Pub Date : 2021-04-21DOI: 10.1109/WTS51064.2021.9433712
A. Gehani, Sri Harsha Shatagopam, Rahul Raghav, M. Sarkar, C. Paolini
Use of the LoRa low-power wide-area network modulation scheme with the LoRaWAN® (Long Range Wide Area Network) MAC layer is becoming popular for subterranean agro-informatics networking applications. LoRa uses chirp spread spectrum technology and is licensed by Semtech. Sensors with LoRa radios can be designed to detect and measure toxins that can leach into agricultural soils from industrial and storm water sources. Sensors can be buried with cameras that can detect and classify pathogens affecting the roots of plants. Sensor measurements and camera images can be sampled in situ and transmitted to an above-ground central LoRa concentrator (gateway) on a farm. LoRa devices can be buried at variable depth, however soil and water both attenuate the strength of a transmitted signal. In this work, we conduct experiments to measure the received signal strength indicator (RSSI) and signal-to-noise ratio (SNR) under different LoRa spreading factors, coding rates, and soil depths. Our results show LoRa transceiver burial depth should not exceed 50cm for agro-informatics applications.
{"title":"Application of 915 MHz Band LoRa for Agro-Informatics","authors":"A. Gehani, Sri Harsha Shatagopam, Rahul Raghav, M. Sarkar, C. Paolini","doi":"10.1109/WTS51064.2021.9433712","DOIUrl":"https://doi.org/10.1109/WTS51064.2021.9433712","url":null,"abstract":"Use of the LoRa low-power wide-area network modulation scheme with the LoRaWAN® (Long Range Wide Area Network) MAC layer is becoming popular for subterranean agro-informatics networking applications. LoRa uses chirp spread spectrum technology and is licensed by Semtech. Sensors with LoRa radios can be designed to detect and measure toxins that can leach into agricultural soils from industrial and storm water sources. Sensors can be buried with cameras that can detect and classify pathogens affecting the roots of plants. Sensor measurements and camera images can be sampled in situ and transmitted to an above-ground central LoRa concentrator (gateway) on a farm. LoRa devices can be buried at variable depth, however soil and water both attenuate the strength of a transmitted signal. In this work, we conduct experiments to measure the received signal strength indicator (RSSI) and signal-to-noise ratio (SNR) under different LoRa spreading factors, coding rates, and soil depths. Our results show LoRa transceiver burial depth should not exceed 50cm for agro-informatics applications.","PeriodicalId":443112,"journal":{"name":"2021 Wireless Telecommunications Symposium (WTS)","volume":"75 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130514407","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}
Pub Date : 2021-04-21DOI: 10.1109/WTS51064.2021.9433679
Xuan Luo, Mingyuan Zang, Ying Yan, L. Dittmann
Since Bluetooth5 standard released in 2016, its usage in commercial electronic products has been increased rapidly and substantially. Comparing to BLE 4.2, Bluetooth5 supports three PHY modes, respectively 2M, 1M and Coded PHY mode, providing a higher throughput and a wider range. Whereas there is a trade-off between its throughput and coverage. When the connection is established, the PHY mode is commonly pre-configured and fixed. This rigid design limits the flexibility in offering dynamic throughput and coverage. Therefore, we propose a method termed AptBLE, that switches the PHY mode in Bluetooth5 adaptively by considering the Received Signal Strength Indicator (RSSI) level. Specifically, we optimise the RSSI threshold for different PHY modes using the K-means clustering algorithm. Moreover, based on AptBLE, we further enable the Data Length Extension (DLE) feature and term the improved method as AptBLEM. We implement AptBLE (M) on the boards and test in indoor environment. The experimental results show that, AptBLE is more flexible, robust and outperforms the original fixed PHY mode in terms of throughput and transmission range. Furthermore, AptBLEM can triple the throughput than AptBLE, with a maximum throughput value in 1035Kbps and 42m range in indoor environment.
