M. Gjoreski, M. Simjanoska, A. Gradišek, A. Peterlin, M. Gams, G. Poglajen
Chronic heart failure represents a global pandemic, currently affecting over 26 million of patients worldwide. It is a major contributor in the death rate of patients with cardiovascular diseases and results in more than 1 million hospitalizations annually in Europe and North America. Methods for chronic heart failure detection can be utilized to act preventive, improve early diagnosis and avoid hospitalizations or even life-threatening situations, thus highly enhance the quality of patient’s life. In this paper, we present a machine-learning method for chronic heart failure detection from heart sounds. The method consists of: filtering, segmentation, feature extraction and machine learning. The method was tested with a leave-one-subject-out evaluation technique on data from 122 subjects, gathered in the study. The method achieved 96% accuracy, outperforming a majority classifier for 15 percentage points. More specifically, it detects (recalls) 87% of the chronic heart failure subjects with a precision of 87%. The study confirmed that advanced machine learning applied on real-life sounds recorded with an unobtrusive digital stethoscope can be used for chronic heart failure detection.
{"title":"Chronic Heart Failure Detection from Heart Sounds Using a Stack of Machine-Learning Classifiers","authors":"M. Gjoreski, M. Simjanoska, A. Gradišek, A. Peterlin, M. Gams, G. Poglajen","doi":"10.1109/IE.2017.19","DOIUrl":"https://doi.org/10.1109/IE.2017.19","url":null,"abstract":"Chronic heart failure represents a global pandemic, currently affecting over 26 million of patients worldwide. It is a major contributor in the death rate of patients with cardiovascular diseases and results in more than 1 million hospitalizations annually in Europe and North America. Methods for chronic heart failure detection can be utilized to act preventive, improve early diagnosis and avoid hospitalizations or even life-threatening situations, thus highly enhance the quality of patient’s life. In this paper, we present a machine-learning method for chronic heart failure detection from heart sounds. The method consists of: filtering, segmentation, feature extraction and machine learning. The method was tested with a leave-one-subject-out evaluation technique on data from 122 subjects, gathered in the study. The method achieved 96% accuracy, outperforming a majority classifier for 15 percentage points. More specifically, it detects (recalls) 87% of the chronic heart failure subjects with a precision of 87%. The study confirmed that advanced machine learning applied on real-life sounds recorded with an unobtrusive digital stethoscope can be used for chronic heart failure detection.","PeriodicalId":306693,"journal":{"name":"2017 International Conference on Intelligent Environments (IE)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124572066","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}
Small cells are low-powered cellular radio access nodes which make best use of available spectrum by reusing the same frequencies many times within a geographical area. However, the deployment of small cells (e.g., femtocells) may introduce extra interferences such as cross-tier(macrocellfemtocell) and co-tier (femtocell-femtocell) interferences. In this regard, an effective interference management mechanism is required for improving the performance of the network. In this study, a distributed resource allocation is introduced to deal with the interference problem in two-tier network. Specifically, we first apply FFR scheme to mitigate interference for crosstier problem. To reduce co-tier interference, a cooperative game model is proposed where each femtocells are regard as players of the game. Simulation results reveal that the proposed approach significantly improves capacity of the networks.
