Pub Date : 2018-12-01DOI: 10.1109/ICSEE.2018.8646026
A. Frid, L. Manevitz, Ohad Mosafi
Classifying the degree of Parkinson’s disease is an important clinical necessity. Nonetheless, current methodology requires manual (and subjective) evaluation by a trained clinical expert. Recently, Machine Learning tools have been developed that can produce a classification of the presence of PD directly from the speech signal in an automated and objective fashion. However, these methods were not sufficient for the classification of the degree of the disease. In this work, we show how to apply and leverage topological information on the both the label space and the feature space of the speech signal in order to solve this problem.We address the problem by performing topological clustering (using a version of the Kohonen Self Organizing Map algorithm) of the feature space and then optimizing separate multi-class classifiers on each cluster.Using these methods, we can reliably train our system to classify new speech signal data to more than the 70% level on a 7 degree classification (where random level is 14%) which is close to the obtainable accuracy on the simple 2 class classification.
{"title":"Kohonen-Based Topological Clustering as an Amplifier for Multi-Class Classification for Parkinson’s Disease","authors":"A. Frid, L. Manevitz, Ohad Mosafi","doi":"10.1109/ICSEE.2018.8646026","DOIUrl":"https://doi.org/10.1109/ICSEE.2018.8646026","url":null,"abstract":"Classifying the degree of Parkinson’s disease is an important clinical necessity. Nonetheless, current methodology requires manual (and subjective) evaluation by a trained clinical expert. Recently, Machine Learning tools have been developed that can produce a classification of the presence of PD directly from the speech signal in an automated and objective fashion. However, these methods were not sufficient for the classification of the degree of the disease. In this work, we show how to apply and leverage topological information on the both the label space and the feature space of the speech signal in order to solve this problem.We address the problem by performing topological clustering (using a version of the Kohonen Self Organizing Map algorithm) of the feature space and then optimizing separate multi-class classifiers on each cluster.Using these methods, we can reliably train our system to classify new speech signal data to more than the 70% level on a 7 degree classification (where random level is 14%) which is close to the obtainable accuracy on the simple 2 class classification.","PeriodicalId":254455,"journal":{"name":"2018 IEEE International Conference on the Science of Electrical Engineering in Israel (ICSEE)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124253053","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 : 2018-12-01DOI: 10.1109/ICSEE.2018.8646219
Sahar Borafker, Miriam Drujin, S. Ben-Yaakov
A proposed voltage-dependent-capacitor tuning method for WPT systems was studied analytically, by simulation and verified experimentally. The circuit implementation applies common ferroelectric ceramic capacitors as voltage dependent elements. The experimental results on a mockup of autonomous mini-submarine charging, suggest that commercial ceramic capacitors are a viable option for tuning WPT.
{"title":"Voltage-Dependent-Capacitor Control of Wireless Power Transfer (WPT)","authors":"Sahar Borafker, Miriam Drujin, S. Ben-Yaakov","doi":"10.1109/ICSEE.2018.8646219","DOIUrl":"https://doi.org/10.1109/ICSEE.2018.8646219","url":null,"abstract":"A proposed voltage-dependent-capacitor tuning method for WPT systems was studied analytically, by simulation and verified experimentally. The circuit implementation applies common ferroelectric ceramic capacitors as voltage dependent elements. The experimental results on a mockup of autonomous mini-submarine charging, suggest that commercial ceramic capacitors are a viable option for tuning WPT.","PeriodicalId":254455,"journal":{"name":"2018 IEEE International Conference on the Science of Electrical Engineering in Israel (ICSEE)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116617065","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 : 2018-12-01DOI: 10.1109/ICSEE.2018.8646197
V. Manikandan, V. Masilamani
Capturing of videos from the television (TV) screens or from the theater screens by using the mobile cameras and its illegal distribution through video-sharing websites like YouTube, Dailymotion, Metacafe, etc. is a well-known challenge faced by the film industry. The video-sharing websites like YouTube does not encourage the illegal distribution of videos (without proper consent from the content owner). Currently, the YouTube has a facility to remove an illegally distributed video content from its video repository based on the request from the content owner. In general, the removal of an illegally distributed video may take a few days, hence during this period, the video may be downloaded by many of the people. The downloaded videos may be again distributed over the internet through different modes. This paper proposed a new technique which will classify a given video into normal video or screen captured video and it can be incorporated with video-sharing websites to prevent the illegal distribution of screen captured videos. The proposed scheme uses a support vector machine model which is trained using no-reference image quality measures. As far as our knowledge is concerned, there is no related work in this area.