{"title":"AptBLE: Adaptive PHY Mode based on K-means Algorithm in Bluetooth5","authors":"Xuan Luo, Mingyuan Zang, Ying Yan, L. Dittmann","doi":"10.1109/WTS51064.2021.9433679","DOIUrl":"https://doi.org/10.1109/WTS51064.2021.9433679","url":null,"abstract":"Since Bluetooth5 standard released in 2016, its usage in commercial electronic products has been increased rapidly and substantially. Comparing to BLE 4.2, Bluetooth5 supports three PHY modes, respectively 2M, 1M and Coded PHY mode, providing a higher throughput and a wider range. Whereas there is a trade-off between its throughput and coverage. When the connection is established, the PHY mode is commonly pre-configured and fixed. This rigid design limits the flexibility in offering dynamic throughput and coverage. Therefore, we propose a method termed AptBLE, that switches the PHY mode in Bluetooth5 adaptively by considering the Received Signal Strength Indicator (RSSI) level. Specifically, we optimise the RSSI threshold for different PHY modes using the K-means clustering algorithm. Moreover, based on AptBLE, we further enable the Data Length Extension (DLE) feature and term the improved method as AptBLEM. We implement AptBLE (M) on the boards and test in indoor environment. The experimental results show that, AptBLE is more flexible, robust and outperforms the original fixed PHY mode in terms of throughput and transmission range. Furthermore, AptBLEM can triple the throughput than AptBLE, with a maximum throughput value in 1035Kbps and 42m range in indoor environment.","PeriodicalId":443112,"journal":{"name":"2021 Wireless Telecommunications Symposium (WTS)","volume":"655 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125968448","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}
Pub Date : 2021-04-21DOI: 10.1109/WTS51064.2021.9433710
Willie K. Harrison, M. Shoushtari
In this paper, we show that caching can aid in achieving secure communications by considering a wiretap scenario where the transmitter and legitimate receiver share access to a secure cache, and an eavesdropper is able to tap transmissions over a binary erasure wiretap channel during the delivery phase of a caching protocol. The scenario under consideration gives rise to a new channel model for wiretap coding that allows the transmitter to effectively choose a subset of bits to erase at the eavesdropper by caching the bits ahead of time. The eavesdropper observes the remainder of the coded bits through the wiretap channel for the general case. In the wiretap type-II scenario, the eavesdropper is able to choose a set of revealed bits only from the subset of bits not cached. We present a coding approach that allows efficient use of the cache to realize a caching gain in the network, and show how to use the cache to optimize the information theoretic security in the choice of a finite blocklength code and the choice of the cached bit set. To our knowledge, this is the first work on explicit algorithms for secrecy coding in any type of caching network.
{"title":"On Caching with Finite Blocklength Coding for Secrecy over the Binary Erasure Wiretap Channel","authors":"Willie K. Harrison, M. Shoushtari","doi":"10.1109/WTS51064.2021.9433710","DOIUrl":"https://doi.org/10.1109/WTS51064.2021.9433710","url":null,"abstract":"In this paper, we show that caching can aid in achieving secure communications by considering a wiretap scenario where the transmitter and legitimate receiver share access to a secure cache, and an eavesdropper is able to tap transmissions over a binary erasure wiretap channel during the delivery phase of a caching protocol. The scenario under consideration gives rise to a new channel model for wiretap coding that allows the transmitter to effectively choose a subset of bits to erase at the eavesdropper by caching the bits ahead of time. The eavesdropper observes the remainder of the coded bits through the wiretap channel for the general case. In the wiretap type-II scenario, the eavesdropper is able to choose a set of revealed bits only from the subset of bits not cached. We present a coding approach that allows efficient use of the cache to realize a caching gain in the network, and show how to use the cache to optimize the information theoretic security in the choice of a finite blocklength code and the choice of the cached bit set. To our knowledge, this is the first work on explicit algorithms for secrecy coding in any type of caching network.","PeriodicalId":443112,"journal":{"name":"2021 Wireless Telecommunications Symposium (WTS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130733212","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}
Pub Date : 2021-04-21DOI: 10.1109/WTS51064.2021.9433709
Edward J. Glantz, Michael R. Bartolacci, M. Nasereddin, D. Fusco, Joanne C. Peca, Devin Kachmar
Higher education is increasingly called upon to enhance cyber education, including hands-on "experiential" training. The good news is that additional tools and techniques are becoming more available, both in-house and through third parties, to provide cyber training environments and simulations at various features and price points. However, the training thus far has only focused on "traditional" Cybersecurity that lightly touches on wireless in undergraduate and master’s degree programs, and certifications. The purpose of this research is to identify and recognize nascent cyber training emphasizing a broader spectrum of wireless security and encourage curricular development that includes critical experiential training. Experiential wireless security training is important to keep pace with the growth in wireless communication mediums and associated Internet of Things (IoT) and Cyber Physical System (CPS) applications. Cyber faculty at a university offering undergraduate and master’s Cybersecurity degrees authored this paper; both degrees are offered to resident as well as online students.
