Pub Date : 2015-07-06DOI: 10.1109/IISA.2015.7388071
Joseph DiRenzo, Dana A. Goward, F. Roberts
The vulnerabilities to cyber attacks of today's marine transportation system have not been well studied. This paper explores vulnerabilities of shipboard systems, oil rigs, cargo, and port operations.
{"title":"The little-known challenge of maritime cyber security","authors":"Joseph DiRenzo, Dana A. Goward, F. Roberts","doi":"10.1109/IISA.2015.7388071","DOIUrl":"https://doi.org/10.1109/IISA.2015.7388071","url":null,"abstract":"The vulnerabilities to cyber attacks of today's marine transportation system have not been well studied. This paper explores vulnerabilities of shipboard systems, oil rigs, cargo, and port operations.","PeriodicalId":433872,"journal":{"name":"2015 6th International Conference on Information, Intelligence, Systems and Applications (IISA)","volume":"411 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":"129283596","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.2015.7388067
D. Tselios, P. Ipsilandis, V. Gerogiannis
The Incremental Funding Method (IFM) in software development projects aims at optimizing the financial return of a software project through proper sequencing of development activities and incremental releases of the software product. This paper presents a Dynamic Programming (DP) project scheduling algorithm that maximizes a software project's net present value (NPV) under IFM assumptions. Through an exemplar case study we demonstrate that the DP algorithm guarantees optimality in the project scheduling sequence and offers flexibility in adjusting the optimum project schedule dynamically, as market or development conditions change.
{"title":"A dynamic programming algorithm for optimizing the financial return of software projects","authors":"D. Tselios, P. Ipsilandis, V. Gerogiannis","doi":"10.1109/IISA.2015.7388067","DOIUrl":"https://doi.org/10.1109/IISA.2015.7388067","url":null,"abstract":"The Incremental Funding Method (IFM) in software development projects aims at optimizing the financial return of a software project through proper sequencing of development activities and incremental releases of the software product. This paper presents a Dynamic Programming (DP) project scheduling algorithm that maximizes a software project's net present value (NPV) under IFM assumptions. Through an exemplar case study we demonstrate that the DP algorithm guarantees optimality in the project scheduling sequence and offers flexibility in adjusting the optimum project schedule dynamically, as market or development conditions change.","PeriodicalId":433872,"journal":{"name":"2015 6th International Conference on Information, Intelligence, Systems and Applications (IISA)","volume":"63 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":"128632855","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.2015.7388079
Jean-Sébastien Bilodeau, Dany Fortin-Simard, S. Gaboury, B. Bouchard, A. Bouzouane
The rapid adoption of wireless technologies has increased the interest of many laboratories about the field of Wireless Sensor Network (WSN) or the Radio-Frequency Identification (RFID) technology which has emerged as a winning combination for the implementation of an advanced assistance system within smart environments. To fulfill the important mission of a technological assistance, an algorithm first had to identify the ongoing activities of its user by tracking everyday life objects in real time using, for example, passive RFID tags. To increase the quality of information extracted from the objects localization by properly using the Received Signal Strength Indicator (RSSI), this paper explores Kalman filter, particle filter and few others filtering algorithm that enhances the tracking performance. It also discusses three of the most interesting methods that can be applied for the localization of objects in smart environments without requiring the installation of references tags everywhere. Finally, to increase the value, we include experiments that were conducted within a real smart home infrastructure to review the positive and negative elements of each method.
