Pub Date : 2015-07-06DOI: 10.1109/IISA.2015.7388125
E. Christopoulou, Dimitris Ringas
In this paper we present field experience from the in-the-wild deployment of the recommendation mechanism of CLIO, a novel urban computing system that allows forming and interacting with the collective city memory. Our goal has been to study how users perceive relevant content and in which way the context affects the content they want to explore. We had the opportunity to evaluate for a long-term CLIO in two different cities, in Greece and Finland. The recommendation mechanism of CLIO exploits intelligent techniques in order to present users suitable memories. Intelligence in CLIO is primarily grounded on its ontology-based context model, a reasoning and inference mechanism that support context-awareness and finally a rule-based system producing content recommendations for users based on their random interactions with the system. Our findings during two distinct phases of evaluation shed light on how users consider their profile and preferences, how they perceive relevant content and how the context affects their selections. These results allowed us to develop a recommendation mechanism for the CLIO system, that produces "wild" recommendations for users based on their random interactions with CLIO.
{"title":"Wild recommendations: Presenting citizens relevant content based on use patterns and context","authors":"E. Christopoulou, Dimitris Ringas","doi":"10.1109/IISA.2015.7388125","DOIUrl":"https://doi.org/10.1109/IISA.2015.7388125","url":null,"abstract":"In this paper we present field experience from the in-the-wild deployment of the recommendation mechanism of CLIO, a novel urban computing system that allows forming and interacting with the collective city memory. Our goal has been to study how users perceive relevant content and in which way the context affects the content they want to explore. We had the opportunity to evaluate for a long-term CLIO in two different cities, in Greece and Finland. The recommendation mechanism of CLIO exploits intelligent techniques in order to present users suitable memories. Intelligence in CLIO is primarily grounded on its ontology-based context model, a reasoning and inference mechanism that support context-awareness and finally a rule-based system producing content recommendations for users based on their random interactions with the system. Our findings during two distinct phases of evaluation shed light on how users consider their profile and preferences, how they perceive relevant content and how the context affects their selections. These results allowed us to develop a recommendation mechanism for the CLIO system, that produces \"wild\" recommendations for users based on their random interactions with CLIO.","PeriodicalId":433872,"journal":{"name":"2015 6th International Conference on Information, Intelligence, Systems and Applications (IISA)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127595601","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 : 2015-07-06DOI: 10.1109/IISA.2015.7387980
Paul-Stefan Popescu, M. Mocanu, D. Burdescu, M. Mihăescu
This paper presents the design of a system that performs a data analysis processes on the students' interaction activity. We aim to find if there is any correlation between student's knowledge level and their messaging activity. In the first phase, we perform a comprehensive literature review such that we obtain an extensive listing of relevant features. Once the features list is obtained and the dataset is built, we can perform several data analysis processes in order to see which machine learning algorithm can perform better on the available data. As application domain we propose the use of Tesys e-Learning platform, which runs at several faculties from University of Craiova.
{"title":"Messaging activity impact on learner's profiling","authors":"Paul-Stefan Popescu, M. Mocanu, D. Burdescu, M. Mihăescu","doi":"10.1109/IISA.2015.7387980","DOIUrl":"https://doi.org/10.1109/IISA.2015.7387980","url":null,"abstract":"This paper presents the design of a system that performs a data analysis processes on the students' interaction activity. We aim to find if there is any correlation between student's knowledge level and their messaging activity. In the first phase, we perform a comprehensive literature review such that we obtain an extensive listing of relevant features. Once the features list is obtained and the dataset is built, we can perform several data analysis processes in order to see which machine learning algorithm can perform better on the available data. As application domain we propose the use of Tesys e-Learning platform, which runs at several faculties from University of Craiova.","PeriodicalId":433872,"journal":{"name":"2015 6th International Conference on Information, Intelligence, Systems and Applications (IISA)","volume":"72 11","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120904882","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 : 2015-07-06DOI: 10.1109/IISA.2015.7388069
Avar Pentel
The aim of the current study is to compare the effect of three different feature types for age-based categorization of short texts as average 85 words per author. Besides widely used word and character n-grams, text readability features are proposed as an alternative. By readability features we mean different relative ratios of text elements as characters per word, words per sentence, etc. Support Vector Machines, Logistic Regression, and Bayesian algorithms were used to build models. Most effective features were readability features and character n-grams. Model generated by Support Vector Machine and combined feature set yield to f-score 0.968. Age prediction application was built using a model with readability features.