{"title":"Wireless Cybersecurity Education: A Focus on Curriculum","authors":"Edward J. Glantz, Michael R. Bartolacci, M. Nasereddin, D. Fusco, Joanne C. Peca, Devin Kachmar","doi":"10.1109/WTS51064.2021.9433709","DOIUrl":"https://doi.org/10.1109/WTS51064.2021.9433709","url":null,"abstract":"Higher education is increasingly called upon to enhance cyber education, including hands-on \"experiential\" training. The good news is that additional tools and techniques are becoming more available, both in-house and through third parties, to provide cyber training environments and simulations at various features and price points. However, the training thus far has only focused on \"traditional\" Cybersecurity that lightly touches on wireless in undergraduate and master’s degree programs, and certifications. The purpose of this research is to identify and recognize nascent cyber training emphasizing a broader spectrum of wireless security and encourage curricular development that includes critical experiential training. Experiential wireless security training is important to keep pace with the growth in wireless communication mediums and associated Internet of Things (IoT) and Cyber Physical System (CPS) applications. Cyber faculty at a university offering undergraduate and master’s Cybersecurity degrees authored this paper; both degrees are offered to resident as well as online students.","PeriodicalId":443112,"journal":{"name":"2021 Wireless Telecommunications Symposium (WTS)","volume":"292 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114105575","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}
Pub Date : 2021-04-21DOI: 10.1109/WTS51064.2021.9433685
Elhadj Moustapha Diallo, Rong Chai, Tazeem Ahmad
Non-orthogonal multiple access (NOMA) and orthogonal frequency division multiple access (OFDMA) are two typical access techniques which can be applied for cellular systems. A hybrid scheme leveraging the advantages of NOMA and OMA schemes has been recently proved to be a promising approach to reduce the interference among users and enhance the performance of cellular device to device (D2D) networks. In this paper, we study the problem of resource allocation and mode selection for content fetching in a cellular D2D network. In order to improve the energy efficiency of the network, we formulate the joint problem as a system energy efficiency maximization problem. As this problem is a non-linear fractional problem that cannot be solved conveniently, we transform it into power allocation subproblem and content fetching mode selection subproblem, and then using the Lagrange dual method and a heuristic algorithm solve these two subproblems, respectively. The presented numerical results demonstrate the effectiveness of the proposed algorithm.
{"title":"Energy Efficient Resource Allocation and Mode Selection for Content Fetching in Cellular D2D Networks","authors":"Elhadj Moustapha Diallo, Rong Chai, Tazeem Ahmad","doi":"10.1109/WTS51064.2021.9433685","DOIUrl":"https://doi.org/10.1109/WTS51064.2021.9433685","url":null,"abstract":"Non-orthogonal multiple access (NOMA) and orthogonal frequency division multiple access (OFDMA) are two typical access techniques which can be applied for cellular systems. A hybrid scheme leveraging the advantages of NOMA and OMA schemes has been recently proved to be a promising approach to reduce the interference among users and enhance the performance of cellular device to device (D2D) networks. In this paper, we study the problem of resource allocation and mode selection for content fetching in a cellular D2D network. In order to improve the energy efficiency of the network, we formulate the joint problem as a system energy efficiency maximization problem. As this problem is a non-linear fractional problem that cannot be solved conveniently, we transform it into power allocation subproblem and content fetching mode selection subproblem, and then using the Lagrange dual method and a heuristic algorithm solve these two subproblems, respectively. The presented numerical results demonstrate the effectiveness of the proposed algorithm.","PeriodicalId":443112,"journal":{"name":"2021 Wireless Telecommunications Symposium (WTS)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122472512","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}
Pub Date : 2021-04-21DOI: 10.1109/WTS51064.2021.9433675
Lei Cao, R. Viswanathan
As the data delivery protocol in the Delay/ disruption-Tolerant Networks (DTN), the Bundle Protocol (BP) has gained much interest in its performance analysis. Existing analytic results in terms of the average file delivery time (AFDT) are mainly approximations, which provide reasonably close estimates in some cases but exhibit large discrepancies in other cases. In this paper, we point out a fallacy used in existing work, and, for the first time, provide an exact mathematical solution of the AFDT of the bundle protocol. This result works for both symmetric and asymmetric channel conditions, with either unlimited or limited total number of transmission rounds. Validation via simulation is also provided.
