Pub Date : 2017-07-01DOI: 10.1109/EUROCON.2017.8011125
Aleksandar Melov, B. Gerazov, Z. Ivanovski
The design of speaker diarisation and recognition systems is a mature research area and their deployment in the real world has gained momentum. There are still a number of parameters of these systems that have to be tuned and optimised for the application scenario at hand. An online call recording diarisation system is designed with integrated speaker identification of the call-centre operators. The parameters of the speaker diarisation and identification algorithms are cross-tuned using a testbench database. The system performance, as assessed by the true positive rate (TPR), is optimised in respect to the delay introduced by the system. As the system is designed to be used online, the TPR-delay trade-off is crucial to its deployment. The finalised system is flexible in that it allows the user to choose the delay or accuracy needed for on-site deployment.
{"title":"Delay based optimisation of an integrated online call recording speaker diarisation and identification system","authors":"Aleksandar Melov, B. Gerazov, Z. Ivanovski","doi":"10.1109/EUROCON.2017.8011125","DOIUrl":"https://doi.org/10.1109/EUROCON.2017.8011125","url":null,"abstract":"The design of speaker diarisation and recognition systems is a mature research area and their deployment in the real world has gained momentum. There are still a number of parameters of these systems that have to be tuned and optimised for the application scenario at hand. An online call recording diarisation system is designed with integrated speaker identification of the call-centre operators. The parameters of the speaker diarisation and identification algorithms are cross-tuned using a testbench database. The system performance, as assessed by the true positive rate (TPR), is optimised in respect to the delay introduced by the system. As the system is designed to be used online, the TPR-delay trade-off is crucial to its deployment. The finalised system is flexible in that it allows the user to choose the delay or accuracy needed for on-site deployment.","PeriodicalId":114100,"journal":{"name":"IEEE EUROCON 2017 -17th International Conference on Smart Technologies","volume":"39 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":"127184291","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/EUROCON.2017.8011231
Nemanja Gazivoda, P. Sovilj, V. Vujicic, Z. Mitrović
The paper gives an elaborated proposal that the extended paradigm of discrete digital measurement, in addition to the standard sampling method (SSM), should also include stochastic digital measurement method (SDMM).
{"title":"Proposal for extension of the standard paradigm of discrete digital measurement","authors":"Nemanja Gazivoda, P. Sovilj, V. Vujicic, Z. Mitrović","doi":"10.1109/EUROCON.2017.8011231","DOIUrl":"https://doi.org/10.1109/EUROCON.2017.8011231","url":null,"abstract":"The paper gives an elaborated proposal that the extended paradigm of discrete digital measurement, in addition to the standard sampling method (SSM), should also include stochastic digital measurement method (SDMM).","PeriodicalId":114100,"journal":{"name":"IEEE EUROCON 2017 -17th International Conference on Smart Technologies","volume":"299 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":"121210457","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/EUROCON.2017.8011214
Aleksandra Zdravevska, Ace Dimitrievski, Petre Lameski, Eftim Zdravevski, V. Trajkovik
Automatic recognition of complex activities can aid in finding correlations between the daily habits of people and their health state, and can further lead to early detection of diseases or accidents. In this paper we propose a cloud-based system for recognition of complex activities by detecting series of atomic actions with non-invasive sensors. Collected data from non-invasive, non-intrusive and privacy preserving sensors is streamed into a cloud-based system, where automated feature extraction and activity recognition is performed. The prototype of the proposed system is evaluated with an experiment. Five activities performed by a person in a room were monitored by a sensor kit and streamed to the cloud, where the built classification models could recognize the activities with accuracy of 80% to 95%, depending on the length of segmentation windows which varied from 5 to 20 seconds, respectively.
