检索结果-内蒙古大学图书馆

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Ilaria Siviero Florian Helmhold Andreas M. Ray Carlos Bibián Gloria Menegaz Ander Ramos Murguialday Silvia F. Storti Dept. of Computer Science University of Verona Verona Italy Inst. of Medical Psychology and Behavioral Neurobiology University of Tübingen Tübingen Germany GTC of Neuroscience / IMPRS for Cognitive and Systems Neuroscience Tübingen Germany Dept. of Engineering for Innovation Medicine University of Verona Verona Italy TECNALIA Basque Research and Technology Alliance San Sebastian Spain Dept. of Neurology and Stroke University of Tübingen Tübingen Germany Athenea Neuroclinics San Sebastian Spain

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

technology for motor rehabilitation faces challenges in uncontrolled settings, such as at home. In these real-world scenarios, robust signals like electromyographic (EMG) and inertial measurement unit (IMU) data are crucial for decoding continuous human actions. Classical modeling methods, such as linear, adaptive, or static filters, lack the capacity to capture complex relationships between surface EMG and kinematics, as well as generalizability across subjects. We propose a deep learning (DL) model for the continuous decoding of hand motion. Custom-made wearable devices acquired EMG-IMU data from 27 healthy subjects performing a wrist flexion/extension task. Two regression models were compared with a hybrid convolutional neural network and a gated recurrent unit. To address inter-subject variability, a leave-one-subject-out cross-validation approach was implemented. The DL model showed a mean R 2 increase of 0.18 compared to the polynomial regressor. Our approach enhances wrist kinematics decoding providing a generalized model based on data captured with wearable devices. The findings hold potential for innovative home-based telemedicine solutions in motor rehabilitation.

关键词： Wrist Deep learning Adaptation models Biological system modeling Telemedicine Kinematics Motors Electromyography Decoding Wearable devices

来源：评论

学校读者我要写书评

暂无评论

Clustering Based User Allocation in 5G Networks*

Clustering Based User Allocation in 5G Networks*

引用

International Symposium on Networks, computers and Communications (ISNCC)

作者： Christos Bouras Rafail Kalogeropoulos Ioannis Sina Computer Technology Institute & Press “Diophantus201D Univ. of Patras Greece Patras Greece Computer Engineering and Informatics Dept.

Machine learning is an extremely efficient technique for solving complex problems without the use of traditional programming but rather enabling machines to learn from an input of data and train them to cope with various problems. The rapid growth in the number of active mobile devices, mobile applications and services dictates an efficient utilization of mobile and wireless networking infrastructure. Communication networks need to evolve and valorize machine learning methods in order to process large volumes of data without introducing excessive time delay in these computations. Upcoming 5G systems are expected to be the first network infrastructure to support exploding mobile traffic volumes and machine learning techniques can be used in order to help manage the rise in data volumes. We present a mechanism for resource allocation in mobile and wireless networks, that effectively utilizes machine learning techniques.

关键词：

来源：评论

学校读者我要写书评

暂无评论

High Speed Photonic Neuromorphic Computing Using Recurrent Optical Spectrum Slicing Neural Networks

arXiv

引用

arXiv 2022年

作者： Sozos, K. Bogris, A. Bienstman, P. Sarantoglou, G. Deligiannidis, S. Mesaritakis, Charis Dept. of Informatics and Computer Engineering University of West Attica Aghiou Spiridonos Egaleo 12243 Greece Dept. of Information Technology Ghent University-Imec Technologiepark Zwijnaarde 126 Gent9052 Belgium Dept. Information and Communication Systems Engineering Engineering School University of the Aegean Palama 2 Samos83200 Greece

