Pub Date : 2017-07-01DOI: 10.1109/ISSCS.2017.8034885
A. Pasarica, O. Eva, D. Tarniceriu
The analysis of electroencephalographic (EEG) signals for motor imagery applications using the partial directed coherence (PDC) method highlights significant differences between channel pairs that correspond to movement and movement imagination brain activities. We improve the analysis based on PDC by decomposing the EEG signal into frequency components, in order to identify the frequency bands that are mostly influenced by motor imagery activity. We focus on the channel pairs Cz-FP1 and FP1-FP2 due to the fact that they show the highest difference when consider the PDC indicator mean values obtained for the recordings from the dataset. We compute the statistical difference between movement and movement imagery recordings by means of data dispersion and Student “t” test. These results are used to identify channels that are suitable for motor imagery application, in order to reduce the computational complexity of the brain computer interface (BCI) system and the corresponding algorithm.
{"title":"Analysis of EEG channel coupling for motor imagery applications","authors":"A. Pasarica, O. Eva, D. Tarniceriu","doi":"10.1109/ISSCS.2017.8034885","DOIUrl":"https://doi.org/10.1109/ISSCS.2017.8034885","url":null,"abstract":"The analysis of electroencephalographic (EEG) signals for motor imagery applications using the partial directed coherence (PDC) method highlights significant differences between channel pairs that correspond to movement and movement imagination brain activities. We improve the analysis based on PDC by decomposing the EEG signal into frequency components, in order to identify the frequency bands that are mostly influenced by motor imagery activity. We focus on the channel pairs Cz-FP1 and FP1-FP2 due to the fact that they show the highest difference when consider the PDC indicator mean values obtained for the recordings from the dataset. We compute the statistical difference between movement and movement imagery recordings by means of data dispersion and Student “t” test. These results are used to identify channels that are suitable for motor imagery application, in order to reduce the computational complexity of the brain computer interface (BCI) system and the corresponding algorithm.","PeriodicalId":338255,"journal":{"name":"2017 International Symposium on Signals, Circuits and Systems (ISSCS)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122230688","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 : 2017-07-01DOI: 10.1109/ISSCS.2017.8034944
L. Grama, Elena Roxana Buhus, C. Rusu
In this work we compare different classification algorithms applied on different number of features (linear predictive coding coefficients) in order to detect audio signals from wildlife areas. The final goal is to find the appropriate number of linear predictive coding coefficients to provide the desired accuracy for a certain framework. The experimental results prove that the best classifier is Logistic Model Trees regardless the number of features, having a constant classification accuracy greater than 95%. In the case of a reduced number of features, both Random Forest and Lazy IBk have good results; the classification accuracy is greater than 98%.
在这项工作中，我们比较了应用于不同数量的特征(线性预测编码系数)的不同分类算法，以检测来自野生动物区域的音频信号。最终目标是找到适当数量的线性预测编码系数，为特定框架提供所需的精度。实验结果证明，无论特征个数多少，最佳分类器都是Logistic模型树(Logistic Model Trees)，分类准确率恒定在95%以上。在特征数量减少的情况下，随机森林和懒惰IBk都有很好的结果;分类准确率大于98%。
{"title":"Acoustic classification using linear predictive coding for wildlife detection systems","authors":"L. Grama, Elena Roxana Buhus, C. Rusu","doi":"10.1109/ISSCS.2017.8034944","DOIUrl":"https://doi.org/10.1109/ISSCS.2017.8034944","url":null,"abstract":"In this work we compare different classification algorithms applied on different number of features (linear predictive coding coefficients) in order to detect audio signals from wildlife areas. The final goal is to find the appropriate number of linear predictive coding coefficients to provide the desired accuracy for a certain framework. The experimental results prove that the best classifier is Logistic Model Trees regardless the number of features, having a constant classification accuracy greater than 95%. In the case of a reduced number of features, both Random Forest and Lazy IBk have good results; the classification accuracy is greater than 98%.","PeriodicalId":338255,"journal":{"name":"2017 International Symposium on Signals, Circuits and Systems (ISSCS)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129768697","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 : 2017-07-01DOI: 10.1109/ISSCS.2017.8034923
Liviu-Daniel Stefan, Ionut Mironica, C. Mitrea, B. Ionescu
Convolutional Neural Networks (CNNs) are responsible for major breakthroughs in object recognition in still images. This work presents an end to end very deep architecture with small convolutional kernel size, small convolutional strides and very deep network architecture for person re-identification in video streams. To achieve such system several good practices for the training were tested, namely: (i) training from scratch, (ii) pre-training last layer, (iii) small learning rates, (iv) data augmentation techniques, (v) high dropout ratio. The key contribution of this paper is a trainable, end-to-end deep network approach that allows for effective re-identification in real time of people in multiple-stream video from various sources (indoor and outdoor). Experimental evaluation was conducted on a real-world publicly available dataset showing the benefits of this approach.
