检索结果-内蒙古大学图书馆

10th International Conference on Applied System Innovation, ICASI 2024

作者： Tu, Yu-Chen Wang, Hsuan-Chih Liu, Chien-Pin Hsieh, Chia-Yeh Chan, Chia-Tai National Yang Ming Chiao Tung University Department of Biomedical Engineering Taipei City112 Taiwan Bachelor's Program in Medical Informatics and Innovative Applications Fu Jen Catholic University New Taipei City242062 Taiwan

ISBN: (纸本)9798350394924

Fall incidents among the elderly represent a significant global concern, often resulting in physical injuries and psychological distress. It is crucial to develop reliable fall detection systems which are capable of identifying fall events immediately and triggering alerts for assistance. However, real-world fall occurrences are infrequent, leading to a highly imbalanced class situation. Training a model with imbalanced datasets may result in biased models with poor performance in fall detection. To address this challenge, various techniques such as data transformation and Synthetic Minority Oversampling Technique (SMOTE) have been proposed. However, these methods are constrained by issues such as limitations in input data size or sensitivity to outliers. Compared to other methods, variational autoencoder (VAE) can generate data with a similar probability distribution to the original input data while constraining the latent representation in a Gaussian distribution. This study proposes a VAE-based data augmentation method for wearable-based fall detection system. The proposed method is validated on the FallAllD public dataset, achieving a F-score of 99.46%. The performance has been increased by 2.21%. The results demonstrate the effectiveness of VAE-based data augmentation technique in enhancing fall detection systems and its superior performance compared with other traditional data augmentation methods. © 2024 IEEE.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Local Periodicity-Based Beat Tracking for Expressive Classical Piano Music

引用

IEEE/ACM Transactions on Audio Speech and Language Processing 2023年 31卷 2824-2835页

作者： Chiu, Ching-Yu Muller, Meinard Davies, Matthew E. P. Su, Alvin Wen-Yu Yang, Yi-Hsuan National Cheng Kung University Academia Sinica Graduate Program of Multimedia Systems and Intelligent Computing Tainan701401 Taiwan International Audio Laboratories Erlangen Erlangen91058 Germany University of Coimbra Department of Informatics Engineering Centre for Informatics and Systems Coimbra3004-531 Portugal National Cheng Kung University Department of Computer Science and Information Engineering Tainan701401 Taiwan Taiwan AI Labs Yating Music Team Taipei103622 Taiwan Academia Sinica Research Center for IT Innovation Taipei11529 Taiwan

To model the periodicity of beats, state-of-the-art beat tracking systems use 'post-processing trackers' (PPTs) that rely on several empirically determined global assumptions for tempo transition, which work well for music with a steady tempo. For expressive classical music, however, these assumptions can be too rigid. With two large datasets of Western classical piano music, namely the Aligned Scores and Performances (ASAP) dataset and a dataset of Chopin's Mazurkas (Maz-5), we report on experiments showing the failure of existing PPTs to cope with local tempo changes, thus calling for new methods. In this paper, we propose a new local periodicity-based PPT, called predominant local pulse-based dynamic programming (PLPDP) tracking, that allows for more flexible tempo transitions. Specifically, the new PPT incorporates a method called 'predominant local pulses' (PLP) in combination with a dynamic programming (DP) component to jointly consider the locally detected periodicity and beat activation strength at each time instant. Accordingly, PLPDP accounts for the local periodicity, rather than relying on a global tempo assumption. Compared to existing PPTs, PLPDP particularly enhances the recall values at the cost of a lower precision, resulting in an overall improvement of F1-score for beat tracking in ASAP (from 0.473 to 0.493) and Maz-5 (from 0.595 to 0.838). © 2014 IEEE.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Improvement of E-Nose Sensor Signal Using MVA, FFT, DWT Methods on Pineapple Fruit Maturity 6

Improvement of E-Nose Sensor Signal Using MVA, FFT, DWT Meth...

