检索结果-内蒙古大学图书馆

Classification and Self-Supervised Regression of Arrhythmic ECG Signals Using Convolutional Neural Networks

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Grabowski, Bartosz Glomb, Przemyslaw Masarczyk, Wojciech Plawiak, Pawel Yıldırım, Özal Acharya, U. Rajendra Tan, Ru-San Institute of Theoretical and Applied Informatics Polish Academy of Sciences Baltycka 5 Gliwice44-100 Poland Warsaw University of Technology Pl. Politechniki 1 Warsaw00-661 Poland Department of Computer Science Faculty of Computer Science and Telecommunications Cracow University of Technology Warszawska 24 Krakow31-155 Poland Department of Software Engineering Firat University Elazig Turkey School of Science and Technology Singapore University of Social Sciences Singapore Faculty of Business Education Law and Arts University of Southern Queensland Australia School of Engineering Ngee Ann Polytechnic 535 Clementi Road 599489 Singapore Department of Bioinformatics and Medical Engineering Asia University Taiwan Kumamoto University Kumamoto Japan Department of Cardiology National Heart Centre Singapore169609 Singapore Duke-NUS Medical School 169857 Singapore

Interpretation of electrocardiography (ECG) signals is required for diagnosing cardiac arrhythmia. Recently, machine learning techniques have been applied for automated computer-aided diagnosis. Machine learning tasks can be divided into regression and classification. Regression can be used for noise and artifacts removal as well as resolve issues of missing data from low sampling frequency. Classification task concerns the prediction of output diagnostic classes according to expert-labeled input classes. In this work, we propose a deep neural network model capable of solving regression and classification tasks. Moreover, we combined the two approaches, using unlabeled and labeled data, to train the model. We tested the model on the MIT-BIH Arrhythmia database. Our method showed high effectiveness in detecting cardiac arrhythmia based on modified Lead II ECG records, as well as achieved high quality of ECG signal approximation. For the former, our method attained overall accuracy of 87.33% and balanced accuracy of 80.54%, on par with reference approaches. For the latter, application of self-supervised learning allowed for training without the need for expert labels. The regression model yielded satisfactory performance with fairly accurate prediction of QRS complexes. Transferring knowledge from regression to the classification task, our method attained higher overall accuracy of 87.78%. © 2022, CC BY.

关键词： Electrocardiography

Narrowband-internet of things (NB-IoT) system for elderly healthcare services 5

学校读者我要写书评

暂无评论

Narrowband-internet of things (NB-IoT) system for elderly he...

5th International Conference on engineering, Applied sciences and Technology, ICEAST 2019

作者： Manatarinat, Wiraphon Poomrittigul, Suvit Tantatsanawong, Panjai Electrical Engineering Department Faculty of Engineering Pathumwan Institute of Technology Bangkok Thailand Software Engineering and Information System Department Faculty of Science and Technology Pathumwan Institute of Technology Bangkok Thailand Computer Technology Department Faculty of Science Silpakorn University Bangkok Thailand

ISBN: (纸本)9781728100678

3G and 4G wireless communication technology, which requires broad network resources and large amounts of available electricity, was designed for high-speed Internet usage. Most narrowband-Internet of Things (NB-IoT) devices do not require high-speed Internet because most IoTs work by sending commands to and receiving commands from a server only. NB-IoT is a low-power wide area (LPWA) technology that was developed to accommodate a broad variety of new IoT devices. A low-power wide area network (LPWAN) uses narrow frequencies that support the use of devices in the 900 MHz frequency range that are inexpensive and that can be used in both buildings and wide areas. NB-IoT devices can also be used to assist medical patients, the elderly, and disabled people that are susceptible to falling. Our newly developed monitoring system has the ability to immediately recognize a fall, and then automatically alert up to 4 contacts via the LINE application. If dispatch of a medical unit is required, the patient's location is automatically available without the need for voice contact by the patient. © 2019 IEEE.

