检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Vidal, Alexander Fung, Samy Wu Tenorio, Luis Osher, Stanley Nurbekyan, Levon Dept. of Applied Mathematics and Statistics Colorado School of Mines United States Dept. of Applied Mathematics and Statistics Dept. of Computer Science Colorado School of Mines United States Dept. of Mathematics University of California Los Angeles United States

A normalizing flow (NF) is a mapping that transforms a chosen probability distribution to a normal distribution. Such flows are a common technique used for data generation and density estimation in machine learning and data science. The density estimate obtained with a NF requires a change of variables formula that involves the computation of the Jacobian determinant of the NF transformation. In order to tractably compute this determinant, continuous normalizing flows (CNF) estimate the mapping and its Jacobian determinant using a neural ODE. Optimal transport (OT) theory has been successfully used to assist in finding CNFs by formulating them as OT problems with a soft penalty for enforcing the standard normal distribution as a target measure. A drawback of OT-based CNFs is the addition of a hyperparameter, α, that controls the strength of the soft penalty and requires significant tuning. We present JKO-Flow, an algorithm to solve OT-based CNF without the need of tuning α. This is achieved by integrating the OT CNF framework into a Wasserstein gradient flow framework, also known as the JKO scheme. Instead of tuning α, we repeatedly solve the optimization problem for a fixed α effectively performing a JKO update with a time-step α. Hence we obtain a "divide and conquer" algorithm by repeatedly solving simpler problems instead of solving a potentially harder problem with large α. © 2022, CC BY.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Optimizing Healthcare Accessibility and Effectiveness through the Implementation of AI Solutions for Remote Patient Monitoring

Optimizing Healthcare Accessibility and Effectiveness throug...

引用

applied Intelligence and Computing (AIC), IEEE World Conference on

作者： Jagendra Singh Dinesh Prasad Sahu Ashwini Kumar Salman Khursheed Ahmad Jayeeta Majumder Sourav Gangopadhyay School of Computer Science Engineering & Technology Bennett University Greater Noida India Department of Computer Science & Engineering Camellia Institute of Technology & Management Jaipur India Dept. of Applied Computational Science and Engineering GL Bajaj Institute of Technology & Management Greater Noida India Department of Hospital Management Brainware University Kolkata India

ISBN: (数字)9798350384598

ISBN: (纸本)9798350384604

This study investigates the optimization of healthcare accessibility and effectiveness by integrating artificial intelligence (AI) solutions within Internet of Things (IoT) systems for remote patient monitoring. Embracing a holistic approach, we deploy medical sensors, including temperature, pressure, heart rate, and oxygen sensors, to collect patients' continuous health metrics (vital signs). These sensed data are then transmitted to an Arduino controller, responsible for managing data communication with the cloud infrastructure using a Wi-Fi module that facilitates data storage and analysis. Stored data are accessed by authorized healthcare professionals, who exploit machine learning models, including Artificial Neural Networks (ANN), Logistic Regression (LR) and Decision Tree (DT), to forecast patients' health outcome in advance using the sensed data. A rigorous evaluation demonstrated the IoT system's effectiveness, based on testing with sensed data from ten patients over a month, where 70% of the data were used for training the models, and the rest for testing. The proposed IoT system demonstrates the success; ANN exhibited the highest accuracy at 97.88%, followed by LR at 93.43%, and DT at 91.20%. Precision, recall, and F1 scores further validated the models' ability to predict health outcome accurately. Evaluation of the accuracy and loss curves showed the convergence of the models towards optimal performance. This study contributes to remote healthcare monitoring and provides a promising IoT paradigm for realizing ubiquitous remote monitoring, optimized healthcare effectiveness, and patient outcome through AI-enabled IoT systems.

关键词： Temperature sensors Measurement Patient monitoring Accuracy Medical services Artificial neural networks Predictive models Internet of Things Monitoring Testing

来源：评论

学校读者我要写书评

暂无评论

Reliability of Electronic Connections in Fast Chargers of Electric Vehicle 1

Reliability of Electronic Connections in Fast Chargers of El...