Neuromorphic Computing implemented in photonic hardware is one of the most promising routes towards achieving machine learning processing at the picosecond scale, with minimum power consumption. In this work, we present a new concept for realizing photonic recurrent neural networks and reservoir computing architectures with the use of recurrent optical spectrum slicing. This is accomplished through simple optical filters placed in an loop, where each filter processes a specific spectral slice of the incoming optical signal. The synaptic weights in our scheme are equivalent to filters' central frequencies and bandwidths. This new method for implementing recurrent neural processing in the photonic domain, which we call Recurrent Optical Spectrum Slicing Neural Networks (ROSS-NNs), is numerically evaluated on a demanding, industry-relevant task such as high baud rate optical signal equalization (>100 Gbaud), exhibiting ground-breaking performance. The performance enhancement surpasses state-of-the-art digital processing techniques by doubling the reach while minimizing complexity and power consumption by a factor of 10 compared to state-of-the-art solutions. In this respect, ROSS-NNs can pave the way for the implementation of ultra-efficient photonic hardware accelerators tailored for processing high-bandwidth (> 100 GHz) optical signals in optical communication and high-speed imaging applications. Copyright © 2022, The Authors. All rights reserved.

关键词： Optical communication

来源：评论

学校读者我要写书评

暂无评论

CT Image Harmonization for Enhancing Radiomics Studies

CT Image Harmonization for Enhancing Radiomics Studies

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Selim, Md Zhang, Jie Fei, Baowei Zhang, Guo-Qiang Chen, Jin Dept. of Computer Science University of Kentucky LexingtonKY United States Dept. of Radiology University of Kentucky LexingtonKY United States Dept. of Bioengineering University of Texas at Dallas DallasTX United States Dept. of Neurology University of Texas Health Science Center at Houston HoustonTX United States Inst. for Biomedical Informatics University of Kentucky LexingtonKY United States

ISBN: (纸本)9781665401265

While remarkable advances have been made in Computed Tomography (CT), most of the existing efforts focus on imaging enhancement while reducing radiation dose. How to normalize CT images acquired using non-standard protocols is vital for decision-making in cross-center large-scale radiomics studies but remains the boundary to explore. We develop a novel GAN-based image standardization algorithm called RadiomicGAN to mitigate the discrepancy caused by using non-standard acquisition protocols. In RadiomicGAN, a pre-trained U-Net has been adopted as part of the generator to learn radiomic feature distributions efficiently, and a novel training approach, called Window Training, has been developed to smoothly transform the pre-trained model to the medical imaging domain. In the experiments, we compared RadiomicGAN with four state-of-the-art CT image standardization approaches on both patient and phantom CT images acquired using three different reconstruction kernels. We objectively evaluated model performance based on more than 1,000 radiomic features. The results show that RadiomicGAN clearly outperforms the compared models. The source code, manual, and sample data are available at https://*** selim-iitdu/radiomicGAN. © 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

Constructing a Cryptocurrency-Price Prediction Model Using Deep Learning 8

Constructing a Cryptocurrency-Price Prediction Model Using D...

引用

8th International Conference on engineering and Emerging Technologies, ICEET 2022

作者： Tran, Toai Kim Le, Thanh Thi Tuyet Bui, Thinh Tien Dang, Vang Quang Senkerik, Roman Ho Chi Minh City University of Technology and Education Faculty of Economics No 1 Vo Van Ngan Street Linh Chieu Ward Thu Duc City Viet Nam VSB-Technical University of Ostrava Faculty of Electrical Engineering and Computer Science Dept. of Computer Science 17. Listopadu 2172/15 Ostrava-Poruba708 00 Czech Republic Tomas Bata University in Zlin Faculty of Applied Informatics T. G. Masaryka 5555 Zlin76001 Czech Republic

ISBN: (纸本)9781665491068

The purpose of this study is to discover the optimal Deep Learning model for Bitcoin prediction among the Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM). Our empirical results indicate that LSTM is the optimal model for predicting Bitcoin price and trend with the prediction accuracy of 88.9%. Our study serves as a stepping stone for novice cryptocurrency investors and future studies of more advanced and sophisticated algorithms. Finally, given that the ideal model for predicting the price of cryptocurrencies is still a topic of controversy, the findings of this study will serve as a valuable empirical resource for future studies. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Brazilian engineering Research Center for the Aerial Mobility of the Future

Brazilian Engineering Research Center for the Aerial Mobilit...