{"title":"Cloud-based recognition of complex activities for ambient assisted living in smart homes with non-invasive sensors","authors":"Aleksandra Zdravevska, Ace Dimitrievski, Petre Lameski, Eftim Zdravevski, V. Trajkovik","doi":"10.1109/EUROCON.2017.8011214","DOIUrl":"https://doi.org/10.1109/EUROCON.2017.8011214","url":null,"abstract":"Automatic recognition of complex activities can aid in finding correlations between the daily habits of people and their health state, and can further lead to early detection of diseases or accidents. In this paper we propose a cloud-based system for recognition of complex activities by detecting series of atomic actions with non-invasive sensors. Collected data from non-invasive, non-intrusive and privacy preserving sensors is streamed into a cloud-based system, where automated feature extraction and activity recognition is performed. The prototype of the proposed system is evaluated with an experiment. Five activities performed by a person in a room were monitored by a sensor kit and streamed to the cloud, where the built classification models could recognize the activities with accuracy of 80% to 95%, depending on the length of segmentation windows which varied from 5 to 20 seconds, respectively.","PeriodicalId":114100,"journal":{"name":"IEEE EUROCON 2017 -17th International Conference on Smart Technologies","volume":"6 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":"126927156","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/EUROCON.2017.8011101
S. Vehring, Yaoshun Ding, D. Maurath, F. Gerfers, Georg Böck
In this paper, advanced link-budget calculations for microwave receivers are introduced. Microwave receivers typically consist of narrowband circuits in the high frequency part and broadband circuits in the baseband part. In general narrowband circuits and broadband circuits are characterized in different ways. Narrowband circuits are described by impedance matching, power gain and noise figure while broadband circuits by voltage gain and input referred noise. This makes the link-budget calculation not straight-forward and often leads to errors. The paper presents a way to calculate link-budgets from the received power at an antenna output until an analog-to-digital converter's output. This incorporates narrowband and broadband circuits. At first a formel-set from theory is derived and furthermore applied to two practical case studies. The first case study is a 24 GHz CMOS receiver intended for industry radar while the second case study is a full W-Band CMOS receiver intended for 100Gb/s communication.
{"title":"Link-budget calculations for CMOS integrated microwave receivers","authors":"S. Vehring, Yaoshun Ding, D. Maurath, F. Gerfers, Georg Böck","doi":"10.1109/EUROCON.2017.8011101","DOIUrl":"https://doi.org/10.1109/EUROCON.2017.8011101","url":null,"abstract":"In this paper, advanced link-budget calculations for microwave receivers are introduced. Microwave receivers typically consist of narrowband circuits in the high frequency part and broadband circuits in the baseband part. In general narrowband circuits and broadband circuits are characterized in different ways. Narrowband circuits are described by impedance matching, power gain and noise figure while broadband circuits by voltage gain and input referred noise. This makes the link-budget calculation not straight-forward and often leads to errors. The paper presents a way to calculate link-budgets from the received power at an antenna output until an analog-to-digital converter's output. This incorporates narrowband and broadband circuits. At first a formel-set from theory is derived and furthermore applied to two practical case studies. The first case study is a 24 GHz CMOS receiver intended for industry radar while the second case study is a full W-Band CMOS receiver intended for 100Gb/s communication.","PeriodicalId":114100,"journal":{"name":"IEEE EUROCON 2017 -17th International Conference on Smart Technologies","volume":"9 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":"124271515","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/EUROCON.2017.8011159
Stojan Kitanov, T. Janevski
Today many users with their smart mobile devices enjoy the benefits of broadband Internet services. This is primarily enabled by pushing computing, control, data storage and processing into the cloud. However, the cloud encounters growing limitations, such as reduced latency, high mobility, high scalability and real-time execution in order to meet the computing and intelligent networking demands for the next 5G mobile and wireless network. A new paradigm called Fog Computing and Networking, or briefly Fog has emerged to resolve these limits. Fog distributes computing, data processing, and networking services closer to the end users. It is an architecture where distributed edge and user devices collaborate with each other and with the clouds to carry out computing, control, networking, and data management tasks. Fog applied in 5G network can significantly improve network performance in terms of spectral and energy efficiency, enable direct device-to-device wireless communications, and support the growing trend of network function virtualization and separation of network control intelligence from radio network hardware. This paper evaluates the quality of cloud and fog computing and networking orchestrated services in 5G mobile and wireless network in terms of energy efficiency.
