Pub Date : 2019-07-25DOI: 10.1109/TSP.2019.8769118
J. Mekyska, Matej Istvanek, Lubomir Spurny, Z. Smékal
Beat detection systems are widely used in music information retrieval (MIR) research field for the computation of tempo and beat positions in audio signals. One of the most important parts of these systems is the onset detection function. The aim of this study is to introduce an enhancement of a conventional onset detector and employ it in a beat tracking system that could be utilized for an analysis of interpretation and performance changes in string quartets. The enhancement is based on the Teager-Kaiser energy operator (TKEO), which pre-processes input audio signal before spectral flux calculation. The proposed approach is firstly evaluated in terms of ability to estimate global tempo (GT) of a given audio track. Next, the accuracy of the GT estimation is compared with a manually-labelled reference dataset. Then, this system was tested on the first motif of the string quartet database. Results suggest that the TKEO could improve accuracy of the GT estimation. Average deviation from the reference tempo in the string quartet is 8.29%, which slightly improves the conventional methodology, where the deviance is 8.96%. This study has a pilot character and provides some suggestions of the beat tracking system enhancement.
{"title":"Enhancement of Beat Tracking in String Quartet Music Analysis Based on the Teager-Kaiser Energy Operator","authors":"J. Mekyska, Matej Istvanek, Lubomir Spurny, Z. Smékal","doi":"10.1109/TSP.2019.8769118","DOIUrl":"https://doi.org/10.1109/TSP.2019.8769118","url":null,"abstract":"Beat detection systems are widely used in music information retrieval (MIR) research field for the computation of tempo and beat positions in audio signals. One of the most important parts of these systems is the onset detection function. The aim of this study is to introduce an enhancement of a conventional onset detector and employ it in a beat tracking system that could be utilized for an analysis of interpretation and performance changes in string quartets. The enhancement is based on the Teager-Kaiser energy operator (TKEO), which pre-processes input audio signal before spectral flux calculation. The proposed approach is firstly evaluated in terms of ability to estimate global tempo (GT) of a given audio track. Next, the accuracy of the GT estimation is compared with a manually-labelled reference dataset. Then, this system was tested on the first motif of the string quartet database. Results suggest that the TKEO could improve accuracy of the GT estimation. Average deviation from the reference tempo in the string quartet is 8.29%, which slightly improves the conventional methodology, where the deviance is 8.96%. This study has a pilot character and provides some suggestions of the beat tracking system enhancement.","PeriodicalId":399087,"journal":{"name":"2019 42nd International Conference on Telecommunications and Signal Processing (TSP)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127276867","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 : 2019-07-01DOI: 10.1109/TSP.2019.8768887
Vojtech Myska, Radim Burget, Lukas Povoda, M. Dutta
Text classification is a process which analyses text and assigns one or more classes to it based on its content. This paper introduces a linguistically independent text classifier based on convolutional–recurrent neural networks. The classifier works at character level instead of some higher structures such as words, sentences, etc. To evaluate the accuracy of the proposed methodology, the Yelp data set and other multilingual data set obtained from film review databases containing Czech, German and Spanish languages were used. The resulting accuracy on the Yelp data set is 93,64%. We also proved that the proposed model can work for various languages.