{"title":"A practical comparison between filtering algorithms for enhanced RFID localization in smart environments","authors":"Jean-Sébastien Bilodeau, Dany Fortin-Simard, S. Gaboury, B. Bouchard, A. Bouzouane","doi":"10.1109/IISA.2015.7388079","DOIUrl":"https://doi.org/10.1109/IISA.2015.7388079","url":null,"abstract":"The rapid adoption of wireless technologies has increased the interest of many laboratories about the field of Wireless Sensor Network (WSN) or the Radio-Frequency Identification (RFID) technology which has emerged as a winning combination for the implementation of an advanced assistance system within smart environments. To fulfill the important mission of a technological assistance, an algorithm first had to identify the ongoing activities of its user by tracking everyday life objects in real time using, for example, passive RFID tags. To increase the quality of information extracted from the objects localization by properly using the Received Signal Strength Indicator (RSSI), this paper explores Kalman filter, particle filter and few others filtering algorithm that enhances the tracking performance. It also discusses three of the most interesting methods that can be applied for the localization of objects in smart environments without requiring the installation of references tags everywhere. Finally, to increase the value, we include experiments that were conducted within a real smart home infrastructure to review the positive and negative elements of each method.","PeriodicalId":433872,"journal":{"name":"2015 6th International Conference on Information, Intelligence, Systems and Applications (IISA)","volume":"52 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":"116364909","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.2015.7388083
C. Stephens, Hugo Flores, Ana Ruiz Linares
The Naive Bayes approximation and associated classifier is widely used in machine learning and data mining and offers very robust performance across a large spectrum of problem domains. As it depends on a very strong assumption - independence among features - this has been somewhat puzzling. Various hypotheses have been put forward to explain its success and moreover many generalizations have been proposed. In this paper we propose a set of "local" error measures - associated with the likelihood functions for particular subsets of attributes and for each class - and show explicitly how these local errors combine to give a "global" error associated to the full attribute set. By so doing we formulate a framework within which the phenomenon of error cancelation, or augmentation, can be quantitatively evaluated and its impact on classifier performance estimated and predicted a priori. These diagnostics also allow us to develop a deeper and more quantitative understanding of why the Naive Bayes approximation is so robust and under what circumstances one expects it to break down.
{"title":"Why the Naive Bayes approximation is not as Naive as it appears","authors":"C. Stephens, Hugo Flores, Ana Ruiz Linares","doi":"10.1109/IISA.2015.7388083","DOIUrl":"https://doi.org/10.1109/IISA.2015.7388083","url":null,"abstract":"The Naive Bayes approximation and associated classifier is widely used in machine learning and data mining and offers very robust performance across a large spectrum of problem domains. As it depends on a very strong assumption - independence among features - this has been somewhat puzzling. Various hypotheses have been put forward to explain its success and moreover many generalizations have been proposed. In this paper we propose a set of \"local\" error measures - associated with the likelihood functions for particular subsets of attributes and for each class - and show explicitly how these local errors combine to give a \"global\" error associated to the full attribute set. By so doing we formulate a framework within which the phenomenon of error cancelation, or augmentation, can be quantitatively evaluated and its impact on classifier performance estimated and predicted a priori. These diagnostics also allow us to develop a deeper and more quantitative understanding of why the Naive Bayes approximation is so robust and under what circumstances one expects it to break down.","PeriodicalId":433872,"journal":{"name":"2015 6th International Conference on Information, Intelligence, Systems and Applications (IISA)","volume":"97 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":"116920829","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.2015.7388128
Evangelos Spiliotis, G. Anastasopoulos, Phaedra Dede, Vangelis Marinakis, H. Doukas
This paper introduces a methodological approach for evaluating the thermal comfort of building users, captured through social media, in order to evaluate and accordingly adjust energy management action plans. A framework for performing sentiment analysis of messages is developed and a pilot case is presented for optimally scheduling the temperature set-point adjustment of a municipal building, based on user thermal comfort criteria retrieved from social data.
{"title":"A framework for integrating user experience in action plan evaluation through social media: Transforming user generated content into knowledge to optimise energy use in buildings","authors":"Evangelos Spiliotis, G. Anastasopoulos, Phaedra Dede, Vangelis Marinakis, H. Doukas","doi":"10.1109/IISA.2015.7388128","DOIUrl":"https://doi.org/10.1109/IISA.2015.7388128","url":null,"abstract":"This paper introduces a methodological approach for evaluating the thermal comfort of building users, captured through social media, in order to evaluate and accordingly adjust energy management action plans. A framework for performing sentiment analysis of messages is developed and a pilot case is presented for optimally scheduling the temperature set-point adjustment of a municipal building, based on user thermal comfort criteria retrieved from social data.","PeriodicalId":433872,"journal":{"name":"2015 6th International Conference on Information, Intelligence, Systems and Applications (IISA)","volume":"25 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":"115588359","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.2015.7388048
C. Troussas, K. Espinosa, M. Virvou
Computer-based advising is focusing on factors that facilitate advice giving in educational systems. In this paper, an intelligent advice generation module is presented. As a testbed for our research, we have incorporated the advice generation mechanism in a Facebook application for language learning. A significant feature in the proposed framework of advice generation is user modeling. The advice generation is required to reason about the students' knowledge status and to decide appropriate advice. Actions, recorded by the application and transformed by the student modeler into student models, serve as the source from which diagnostic information about the student can be extracted. This information indicates which concepts were presented to the student, the duration of time the student spent working with learning objects related to a specific concept, which concepts probably mastered by the student and which concepts not yet mastered. The advice generation can identify the status of students and groups of students. This is used as a source for the generation of appropriate advice to the course instructor, who can then pass the advice to the students or consequently take some pedagogical actions that should be educationally appropriate. The advice generating mechanism based on a set of criteria for selecting appropriate advice according to the current student situation is explained in detail.
