检索结果-内蒙古大学图书馆

International Conference on AeroSpace Science and Technology 2023, ICASST 2023

作者： García-Guillén, L.A. Sanchéz-Sanchéz, J.L. Ramírez-Aguilar, J.A. Ferrer-Pérez, J.A. Romo-Fuentes, J.C. Farah-Simón, A. Chávez-Moreno, R.G. Sánchez Hernández, D.C. Sánchez-Guzmán, J.A. Valdés-Galicia, J.F. Master's and Doctorate Programm in Engineering Engineering Faculty Universidad Nacional Autónoma de México CDMX Mexico Bachelor's in Aero Systems Electronics Engineering Universidad Aeronáutica en Querétaro Queretaro Mexico Advanced Technology Unit School of Engineering UNAM Queretaro Juriquilla Mexico Astronomy Institute Universidad Nacional Autónoma de México CDMX Mexico Faculty of Informatics Autonomous University of Queretaro Queretaro Juriquilla Mexico Space Program University Universidad Nacional Autónoma de México CDMX Mexico

A trend in the development of nanosatellite platforms for technology demonstration has increased in both private industry and academic projects. Communication link design plays a crucial role in the success of space missions, enabling efficient and reliable data transmission between satellites and ground stations. In this context, the use of advanced tools such as System Tool Kit (STK) has gained significant importance by enabling a comprehensive analysis of the technical and operational aspects of the communication link. In an effort to make the future design of the communications subsystem payload on a nanosatellite more efficient and accessible, this paper shows a methodology for the efficient use of STK to perform link analysis. © Published under licence by IOP Publishing Ltd.

关键词： Nanosatellites

来源：评论

学校读者我要写书评

暂无评论

High-Capacity Double-Layer Data Hiding Technique Based on 3D Magic Cube 25th

High-Capacity Double-Layer Data Hiding Technique Based on 3D...

引用

25th International Computer Symposium on New Trends in Computer Technologies and Applications, ICS 2022

作者： Weng, Hao-Yu Tsai, Min-Yi Wang, Wei-Jen Huang, Cheng-Ta Department of Computer Science and Information Engineering National Central University Taoyuan City320 Taiwan Department of Information Management Yuan Ze University Taoyuan City320 Taiwan International Bachelor Program in Informatics Yuan Ze University Taoyuan City320 Taiwan

ISBN: (纸本)9789811995811

Information technology and the Internet have progressed rapidly in people’s lives, the privacy of information has become an important issue due to the accessibility of data. Therefore, to enhance information security and privacy protection, this paper proposes a new high-capacity method for data hiding. The proposed method is based on 3D magic cube with double layers embedding. In the field of data hiding, the reference matrix-based methods attract many researchers because of its high-capacity. Recently, as the needs of the high payloads of the stego-image, the multi-layers-based technique is applied to provide larger embedding capacity. However, the image after data embedding will cause serious distortions, especially on multi-layers embedding, hence, keeping the image at a good visual quality and achieving high-payloads are the main challenges for data hiding. In this scheme, we take advantage of 3D magic cube and 3D reference space with double layers embedding for our data hiding technique to improve the embedding payloads. The experimental results show that our method not only provides good embedding capacity (4.00 bpp) but also keeps the image at acceptable quality (In terms of PSNR > 30). © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

A VAE-Based Data Augmentation Method for Fall Detection System using Wearable Sensor

A VAE-Based Data Augmentation Method for Fall Detection Syst...

引用

International Conference on Applied System Innovation (ICASI)

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

ISBN: (数字)9798350394924

ISBN: (纸本)9798350394931

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.

关键词： Training Technological innovation Sensitivity Psychology Data augmentation Probability distribution Reliability

来源：评论

学校读者我要写书评

暂无评论

PREFALLKD: PRE-IMPACT FALL DETECTION VIA CNN-VIT KNOWLEDGE DISTILLATION

arXiv

引用

arXiv 2023年

作者： Chi, Tin-Han Liu, Kai-Chun Hsieh, Chia-Yeh Tsao, Yu Chan, Chia-Tai Department of Biomedical Engineering National Yang Ming Chiao Tung University Taiwan Research Center for information Technology Innovation Academia Sinica Taiwan Bachelor’s Program in Medical Informatics and Innovative Applications Fu Jen Catholic University Taiwan

Fall accidents are critical issues in an aging and aged society. Recently, many researchers developed "pre-impact fall detection systems" using deep learning to support wearable-based fall protection systems for preventing severe injuries. However, most works only employed simple neural network models instead of complex models considering the usability in resource-constrained mobile devices and strict latency requirements. In this work, we propose a novel pre-impact fall detection via CNN-ViT knowledge distillation, namely PreFallKD, to strike a balance between detection performance and computational complexity. The proposed PreFallKD transfers the detection knowledge from the pre-trained teacher model (vision transformer) to the student model (lightweight convolutional neural networks). Additionally, we apply data augmentation techniques to tackle issues of data imbalance. We conduct the experiment on the KFall public dataset and compare PreFallKD with other state-of-the-art models. The experiment results show that PreFallKD could boost the student model during the testing phase and achieves reliable F1-score (92.66%) and lead time (551.3 ms). Copyright © 2023, The Authors. All rights reserved.