引用

International Conference on Electrical Systems for Aircraft, Railway, Ship Propulsion and Road Vehicles & International Transportation Electrification Conference (ESARS-ITEC)

作者： Domingos A. Rade Luciano J. Pedrote dos Santos Jose A. Pomilio Roberto G. Annes da Silva Carlos Henrique C. Ribeiro Alfredo Rocha de Faria Emilia Villani Mechanical Eng. Division Aeronautics Inst. of Technology Sao Jose dos Campos Brazil R&D Deptartment Embraer S.A. Sao Jose dos Campos Brazil Systems and Energy Dept. University of Campinas Campinas Brazil Aeronautics Division Aeronautics Inst. of Technology Sao Jose dos Campos Brazil Computer Science Division Aeronautics Inst. of Technology Sao Jose dos Campos Brazil

The paper describes the constitution of the engineering Research Center for the Aerial Mobility of the Future (ERC-AMF) having ITA as the host inst.tution, Embraer as the industrial partner, and researchers from the University of São Paulo and the University of Campinas. The objective of the ERC-AMF is the realization of R&D to contribute to overcoming challenges to the shaping of aerial mobility in the upcoming decades. These challenges arise from the necessity of reducing pollutant and noise emissions, and the need for increased efficiency of manufacturing processes, besides the trend of introducing in the market novel aircraft adapted for operation in urban environments and short-range travels. Five research areas are focused on the first operation phase of the Center: Machine Control for Electric Propulsion; Aeropropulsion Integration in Electric Aircraft; Methods for Decision Making in Autonomous Systems; Advanced Design for Metallic Additive Manufacturing; and Intelligent Aircraft Final Assembly. Each line will be developed by researchers from partner universities and engineers from Embraer. It is expected that the Center will contribute to the appropriation, by the Brazilian aeronautical industry, of scientific and technological knowledge generated, and, as a result, increase its preparedness to face challenges that shall be overcome in the process of shaping the aerial mobility of the upcoming decades.

关键词： Industries Urban areas Transportation Three-dimensional printing Manufacturing Aircraft manufacture Aircraft propulsion

来源：评论

学校读者我要写书评

暂无评论

A Web and Mobile Application to Identify the Availability of Drinking Water Information During a Water Crisis

A Web and Mobile Application to Identify the Availability of...

引用

Intelligent Computing and Control for engineering and Business Systems (ICCEBS)

作者： Suhail Razeeth Fathima Shihara Kasuni Pavithra Maran Kaliyamoorthy Samsudeen Sabraz Nawaz Rkar Kariyapper Dept. of Information and Communication Technology South Eastern University of Sri Lanka Sri Lanka Dept. of Computer Science and Informatics Uva Wellassa University of Sri Lanka Sri Lanka Sri Sai Ram Institute of Management Studies Sri Sai Ram Engineering College India Department of Management and Information Technology South Eastern University of Sri Lanka Sri Lanka

Sri Lanka faces drinking water related issues often due to many reasons like weather changes, floods, droughts, and tsunamis, affecting the drinking water availability. In such inst.nces, people find difficult to gather information regarding consumable drinking water availability. In order to facilitate the meeting of commercial water sellers and customers and to engage the general public and social services in addressing the drinking water problem, this study is focused on building both web and mobile applications. The web application was implemented with a selected set of functionalities such as social login, social sharing, geocoding, reverse geocoding, viewing, and filtering posts using Angular 6, *** web framework, and Leaflet. The mobile application was developed to direct the customers to the water availability location with a shortest path using the Dijkstra's algorithm. Case evaluation was conducted with the Rotaract Club members in Badulla and thinking aloud method was used to pick up the user's ideas while interacting with the system. It can be concluded that the created web and mobile applications would offer the public a clever way to draw attention to an issue with water availability, and the commercial water service providers are given a venue to market their services and locate potential customers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Live multi-streaming and donation recommendations via coupled donation-response tensor factorization

arXiv

引用

arXiv 2021年

作者： Lai, Hsu-Chao Huang, Jiun-Long Tsai, Jui-Yi Lee, Wang-Chien Shuai, Hong-Han Yang, De-Nian Dept. of Computer Science National Chiao Tung Univ. Inst. of Information Science Academia Sinica Taiwan Dept. of Computer Science National Chiao Tung Univ. Taiwan Dept. of Electrical and Computer Engineering National Chiao Tung Univ. Inst. of Information Science Academia Sinica Taiwan Dept. of Computer Science and Engineering Pennsylvania State Univ. United States Dept. of Electrical and Computer Engineering National Chiao Tung Univ. Taiwan Inst. of Information Science Research Center Information Technology Innovation Academia Sinica Taiwan