引用

1st International Conference on Advances in computer science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Semwal, Priyanka Raturi Ekatpure, Shubham Rajendra Sharma, Merlyn Singh, Neelima Kumar, Anil Pandey, Bhumika Tula's Institute Dehradun Department of Electrical & Electronics Engineering Dehradun India Global Supply Chain in Semiconductor Manufacturing Kulicke and Soffa PA United States IIMT College of Engineering Department of ASH UP Grater Noida India Uttaranchal University Department of Computer Science and Engineering Dehradun India Physics Bharati Vidyapeeth's College of Engineering Dept. of Applied Science New Delhi India Bipin Tripathi Kumaon Institute of Technology Department of ECE Almora Dwarahat India

ISBN: (纸本)9798331518578

Global mobility is undergoing a dramatic change as cars fuelled by fossil fuels give way to those with zero or extremely low tailpipe emissions. Every one of the parts in big battery packs normally don't have similar properties and may corrupt essentially in view of assembling fluctuation and different elements. The performance and economics of the entire battery pack are impacted by the increased power waste from degraded battery modules. Additionally, the influence changes depending on the trip pattern. A variety of important factors, such as the age of the car, the internal resistance of the lithium-ion battery pack, awareness of grid energy pricing, and the distance driven, affect how much an electric vehicle (EV) costs to drive every day. It has used the grid's energy price data to optimise the cost of the typical driving cycle. Accurately forecasting battery behaviour reliability for the daily driving cycle is the aim of this project. The driver will be able to determine the best charging schedules, driving energy consumption, and excess battery energy with the aid of the reliability battery behaviour forecast. The driver can reduce the cost of travel both daily and over the battery's lifespan by having a previous understanding of the battery's behaviour, the grid's energy pricing, and the trip's duration. © 2025 IEEE.

关键词： Lithium-ion batteries

来源：评论

学校读者我要写书评

暂无评论

Identifying COVID-19 through X-ray and CT scan images using Machine Learning

Identifying COVID-19 through X-ray and CT scan images using ...

引用

International Conference on Emerging Technologies, ICET

作者： Maham Shehzadi Usama Arshad Zainul Abideen Raja Hashim Ali Ammad Aslam Khan Ali Zeeshan Ijaz Faculty of Computer Science & Engineering GIK Institute of Engg. Sciences & Technology Topi Pakistan BCMaterials Basque Center for Materials Applications & Nanostructure Leioa Basque Country Spain Dept. of Technology & Software Engineering University of Europe for Applied Sciences Berlin Germany Dept. of Biological Sciences Virtual University of Pakistan Rawalpindi Pakistan Dept. of Computer Science National University of Computer & Emerging Sciences Islamabad Pakistan

In the current global scenario, marked by the COVID-19 pandemic, it has become imperative for healthcare systems around the globe to swiftly and accurately diagnose the disease. This is where cutting-edge approaches such as machine learning (ML) come into play, specifically, ML-based identification of COVID-19 from chest X-ray and CT-Scan imagery. Our research collective is devotedly working towards devising a robust, accurate ML model capable of deciphering these images to identify COVID-19 effectively. This involves the application of a variety of AI algorithms and vast data resources. Our work is grounded on a large, annotated image dataset that aids in training and refining the model. Our findings indicate that ML methodologies can discern COVID-19 from chest X-ray and CT scan images with a mean accuracy of 90%. Such a tool holds promise in aiding medical practitioners in prompt and precise patient diagnosis, thereby improving patient prognosis. The most notable contribution of our study lies in the creation of an ML model that can accurately detect COVID-19 in chest X-ray and CT-Scan images, potentially aiding in early disease detection and management.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DeCon: Detecting Incorrect Assertions via Postconditions Generated by a Large Language Model

arXiv

引用

arXiv 2025年

作者： Yu, Hao Chen, Tianyu Huang, Jiaming Li, Zongyang Ran, Dezhi Wang, Xinyu Li, Ying Marron, Assaf Harel, David Xie, Yuan Xie, Tao Peking University Beijing China University of Michigan Ann Arbor United States Dept. of Computer Science and Applied Mathematics Weizmann Institute of Science Rehovot Israel The Hong Kong University of Science and Technology China Key Lab of HCST PKU MOE SCS Peking University China