关键词： Fall detection

来源：评论

学校读者我要写书评

暂无评论

Prefallkd: Pre-Impact Fall Detection Via CNN-ViT Knowledge Distillation

Prefallkd: Pre-Impact Fall Detection Via CNN-ViT Knowledge D...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Tin-Han Chi Kai-Chun Liu Chia-Yeh Hsieh Yu Tsao Chia-Tai Chan Department of Biomedical Engineering National Yang Ming Chiao Tung University Taiwan Research Center for Information Technology Innovation Academia Sinica Taiwan Bachelor’s Program in Medical Informatics and Innovative Applications Fu Jen Catholic University Taiwan

关键词： Computational modeling System performance Aging Transformers Reliability Fall detection Usability

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning for Keypoint Detection in Low-Resolution Thermal TUG Test Images

arXiv

引用

arXiv 2025年

作者： Chen, Wei-Lun Hsieh, Chia-Yeh Kao, Yu-Hsiang Liu, Kai-Chun Peng, Sheng-Yu Tsao, Yu Research Center for Information Technology Innovation Academic Sinica Taiwan Graduate Institute of Electrical Engineering National Taiwan University Taiwan Bachelor’s Program in Medical Informatics and Innovative Applications Fu Jen Catholic University Taiwan Department of Electrical Engineering National Taiwan University Taiwan College of Information and Computer Sciences University of Massachusetts AmherstMA01003 United States Department of Electrical Engineering National Taiwan University of Science of Technology Taiwan

This study presents a novel approach to human keypoint detection in low-resolution thermal images using transfer learning techniques. We introduce the first application of the Timed Up and Go (TUG) test in thermal image computer vision, establishing a new paradigm for mobility assessment. Our method leverages a MobileNetV3-Small encoder and a ViTPose decoder, trained using a composite loss function that balances latent representation alignment and heatmap accuracy. The model was evaluated using the Object Keypoint Similarity (OKS) metric from the COCO Keypoint Detection Challenge. The proposed model achieves better performance with AP, AP50, and AP75 scores of 0.861, 0.942, and 0.887 respectively, outperforming traditional supervised learning approaches like Mask R-CNN and ViTPose-Base. Moreover, our model demonstrates superior computational efficiency in terms of parameter count and FLOPS. This research lays a solid foundation for future clinical applications of thermal imaging in mobility assessment and rehabilitation monitoring. Copyright © 2025, The Authors. All rights reserved.

关键词： Thermography (imaging)

来源：评论

学校读者我要写书评

暂无评论

AI in Industry: Real-World Applications and Case Studies

TechRxiv

引用

TechRxiv 2023年

作者： Rahmaniar, Wahyu Maarif, Alfian ul Haq, Qazi Mazhar Iskandar, Muchammad Edo Institute of Innovative Research Tokyo Institute of Technology Kanagawa226-8503 Japan Department of Electrical Engineering Universitas Ahmad Dahlan Yogyakarta55166 Indonesia International Bachelor Program in Informatics and Computer Science Yuan Ze University Taoyuan320315 Taiwan Ezy Industries Jakarta Indonesia

Artificial intelligence (AI) has advanced rapidly and is becoming a cornerstone technology that drives innovation and efficiency in various industries. This paper examines the real-world application of AI in multiple sectors, including healthcare, finance, agriculture, retail, energy, and automotive. Several case studies are described to understand better the practical applications, results, and challenges of implementing AI. While many industries have reaped enormous benefits from AI, inherent challenges include data privacy, the potential for bias, and the continuing demand for skilled labor. This comprehensive review aims to provide AI application insights to professionals and researchers. Thus, as AI grows, there may be challenges and avenues for future research. © 2023, CC BY.

关键词： Agriculture

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Fall Detection Algorithm Using Ensemble Model of Coarse-fine CNN and GRU Networks

Deep Learning-based Fall Detection Algorithm Using Ensemble ...