{"title":"Energy efficiency of Fog Computing and Networking services in 5G networks","authors":"Stojan Kitanov, T. Janevski","doi":"10.1109/EUROCON.2017.8011159","DOIUrl":"https://doi.org/10.1109/EUROCON.2017.8011159","url":null,"abstract":"Today many users with their smart mobile devices enjoy the benefits of broadband Internet services. This is primarily enabled by pushing computing, control, data storage and processing into the cloud. However, the cloud encounters growing limitations, such as reduced latency, high mobility, high scalability and real-time execution in order to meet the computing and intelligent networking demands for the next 5G mobile and wireless network. A new paradigm called Fog Computing and Networking, or briefly Fog has emerged to resolve these limits. Fog distributes computing, data processing, and networking services closer to the end users. It is an architecture where distributed edge and user devices collaborate with each other and with the clouds to carry out computing, control, networking, and data management tasks. Fog applied in 5G network can significantly improve network performance in terms of spectral and energy efficiency, enable direct device-to-device wireless communications, and support the growing trend of network function virtualization and separation of network control intelligence from radio network hardware. This paper evaluates the quality of cloud and fog computing and networking orchestrated services in 5G mobile and wireless network in terms of energy efficiency.","PeriodicalId":114100,"journal":{"name":"IEEE EUROCON 2017 -17th International Conference on Smart Technologies","volume":"23 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":"114042308","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/EUROCON.2017.8011088
Zoran Asenov, V. Atanasovski
This paper targets empirical voice and video quality assessment in mobile networks and presents fundamental QoS testing methods in correlation to RF indicators. The paper focuses on the most critical performance parameters for real-time services (e.g. voice) such as call drop vs. poor coverage in UMTS. The empirical study was based on a clearly defined drive test scenario with predetermined routes and communication profiles such as mobile to data server and call server setup.
{"title":"The impact of RF parameters on perceived QoS in cellular mobile networks","authors":"Zoran Asenov, V. Atanasovski","doi":"10.1109/EUROCON.2017.8011088","DOIUrl":"https://doi.org/10.1109/EUROCON.2017.8011088","url":null,"abstract":"This paper targets empirical voice and video quality assessment in mobile networks and presents fundamental QoS testing methods in correlation to RF indicators. The paper focuses on the most critical performance parameters for real-time services (e.g. voice) such as call drop vs. poor coverage in UMTS. The empirical study was based on a clearly defined drive test scenario with predetermined routes and communication profiles such as mobile to data server and call server setup.","PeriodicalId":114100,"journal":{"name":"IEEE EUROCON 2017 -17th International Conference on Smart Technologies","volume":"8 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":"114191628","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/EUROCON.2017.8011172
A. Michalczuk, Kamil Wereszczynski, A. Świtoński, Henryk Josiński, K. Wojciechowski
In this paper we present a review of gait analysis methods used for medical applications. First of all, we introduce a system of real-time gait acquisition. Next, three ways of gait data representation: trajectories, Euler angles and medical angles are described along with the most promising methods of gait analysis based on those representations like gait indices, Dynamic Time Warping, manifold methods and a ranking of most significant joints for different disease units. We present also some results of the aforementioned methods, summarize our research and discuss future plans.
{"title":"The overview of automatically supported gait analysis methods for medical diagnoses and rehabilitation","authors":"A. Michalczuk, Kamil Wereszczynski, A. Świtoński, Henryk Josiński, K. Wojciechowski","doi":"10.1109/EUROCON.2017.8011172","DOIUrl":"https://doi.org/10.1109/EUROCON.2017.8011172","url":null,"abstract":"In this paper we present a review of gait analysis methods used for medical applications. First of all, we introduce a system of real-time gait acquisition. Next, three ways of gait data representation: trajectories, Euler angles and medical angles are described along with the most promising methods of gait analysis based on those representations like gait indices, Dynamic Time Warping, manifold methods and a ranking of most significant joints for different disease units. We present also some results of the aforementioned methods, summarize our research and discuss future plans.","PeriodicalId":114100,"journal":{"name":"IEEE EUROCON 2017 -17th International Conference on Smart Technologies","volume":"68 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":"114676925","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/EUROCON.2017.8011092
I. Petrov, T. Janevski
G-TCP represents novel transport protocol designed to be used by Next Generation Networks. It engages famous Fibonacci sequence to calculate congestion window size when the protocol operates in congestion avoidance phase. Modification of window decrease parameter is introduced in order to improve protocol behaviour in high and low speed networks.