关键词： Internet of things

A Unified Graph-Theoretic Framework for Free-Fermion Solvability

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chapman, Adrian Elman, Samuel J. Mann, Ryan L. Department of Materials University of Oxford Parks Road OxfordOX1 3PH United Kingdom Centre for Quantum Software and Information School of Computer Science Faculty of Engineering & Information Technology University of Technology Sydney NSW 2007 Australia Centre for Engineered Quantum Systems School of Physics The University of Sydney Sydney Australia Centre for Quantum Computation and Communication Technology Australia School of Mathematics University of Bristol BristolBS8 1UG United Kingdom

We show that a quantum spin system has an exact description by non-interacting fermions if its frustration graph is claw-free and contains a simplicial clique. The frustration graph of a spin model captures the pairwise anticommutation relations between Pauli terms of its Hamiltonian in a given basis. This result captures a vast family of known free-fermion solutions. In previous work, it was shown that a free-fermion solution exists if the frustration graph is either a line graph, or (even-hole, claw)-free. The former case generalizes the celebrated Jordan-Wigner transformation and includes the exact solution to the Kitaev honeycomb model. The latter case generalizes a non-local solution to the four-fermion model given by Fendley. Our characterization unifies these two approaches, extending generalized Jordan-Wigner solutions to the non-local setting and generalizing the four-fermion solution to models of arbitrary spatial dimension. Our key technical insight is the identification of a class of cycle symmetries for all models with claw-free frustration graphs. We prove that these symmetries commute, and this allows us to apply Fendley's solution method to each symmetric subspace independently. Finally, we give a physical description of the fermion modes in terms of operators generated by repeated commutation with the Hamiltonian. This connects our framework to the developing body of work on operator Krylov subspaces. Our results deepen the connection between many-body physics and the mathematical theory of claw-free graphs. Copyright © 2023, The Authors. All rights reserved.

关键词： Hamiltonians

Extended Bat Algorithm (EBA) as an Improved Searching Optimization Algorithm 10th

学校读者我要写书评

暂无评论

Extended Bat Algorithm (EBA) as an Improved Searching Optimi...

10th National Technical Seminar on Underwater System Technology, NUSYS 2018

作者： Pebrianti, Dwi Ann, Nurnajmin Qasrina Bayuaji, Luhur Abdullah, N. R. Hasma Zain, Zainah Md. Riyanto, Indra Faculty of Electrical and Electronics Engineering Universiti Malaysia Pahang Pekan26600 Malaysia Faculty of Computer Science and Software Engineering Universiti Malaysia Pahang Pekan Malaysia Magister of Computer Science Universitas Budi Luhur South Jakarta Indonesia Department of Electronics Engineering Faculty of Engineering Universitas Budi Luhur South Jakarta Indonesia

ISBN: (纸本)9789811337079

This paper presents a new searching technique by using a new variant of Bat Algorithm (BA) known as Extended Bat Algorithm (EBA). EBA introduces the spiral searching method instead of randomly searching used in original BA. Spiral searching method taken from Spiral Dynamic Algorithm (SDA) is performed to improve the accuracy and efficiency of the original algorithm such as stabilizing the convergence when reaching ideal value. EBA conserves the robustness of BA and SDA and increases the performance of the proposed algorithm. The proposed algorithm is tested by using numerical experiments with three different objective functions. The results show that EBA outperforms original Bat Algorithm (BA) and Particle Swarm Optimization (PSO) in almost test functions and successfully optimizes the numerical problems. © 2019, Springer Nature Singapore Pte Ltd.

关键词： Particle swarm optimization (PSO)

Affective visualization in virtual reality: An integrative review

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Pinilla, Andres Garcia, Jaime Raffe, William Voigt-Antons, Jan-Niklas Spang, Robert P. Möller, Sebastian Quality and Usability Lab Institute for Software Technology and Theoretical Computer Science Faculty of Electrical Engineering and Computer Science Technische Universität Berlin Germany UTS Games Studio Faculty of Engineering and IT University of Technology Sydney UTS Sydney Australia Berlin Germany

A cluster of research in Affective Computing suggests that it is possible to infer some characteristics of users' affective states by analyzing their electrophysiological activity in real-time. However, it is not clear how to use the information extracted from electrophysiological signals to create visual representations of the affective states of Virtual Reality (VR) users. Visualization of users' affective states in VR can lead to biofeedback therapies for mental health care. Understanding how to visualize affective states in VR requires an interdisciplinary approach that integrates psychology, electrophysiology, and audio-visual design. Therefore, this review aims to integrate previous studies from these fields to understand how to develop virtual environments that can automatically create visual representations of users' affective states. The manuscript addresses this challenge in four sections: First, theories related to emotion and affect are summarized. Second, evidence suggesting that visual and sound cues tend to be associated with affective states are discussed. Third, some of the available methods for assessing affect are described. The fourth and final section contains five practical considerations for the development of virtual reality environments for affect visualization. © 2020, CC BY.

