检索结果-内蒙古大学图书馆

Under the Cover Infant Pose Estimation using Multimodal Data

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Kyrollos, Daniel G. Fuller, Anthony Greenwood, Kim Harrold, JoAnn Green, James R. Carleton University Biomedical Informatics Collaboratory Department of Systems and Computer Engineering Carleton University Ottawa Canada The Department of Clinical Engineering Children’s Hospital of Eastern Ontario Ottawa Canada The Department of Neonatology Children’s Hospital of Eastern Ontario Ottawa Canada

Infant pose monitoring during sleep has multiple applications in both healthcare and home settings. In a healthcare setting, pose detection can be used for region of interest detection and movement detection for noncontact based monitoring systems. In a home setting, pose detection can be used to detect sleep positions which has shown to have a strong influence on multiple health factors. However, pose monitoring during sleep is challenging due to heavy occlusions from blanket coverings and low lighting. To address this, we present a novel dataset, Simultaneously-collected multimodal Mannequin Lying pose (SMaL) dataset, for under the cover infant pose estimation. We collect depth and pressure imagery of an infant mannequin in different poses under various cover conditions. We successfully infer full body pose under the cover by training state-of-art pose estimation methods and leveraging existing multimodal adult pose datasets for transfer learning. We demonstrate a hierarchical pretraining strategy for transformer-based models to significantly improve performance on our dataset. Our best performing model was able to detect joints under the cover within 25mm 86% of the time with an overall mean error of 16.9mm. Data, code and models publicly available at https://***/DanielKyr/SMaL © 2022, CC BY.

关键词： Sleep research

Optimized Three Deep Learning Models Based-PSO Hyperparameters for Beijing PM2.5 Prediction

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Pranolo, Andri Mao, Yingchi Wibawa, Aji Prasetya Utama, Agung Bella Putra Dwiyanto, Felix Andika Department of Computer and Technology College of Computer and Information Hohai University 1 Xikang Road Jiangsu Nanjing211100 China Department of Informatics Faculty of Industrial Technology Universitas Ahmad Dahlan Jl. Prof. Dr. Soepomo S.H. Janturan Warungboto Umbulharjo Yogyakarta55164 Indonesia Department of Electrical Engineering Faculty of Engineering Universitas Negeri Malang Jl Semarang 5 East Java Malang65145 Indonesia

Deep learning is a machine learning approach that produces excellent performance in various applications, including natural language processing, image identification, and forecasting. Deep learning network performance depends on the hyperparameter settings. This research attempts to optimize the deep learning architecture of Long short term memory (LSTM), Convolutional neural network (CNN), and Multilayer perceptron (MLP) for forecasting tasks using Particle swarm optimization (PSO), a swarm intelligence-based metaheuristic optimization methodology: Proposed M-1 (PSO-LSTM), M-2 (PSO-CNN), and M-3 (PSO-MLP). Beijing PM2.5 datasets was analyzed to measure the performance of the proposed models. PM2.5 as a target variable was affected by dew point, pressure, temperature, cumulated wind speed, hours of snow, and hours of rain. The deep learning network inputs consist of three different scenarios: daily, weekly, and monthly. The results show that the proposed M-1 with three hidden layers produces the best results of RMSE and MAPE compared to the proposed M-2, M-3, and all the baselines. A recommendation for air pollution management could be generated by using these optimized models. © 2023, CC BY-SA.

关键词： Forecasting

Multicell converters for energy efficient power supplies in the ICT industry 12

学校读者我要写书评

暂无评论

Multicell converters for energy efficient power supplies in ...

12th Mediterranean Conference on Power Generation, Transmission, Distribution and Energy Conversion, MEDPOWER 2020

作者： Chrysostomou, Michael Christofides, Nicholas Ioannou, Stelios Polycarpou, Alexis Frederick University Department of Electrical Engineering Computer Engineering and Informatics Y. Frederickou Str. Nicosia Cyprus University of Central Lancashire Electrical and Computer Engineering dept. Pyla Cyprus

ISBN: (纸本)9781839535635

The introduction of 5G technology in the telecommunications sector requires multiple base stations and micro-datacentres to serve the increased network speeds and latency requirements. As a result, this has led to a huge increase in the power requirements and consequently in the energy consumption. To meet the increased power requirements for the 5G ICT equipment, new high power and high efficiency power supplies should be sought in an attempt to retain the increase in energy and running costs. The work analyses how power supply systems in multicell structures can contribute to the problem. A new multicell structure is proposed and simulated in PSIM’s thermal module. It is proven that using multicell structures, high efficiency at varying load levels can be achieved. © 2020 Institution of engineering and Technology. All rights reserved.

