Pub Date : 2019-12-01DOI: 10.1109/CSCI49370.2019.00062
Fred Y. Wu, Shaofei Lu, Lopez-Aeamburo Armando, Jingke She
Objective: This paper has been prepared as an effort to reassess the research studies on the relevance of Longshort term memory (LSTM) in the correction and prediction of sensor data for temperature. Methods: This methods are a multiple input parameters model of LSTM and an input parameter model of LSTM, the first one corrects one of those parameter and the next one predict the remaining data of one parameter of sensor data after training history data. Findings: The training data reach 87,600 with 8 parameter, the error of first model reduce to 0.13% . The training data reach 11,682, the error between real data and predicted data is from 3.4% to 0.03% Application / Improvement: The methods will be used to correct the history data of sensors and determine which seed to plant and whether to irrigate. In future, we will integrate Markov chain with LSTM to improve the precision of LSTM and reduce the size of training data.
{"title":"Temperature Prediction Based on Long Short Term Memory Networks","authors":"Fred Y. Wu, Shaofei Lu, Lopez-Aeamburo Armando, Jingke She","doi":"10.1109/CSCI49370.2019.00062","DOIUrl":"https://doi.org/10.1109/CSCI49370.2019.00062","url":null,"abstract":"Objective: This paper has been prepared as an effort to reassess the research studies on the relevance of Longshort term memory (LSTM) in the correction and prediction of sensor data for temperature. Methods: This methods are a multiple input parameters model of LSTM and an input parameter model of LSTM, the first one corrects one of those parameter and the next one predict the remaining data of one parameter of sensor data after training history data. Findings: The training data reach 87,600 with 8 parameter, the error of first model reduce to 0.13% . The training data reach 11,682, the error between real data and predicted data is from 3.4% to 0.03% Application / Improvement: The methods will be used to correct the history data of sensors and determine which seed to plant and whether to irrigate. In future, we will integrate Markov chain with LSTM to improve the precision of LSTM and reduce the size of training data.","PeriodicalId":103662,"journal":{"name":"2019 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":" 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113949257","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 : 2019-12-01DOI: 10.1109/CSCI49370.2019.00202
Y. Aoi, H. Higaki
For support of interactive multimedia applications in wireless multihop networks, a sequence of data messages are required to be transmitted simultaneously in both directions. Here, intermediate wireless nodes hold temporarily data messages in both directions with high probability. Network coding methods have been proposed for reduction of forwarding and end-to-end transmission delays and for increase of end-to-end data message throughput. However, for collision-free transmissions, all the 2-hop neighbor intermediate nodes are required to be suspended during a data message transmission. Some extended Request To Send/Clear To Send (RTS/CTS) controls have been proposed for network coding support; however, for avoidance of collisions between control messages, longer transmission delay is inevitable. This paper proposes a novel RTS/CTS control method for supporting network coding in bidirectional data message transmission. Here, the CTS and ACK control messages are transmitted with the usual Short Inter Frame Space (SIFS) interval and their correct simultaneous transmissions are detected by their collisions. In simulation experiments, 30.2% higher end-to-end throughput of data messages is achieved by the proposed RTS/CTS control in comparison with conventional methods.
{"title":"Low-Overhead Network Coding Communication for Wireless Multihop Networks","authors":"Y. Aoi, H. Higaki","doi":"10.1109/CSCI49370.2019.00202","DOIUrl":"https://doi.org/10.1109/CSCI49370.2019.00202","url":null,"abstract":"For support of interactive multimedia applications in wireless multihop networks, a sequence of data messages are required to be transmitted simultaneously in both directions. Here, intermediate wireless nodes hold temporarily data messages in both directions with high probability. Network coding methods have been proposed for reduction of forwarding and end-to-end transmission delays and for increase of end-to-end data message throughput. However, for collision-free transmissions, all the 2-hop neighbor intermediate nodes are required to be suspended during a data message transmission. Some extended Request To Send/Clear To Send (RTS/CTS) controls have been proposed for network coding support; however, for avoidance of collisions between control messages, longer transmission delay is inevitable. This paper proposes a novel RTS/CTS control method for supporting network coding in bidirectional data message transmission. Here, the CTS and ACK control messages are transmitted with the usual Short Inter Frame Space (SIFS) interval and their correct simultaneous transmissions are detected by their collisions. In simulation experiments, 30.2% higher end-to-end throughput of data messages is achieved by the proposed RTS/CTS control in comparison with conventional methods.","PeriodicalId":103662,"journal":{"name":"2019 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124391344","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 : 2019-12-01DOI: 10.1109/CSCI49370.2019.00149
P. Jamieson, M. Herbordt, M. Kinsy