{"title":"Cooperative Game Theoretic Approach for Distributed Resource Allocation in Heterogeneous Network","authors":"Khac-Hoai Nam Bui, Jason J. Jung","doi":"10.1109/IE.2017.14","DOIUrl":"https://doi.org/10.1109/IE.2017.14","url":null,"abstract":"Small cells are low-powered cellular radio access nodes which make best use of available spectrum by reusing the same frequencies many times within a geographical area. However, the deployment of small cells (e.g., femtocells) may introduce extra interferences such as cross-tier(macrocellfemtocell) and co-tier (femtocell-femtocell) interferences. In this regard, an effective interference management mechanism is required for improving the performance of the network. In this study, a distributed resource allocation is introduced to deal with the interference problem in two-tier network. Specifically, we first apply FFR scheme to mitigate interference for crosstier problem. To reduce co-tier interference, a cooperative game model is proposed where each femtocells are regard as players of the game. Simulation results reveal that the proposed approach significantly improves capacity of the networks.","PeriodicalId":306693,"journal":{"name":"2017 International Conference on Intelligent Environments (IE)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131092791","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}
Chunyun Zhang, Sheng Gao, Baolin Zhao, Lu Yang, Xiaoming Xi, C. Cui, Yilong Yin
Nature Language Processing has been paid more attention recently. Traditional approaches for language model primarily rely on elaborately designed features and complicated natural language processing tools, which take a large amount of human effort and are prone to error propagation and data sparse problem. Deep neural network method has been shown to be able to learn implicit semantics of text without extra knowledge. To better learn deep underlying semantics of sentences, most deepneuralnetworklanguagemodelsutilizemulti-gramstrategy. However, the current multi-gram strategies in CNN framework are mostly realized by concatenating trained multi-gram vectors to form the sentence vector, which can increase the number of parameters to be learned and is prone to over fitting. To alleviate the problem mentioned above, we propose a novel adaptive sentence representation learning model based on multigram CNN framework. It learns adaptive importance weights of different n-gram features and forms sentence representation by using weighted sum operation on extracted n-gram features, which can largely reduce parameters to be learned and alleviate the threat of over fitting. Experimental results show that the proposed method can improve performances when be used in sentiment and relation classification tasks.
{"title":"An Adaptive Sentence Representation Learning Model Based on Multi-gram CNN","authors":"Chunyun Zhang, Sheng Gao, Baolin Zhao, Lu Yang, Xiaoming Xi, C. Cui, Yilong Yin","doi":"10.1109/IE.2017.18","DOIUrl":"https://doi.org/10.1109/IE.2017.18","url":null,"abstract":"Nature Language Processing has been paid more attention recently. Traditional approaches for language model primarily rely on elaborately designed features and complicated natural language processing tools, which take a large amount of human effort and are prone to error propagation and data sparse problem. Deep neural network method has been shown to be able to learn implicit semantics of text without extra knowledge. To better learn deep underlying semantics of sentences, most deepneuralnetworklanguagemodelsutilizemulti-gramstrategy. However, the current multi-gram strategies in CNN framework are mostly realized by concatenating trained multi-gram vectors to form the sentence vector, which can increase the number of parameters to be learned and is prone to over fitting. To alleviate the problem mentioned above, we propose a novel adaptive sentence representation learning model based on multigram CNN framework. It learns adaptive importance weights of different n-gram features and forms sentence representation by using weighted sum operation on extracted n-gram features, which can largely reduce parameters to be learned and alleviate the threat of over fitting. Experimental results show that the proposed method can improve performances when be used in sentiment and relation classification tasks.","PeriodicalId":306693,"journal":{"name":"2017 International Conference on Intelligent Environments (IE)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132600889","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}
Claudia Vannucchi, Michelangelo Diamanti, Gianmarco Mazzante, D. Cacciagrano, F. Corradini, R. Culmone, Nikos Gorogiannis, L. Mostarda, F. Raimondi
Intelligent Environments (IE) are a very active area of research and a number of applications are currently being deployed in domains ranging from smart home to e-health and autonomous vehicles. In a number of cases, IE operate together with (or to support) humans, and it is therefore fundamental that IE are thoroughly verified. In this paper we present how a set of techniques and tools developed for the verification of software code can be employed in the verification of IE described by means of event-condition-action rules. In particular, we reduce the problem of verifying key properties of these rules to satisfiability and termination problems that can be addressed using state-of-the-art SMT solvers and program analysers. We introduce a tool called vIRONy that implements these techniques and we validate our approach against a number of case studies from the literature.