关键词： 5G mobile communication systems

Word-Sequence Entropy: Towards Uncertainty Estimation in Free-Form Medical Question Answering Applications and Beyond

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Zhiyuan Duan, Jinhao Yuan, Chenxi Chen, Qingyu Chen, Tianlong Zhang, Yue Wang, Ren Shi, Xiaoshuang Xu, Kaidi Center for Future Media School of Computer Science and Engineering University of Electronic Science and Technology of China Sichuan Chengdu611731 China Department of Computer Science Drexel University PhiladelphiaPA19104 United States Perelman School of Medicine University of Pennsylvania PhiladelphiaPA19104 United States Section of Biomedical Informatics & Data Science Yale School of Medicine Yale University New HavenCT06510 United States Computer Science & Artificial Intelligence Laboratory Massachusetts Institute of Technology CambridgeMA02139 United States Department of Electrical and Computer Engineering Illinois Institute of Technology ChicagoIL60616 United States

Uncertainty estimation is crucial for the reliability of safety-critical human and artificial intelligence (AI) interaction systems, particularly in the domain of healthcare engineering. However, a robust and general uncertainty measure for free-form answers has not been well-established in open-ended medical question-answering (QA) tasks, where generative inequality introduces a large number of irrelevant words and sequences within the generated set for uncertainty quantification (UQ), which can lead to biases. This paper introduces Word-Sequence Entropy (WSE), a method that calibrates uncertainty at both the word and sequence levels, considering semantic relevance. WSE quantifies uncertainty in a way that is more closely aligned with the reliability of LLMs during uncertainty quantification (UQ). We compare WSE with six baseline methods on five free-form medical QA datasets, utilizing seven popular large language models (LLMs). Experimental results demonstrate that WSE exhibits superior performance in UQ under two standard criteria for correctness evaluation. Additionally, in terms of real-world medical QA applications, the performance of LLMs is significantly enhanced (e.g., a 6.36% improvement in model accuracy on the COVID-QA dataset) by employing responses with lower uncertainty that are identified by WSE as final answers, without any additional task-specific fine-tuning or architectural modifications. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

Personalizing text summarization based on sentence weighting

学校读者我要写书评

暂无评论

Personalizing text summarization based on sentence weighting

2007 IADIS European Conference on Data Mining, DM 2007, part of the 1st IADIS Multi Conference on computer Science and Information Systems, MCCSIS 2007

作者： Bouras, Christos Poulopoulos, Vassilis Tsogkas, Vassilis Research Academic Computer Technology Institute Computer Engineering and Informatics Department University of Patras N. Kazantzaki Str. Rion26500 Greece

ISBN: (纸本)9789728924409

The amount of data that exists on the Internet is enormous enough to distract users when trying to find useful information. In addition, the expansive use of small screen devices for browsing the World Wide Web generates huge problems when trying to find and read information. A solution to these problems is to personalize the web and try to reduce algorithmically the amount of text. Many text summarizers have been presented in order to reduce the valueless information that is presented to the users and many web sites, especially news portals, introduce personalization features for the users, though, still these techniques are not often used in combination in order to create more effective results. In this paper a mechanism for creating personalized summaries for the members of a news portal that reproduces articles collected from major portals is presented, together with evaluation both of the summarizer and the personalized summaries. The evaluators of the personalized summaries are members of the news portal. The personalized summary mechanism can also be utilized by users of small screen devices, for easier reading of less but inclusive information. © 2007 IADIS

关键词： Text processing

Massive Access of Static and Mobile Users via Reconfigurable Intelligent Surfaces: Protocol Design and Performance Analysis