{"title":"End to end very deep person re-identification","authors":"Liviu-Daniel Stefan, Ionut Mironica, C. Mitrea, B. Ionescu","doi":"10.1109/ISSCS.2017.8034923","DOIUrl":"https://doi.org/10.1109/ISSCS.2017.8034923","url":null,"abstract":"Convolutional Neural Networks (CNNs) are responsible for major breakthroughs in object recognition in still images. This work presents an end to end very deep architecture with small convolutional kernel size, small convolutional strides and very deep network architecture for person re-identification in video streams. To achieve such system several good practices for the training were tested, namely: (i) training from scratch, (ii) pre-training last layer, (iii) small learning rates, (iv) data augmentation techniques, (v) high dropout ratio. The key contribution of this paper is a trainable, end-to-end deep network approach that allows for effective re-identification in real time of people in multiple-stream video from various sources (indoor and outdoor). Experimental evaluation was conducted on a real-world publicly available dataset showing the benefits of this approach.","PeriodicalId":338255,"journal":{"name":"2017 International Symposium on Signals, Circuits and Systems (ISSCS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131125016","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 : 2017-07-01DOI: 10.1109/ISSCS.2017.8034935
Viorel-Stefan Savinescu, Ioan-Alexandru Nica, L. Goras
A detailed analysis of the nonideal behavior of a cross-coupled CMOS transistor pair used to implement negative resistances and capacitors is presented. Improvement solutions are given as well.
详细分析了用于实现负电阻和负电容的交叉耦合CMOS晶体管对的非理想行为。并给出了改进方案。
{"title":"On the non-ideal behavior of a cross-coupled CMOS transistor Negative Impedance Circuit","authors":"Viorel-Stefan Savinescu, Ioan-Alexandru Nica, L. Goras","doi":"10.1109/ISSCS.2017.8034935","DOIUrl":"https://doi.org/10.1109/ISSCS.2017.8034935","url":null,"abstract":"A detailed analysis of the nonideal behavior of a cross-coupled CMOS transistor pair used to implement negative resistances and capacitors is presented. Improvement solutions are given as well.","PeriodicalId":338255,"journal":{"name":"2017 International Symposium on Signals, Circuits and Systems (ISSCS)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132154436","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 : 2017-07-01DOI: 10.1109/ISSCS.2017.8034891
R. Bozomitu, A. Pasarica, R. Lupu, C. Rotariu, E. Coca
In this paper a new pupil detection algorithm based on RANSAC procedure is presented. Unlike other similar algorithms reported in the literature, the proposed algorithm provides higher accuracy, low running time and operates properly in noise conditions and for variable illumination. This algorithm is used in the field of assistive technology in order to communicate with neuromotor disabled people by detecting their gaze direction, and can easily be adapted for other applications, such as PC control using eye-gaze detection.
