2021 Twelfth International Conference on Ubiquitous and Future Networks (ICUFN)最新文献_第9页

Machine Learning-based Channel Tracking for Next-Generation 5G Communication System 下一代5G通信系统中基于机器学习的信道跟踪

2021 Twelfth International Conference on Ubiquitous and Future Networks (ICUFN) Pub Date : 2021-08-17 DOI: 10.1109/ICUFN49451.2021.9528722

Hyeonsu Kim, Sangmi Moon, I. Hwang

引用次数: 0

Reducing Model Cost Based on the Weights of Each Layer for Federated Learning Clustering 基于各层权重的联邦学习聚类模型成本降低

2021 Twelfth International Conference on Ubiquitous and Future Networks (ICUFN) Pub Date : 2021-08-17 DOI: 10.1109/ICUFN49451.2021.9528575

Hyungbin Kim, Yongho Kim, Hyunhee Park

{"title":"Reducing Model Cost Based on the Weights of Each Layer for Federated Learning Clustering","authors":"Hyungbin Kim, Yongho Kim, Hyunhee Park","doi":"10.1109/ICUFN49451.2021.9528575","DOIUrl":"https://doi.org/10.1109/ICUFN49451.2021.9528575","url":null,"abstract":"Federated Learning (FL) has a different learning framework from existing machine learning, which had to centralize training data. Federated learning has the advantage of protecting privacy because learning is performed on each client device rather than the central server, and only the weight parameter values, which are the learning results, are sent to the central server. However, the performance of federated learning shows relatively low performance compared to cloud computing, and in reality, it is difficult to build a federated learning environment due to the high communication cost between the server and multiple clients. In this paper, we propose Federated Learning with Clustering algorithms (FLC). The proposed FLC is a method of clustering clients with similar characteristics by analyzing the weights of each layer of a machine learning model, and performing federated learning among the clustered clients. The proposed FLC can reduce the communication cost for each model by reducing the number of clients corresponding to each model. As a result of extensive simulation, it is confirmed that the accuracy is improved by 2.4% and the loss by 47% through the proposed FLC compared to the standard federated learning.","PeriodicalId":318542,"journal":{"name":"2021 Twelfth International Conference on Ubiquitous and Future Networks (ICUFN)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114899027","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 7

Multiband FSK with Direct Sequence Spread Spectrum for Underwater Acoustic Communications 基于直接序列扩频的水声通信多频带FSK

2021 Twelfth International Conference on Ubiquitous and Future Networks (ICUFN) Pub Date : 2021-08-17 DOI: 10.1109/ICUFN49451.2021.9528819

Hyun-Woo Jeong, Ji-Eun Shin, Ji-Won Jung

引用次数: 1

Stroke Medical Ontology for Supporting AI-based Stroke Prediction System using Bio-Signals 脑卒中医学本体支持基于人工智能的脑卒中生物信号预测系统

2021 Twelfth International Conference on Ubiquitous and Future Networks (ICUFN) Pub Date : 2021-08-17 DOI: 10.1109/ICUFN49451.2021.9528529

Soonhyun Kwon, Jaehak Yu, Se Jin Park, Jong-Arm Jun, C. Pyo

{"title":"Stroke Medical Ontology for Supporting AI-based Stroke Prediction System using Bio-Signals","authors":"Soonhyun Kwon, Jaehak Yu, Se Jin Park, Jong-Arm Jun, C. Pyo","doi":"10.1109/ICUFN49451.2021.9528529","DOIUrl":"https://doi.org/10.1109/ICUFN49451.2021.9528529","url":null,"abstract":"In this paper, we propose a stroke medical ontology that provides medical knowledge to accompany AI-based stroke disease prediction system's results that were arrived at based on EMG information. This system was developed as a result of the limitations mentioned above being encountered in previous studies. We approached the problem from a viewpoint of knowledge engineering with the aim of modeling medical knowledge related to strokes. Using web ontology language (OWL), a standard ontology language, we developed schema-level stroke ontologies with concepts and properties based on the brain's anatomical structures, lesions, and disease related to strokes. Also, we developed an instance-level medical terms ontology that can span standard medical terms such as those in the international classification diseases (ICD), systematized nomenclature of medicine - clinical terms (SNOMED-CT), and foundational model of anatomy (FMA). The above schema ontology and instance ontology are meaningfully mapped to each other to apply layered ontology modeling techniques that separate schemas from instances. Through semantic web rule language (SWRL)-based inference, we predict lesions, diseases, and anatomical brain structural ripple effects based on the patient's current lesions and diseases. The inferred knowledge information is provided via the SPARQL protocol and RDF query language (SPARQL), a standard ontology query language. To verify the stroke medical ontology proposed in this paper, we developed an ontology-based stroke disease prediction system. This system achieved knowledge augmentation performance of 67.82% by comparing the patients' current lesions and diseases with the lesions, diseases, and areas of disability found by SWRL-based inference using actual stroke emergency data from 37 patients.","PeriodicalId":318542,"journal":{"name":"2021 Twelfth International Conference on Ubiquitous and Future Networks (ICUFN)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130826887","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

Mesh-Clustering-Based Radio Maps Construction for Autonomous Distributed Networks 基于网格聚类的自治分布式网络无线地图构建

