Human activity recognition has become very popular in the field of computer vision. In this paper, we present a simple, robust and computationally efficient algorithm, architecture and implementation to recognise and classify human activities in real-time using very few training data. We employ a spatio-temporal representation of human activities by combining trajectory information and invariant spatial information of the subjects. Activities are classified by a support vector machine (SVM) with a radial basis kernel. Optimal parameters for the SVM are found through a 10-fold cross-validation. Experimental results demonstrate that the proposed system is effective and efficient. When tested on the Weizmann dataset, the system achieves a recognition rate above 90% for one-shot learning which is above benchmark scores in accordance with the literature. The system is also found to be robust against noise, deformation and variation in viewpoints. The system is feasible to operate efficiently in real-time and deployable in intelligent environments.
{"title":"Real-Time Human Activity Recognition Using External and Internal Spatial Features","authors":"Z. Htike, S. Egerton, Y. Kuang","doi":"10.1109/IE.2010.17","DOIUrl":"https://doi.org/10.1109/IE.2010.17","url":null,"abstract":"Human activity recognition has become very popular in the field of computer vision. In this paper, we present a simple, robust and computationally efficient algorithm, architecture and implementation to recognise and classify human activities in real-time using very few training data. We employ a spatio-temporal representation of human activities by combining trajectory information and invariant spatial information of the subjects. Activities are classified by a support vector machine (SVM) with a radial basis kernel. Optimal parameters for the SVM are found through a 10-fold cross-validation. Experimental results demonstrate that the proposed system is effective and efficient. When tested on the Weizmann dataset, the system achieves a recognition rate above 90% for one-shot learning which is above benchmark scores in accordance with the literature. The system is also found to be robust against noise, deformation and variation in viewpoints. The system is feasible to operate efficiently in real-time and deployable in intelligent environments.","PeriodicalId":180375,"journal":{"name":"2010 Sixth International Conference on Intelligent Environments","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126647721","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}
F. Mastrogiovanni, Antonello Scalmato, A. Sgorbissa, R. Zaccaria
The focus of the present work is on daily activity planning, i.e., representations and algorithms able to produce a course of action to deal efficiently with problems of daily living. To achieve this, the article proposes a functional representation of everyday objects, places and actions described in terms of affordances. Its contributions are two--fold: i) it proposes to represent affordances and capabilities as regions in a proper affordance and capability space, and to describe such regions using neural maps; ii) it proposes to decompose the planning process into different activities, by introducing a phase referred to as Problem Awareness preceding Action Planning, which allows to reduce the planning space in order to tackle large-scale planning problems.
{"title":"Affordance-Based Planning for Assisting Humans in Daily Activities","authors":"F. Mastrogiovanni, Antonello Scalmato, A. Sgorbissa, R. Zaccaria","doi":"10.1109/IE.2010.11","DOIUrl":"https://doi.org/10.1109/IE.2010.11","url":null,"abstract":"The focus of the present work is on daily activity planning, i.e., representations and algorithms able to produce a course of action to deal efficiently with problems of daily living. To achieve this, the article proposes a functional representation of everyday objects, places and actions described in terms of affordances. Its contributions are two--fold: i) it proposes to represent affordances and capabilities as regions in a proper affordance and capability space, and to describe such regions using neural maps; ii) it proposes to decompose the planning process into different activities, by introducing a phase referred to as Problem Awareness preceding Action Planning, which allows to reduce the planning space in order to tackle large-scale planning problems.","PeriodicalId":180375,"journal":{"name":"2010 Sixth International Conference on Intelligent Environments","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127049532","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}
Alexander Kröner, Gerrit Kahl, L. Spassova, C. Magerkurth, T. Feld, D. Mayer, Ali Dada
The carbon footprint is an environment indicator, which is of special interest not only for assessing and optimizing production and logistic processes, but also for addressing a growing interest of customers in the ecologic characteristics of a product. Its computation and processing are tightly bound to research challenges, such as the capturing and exploration of item-level data, and the aggregation of item-level process instances. In this article, we report about a demonstration system, which aims at illustrating visitors of a technology fair how these challenges can be addressed by means of item-level records created from input obtained via smart labels. In a scenario spanning several steps of a product's lifecycle, the system enables the creation and exploitation of these records. During each stage, the system combines item-level data with more general information related, e.g., to the product class and the underlying process model - with the ultimate goal not only to support the assessment of an item’s carbon footprint, but also its reduction for future products of the same class.