{"title":"Pupil detection algorithm based on RANSAC procedure","authors":"R. Bozomitu, A. Pasarica, R. Lupu, C. Rotariu, E. Coca","doi":"10.1109/ISSCS.2017.8034891","DOIUrl":"https://doi.org/10.1109/ISSCS.2017.8034891","url":null,"abstract":"In this paper a new pupil detection algorithm based on RANSAC procedure is presented. Unlike other similar algorithms reported in the literature, the proposed algorithm provides higher accuracy, low running time and operates properly in noise conditions and for variable illumination. This algorithm is used in the field of assistive technology in order to communicate with neuromotor disabled people by detecting their gaze direction, and can easily be adapted for other applications, such as PC control using eye-gaze detection.","PeriodicalId":338255,"journal":{"name":"2017 International Symposium on Signals, Circuits and Systems (ISSCS)","volume":"176 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122101538","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 : 2017-07-01DOI: 10.1109/ISSCS.2017.8034873
S. Demir, O. Aydin
More than two decades, circuit switched systems have been replaced by packet switched systems in telecommunication infrastructure. However, there are considerable amount of circuit switched equipment in telecommunication networks. Therefore, interconnection of existing circuit switched networks with packet switched networks is needed. For this reason, new methods are still being developed to transport circuit switched services over packet switched networks. The aim of this paper is to propose a new method for clock synchronization with fast response, high accuracy and suitable for the implementation on real-time systems. The proposed method is tested on a network with the standard TDM interfaces of 2.048 Mbps, 8.448 Mbps, 34.368 Mbps and the packet interface of 1 Gbps Ethernet. The results show that the proposed method accomplishes high performance.
{"title":"A new adaptive clock synchronization method based on timestamp and jitter buffer for TDMoIP systems","authors":"S. Demir, O. Aydin","doi":"10.1109/ISSCS.2017.8034873","DOIUrl":"https://doi.org/10.1109/ISSCS.2017.8034873","url":null,"abstract":"More than two decades, circuit switched systems have been replaced by packet switched systems in telecommunication infrastructure. However, there are considerable amount of circuit switched equipment in telecommunication networks. Therefore, interconnection of existing circuit switched networks with packet switched networks is needed. For this reason, new methods are still being developed to transport circuit switched services over packet switched networks. The aim of this paper is to propose a new method for clock synchronization with fast response, high accuracy and suitable for the implementation on real-time systems. The proposed method is tested on a network with the standard TDM interfaces of 2.048 Mbps, 8.448 Mbps, 34.368 Mbps and the packet interface of 1 Gbps Ethernet. The results show that the proposed method accomplishes high performance.","PeriodicalId":338255,"journal":{"name":"2017 International Symposium on Signals, Circuits and Systems (ISSCS)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130149530","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 : 2017-07-01DOI: 10.1109/ISSCS.2017.8034930
R. Matei
This paper proposes an analytical design method for a class of two-dimensional recursive zero-phase filters with a shape specified in polar coordinates in the frequency plane. The design is based on applying a frequency transformation to a given 1D prototype filter, which leads to the 2D filter with a desired shape. For each particular 2D filter, the design consists in finding the appropriate frequency transformation. The resulted filters are efficient, of low order and relatively high selectivity. Simulation results are provided for one type of filter, to show its capabilities in image filtering.
{"title":"Design approach for a class of 2D recursive filters","authors":"R. Matei","doi":"10.1109/ISSCS.2017.8034930","DOIUrl":"https://doi.org/10.1109/ISSCS.2017.8034930","url":null,"abstract":"This paper proposes an analytical design method for a class of two-dimensional recursive zero-phase filters with a shape specified in polar coordinates in the frequency plane. The design is based on applying a frequency transformation to a given 1D prototype filter, which leads to the 2D filter with a desired shape. For each particular 2D filter, the design consists in finding the appropriate frequency transformation. The resulted filters are efficient, of low order and relatively high selectivity. Simulation results are provided for one type of filter, to show its capabilities in image filtering.","PeriodicalId":338255,"journal":{"name":"2017 International Symposium on Signals, Circuits and Systems (ISSCS)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129564408","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 : 2017-07-01DOI: 10.1109/ISSCS.2017.8034914
M. Constantin, B. Ionescu
In this article we analyze the prediction of image interestingness, a domain that is gaining importance in the fields such as recommendation systems, social media and advertising. We investigate the contribution of early and late fusion techniques, while using a set of image descriptors and analyze the best combinations that predict interestingness. Experimental validation is carried out on the MediaEval 2016 Predicting Media Interestingness image dataset. Results show the benefit of the introduction of late fusion approaches to solve the task, allowing to achieve better results than the state of the art.
