Pub Date : 2019-07-01DOI: 10.1109/TSP.2019.8768823
Özge Canlı, Serkan Günel
Sub-systems in a network of chaotic dynamic systems can form clusters of synchronization. In this study, we investigate the problem of detection of cluster synchronization via information theoretic measures. We have shown that, if the existing information measures in the literature, particularly transfer entropy, is estimated from sequential observations of continuous chaotic systems, it is hard to detect cluster synchronization, directly. On the other hand, if the state space is reconstructed from the observed data in the light of Takens’ embedding theorem first, the cluster synchronization can be detected easily.
{"title":"Detecting Cluster Synchronization in Chaotic Dynamic Networks via Information Theoretic Measures","authors":"Özge Canlı, Serkan Günel","doi":"10.1109/TSP.2019.8768823","DOIUrl":"https://doi.org/10.1109/TSP.2019.8768823","url":null,"abstract":"Sub-systems in a network of chaotic dynamic systems can form clusters of synchronization. In this study, we investigate the problem of detection of cluster synchronization via information theoretic measures. We have shown that, if the existing information measures in the literature, particularly transfer entropy, is estimated from sequential observations of continuous chaotic systems, it is hard to detect cluster synchronization, directly. On the other hand, if the state space is reconstructed from the observed data in the light of Takens’ embedding theorem first, the cluster synchronization can be detected easily.","PeriodicalId":399087,"journal":{"name":"2019 42nd International Conference on Telecommunications and Signal Processing (TSP)","volume":"31 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":"114225685","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.2019.8768885
Michal Zygmunt, Marek Konieczny, Sławomir Zieliński
This paper is focused on evaluating the applicability of statistical machine learning methods to identifying flows and user behavior patterns at the source (client) network edge. The research was conducted in a mid-size (covering ca 150 geographically scattered locations) network developed for the Malopolska Educational Cloud (MEC) project. Due to the lack of validation sets we focused on unsupervised learning methods. Modules implementing the methods were fed with the headers of the user-generated packets; payloads were not analyzed due to privacy concerns. The presented research proved that in client edge networks even the simple classification methods yield satisfactory results in flows classification.
{"title":"Accuracy of statistical machine learning methods in identifying client behavior patterns at network edge","authors":"Michal Zygmunt, Marek Konieczny, Sławomir Zieliński","doi":"10.1109/TSP.2019.8768885","DOIUrl":"https://doi.org/10.1109/TSP.2019.8768885","url":null,"abstract":"This paper is focused on evaluating the applicability of statistical machine learning methods to identifying flows and user behavior patterns at the source (client) network edge. The research was conducted in a mid-size (covering ca 150 geographically scattered locations) network developed for the Malopolska Educational Cloud (MEC) project. Due to the lack of validation sets we focused on unsupervised learning methods. Modules implementing the methods were fed with the headers of the user-generated packets; payloads were not analyzed due to privacy concerns. The presented research proved that in client edge networks even the simple classification methods yield satisfactory results in flows classification.","PeriodicalId":399087,"journal":{"name":"2019 42nd International Conference on Telecommunications and Signal Processing (TSP)","volume":"17 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":"114883224","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.2019.8769088
Plamen T. Semov, P. Koleva, V. Poulkov
Nowadays with the deployment of a large and dense heterogeneous networks more sophisticated algorithms for resource scheduling are needed. Implementing hard coded scheduling algorithms without taking into account the very specific dynamic of the traffic generated by the mobile users can lead to a network performance quite far from the optimal. By using novel machine learning (ML) algorithms we can store not only the raw traffic data and its variations but also build the so-called heat maps, reflecting the changes of the traffic over time, space and per user. Using neural network (NN) architectures, trained by the raw data statistics, we can store the network traffic model at minimum data storage without the need of keeping and looking up at the raw data. Using such NN architecture the network state in next time intervals could be predicted and this prediction used for decision making about how the network resources to be scheduled among the active mobile users. To implement adaptive resource scheduling named “AdaptSch” a neural network architecture with two main blocks is proposed. The simulation results show that by incorporating a neural classifier for adapting the resource scheduler we can utilize the advantages and the effectiveness of multiple scheduler algorithms and improve overall throughput and packet delay.