High Performance Computing (HPC) continues to develop and encroach on higher-education in the computing fields. With the ubiquitous availability and growth in commercial cloud computing and the diminishing performance returns on sequential programs, many developers must be able to understand and exploit parallel computing paradigms for certain applications. Focusing on Computer Engineering undergraduates, who arguably, will be future leaders in these parallel domains, the CE2016 recommended curriculum has a number of hours dedicated for parallel and distributed computing where approximately 10 core hours are to be taught in parallel programming, other ideas are taught in and among networking and embedded systems, and an entire section on digital design (50 hours). In reality, this is not enough time to become competent in the broader HPC field, nor do we expect standard undergraduate curriculum to develop competent undergraduate into parallel programmers. However, as demand increases for HPC developers, one wonders how students will attain this knowledge. Many people learn HPC competencies in graduate work and industrial work, but what might be done early. In this paper, we look at what a developer can possibly learn in the HPC world, and what tools and understanding is needed to build and experiment with parallel implementations. Our goal is to look at aspects of HPC given the constraints of a typical laptop, and we ask what can a developer test and learn about on their system in the HPC domain. The benefits of this work is a better understanding of what tool sets students will need to understand to develop simple parallel implementations, what HPC platforms can be used for courses or personalized learning, and we provide a basic framework and code samples for people to start from.
{"title":"A Case Study: Undergraduate Self-Learning in HPC Including OpenMP, MPI, OpenCL, and FPGAs","authors":"P. Jamieson, M. Herbordt, M. Kinsy","doi":"10.1109/CSCI49370.2019.00149","DOIUrl":"https://doi.org/10.1109/CSCI49370.2019.00149","url":null,"abstract":"High Performance Computing (HPC) continues to develop and encroach on higher-education in the computing fields. With the ubiquitous availability and growth in commercial cloud computing and the diminishing performance returns on sequential programs, many developers must be able to understand and exploit parallel computing paradigms for certain applications. Focusing on Computer Engineering undergraduates, who arguably, will be future leaders in these parallel domains, the CE2016 recommended curriculum has a number of hours dedicated for parallel and distributed computing where approximately 10 core hours are to be taught in parallel programming, other ideas are taught in and among networking and embedded systems, and an entire section on digital design (50 hours). In reality, this is not enough time to become competent in the broader HPC field, nor do we expect standard undergraduate curriculum to develop competent undergraduate into parallel programmers. However, as demand increases for HPC developers, one wonders how students will attain this knowledge. Many people learn HPC competencies in graduate work and industrial work, but what might be done early. In this paper, we look at what a developer can possibly learn in the HPC world, and what tools and understanding is needed to build and experiment with parallel implementations. Our goal is to look at aspects of HPC given the constraints of a typical laptop, and we ask what can a developer test and learn about on their system in the HPC domain. The benefits of this work is a better understanding of what tool sets students will need to understand to develop simple parallel implementations, what HPC platforms can be used for courses or personalized learning, and we provide a basic framework and code samples for people to start from.","PeriodicalId":103662,"journal":{"name":"2019 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124536552","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 : 2019-12-01DOI: 10.1109/CSCI49370.2019.00136
J. Jennings, F. Kamangar
We introduce a method for pose estimation from sensor array data utilizing an inverse graphics approach. We propose a general unsupervised method based on manipulating a 3D model to discover the joint-space parameters that produce an observed image or sensor reading. Using our novel architecture, we discuss the design of a model for performing human pose estimation on data obtained from a mattress pressure sensor.
{"title":"Unsupervised Pose Estimation via Inverse Graphics","authors":"J. Jennings, F. Kamangar","doi":"10.1109/CSCI49370.2019.00136","DOIUrl":"https://doi.org/10.1109/CSCI49370.2019.00136","url":null,"abstract":"We introduce a method for pose estimation from sensor array data utilizing an inverse graphics approach. We propose a general unsupervised method based on manipulating a 3D model to discover the joint-space parameters that produce an observed image or sensor reading. Using our novel architecture, we discuss the design of a model for performing human pose estimation on data obtained from a mattress pressure sensor.","PeriodicalId":103662,"journal":{"name":"2019 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"149 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124161603","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 : 2019-12-01DOI: 10.1109/CSCI49370.2019.00019
V. Mounika, Xiaohong Yuan, Kanishka Bandaru
This paper describes our study of the vulnerability reports in the Common Vulnerability and Exposures (CVE) database by using topic modeling on the description texts of the vulnerabilities. Prevalent vulnerability types were found, and new trends of vulnerabilities were discovered by studying the 121,716 unique CVE entries that are reported from January 1999 to July 2019. The topics found through topic modeling were mapped to OWASP Top 10 vulnerabilities. It was found that the OWASP vulnerabilities A2: 2017-Broken Authentication, A4:2017-XML External Entities (XXE), and A5:2017-Broken Access Control increased, yet the vulnerability A7:2017-Cross-Site Scripting (XSS) had a steep decrease over the period of 20 years.