{"title":"Demonstrating the Application of Digital Product Memories in a Carbon Footprint Scenario","authors":"Alexander Kröner, Gerrit Kahl, L. Spassova, C. Magerkurth, T. Feld, D. Mayer, Ali Dada","doi":"10.1109/IE.2010.37","DOIUrl":"https://doi.org/10.1109/IE.2010.37","url":null,"abstract":"The carbon footprint is an environment indicator, which is of special interest not only for assessing and optimizing production and logistic processes, but also for addressing a growing interest of customers in the ecologic characteristics of a product. Its computation and processing are tightly bound to research challenges, such as the capturing and exploration of item-level data, and the aggregation of item-level process instances. In this article, we report about a demonstration system, which aims at illustrating visitors of a technology fair how these challenges can be addressed by means of item-level records created from input obtained via smart labels. In a scenario spanning several steps of a product's lifecycle, the system enables the creation and exploitation of these records. During each stage, the system combines item-level data with more general information related, e.g., to the product class and the underlying process model - with the ultimate goal not only to support the assessment of an item’s carbon footprint, but also its reduction for future products of the same class.","PeriodicalId":180375,"journal":{"name":"2010 Sixth International Conference on Intelligent Environments","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122091802","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}
Autonomy of embedded agents in intelligent environments is highly debated topic; while some believe that agents should have very minimal autonomy and should only act as directly instructed by the user, others consider providing agents with autonomy to be an essential aspect to building intelligent environments. This paper reports on the current progress of our project to enable human users and agents to collaborate in managing intelligent environments as a team. We seek to develop an adjustable-autonomy agent in an effort to explore user acceptance of pervasive computing and the use of autonomous agents therein, as wells as aiming to improve the robustness and reliability of future intelligent environment systems. We present our Adjustable-autonomy Behaviour-Based Agent (ABBA) architecture model and discuss our initial trials with our prototype system, built on a smart home emulator, which demonstrate the plausibility of employing adjustable-autonomy in full-scale intelligent environments and pervasive computing systems.
{"title":"An Adjustable-Autonomy Agent for Intelligent Environments","authors":"Matthew Ball, V. Callaghan, M. Gardner","doi":"10.1109/IE.2010.8","DOIUrl":"https://doi.org/10.1109/IE.2010.8","url":null,"abstract":"Autonomy of embedded agents in intelligent environments is highly debated topic; while some believe that agents should have very minimal autonomy and should only act as directly instructed by the user, others consider providing agents with autonomy to be an essential aspect to building intelligent environments. This paper reports on the current progress of our project to enable human users and agents to collaborate in managing intelligent environments as a team. We seek to develop an adjustable-autonomy agent in an effort to explore user acceptance of pervasive computing and the use of autonomous agents therein, as wells as aiming to improve the robustness and reliability of future intelligent environment systems. We present our Adjustable-autonomy Behaviour-Based Agent (ABBA) architecture model and discuss our initial trials with our prototype system, built on a smart home emulator, which demonstrate the plausibility of employing adjustable-autonomy in full-scale intelligent environments and pervasive computing systems.","PeriodicalId":180375,"journal":{"name":"2010 Sixth International Conference on Intelligent Environments","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121193718","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}
With fast proceeding demographic change, lack of qualified nursing staff and costs explosion concerning our health and welfare systems, new methods have to be developed to support elderly people in their home environment with ambient integrated and intelligent assistance/service technologies. Service units and related typologies presented in this paper are adding new layers of functionalities to conventional home care environments. To simplify implementation, service units shift the complexity arising with more and more complex high-tech buildings to a compact entity/unit which could be industrially prefabricated/customized and equipped with various assistance technologies in a controlled factory environment. Moreover, service units can be installed within new or existing buildings rapidly and with minimized effort as an additional building sub-module.
{"title":"Compacted and Industrially Customizable Ambient Intelligent Service Units: Typology, Examples and Performance","authors":"T. Linner, M. Kranz, L. Roalter, T. Bock","doi":"10.1109/IE.2010.60","DOIUrl":"https://doi.org/10.1109/IE.2010.60","url":null,"abstract":"With fast proceeding demographic change, lack of qualified nursing staff and costs explosion concerning our health and welfare systems, new methods have to be developed to support elderly people in their home environment with ambient integrated and intelligent assistance/service technologies. Service units and related typologies presented in this paper are adding new layers of functionalities to conventional home care environments. To simplify implementation, service units shift the complexity arising with more and more complex high-tech buildings to a compact entity/unit which could be industrially prefabricated/customized and equipped with various assistance technologies in a controlled factory environment. Moreover, service units can be installed within new or existing buildings rapidly and with minimized effort as an additional building sub-module.","PeriodicalId":180375,"journal":{"name":"2010 Sixth International Conference on Intelligent Environments","volume":"128 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116218160","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}
Intelligent environments have been commercially available already over ten years without becoming such a mass product as expected. The expectations of potential users of mentioned solutions have not fulfilled yet due to missing globally accepted standards causing interoperability problems of different hardware and software components, complexity of configuration and use, lack of universal service consideration, and insufficient ROI for private residence owners. Clearly, a stronger emphasis needs to be set on device adaptation, usability and scalability, which can seamlessly accommodate new smart environment services. This paper presents a framework for network adaptation in intelligent environments using OSGi and UPnP technology allowing the uniform and transparent access to devices and services present in the networked environment and supporting the realization of activity spheres across a mixture of heterogeneous networks. The proposed network adaptation framework has been implemented within the ATRACO project and supports an ambient ecology trial hosted in the iSpace in Essex demonstrating a “feeling comfortable with guests” scenario.