{"title":"Linguistically independent sentiment analysis using convolutional-recurrent neural networks model","authors":"Vojtech Myska, Radim Burget, Lukas Povoda, M. Dutta","doi":"10.1109/TSP.2019.8768887","DOIUrl":"https://doi.org/10.1109/TSP.2019.8768887","url":null,"abstract":"Text classification is a process which analyses text and assigns one or more classes to it based on its content. This paper introduces a linguistically independent text classifier based on convolutional–recurrent neural networks. The classifier works at character level instead of some higher structures such as words, sentences, etc. To evaluate the accuracy of the proposed methodology, the Yelp data set and other multilingual data set obtained from film review databases containing Czech, German and Spanish languages were used. The resulting accuracy on the Yelp data set is 93,64%. We also proved that the proposed model can work for various languages.","PeriodicalId":399087,"journal":{"name":"2019 42nd International Conference on Telecommunications and Signal Processing (TSP)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115513837","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 : 2019-07-01DOI: 10.1109/TSP.2019.8769073
A. Shah, H. Ilhan, U. Tureli
Vehicular ad hoc networks (VANETs) have recently attracted interest for automation and intelligent transportation system (ITS). In this paper, to assess the performance of the IEEE 802.11p medium access control (MAC) for VANETs, an analytical model based on Markov chain model is presented. The parameters that could impact performance such as number of vehicles, velocity, vehicle density, contention window (CW) size, packet size, transmission range etc. are taken into consideration. The relationship among parameters and performance metrics are derived. The probability of successful transmission, throughput, and delay expressions are obtained. Furthermore, to verify the analytical studies numerical results are presented and whether the IEEE 802.11p can fulfill the performance criteria for VANETs or not is checked.
{"title":"Modeling and Performance Analysis of the IEEE 802.11P MAC for VANETs","authors":"A. Shah, H. Ilhan, U. Tureli","doi":"10.1109/TSP.2019.8769073","DOIUrl":"https://doi.org/10.1109/TSP.2019.8769073","url":null,"abstract":"Vehicular ad hoc networks (VANETs) have recently attracted interest for automation and intelligent transportation system (ITS). In this paper, to assess the performance of the IEEE 802.11p medium access control (MAC) for VANETs, an analytical model based on Markov chain model is presented. The parameters that could impact performance such as number of vehicles, velocity, vehicle density, contention window (CW) size, packet size, transmission range etc. are taken into consideration. The relationship among parameters and performance metrics are derived. The probability of successful transmission, throughput, and delay expressions are obtained. Furthermore, to verify the analytical studies numerical results are presented and whether the IEEE 802.11p can fulfill the performance criteria for VANETs or not is checked.","PeriodicalId":399087,"journal":{"name":"2019 42nd International Conference on Telecommunications and Signal Processing (TSP)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116188840","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 : 2019-07-01DOI: 10.1109/TSP.2019.8769057
P. Kamencay, M. Šinko, R. Hudec, M. Benco, R. Radil
This paper proposes a 3D surface registration algorithm based on the iterated closest point algorithm (ICP). The proposed algorithm uses the Scale-Invariant Feature Transform (SIFT) functions for initial alignment in combination with the K-Nearst Neighbor (KNN) algorithm for function comparison and the Iterative Closest Point (ICP) algorithm weighted for performing accurate registration. First, the point area properties are used for corresponding cloud point areas. Second, files with associated regions are classified to calculate the initial registration transformation matrix. Based on this combination, the correct matching points were extracted between the input data. The proposed registration approach is able to perform automatic registration without any assumptions about their initial positions. Experimental results using biomedical data (CT data) indicate the effectiveness of the proposed approach. Experimental results show that the proposed algorithm increases the number of correct function correspondences while reducing significantly corresponding errors compared to the original ICP and RPM algorithms.