{"title":"Effect of different feature types on age based classification of short texts","authors":"Avar Pentel","doi":"10.1109/IISA.2015.7388069","DOIUrl":"https://doi.org/10.1109/IISA.2015.7388069","url":null,"abstract":"The aim of the current study is to compare the effect of three different feature types for age-based categorization of short texts as average 85 words per author. Besides widely used word and character n-grams, text readability features are proposed as an alternative. By readability features we mean different relative ratios of text elements as characters per word, words per sentence, etc. Support Vector Machines, Logistic Regression, and Bayesian algorithms were used to build models. Most effective features were readability features and character n-grams. Model generated by Support Vector Machine and combined feature set yield to f-score 0.968. Age prediction application was built using a model with readability features.","PeriodicalId":433872,"journal":{"name":"2015 6th International Conference on Information, Intelligence, Systems and Applications (IISA)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117062698","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 : 2015-07-06DOI: 10.1109/IISA.2015.7387999
Vassiliki Mpelogianni, P. Groumpos, Dimitris Tsipianitis, P. Mantas, Stefanos Michos, S. Pravadalioglu
An intelligent software tool for the reduction of the energy consumption of buildings is being presented. A case of a commercial building in the southern part of Greece is examined. In this study we will simulate the above-mentioned building and study its energy consumption. Fuzzy Logic Controllers that control the various parts of the building automation (HVAC, Lighting etc) are being developed. The energy requirements of the building are modeled using the TRNSYS Software tool.
{"title":"A fuzzy inference tool for the achievement of sustainable energy solutions","authors":"Vassiliki Mpelogianni, P. Groumpos, Dimitris Tsipianitis, P. Mantas, Stefanos Michos, S. Pravadalioglu","doi":"10.1109/IISA.2015.7387999","DOIUrl":"https://doi.org/10.1109/IISA.2015.7387999","url":null,"abstract":"An intelligent software tool for the reduction of the energy consumption of buildings is being presented. A case of a commercial building in the southern part of Greece is examined. In this study we will simulate the above-mentioned building and study its energy consumption. Fuzzy Logic Controllers that control the various parts of the building automation (HVAC, Lighting etc) are being developed. The energy requirements of the building are modeled using the TRNSYS Software tool.","PeriodicalId":433872,"journal":{"name":"2015 6th International Conference on Information, Intelligence, Systems and Applications (IISA)","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117266135","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 : 2015-07-06DOI: 10.1109/IISA.2015.7388102
Lotta Haukipuro, I. Shabalina, M. Ylianttila
The paper addresses opportunities that the fast diffusion of Information and Communication Technology is opening for people with different levels of physical restrictions, or disabilities. For these people mobile technology not only allows ubiquity for communications but also anytime access to some services that are vital for their security and autonomy thus preventing social exclusion. More specifically, the paper describes evaluation study and four developed ICT based services aimed to prevent social exclusion and ease everyday life of persons with disabilities. Findings of the study show that there is enormous need for the services aimed for disabled to promote their equal status in society.
{"title":"Preventing social exclusion for persons with disabilities through ICT based services","authors":"Lotta Haukipuro, I. Shabalina, M. Ylianttila","doi":"10.1109/IISA.2015.7388102","DOIUrl":"https://doi.org/10.1109/IISA.2015.7388102","url":null,"abstract":"The paper addresses opportunities that the fast diffusion of Information and Communication Technology is opening for people with different levels of physical restrictions, or disabilities. For these people mobile technology not only allows ubiquity for communications but also anytime access to some services that are vital for their security and autonomy thus preventing social exclusion. More specifically, the paper describes evaluation study and four developed ICT based services aimed to prevent social exclusion and ease everyday life of persons with disabilities. Findings of the study show that there is enormous need for the services aimed for disabled to promote their equal status in society.","PeriodicalId":433872,"journal":{"name":"2015 6th International Conference on Information, Intelligence, Systems and Applications (IISA)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115744052","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 : 2015-07-06DOI: 10.1109/IISA.2015.7388057
Radhouane B. N. Jrad, D. Sundaram
Inter-Organizational Information Systems (IOIS) are automated Information Systems spanning across partnering organizations and aiming at synergizing their forces to increase competitiveness and cost efficiency [1], [2]. An Inter-Organizational Middleware System (IOMS) is the component inside IOIS that is responsible for bridging various partners' systems while holding some business intelligence [3]. Processes, roadmaps, and frameworks managing change in Information Systems are in abundance. However there is a paucity of literature on frameworks for managing change in IOIS and the situation is even direr in the context of IOMS. In this paper we first explore the concept of frameworks and in particular IS and IOIS frameworks. Using these as a foundation, we go on to propose a framework to manage IOMS changes, and we discuss their bases and merits. We then validate it through application in the context of a real-world project in an international firm. The authors of this article have over a decade of experience in IOIS and IOMS systems, and use an interpretative lens to study the implementation.