{"title":"G-TCP, next generation transport protocol","authors":"I. Petrov, T. Janevski","doi":"10.1109/EUROCON.2017.8011092","DOIUrl":"https://doi.org/10.1109/EUROCON.2017.8011092","url":null,"abstract":"G-TCP represents novel transport protocol designed to be used by Next Generation Networks. It engages famous Fibonacci sequence to calculate congestion window size when the protocol operates in congestion avoidance phase. Modification of window decrease parameter is introduced in order to improve protocol behaviour in high and low speed networks.","PeriodicalId":114100,"journal":{"name":"IEEE EUROCON 2017 -17th International Conference on Smart Technologies","volume":"26 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":"114719437","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/EUROCON.2017.8011103
K. Salah
In this Paper, a Particle Swarm Optimization based solution is proposed to solve the problem of model order reduction for high order transfer functions. The main advantages of our approach are that it is generic, with relatively small time and reasonable accuracy. Moreover, it preserves both time and frequency responses of the original transfer function.
{"title":"A generic model order reduction technique based on Particle Swarm Optimization (PSO) algorithm","authors":"K. Salah","doi":"10.1109/EUROCON.2017.8011103","DOIUrl":"https://doi.org/10.1109/EUROCON.2017.8011103","url":null,"abstract":"In this Paper, a Particle Swarm Optimization based solution is proposed to solve the problem of model order reduction for high order transfer functions. The main advantages of our approach are that it is generic, with relatively small time and reasonable accuracy. Moreover, it preserves both time and frequency responses of the original transfer function.","PeriodicalId":114100,"journal":{"name":"IEEE EUROCON 2017 -17th International Conference on Smart Technologies","volume":"50 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":"121917970","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/EUROCON.2017.8011221
I. Tyuryukanov, J. Quirós-Tortós, M. Naglic, M. Popov, M. Meijden, V. Terzija
Partitioning of electric networks into zones or areas is a procedure that has numerous applications in power system planning, operation and control. Spectral clustering based approaches are among the most favoured ones to solve the partitioning problem. Applications of spectral clustering include definition of control zones, analysis of connectivity structure of power networks, intentional controlled islanding, design of sectionalising strategies, and visualisation. Although spectral clustering is a state-of-the-art family of methods with numerous extensions, some practical issues can arise when applying it to large-scale power networks. While spectral clustering becomes significantly more robust to outliers when combined with a robust post-processing method like k-medoids, the connectedness of the resulting partitioning cannot be guaranteed. This paper proposes a greedy algorithm to solve the connectedness issues inherent to many robust post-processing methods. Furthermore, it is proposed to utilise a label propagation based heuristic to improve the quality of the final partitions. The test results evaluate the steps of the methodology on a large-scale 1354-bus PEGASE test network.
{"title":"A post-processing methodology for robust spectral embedded clustering of power networks","authors":"I. Tyuryukanov, J. Quirós-Tortós, M. Naglic, M. Popov, M. Meijden, V. Terzija","doi":"10.1109/EUROCON.2017.8011221","DOIUrl":"https://doi.org/10.1109/EUROCON.2017.8011221","url":null,"abstract":"Partitioning of electric networks into zones or areas is a procedure that has numerous applications in power system planning, operation and control. Spectral clustering based approaches are among the most favoured ones to solve the partitioning problem. Applications of spectral clustering include definition of control zones, analysis of connectivity structure of power networks, intentional controlled islanding, design of sectionalising strategies, and visualisation. Although spectral clustering is a state-of-the-art family of methods with numerous extensions, some practical issues can arise when applying it to large-scale power networks. While spectral clustering becomes significantly more robust to outliers when combined with a robust post-processing method like k-medoids, the connectedness of the resulting partitioning cannot be guaranteed. This paper proposes a greedy algorithm to solve the connectedness issues inherent to many robust post-processing methods. Furthermore, it is proposed to utilise a label propagation based heuristic to improve the quality of the final partitions. The test results evaluate the steps of the methodology on a large-scale 1354-bus PEGASE test network.","PeriodicalId":114100,"journal":{"name":"IEEE EUROCON 2017 -17th International Conference on Smart Technologies","volume":"5 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":"116891737","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：