{"title":"Adaptive Resource Scheduling based on Neural Network and Mobile Traffic Prediction","authors":"Plamen T. Semov, P. Koleva, V. Poulkov","doi":"10.1109/TSP.2019.8769088","DOIUrl":"https://doi.org/10.1109/TSP.2019.8769088","url":null,"abstract":"Nowadays with the deployment of a large and dense heterogeneous networks more sophisticated algorithms for resource scheduling are needed. Implementing hard coded scheduling algorithms without taking into account the very specific dynamic of the traffic generated by the mobile users can lead to a network performance quite far from the optimal. By using novel machine learning (ML) algorithms we can store not only the raw traffic data and its variations but also build the so-called heat maps, reflecting the changes of the traffic over time, space and per user. Using neural network (NN) architectures, trained by the raw data statistics, we can store the network traffic model at minimum data storage without the need of keeping and looking up at the raw data. Using such NN architecture the network state in next time intervals could be predicted and this prediction used for decision making about how the network resources to be scheduled among the active mobile users. To implement adaptive resource scheduling named “AdaptSch” a neural network architecture with two main blocks is proposed. The simulation results show that by incorporating a neural classifier for adapting the resource scheduler we can utilize the advantages and the effectiveness of multiple scheduler algorithms and improve overall throughput and packet delay.","PeriodicalId":399087,"journal":{"name":"2019 42nd International Conference on Telecommunications and Signal Processing (TSP)","volume":"32 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":"122582228","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.2019.8769056
Stefan Grivalsky, Martin Tamajka, Wanda Benesova
In our work we focus on automatic segmentation of high-grade gliomas (HGG) from magnetic resonance images (MRI). The results of segmentation have great impact on treatment of patients and consequently on the length of their life. In this paper a new approach of automatic glioma segmentation based on recurrent neural units is proposed. We use the Long Short-Term Memory units (LSTMs) which are able to extract latent features of brain structure by global contextual information. Unlike convolutional neural networks, where global context is gained by combination of local features, LSTMs have the potential to capture the global context at once. We use a region-based classification using the 3D Hilbert space-filling curve. To evaluate this method, the HGG data from the International Multimodal Brain Tumor Segmentation (BraTS-17) Challenge 2017 are being used. Our method achieved a dice score 0.62, 0.77, 0.64, on validation dataset of BraTS-17, for enhancing tumor, whole tumor and tumor core, respectively.
{"title":"Segmentation of gliomas in magnetic resonance images using recurrent neural networks","authors":"Stefan Grivalsky, Martin Tamajka, Wanda Benesova","doi":"10.1109/TSP.2019.8769056","DOIUrl":"https://doi.org/10.1109/TSP.2019.8769056","url":null,"abstract":"In our work we focus on automatic segmentation of high-grade gliomas (HGG) from magnetic resonance images (MRI). The results of segmentation have great impact on treatment of patients and consequently on the length of their life. In this paper a new approach of automatic glioma segmentation based on recurrent neural units is proposed. We use the Long Short-Term Memory units (LSTMs) which are able to extract latent features of brain structure by global contextual information. Unlike convolutional neural networks, where global context is gained by combination of local features, LSTMs have the potential to capture the global context at once. We use a region-based classification using the 3D Hilbert space-filling curve. To evaluate this method, the HGG data from the International Multimodal Brain Tumor Segmentation (BraTS-17) Challenge 2017 are being used. Our method achieved a dice score 0.62, 0.77, 0.64, on validation dataset of BraTS-17, for enhancing tumor, whole tumor and tumor core, respectively.","PeriodicalId":399087,"journal":{"name":"2019 42nd International Conference on Telecommunications and Signal Processing (TSP)","volume":"70 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":"122602106","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.2019.8768835
Alina Elena Marcu, G. Suciu, E. Olteanu, Delia Miu, Alexandru Drosu, I. Marcu
Several important issues are affecting the forest environment due to deforestation and natural disasters (for example forest fires, or increased gas emissions). This paper proposes an intelligent forest environment monitoring solution based on the Raspberry Pi Model 3, analogical and digital sensors and signals analysis algorithms. Parameters such as temperature, gas concentrations, soil humidity etc. are monitored with sensors while background sounds are analyzed with a classification algorithm on the basis of which the generated event can be classified into one of the following categories: Chainsaw, Vehicle, or Forest background noise. The user’s accessibility to the collected data is ensured via Internet and a mobile applications that allows the user to receive notifications, whenever fire, pollution sources, or illegal deforestation are detected. The SeaForest environment monitoring solution is an IoT project, addressed to public and private forest owners as well as to national environmental and disaster response authorities.
