检索结果-内蒙古大学图书馆

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

作者： Abbaraju, Vikram Bashar, Syed Khairul Nawar, Afra Rahman, Farhan N. Choi, Jaiyoun Lambert, Tamara P. Gazi, Asim H. Harrison, Anna B. Robinson, Madeline R. Mesfin, Hewitt Gray, Trinity A. Mermin-Bunnell, Kellen Jacquement, Nora Tomic, Nikolina Welsh, Justine W. Patel, Santosh Vaccarino, Viola Shah, Amit J. Douglas Bremner, J. Inan, Omer T. Georgia Institute of Technology School of Electrical and Computer Engineering AtlantaGA United States Emory University School of Medicine Department of Psychiatry and Behavioral Sciences AtlantaGA United States Georgia Institute of Technology The Wallace H. Coulter Department of Biomedical Engineering AtlantaGA United States Emory University Department of Epidemiology Rollins School of Public Health AtlantaGA United States

ISBN: (纸本)9798350371499

Induced craving frequently leads to relapse in patients with a history of opioid use disorder (OUD). Quantifying the physiological manifestations of craving can enable caregivers of patients with OUD to continuously monitor craving and thus help inform treatment plans. Heart rate variability (HRV) is a promising candidate to capture the trends in such manifestations due to the ease of measuring changes in heartbeat intervals using the electrocardiogram. However, the relationship between craving and HRV measured over periods shorter than 5 minutes, i.e., ultra-short-term HRV, has not yet been investigated in detail. In this work, we present the first analysis on the relationship between 12 HRV features computed over ~2-minute periods and subjective craving reported on the visual analog scale (VAS-craving). Patients with OUD stable on medication (N = 12) went through an approximately 2-hour protocol involving audio/visual opioid cues to induce craving, alongside active transcutaneous vagus nerve stimulation or sham stimulation. Regardless of stimulation type, changes in VAS-craving scores over the course of the protocol were negatively correlated with changes in two ultra-short-term HRV features: the number of adjacent normal heartbeat intervals differing by more than 50 milliseconds (r = -0.63, p = 0.03) and the total power across all frequency bands (r = -0.69, p = 0.03).Clinical relevance - This preliminary study suggests that certain ultra-short-term HRV features can potentially serve as indicators of craving in patients with a history of OUD. Using such metrics computed over small data intervals can enable efficient clinical decision making and may help prevent opioid relapse. © 2024 IEEE.

关键词： Heart

来源：评论

学校读者我要写书评

暂无评论

Intelligent Participation of Electric Vehicles in Demand Response Programs

Intelligent Participation of Electric Vehicles in Demand Res...

引用

2023 International Conference on Smart Energy Systems and Technologies, SEST 2023

作者： Guzman, Cindy P. Lekidis, Alexios Pediaditis, Panagiotis Carvalho, Pedro Ms Morais, Hugo INESC-ID Instituto Superior Técnico-IST Universidade de Lisboa Lisboa1049-001 Portugal Public Power Corporation S.A. Athens10432 Greece School of Electrical and Computer Engineering National Technical University of Athens Greece

ISBN: (纸本)9798350397901

Demand Response (DR) has been proposed and implemented in recent years to enable the participation of active consumers in energy management. However, existing programs do not consider the characteristics and opportunities introduced by electric vehicles (EVs). EVs have more flexibility than traditional loads and can be used as battery energy storage systems if the vehicle-to-grid capability is available. The main contribution of this paper is the analysis of the EV user's point of view concerning different DR programs (implicit and explicit) as well as the EVs management considering different strategies. One of the most interesting strategies that have been proposed and tested is opportunity cost optimization, where the expected prices of the next days are considered. Some of the results show that DR programs with less cost are interesting for the users since also minimise the EV charging during the DR time operation. On the other hand, realtime pricing program is not interesting for the users since its performance is highly dependent on the market price. © 2023 IEEE.

关键词： Electric vehicles

来源：评论

学校读者我要写书评

暂无评论

Residential demand-side flexibility provision under a multi-level segmented tariff

Residential demand-side flexibility provision under a multi-...