In contrast to traditional online videos, live multi-streaming supports real-time social interactions between multiple streamers and viewers, such as donations. However, donation and multi-streaming channel recommendations are challenging due to complicated streamer and viewer relations, asymmetric communications, and the tradeoff between personal interests and group interactions. In this paper, we introduce Multi-Stream Party (MSP) and formulate a new multi-streaming recommendation problem, called Donation and MSP Recommendation (DAMRec). We propose Multi-stream Party Recommender System (MARS) to extract latent features via socio-temporal coupled donation-response tensor factorization for donation and MSP recommendations. Experimental results on Twitch and Douyu manifest that MARS significantly outperforms existing recommenders by at least 38.8% in terms of hit ratio and mean average precision. Copyright © 2021, The Authors. All rights reserved.

关键词： Factorization

来源：评论

学校读者我要写书评

暂无评论

Real-Time Safety Helmet Detection Using Enhanced YOLOv5 Object Detection

Real-Time Safety Helmet Detection Using Enhanced YOLOv5 Obje...

引用

IEEE International Conference on Smart inst.umentation, Measurement and Applications (ICSIMA)

作者： Fatin Najihah Muhamad Zamri Mira Kartiwi Nurul Fariza Zulkurnain Nelidya Md. Yusoff Teddy Surya Gunawan Levy Olivia Nur Electrical and Computer Engineering Dept. International Islamic University Malaysia Kuala Lumpur Malaysia Information Systems Department International Islamic University Malaysia Kuala Lumpur Malaysia Razak Faculty of Technology & Informatics UTM Kuala Lumpur Kuala Lumpur Malaysia School of Electrical Engineering Telkom University Bandung Indonesia

Personal Protective Equipment (PPE) regulations require construction workers to wear safety helmets to ensure site safety. However, monitoring PPE compliance consistently in fast-paced, dynamic construction environments poses a significant challenge. In response, we developed a sophisticated object detection system that automates the real-time verification of helmet use, thereby improving safety standards and reducing the likelihood of accidents. Extensive research was conducted to analyze all feasible algorithms that can be implemented in the safety helmet detection system and compare the proposed model with an existing one to ensure the proposed system can give high accuracy and high inference speed. Therefore, YOLOv5 was identified as the ideal choice in terms of accuracy and speed, and it was then enhanced with optimized transfer learning. We began our methodology by pre-training a comprehensive Kaggle dataset before refining the model using Roboflow on a specialized dataset. Using PyTorch and YOLOv5, we conducted exhaustive model training, testing, and evaluation. Our system achieved a lightning-fast inference speed of 39.8 milliseconds and a remarkable 91.4 percent accuracy in identifying helmet compliance. The implementation of such object detection technologies has the potential to significantly increase safety helmet compliance, thereby creating a safer environment for construction workers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Techno-economic analysis of cognitive radio models in 5G networks 17

Techno-economic analysis of cognitive radio models in 5G net...

引用

17th International Conference on Mobile Systems and Pervasive Computing, MobiSPC 2020

作者： Bouras, Christos Kollia, Anastasia Papazois, Andreas Computer Technology Institute and Press Diophantus PatrasP.C. 26504 Greece Computer Engineering and Informatics Dept. University of Patras PatrasP.C. 26504 Greece

The first commercial products of 5G will be released within 2020 and therefore, it becomes an absolute necessity to research whether the key enabling technologies are advantageous for the operators to invest in. One of the most fundamental technologies Cognitive Radio (CR), since there is not much research in the field. This paper develops a techno-economic framework for the CR technology and is contrasted with an already existing model for Software Defined Networks (SDN). A Sensitivity Analysis (SA) indicates the cost parameters that are the most expensive ones and should be reconsidered for the model's wide adoption and viability. © 2020 The Authors.

关键词： Cognitive radio

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：