{"title":"Analyzing CVE Database Using Unsupervised Topic Modelling","authors":"V. Mounika, Xiaohong Yuan, Kanishka Bandaru","doi":"10.1109/CSCI49370.2019.00019","DOIUrl":"https://doi.org/10.1109/CSCI49370.2019.00019","url":null,"abstract":"This paper describes our study of the vulnerability reports in the Common Vulnerability and Exposures (CVE) database by using topic modeling on the description texts of the vulnerabilities. Prevalent vulnerability types were found, and new trends of vulnerabilities were discovered by studying the 121,716 unique CVE entries that are reported from January 1999 to July 2019. The topics found through topic modeling were mapped to OWASP Top 10 vulnerabilities. It was found that the OWASP vulnerabilities A2: 2017-Broken Authentication, A4:2017-XML External Entities (XXE), and A5:2017-Broken Access Control increased, yet the vulnerability A7:2017-Cross-Site Scripting (XSS) had a steep decrease over the period of 20 years.","PeriodicalId":103662,"journal":{"name":"2019 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126218486","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 : 2019-12-01DOI: 10.1109/CSCI49370.2019.00012
B. Goodwin, Patryk Szewczyk
Authentication mechanisms are a core component in cyber-security and are becoming increasingly exposed as traditional networks extend into the cloud. The resulting systems become harder to define, harder to protect, and authentication mechanisms are left vulnerable to attacks. Compounding this is the human factor, where a poor understanding of responsibilities, reluctance to deal with conflict, and the inability to effect change, undermine what is often considered to be a technical problem. Whilst technical measures to effectively mitigate these risks are known, frequency of attacks continue to demonstrate success. Using six popular cyber-breach examples these non-technical challenges are identified and their effect is examined. This paper demonstrates that technical measures are key to authentication and overall cyber-security posture. These technical measures may be better understood than their non-technical counterparts that frequently lead to authentication failure and public downfall.
{"title":"Demystifying the Technical and Managerial Challenges of Authentication","authors":"B. Goodwin, Patryk Szewczyk","doi":"10.1109/CSCI49370.2019.00012","DOIUrl":"https://doi.org/10.1109/CSCI49370.2019.00012","url":null,"abstract":"Authentication mechanisms are a core component in cyber-security and are becoming increasingly exposed as traditional networks extend into the cloud. The resulting systems become harder to define, harder to protect, and authentication mechanisms are left vulnerable to attacks. Compounding this is the human factor, where a poor understanding of responsibilities, reluctance to deal with conflict, and the inability to effect change, undermine what is often considered to be a technical problem. Whilst technical measures to effectively mitigate these risks are known, frequency of attacks continue to demonstrate success. Using six popular cyber-breach examples these non-technical challenges are identified and their effect is examined. This paper demonstrates that technical measures are key to authentication and overall cyber-security posture. These technical measures may be better understood than their non-technical counterparts that frequently lead to authentication failure and public downfall.","PeriodicalId":103662,"journal":{"name":"2019 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126524013","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 : 2019-12-01DOI: 10.1109/CSCI49370.2019.00146
Andrew Corsi, E. Romero, Mira Yun, L. Deligiannidis
Colleges of the Fenway (CoF) is a joint effort of five neighboring Boston-based colleges in the Fenway area. Cross registration enables students of the CoF to register for courses offered in the other institutions. However, current search functions of the crossregistration system lack key features, such as searching by number of credits, categories of classes, or searching by a specific school. In order to offer these features, we propose a new user-friendly website named CrossConnect. CrossConnect uses the Bootstrap framework and responsive Ajax library to connect and query the course databases across all CoF institutions. CrossConnect allows students to perform enhanced queries and provides a user-friendly search interface.