引用

IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT Europe)

作者： Na Li Kenneth Bruninx Simon Tindemans Faculty of Electrical Engineering Mathematics and Computer Science Faculty of Technology Policy and Management Delft University of Technology Delft the Netherlands

This paper proposes a multi-level segmented tariff to encourage consumers to provide demand response using a battery. The aim of the tariff is to (i) properly reflect consumers’ contribution to the distribution grid cost while ensuring cost recovery for the distribution network operator and (ii) to provide consumers with a financial incentive to flatten their load profile and avoid peak demand. An optimization problem is formulated to describe how consumers can provide demand response by managing their batteries. To evaluate the effectiveness of the proposed multi-level segmented tariff, four case studies were conducted. The results indicate that the multi-level segmented tariff is the most effective in reducing coincident peak demand, with a reduction of 22%. policymakers and regulators are recommended to consider multi-level segmented distribution tariffs, as it provides an incentive to consumers to manage their assets to provide demand response.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Emergency Load Shedding to Enhance Resiliency Considering Operator and Customer Equity

Emergency Load Shedding to Enhance Resiliency Considering Op...

引用

IEEE Green Technologies Conference (IEEE-Green)

作者： Nirasha Bataduvaarachchi Demy Alexander Visvakumar Aravinthan Al Tamimi Department of Electrical and Computer Engineering Wichita State University Wichita Kansas USA Transmission Planning & Policy Sunflower Electric Corporation Wichita Kansas USA

Recent high impact low frequency events have caused significant concerns on reliability and resiliency of electrical grid. Transmission operators might enforce load curtailment during such events to preserve the integrity of the power network and to prevent catastrophic system failures and long-lasting outages. Although load-shedding procedures employed by system operators are reviewed and constraints are highlighted throughout most hazardous incidents, such mechanisms are not evaluated to ensure consumer fairness and system impacts are addressed. This study was conducted at the transmission level in order to propose a new curtailment algorithm that addresses the limitations of the load shedding mechanism of the Southwest Power Pool. The study was motivated by the North American winter storm occurred in February 2021. The performance of the proposed algorithm is tested and compared with Southwest Power Pool's curtailment model via IEEE RTS-96 test system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Self-Supervision for Tackling Unsupervised Anomaly Detection: Pitfalls and Opportunities

arXiv

引用

arXiv 2023年

作者： Akoglu, Leman Yoo, Jaemin Heinz College of Information Systems and Public Policy Carnegie Mellon University United States School of Electrical Engineering KAIST Korea Republic of

Self-supervised learning (SSL) is a growing torrent that has recently transformed machine learning and its many real world applications, by learning on massive amounts of unlabeled data via self-generated supervisory signals. Unsupervised anomaly detection (AD) has also capitalized on SSL, by self-generating pseudo-anomalies through various data augmentation functions or external data exposure. In this vision paper, we first underline the importance of the choice of SSL strategies on AD performance, by presenting evidences and studies from the AD literature. Equipped with the understanding that SSL incurs various hyperparameters (HPs) to carefully tune, we present recent developments on unsupervised model selection and augmentation tuning for SSL-based AD. We then highlight emerging challenges and future opportunities;on designing new pretext tasks and augmentation functions for different data modalities, creating novel model selection solutions for systematically tuning the SSL HPs, as well as on capitalizing on the potential of pretrained foundation models on AD through effective density estimation. © 2023, CC BY-NC-SA.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Dynamic Load Frequency Control for Small Signal Stability Analysis in Steam Plant with Reheater 21

Dynamic Load Frequency Control for Small Signal Stability An...

