Using mobile devices to enhance users interaction with CPS has many potential benefits for healthcare applications. Recent research has looked at how to recognize human activities using smartphones, to indicate health status. But little attention has been paid to automatically identify the activity habits of individuals in real-time. Of course, the energy constraint in smartphones must be considered during the design of such cyber-physical recognition systems. In this paper, we propose a prediction-based smart sensing strategy that is energy efficient and works in real-time. By making use of the temporal correlation property of real-world phenomena, an adaptive k-order Markov chain based prediction algorithm is proposed to avoid continuous sensing so that significant energy savings can be achieved. The prediction results are analyzed online in real-time, to ensure that the system can track an individual's behavior pattern and provide timely response to changes in behavior. Real-world experiments using our prototype show that such recognition oriented CPS systems can not only achieve energy savings, but also converge to steady state with high individual recognition accuracy, in a real-time manner.
{"title":"SmartSen: smart sensing for enhancing real-time activity recognition in phone-based interactive CPS","authors":"Huan Li, Qinghua Yu, K. Ramamritham, Xiaotao Liu","doi":"10.1145/3019612.3019648","DOIUrl":"https://doi.org/10.1145/3019612.3019648","url":null,"abstract":"Using mobile devices to enhance users interaction with CPS has many potential benefits for healthcare applications. Recent research has looked at how to recognize human activities using smartphones, to indicate health status. But little attention has been paid to automatically identify the activity habits of individuals in real-time. Of course, the energy constraint in smartphones must be considered during the design of such cyber-physical recognition systems. In this paper, we propose a prediction-based smart sensing strategy that is energy efficient and works in real-time. By making use of the temporal correlation property of real-world phenomena, an adaptive k-order Markov chain based prediction algorithm is proposed to avoid continuous sensing so that significant energy savings can be achieved. The prediction results are analyzed online in real-time, to ensure that the system can track an individual's behavior pattern and provide timely response to changes in behavior. Real-world experiments using our prototype show that such recognition oriented CPS systems can not only achieve energy savings, but also converge to steady state with high individual recognition accuracy, in a real-time manner.","PeriodicalId":20728,"journal":{"name":"Proceedings of the Symposium on Applied Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82846963","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}
Gamification is an emerging phenomenon for using in educational software in order to engage, motivate and improve the performance of students inside the learning context. However, despite its importance, the identification of significant gamification requirements for educational software is not trivial and a consensus of such requirements has not been reached. Motivated by this situation, the objective of this paper is to present a gamification requirements catalog for educational software. The requirements were identified from a systematic literature review, subsequently prioritized and validated through a survey conducted with 64 experts in the field. The results suggest that the requirements of the catalog are important to be applied in educational software.
{"title":"A gamification requirements catalog for educational software: results from a systematic literature review and a survey with experts","authors":"M. Peixoto, Carla Schuenemann","doi":"10.1145/3019612.3019752","DOIUrl":"https://doi.org/10.1145/3019612.3019752","url":null,"abstract":"Gamification is an emerging phenomenon for using in educational software in order to engage, motivate and improve the performance of students inside the learning context. However, despite its importance, the identification of significant gamification requirements for educational software is not trivial and a consensus of such requirements has not been reached. Motivated by this situation, the objective of this paper is to present a gamification requirements catalog for educational software. The requirements were identified from a systematic literature review, subsequently prioritized and validated through a survey conducted with 64 experts in the field. The results suggest that the requirements of the catalog are important to be applied in educational software.","PeriodicalId":20728,"journal":{"name":"Proceedings of the Symposium on Applied Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80958681","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}
Geunseok Yang, Seungsuk Baek, Jung-Won Lee, Byungjeong Lee
A successful software development project becomes an essential part of a software company's reputation. Thus, lots of project managers focus more on maintenance than on other management processes. Previous works studied how to help the maintenance process by detecting bug duplication and predicting the severity of bugs. This paper continues that kind of special work by analyzing emotion words for bug-severity prediction. In detail, we construct an emotion words-based dictionary for verifying bug reports' textual emotion analyses based on positive and negative terms. Then, we modify a machine learning algorithm, the Naïve Bayes multinomial, calling the new algorithm EWD-Multinomial. We compare this EWD-Multinomial study with our baselines, including Naïve Bayes multinomial and a Lamkanfi study, for open source projects such as Eclipse, Android, and JBoss. The result shows this study's algorithm outperforms the others.