{"title":"CrossConnect: A Cross Registration Tool","authors":"Andrew Corsi, E. Romero, Mira Yun, L. Deligiannidis","doi":"10.1109/CSCI49370.2019.00146","DOIUrl":"https://doi.org/10.1109/CSCI49370.2019.00146","url":null,"abstract":"Colleges of the Fenway (CoF) is a joint effort of five neighboring Boston-based colleges in the Fenway area. Cross registration enables students of the CoF to register for courses offered in the other institutions. However, current search functions of the crossregistration system lack key features, such as searching by number of credits, categories of classes, or searching by a specific school. In order to offer these features, we propose a new user-friendly website named CrossConnect. CrossConnect uses the Bootstrap framework and responsive Ajax library to connect and query the course databases across all CoF institutions. CrossConnect allows students to perform enhanced queries and provides a user-friendly search interface.","PeriodicalId":103662,"journal":{"name":"2019 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125487505","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 : 2019-12-01DOI: 10.1109/CSCI49370.2019.00187
Linda Askenäs, Jaime Campos, Jan Aidemark
This paper presents a framework for the development of flexible eHealth solutions based on a platform logic and a set of processes for cooperative development. The framework consists of both a specification detailing the activities of the development process and a technical platform integrating sensors, IoT integration data management and end-user interfaces as well as business and user processes.
{"title":"Challenges for a Flexible eHealth Future: Framework and Platform for Continuous Development","authors":"Linda Askenäs, Jaime Campos, Jan Aidemark","doi":"10.1109/CSCI49370.2019.00187","DOIUrl":"https://doi.org/10.1109/CSCI49370.2019.00187","url":null,"abstract":"This paper presents a framework for the development of flexible eHealth solutions based on a platform logic and a set of processes for cooperative development. The framework consists of both a specification detailing the activities of the development process and a technical platform integrating sensors, IoT integration data management and end-user interfaces as well as business and user processes.","PeriodicalId":103662,"journal":{"name":"2019 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127929318","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 : 2019-12-01DOI: 10.1109/CSCI49370.2019.00057
N. Loukeris, George Chalamandaris, I. Eleftheriadis
We investigate the optimal performance of Self Organized Feature Maps in 60 different models of plain and hybrid form to define the optimal classifier. We also apply it on a novel model of optimal portfolio selection in hedging aspects.
{"title":"Self Organized Features Maps SOFM and Hybrid Neuro-Genetic SOFMs in Optimal Portfolio Management","authors":"N. Loukeris, George Chalamandaris, I. Eleftheriadis","doi":"10.1109/CSCI49370.2019.00057","DOIUrl":"https://doi.org/10.1109/CSCI49370.2019.00057","url":null,"abstract":"We investigate the optimal performance of Self Organized Feature Maps in 60 different models of plain and hybrid form to define the optimal classifier. We also apply it on a novel model of optimal portfolio selection in hedging aspects.","PeriodicalId":103662,"journal":{"name":"2019 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131960880","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 : 2019-12-01DOI: 10.1109/CSCI49370.2019.00201
J. S. Silva, R. Saldanha, Vasco Pereira, Duarte M. G. Raposo, F. Boavida, A. Rodrigues, M. Abreu
One of the biggest problems in the current society is people's safety. Safety measures and mechanisms are especially important in the case of vulnerable social groups, such as migrants, homeless, and victims of domestic and/or sexual violence. In order to cope with this problem, we witness an increasing number of personal alarm systems in the market, most of them based on panic buttons. Nevertheless, none of them has got widespread acceptance mainly because of limited Human-Computer Interaction. In the context of this work, we developed an innovative mobile application that recognizes an attack through speech and gesture recognition. This paper describes such a system and presents its features, some of them based on the emerging concept of Human-in-the-Loop Cyber-physical Systems and new concepts of Human-Computer Interaction.
{"title":"WeDoCare: A System for Vulnerable Social Groups","authors":"J. S. Silva, R. Saldanha, Vasco Pereira, Duarte M. G. Raposo, F. Boavida, A. Rodrigues, M. Abreu","doi":"10.1109/CSCI49370.2019.00201","DOIUrl":"https://doi.org/10.1109/CSCI49370.2019.00201","url":null,"abstract":"One of the biggest problems in the current society is people's safety. Safety measures and mechanisms are especially important in the case of vulnerable social groups, such as migrants, homeless, and victims of domestic and/or sexual violence. In order to cope with this problem, we witness an increasing number of personal alarm systems in the market, most of them based on panic buttons. Nevertheless, none of them has got widespread acceptance mainly because of limited Human-Computer Interaction. In the context of this work, we developed an innovative mobile application that recognizes an attack through speech and gesture recognition. This paper describes such a system and presents its features, some of them based on the emerging concept of Human-in-the-Loop Cyber-physical Systems and new concepts of Human-Computer Interaction.","PeriodicalId":103662,"journal":{"name":"2019 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134539238","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：