Recently, given the docstring for the target problem and the target function signature, large language models (LLMs) have been used not only to generate source code, but also to generate test cases, consisting of test inputs and assertions (e.g., in the form of checking an actual output against the expected output). However, as shown by our empirical study on assertions generated by four LLMs for the HumanEval benchmark, over 62% of the generated assertions are incorrect (i.e., failed on the ground-truth problem solution). To detect incorrect assertions (given the docstring and the target function signature along with a sample of example inputs and outputs), in this paper, we propose a new approach named DeCon to effectively detect incorrect assertions via LLM-generated postconditions for the target problem (a postcondition is a predicate that must always be true just after the execution of the ground-truth problem solution). Our approach requires a small set of I/O examples (i.e., a sample of example inputs and outputs) for the target problem (e.g., the I/O examples included in the docstring for a target problem in HumanEval). We use the given I/O examples to filter out those LLM-generated postconditions that are violated by at least one given I/O example. We then use the remaining postconditions to detect incorrect assertions as those assertions that violate at least one remaining postcondition. Experimental results show that DeCon can detect averagely more than 64% (63% and 65.5% detected by GPT-3.5 and GPT-4, respectively) incorrect assertions generated by four state-of-the-art LLMs, and DeCon can also improve the effectiveness of these LLMs in code generation by 4% in terms of Pass@1. In addition, although DeCon might filter out correct assertions, the fault-finding ability of the remaining correct assertions decreases only slightly. Copyright © 2025, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

引用

Proceedings of the 14th International Conference on Education Technology and computers

作者： Veronica Segarra-Faggioni Sylvie Ratté Frank De Jong Dept. Software and IT Engineering École de technologie supérieure Canada and Dept. Computer Science and Electronics Universidad Tecnica Particular de Loja Ecuador Dept. Software and IT Engineering École de technologie supérieure Canada Dept. Learning and Innovation Aeres Wageningen Applied University Netherlands

ISBN: (纸本)9781450397766

Knowledge Building as a pedagogy supports collaborative work between students to improve ideas. The result of knowledge-building discourse in student communities is the development of academic artifacts. Student reports are academic artifacts that can result from a knowledge-building process during their learning. However, the automatic analysis of student reports is quite challenging due to the documents’ length and written language. Given this context, our goal is to analyze the semantic similarity between student reports and curriculum literature using the information coverage measure based on the Skip-gram word2vec model. Word2vec is a well-known set of techniques that provides a way to create a representation of words to predict the nearby words between every word and its context to capture the internal semantic and syntactic information. In this work, through the experimental comparison between the vocabulary list, the best similarity value is 0.90 using word2vec. The results show that each student report was aligned with each document in the curriculum literature using the information coverage measure based on word2vec.

关键词： Machine learning natural language processing word2vec

来源：评论

学校读者我要写书评

暂无评论

Occluded Face Recovery by Image Retrieval

Occluded Face Recovery by Image Retrieval

引用

2021 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2021

作者： Tu, Ching-Ting Lee, Kuan-Hsin National Chung Hsing University Department of Applied Mathematics Taichung Taiwan Tamkang University Dept. of Computer Science and Information Engineering New Taipei Taiwan

ISBN: (纸本)9781665419512

In this paper, we propose an occluded face recovery framework to improve the face recognition rate for the occlusion case. The occluded facial image of an unseen testing subject is automatically recovered, the generated results are diverse and fit the personal characteristics of the observable regions, and thus can be used to increase the face recognition performance for occlusion cases. © 2021 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Pulling Figure of Dielectric Resonator for 3D Filament Defectoscopy

Pulling Figure of Dielectric Resonator for 3D Filament Defec...