引用

IEEE International Workshop on Medical Measurement and Applications (MEMEA)

作者： Chien-Pin Liu Ju-Hsuan Li En-Ping Chu Chia-Yeh Hsieh Kai-Chun Liu Chia-Tai Chan Yu Tsao Department of Biomedical Engineering National Yang Ming Chiao Tung University Taipei City Taiwan Bachelor’s Program in Medical Informatics and Innovative Applications Fu Jen Catholic University New Taipei City Taiwan Research Center for Information Technology Innovation Academia Sinica Taipei City Taiwan

Falls are the public health issue for the elderly all over the world since the fall-induced injuries are associated with a large amount of healthcare cost. Falls can cause serious injuries, even leading to death if the elderly suffers a “long-lie.” Hence, a reliable fall detection (FD) system is required to provide an emergency alarm for first aid. Due to the advances in wearable device technology and artificial intelligence, some fall detection systems have been developed using machine learning and deep learning methods to analyze the signal collected from accelerometer and gyroscopes. In order to achieve better fall detection performance, an ensemble model that combines a coarse-fine convolutional neural network and gated recurrent unit is proposed in this study. The parallel structure design used in this model restores the different grains of spatial characteristics and capture temporal dependencies for feature representation. This study applies the FallAllD public dataset to validate the reliability of the proposed model, which achieves a recall, precision, and F-score of 92.54%, 96.13%, and 94.26%, respectively. The results demonstrate the reliability of the proposed ensemble model in discriminating falls from daily living activities and its superior performance compared to the state-of-the-art convolutional neural network long short-term memory (CNN-LSTM) for FD.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Fall Detection Algorithm Using Ensemble Model of Coarse-fine CNN and GRU Networks

arXiv

引用

arXiv 2023年

作者： Liu, Chien-Pin Li, Ju-Hsuan Chu, En-Ping Hsieh, Chia-Yeh Liu, Kai-Chun Chan, Chia-Tai Tsao, Yu Department of Biomedical Engineering National Yang Ming Chiao Tung University Taipei112 Taiwan Bachelor's Program in Medical Informatics and Innovative Applications Fu Jen Catholic University New Taipei242062 Taiwan Research Center for Information Technology Innovation Academia Sinica Taipei115 Taiwan

Falls are the public health issue for the elderly all over the world since the fall-induced injuries are associated with a large amount of healthcare cost. Falls can cause serious injuries, even leading to death if the elderly suffers a "long-lie." Hence, a reliable fall detection (FD) system is required to provide an emergency alarm for first aid. Due to the advances in wearable device technology and artificial intelligence, some fall detection systems have been developed using machine learning and deep learning methods to analyze the signal collected from accelerometer and gyroscopes. In order to achieve better fall detection performance, an ensemble model that combines a coarse-fine convolutional neural network and gated recurrent unit is proposed in this study. The parallel structure design used in this model restores the different grains of spatial characteristics and capture temporal dependencies for feature representation. This study applies the FallAllD public dataset to validate the reliability of the proposed model, which achieves a recall, precision, and F-score of 92.54%, 96.13%, and 94.26%, respectively. The results demonstrate the reliability of the proposed ensemble model in discriminating falls from daily living activities and its superior performance compared to the state-of-the-art convolutional neural network long short-term memory (CNN-LSTM) for FD. Copyright © 2023, The Authors. All rights reserved.

关键词： Fall detection

来源：评论

学校读者我要写书评

暂无评论

Entropy and information gain analysis on low cost BCI for motorbike users to prevent accident 4

Entropy and information gain analysis on low cost BCI for mo...

引用

4th International Conference on Information Technology, Information Systems and Electrical engineering, ICITISEE 2019

作者： Awangga, Rolly Maulana Pane, Syafrial Fachri Majesty, Dinda Setiawan, Asep Asyhari, Moch Yusuf Applied Bachelor Program of Informatics Engineering Politeknik Pos Indonesia Bandung Indonesia Universitas Islam Indonesia Magister Program of Informatics Engineering Yogyakarta Indonesia

ISBN: (纸本)9781728151182

The phenomenon of mothers giving the wrong vehicle signal lights to turn left and right reminds the effect of giving the right signal lights to other road users. Weak human concentration while driving can cause errors when giving vehicle signal lights or not giving vehicle signal lights. Mistakes when giving a signal light a vehicle has a risk of an accident. The driver's brain wave data will show the results of the rider's brain thinking when turning. This study aims to analyze the concentration of the driver when driving. This research will obtain driver brain wave data when driving and analyze human brain waves while riding a motorcycle, especially when turning left and right, to reduce the risk of accidents while driving. The driver will use brain waves tool while driving, and the computer will detect the driver's brain waves, and then send brainwave data to the computer. Driver brain waves are analyzed using the formula entropy and gain. The results of the driver's brain waves become a decision whether the driver is allowed to drive on the highway based on the detected waves (alpha, beta, gamma, theta, and delta) to reduce the chance of an accident. © 2019 IEEE.

关键词： Entropy

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：