{"title":"vIRONy: A Tool for Analysis and Verification of ECA Rules in Intelligent Environments","authors":"Claudia Vannucchi, Michelangelo Diamanti, Gianmarco Mazzante, D. Cacciagrano, F. Corradini, R. Culmone, Nikos Gorogiannis, L. Mostarda, F. Raimondi","doi":"10.1109/IE.2017.32","DOIUrl":"https://doi.org/10.1109/IE.2017.32","url":null,"abstract":"Intelligent Environments (IE) are a very active area of research and a number of applications are currently being deployed in domains ranging from smart home to e-health and autonomous vehicles. In a number of cases, IE operate together with (or to support) humans, and it is therefore fundamental that IE are thoroughly verified. In this paper we present how a set of techniques and tools developed for the verification of software code can be employed in the verification of IE described by means of event-condition-action rules. In particular, we reduce the problem of verifying key properties of these rules to satisfiability and termination problems that can be addressed using state-of-the-art SMT solvers and program analysers. We introduce a tool called vIRONy that implements these techniques and we validate our approach against a number of case studies from the literature.","PeriodicalId":306693,"journal":{"name":"2017 International Conference on Intelligent Environments (IE)","volume":"155 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128465890","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}
Seonghun Lee, Messaoudi Oumaima, Su-Hyeon Ryu, Jaehwa Park
A real-time data acquisition system for precision agricultural is presented. Using the system, the spatiotemporal data for the specific local area can be collected at small expense. A hardware frame is designed to take synchronized multi-view images of the target plants as well as environmental data. To monitor the growth of plants or crops, set of images are taken periodically and a multi-view stereo technique is adopted to build a 3-D model to represent the target plant. For real-time monitoring an application running on the Android platform is developed also.
{"title":"A Realtime Spatiotemporal Data Acquisition System for Precision Agriculture","authors":"Seonghun Lee, Messaoudi Oumaima, Su-Hyeon Ryu, Jaehwa Park","doi":"10.1109/IE.2017.23","DOIUrl":"https://doi.org/10.1109/IE.2017.23","url":null,"abstract":"A real-time data acquisition system for precision agricultural is presented. Using the system, the spatiotemporal data for the specific local area can be collected at small expense. A hardware frame is designed to take synchronized multi-view images of the target plants as well as environmental data. To monitor the growth of plants or crops, set of images are taken periodically and a multi-view stereo technique is adopted to build a 3-D model to represent the target plant. For real-time monitoring an application running on the Android platform is developed also.","PeriodicalId":306693,"journal":{"name":"2017 International Conference on Intelligent Environments (IE)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130682367","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}
The wide availability of GPS-enabled devices has fueled the development of location-based applications. Among the most popular are navigation applications that guide users along their way. Due to the limited availability and precision of GPS in typical indoor environments, most navigation applications are limited to outdoor scenarios. To mitigate this, researchers and practitioners have been developing alternative systems to capture the position of a mobile device indoors. Using these systems, they clearly show that it is possible to provide precise location information at a reasonable cost. However, past applications in this domain have often focused exclusively on indoor scenarios.In this paper, we describe an approach to integrate the indoor and outdoor world to provide a seamless hybrid navigation experience. The approach builds upon our past work on indoor localization and integrates with our existing infrastructure for outdoor navigation that has been developed in the GAMBAS European research project. To evaluate the approach, we present data gathered from a real-world deployment as part of the SIMON European research project.
{"title":"An Approach for Hybrid Indoor/Outdoor Navigation","authors":"Stephan Wagner, Ngewi Fet, M. Handte, P. Marrón","doi":"10.1109/IE.2017.22","DOIUrl":"https://doi.org/10.1109/IE.2017.22","url":null,"abstract":"The wide availability of GPS-enabled devices has fueled the development of location-based applications. Among the most popular are navigation applications that guide users along their way. Due to the limited availability and precision of GPS in typical indoor environments, most navigation applications are limited to outdoor scenarios. To mitigate this, researchers and practitioners have been developing alternative systems to capture the position of a mobile device indoors. Using these systems, they clearly show that it is possible to provide precise location information at a reasonable cost. However, past applications in this domain have often focused exclusively on indoor scenarios.In this paper, we describe an approach to integrate the indoor and outdoor world to provide a seamless hybrid navigation experience. The approach builds upon our past work on indoor localization and integrates with our existing infrastructure for outdoor navigation that has been developed in the GAMBAS European research project. To evaluate the approach, we present data gathered from a real-world deployment as part of the SIMON European research project.","PeriodicalId":306693,"journal":{"name":"2017 International Conference on Intelligent Environments (IE)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122595984","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}
Yannick Körber, Vanessa Hahn, M. Moniri, Tim Schwartz, M. Feld
Today, cyber-physical environments (CPEs) are omnipresent–for instance as smart homes, cars, shopping environments, business facilities, Industrie 4.0 factories, and smart cities. Characterized by a large number of individual systems and devices with their sensors and actuators, the interaction paradigm from the user's perspective is shifting towards system-environment interaction. Following this principle, a single user or user groups can freely choose an interaction modality to address the environment, which responds in multiadaptive manner. This paper presents a car repair garage scenario and introduces a dialogue platform, a device platform, as well as several related dialogue management and group interaction technologies. Collectively, they represent a major result of the MADMACS project aimed at developing a framework for multiadaptive interaction in and with CPEs.
