检索结果-内蒙古大学图书馆

TechRxiv 2021年

作者： Gu, Yu Zhang, Xiang Wang, Yantong Wang, Meng Liu, Zhi Li, Jianhua Dong, Mianxiong School of Computer and Information Hefei University of Technology China Department of Computer and Network Engineering The University of Electro-Communications Tokyo Japan Dept. of Sciences and Informatics Muroran Institute of Technology Japan

Gestures constitute an important form of nonverbal communication where bodily actions are used for delivering messages alone or in parallel with spoken words. Recently, there exists an emerging trend of WiFi sensing enabled gesture recognition due to its inherent merits like device-free, non-line-of-sight covering, and privacy-friendly. However, current WiFi-based approaches mainly reply on domain-specific training since they don’t know "where to look" and "when to look". To this end, we propose WiGRUNT, a WiFi-enabled gesture recognition system using dual-attention network, to mimic how a keen human being intercepting a gesture regardless of the environment variations. The key insight is to train the network to dynamically focus on the domain-independent features of a gesture on the WiFi Channel State Information (CSI) via a spatial-temporal dual-attention mechanism. WiGRUNT roots in a Deep Residual Network (ResNet) backbone to evaluate the importance of spatial-temporal clues and exploit their inbuilt sequential correlations for fine-grained gesture recognition. We evaluate WiGRUNT on the open Widar3 dataset and show that it significantly outperforms its state-of-the-art rivals by achieving the best-ever performance in-domain or cross-domain. © 2021, CC BY.

关键词： Channel state information

来源：评论

学校读者我要写书评

暂无评论

Secrecy outage performance and deep learning evaluation of multihop energy harvesting IoT networks over Nakagami-m fading channels

Secrecy outage performance and deep learning evaluation of m...

引用

2020 International Symposium on computer, Consumer and Control, IS3C 2020

作者： Nguyen, Toan-Van Tran, Thong-Nhat Shim, Kyusung Huynh-The, Thien An, Beongku Dept. of Electronics and Computer Engineering in Graduate School Hongik University Korea Republic of ICT Convergence Research Center Kumoh National Institute of Technology Korea Republic of Dept. of Software and Communications Engineering Hongik University Korea Republic of

ISBN: (纸本)9781728193625

In this paper, we study the secrecy outage performance of multi-hop energy harvesting Internet-of-Things (IoT) networks, where all IoT devices harvest energy from a power beacon for conveying a confidential message to multiple legitimate users in the presence of an eavesdropper. To enhance the secrecy outage probability (SOP), we propose and analyze the best relay selection (BRE) and best-path selection (BPA) schemes under Nakagami-m fading environments. Based on the analysis results, we develop a deep learning model for the proposed schemes to evaluate the system SOP. Numerical results show that the BPA scheme greatly outperforms the BRE one, showing the efficiency of the best-path selection approach. Moreover, the deep learning model is capable of predicting the SOP of all schemes with high accuracy while it drastically reduces the execution time, arising a real-time configuration for multi-hop energy harvesting IoT networks. © 2020 IEEE

关键词： Energy harvesting

来源：评论

学校读者我要写书评

暂无评论

5G-GOVSATCOM: 5G EU-GOVSATCOM Non-terrestrial networks for Humanitarian Connectivity

5G-GOVSATCOM: 5G EU-GOVSATCOM Non-terrestrial Networks for H...

引用

IEEE Canada International Humanitarian technology Conference (IHTC)

作者： Miguel Ángel Vázquez Sergio Barrachina-Muñoz Mauro Di Si Fotis Foukalas Basilio Garrido Giovanni Giambene Makhlouf Hadji Hamzeh Khalili Josep Mangues-Bafalluy Sara Nasirian Marina Santos Lorenzo Santilli Theodoros A. Tsiftsis Marco Viali Space and Resilient Communications and Systems Centre Tecnològic de Telecomunicacions de Catalunya Castelldefels Spain Service as Networks (SaS) Centre Tecnològic de Telecomunicacions de Catalunya Castelldefels Spain Information Technology Open Arms Badalona Spain Dept. of Informatics & Telecommunications University of Thessaly Lamia Greece Chief Operations Office Hisdesat Servicios Estratégicos Madrid Spain Department of Information Engineering and Mathematics Università di Siena Siena Italy Mission Critial Networks Airbus Defense and Space Paris France Project Engineering INSTER – Grupo Oesía Getafe Spain Chief Innovation and Information Office Telecom Italia S.p.A. Torino Italy Information and Communications Technology Croce Rossa Italiana Rome Italy