{"title":"IoT System for Forest Monitoring","authors":"Alina Elena Marcu, G. Suciu, E. Olteanu, Delia Miu, Alexandru Drosu, I. Marcu","doi":"10.1109/TSP.2019.8768835","DOIUrl":"https://doi.org/10.1109/TSP.2019.8768835","url":null,"abstract":"Several important issues are affecting the forest environment due to deforestation and natural disasters (for example forest fires, or increased gas emissions). This paper proposes an intelligent forest environment monitoring solution based on the Raspberry Pi Model 3, analogical and digital sensors and signals analysis algorithms. Parameters such as temperature, gas concentrations, soil humidity etc. are monitored with sensors while background sounds are analyzed with a classification algorithm on the basis of which the generated event can be classified into one of the following categories: Chainsaw, Vehicle, or Forest background noise. The user’s accessibility to the collected data is ensured via Internet and a mobile applications that allows the user to receive notifications, whenever fire, pollution sources, or illegal deforestation are detected. The SeaForest environment monitoring solution is an IoT project, addressed to public and private forest owners as well as to national environmental and disaster response authorities.","PeriodicalId":399087,"journal":{"name":"2019 42nd International Conference on Telecommunications and Signal Processing (TSP)","volume":"339 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":"124772375","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.2019.8769090
I. Nakanishi, Takehiro Maruoka
In recent years, biometrics such as fingerprints and iris scans has been used in authentication. However, conventional biometrics is vulnerable to identity theft, especially in user management systems. As a new biometric without this vulnerability, we focused on brain waves. In this paper, we show that individuals can be authenticated using evoked potentials when they are subjected to ultrasound. We measured the electroencephalograms (EEGs) of 10 experimental subjects. Individual features were extracted from the power spectra of the EEGs using the principle component analysis and verification was achieved using the support vector machine. We found that for the proposed authentication method, the equal error rate for a single electrode was about 22-32 %. For a multi-electrode, the equal error rate was 4.4 % using the majority decision rule.
{"title":"Biometric authentication using evoked potentials stimulated by personal ultrasound","authors":"I. Nakanishi, Takehiro Maruoka","doi":"10.1109/TSP.2019.8769090","DOIUrl":"https://doi.org/10.1109/TSP.2019.8769090","url":null,"abstract":"In recent years, biometrics such as fingerprints and iris scans has been used in authentication. However, conventional biometrics is vulnerable to identity theft, especially in user management systems. As a new biometric without this vulnerability, we focused on brain waves. In this paper, we show that individuals can be authenticated using evoked potentials when they are subjected to ultrasound. We measured the electroencephalograms (EEGs) of 10 experimental subjects. Individual features were extracted from the power spectra of the EEGs using the principle component analysis and verification was achieved using the support vector machine. We found that for the proposed authentication method, the equal error rate for a single electrode was about 22-32 %. For a multi-electrode, the equal error rate was 4.4 % using the majority decision rule.","PeriodicalId":399087,"journal":{"name":"2019 42nd International Conference on Telecommunications and Signal Processing (TSP)","volume":"59 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":"126421204","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.2019.8769100
V. Oujezský, T. Horváth, P. Munster
This article presents a part of our project focused on developing a measuring device for Gigabit-capable Passive Optical Networks. A part of the device is a Python application used to detect whether captured IP addresses belong to a map by their coordinates. Two methods are tested and compared. First, a clustering method to calculate if given IP lies inside a created map based on latitude and longitude positions, and the other, an intersection method for the same purpose. It is our idea to verify that either this method can be used for localization purposes. With this article, a basic schema and functionality of the application and tests results of the methods are described.
{"title":"Application for Determining whether IP Addresses belong to a Map by Coordinates","authors":"V. Oujezský, T. Horváth, P. Munster","doi":"10.1109/TSP.2019.8769100","DOIUrl":"https://doi.org/10.1109/TSP.2019.8769100","url":null,"abstract":"This article presents a part of our project focused on developing a measuring device for Gigabit-capable Passive Optical Networks. A part of the device is a Python application used to detect whether captured IP addresses belong to a map by their coordinates. Two methods are tested and compared. First, a clustering method to calculate if given IP lies inside a created map based on latitude and longitude positions, and the other, an intersection method for the same purpose. It is our idea to verify that either this method can be used for localization purposes. With this article, a basic schema and functionality of the application and tests results of the methods are described.","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":"129580094","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.2019.8769030
R. Moreno-Alvarado, Eduardo Rivera-Jaramillo, M. Nakano-Miyatake, H. Meana
The increasing amount of sensible information transmitted through insecure communications channels requires, the development of algorithms with the capacity of simultaneously compress and encrypt digital information. To solve this problem, this paper proposes an algorithm based on compressing sensing, which simultaneously compress and encrypt audio signals. In the proposed scheme the audio signal is segmented in frames of1000 samples which are then transformed in sparse frames using the DCT. Next each sparse frame is compressed using a different sensing matrix in each frame, to assure that the proposed system satisfies the Extended Wyner Secrecy (EWS) criterion. Evaluation results show that the proposed scheme allows the secure communication of audio signals.