{"title":"MADMACS - Multiadaptive Dialogue Management in Cyber-Physical Environments","authors":"Yannick Körber, Vanessa Hahn, M. Moniri, Tim Schwartz, M. Feld","doi":"10.1109/IE.2017.33","DOIUrl":"https://doi.org/10.1109/IE.2017.33","url":null,"abstract":"Today, cyber-physical environments (CPEs) are omnipresent–for instance as smart homes, cars, shopping environments, business facilities, Industrie 4.0 factories, and smart cities. Characterized by a large number of individual systems and devices with their sensors and actuators, the interaction paradigm from the user's perspective is shifting towards system-environment interaction. Following this principle, a single user or user groups can freely choose an interaction modality to address the environment, which responds in multiadaptive manner. This paper presents a car repair garage scenario and introduces a dialogue platform, a device platform, as well as several related dialogue management and group interaction technologies. Collectively, they represent a major result of the MADMACS project aimed at developing a framework for multiadaptive interaction in and with CPEs.","PeriodicalId":306693,"journal":{"name":"2017 International Conference on Intelligent Environments (IE)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124590787","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}
Social events like carnival parades are major activities for modern urban life. However, public authorities should tackle a series of challenges in order to successfully manage such spectacles that take place in specific time periods and urban areas inside a city. Such challenges mainly concern crowd management and resource planning operations. Local public authorities should be able to take fast and efficient decisions prior, during and after the carnival parade. Decisions taken prior to the event are non-dynamic by nature, while during the event officials should make decisions in real-time based on instant data collected on the spot. Smartphone technology provides the appropriate critical infrastructure that facilitates the efficient collection and distribution of collected data. In this work, we present a specific architecture that aspires to help public authorities in managing carnival parades efficiently. Proposed architecture supports the establishment of an intelligent environment providing specific services which promote crowd management in terms of safety, cost effectiveness concerning better personnel management and spectator perceived usefulness and entertainment.
{"title":"Parades Aiding System (PAR.AID.S): Intelligent Management of Carnival Parades","authors":"Zois Koukopoulos, D. Koukopoulos","doi":"10.1109/IE.2017.24","DOIUrl":"https://doi.org/10.1109/IE.2017.24","url":null,"abstract":"Social events like carnival parades are major activities for modern urban life. However, public authorities should tackle a series of challenges in order to successfully manage such spectacles that take place in specific time periods and urban areas inside a city. Such challenges mainly concern crowd management and resource planning operations. Local public authorities should be able to take fast and efficient decisions prior, during and after the carnival parade. Decisions taken prior to the event are non-dynamic by nature, while during the event officials should make decisions in real-time based on instant data collected on the spot. Smartphone technology provides the appropriate critical infrastructure that facilitates the efficient collection and distribution of collected data. In this work, we present a specific architecture that aspires to help public authorities in managing carnival parades efficiently. Proposed architecture supports the establishment of an intelligent environment providing specific services which promote crowd management in terms of safety, cost effectiveness concerning better personnel management and spectator perceived usefulness and entertainment.","PeriodicalId":306693,"journal":{"name":"2017 International Conference on Intelligent Environments (IE)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123655821","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：