{"title":"Improved Feature Point Algorithm for 3D Point Cloud Registration","authors":"P. Kamencay, M. Šinko, R. Hudec, M. Benco, R. Radil","doi":"10.1109/TSP.2019.8769057","DOIUrl":"https://doi.org/10.1109/TSP.2019.8769057","url":null,"abstract":"This paper proposes a 3D surface registration algorithm based on the iterated closest point algorithm (ICP). The proposed algorithm uses the Scale-Invariant Feature Transform (SIFT) functions for initial alignment in combination with the K-Nearst Neighbor (KNN) algorithm for function comparison and the Iterative Closest Point (ICP) algorithm weighted for performing accurate registration. First, the point area properties are used for corresponding cloud point areas. Second, files with associated regions are classified to calculate the initial registration transformation matrix. Based on this combination, the correct matching points were extracted between the input data. The proposed registration approach is able to perform automatic registration without any assumptions about their initial positions. Experimental results using biomedical data (CT data) indicate the effectiveness of the proposed approach. Experimental results show that the proposed algorithm increases the number of correct function correspondences while reducing significantly corresponding errors compared to the original ICP and RPM algorithms.","PeriodicalId":399087,"journal":{"name":"2019 42nd International Conference on Telecommunications and Signal Processing (TSP)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116377372","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 : 2019-07-01DOI: 10.1109/TSP.2019.8768834
Si-Phu Le, Chi‐Bao Le, H. Nguyen, Ngoc-Long Nguyen, Nhat-Tien Nguyen, D. Do, M. Voznák
This paper examines non-orthogonal multiple access (NOMA) and explores the effect of multiple antenna equipped at base station to serve many users who expect to multiple access to core network. This system model using multiple input single output (MISO) contributes enhancement on the outage performance of two NOMA end-users. We first introduce a simple model of power distribution to NOMA users who use both direct link and relay link to improve quality of transmission. Inspired by NOMA strategy, we then identify signal to noise ratio to discover separated signal for each user, and exact expressions of outage probability are developed in assumption that receiver can eliminate the interference completely with successive interference cancellation. Theoretical and simulation results show that the both suggested models can achieve the remarkable performance improvement of two NOMA users.
{"title":"Exploitting Performance Of Miso Based Non-Orthogonal Multiple Access","authors":"Si-Phu Le, Chi‐Bao Le, H. Nguyen, Ngoc-Long Nguyen, Nhat-Tien Nguyen, D. Do, M. Voznák","doi":"10.1109/TSP.2019.8768834","DOIUrl":"https://doi.org/10.1109/TSP.2019.8768834","url":null,"abstract":"This paper examines non-orthogonal multiple access (NOMA) and explores the effect of multiple antenna equipped at base station to serve many users who expect to multiple access to core network. This system model using multiple input single output (MISO) contributes enhancement on the outage performance of two NOMA end-users. We first introduce a simple model of power distribution to NOMA users who use both direct link and relay link to improve quality of transmission. Inspired by NOMA strategy, we then identify signal to noise ratio to discover separated signal for each user, and exact expressions of outage probability are developed in assumption that receiver can eliminate the interference completely with successive interference cancellation. Theoretical and simulation results show that the both suggested models can achieve the remarkable performance improvement of two NOMA users.","PeriodicalId":399087,"journal":{"name":"2019 42nd International Conference on Telecommunications and Signal Processing (TSP)","volume":"293 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116868462","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 : 2019-07-01DOI: 10.1109/TSP.2019.8769114
S. Rozum, Jan Kufa, L. Polak
The proposed Bluetooth Low Power (BLE) localization system focuses on simplifying deployment procedures in corridors while preserving the accuracy. It uses the Log-Distance path loss model, where the determination of environment constants is easier than creating fingerprints. Next, when the corridor is narrow enough (e.g., hospitals or office buildings), the perpendicular coordinate may not be required, and further simplification in the floor plan design can be adopted. That results in a simple line per corridor (1D system). To reduce fluctuations in the Received Signal Strength Indicator (RSSI) and achieve an easy and portable solution to perform measurements on several sites a wireless BLE Single Input Multiple Output (SIMO) system is introduced. The accuracy of the system for a fixed tag, placed in different spots on the line across the whole corridor, is better than 2. 4m in a 90% of measurements. The average error is 0.92 m without any filtration algorithms.