ISBN: (数字)9798350354645

ISBN: (纸本)9798350354652

This paper introduces the concept of the project 5G-GOVSATCOM funded by the European Union. 5G non-terrestrial networks (5G-NTN) will soon be able to handle all types of applications and provide service to a massive number of users. In this complex and dynamic network ecosystem, end-to-end adaptation of 5G-NTN to meet the specific requirements and use cases of EU-GOVSATCOM humanitarian services is crucial for the efficient deployment of European governmental satellite services. To enable such a vision, the 5GGOVSATCOM project targets the development and evaluation in a natural user environment of different key enabling technologies that aim to provide full integration of 5G-NTN (and terrestrial networks) in the EU-GOVSATCOM framework. All project developments are planned to be first validated in a controlled lab with satellite (and terrestrial) connectivity and, subsequently, to be experimentally tested in field trials in close collaboration with final users. These latter tests will constitute the first 5G-NTN trials with humanitarian final users devoted to i) ubiquitous telemedicine in maritime areas and ii) crisis management connectivity bubble.

关键词： Crisis management Satellites Costs 5G mobile communication Telemedicine Ecosystems Europe Collaboration

来源：评论

学校读者我要写书评

暂无评论

Emotion detection in infants using an ensemble classifier with a novel member selection technique

Emotion detection in infants using an ensemble classifier wi...

引用

2020 Summer computer Simulation Conference, SCSC 2020, Held at the 2020 Summer Simulation Multi-Conference, SummerSim 2020

作者： Fahmy, Hesham Ahmed Fahmy, Sherif Fadel Del Barrio García, Alberto A. Juan, Guillermo Botella Dept. of Electronics and Communications Dept. of Computer Engineering Arab Academy for Science Technology and Maritime Transport 2401 Smart Village Campus Giza12577 Egypt Dept. of Computer Architecture and Automation Complutense University of Madrid Ciudad Universitaria C/ Jose Santesmases 9 Madrid28040 Spain

ISBN: (纸本)9781713819462

In this paper, we develop a method for detecting infant emotion from images using machine learning techniques. It is important to develop automatic infant emotion detection algorithms as they can become part of an integrated system that monitors the well-being of infants at home and in institutional settings. In particular, we develop an ensemble classifier that combines the results from diverse individual classifiers to produce better classification results. We present a novel method for selecting members of the ensemble that is based on the Pearson correlation coefficient of the location of the errors in the classifiers. The results show that the ensemble classifier outperforms individual classifiers by at least 1.4 times, and outperforms a state-of-the-art open-source algorithm for adult emotion detection by a larger margin. The results also indicate that Pearson Correlation among classifiers at a certain number of classifier count is a good criterion for selecting ensemble members. ©2020 Society for Modeling & Simulation (SCS) International

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Multi-strand reconstruction from substrings

arXiv

引用

arXiv 2021年

作者： Yehezkeally, Yonatan Marcovich, Sagi Yaakobi, Eitan Institute for Communications Engineering Technical University of Munich Munich80333 Germany Dept. of Computer Science Technion-Israel Institute of Technology Haifa3200003 Israel

The problem of string reconstruction based on its substrings spectrum has received significant attention recently due to its applicability to DNA data storage and sequencing. In contrast to previous works, we consider in this paper a setup of this problem where multiple strings are reconstructed together. Given a multiset S of strings, all their substrings of some fixed length , defined as the -profile of S, are received and the goal is to reconstruct all strings in S. A multi-strand -reconstruction code is a set of multisets such that every element S can be reconstructed from its -profile. Given the number of strings k and their length n, we first find a lower bound on the value of necessary for existence of multi-strand -reconstruction codes with non-vanishing asymptotic rate. We then present two constructions of such codes and show that their rates approach 1 for values of that asymptotically behave like the lower bound. Copyright © 2021, The Authors. All rights reserved.

关键词： Gene encoding

来源：评论

学校读者我要写书评

暂无评论

A Theoretical Demonstration for Reinforcement Learning of Pi Control Dynamics for Optimal Speed Control of Dc Motors by Using Twin Delay Deep Deterministic Policy Gradient Algorithm

SSRN

引用

SSRN 2022年

作者： Tufenkci, Sevilay Alagoz, Baris Baykant Kavuran, Gurkan Yeroglu, Celaleddin Herencsar, Norbert Mahata, Shibendu Malatya Turgut Ozal University Department of Computer Technology Malatya44100 Turkey Inonu University Department of Computer Engineering Malatya44100 Turkey Malatya Turgut Ozal University Department of Electrical-Electronics Engineering Malatya44100 Turkey Brno University of Technology Faculty of Electrical Engineering and Communications Dept. of Telecommunications Technicka 12 Brno616 00 Czech Republic Dr. B. C. Roy Engineering College Department of Electrical Engineering West Bengal Durgapur713206 India