{"title":"Intelligent advice generator for personalized language learning through social networking sites","authors":"C. Troussas, K. Espinosa, M. Virvou","doi":"10.1109/IISA.2015.7388048","DOIUrl":"https://doi.org/10.1109/IISA.2015.7388048","url":null,"abstract":"Computer-based advising is focusing on factors that facilitate advice giving in educational systems. In this paper, an intelligent advice generation module is presented. As a testbed for our research, we have incorporated the advice generation mechanism in a Facebook application for language learning. A significant feature in the proposed framework of advice generation is user modeling. The advice generation is required to reason about the students' knowledge status and to decide appropriate advice. Actions, recorded by the application and transformed by the student modeler into student models, serve as the source from which diagnostic information about the student can be extracted. This information indicates which concepts were presented to the student, the duration of time the student spent working with learning objects related to a specific concept, which concepts probably mastered by the student and which concepts not yet mastered. The advice generation can identify the status of students and groups of students. This is used as a source for the generation of appropriate advice to the course instructor, who can then pass the advice to the students or consequently take some pedagogical actions that should be educationally appropriate. The advice generating mechanism based on a set of criteria for selecting appropriate advice according to the current student situation is explained in detail.","PeriodicalId":433872,"journal":{"name":"2015 6th International Conference on Information, Intelligence, Systems and Applications (IISA)","volume":"38 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":"126623014","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.2015.7388056
K. Kenda, Maja Skrjanc, A. Borstnik
The following contribution offers technical solution for heterogeneous multivariate data streaming modelling built on top of open-source QMiner platform. The presented infrastructure is able to receive data from different sources (sensors, weather, weather and other forecast, static properties, ...) with many different properties (frequency, update interval, ...), it is able to merge and resample this data and build models on top of it. Technology was used to prepare prediction models for 5 different energy related use cases which include public buildings, thermal plant production, university campus buildings, EPEX energy spot market prices and total traded energy. Average relative mean absolute error of the model predictions varies between 5-10%, and qualitative analysis of predictions shows significant correlation between predictions and true values.
{"title":"Modelling of the complex data space: Architecture and use cases from NRG4CAST project","authors":"K. Kenda, Maja Skrjanc, A. Borstnik","doi":"10.1109/IISA.2015.7388056","DOIUrl":"https://doi.org/10.1109/IISA.2015.7388056","url":null,"abstract":"The following contribution offers technical solution for heterogeneous multivariate data streaming modelling built on top of open-source QMiner platform. The presented infrastructure is able to receive data from different sources (sensors, weather, weather and other forecast, static properties, ...) with many different properties (frequency, update interval, ...), it is able to merge and resample this data and build models on top of it. Technology was used to prepare prediction models for 5 different energy related use cases which include public buildings, thermal plant production, university campus buildings, EPEX energy spot market prices and total traded energy. Average relative mean absolute error of the model predictions varies between 5-10%, and qualitative analysis of predictions shows significant correlation between predictions and true values.","PeriodicalId":433872,"journal":{"name":"2015 6th International Conference on Information, Intelligence, Systems and Applications (IISA)","volume":"110 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":"127010238","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.2015.7388123
A. Lipitakis, G. Antzoulatos, S. Kotsiantis, M. Vrahatis
Several data analysis problems require investigations of relationships between attributes in related heterogeneous databases, where different prediction models can be more appropriate for different regions. A new technique of integrating global and local boosting is proposed. A comparison with other well known and widely used combining methods on standard benchmark datasets has shown that the proposed technique leads to more accurate results.