{"title":"Analyzing emotion words to predict severity of software bugs: a case study of open source projects","authors":"Geunseok Yang, Seungsuk Baek, Jung-Won Lee, Byungjeong Lee","doi":"10.1145/3019612.3019788","DOIUrl":"https://doi.org/10.1145/3019612.3019788","url":null,"abstract":"A successful software development project becomes an essential part of a software company's reputation. Thus, lots of project managers focus more on maintenance than on other management processes. Previous works studied how to help the maintenance process by detecting bug duplication and predicting the severity of bugs. This paper continues that kind of special work by analyzing emotion words for bug-severity prediction. In detail, we construct an emotion words-based dictionary for verifying bug reports' textual emotion analyses based on positive and negative terms. Then, we modify a machine learning algorithm, the Naïve Bayes multinomial, calling the new algorithm EWD-Multinomial. We compare this EWD-Multinomial study with our baselines, including Naïve Bayes multinomial and a Lamkanfi study, for open source projects such as Eclipse, Android, and JBoss. The result shows this study's algorithm outperforms the others.","PeriodicalId":20728,"journal":{"name":"Proceedings of the Symposium on Applied Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89471731","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}
Riding on the success of previous Mobile Computing and Applications Tracks spanning from 2003 to 2016, we are delighted to celebrate the 15th anniversary of the Mobile Computing and Applications Track this year with a truly inter-continental track chair composition with further PC diversity. The track features research papers drawn from a highly diversified spectrum of mobile computing, with a collection of papers relevant to the up-surging security measures. We have been receiving a good number of submissions throughout the years. According to the nature of the papers collected in this track, the accepted regular papers are organized into two sessions, covering very much on the security issues as well as system and application aspects: Security in Mobile Systems and Mobile Platforms and Applications. The track is dedicated to draw upon research efforts and expertise from different areas of research, so as to promote better synergy and to bring forth not only core communications and security protocols for application development and data management, but also important and upcoming research applications to realize the benefits of anywhere, any place and anytime pervasive and ubiquitous computing.
{"title":"Session details: MCA - mobile computing and applications track","authors":"","doi":"10.1145/3243952","DOIUrl":"https://doi.org/10.1145/3243952","url":null,"abstract":"Riding on the success of previous Mobile Computing and Applications Tracks spanning from 2003 to 2016, we are delighted to celebrate the 15th anniversary of the Mobile Computing and Applications Track this year with a truly inter-continental track chair composition with further PC diversity. The track features research papers drawn from a highly diversified spectrum of mobile computing, with a collection of papers relevant to the up-surging security measures. We have been receiving a good number of submissions throughout the years. According to the nature of the papers collected in this track, the accepted regular papers are organized into two sessions, covering very much on the security issues as well as system and application aspects: Security in Mobile Systems and Mobile Platforms and Applications. The track is dedicated to draw upon research efforts and expertise from different areas of research, so as to promote better synergy and to bring forth not only core communications and security protocols for application development and data management, but also important and upcoming research applications to realize the benefits of anywhere, any place and anytime pervasive and ubiquitous computing.","PeriodicalId":20728,"journal":{"name":"Proceedings of the Symposium on Applied Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80352770","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}
Feature selection and feature ranking are two aspects of the same learning task. They are well studied in batch scenarios, but not in the streaming setting. This paper presents a study on feature ranking from data streams in online learning regression models. The main challenge here is the relevance of features might change over time: features relevant in the past might be irrelevant now and vice-versa. We propose three new online feature ranking algorithms designed for Hoeffding algorithms. We have implemented the three methods in AMRules, a streaming regression algorithm to learn model rules. We compare their behaviour experimentally and present the pros and cons of each method.
{"title":"Feature ranking in hoeffding algorithms for regression","authors":"J. Duarte, João Gama","doi":"10.1145/3019612.3019670","DOIUrl":"https://doi.org/10.1145/3019612.3019670","url":null,"abstract":"Feature selection and feature ranking are two aspects of the same learning task. They are well studied in batch scenarios, but not in the streaming setting. This paper presents a study on feature ranking from data streams in online learning regression models. The main challenge here is the relevance of features might change over time: features relevant in the past might be irrelevant now and vice-versa. We propose three new online feature ranking algorithms designed for Hoeffding algorithms. We have implemented the three methods in AMRules, a streaming regression algorithm to learn model rules. We compare their behaviour experimentally and present the pros and cons of each method.","PeriodicalId":20728,"journal":{"name":"Proceedings of the Symposium on Applied Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81882728","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}
Marcelo Pitanga Alves, Flávia Coimbra Delicato, Paulo F. Pires
This paper presents IoTA-MD, a model-driven approach to instantiate the IoT-A Reference Architecture and manage QoS attributes in the early stages of IoT system modeling. It uses the principle of Separation of Concerns (SoC) to address complexity issues of the IoT system development considering both vertical and horizontal perspectives. The horizontal SoC is addressed by handling quality attributes separately from the Domain and Information models. The vertical SoC is addressed by using MDA to design the system models with the appropriate abstraction level, and its transformation artifacts to refine such models from an abstraction level to other. Moreover, the IoTA-MD provides a modeling tool to facilitate the design/maintenance of the IoT-A models at the CIM and PIM levels.