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Cao, Xuelin Yang, Bo Huang, Chongwen Alexandropoulos, George C. Yuen, Chau Han, Zhu Vincent Poor, H. Hanzo, Lajos The School of Cyber Engineering Xidian University Xi’an710071 China The Engineering Product Development Pillar Singapore University of Technology and Design 487372 Singapore College of Information Science and Electronic Engineering Zhejiang University Hangzhou310027 China International Joint Innovation Center Zhejiang University Haining314400 China Hangzhou310027 China The Department of Informatics and Telecommunications National and Kapodistrian University of Athens Athens15784 Greece The Department of Electrical and Computer Engineering The University of Houston HoustonTX77004 United States The Department of Computer Science and Engineering Kyung Hee University Seoul446-701 Korea Republic of The Department of Electrical and Computer Engineering Princeton University PrincetonNJ08544 United States The School of Electronics and Computer Science University of Southampton SouthamptonSO17 1BJ United Kingdom

The envisioned wireless networks of the future entail the provisioning of massive numbers of connections, heterogeneous data traffic, ultra-high spectral efficiency, and low latency services. This vision is spurring research activities focused on defining a next generation multiple access (NGMA) protocol that can accommodate massive numbers of users in different resource blocks, thereby, achieving higher spectral efficiency and increased connectivity compared to conventional multiple access schemes. In this article, we present a multiple access scheme for NGMA in wireless communication systems assisted by multiple reconfigurable intelligent surfaces (RISs). In this regard, considering the practical scenario of static users operating together with mobile ones, we first study the interplay of the design of NGMA schemes and RIS phase configuration in terms of efficiency and complexity. Based on this, we then propose a multiple access framework for RIS-assisted communication systems, and we also design a medium access control (MAC) protocol incorporating RISs. In addition, we give a detailed performance analysis of the designed RIS-assisted MAC protocol. Our extensive simulation results demonstrate that the proposed MAC design outperforms the benchmarks in terms of system throughput and access fairness, and also reveal a trade-off relationship between the system throughput and fairness. © 2023, CC BY.

关键词： Medium access control

Personalized Meal Planning in Inpatient Clinical Dietetics Using Generative Artificial Intelligence: System Description

学校读者我要写书评

暂无评论

Personalized Meal Planning in Inpatient Clinical Dietetics U...

IEEE International Conference on Healthcare informatics (ICHI)

作者： Leon Kopitar Gregor Stiglic Leon Bedrac Jiang Bian Faculty of Health Sciences Faculty of Electrical Engineering and Computer Science University of Maribor Maribor Slovenia Faculty of Health Sciences University of Maribor Maribor Slovenia The NU B.V. Leiden The Netherlands Department of Health Outcomes and Biomedical Informatics College of Medicine University of Florida FL USA

ISBN: (数字)9798350383737

ISBN: (纸本)9798350383744

This study addresses the limitations of traditional prescribed meal plans, which lack personalization and often prove monotonous and challenging for patients to follow. We propose a novel approach employing generative artificial intelligence in the context of a learning health system, with an emphasis on inpatient clinical dietetics. The system incorporates two key models: the Meal Plan Generation Model, MeaIGM, and the Meal Plan Image Generation Model, MealImageGM, leveraging state-of-the-art large language models. Patient information from electronic health records and clinical dietetics guidelines are incorporated into prompts for MeaIGM, which is refined through nutritionist validations and users' feedback. On the other hand, MealImageGM generates visual representations of meal plans to enhance patient engagement, utilizing crowd-sourced feedback to optimize image generation prompts. The overall system process includes extracting data from electronic health records, pre-designed user meal generation prompts, and the generation of personalized meal plans and images. Nutritionists play a crucial role in monitoring patient adherence and preferences, contributing to a continuous learning health system cycle. The proposed framework ensures clinically appropriate and personalized meal plans, aligning with dynamic dietary recommendations. The study emphasizes the importance of patient-physician co-creation for constant optimization and highlights the potential positive impact on health outcomes.