{"title":"A Novel Machine Learning Approach to Prevent Illegal Distribution of Screen Captured Videos","authors":"V. Manikandan, V. Masilamani","doi":"10.1109/ICSEE.2018.8646197","DOIUrl":"https://doi.org/10.1109/ICSEE.2018.8646197","url":null,"abstract":"Capturing of videos from the television (TV) screens or from the theater screens by using the mobile cameras and its illegal distribution through video-sharing websites like YouTube, Dailymotion, Metacafe, etc. is a well-known challenge faced by the film industry. The video-sharing websites like YouTube does not encourage the illegal distribution of videos (without proper consent from the content owner). Currently, the YouTube has a facility to remove an illegally distributed video content from its video repository based on the request from the content owner. In general, the removal of an illegally distributed video may take a few days, hence during this period, the video may be downloaded by many of the people. The downloaded videos may be again distributed over the internet through different modes. This paper proposed a new technique which will classify a given video into normal video or screen captured video and it can be incorporated with video-sharing websites to prevent the illegal distribution of screen captured videos. The proposed scheme uses a support vector machine model which is trained using no-reference image quality measures. As far as our knowledge is concerned, there is no related work in this area.","PeriodicalId":254455,"journal":{"name":"2018 IEEE International Conference on the Science of Electrical Engineering in Israel (ICSEE)","volume":"53 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123179225","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 : 2018-12-01DOI: 10.1109/ICSEE.2018.8646013
L. Dery, Oren Musicant
People with Attention Deficit Hyperactivity Disorder (ADHD) have been reported to be involved in more crash accidents and near-crash incidents. In this paper, we suggest that driving patterns may be used to detect the existence of ADHD. We analyzed driving behavior and phone usage during driving, as obtained during a naturalistic driving study. Our preliminary results show that $sim 88$% of ADHD-drivers can be detected by their driving pattern, such as extreme events during driving, speed and phone usage.
{"title":"ADHD Detection from Driving Patterns","authors":"L. Dery, Oren Musicant","doi":"10.1109/ICSEE.2018.8646013","DOIUrl":"https://doi.org/10.1109/ICSEE.2018.8646013","url":null,"abstract":"People with Attention Deficit Hyperactivity Disorder (ADHD) have been reported to be involved in more crash accidents and near-crash incidents. In this paper, we suggest that driving patterns may be used to detect the existence of ADHD. We analyzed driving behavior and phone usage during driving, as obtained during a naturalistic driving study. Our preliminary results show that $sim 88$% of ADHD-drivers can be detected by their driving pattern, such as extreme events during driving, speed and phone usage.","PeriodicalId":254455,"journal":{"name":"2018 IEEE International Conference on the Science of Electrical Engineering in Israel (ICSEE)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123746509","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 : 2018-12-01DOI: 10.1109/ICSEE.2018.8646170
O. Levi, D. Raphaeli
In this paper we present an approach to reduce the receiver dynamic range in wireline channels, by decreasing the peak to average power ratio (PAPR) at the analog to digital converter (ADC) input. The suggested approach uses precoding at the transmitter which creates a maximal entropy distribution, such that symbol sequences that will result to high peak power values at the receiver are avoided. The overall gain of such shaped system is measured compared to a non-shaped system. For 8-PAM system over typical wireline channel, an overall theoretical gain of 3 dB is achievable with data rate of 2.5 biysymbol. The suggested approach can be used to improve any wireline communication link, limited by the ADC saturation point.
{"title":"Transmitter Precoding for Reducing Receiver Dynamic Range in Wireline Channels","authors":"O. Levi, D. Raphaeli","doi":"10.1109/ICSEE.2018.8646170","DOIUrl":"https://doi.org/10.1109/ICSEE.2018.8646170","url":null,"abstract":"In this paper we present an approach to reduce the receiver dynamic range in wireline channels, by decreasing the peak to average power ratio (PAPR) at the analog to digital converter (ADC) input. The suggested approach uses precoding at the transmitter which creates a maximal entropy distribution, such that symbol sequences that will result to high peak power values at the receiver are avoided. The overall gain of such shaped system is measured compared to a non-shaped system. For 8-PAM system over typical wireline channel, an overall theoretical gain of 3 dB is achievable with data rate of 2.5 biysymbol. The suggested approach can be used to improve any wireline communication link, limited by the ADC saturation point.","PeriodicalId":254455,"journal":{"name":"2018 IEEE International Conference on the Science of Electrical Engineering in Israel (ICSEE)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123838279","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 : 2018-12-01DOI: 10.1109/ICSEE.2018.8646089
Ofer Schwartz, Aviv David, Ofer Shahen-Tov, S. Gannot
Voice activity detection (VAD), namely determining whether a speech signal is active or inactive, and single talk detector (STD), namely detecting that only one speaker is active, are important building blocks in many speech processing applications. A speaker-localization stage (such as the steered response power (SRP)) is often concurrently implemented on the same device.In this paper, the spatial properties of the SRP are utilized for improving the performance of both the voice activity detector (VAD) and the STD. We propose to measure the entropy at the SRP output and compare with the typical entropy of noise-only frames. This feature utilizes spatial information and may therefore become advantageous in nonstationary noise environments. The STD can then be implemented by determining local minimum values of the entropy measure of the SRP.The proposed VAD was tested for a single speaker with two cases, directional background noise with changing level and with a background music source. The proposed STD was tested using real recordings of two concurrent speakers.