{"title":"Exact File Delivery Time of Bundle Protocol in Delay/disruption-Tolerant Networks","authors":"Lei Cao, R. Viswanathan","doi":"10.1109/WTS51064.2021.9433675","DOIUrl":"https://doi.org/10.1109/WTS51064.2021.9433675","url":null,"abstract":"As the data delivery protocol in the Delay/ disruption-Tolerant Networks (DTN), the Bundle Protocol (BP) has gained much interest in its performance analysis. Existing analytic results in terms of the average file delivery time (AFDT) are mainly approximations, which provide reasonably close estimates in some cases but exhibit large discrepancies in other cases. In this paper, we point out a fallacy used in existing work, and, for the first time, provide an exact mathematical solution of the AFDT of the bundle protocol. This result works for both symmetric and asymmetric channel conditions, with either unlimited or limited total number of transmission rounds. Validation via simulation is also provided.","PeriodicalId":443112,"journal":{"name":"2021 Wireless Telecommunications Symposium (WTS)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123826863","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}
Pub Date : 2021-04-21DOI: 10.1109/WTS51064.2021.9433682
Sunil Panthi, P. Amodio
The aeronautical broadband services ("inflight internet") with geostationary satellites have been expanding for the last two decades. The inflight internet transformed from being a privilege for business travelers to a necessity for every passenger. The unprecedented development of terrestrial fifth-generation (5G) applications and far-reaching aeronautical broadband services need to address the growing need for capacity. The International Telecommunication Union (ITU), responsible for promoting the shared global use of the radio spectrum, adopted provisions in governing the use of 4 GHz of Ka-band spectrum to terrestrial and space applications during the World Radiocommunication Conference 2019 (WRC 19). Sharing the spectrum requires keeping each party from unacceptable interferences. While operating in uplink frequency (27.5 GHz to 29.5 GHz), aeronautical broadband service ("Aeronautical Earth Station in Motion") must ensure compliance with Power Flux Density (PFD) envelop limits on the ground as defined by ITU. We study the co-existence of space and terrestrial application, present a methodology to examining the PFD conformity, and verify the methodology with a simulation. We recommend considering this methodology for examining conformity of aeronautical earth station in motion (A-ESIM) with respect to PFD limits in 27.5 GHz to 29.5 GHz bands.
{"title":"Study of Aeronautical Broadband Service Protecting Co-Frequency Terrestrial Services in Ka-band","authors":"Sunil Panthi, P. Amodio","doi":"10.1109/WTS51064.2021.9433682","DOIUrl":"https://doi.org/10.1109/WTS51064.2021.9433682","url":null,"abstract":"The aeronautical broadband services (\"inflight internet\") with geostationary satellites have been expanding for the last two decades. The inflight internet transformed from being a privilege for business travelers to a necessity for every passenger. The unprecedented development of terrestrial fifth-generation (5G) applications and far-reaching aeronautical broadband services need to address the growing need for capacity. The International Telecommunication Union (ITU), responsible for promoting the shared global use of the radio spectrum, adopted provisions in governing the use of 4 GHz of Ka-band spectrum to terrestrial and space applications during the World Radiocommunication Conference 2019 (WRC 19). Sharing the spectrum requires keeping each party from unacceptable interferences. While operating in uplink frequency (27.5 GHz to 29.5 GHz), aeronautical broadband service (\"Aeronautical Earth Station in Motion\") must ensure compliance with Power Flux Density (PFD) envelop limits on the ground as defined by ITU. We study the co-existence of space and terrestrial application, present a methodology to examining the PFD conformity, and verify the methodology with a simulation. We recommend considering this methodology for examining conformity of aeronautical earth station in motion (A-ESIM) with respect to PFD limits in 27.5 GHz to 29.5 GHz bands.","PeriodicalId":443112,"journal":{"name":"2021 Wireless Telecommunications Symposium (WTS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131036942","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}
Pub Date : 2021-04-21DOI: 10.1109/WTS51064.2021.9433714
Kyungchun Lee, Yeon-Ju Song, Jae-Seon Jang
The precise channel estimation is a prerequisite to acquire beamforming performance that the massive multi-input and multi-output (MIMO) system guarantees. There is pre-coding matrix indicator (PMI) based downlink beamforming as the beamforming method using downlink channel estimation. The PMI based downlink beamforming uses grid of beam (GoB) based on codebook. That is why it is challenging to track down the exact location of a mobile station and to obtain the maximum beamforming gain. The sounding reference signal (SRS) based downlink beamforming using uplink channel estimation gets the correlation coefficient between SRSs received from each receiver of a base station and obtains the maximum beamforming gain by tracking down the location of a mobile station accurately. However, as the SRS based downlink beamforming is required to be detected at each receiver of a base station, it has coverage limitation at the cell edge compared to the PMI based downlink beamforming using the combined feedback at a base station. This paper proposes that system obtains the maximum beamforming gain by using the SRS based downlink beamforming at the cell center and supplements coverage limitation by switching it to the PMI based downlink beamforming at the cell edge and using coherence bandwidth.
