检索结果-内蒙古大学图书馆

2024 IEEE International Conference on E-Health Networking, Application and Services, HealthCom 2024

作者： Ruiz Mejia, Jose M. Rawat, Danda B. Department of Electrical Engineering and Computer Science Howard University WashingtonDC United States

ISBN: (纸本)9798350350548

Electronic Health Records (EHR) are well-known for their extensive capabilities in storing pertinent patient information across various specializations. However, EHRs are part of a broader ecosystem of applications that support the medical treatment process. This ecosystem, although somewhat centralized, does not have the interoperability that many assume. The main issue is that current triage models are not personalized to each patient. Context matters in a medical emergency situation especially when resources are low. In this research, we propose a possible solution by applying state of the art techniques in order to develop a clinical knowledge graph that contains relevant data used for triage optimization. We utilize a fine-tuned named entity recognition model (NER) to extract 41 label entity categories from previous medical records. Additionally, we employed prompt engineering utilizing a large language text generation model with medical knowledge to generate relationships. This resulted in a sum of 1,429 relationship type categories and approximately 999 entity nodes were created with 2,387 relationships. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

SADA: Unsupervised Domain Adaptation for Reliable Scene Awareness 59

SADA: Unsupervised Domain Adaptation for Reliable Scene Awar...

引用

59th Annual Conference on Information sciences and Systems, CISS 2025

作者： Maghsoumi, Hossein Fallah, Yaser P. Atia, George University of Central Department of Electrical and Computer Engineering OrlandoFL United States University of Central Department of Computer Science OrlandoFL United States

ISBN: (纸本)9798331513269

Although deep neural networks are extensively employed in autonomous driving, they must be adjusted to handle unforeseen environmental conditions that were not included in their initial training. Unsupervised domain adaptation (UDA) techniques have proven effective in transferring learned knowledge from one domain to another when the labels in the target domain are unavailable. However, their potential application in scene awareness remains underexplored. This paper introduces SADA (Scene Awareness with Unsupervised Domain Adaptation), a novel approach designed to enhance the reliability of drivable area and lane detection tasks in autonomous driving systems. We leverage UDA techniques in unified multi-task networks to address domain shift challenges, ensuring robust feature extraction under diverse and complex conditions. The proposed technique is evaluated on different real-world datasets and the results demonstrate that the proposed methods outperform the baseline scheme in terms of detection accuracy and consistency. © 2025 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A low-cost buoyant force measurement device for monitoring sugar concentration in water solution

A low-cost buoyant force measurement device for monitoring s...

引用

2023 International Conference on electrical, computer, Communications and Mechatronics engineering, ICECCME 2023

作者： Kaučić, Luka Kovačević, Ivana Aleksi, Ivan Keser, Tomislav Zidar, Josip Rimac-Drlje, Snježana Computer Science and Information Technology Osijek Faculty of Electrical Engineering Department of Computer Engineering and Automation Osijek Croatia Computer Science and Information Technology Osijek Faculty of Electrical Engineering Department of Communications Osijek Croatia

ISBN: (纸本)9798350322972

Monitoring sugar concentration during fermentation is crucial for producing high-quality alcoholic beverages. Traditional methods for measuring sugar concentration can be costly and time-consuming, especially for small-scale producers. In this study, we developed a low-cost buoyant force measurement device for monitoring sugar concentration in water solutions. The device consists of a buoyant object fully submerged in the solution and connected to a load-cell sensor. As the sugar concentration in the liquid increases, the buoyant force on the object increases, and the load-cell measures this force. Proposed device is calibrated using solutions of known sugar concentrations and its high accuracy and precision is presented. The device is tested in controlled environment to ensure accurate tracking changes in sugar concentration over time. Proposed device can be a valuable tool for small-scale producers looking to optimize their fermentation processes while minimizing costs. © 2023 IEEE.