{"title":"Multi-microphone voice activity and single-talk detectors based on steered-response power output entropy","authors":"Ofer Schwartz, Aviv David, Ofer Shahen-Tov, S. Gannot","doi":"10.1109/ICSEE.2018.8646089","DOIUrl":"https://doi.org/10.1109/ICSEE.2018.8646089","url":null,"abstract":"Voice activity detection (VAD), namely determining whether a speech signal is active or inactive, and single talk detector (STD), namely detecting that only one speaker is active, are important building blocks in many speech processing applications. A speaker-localization stage (such as the steered response power (SRP)) is often concurrently implemented on the same device.In this paper, the spatial properties of the SRP are utilized for improving the performance of both the voice activity detector (VAD) and the STD. We propose to measure the entropy at the SRP output and compare with the typical entropy of noise-only frames. This feature utilizes spatial information and may therefore become advantageous in nonstationary noise environments. The STD can then be implemented by determining local minimum values of the entropy measure of the SRP.The proposed VAD was tested for a single speaker with two cases, directional background noise with changing level and with a background music source. The proposed STD was tested using real recordings of two concurrent speakers.","PeriodicalId":254455,"journal":{"name":"2018 IEEE International Conference on the Science of Electrical Engineering in Israel (ICSEE)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126151645","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 : 2018-12-01DOI: 10.1109/ICSEE.2018.8646071
I. Rusnak
Problems of state estimation and the optimal-best linear approximation of continuous time-variant non-linear system are formulated. A solution is proposed by generalization of the State and Parameters Observability Canonical form - SPOC to parameters varying systems. The SPOC representation of linear parameter varying systems enables application of tools from the existing estimation theories for linear time-varying systems to state estimation and identification of nonlinear systems. The solution is explicit, in closed form and gives recursive formulas of the optimal filter. The performance of the proposed algorithm is demonstrated for parameters varying parameters by simulations.
{"title":"Application of the SPOC form to Estimation and Identification of Nonlinear Systems","authors":"I. Rusnak","doi":"10.1109/ICSEE.2018.8646071","DOIUrl":"https://doi.org/10.1109/ICSEE.2018.8646071","url":null,"abstract":"Problems of state estimation and the optimal-best linear approximation of continuous time-variant non-linear system are formulated. A solution is proposed by generalization of the State and Parameters Observability Canonical form - SPOC to parameters varying systems. The SPOC representation of linear parameter varying systems enables application of tools from the existing estimation theories for linear time-varying systems to state estimation and identification of nonlinear systems. The solution is explicit, in closed form and gives recursive formulas of the optimal filter. The performance of the proposed algorithm is demonstrated for parameters varying parameters by simulations.","PeriodicalId":254455,"journal":{"name":"2018 IEEE International Conference on the Science of Electrical Engineering in Israel (ICSEE)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125918054","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 : 2018-12-01DOI: 10.1109/ICSEE.2018.8646161
A. Vaintraub, R. Kahn, S. Weiss
Prefetching has been a commonplace feature in the general purpose CPU world for more than a decade but has been much less common in the embedded and mobile world, moreover it has not been utilized for DSPs. The goal of this paper is to adapt and simulate straight-forward hardware prefetching techniques for embedded DSPs, assess their performance using the cycle count metric and find their potential improvement under the strict constraints of low power and low complexity. By using industry standard benchmarks we come to the conclusion that even though these algorithms exhibit a very high inherent hit rate, total cycle count improvement is possible due to relatively high external memory delay that stems from shared buses. Several parameters are simulated, including but not limited to cache size, number of prefetched blocks and the use of a small FIFO buffer to store the prefetched blocks as opposed to writing them directly into cache memory. We show that even a small FIFO buffer results in an improvement of 8% on average and up to 35% in total cycle count even in traces that exhibited a cache hit rate of over 99% without prefetching. We also show that a small prefetch buffer enables us to halve the cache size with no discernible effect on performance.