关键词： Visualization Image synthesis Generative AI Medical services Learning (artificial intelligence) Planning Electronic medical records

Efficient Self-Learning Evolutionary Neural Architecture Search

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Qiu, Zhengzhong Bi, Wei Xu, Dong Guo, Hua Ge, Hongwei Liang, Yanchun Lee, Heow Pueh Wu, Chunguo Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education College of Computer Science and Technology Jilin University Jilin Changchun130012 China YGSOFT INC Guangdong Zhuhai519085 China Department of Electrical Engineering and Computer Science Informatics Institute Christopher S. Bond Life Sciences Center University of Missouri ColumbiaMO65211 United States College of Computer Science and Technology Dalian University of Technology Liaoning Dalian116081 China School of Computer Science Zhuhai College of Science and Technology Guangdong Zhuhai519041 China Department of Mechanical Engineering National University of Singapore 9 Engineering Drive 1 117575 Singapore

The evolutionary algorithm has become a major method for neural architecture search recently. However, the fixed probability distribution adopted by the traditional evolutionary algorithm makes the algorithm unable to control the increase or decrease of the individual architecture size and thus cannot guarantee the lightweight and inference efficiency of the candidate architecture. In addition, the existing approaches cannot learn the optimal sampling probability distribution relevant to the specific problem from the empirical information accumulated through the search process. What’s more, the algorithm needs to evaluate the performance of all the individual architectures, which requires huge computing resources and time overhead. To overcome these problems and challenges, an Efficient Self-learning Evolutionary Neural Architecture Search method, called ESE-NAS, is presented in this paper. Firstly, we propose a Model Size Control module, which generates the probability distribution for sampling the type of mutation operators according to the current model size, so as to control both the node number of network architecture and the sparsity of links, therefore ensuring that neural architectures can remain compact and efficient as they evolve. Thereafter, a Mutation Candidate Credit Assignment method is proposed, which enables the algorithm to dynamically adjust the probability distribution for available types of node operations and directed links according to the empirical information from individuals’ performance evaluation, which can guide the evolutionary direction of neural architecture and shorten the first hitting time of the optimal architecture. Finally, a neural architecture performance predictor is formulated, and the accuracy of each individual architecture is predicted by using the simplified input features, to further improve the efficiency of neural architecture search. Experiments show that the ESE-NAS method proposed in this paper can learn a highly i

关键词： Evolutionary algorithms

Improving WiFi Fingerprint Database With Irregular Distribution of Reference Points Using Interpolation Methods

学校读者我要写书评

暂无评论

Improving WiFi Fingerprint Database With Irregular Distribut...

International Conference on Advanced Technologies for Communications, ATC

作者： Trung Vu-Thanh Jing He Ninh Duong-Bao Seon-Woo Lee Luong Nguyen Thi Khanh Nguyen-Huu College of Computer Science and Electronic Engineering Hunan University Changsha China Faculty of Mathematics and Informatics Dalat University Dalat Vietnam Division of Software Hallym University Chuncheon Korea Faculty of Information Technology Dalat University Dalat Vietnam Department of Electronics and Telecommunications Dalat University Dalat Vietnam

ISBN: (数字)9798350353983

ISBN: (纸本)9798350353990

Using WiFi Fingerprinting for indoor positioning is becoming increasingly popular due to its cost-effectiveness. However, to ensure the system can operate with high accuracy and stability, this technique requires a burden of data collection tasks from a dense distribution of reference points (RPs). To decrease the cost of data collection, as well as to improve the WiFi fingerprint database with irregular distribution of RPs, this study applies and compares different interpolation methods. Evaluating these methods in a public dataset including multiple sub-datasets with irregular distributions of RPs, the results highlight the Linear Barycentric interpolation (LB) as the most favorable method due to its low complexity and stable performance. The LB-based fingerprint database achieves an average interpolation error of less than 3 dBm compared to the original one. When applying the interpolated database to positioning tasks, it can help reduce acquisition costs by up to 50% while improving positioning accuracy by up to 11%. The study reveals the feasibility of interpolation in optimizing WiFi fingerprint data collection, especially in large and complex environments where regular distribution of RPs cannot be deployed.

关键词： Interpolation Costs Accuracy Databases Fingerprint recognition Data collection Reliability Computational complexity Wireless fidelity Floors