{"title":"Joint Encryption and Compression of Audio Based on Compressive Sensing","authors":"R. Moreno-Alvarado, Eduardo Rivera-Jaramillo, M. Nakano-Miyatake, H. Meana","doi":"10.1109/TSP.2019.8769030","DOIUrl":"https://doi.org/10.1109/TSP.2019.8769030","url":null,"abstract":"The increasing amount of sensible information transmitted through insecure communications channels requires, the development of algorithms with the capacity of simultaneously compress and encrypt digital information. To solve this problem, this paper proposes an algorithm based on compressing sensing, which simultaneously compress and encrypt audio signals. In the proposed scheme the audio signal is segmented in frames of1000 samples which are then transformed in sparse frames using the DCT. Next each sparse frame is compressed using a different sensing matrix in each frame, to assure that the proposed system satisfies the Extended Wyner Secrecy (EWS) criterion. Evaluation results show that the proposed scheme allows the secure communication of audio signals.","PeriodicalId":399087,"journal":{"name":"2019 42nd International Conference on Telecommunications and Signal Processing (TSP)","volume":"60 3 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":"131155611","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.2019.8768856
Ritesh Maurya, M. Dutta, K. Říha, Petr Kritz
Water bodies are getting polluted day by day due to discharge of industrial waste, agricultural waste, waste water and other effluents which in turn causing harm to health status to living organism including fish. The proposed work used an image processing based framework to identify the fish exposed to polluted water. The proposed work segments fish gills and contributes in identification of texture features that can be used to distinguish normal fish from fish exposed to pollution. It was evident from the statistical analysis of these features that there occured changes in the texture properties of fish gill which were exposed to such pollutants.
{"title":"An Image Processing based Identification of Fish Exposed to Polluted Water","authors":"Ritesh Maurya, M. Dutta, K. Říha, Petr Kritz","doi":"10.1109/TSP.2019.8768856","DOIUrl":"https://doi.org/10.1109/TSP.2019.8768856","url":null,"abstract":"Water bodies are getting polluted day by day due to discharge of industrial waste, agricultural waste, waste water and other effluents which in turn causing harm to health status to living organism including fish. The proposed work used an image processing based framework to identify the fish exposed to polluted water. The proposed work segments fish gills and contributes in identification of texture features that can be used to distinguish normal fish from fish exposed to pollution. It was evident from the statistical analysis of these features that there occured changes in the texture properties of fish gill which were exposed to such pollutants.","PeriodicalId":399087,"journal":{"name":"2019 42nd International Conference on Telecommunications and Signal Processing (TSP)","volume":"89 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":"134377227","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.2019.8769103
J. Chaloupka
This paper focuses on the use of methods and algorithms from the area of speech processing and recognition and from the area of machine vision for designing of system for automatic audio-visual broadcast transcription. The resulting audio-visual system has been designed and created mainly for transcription of huge video databases with TV recordings in this work. The visual signal processing and recognition is usually several times computationally more demanding than audio signal processing and recognition. Therefore, all applied machine vision methods and algorithms were considered with respect to low computing time as well as the highest possible recognition rate. Our proposed broadcast transcription system was extended by several modules for visual signal segmentation, for TV channel identification, for face detection and identification and for Optical Character Recognition (OCR).
{"title":"A prototype of Audio-Visual Broadcast Transcription System","authors":"J. Chaloupka","doi":"10.1109/TSP.2019.8769103","DOIUrl":"https://doi.org/10.1109/TSP.2019.8769103","url":null,"abstract":"This paper focuses on the use of methods and algorithms from the area of speech processing and recognition and from the area of machine vision for designing of system for automatic audio-visual broadcast transcription. The resulting audio-visual system has been designed and created mainly for transcription of huge video databases with TV recordings in this work. The visual signal processing and recognition is usually several times computationally more demanding than audio signal processing and recognition. Therefore, all applied machine vision methods and algorithms were considered with respect to low computing time as well as the highest possible recognition rate. Our proposed broadcast transcription system was extended by several modules for visual signal segmentation, for TV channel identification, for face detection and identification and for Optical Character Recognition (OCR).","PeriodicalId":399087,"journal":{"name":"2019 42nd International Conference on Telecommunications and Signal Processing (TSP)","volume":"138 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":"133663313","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：