{"title":"Bluetooth Low Power Portable Indoor Positioning System Using SIMO Approach","authors":"S. Rozum, Jan Kufa, L. Polak","doi":"10.1109/TSP.2019.8769114","DOIUrl":"https://doi.org/10.1109/TSP.2019.8769114","url":null,"abstract":"The proposed Bluetooth Low Power (BLE) localization system focuses on simplifying deployment procedures in corridors while preserving the accuracy. It uses the Log-Distance path loss model, where the determination of environment constants is easier than creating fingerprints. Next, when the corridor is narrow enough (e.g., hospitals or office buildings), the perpendicular coordinate may not be required, and further simplification in the floor plan design can be adopted. That results in a simple line per corridor (1D system). To reduce fluctuations in the Received Signal Strength Indicator (RSSI) and achieve an easy and portable solution to perform measurements on several sites a wireless BLE Single Input Multiple Output (SIMO) system is introduced. The accuracy of the system for a fixed tag, placed in different spots on the line across the whole corridor, is better than 2. 4m in a 90% of measurements. The average error is 0.92 m without any filtration algorithms.","PeriodicalId":399087,"journal":{"name":"2019 42nd International Conference on Telecommunications and Signal Processing (TSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129943303","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 : 2019-07-01DOI: 10.1109/TSP.2019.8768869
Petr Blazek, Tomas Gerlich, Zdenek Martinasek
Distributed Denial of Service attacks (DDoS) are used by attackers for their effectiveness. This type of attack is one of the most devastating attacks in the Internet. Every year, the intensity of DDoS attacks increases and attackers use sophisticated multi-target DDoS attacks. In this paper, a modular system that allows to increase the filtering capacity linearly and allows to protect against the combination of DDoS attacks is designed and implemented. The main motivation for development of the modular filtering system was to find a cheap solution for filtering DDoS attacks with possibility to increase filtering capacity. The proposed system is based on open-source detection and filtration tools.
分布式拒绝服务攻击(Distributed Denial of Service attack, DDoS)因其有效性而被攻击者所使用。这种类型的攻击是互联网上最具破坏性的攻击之一。每年DDoS攻击的强度都在增加，攻击者采用了复杂的多目标DDoS攻击。本文设计并实现了一个模块化的系统，该系统可以线性增加过滤能力，并可以防止DDoS攻击的组合。开发模块化过滤系统的主要动机是找到一种廉价的解决方案来过滤DDoS攻击，并有可能增加过滤容量。该系统基于开源的检测和过滤工具。
{"title":"Scalable DDoS Mitigation System","authors":"Petr Blazek, Tomas Gerlich, Zdenek Martinasek","doi":"10.1109/TSP.2019.8768869","DOIUrl":"https://doi.org/10.1109/TSP.2019.8768869","url":null,"abstract":"Distributed Denial of Service attacks (DDoS) are used by attackers for their effectiveness. This type of attack is one of the most devastating attacks in the Internet. Every year, the intensity of DDoS attacks increases and attackers use sophisticated multi-target DDoS attacks. In this paper, a modular system that allows to increase the filtering capacity linearly and allows to protect against the combination of DDoS attacks is designed and implemented. The main motivation for development of the modular filtering system was to find a cheap solution for filtering DDoS attacks with possibility to increase filtering capacity. The proposed system is based on open-source detection and filtration tools.","PeriodicalId":399087,"journal":{"name":"2019 42nd International Conference on Telecommunications and Signal Processing (TSP)","volume":"1998 14","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121011490","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 : 2019-07-01DOI: 10.1109/TSP.2019.8768827
D. Kaplun, N. Chervyakov, P. Lyakhov, A. S. Ionisyan, M. Valueva, V. V. Gulvanskiy, Rangababu Peesapati
This paper considers the creation of video signal processing device. Important performance criteria of these devices are speed and power consumption. We used an Alinx AX309 board containing FPGA Xilinx Spartan6-xc6s1x9 as a hardware basis for the implementation of the system. OV7670 video camera was used to obtain a video signal. The output of the processed video was carried out on the Alinx AN430 LCD display and on the standard VGA port. We used the Residue Number System to accelerate calculations. It allowed to improve device speed by 28% compared to using traditional two’s complement number system.