引用

21st IEEE International Symposium on Intelligent Systems and Informatics, SISY 2023

作者： Shahgholian, Ghazanfar Fathollahi, Arman Mosavi, Amirhosein Islamic Azad University Smart Microgrid Research Center Najafabad Branch Najafabad Iran Aarhus University Department of Electrical and Computer Engineering Aarhus Denmark John von Neumann Faculty of Informatics Budapest Hungary Ludovika University of Public Service Budapest Hungary

ISBN: (纸本)9798350343366

Steam energy plants are the fundamental source of electricity in the world, which has a large share of renewable energy. Load changes impact the frequency of electrical networks. Frequency stabilization is very important based on the boosting influence of renewable power sources in energy systems. The main task of load frequency control is to keep the system frequency according to the determined nominal value and to maintain the correct amount of exchange energy between the control areas. Maintaining the output power and actual frequency of the interconnected energy system and controlling the variation in power along the connection link between control areas are the central objectives of load frequency control (LFC). In this work, the purpose is to analyze and investigate load frequency control in a two-area energy system. Each area contains a steam turbine with a reheater. The system equations are expressed in state space and analyzed in MATLAB software. The simulation outcomes demonstrate the impact of changes in the gain parameters of the equivalent power system model and high-pressure coefficient in an area. © 2023 IEEE.

关键词： Thermoanalysis

来源：评论

学校读者我要写书评

暂无评论

A bias evaluation checklist for predictive models and its pilot application for 30-day hospital readmission models (May, 10.1093/jamia/ocac065, 2022)

引用

JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION 2022年第9期29卷 1656-1656页

作者： Wang, H. Echo Landers, Matthew Adams, Roy Subbaswamy, Adarsh Kharrazi, Hadi Gaskin, Darrell J. Saria, Suchi Department of Health Policy and Management Johns Hopkins Bloomberg School of Public Health Baltimore Maryland USA Department of Computer Science University of Virginia Charlottesville Virginia USA Department of Psychiatry and Behavioral Sciences Johns Hopkins School of Medicine Baltimore Maryland USA Department of Computer Science and Statistics Whiting School of Engineering Johns Hopkins University Baltimore Maryland USA

Objective Health care providers increasingly rely upon predictive algorithms when making important treatment decisions, however, evidence indicates that these tools can lead to inequitable outcomes across racial and socio-economic groups. In this study, we introduce a bias evaluation checklist that allows model developers and health care providers a means to systematically appraise a model’s potential to introduce bias. Materials and Methods Our methods include developing a bias evaluation checklist, a scoping literature review to identify 30-day hospital readmission prediction models, and assessing the selected models using the checklist. Results We selected 4 models for evaluation: LACE, HOSPITAL, Johns Hopkins ACG, and HATRIX. Our assessment identified critical ways in which these algorithms can perpetuate health care inequalities. We found that LACE and HOSPITAL have the greatest potential for introducing bias, Johns Hopkins ACG has the most areas of uncertainty, and HATRIX has the fewest causes for concern. Discussion Our approach gives model developers and health care providers a practical and systematic method for evaluating bias in predictive models. Traditional bias identification methods do not elucidate sources of bias and are thus insufficient for mitigation efforts. With our checklist, bias can be addressed and eliminated before a model is fully developed or deployed. Conclusion The potential for algorithms to perpetuate biased outcomes is not isolated to readmission prediction models; rather, we believe our results have implications for predictive models across health care. We offer a systematic method for evaluating potential bias with sufficient flexibility to be utilized across models and applications.

关键词： predictive model hospital readmission bias health care disparity clinical decision-making

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Charging Circuit for Energy Storage System in Multi-Input Non-Isolated Converter with High Gain 27

Design and Implementation of Charging Circuit for Energy Sto...

引用

27th IEEE International Conference on Intelligent engineering Systems, INES 2023

作者： Taheri, Donya Shahgholian, Ghazanfar Mirtalaei, Mohammad Mehdi Mosavi, Amirhosein Fathollahi, Arman Varkonyi-Koczy, Annamaria Islamic Azad University Department of Electrical Engineering Najafabad Branch Najafabad Iran Islamic Azad University Smart Microgrid Research Center Najafabad Branch Najafabad Iran John von Neumann Faculty of Informatics Budapest Hungary University of Public Service Budapest Hungary Aarhus University Department of Electrical and Computer Engineering Aarhus Denmark Obuda University John von Neumann Faculty of Informatics Budapest Hungary