{"title":"Network Adaptation in Intelligent Environments","authors":"A. Meliones, D. Economou, Ioannis Liverezas","doi":"10.1109/IE.2010.48","DOIUrl":"https://doi.org/10.1109/IE.2010.48","url":null,"abstract":"Intelligent environments have been commercially available already over ten years without becoming such a mass product as expected. The expectations of potential users of mentioned solutions have not fulfilled yet due to missing globally accepted standards causing interoperability problems of different hardware and software components, complexity of configuration and use, lack of universal service consideration, and insufficient ROI for private residence owners. Clearly, a stronger emphasis needs to be set on device adaptation, usability and scalability, which can seamlessly accommodate new smart environment services. This paper presents a framework for network adaptation in intelligent environments using OSGi and UPnP technology allowing the uniform and transparent access to devices and services present in the networked environment and supporting the realization of activity spheres across a mixture of heterogeneous networks. The proposed network adaptation framework has been implemented within the ATRACO project and supports an ambient ecology trial hosted in the iSpace in Essex demonstrating a “feeling comfortable with guests” scenario.","PeriodicalId":180375,"journal":{"name":"2010 Sixth International Conference on Intelligent Environments","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126534330","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}
V. Zamudio, Rosario Baltazar, M. A. Casillas, V. Callaghan
Ambient Intelligence, and in general, any autonomous rule based system has been found to suffer from cyclic instability. This behaviour is characterized by unwanted oscillations, due to interacting rules within networks of pervasive computing devices. The binary behaviour of each agent is defined via a set of boolean rules, and the behaviour of the system as a whole is given by the ensemble of rules defined over the set of agents. From complex theory it has been found that the problem of cyclic instability cannot be solved analytically; however, it is possible to prevent it. In this paper we present a novel solution based on locking, to prevent cyclic instability. This strategy makes use of the topological properties of the digraph associated called Interaction Network (IN), and the local rules of the interacting agents. The concept of strong and weak coupling is introduced. Using the strong and weak concepts, a strategy c-INPRES that minimizes the number of agents locked is presented. Preliminary and encouraging results are shown.
{"title":"c-INPRES: Coupling Analysis towards Locking Optimization in Ambient Intelligence","authors":"V. Zamudio, Rosario Baltazar, M. A. Casillas, V. Callaghan","doi":"10.1109/IE.2010.20","DOIUrl":"https://doi.org/10.1109/IE.2010.20","url":null,"abstract":"Ambient Intelligence, and in general, any autonomous rule based system has been found to suffer from cyclic instability. This behaviour is characterized by unwanted oscillations, due to interacting rules within networks of pervasive computing devices. The binary behaviour of each agent is defined via a set of boolean rules, and the behaviour of the system as a whole is given by the ensemble of rules defined over the set of agents. From complex theory it has been found that the problem of cyclic instability cannot be solved analytically; however, it is possible to prevent it. In this paper we present a novel solution based on locking, to prevent cyclic instability. This strategy makes use of the topological properties of the digraph associated called Interaction Network (IN), and the local rules of the interacting agents. The concept of strong and weak coupling is introduced. Using the strong and weak concepts, a strategy c-INPRES that minimizes the number of agents locked is presented. Preliminary and encouraging results are shown.","PeriodicalId":180375,"journal":{"name":"2010 Sixth International Conference on Intelligent Environments","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130749855","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}
Sensor networks are gaining popularity in pervasive environment for tracking events such as habitat monitoring, weather monitoring, hazard detection etc. These sensor nodes are very much power constrained and therefore requires energy efficient protocol to well manage their energy resources. An architecture based on biologically-inspired (botany) mobile agent based sensor (BIMAS) is proposed to tackle the energy issues of sensor networks. BIMAS handles the energy issues by exploiting mobile agents that communicates with static sensor nodes and forwards sensed data to a base station. The introduction of mobile agents brings benefit in terms of shifting routing issues away from sensor nodes to mobile agents. The advantage of BIMAs can be shown in terms of efficient energy resources, fault tolerance and efficient handling of hole problems.