关键词： Fermentation

来源：评论

学校读者我要写书评

暂无评论

Prompt Distillation for Emotion Analysis 16

Prompt Distillation for Emotion Analysis

引用

16th International Conference on Knowledge Discovery and Information Retrieval, KDIR 2024 as part of 16th International Joint Conference on Knowledge Discovery, Knowledge engineering and Knowledge Management, IC3K 2024

作者： Mackey, Andrew L. Gauch, Susan Cuevas, Israel Department of Electrical Engineering and Computer Science University of Arkansas FayettevilleAR United States

ISBN: (纸本)9789897587160

Emotion Analysis (EA) is a field of study closely aligned with sentiment analysis whereby a discrete set of emotions are extracted from a given document. Existing methods of EA have traditionally explored both lexicon and machine learning techniques for this task. Recent advancements in large language models have achieved success in a wide range of tasks, including language, images, speech, and videos. In this work, we construct a model that applies knowledge distillation techniques to extract information from a large language model which instructs a lightweight student model to improve its performance with the EA task. Specifically, the teacher model, which is much larger in terms of parameters and training inputs, performs an analysis of the document and shares this information with the student model to predict the target emotions for a given document. Experimental results demonstrate the efficacy of our proposed prompt-based knowledge distillation approach for EA. © 2024 by SCITEPRESS – science and Technology Publications, Lda.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

A SiC MOSFET Based Multi-Port Solid State Circuit Breaker for DC Protection

A SiC MOSFET Based Multi-Port Solid State Circuit Breaker fo...

引用

2024 IEEE Energy Conversion Congress and Exposition, ECCE 2024

作者： Song, Xiaoqing Nawafleh, Yannal Rahman, Mohammad Dehan University of Arkansas Department of Electrical Engineering and Computer Science FayettevilleAR United States

ISBN: (纸本)9798350376067

Direct current (DC) systems require fast fault protection speed due to ultrafast transients with high currents in short circuit faults, where solid state circuit breakers (SSCBs) can perfectly fit. Compared to the traditional mechanical circuit breakers (MCBs), SSCBs demonstrate 10 to 100 orders of magnitude faster fault breaking speed and enhanced safety with arc-less fault current interruption. One remaining challenge of the SSCB is large conduction losses, resulting in heavy and bulky cooling systems. In this paper, a novel high efficiency multi-port SSCB is proposed, which reduces >50% conduction losses compared to conventional SSCB topology. The power loss reduction benefits and operation principles of the proposed multiport SSCB are analyzed. A SiC MOSFET based SSCB hardware prototype is built, and experimental results validate the feasibility and effectiveness of the proposed SSCB concept. © 2024 IEEE.

关键词： MOSFET devices

来源：评论

学校读者我要写书评

暂无评论

Passive islanding detection in microgrids using artificial neural networks

引用

Applied Nanoscience (Switzerland) 2023年第4期13卷 2885-2900页

作者： Alyasiri, Ali Majeed Mohammed Kurnaz, Sefer Department of Electrical and Computer Engineering Institute of Science Altinbas University Istanbul Turkey

This research focuses on modeling and simulating voltage control of passive islanding detections with distributed generation. This research presents how reactive power generation and/or absorption can be utilized to partake voltage control in medium voltage distribution through multi-microgrids for passive islanding detection with rule-based mathematical model and artificial neural network (ANN). With the increased emphasis on renewable energy, modern power grids have become more reliant to smaller distributed generation units. Unlike traditional power grids that rely on larger centralized units, the detection of islanding events in these grids is more complex. However, it is still important to maintain the connection to the power grid to maintain high stability of the system and is also important to deenergize the grid when an islanding event happens, to protect the workers that may be working on the grid to clear the cause of the islanding. Islanding detection methods are categorized into passive, active and communication based. Active methods detect islanding by measuring the influence of noise they add to the grid, to predict the size of the grid, which reduces the quality of the power provided on that grid. Communication-based methods are expensive and highly reliable on the communications infrastructure, which limits their application. Unlike existing methods, the proposed method of ANN relies on the instantaneous current and voltage values to detect any islanding with an accuracy of 97.89% precisely. These values are directly fed to the ANN, i.e., without applying any feature extraction, so that, faster and more accurate decisions are made. The proposed method is expected to combine the high accuracy of ANNs with the faster change in instantaneous values, so that, faster and more accurate detection can be achieved. © 2022, King Abdulaziz City for science and Technology.

关键词： Detection Distributed energy Distribution grid Islanding Microgrid Reactive power Voltage control

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study on Prosumers Load Demand and Production Forecasting Using Machine Learning and Time Series Techniques 16

A Comparative Study on Prosumers Load Demand and Production ...