引用

International Scientific Symposium on Metrology and Metrology Assurance (MMA)

作者： Maryna Miroshnyk Olga Zaichenko Anatolii Miroshnyk Nataliia Hapon Yurii Pakhomov Liubov Klymenko dept. of Theoretical and Applied System Engineering V. N. Karazin Kharkiv National University Kharkov Ukraine dept. of Design and Operation of Electronic Devices Kharkiv National University of Radioelectronics Kharkiv Ukraine dept. of Design Automation Kharkiv National University of Radioelectronics) Kharkiv Ukraine dept. of Computer Science and Information Technologies O.M. Beketov National University of Urban Economy in Kharkiv Kharkiv Ukraine dept. of Specialized Computer Systems Ukrainian State University of Railway Transport Kharkiv Ukraine

ISBN: (数字)9798350352832

ISBN: (纸本)9798350352849

The research aim is to derive connection between the parameters of dielectric resonators frequency shift and the warp defect of 3D printing filament. Object of investigation are the processes of interaction of electromagnetic wave of a dielectric resonator with filament for 3D printing. The proposed model describes the connection between the frequency shift and defect warp of filament frequency pulling depending on the load.

关键词： Electromagnetic scattering Resonant frequency Estimation Metrology Three-dimensional printing Resonance Dielectrics Frequency measurement Resonators Load modeling

来源：评论

学校读者我要写书评

暂无评论

Evaluating Common Electronic Components and GaN HEMTs under Cryogenic Conditions

Evaluating Common Electronic Components and GaN HEMTs under ...

引用

2021 IEEE Southern Power Electronics Conference, SPEC 2021

作者： Wadsworth, Aaron Pais, Brandon Kyle, Shaun Thrimawithana, Duleepa J. Badcock, Rodney A. Lapthorn, Andrew Heffernan, Bill Oliver, Rachel A. Wallis, David J. Neuberger, Martin University of Auckland Dept. of Electrical and Computer Engineering New Zealand Robinson Research Institute Victoria University of Wellington New Zealand University of Canterbury Dept. of Electrical and Computer Engineering New Zealand University of Cambridge Dept. of Material Science and Metallurgy United Kingdom Esslingen University of Applied Sciences Dept. of Mechatronics Electrical Engineering Germany

ISBN: (纸本)9781665436236

Superconducting motors are a solution to electrifying large scale transport (aviation, rail, shipping) due to their superior power density over conventional electric motors. Cooling a superconducting motor and its power converter using the same cryogenic system provides a unique opportunity to increase the converter's power density. This paper evaluates how conventional power converter components and emerging Gallium Nitride (GaN) technologies would fare at cryogenic temperatures. It is shown that GaN devices have a significant reduction in conduction losses at cryogenic temperatures. The behaviour of integrated circuits varies depending on device technology (CMOS, BJT, JFET), while temperature variation in capacitors depends on their dielectric material. © 2021 IEEE.

关键词： Wide band gap semiconductors

来源：评论

学校读者我要写书评

暂无评论

New Version of Fast Automatic Determination of Cluster Numbers for High Dimensional Big Data

New Version of Fast Automatic Determination of Cluster Numbe...

引用

International Conference on Computational science and Computational Intelligence (CSCI)

作者： Zohreh Safari Dept. Computer Science Math Engineerign Technology Elizabeth City State University Elizabeth City USA

The main issue in clustering algorithms is how to efficiently define number of clusters automatically. Considering both the quality of clustering and efficiency of clustering algorithm during determination of number of clusters can be a trade off that was our main purpose to overcome with. Successfully, In our approach the best number of clusters for a large data set of high dimensional data automatically would be determined with respect to clustering quality and efficiency. We carried out experimental studies on our five previous data sets [43]. and 4 new larger ones by which we found that our procedure has the flexibility of choosing different criteria to determine the optimal K under each of them. The procedure takes the advantages of Bisecting K-Means algorithm, and indicated higher efficiency compared with Ray & Turi method when it comes to find the best number of clusters.

关键词：

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：