{"title":"Biologically Inspired (Botany) Mobile Agent Based Self-Healing Wireless Sensor Network","authors":"V. Ponnusamy, A. Abdullah","doi":"10.1109/IE.2010.46","DOIUrl":"https://doi.org/10.1109/IE.2010.46","url":null,"abstract":"Sensor networks are gaining popularity in pervasive environment for tracking events such as habitat monitoring, weather monitoring, hazard detection etc. These sensor nodes are very much power constrained and therefore requires energy efficient protocol to well manage their energy resources. An architecture based on biologically-inspired (botany) mobile agent based sensor (BIMAS) is proposed to tackle the energy issues of sensor networks. BIMAS handles the energy issues by exploiting mobile agents that communicates with static sensor nodes and forwards sensed data to a base station. The introduction of mobile agents brings benefit in terms of shifting routing issues away from sensor nodes to mobile agents. The advantage of BIMAs can be shown in terms of efficient energy resources, fault tolerance and efficient handling of hole problems.","PeriodicalId":180375,"journal":{"name":"2010 Sixth International Conference on Intelligent Environments","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132985375","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}
In this paper we present an overview of the state-of- the-art approaches for speech recognition of the Russian language. Since Russian is a highly inflective language with a complex mechanism of word formation, the main approaches for English speech recognition are not optimally applicable for Russian speech, at least directly and without appropriate adaptation. We make here an overview of some modern methods designed specially for Russian and other languages with similar word formation mechanism and grammar basis. Among them there are morpheme based speech recognition and compound language modeling. We also describe here our direction for possible subsequent Russian speech recognizer improvements.
{"title":"Some Approaches for Russian Speech Recognition","authors":"Sergey Zablotskiy, Kseniya Zablotskaya, W. Minker","doi":"10.1109/IE.2010.25","DOIUrl":"https://doi.org/10.1109/IE.2010.25","url":null,"abstract":"In this paper we present an overview of the state-of- the-art approaches for speech recognition of the Russian language. Since Russian is a highly inflective language with a complex mechanism of word formation, the main approaches for English speech recognition are not optimally applicable for Russian speech, at least directly and without appropriate adaptation. We make here an overview of some modern methods designed specially for Russian and other languages with similar word formation mechanism and grammar basis. Among them there are morpheme based speech recognition and compound language modeling. We also describe here our direction for possible subsequent Russian speech recognizer improvements.","PeriodicalId":180375,"journal":{"name":"2010 Sixth International Conference on Intelligent Environments","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123689665","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}
In this paper we present results from a questionnaire on public displays that aim to increase social cohesion. The displays highlight unexpected social links between passers-by in urban areas, which might lead to the strengthening of existing links and even the creation of new links between people. The results from the questionnaire show that the majority of respondents believes that the proposed displays might increase social cohesion, and about half of them would use them. Some respondents however are afraid for their privacy, security, and being annoyed by strangers. For personal displays, which show information only about single persons, the most popular content are name, interests and contact options. For interpersonal displays, which show information about pairs of people, the most popular information are common friends and common interests. The popularity of the proposed displays however depended strongly on the social context where they would be used. We present a preliminary prototype of a personal display, which is deployed in a university context.
{"title":"Users' Opinions on Public Displays that Aim to Increase Social Cohesion","authors":"Matthias Böhmer, Jörg Müller","doi":"10.1109/IE.2010.53","DOIUrl":"https://doi.org/10.1109/IE.2010.53","url":null,"abstract":"In this paper we present results from a questionnaire on public displays that aim to increase social cohesion. The displays highlight unexpected social links between passers-by in urban areas, which might lead to the strengthening of existing links and even the creation of new links between people. The results from the questionnaire show that the majority of respondents believes that the proposed displays might increase social cohesion, and about half of them would use them. Some respondents however are afraid for their privacy, security, and being annoyed by strangers. For personal displays, which show information only about single persons, the most popular content are name, interests and contact options. For interpersonal displays, which show information about pairs of people, the most popular information are common friends and common interests. The popularity of the proposed displays however depended strongly on the social context where they would be used. We present a preliminary prototype of a personal display, which is deployed in a university context.","PeriodicalId":180375,"journal":{"name":"2010 Sixth International Conference on Intelligent Environments","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128173272","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：