{"title":"Hardware Implementation of Video Processing Device using Residue Number System","authors":"D. Kaplun, N. Chervyakov, P. Lyakhov, A. S. Ionisyan, M. Valueva, V. V. Gulvanskiy, Rangababu Peesapati","doi":"10.1109/TSP.2019.8768827","DOIUrl":"https://doi.org/10.1109/TSP.2019.8768827","url":null,"abstract":"This paper considers the creation of video signal processing device. Important performance criteria of these devices are speed and power consumption. We used an Alinx AX309 board containing FPGA Xilinx Spartan6-xc6s1x9 as a hardware basis for the implementation of the system. OV7670 video camera was used to obtain a video signal. The output of the processed video was carried out on the Alinx AN430 LCD display and on the standard VGA port. We used the Residue Number System to accelerate calculations. It allowed to improve device speed by 28% compared to using traditional two’s complement number system.","PeriodicalId":399087,"journal":{"name":"2019 42nd International Conference on Telecommunications and Signal Processing (TSP)","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121445579","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 : 2019-07-01DOI: 10.1109/TSP.2019.8769101
E. Kolárová, L. Brancík
In this paper we introduce stochastic ordinary and stochastic partial differential equations and apply the theory to the model of transmission line. First we consider transmission line with external sources affected by randomness. Here the theory of ordinary stochastic differential equations is applied. We illustrate the solution by an example, where we simulate the stochastic responses of the system. While considering stochastic effects inside of the transmission line, we have to use the stochastic partial differential equation model. Here we present the theoretical background of the situation.
{"title":"Noise Influenced Transmission Line Model via Partial Stochastic Differential Equations","authors":"E. Kolárová, L. Brancík","doi":"10.1109/TSP.2019.8769101","DOIUrl":"https://doi.org/10.1109/TSP.2019.8769101","url":null,"abstract":"In this paper we introduce stochastic ordinary and stochastic partial differential equations and apply the theory to the model of transmission line. First we consider transmission line with external sources affected by randomness. Here the theory of ordinary stochastic differential equations is applied. We illustrate the solution by an example, where we simulate the stochastic responses of the system. While considering stochastic effects inside of the transmission line, we have to use the stochastic partial differential equation model. Here we present the theoretical background of the situation.","PeriodicalId":399087,"journal":{"name":"2019 42nd International Conference on Telecommunications and Signal Processing (TSP)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114842555","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 : 2019-07-01DOI: 10.1109/TSP.2019.8769072
M. Z. A. Faiz, Ammar A. Al-hamadani
The proposed system had three stages in general, first stage was feature extraction, second stage was training a machine learning algorithm and third stage was online feature extraction and classification of ME/MI to control HRH. Variation for two kinds of feature extraction methods were proposed, Autoregressive (AR) coefficients and Common Spatial Pattern (CSP). Principal Component analysis (PCA) was used to reduce the dimensionality of AR feature. The output of the two methods were concatenated and normalized to train Support Vector Machine (SVM) algorithm. During online stage, EEG signal was acquired using EMOTIV EPOC EEG headset and same processing steps were applied as in training phase. The trained SVM module was used to predict the class of motion from the acquired EEG signal with 97.5% of online accuracy with the aid of majority voting. The predicted class was used as online signal to move the HRH to its corresponding hand gesture.
{"title":"Online Brain Computer Interface Based Five Classes EEG To Control Humanoid Robotic Hand","authors":"M. Z. A. Faiz, Ammar A. Al-hamadani","doi":"10.1109/TSP.2019.8769072","DOIUrl":"https://doi.org/10.1109/TSP.2019.8769072","url":null,"abstract":"The proposed system had three stages in general, first stage was feature extraction, second stage was training a machine learning algorithm and third stage was online feature extraction and classification of ME/MI to control HRH. Variation for two kinds of feature extraction methods were proposed, Autoregressive (AR) coefficients and Common Spatial Pattern (CSP). Principal Component analysis (PCA) was used to reduce the dimensionality of AR feature. The output of the two methods were concatenated and normalized to train Support Vector Machine (SVM) algorithm. During online stage, EEG signal was acquired using EMOTIV EPOC EEG headset and same processing steps were applied as in training phase. The trained SVM module was used to predict the class of motion from the acquired EEG signal with 97.5% of online accuracy with the aid of majority voting. The predicted class was used as online signal to move the HRH to its corresponding hand gesture.","PeriodicalId":399087,"journal":{"name":"2019 42nd International Conference on Telecommunications and Signal Processing (TSP)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130213143","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：