To benefit from the advantages of Reinforcement Learning (RL) in industrial control applications, RL methods can be used for optimal tuning of the classical controllers based on the simulation scenarios of operating conditions. In this study, the Twin Delay Deep Deterministic (TD3) policy gradient method, which is an effective actor-critic RL method, is implemented to learn optimal Proportional Integral (PI) controller dynamics from a Direct Current (DC) motor control simulation environment. For this purpose, the PI controller dynamics are introduced to the actor-network by using the PI-based observer states from the control simulation environment. A suitable Simulink simulation environment is adapted to perform the training process of the TD3 algorithm. The actor-network learns the optimal PI controller dynamics by using the reward mechanism that implements the minimization of the optimal control objective function. A setpoint filter is used to define the desired setpoint response, and random disturbance signals are applied in the simulation environment to improve disturbance rejection control skills with the help of the agent's experience in the designed control simulation environment. When the training task is completed, the optimal PI coefficients are obtained from the weight coefficients of the actor-network. The performance of the optimal PI dynamics, which is learned by using the TD3 algorithm, is compared with the results of other genetic algorithm tuned optimal PI and fractional-order PI controllers;thus, the setpoint and disturbance rejection control performance improvements of RL approach were demonstrated. © 2022, The Authors. All rights reserved.

关键词： DC motors

来源：评论

学校读者我要写书评

暂无评论

An Efficient Deep CNN Design for EH Short-Packet communications in Multihop Cognitive IoT networks

arXiv

引用

arXiv 2022年

作者： Nguyen, Toan-Van Huynh-The, Thien Nguyen, Van-Dinh da Costa, Daniel Benevides Hu, Rose Qingyang An, Beongku Dept. of Electrical and Computer Engineering Utah State University LoganUT United States ICT Convergence Research Center Kumoh National Institute of Technology Korea Republic of SnT-Interdisciplinary Centre for Security Reliability and Trust University of Luxembourg Luxembourg AI & Telecom Research Center Technology Innovation Institute 9639 Masdar City Abu Dhabi United Arab Emirates Taiwan Dept. of Software and Communications Engineering Hongik University Korea Republic of

In this paper, we design an efficient deep convolutional neural network (CNN) to improve and predict the performance of energy harvesting (EH) short-packet communications in multi-hop cognitive Internet-of-Things (IoT) networks. Specifically, we propose a Sum-EH scheme that allows IoT nodes to harvest energy from either a power beacon or primary transmitters to improve not only packet transmissions but also energy harvesting capabilities. We then build a novel deep CNN framework with feature enhancement-collection blocks based on the proposed Sum-EH scheme to simultaneously estimate the block error rate (BLER) and throughput with high accuracy and low execution time. Simulation results show that the proposed CNN framework achieves almost exactly the BLER and throughput of Sum-EH one, while it considerably reduces computational complexity, suggesting a real-time setting for IoT systems under complex scenarios. Moreover, the designed CNN model achieves the root-mean-square-error (RMSE) of 1.33 × 10−2 on the considered dataset, which exhibits the lowest RMSE compared to the deep neural network and state-of-the-art machine learning approaches. © 2022, CC BY.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Conventional Spectrum-Allocation Policies for C+L Band Elastic Optical networks

Performance Evaluation of Conventional Spectrum-Allocation P...

引用

International Symposium on Advanced networks and Telecommunication Systems (ANTS)

作者： Rana Kumar Jana Bijoy Chand Chatterjee Abhishek Pratap Singh Anand Srivastava Biswanath Mukherjee Andrew Lord Abhijit Mitra Dept. of Electronics and Communications Engineering Indraprastha Institute of Information Technology New Delhi India Dept. of Computer Science South Asian University New Delhi India Dept. of Mathematics Indraprastha Institute of Information Technology New Delhi India Dept. of Computer Science University of California Davis USA Optics Research Lab British Telecom Ipswich UK

ISBN: (数字)9781665448932

ISBN: (纸本)9781665448949

Multiband elastic optical network (MB-EON) technology is a promising solution to support the exponential traffic growth in optical backbone networks. For C-band-only systems, optimal routing and spectrum allocation (RSA) policies have been investigated in the context of EON to enhance its spectrum utilization. However, for a multiband system, the same allocation strategies may not provide the best performance due to the presence of heterogeneous, complex, non-linear, physical-layer impairments (PLI), such as inter-channel stimulated Raman scattering (ISRS). This paper investigates the performance of the state-of-the-art spectrum-allocation policies in different geographies with different channel launch power for C+l band systems. Simulation results show that the Last-Fit policy performs best in terms of traffic admissibility, blocking probability, resource utilization, contiguous aligned available slot ratio (CAASR), and quality of established lightpaths.