{"title":"Cache Prefetching in Embedded DSPs","authors":"A. Vaintraub, R. Kahn, S. Weiss","doi":"10.1109/ICSEE.2018.8646161","DOIUrl":"https://doi.org/10.1109/ICSEE.2018.8646161","url":null,"abstract":"Prefetching has been a commonplace feature in the general purpose CPU world for more than a decade but has been much less common in the embedded and mobile world, moreover it has not been utilized for DSPs. The goal of this paper is to adapt and simulate straight-forward hardware prefetching techniques for embedded DSPs, assess their performance using the cycle count metric and find their potential improvement under the strict constraints of low power and low complexity. By using industry standard benchmarks we come to the conclusion that even though these algorithms exhibit a very high inherent hit rate, total cycle count improvement is possible due to relatively high external memory delay that stems from shared buses. Several parameters are simulated, including but not limited to cache size, number of prefetched blocks and the use of a small FIFO buffer to store the prefetched blocks as opposed to writing them directly into cache memory. We show that even a small FIFO buffer results in an improvement of 8% on average and up to 35% in total cycle count even in traces that exhibited a cache hit rate of over 99% without prefetching. We also show that a small prefetch buffer enables us to halve the cache size with no discernible effect on performance.","PeriodicalId":254455,"journal":{"name":"2018 IEEE International Conference on the Science of Electrical Engineering in Israel (ICSEE)","volume":"2016 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125735614","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 : 2018-12-01DOI: 10.1109/ICSEE.2018.8646005
Ofir Krengel, Eli Appleboim, Yehoshua Y.Zeevi
Inpainting of images, represented on surfaces, was previously considered successfully by the application of a two-dimensional Laplacian operator, including in the context of the discrete representation on surfaces. Considering the shortcoming of errors and computational complexity of the strictly-two-dimensional approaches, we propose a one-dimensional-based multi-line approach, wherein the set of lines cover the region of inpainting and its boundaries. The multi-line framework is implemented on smooth and non-smooth surfaces and on images and the results are found to be superior to the previously published results. Additional possible one-dimensional representations are discussed.
{"title":"Inpainting of surfaces and Images","authors":"Ofir Krengel, Eli Appleboim, Yehoshua Y.Zeevi","doi":"10.1109/ICSEE.2018.8646005","DOIUrl":"https://doi.org/10.1109/ICSEE.2018.8646005","url":null,"abstract":"Inpainting of images, represented on surfaces, was previously considered successfully by the application of a two-dimensional Laplacian operator, including in the context of the discrete representation on surfaces. Considering the shortcoming of errors and computational complexity of the strictly-two-dimensional approaches, we propose a one-dimensional-based multi-line approach, wherein the set of lines cover the region of inpainting and its boundaries. The multi-line framework is implemented on smooth and non-smooth surfaces and on images and the results are found to be superior to the previously published results. Additional possible one-dimensional representations are discussed.","PeriodicalId":254455,"journal":{"name":"2018 IEEE International Conference on the Science of Electrical Engineering in Israel (ICSEE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129218707","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 : 2018-12-01DOI: 10.1109/ICSEE.2018.8646046
Y. Levi, Ayal Taitler, I. Keslassy
In this paper, we consider the practical problem of scheduling traffic lights to reduce the average vehicle waiting times. We find that existing scheduling algorithms have lackluster performance. Instead, we introduce two algorithms. First, extended CMSM (eCMSM), which extends CMSM from a switch scheduling model to a general traffic-light scheduling model. We prove that eCMSM can optimally schedule any traffic batch. Second, we introduce Front-Pressure (FP), which aims to further reduce the average waiting time at general intersections. We then evaluate empirically these two algorithms. We find that when using them, the best average waiting time can be improved in 98% of the simulations when compared to several existing algorithms, most significantly in congested settings.
{"title":"Unspread the Jam: Scheduling Traffic Lights to Reduce Congestion","authors":"Y. Levi, Ayal Taitler, I. Keslassy","doi":"10.1109/ICSEE.2018.8646046","DOIUrl":"https://doi.org/10.1109/ICSEE.2018.8646046","url":null,"abstract":"In this paper, we consider the practical problem of scheduling traffic lights to reduce the average vehicle waiting times. We find that existing scheduling algorithms have lackluster performance. Instead, we introduce two algorithms. First, extended CMSM (eCMSM), which extends CMSM from a switch scheduling model to a general traffic-light scheduling model. We prove that eCMSM can optimally schedule any traffic batch. Second, we introduce Front-Pressure (FP), which aims to further reduce the average waiting time at general intersections. We then evaluate empirically these two algorithms. We find that when using them, the best average waiting time can be improved in 98% of the simulations when compared to several existing algorithms, most significantly in congested settings.","PeriodicalId":254455,"journal":{"name":"2018 IEEE International Conference on the Science of Electrical Engineering in Israel (ICSEE)","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133477020","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：