ISBN: (纸本)9798350328516

In this study, the topology of a multi-input high-gain non-isolated power converter is suggested. Within this converter, techniques involving voltage multiplier cells and a coupling inductor are utilized. It is possible to use switches that have low voltage stress and, as a result, low conductivity by combining these two methodologies. For applications dealing with clean energy, like green electrical power for public hospitals and etc., that consider a specific type of energy storage system, this particular configuration is an excellent choice. First, the charging performance of the energy storage system is explained, and then, for the design of the multi-input non-isolated power converter with a high voltage gain, the configuration and functionality of the proposed converter are fully investigated. This is accomplished so that the multi-input non-isolated converter can have high voltage gain. The correct operation of the converter is demonstrated through the presentation of a detailed design method, and numerical outcomes are shown for a variety of modes in which the converter can operate effectively. Eventually, to guarantee that the simulation outcomes are accurate, an experimental prototype of the proposed converter has been produced in a laboratory, and the results of the simulation have been validated with those obtained in practice. © 2023 IEEE.

关键词： Energy storage

来源：评论

学校读者我要写书评

暂无评论

Compressed VGGNet for Automatic COVID-19 Disease Detection from CT Scan Images 8th

Compressed VGGNet for Automatic COVID-19 Disease Detection f...

引用

8th IFIP TC 12 International Conference on computer, Communication and Signal Processing, ICCCSP 2024

作者： Vinothini, R. Niranjana, G. Dhamanti, Inge Lailiyah, Syifa’ul Yakub, Fitri Department of Computer Science and Engineering SRM Institute of Science and Technology Kattankulathur 603203 India Department of Computing Technologies School of Computing SRM Institute of Science and Technology Kattankulathur 603203 India Department of Health Policy and Administration Faculty of Public Health Universitas Airlangga Surabaya Indonesia Faculty of Health Medicine and Life Sciences Universitas Airlangga East Java Indonesia Electronic System Engineering Department Malaysia-Japan International Institute of Technology Kuala Lumpur Malaysia

ISBN: (纸本)9783031736162

Millions of people across the globe were affected by this rapidly spreading disease by the year 2020. Contamination of the respiratory system results from contracting COVID-19. Nonetheless, establishing a conclusive diagnosis of COVID-19 may prove difficult due to the subtle differences it shares with conventional pneumonia and the complexities involved in identifying areas of infection. A growing number of approaches based on deep learning (DL) are being proposed for the automated detection of COVID-19 from CT scan images. By employing the data pretreatment methodology, unprocessed image data becomes prepared for further analysis. The proposed framework utilised transfer learning to construct VGGNet, which is capable of discerning the Covid-19 disease. The model was subsequently assessed in comparison to the most sophisticated models, VGG16 and VGG19, using the SARS-COV2 CT scan dataset. This dataset contains 1230 CT scans of non-infected images and 1252 CT scans of Covid-19-infected images. The model has achieved 99% accuracy, 98% precision, 97% recall, and 98% F1-score, among other performance metrics. © IFIP International Federation for Information Processing 2025.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

CHARLIE: A Chatbot That Recommends Daily Fitness and Diet Plans

CHARLIE: A Chatbot That Recommends Daily Fitness and Diet Pl...

引用

2023 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events, PerCom Workshops 2023

作者： Chowdhury, Deepanjali Roy, Ahana Ramamurthy, Sreenivasan Ramasamy Roy, Nirmalya Texas A&m University Department of Electrical and Computer Engineering College Station United States Howard County Public School System MD United States Bowie State University Department of Computer Science Bowie United States University of Maryland Baltimore County Department of Information Systems Baltimore United States

ISBN: (纸本)9781665453813

Managing a work-life balance has always been challenging, especially after the recent trend of working from home, which has made maintaining one's fitness and diet regime strenuous. Failing to adhere to a fitness and diet plan has been shown to cause long-term effects on a person's health including obesity and shortened lifespans. Currently, people plan their fitness and diet plans around their schedule, but these tasks are challenging to maintain. Users tend to give up these plans due to a lack of time and planning. To help with better planning for a fitness and diet regime, we propose, CHARLIE, a chatbot that works around a user's schedule to intelligently recommend diets and fitness goals based on their calendar. CHARLIE is a recommendation system that suggests the users' a certain meal and fitness activities based on the amount of time they have left in their day and the number of calories they lose. © 2023 IEEE.

关键词： Recommender systems

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：