关键词： Virtual reality

The First Competition on Resource-Limited Infrared Small Target Detection Challenge: Methods and Results

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Boyang Ying, Xinyi Li, Ruojing Liu, Yongxian Shi, Yangsi Li, Miao Zhang, Xin Hu, Mingyuan Wu, Chenyang Zhang, Yukai Wei, Hui Tang, Dongli Zhao, Jian Jin, Lei Xiao, Chao Ling, Qiang Lin, Zaiping Sheng, Weidong Peng, Chenxu Ke, Wei He, Yuhang Yang, Huoren Liu, Lingjie Liu, Ziqi Shi, Zelin Liu, Yunpeng Yu, Chuang Zhao, Jinmiao Xiang, Heng Yang, Shan Li, You Wang, Guoqing Li, Tianyu Zhou, Minghang Xie, Dongyu Lan, Chenxi Qiao, Chaofan Gao, Yupeng Liu, Yongxu Feng, Wei Ma, Zhihao Chen, Deping Song, Xiaopeng Yang, Jiuping Qiu, Zhaobing Ni, Rixiang Lin, Ye Luo, Changhai Zheng, Shuyuan Huang, Baojin Zhou, Xiaoqi Guo, Qingshan Zhang, Xuyang Li, Xiuhong Wu, Dangxuan Ma, Jian Zeng, Haodong Wang, Luyao Fu, Qiang Dai, Yimian Kou, Renke Song, Jian Feng, Changfeng Xiao, Mengxuan Xiong, Zihao Huang, Hong Liu, Yingxu Zhao, Quanyi National University of Defense Technology China China Telecom Institute of AI China Northwestern Polytechnical University China Beijing University of Posts and Telecommunications China Zhejiang Supcon Information Co. Ltd. China School of Physics Xi’an Jiaotong University China College of Artificial Intelligence Faculty of Electronic and Information Engineering Xi’an Jiaotong University China School of Software Engineering Faculty of Electronic and Information Engineering Xi’an Jiaotong University China The Key Laboratory of Opto-Electronic Information Processing Chinese Academy of Sciences Shenyang110016 China The Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing100049 China Sichuan Zhongke Langxing Photoelectric Technology Co. Ltd. China Center for Future Media University of Electronic Science and Technology of China China Hangzhou Institute of Technology Xidian University China School of Electronic Engineering Xidian University China School of Mechanical Engineering and Automation Fuzhou University China Beijing Insitute of Technology Chongqing Innovation Center China Xinjiang University China Army Engineering University PLA Shijiazhuang Campus China Nanjing University of Science and Technology China Henan University of Technology China Chongqing University China

In this paper, we briefly summarize the first competition on resource-limited infrared small target detection (namely, LimitIRSTD). This competition has two tracks, including weakly-supervised infrared small target detection (Track 1) and lightweight infrared small target detection (Track 2). 46 and 60 teams successfully registered and took part in Tracks 1 and Track 2, respectively. The top-performing methods and their results in each track are described with details. This competition inspires the community to explore the tough problems in the application of infrared small target detection, and ultimately promote the deployment of this technology under limited resource. © 2024, CC BY-NC-SA.