{"title":"Adaptive Downlink Beamforming based on SRS for Channel Estimation using Coherence Bandwidth Characteristic in sub-6GHz 5G NR","authors":"Kyungchun Lee, Yeon-Ju Song, Jae-Seon Jang","doi":"10.1109/WTS51064.2021.9433714","DOIUrl":"https://doi.org/10.1109/WTS51064.2021.9433714","url":null,"abstract":"The precise channel estimation is a prerequisite to acquire beamforming performance that the massive multi-input and multi-output (MIMO) system guarantees. There is pre-coding matrix indicator (PMI) based downlink beamforming as the beamforming method using downlink channel estimation. The PMI based downlink beamforming uses grid of beam (GoB) based on codebook. That is why it is challenging to track down the exact location of a mobile station and to obtain the maximum beamforming gain. The sounding reference signal (SRS) based downlink beamforming using uplink channel estimation gets the correlation coefficient between SRSs received from each receiver of a base station and obtains the maximum beamforming gain by tracking down the location of a mobile station accurately. However, as the SRS based downlink beamforming is required to be detected at each receiver of a base station, it has coverage limitation at the cell edge compared to the PMI based downlink beamforming using the combined feedback at a base station. This paper proposes that system obtains the maximum beamforming gain by using the SRS based downlink beamforming at the cell center and supplements coverage limitation by switching it to the PMI based downlink beamforming at the cell edge and using coherence bandwidth.","PeriodicalId":443112,"journal":{"name":"2021 Wireless Telecommunications Symposium (WTS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129845545","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}
Pub Date : 2021-04-21DOI: 10.1109/WTS51064.2021.9433683
Sai Bharadwaj Appakaya, R. Sankar, E. Sheybani
Speech processing has generated substantial research interest for telemonitoring and classification applications in healthcare due to the ease of acquisition and availability of established research protocols. This growing research interest has shown significant progress in processing Parkinsonian speech for monitoring and classification applications. A considerable portion of the studies in this research area focuses on developing automatic telemonitoring protocols with passive data collection using wearable or mobile devices. Most of these studies focus on using sustained vowel phonations and handcrafted features for training classifiers. Though some researchers suggest better suitability of connected/running speech for this application, fewer studies focus on it predominantly because of the processing complexity. This study focuses on using connected speech with pitch synchronous segmentation and convolutional Autoencoders for feature extraction from regular and advanced spectrograms. The spectrograms were created using pitch synchronous and block processing segmentations have been evaluated in this study. This methodology also aims to bypass data availability issues by using standardized TIMIT dataset for training Autoencoders. With Logistic regression and Linear SVM, we achieved 85% classification accuracy using the features from Autoencoders. Mean accuracy of 84% was obtained under leave one subject out (LOSO) classification indicating the performance reliability for entirely new data.