关键词： Performance evaluation Law enforcement Simulation Raman scattering Optical fiber networks Routing Minimization

来源：评论

学校读者我要写书评

暂无评论

Automatic Diagnosis of Schizophrenia and Attention Deficit Hyperactivity Disorder in rs-fMRI Modality using Convolutional Autoencoder Model and Interval Type-2 Fuzzy Regression

arXiv

引用

arXiv 2022年

作者： Shoeibi, Afshin Ghassemi, Navid Khodatars, Marjane Moridian, Parisa Khosravi, Abbas Zare, Assef Gorriz, Juan M. Chale-Chale, Amir Hossein Khadem, Ali Rajendra Acharya, U. Faculty of Electrical Engineering FPGA Lab K. N. Toosi University of Technology Tehran Iran Computer Engineering Department Ferdowsi University of Mashhad Mashhad Iran Dept. of Medical Engineering Mashhad Branch Islamic Azad University Mashhad Iran Faculty of Engineering Science and Research Branch Islamic Azad University Tehran Iran Deakin University Geelong Australia Faculty of Electrical Engineering Gonabad Branch Islamic Azad University Gonabad Iran Department of Signal Theory Networking and Communications Universidad de Granada Spain Faculty of Electrical Engineering K. N. Toosi University of Technology Tehran Iran Ngee Ann Polytechnic Singapore599489 Singapore Dept. of Biomedical Informatics and Medical Engineering Asia University Taichung Taiwan Dept. of Biomedical Engineering School of Science and Technology Singapore University of Social Sciences Singapore

Nowadays, many people worldwide suffer from brain disorders, and their health is in danger. So far, numerous methods have been proposed for the diagnosis of Schizophrenia (SZ) and attention deficit hyperactivity disorder (ADHD), among which functional magnetic resonance imaging (fMRI) modalities are known as a popular method among physicians. This paper presents an SZ and ADHD intelligent detection method of resting-state fMRI (rs-fMRI) modality using a new deep learning method. The university of California Los Angeles dataset, which contains the rs-fMRI modalities of SZ and ADHD patients, has been used for experiments. The FMRIB software library toolbox first performed preprocessing on rs-fMRI data. Then, a convolutional Autoencoder model with the proposed number of layers is used to extract features from rs-fMRI data. In the classification step, a new fuzzy method called interval type-2 fuzzy regression (IT2FR) is introduced and then optimized by genetic algorithm, particle swarm optimization, and gray wolf optimization (GWO) techniques. Also, the results of IT2FR methods are compared with multilayer perceptron, k-nearest neighbors, support vector machine, random forest, and decision tree, and adaptive neuro-fuzzy inference system methods. The experiment results show that the IT2FR method with the GWO optimization algorithm has achieved satisfactory results compared to other classifier methods. Finally, the proposed classification technique was able to provide 72.71% accuracy. © 2022, CC BY-NC-ND.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A Summary Evaluation Method Combining Linguistic Quality and Semantic Similarity

A Summary Evaluation Method Combining Linguistic Quality and...

引用

2020 International Conference on Computational Science and Computational Intelligence, CSCI 2020

作者： Wang, Xingwen Liu, Bo Shen, Libin Li, Yong Gu, Rentao Qu, Guangzhi Beijing University of Technology School of Software Engineering Faculty of Information Technology Beijing100124 China Beijing University of Posts and Telecommunications School of Information and Communication Engineering Beijing Laboratory of Advanced Information Networks Beijing100876 China Oakland University Computer Science and Engineering Dept. RochesterMI48309 United States

ISBN: (纸本)9781728176246

Summary evaluation method is crucial to promote the development of summarization technologies. However, most of the existing summary evaluation methods seldom consider the content integrity and readability of summaries simultaneously. This paper proposed a Linguistic Quality and Semantic Similarity Model (LQSSM) to evaluate generated summaries more comprehensively. Considering the readability of summaries, a linguistic quality evaluation network (LQEN) is proposed to evaluate summaries automatically. Meanwhile, a semantic similarity evaluation network (SSEN) is introduced to directly measure the informativeness between the summary and original . Additionally, there is also a comprehensive evaluation using fusion indicators. The LQSSM and Recall-Oriented Understudy for Gisting Evaluation (ROUGE) methods were used to score the summaries generated by five models. The results showed that the proposed method gave further feedback from different angles on the basis of reaching the level of other methods. © 2020 IEEE.

关键词： Semantics

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：