关键词：

Prediction of global spread of covid-19 pandemic: A review and research challenges

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2020年

作者： Shah, Saloni Mulahuwaish, Aos Ghafoor, Kayhan Zrar Maghdid, Halgurd S. Department of Computer Science and Information Systems Saginaw Valley State University MI United States Department of Software Engineering Salahaddin University Erbil Iraq School of Mathematics and Computer Science University of Wolverhampton Wolverhampton United Kingdom Department of Software Engineering Faculty of Engineering Koya University Kurdistan Iraq

Since the initial reports of the Coronavirus surfacing in Wuhan, China;the novel virus currently without a cure has spread like a wildfire across the globe. The virus spread exponentially across all inhabited continent;catching local governments by surprise in many cases and bringing the world economy to a standstill. As local authorities work on a response to deal with the virus, the scientific community has stepped in to help analyse and predict the pattern and conditions that would influence the spread of this unforgiving virus. Using existing statistical modelling tools to latest AI technology;the scientific community has used public and privately available data to help with predictions. A lot of this data research has enabled local authorities to plan their response – whether that is to deploy tightly available medical resources like ventilators or how and when to enforce policies to social distance including lockdowns. On one hand, this paper shows what accuracy of research brings to enable fighting this disease;while on the other hand it also shows what lack of response from local authorities can do in spreading this virus. This is our attempt in compiling different research methods and comparing their accuracy in predicting the spread of COVID-19. © 2020, CC BY.

关键词： Viruses

C²-CapsViT: Cross-Context and Cross-Scale Capsule Vision Transformers for Remote Sensing Image Scene Classification

学校读者我要写书评

暂无评论

IEEE Geoscience and Remote Sensing Letters 2022年 19卷

作者： Yongtao Yu Yinyin Li Jun Wang Haiyan Guan Fenfen Li Shaozhang Xiao E. Tang Xiwang Ding Faculty of Computer and Software Engineering Huaiyin Institute of Technology Huaian China School of Remote Sensing and Geomatics Engineering Nanjing University of Information Science and Technology Nanjing China

Accurately interpreting image contents plays a vital role in many Earth observation tasks. This letter constructs a novel cross-context and cross-scale capsule vision transformer (C 2 -CapsViT) architecture to serve for remote sensing image scene classification. First, employed with a multicontext patch embedding strategy, the token representation quality is greatly boosted to encode different-context feature semantics. Second, designed with a multiscale transformer block, different-grained long-range global feature interactions and different-type feature self-attentions are concurrently exploited to promote the feature encoding quality. Moreover, by combining the convolution and transformer structures, local and global feature semantics are effectively fused to direct accurate predictions. The C 2 -CapsViT is elaborately verified on three scene classification datasets. Both quantitative evaluations and comparative analyses prove its competitive capability and advanced performance.

关键词： Semantics Transformers Image analysis Remote sensing Encoding Convolution Task analysis

Single-path Bit Sharing for Automatic Loss-aware Model Compression

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liu, Jing Zhuang, Bohan Chen, Peng Shen, Chunhua Cai, Jianfei Tan, Mingkui The School of Software Engineering South China University of Technology China The Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education China The Pazhou Laboratory Guangzhou China The School of Computer Science the University of Adelaide Australia The Faculty of Information Technology Monash University Australia The College of Computer Science and Technology Zhejiang University Hangzhou China

Network pruning and quantization are proven to be effective ways for deep model compression. To obtain a highly compact model, most methods first perform network pruning and then conduct quantization based on the pruned model. However, this strategy may ignore that the pruning and quantization would affect each other and thus performing them separately may lead to sub-optimal performance. To address this, performing pruning and quantization jointly is essential. Nevertheless, how to make a trade-off between pruning and quantization is non-trivial. Moreover, existing compression methods often rely on some pre-defined compression configurations (i.e., pruning rates or bitwidths). Some attempts have been made to search for optimal configurations, which however may take unbearable optimization cost. To address these issues, we devise a simple yet effective method named Single-path Bit Sharing (SBS) for automatic loss-aware model compression. To this end, we consider the network pruning as a special case of quantization and provide a unified view for model pruning and quantization. We then introduce a single-path model to encode all candidate compression configurations, where a high bitwidth value will be decomposed into the sum of a lowest bitwidth value and a series of re-assignment offsets. Relying on the single-path model, we introduce learnable binary gates to encode the choice of configurations and learn the binary gates and model parameters jointly. More importantly, the configuration search problem can be transformed into a subset selection problem, which helps to significantly reduce the optimization difficulty and computation cost. In this way, the compression configurations of each layer and the trade-off between pruning and quantization can be automatically determined. Extensive experiments on CIFAR-100 and ImageNet show that SBS significantly reduces computation cost while achieving promising performance. For example, our SBS compressed MobileNetV2 achieves

关键词： Encoding (symbols)