{"title":"IoTA-MD: a model-driven approach for applying QoS attributes in the development of the IoT systems","authors":"Marcelo Pitanga Alves, Flávia Coimbra Delicato, Paulo F. Pires","doi":"10.1145/3019612.3019800","DOIUrl":"https://doi.org/10.1145/3019612.3019800","url":null,"abstract":"This paper presents IoTA-MD, a model-driven approach to instantiate the IoT-A Reference Architecture and manage QoS attributes in the early stages of IoT system modeling. It uses the principle of Separation of Concerns (SoC) to address complexity issues of the IoT system development considering both vertical and horizontal perspectives. The horizontal SoC is addressed by handling quality attributes separately from the Domain and Information models. The vertical SoC is addressed by using MDA to design the system models with the appropriate abstraction level, and its transformation artifacts to refine such models from an abstraction level to other. Moreover, the IoTA-MD provides a modeling tool to facilitate the design/maintenance of the IoT-A models at the CIM and PIM levels.","PeriodicalId":20728,"journal":{"name":"Proceedings of the Symposium on Applied Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82018388","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 special track on Intelligent Robotics and Multi-Agent Systems (IRMAS) focuses on all aspects of intelligent robotics and multi-agent systems (MAS) including related areas and applications. Its primary goal is to exploit synergies between robotics and artificial intelligence (AI), more precisely between intelligent robotics and MAS, and bring together researchers from both fields. For many years, robotics and AI researchers have worked separately, both fields have matured enormously, and today there is a growing interest in getting the two research fields together. Many in robotics believe that the focus in the near future should be adding capabilities to robots that lie at the core of AI research. Reciprocally, AI researchers aim at embedding their techniques in physical robots that can perceive, reason and act in real, dynamic environments.
{"title":"Session details: IRMAS - intelligent robotics and multi-agent systems track","authors":"","doi":"10.1145/3243947","DOIUrl":"https://doi.org/10.1145/3243947","url":null,"abstract":"The special track on Intelligent Robotics and Multi-Agent Systems (IRMAS) focuses on all aspects of intelligent robotics and multi-agent systems (MAS) including related areas and applications. Its primary goal is to exploit synergies between robotics and artificial intelligence (AI), more precisely between intelligent robotics and MAS, and bring together researchers from both fields. For many years, robotics and AI researchers have worked separately, both fields have matured enormously, and today there is a growing interest in getting the two research fields together. Many in robotics believe that the focus in the near future should be adding capabilities to robots that lie at the core of AI research. Reciprocally, AI researchers aim at embedding their techniques in physical robots that can perceive, reason and act in real, dynamic environments.","PeriodicalId":20728,"journal":{"name":"Proceedings of the Symposium on Applied Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78179260","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}
Michael Rovatsos, Dimitrios I. Diochnos, Z. Wen, S. Ceppi, Pavlos Andreadis
Web-based collaborative systems, where most computation is performed by human collectives, have distinctly different requirements from traditional workflow orchestration systems, as humans have to be mobilised to perform computations and the system has to adapt to their collective behaviour at runtime. In this paper, we present a social orchestration system called SmartOrch, which has been designed specifically for collective adaptive systems in which human participation is at the core of the overall distributed computation. SmartOrch provides a flexible and customisable workflow composition framework that has multi-level optimisation capabilities. These features allow us to manage the uncertainty that collective adaptive systems need to deal with in a principled way. We demonstrate the benefits of SmartOrch with simulation experiments in a ridesharing domain. Our experiments show that SmartOrch is able to respond flexibly to variation in collective human behaviour, and to adapt to observed behaviour at different levels. This is accomplished by learning how to propose and route human-based tasks, how to allocate computational resources when managing these tasks, and how to adapt the overall interaction model of the platform based on past performance. By proposing novel, solid engineering principles for these kinds of systems, SmartOrch addresses shortcomings of previous work that mostly focused on application-specific, non-adaptive solutions.