{"title":"Novel Unsupervised Feature Extraction Protocol using Autoencoders for Connected Speech: Application in Parkinson's Disease Classification","authors":"Sai Bharadwaj Appakaya, R. Sankar, E. Sheybani","doi":"10.1109/WTS51064.2021.9433683","DOIUrl":"https://doi.org/10.1109/WTS51064.2021.9433683","url":null,"abstract":"Speech processing has generated substantial research interest for telemonitoring and classification applications in healthcare due to the ease of acquisition and availability of established research protocols. This growing research interest has shown significant progress in processing Parkinsonian speech for monitoring and classification applications. A considerable portion of the studies in this research area focuses on developing automatic telemonitoring protocols with passive data collection using wearable or mobile devices. Most of these studies focus on using sustained vowel phonations and handcrafted features for training classifiers. Though some researchers suggest better suitability of connected/running speech for this application, fewer studies focus on it predominantly because of the processing complexity. This study focuses on using connected speech with pitch synchronous segmentation and convolutional Autoencoders for feature extraction from regular and advanced spectrograms. The spectrograms were created using pitch synchronous and block processing segmentations have been evaluated in this study. This methodology also aims to bypass data availability issues by using standardized TIMIT dataset for training Autoencoders. With Logistic regression and Linear SVM, we achieved 85% classification accuracy using the features from Autoencoders. Mean accuracy of 84% was obtained under leave one subject out (LOSO) classification indicating the performance reliability for entirely new data.","PeriodicalId":443112,"journal":{"name":"2021 Wireless Telecommunications Symposium (WTS)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115771919","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}
Pub Date : 2021-04-21DOI: 10.1109/WTS51064.2021.9433711
Cong Pu
Recent advancements in embedded sensing system, wireless communication technologies, big data, and artificial intelligence have fueled the development of Internet of Vehicles (IoV), where vehicles, road side unit (RSUs), and smart devices seamlessly interact with each other to enable the gathering and sharing of information on vehicles, roads, and their surrounds. As a fundamental component of IoV, vehicular networks (VANETs) are playing a critical role in processing, computing, and sharing travel-related information, which can help vehicles timely be aware of traffic situation and finally improve road safety and travel experience. However, due to the unique characteristics of vehicles, such as high mobility and sparse deployment making neighbor vehicles unacquainted and unknown to each other, VANETs are facing the challenge of evaluating the credibility of road safety messages. In this paper, we propose a blockchain-based trust management system using multi-criteria decision-making model, also referred to as $Trust_{MCDM}^{Block}$, in VANETs. In the $Trust_{MCDM}^{Block}$, each vehicle evaluates the credibility of received road safety message and generates the trust value of message originator. Due to the limited storage capacity, each vehicle periodically uploads the trust value to a nearby RSU. After receiving various trust values from vehicles, the RSU calculates the reputation value of message originator of road safety message using multi-criteria decision-making model, packs the reputation value into a block, and competes to add the block into blockchain. We evaluate the proposed $Trust_{MCDM}^{Block}$ approach through simulation experiments using OMNeT++ and compare its performance with prior blockchain-based decentralized trust management approach. The simulation results indicate that the proposed $Trust_{MCDM}^{Block}$ approach can not only improve fictitious message detection rate and malicious vehicle detection rate, but also can increase the number of dropped fictitious messages.
{"title":"A Novel Blockchain-Based Trust Management Scheme for Vehicular Networks","authors":"Cong Pu","doi":"10.1109/WTS51064.2021.9433711","DOIUrl":"https://doi.org/10.1109/WTS51064.2021.9433711","url":null,"abstract":"Recent advancements in embedded sensing system, wireless communication technologies, big data, and artificial intelligence have fueled the development of Internet of Vehicles (IoV), where vehicles, road side unit (RSUs), and smart devices seamlessly interact with each other to enable the gathering and sharing of information on vehicles, roads, and their surrounds. As a fundamental component of IoV, vehicular networks (VANETs) are playing a critical role in processing, computing, and sharing travel-related information, which can help vehicles timely be aware of traffic situation and finally improve road safety and travel experience. However, due to the unique characteristics of vehicles, such as high mobility and sparse deployment making neighbor vehicles unacquainted and unknown to each other, VANETs are facing the challenge of evaluating the credibility of road safety messages. In this paper, we propose a blockchain-based trust management system using multi-criteria decision-making model, also referred to as $Trust_{MCDM}^{Block}$, in VANETs. In the $Trust_{MCDM}^{Block}$, each vehicle evaluates the credibility of received road safety message and generates the trust value of message originator. Due to the limited storage capacity, each vehicle periodically uploads the trust value to a nearby RSU. After receiving various trust values from vehicles, the RSU calculates the reputation value of message originator of road safety message using multi-criteria decision-making model, packs the reputation value into a block, and competes to add the block into blockchain. We evaluate the proposed $Trust_{MCDM}^{Block}$ approach through simulation experiments using OMNeT++ and compare its performance with prior blockchain-based decentralized trust management approach. The simulation results indicate that the proposed $Trust_{MCDM}^{Block}$ approach can not only improve fictitious message detection rate and malicious vehicle detection rate, but also can increase the number of dropped fictitious messages.","PeriodicalId":443112,"journal":{"name":"2021 Wireless Telecommunications Symposium (WTS)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122575178","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：