2021 Twelfth International Conference on Ubiquitous and Future Networks (ICUFN) Pub Date : 2021-08-17 DOI: 10.1109/ICUFN49451.2021.9528740

Keita Katagiri, T. Fujii

引用次数: 2

User Clustering Techniques for Massive MIMO-NOMA Enabled mmWave/THz Communications in 6G 6G中大规模MIMO-NOMA支持毫米波/太赫兹通信的用户集群技术

2021 Twelfth International Conference on Ubiquitous and Future Networks (ICUFN) Pub Date : 2021-08-17 DOI: 10.1109/ICUFN49451.2021.9528659

M. Shahjalal, Md. Habibur Rahman, Md. Osman Ali, ByungDeok Chung, Y. Jang

{"title":"User Clustering Techniques for Massive MIMO-NOMA Enabled mmWave/THz Communications in 6G","authors":"M. Shahjalal, Md. Habibur Rahman, Md. Osman Ali, ByungDeok Chung, Y. Jang","doi":"10.1109/ICUFN49451.2021.9528659","DOIUrl":"https://doi.org/10.1109/ICUFN49451.2021.9528659","url":null,"abstract":"Recently, Cooperative massive multiple-input multiple-output and non-orthogonal multiple access (mMIMO-NOMA) has been considered as a promising solution that can significantly improve the system capacity and the spectral efficiency of the sixth-generation (6G) high frequency spectrum such as Millimeter Wave and Terahertz networks. In this paper, we consider a mMIMO-NOMA enabled base station that can support a number of single antenna users in different clusters. Cooperative use of NOMA can support the users in a cluster by sharing the same frequency and time resources. However, in 6G the networks will be congested with ultra-massive interconnected users and that arises challenges in clustering the users efficiently. Therefore. we briefly summarize the studies about user clustering solutions in mMIMO-NOMA systems and divided them into two categories; resource aware user clustering (RAUC) and learning assisted user clustering (LAUC) approaches. A comparison among those techniques has been tabulated considering the computational complexities. The result depicts that the RAUC demonstrates a polynomial complexity function while that for the LAUC is comparatively low.","PeriodicalId":318542,"journal":{"name":"2021 Twelfth International Conference on Ubiquitous and Future Networks (ICUFN)","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126408758","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Freezing of Gait Detection Using Discrete Wavelet Transform and Hybrid Deep Learning Architecture 基于离散小波变换和混合深度学习结构的冻结步态检测

2021 Twelfth International Conference on Ubiquitous and Future Networks (ICUFN) Pub Date : 2021-08-17 DOI: 10.1109/ICUFN49451.2021.9528547

Nguyen Thi Hoai Thu, Dong Seog Han

{"title":"Freezing of Gait Detection Using Discrete Wavelet Transform and Hybrid Deep Learning Architecture","authors":"Nguyen Thi Hoai Thu, Dong Seog Han","doi":"10.1109/ICUFN49451.2021.9528547","DOIUrl":"https://doi.org/10.1109/ICUFN49451.2021.9528547","url":null,"abstract":"Freezing of gait (FoG) detection using wearable sensors plays an important role in both online and offline monitoring of Parkinson's disease patients. In a FoG detector, feature extraction is commonly considered as a critical part for distilling the sensor signals before the FoG classification. Manually extracted features with domain knowledge are widely used in conventional machine learning methods while recent deep learning algorithms introduce the automatic feature learning approach. In this paper, we propose a FoG detection framework, in which hand-crafted features are used as input to a hybrid deep learning model for further feature learning and classification task. The hand-crafted features with time-frequency representation are extracted from the raw sensor signal by using a multi-level discrete wavelet transform (DWT). A hybrid deep learning architecture constructed from two algorithms: convolutional neural network (CNN) and bidirectional long short-term memory network is then deployed to extract deep features and classify FoG events. For performance comparison purposes, experiments on different input data types and machine learning methods are carried out on the Daphnet public dataset.","PeriodicalId":318542,"journal":{"name":"2021 Twelfth International Conference on Ubiquitous and Future Networks (ICUFN)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132057329","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Analysis of Transport Layer Congestion Control Algorithms over 5G Millimeter Wave Networks 5G毫米波网络传输层拥塞控制算法分析

2021 Twelfth International Conference on Ubiquitous and Future Networks (ICUFN) Pub Date : 2021-08-17 DOI: 10.1109/ICUFN49451.2021.9528538

Farhan Siddiqui, Quan Chau

引用次数: 1

USRP Implementation of Transmission Timing Control Function for Synchronized SS-CDMA Using Wireless Two-Way Interferometry (Wi-Wi) 利用无线双向干涉技术(Wi-Wi) USRP实现同步SS-CDMA传输定时控制功能

2021 Twelfth International Conference on Ubiquitous and Future Networks (ICUFN) Pub Date : 2021-08-17 DOI: 10.1109/ICUFN49451.2021.9528697

S. Kameda, Yusaku Honma, N. Suematsu, S. Yasuda, N. Shiga

引用次数: 2

Construction of Frequency-Hopping System Using Carrier-Signal Generator 利用载波信号发生器构建跳频系统

2021 Twelfth International Conference on Ubiquitous and Future Networks (ICUFN) Pub Date : 2021-08-17 DOI: 10.1109/ICUFN49451.2021.9528677

E. Kudoh, Keisuke Watanabe

引用次数: 0