{"title":"Inter-organizational middleware systems: A framework for managing change","authors":"Radhouane B. N. Jrad, D. Sundaram","doi":"10.1109/IISA.2015.7388057","DOIUrl":"https://doi.org/10.1109/IISA.2015.7388057","url":null,"abstract":"Inter-Organizational Information Systems (IOIS) are automated Information Systems spanning across partnering organizations and aiming at synergizing their forces to increase competitiveness and cost efficiency [1], [2]. An Inter-Organizational Middleware System (IOMS) is the component inside IOIS that is responsible for bridging various partners' systems while holding some business intelligence [3]. Processes, roadmaps, and frameworks managing change in Information Systems are in abundance. However there is a paucity of literature on frameworks for managing change in IOIS and the situation is even direr in the context of IOMS. In this paper we first explore the concept of frameworks and in particular IS and IOIS frameworks. Using these as a foundation, we go on to propose a framework to manage IOMS changes, and we discuss their bases and merits. We then validate it through application in the context of a real-world project in an international firm. The authors of this article have over a decade of experience in IOIS and IOMS systems, and use an interpretative lens to study the implementation.","PeriodicalId":433872,"journal":{"name":"2015 6th International Conference on Information, Intelligence, Systems and Applications (IISA)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131562728","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 : 2015-07-06DOI: 10.1109/IISA.2015.7388086
Alessia Amelio, C. Pizzuti
Community detection in complex networks that evolve over time is a challenging task, intensively studied in the last few years. An algorithm designed for this problem should be able to successfully discover if changes occurred in the network, and quickly react by modifying the community structure for reflecting the new network organization. Evolutionary dynamic optimization is a powerful technique to solve time-dependent problems by applying evolutionary algorithms. In this paper we propose to exploit it for time evolving graphs in order to discover changes in community structure and to quickly adapt when such changes occur. The approach uses a population-based model for change detection, and applies two different strategies to adapt to changes. Experimental results on synthetic networks show the very good performances of evolutionary dynamic optimization to deal with this kind of problem.
{"title":"An evolutionary dynamic optimization framework for structure change detection of streaming networks","authors":"Alessia Amelio, C. Pizzuti","doi":"10.1109/IISA.2015.7388086","DOIUrl":"https://doi.org/10.1109/IISA.2015.7388086","url":null,"abstract":"Community detection in complex networks that evolve over time is a challenging task, intensively studied in the last few years. An algorithm designed for this problem should be able to successfully discover if changes occurred in the network, and quickly react by modifying the community structure for reflecting the new network organization. Evolutionary dynamic optimization is a powerful technique to solve time-dependent problems by applying evolutionary algorithms. In this paper we propose to exploit it for time evolving graphs in order to discover changes in community structure and to quickly adapt when such changes occur. The approach uses a population-based model for change detection, and applies two different strategies to adapt to changes. Experimental results on synthetic networks show the very good performances of evolutionary dynamic optimization to deal with this kind of problem.","PeriodicalId":433872,"journal":{"name":"2015 6th International Conference on Information, Intelligence, Systems and Applications (IISA)","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128328784","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 : 2015-07-06DOI: 10.1109/IISA.2015.7387968
Ariadni-Irini Skoulikari, A. Tsakalidis, D. Tsolis
This paper presents the design and implementation of a eLearning system which supports personalized and adaptive eLearning. The courses and services are especially designed so as to be accessible through mobile networks and devices. The training modules are aiming mainly in Life-Long Learning through cultural education.