引用

16th International Conference on Applied and Theoretical Electricity, ICATE 2024

作者： Solea, Claudiu Hera, Corina Florea, Adrian Morariu, Daniel Stanescu, Dorel Vintan, Maria Lucian Blaga University of Sibiu Computer Science and Electrical Engineering Department Sibiu Romania

ISBN: (纸本)9798350388107

A data-driven and realistic policy could overcome the current turmoil in the intricate energy landscape. With solar and wind expanding faster than liquified natural gas or nuclear ever have, local, bottom-up solutions, such as organising collaboratively residential prosumers into electricity trading communities and the efficient use of aggregators, are one way to resilience and control over these resources. This paper analyses the features and characteristics of some prosumers and facilitates the identification of relevant algorithms for the specific tasks of both load demand and production forecasting using machine learning and time series techniques, thus enabling them to operate on a level playing field in the market. Load demand and production forecast simulations on two data sets, one collected in 2019, corresponding to 50 residential households and a public building from Portugal, and the other from 2023, that aggregates values from 29 household prosumers from Romania, show that both simple and double exponential smoothing techniques are more accurate than Markov predictors. Provided that the external contingencies influencing either the consumption or the production are considered, the latter gives a better prediction accuracy for energy production, whereas the former provides a better forecast for the consumption. © 2024 IEEE.

关键词： Demand response

来源：评论

学校读者我要写书评

暂无评论

TILE: Input Structure Optimization for Neural Networks to Accelerate Secure Inference 40

TILE: Input Structure Optimization for Neural Networks to Ac...

引用

40th Annual computer Security Applications Conference, ACSAC 2024

作者： Feng, Yizhou Zhang, Qiao Cai, Yifei Wu, Hongyi Xin, Chunsheng Department of Electrical and Computer Engineering Old Dominion University NorfolkVA United States College of Computer Science Chongqing University Chongqing China Department of Electrical and Computer Engineering University of Arizona TucsonAZ United States

ISBN: (纸本)9798331520885

Machine Learning as a Service (MLaaS) is an innovative framework that enables a broad range of users to capitalize on the powerful Artificial Intelligence (AI) technologies. Nevertheless, MLaaS raises a privacy concern for both the client data and server model. To address this issue, several Secure Inference (SI) frameworks for MLaaS have been proposed in the literature that take advantage of Homomorphic Encryption (HE) operations. However, the computation cost of these frameworks is still high, especially for real-time applications. In this paper, we propose a novel system called input structure optimization for neural networks (TILE) to accelerate SI. The goal of TILE is to reduce both linear and non-linear computation costs, as well as non-linear communication costs in MLaaS, while maintaining the model accuracy. TILE defines two novel HE-friendly input structures: Internal Tile and External Tile Structures, aimed at reducing the HE operations for SI. We also develop a search mechanism to identify optimal application locations for these input structures. We apply TILE to widely used models such as VGG and ResNet, and datasets including Cifar10 and Tiny-ImageNet. The experimental results demonstrate that TILE effectively reduces the computation time, with up to 51.57% reduction for a state-of-the-art SI framework. Furthermore, TILE can also be applied to models that have already been pruned to significantly reduce the computation time, to further reduce the overall computation time by 25.90%. © 2024 IEEE.

关键词： Structural optimization

来源：评论

学校读者我要写书评

暂无评论

Securing Energy Equity With Multilayer Market Clearing

IEEE Transactions on Energy Markets, Policy and Regulation

引用

IEEE Transactions on Energy Markets, Policy and Regulation 2024年第3期2卷 301-312页

作者： Zhang, Qiwei Li, Fangxing The University of Tennessee Min H. Kao Department of Electrical Engineering and Computer Science KnoxvilleTN37996 United States

Energy equity has been quickly gaining attention as policymakers seek to place 'Clean Energy for ALL' at the center of the low-carbon energy transition. Power system researchers have started to build the groundwork for incorporating energy equity into grid modernization. However, existing research has mostly focused on energy equity from a policy perspective, such as concept clarifications and tariff designs for residential customers. Little effort has been devoted to discussing energy equity in wholesale markets and to reflecting energy equity in electricity price with technical models. To the best of our knowledge, this paper presents the first study attempting to understand and implement energy equity consideration within a physically constrained electricity market-clearing model. First, we identify and discuss several concerns regarding energy equity in the existing locational marginal pricing (LMP) model. Then, we propose a multilayer framework reflecting energy equity in LMPs. Finally, the proposed framework is elaborated via a modified PJM 5-bus system and demonstrated with the WECC 179-bus system. © 2023 IEEE.

关键词： Power markets

来源：评论

学校读者我要写书评

暂无评论

Designing A Student Success Framework with Zachman Architecture

Designing A Student Success Framework with Zachman Architect...

引用

2024 ASEE Annual Conference and Exposition

作者： Chaback, Benjamin Edward Watson, Bryan C. Embry-Riddle Aeronautical University Department of Electrical Engineering and Computer Science United States

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：