引用

6th International Conference on Information Technology, Information Systems and Electrical engineering, ICITISEE 2022

作者： Hasan, Mhd Arief Sarno, Riyanarto Ardani, M. Syauqi Hanif Intitut Teknologi Sepuluh Nopember Informatics Department Surabaya Indonesia Universitas Lancang Kuning Informatic Engineering Study Program Pekanbaru Indonesia

ISBN: (纸本)9798350399615

In this study, we built an Electronic Nose to detect pineapple ripeness. We designed a prototype E-Nose using a wooden crate. Inside the box, we built the E-Nose using 9 MQ sensor circuits connected to the Arduino Microcontroller. In the crate, we put an object, namely a pineapple with three levels of ripeness (ripe, half ripe, and unripe), each weighing 1kg placed in three different positions (5cm, 20cm, and 35cm) from the position of the sensor array (E-nose). We converted the signal output results into ppm units. We compared the value of each fruit signal based on the level of ripeness and distance using E-Nose. We used several signal processing methods (wavelets) for signal processing. Then, we improved the signal generated using wavelet. The wavelet methods used are Moving Average, Fast Fourier Transform (FFT), and Discrete Wavelet Transform (DWT). The contribution of this research is to see the influence of the signal valuegenerated from the sensor (MQ Sensor) to the position (distance) of the object (fruit) and its influence on the level of maturity (fruit). Then signalgenerated from the sensor we make improvements with the mva, fft, and dwt methods. © 2022 IEEE.

关键词： DWT E-Nose FFT MVA Pineapple

来源：评论

学校读者我要写书评

暂无评论

Evaluation of large language models for the classification of medical device software

引用

Bio-Design and Manufacturing 2024年第5期7卷 819-822页

作者： Yu Han Aaron Ceross Florence Bourgeois Paulo Savaget Jeroen H.M.Bergmann Department of Engineering Science University of OxfordOld Road CampusOxford OX37QDUK Harvard-MIT Center for Regulatory Science Harvard Medical SchoolBostonMAUSA Computational Health Informatics Program(CHIP) Boston Children’s HospitalBostonMAUSA Department of Technology and Innovation The University of Southern DenmarkOdenseDenmark

Amidst the rapidly expanding integration of large language models(LLMs)across various sectors(ranging from everyday applications to specialized fields demanding stringent regulatory adherence),our investigation seeks to determine how well these models can support medical device software *** device classification functions to systematically categorize devices according to their designated use,associated risk levels,and requisite regulatory oversight,thereby providing a structured framework for ensuring safety and efficacy as mandated by regulatory authorities.

关键词： everyday demanding thereby

来源：评论

学校读者我要写书评

暂无评论

Hybrid Classical-Quantum Optimization for Ensemble Learning 9

Hybrid Classical-Quantum Optimization for Ensemble Learning

引用

9th International Conference on Advanced informatics: Concepts, Theory and Applications, ICAICTA 2022

作者： Yulianti, Lenny Putri Santoso, Judhi Trisetyarso, Agung Surendro, Kridanto Bandung Institute of Technology School of Electrical Engineering and Informatics Bandung Indonesia Bina Nusantara University Program - Computer Science Bandung Indonesia

ISBN: (数字)9781665456685

ISBN: (纸本)9781665456685

Ensemble learning has gained attention due to its ability to improve predictive performance in classification and regression problems. However, there are several issues related to optimizing accuracy, diversity, and efficiency simultaneously in the ensemble learning process. Existing studies mostly focus on one or two of them, or focus on all three but only on the specific process of ensemble learning. Besides, the quantum approach has been expected to accelerate the optimization process while maintaining accuracy. The contribution of this study is to design a hybrid classical-quantum methodology for optimizing ensemble learning in a holistic way. This methodology combines classical (i.e. clustering, improved evaluation measures, and generalized weighted ensemble with internally tuned hyperparameters) and quantum (i.e. quantum annealing) approaches, and this methodology is analyzed to provide more optimal results. © 2022 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Ensuring Proper Interaction: VR-Based Visual Feedback Interface for Smart Walker Training

Ensuring Proper Interaction: VR-Based Visual Feedback Interf...