{"title":"Integrating global and local boosting","authors":"A. Lipitakis, G. Antzoulatos, S. Kotsiantis, M. Vrahatis","doi":"10.1109/IISA.2015.7388123","DOIUrl":"https://doi.org/10.1109/IISA.2015.7388123","url":null,"abstract":"Several data analysis problems require investigations of relationships between attributes in related heterogeneous databases, where different prediction models can be more appropriate for different regions. A new technique of integrating global and local boosting is proposed. A comparison with other well known and widely used combining methods on standard benchmark datasets has shown that the proposed technique leads to more accurate results.","PeriodicalId":433872,"journal":{"name":"2015 6th International Conference on Information, Intelligence, Systems and Applications (IISA)","volume":"24 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":"126734556","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.2015.7388033
Konstantinos Marmarokopos, G. Efremidis, M. Avlonitis
In this paper we propose a specific framework in order to study landslide stability by means of a network of geophones where the analysis of the corresponding spatiotemporal data, in the light of the previously mentioned recent self-organized critical models, may serve as a valuable and robust tool towards the early prediction of landslides.
{"title":"Geophone networks and environmental studies: Application to landslides","authors":"Konstantinos Marmarokopos, G. Efremidis, M. Avlonitis","doi":"10.1109/IISA.2015.7388033","DOIUrl":"https://doi.org/10.1109/IISA.2015.7388033","url":null,"abstract":"In this paper we propose a specific framework in order to study landslide stability by means of a network of geophones where the analysis of the corresponding spatiotemporal data, in the light of the previously mentioned recent self-organized critical models, may serve as a valuable and robust tool towards the early prediction of landslides.","PeriodicalId":433872,"journal":{"name":"2015 6th International Conference on Information, Intelligence, Systems and Applications (IISA)","volume":"1 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":"123653940","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.2015.7388085
Minmin Lin, Fu-Yu Huang, T. Chiueh
Near Field Communication (NFC) is a technology for wireless short-range communication. The main attribute of NFC is proximity and that data transmission will take place only within a very small area. However, NFC-based applications are still not prevalent due to slow progress of NFC hardware penetration. In this paper, we present A-NFC, an NFC-like communication system, which operates on existing mobile phones. It is an inaudible acoustics-based system utilizing the microphones and speakers on mobile phones. In addition, A-NFC is purely software based and can run on different operating systems. A-NFC implements full-duplex two-way communication by designing two independent channels in the inaudible frequency band. To the best of our knowledge, A-NFC is the first acoustics communication system capable of inaudible and two-way communications on various popular platforms (Android and iOS included). Extensive experiments demonstrate that A-NFC can reliably provide NFC capability with a data rate up to 2.2 Kbps on various devices.
{"title":"A-NFC: Two-way near-field communications (NFC) via inaudible acoustics","authors":"Minmin Lin, Fu-Yu Huang, T. Chiueh","doi":"10.1109/IISA.2015.7388085","DOIUrl":"https://doi.org/10.1109/IISA.2015.7388085","url":null,"abstract":"Near Field Communication (NFC) is a technology for wireless short-range communication. The main attribute of NFC is proximity and that data transmission will take place only within a very small area. However, NFC-based applications are still not prevalent due to slow progress of NFC hardware penetration. In this paper, we present A-NFC, an NFC-like communication system, which operates on existing mobile phones. It is an inaudible acoustics-based system utilizing the microphones and speakers on mobile phones. In addition, A-NFC is purely software based and can run on different operating systems. A-NFC implements full-duplex two-way communication by designing two independent channels in the inaudible frequency band. To the best of our knowledge, A-NFC is the first acoustics communication system capable of inaudible and two-way communications on various popular platforms (Android and iOS included). Extensive experiments demonstrate that A-NFC can reliably provide NFC capability with a data rate up to 2.2 Kbps on various devices.","PeriodicalId":433872,"journal":{"name":"2015 6th International Conference on Information, Intelligence, Systems and Applications (IISA)","volume":"602 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":"123205488","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：