{"title":"Content description for Predicting image Interestingness","authors":"M. Constantin, B. Ionescu","doi":"10.1109/ISSCS.2017.8034914","DOIUrl":"https://doi.org/10.1109/ISSCS.2017.8034914","url":null,"abstract":"In this article we analyze the prediction of image interestingness, a domain that is gaining importance in the fields such as recommendation systems, social media and advertising. We investigate the contribution of early and late fusion techniques, while using a set of image descriptors and analyze the best combinations that predict interestingness. Experimental validation is carried out on the MediaEval 2016 Predicting Media Interestingness image dataset. Results show the benefit of the introduction of late fusion approaches to solve the task, allowing to achieve better results than the state of the art.","PeriodicalId":338255,"journal":{"name":"2017 International Symposium on Signals, Circuits and Systems (ISSCS)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117028698","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 : 2017-07-01DOI: 10.1109/ISSCS.2017.8034949
M. Marin, F. Constantinescu, O. Taus, A. Gheorghe
Measurements of the intermodulation products with frequency 2ƒ1−ƒ2 (ƒ1 - transmitter frequency, ƒ2 - antenna frequency) for a W-CDMA professional duplexer filter are presented. It is proved that the 2ƒ1 signal and the intermodulation product are generated in this power BAW filter, despite its careful design.
{"title":"Intermodulation products in AlN power BAW duplexer filters","authors":"M. Marin, F. Constantinescu, O. Taus, A. Gheorghe","doi":"10.1109/ISSCS.2017.8034949","DOIUrl":"https://doi.org/10.1109/ISSCS.2017.8034949","url":null,"abstract":"Measurements of the intermodulation products with frequency 2ƒ<inf>1</inf>−ƒ<inf>2</inf> (ƒ<inf>1</inf> - transmitter frequency, ƒ<inf>2</inf> - antenna frequency) for a W-CDMA professional duplexer filter are presented. It is proved that the 2ƒ<inf>1</inf> signal and the intermodulation product are generated in this power BAW filter, despite its careful design.","PeriodicalId":338255,"journal":{"name":"2017 International Symposium on Signals, Circuits and Systems (ISSCS)","volume":"229 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124416644","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 : 2017-07-01DOI: 10.1109/ISSCS.2017.8034925
Adrian Done, A. Căilean, C. Lesanu, M. Dimian, A. Graur
In the context of an increasing number of satellites orbiting around the Earth, developing a vast ground stations network becomes very important in order to be able to receive the satellite transmitted data. Consequently, this paper presents the aspects related to the implementation of a ground station for LEO satellites, located in Suceava city. The paper presents a relatively simple and cost efficient ground station solution, and also offers an example of satellite data reception. As the ground station is located within city limits, whereas the antennas are omnidirectional, the paper also analyses the location's radio horizon and radio compatibility.
{"title":"Design and implementation of a satellite communication ground station","authors":"Adrian Done, A. Căilean, C. Lesanu, M. Dimian, A. Graur","doi":"10.1109/ISSCS.2017.8034925","DOIUrl":"https://doi.org/10.1109/ISSCS.2017.8034925","url":null,"abstract":"In the context of an increasing number of satellites orbiting around the Earth, developing a vast ground stations network becomes very important in order to be able to receive the satellite transmitted data. Consequently, this paper presents the aspects related to the implementation of a ground station for LEO satellites, located in Suceava city. The paper presents a relatively simple and cost efficient ground station solution, and also offers an example of satellite data reception. As the ground station is located within city limits, whereas the antennas are omnidirectional, the paper also analyses the location's radio horizon and radio compatibility.","PeriodicalId":338255,"journal":{"name":"2017 International Symposium on Signals, Circuits and Systems (ISSCS)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122763375","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：