{"title":"Personalized and adaptive mobile elearning for cultural education","authors":"Ariadni-Irini Skoulikari, A. Tsakalidis, D. Tsolis","doi":"10.1109/IISA.2015.7387968","DOIUrl":"https://doi.org/10.1109/IISA.2015.7387968","url":null,"abstract":"This paper presents the design and implementation of a eLearning system which supports personalized and adaptive eLearning. The courses and services are especially designed so as to be accessible through mobile networks and devices. The training modules are aiming mainly in Life-Long Learning through cultural education.","PeriodicalId":433872,"journal":{"name":"2015 6th International Conference on Information, Intelligence, Systems and Applications (IISA)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126831347","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 : 2015-07-06DOI: 10.1109/IISA.2015.7388119
A. Demertzis, K. Oikonomou
Many-to-one wireless sensor networks suffer from an extreme variance of energy consumption due to diverse traffic load within the network nodes. Sensor nodes close to the sink consume significantly more energy than the farther ones, resulting in the energy hole problem (i.e., global variance). In addition, even nodes located at the same distance from the sink experience different traffic load with each other (i.e., local variance). The uneven distribution of traffic load, both globally and locally, results in a severe shortening of the time until the first node runs out of battery. This work focuses on balancing the traffic load of equally-distant from the sink nodes by sharing each one's load among its next-hop neighbors. Eventually, packets are traveling from a node to the sink by following interlaced paths. The proposed routing mechanism, called braided routing, is a simple one and can be applied over any least-cost routing policy, incurring a negligible overhead. Simulation results show that the local variance of energy consumption is reduced about 70-80% on average while the time until the first nodal loss can be prolonged more than twice in many cases.
{"title":"A braided routing mechanism to reduce traffic load's local variance in wireless sensor networks","authors":"A. Demertzis, K. Oikonomou","doi":"10.1109/IISA.2015.7388119","DOIUrl":"https://doi.org/10.1109/IISA.2015.7388119","url":null,"abstract":"Many-to-one wireless sensor networks suffer from an extreme variance of energy consumption due to diverse traffic load within the network nodes. Sensor nodes close to the sink consume significantly more energy than the farther ones, resulting in the energy hole problem (i.e., global variance). In addition, even nodes located at the same distance from the sink experience different traffic load with each other (i.e., local variance). The uneven distribution of traffic load, both globally and locally, results in a severe shortening of the time until the first node runs out of battery. This work focuses on balancing the traffic load of equally-distant from the sink nodes by sharing each one's load among its next-hop neighbors. Eventually, packets are traveling from a node to the sink by following interlaced paths. The proposed routing mechanism, called braided routing, is a simple one and can be applied over any least-cost routing policy, incurring a negligible overhead. Simulation results show that the local variance of energy consumption is reduced about 70-80% on average while the time until the first nodal loss can be prolonged more than twice in many cases.","PeriodicalId":433872,"journal":{"name":"2015 6th International Conference on Information, Intelligence, Systems and Applications (IISA)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114282708","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 : 2015-07-06DOI: 10.1109/IISA.2015.7387991
Karen Pajarito, R. Feria
As learners start to become more attuned to using mobile devices, learning-on-the-go is but a natural progression to their way of discovering new knowledge. Whilst the mobile web provides a vast resource of knowledge, structured learning is still one of the most effective means of education. Unlike desktop and portable computers, mobile devices are resource constrained, i.e., lower processing power and less storage capacity, which limits its capability to process large learning resources, or learning objects. This provides an opportunity to introduce micro-learning, a way to shrink a learning material to its smallest and most compact component for easier transmission and lower storage requirement, whilst preserving its effectivity. This paper proposes a platform that implements the proposed standards in creating micro-learning content for mobile devices. The standards cover the recommended technical specifications for software for mobile devices and content packaging format of the learning content. The web-based authoring tool of the platform will allow the teachers to develop micro-learning courses that the learners can access through a mobile application.
{"title":"MicroCAS: Design and implementation of proposed standards in micro-learning on mobile devices","authors":"Karen Pajarito, R. Feria","doi":"10.1109/IISA.2015.7387991","DOIUrl":"https://doi.org/10.1109/IISA.2015.7387991","url":null,"abstract":"As learners start to become more attuned to using mobile devices, learning-on-the-go is but a natural progression to their way of discovering new knowledge. Whilst the mobile web provides a vast resource of knowledge, structured learning is still one of the most effective means of education. Unlike desktop and portable computers, mobile devices are resource constrained, i.e., lower processing power and less storage capacity, which limits its capability to process large learning resources, or learning objects. This provides an opportunity to introduce micro-learning, a way to shrink a learning material to its smallest and most compact component for easier transmission and lower storage requirement, whilst preserving its effectivity. This paper proposes a platform that implements the proposed standards in creating micro-learning content for mobile devices. The standards cover the recommended technical specifications for software for mobile devices and content packaging format of the learning content. The web-based authoring tool of the platform will allow the teachers to develop micro-learning courses that the learners can access through a mobile application.","PeriodicalId":433872,"journal":{"name":"2015 6th International Conference on Information, Intelligence, Systems and Applications (IISA)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114570778","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：