引用

IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob)

作者： Matheus Loureiro Fabiana Machado Ricardo Mello Anselmo Frizera Graduate Program in Electrical Engineering Federal University of Espírito Santo (UFES) Vitória ES Brazil Graduate Program in Informatics UFES

ISBN: (数字)9798350386523

ISBN: (纸本)9798350386530

Smart walkers are robotics devices that can be used to help people with mobility impairments due to aging, diseases, or injuries. However, this kind of device can be complex to use correctly due to the presence of numerous sensors. In this context, this paper presents a pilot study of a virtual reality-based visual feedback interface for training users of smart walkers. Ten volunteers were recruited and divided into two groups (Intervention Group and Control Group). The Intervention Group was provided with a visual feedback training interface, whereas the Control Group was provided with verbal feedback. With the training interface, the users were able to reduce their time of execution between 4% to 29% more than users without access to the interface. Our results indicate that the interface helps the user to understand some parameters of the device, reducing their repetition execution time during and after receiving the visual feedback.

关键词： Training Legged locomotion Visualization Biomechatronics Aging Robot sensing systems Intelligent sensors Injuries Diseases

来源：评论

学校读者我要写书评

暂无评论

Observing Generator Performance by Finite Element Analysis Considering Coil Numbers 5

Observing Generator Performance by Finite Element Analysis C...

引用

5th International Conference on Technology and Policy in Energy and Electric Power, ICT-PEP 2023

作者： Habibi, Muhammad Afnan Ali Irfani, Mochamad Farhan Gumilar, Langlang Kusumawardana, Arya Aripriharta Baskoro, Angger Universitas Negeri Malang Study Program of Power Plant Engineering Technology Malang Indonesia Universitas Negeri Malang Department of Electrical Engineering and Informatics Malang Indonesia National Yang Ming Chiao Tung University Dept. Electrical Engineering and Computer Sciences Hsinchu Taiwan

ISBN: (纸本)9798350369717

This paper conducts a comprehensive analysis of electrical generator performance using Finite Element Analysis (FEA), with a specific emphasis on the role of coil numbers in influencing generator efficiency and functionality. In the context of modern energy systems, where efficient power generation is paramount, this research aims to elucidate the relationship between the number of coils within a generator and its overall performance, including power output and electromagnetic behavior. Through systematic FEA simulations that vary coil numbers while keeping other parameters constant, this study provides valuable insights into the trade-offs associated with increased coil numbers and enhanced efficiency. These findings have significant implications for optimizing generator designs across various applications, from renewable energy systems to industrial power generation, ultimately advancing our understanding of generator dynamics and contributing to more sustainable and efficient power generation technologies. © 2023 IEEE.

关键词： Finite element method

来源：评论

学校读者我要写书评

暂无评论

Effective preprocessed thin blood smear images to improve malaria parasite detection using deep learning 2

Effective preprocessed thin blood smear images to improve ma...

引用

2nd Annual Conference of Science and Technology, ANCOSET 2020

作者： Swastika, W. Kristianti, G.M. Widodo, R.B. Informatics Engineering Study Program Universitas Ma Chung Malang Indonesia

Malaria can be difficult to detect from thin blood smears. Image recognition methods such as convolutional neural network can be used to detect malaria, but the training process takes a long time. Previous research created a new architecture and compares it to several other architectures such as VGG-16 and ResNet. The effect of preprocessing is analyzed in this research. VGG-16, ResNet, and the custom architecture created by the previous research are being used in this study. The preprocessing methods being analyzed in this research include gray-world normalization and comprehensive normalization. The highest accuracy improvement per epoch (0.5256% using ResNet-50 and 0.0352% using custom architecture) is achieved through gray-world normalization, that also improves final accuracy (90.1% using ResNet-50 and 93.1% using custom architecture) when compared to other methods with the same epochs for ResNet and custom architecture. © Published under licence by IOP Publishing Ltd.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Unveiling Factors Affecting Intentions to Use ChatGPT: Perspectives from Indonesian Higher Education Students

Unveiling Factors Affecting Intentions to Use ChatGPT: Persp...