{"title":"SmartOrch: an adaptive orchestration system for human-machine collectives","authors":"Michael Rovatsos, Dimitrios I. Diochnos, Z. Wen, S. Ceppi, Pavlos Andreadis","doi":"10.1145/3019612.3019623","DOIUrl":"https://doi.org/10.1145/3019612.3019623","url":null,"abstract":"Web-based collaborative systems, where most computation is performed by human collectives, have distinctly different requirements from traditional workflow orchestration systems, as humans have to be mobilised to perform computations and the system has to adapt to their collective behaviour at runtime. In this paper, we present a social orchestration system called SmartOrch, which has been designed specifically for collective adaptive systems in which human participation is at the core of the overall distributed computation. SmartOrch provides a flexible and customisable workflow composition framework that has multi-level optimisation capabilities. These features allow us to manage the uncertainty that collective adaptive systems need to deal with in a principled way. We demonstrate the benefits of SmartOrch with simulation experiments in a ridesharing domain. Our experiments show that SmartOrch is able to respond flexibly to variation in collective human behaviour, and to adapt to observed behaviour at different levels. This is accomplished by learning how to propose and route human-based tasks, how to allocate computational resources when managing these tasks, and how to adapt the overall interaction model of the platform based on past performance. By proposing novel, solid engineering principles for these kinds of systems, SmartOrch addresses shortcomings of previous work that mostly focused on application-specific, non-adaptive solutions.","PeriodicalId":20728,"journal":{"name":"Proceedings of the Symposium on Applied Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78854023","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}
M. Danelutto, T. D. Matteis, D. D. Sensi, G. Mencagli, M. Torquati
High-level parallel programming is a de-facto standard approach to develop parallel software with reduced time to development. High-level abstractions are provided by existing frameworks as pragma-based annotations in the source code, or through pre-built parallel patterns that recur frequently in parallel algorithms, and that can be easily instantiated by the programmer to add a structure to the development of parallel software. In this paper we focus on this second approach and we propose P3ARSEC, a benchmark suite for parallel pattern-based frameworks consisting of a representative subset of PARSEC applications. We analyse the programmability advantages and the potential performance penalty of using such high-level methodology with respect to hand-made parallelisations using low-level mechanisms. The results are obtained on the new Intel Knights Landing multicore, and show a significantly reduced code complexity with comparable performance.
{"title":"P3ARSEC: towards parallel patterns benchmarking","authors":"M. Danelutto, T. D. Matteis, D. D. Sensi, G. Mencagli, M. Torquati","doi":"10.1145/3019612.3019745","DOIUrl":"https://doi.org/10.1145/3019612.3019745","url":null,"abstract":"High-level parallel programming is a de-facto standard approach to develop parallel software with reduced time to development. High-level abstractions are provided by existing frameworks as pragma-based annotations in the source code, or through pre-built parallel patterns that recur frequently in parallel algorithms, and that can be easily instantiated by the programmer to add a structure to the development of parallel software. In this paper we focus on this second approach and we propose P3ARSEC, a benchmark suite for parallel pattern-based frameworks consisting of a representative subset of PARSEC applications. We analyse the programmability advantages and the potential performance penalty of using such high-level methodology with respect to hand-made parallelisations using low-level mechanisms. The results are obtained on the new Intel Knights Landing multicore, and show a significantly reduced code complexity with comparable performance.","PeriodicalId":20728,"journal":{"name":"Proceedings of the Symposium on Applied Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76118270","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}
Programmable matter can be seen as a huge modular robot in which each module can communicate to its connected neighbors and work all together to achieve a common goal, more likely changing the shape of the whole robot. However, when the number of modules increases, the memory used in each module to store the target shape or the computation time to recreate this shape increases too. This article studies different approaches to describe the shape of any object for huge modular robots. The use of a good method for coding scene is a critical aspect that can reduce the memory, the time of transfer and the energy used in many distributed algorithms like self-reconfiguration. This paper proposes a method called Constructive Solid Geometry for Programmable Matter (CSG4PM), a compact description of an object and all the associated algorithms pre-processing and runtime. CSG4PM is compared to three existing solutions to describe a scene.
{"title":"Efficient scene encoding for programmable matter self-reconfiguration algorithms","authors":"Thadeu Tucci, Benoît Piranda, J. Bourgeois","doi":"10.1145/3019612.3019706","DOIUrl":"https://doi.org/10.1145/3019612.3019706","url":null,"abstract":"Programmable matter can be seen as a huge modular robot in which each module can communicate to its connected neighbors and work all together to achieve a common goal, more likely changing the shape of the whole robot. However, when the number of modules increases, the memory used in each module to store the target shape or the computation time to recreate this shape increases too. This article studies different approaches to describe the shape of any object for huge modular robots. The use of a good method for coding scene is a critical aspect that can reduce the memory, the time of transfer and the energy used in many distributed algorithms like self-reconfiguration. This paper proposes a method called Constructive Solid Geometry for Programmable Matter (CSG4PM), a compact description of an object and all the associated algorithms pre-processing and runtime. CSG4PM is compared to three existing solutions to describe a scene.","PeriodicalId":20728,"journal":{"name":"Proceedings of the Symposium on Applied Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76550574","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：