic congestion and facilitates car parking inside the campus. © Grenze Scientific Society, 2024.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Real Time Modeling and Control Algorithm of a Grid-Connected Battery Energy Storage System

Real Time Modeling and Control Algorithm of a Grid-Connected...

引用

2025 IEEE Texas Power and Energy Conference, TPEC 2025

作者： Karimi, Sepehr Nazaralizadeh, Solmaz Srivastava, Anurag Salem, Aboubakr Famouri, Parviz West Virginia University Lane Department of Computer Science and Electrical Engineering Morgantown United States WVU-IT Electrical and Computer Engineering Dept. Beckley United States PCS Eaton PittsburghPA United States

ISBN: (纸本)9798331541125

This work develops real time model and associate control for a grid-tied battery energy storage system (BESS), based on the real industrial system specifications, 362kW/1499kWh lithium-ion BESS. An active and reactive power controller based on the dq reference frame is designed for the grid-tied inverter. To ensure system performance, an LCL filter with passive damping is also developed and analyzed. The system is tested using the Controller Hardware-in-the-Loop (CHIL) platform: Typhoon. The results demonstrate the controller's effective reference tracking across varying load conditions, with the filter design achieving a 3.3% output current THD, emphasizing the inverter's optimized performance. © 2025 IEEE.

关键词： Battery storage

来源：评论

学校读者我要写书评

暂无评论

Real-Time Power Monitoring and Fault Detection in Power Distribution System Using FPGA and cRIO 9039

Real-Time Power Monitoring and Fault Detection in Power Dist...

引用

2024 International Conference on Innovations in science, engineering and Technology, ICISET 2024

作者： Mithil, Md. Salman Khan Talha, Md. Abu Ahmad, Shameem Islam, Khandoker Mainul South Dakota School of Mines & Technology Department of Electrical Engineering and Computer Science Rapid CitySD57701 United States Faculty of Engineering Department of Electrical and Electronic Engineering Dhaka1229 Bangladesh

ISBN: (纸本)9798350355499

This paper details developing and implementing a comprehensive power monitoring system, designed for real-time data acquisition and fault detection. Utilizing a cRIO 9039 platform, the system measures voltage and current, calculates RMS values, frequency, and complex power, and identifies fault conditions in voltage levels, frequency, or power factor. A unique aspect of our approach integrates FPGA-based data processing, ensuring high-speed data handling and error detection without interrupting primary data flow. The system also features a user-friendly interface for real-time data display and fault management. If any errors have been detected, the user will be notified using visual and audio warning and the reading and timestamp corresponding to the fault will be recorded. The system accurately monitors power metrics and detects deviations, enhancing industrial power management systems. The architecture, workflow, and user interface design align with industrial standards, offering practical insights into power system monitoring. © 2024 IEEE.

关键词： Power distribution faults

来源：评论

学校读者我要写书评

暂无评论

Leveraging a Novel Two-Level Priority Encoder for High-Precision Integer Multiplication 66

Leveraging a Novel Two-Level Priority Encoder for High-Preci...

引用

2023 IEEE 66th International Midwest Symposium on Circuits and Systems, MWSCAS 2023

作者： Phillips, Maxwell Hassan, Firas Ammar, Ahmed Hagerdorn, Nathan Ohio Northern University Department of Electrical and Computer Engineering and Computer Science AdaOH United States

ISBN: (纸本)9798350302103

High-precision integer multiplication is critical for applications in physics, mathematics, and most importantly, encryption. Existing multiplication algorithms must process every bit of the multiplier, resulting in high hardware complexity and latency. To improve upon this, we propose an integer multiplication algorithm that must only process the high bits of the multiplier. This algorithm improves shift-and-add multiplication by leveraging a novel two-level structure for a priority encoder, decoder, and barrel shifter. Each component splits inputs into coarse and fine sections and processes each separately, simplifying the hardware design. The proposed algorithm takes sign and magnitude inputs, but could be extended to allow streamlined processing of two's complement inputs. We implemented the algorithm on an FPGA device using multiple clocks to allow rapid input of high-precision data over a serial connection and to optimize multiplication speed. By processing only high bits, the average performance of the proposed algorithm is doubled compared to the traditional shift-and-add algorithm. Additionally, our algorithm increases performance significantly for sparse inputs with few high bits. Overall, our algorithm outperforms existing methods in the best case, surpasses or matches other methods in the average case, and performs no worse than the traditional method in the worst case. © 2023 IEEE.

关键词： encryption high precision integer multiplication priority encoder variable radix

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：