引用

International Conference on informatics and Computing (ICIC)

作者： Zaenal Abidin Kongkiti Phusavat Riza Arifudin Endang Sugiharti Study Program of Informatics Engineering Universitas Negeri Semarang Semarang Indonesia Industrial Enginering Faculty of Engineering Kasetsart University Bangkok Thailand

ISBN: (数字)9798331517601

ISBN: (纸本)9798331517618

ChatGPT has generated significant interest and discussion within the academic community since its initial introduction. This study aims to investigate the students’ intentions to use ChatGPT for educational purposes in higher education. A proposed conceptual model based on the unified theory of acceptance and use of technology model-2 (UTAUT2) was employed in this current study. A total of 575 data obtained from a questionnaire survey of higher education students were analyzed using partial least square-structural equation modeling (PLS-SEM). The results of the hypothesis testing revealed that both cognitive attitude and emotional attitude have a significant influence on the intention to use ChatGPT. The cognitive attitude was influenced by performance expectancy and effort expectancy. Affective attitudes were shaped by factors such as novelty value, performance expectancy, hedonic motivation, and effort expectancy.

关键词： Surveys Analytical models Education Position measurement Chatbots Mathematical models Data models informatics Testing

来源：评论

学校读者我要写书评

暂无评论

Selection of Education Assistance Recipients Based on AHP and SAW 23

Selection of Education Assistance Recipients Based on AHP an...

引用

23rd International Seminar on Intelligent Technology and Its Applications, ISITIA 2022

作者： Pranoto, Gatot Tri Pebrianti, Dwi Darwis, Muhammad Yaddarabullah Krishnasari, Erneza Dewi Pelita Bangsa University Informatics Engineering Study Program Bekasi Indonesia Budi Luhur University Computer Science Jakarta Indonesia Universitas Trilogi Department of Informatics Engineering Jakarta Indonesia Universitas Trilogi Department of Visual Communication Design Jakarta Indonesia

ISBN: (数字)9781665460811

ISBN: (纸本)9781665460811

The final decision of the educational assistance recipient in GNOTA Foundation, Jakarta is still processed manually. They usually only look at the father's occupation criteria without looking at other criteria such as the age of the child, the child's orphan status, the occupation of mother, the age of father, the age of mother and other scholarships received. GNOTA Foundation needs to implement a Decision Support System (DSS) for the selection process, so the results are fast and on target. This research applies the Analytical Hierarchy Process (AHP) and Simple Additive Weighting (SAW) methods for the selection of education assistance recipients so the criteria can be weighted and the prospective recipient students can be ranked. This research determines the priority weight and importance of each criterion, namely the age of child age (0.18), the status of child (0.22), the occupation of father (0.08), the occupation of mother (0.06), the age of father (0.05), the age of mother (0.04) and other scholarship assistance (0.36). The results of the weighting of these criteria have been tested and declared consistent through the Consistency Ratio (CR) value of 0.070. This study also produces a list of the best ranking students who are prospective recipients of educational assistance. The ranking results have been tested based on compliance with the provisions of the GNOTA Foundation of 92.91%. The system in this study was developed using a prototyping system development model and utilizing the Unified Modeling Language (UML) tool. The prototype functionality in this study works well by using the Blackbox Testing (BBT) model based on Equivalence Partitioning. In addition, the level of user acceptance of the prototype in this study was 81.2% using the Technology Acceptance Method (TAM). © 2022 IEEE.

关键词： Decision support 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：