Pub Date : 2018-09-01DOI: 10.23919/IConAC.2018.8749126
Lichen Zhang, Dandan Lai, Bingqing Xu, Chunyao Liu
Cyber-physical system (CPS) emphasizes dynamic collaboration of physical process and computation process. Its high demands for real-time, safety, security, and reliability require deep integration of control, computation and communication. To achieve better performance and resource utilization in CPS, we propose a framework named cloud based cyber-physical system (CCPS) which strengthens cooperation among various layers in CPS.CCPS adopts closed-loop control, and makes use of cloud service for data processing in cyber-physical cloud (CPC). In order to balance real-time performance and cost of cloud service, network scheduling algorithms in various cloud models are widely discussed in this paper. In addition, we have a broad discussion on effection of tasks scheduling with respect to stability of controller in CCPS in view of time delay. Accordingly, we give simulation and comparison results of the proposed scheduling algorithms for illustration.
{"title":"Scheduling Algorithms for Cloud Based Cyber-Physical Systems Specification","authors":"Lichen Zhang, Dandan Lai, Bingqing Xu, Chunyao Liu","doi":"10.23919/IConAC.2018.8749126","DOIUrl":"https://doi.org/10.23919/IConAC.2018.8749126","url":null,"abstract":"Cyber-physical system (CPS) emphasizes dynamic collaboration of physical process and computation process. Its high demands for real-time, safety, security, and reliability require deep integration of control, computation and communication. To achieve better performance and resource utilization in CPS, we propose a framework named cloud based cyber-physical system (CCPS) which strengthens cooperation among various layers in CPS.CCPS adopts closed-loop control, and makes use of cloud service for data processing in cyber-physical cloud (CPC). In order to balance real-time performance and cost of cloud service, network scheduling algorithms in various cloud models are widely discussed in this paper. In addition, we have a broad discussion on effection of tasks scheduling with respect to stability of controller in CCPS in view of time delay. Accordingly, we give simulation and comparison results of the proposed scheduling algorithms for illustration.","PeriodicalId":121030,"journal":{"name":"2018 24th International Conference on Automation and Computing (ICAC)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115065659","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 : 2018-09-01DOI: 10.23919/IConAC.2018.8749095
Z. Mo, Jianhong Ma
Embedding texts into vector spaces is a common and fundamental preprocessing. Despite there are several approaches to put documents into vectors, reducing the dimension and improving ability of expression can still be a problem when facing large scale data and sophisticated demand. Distributed dense vector have been shown to be powerful in capturing token level semantics. In this paper, we propose a new method to embed entire documents into vector space using a deep neural network which described as DocNet in this paper. With DocNet, we trained end-to-end learning the vector space and by that we take all the information including semantics into account. Once this space has been produced, tasks such as classification and clustering can be simply done using standard techniques. Our method introduces triplet loss to train. The benefit is vector space can be learned directly so we can control the final dimension of embedding vectors. To demonstrate performance of our method, we built a clustering system compared with several baseline methods. Experiments prove that our approach achieves state-of-art document clustering performance. Furthermore, it proves that complicated clustering or classification demands can be satisfied by our method.
{"title":"DocNet: A document embedding approach based on neural networks","authors":"Z. Mo, Jianhong Ma","doi":"10.23919/IConAC.2018.8749095","DOIUrl":"https://doi.org/10.23919/IConAC.2018.8749095","url":null,"abstract":"Embedding texts into vector spaces is a common and fundamental preprocessing. Despite there are several approaches to put documents into vectors, reducing the dimension and improving ability of expression can still be a problem when facing large scale data and sophisticated demand. Distributed dense vector have been shown to be powerful in capturing token level semantics. In this paper, we propose a new method to embed entire documents into vector space using a deep neural network which described as DocNet in this paper. With DocNet, we trained end-to-end learning the vector space and by that we take all the information including semantics into account. Once this space has been produced, tasks such as classification and clustering can be simply done using standard techniques. Our method introduces triplet loss to train. The benefit is vector space can be learned directly so we can control the final dimension of embedding vectors. To demonstrate performance of our method, we built a clustering system compared with several baseline methods. Experiments prove that our approach achieves state-of-art document clustering performance. Furthermore, it proves that complicated clustering or classification demands can be satisfied by our method.","PeriodicalId":121030,"journal":{"name":"2018 24th International Conference on Automation and Computing (ICAC)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115119982","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 : 2018-09-01DOI: 10.23919/iconac.2018.8749026
{"title":"Organising Institutions","authors":"","doi":"10.23919/iconac.2018.8749026","DOIUrl":"https://doi.org/10.23919/iconac.2018.8749026","url":null,"abstract":"","PeriodicalId":121030,"journal":{"name":"2018 24th International Conference on Automation and Computing (ICAC)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124738480","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 : 2018-09-01DOI: 10.23919/iconac.2018.8749097
{"title":"ICAC'18 2018 24th IEEE International Conference on Automation and Computing","authors":"","doi":"10.23919/iconac.2018.8749097","DOIUrl":"https://doi.org/10.23919/iconac.2018.8749097","url":null,"abstract":"","PeriodicalId":121030,"journal":{"name":"2018 24th International Conference on Automation and Computing (ICAC)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123184887","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 : 2018-09-01DOI: 10.23919/IConAC.2018.8749074
Mahmoud S. Issa, A. Onsy, M. Hamad, A. El-Zonkoly
Driverless Pods can be classified as Electric Vehicles (EVs) which possibly represent environmentally friendly transportations. However, the battery technology is the real restriction in accomplishing this concept due to its drawbacks, for example, high cost, scarce components, weak specific energy and physical contact with charging device requirements. Besides the pursuit of materials and energy density development, wireless power transfer (WPT) technology which is another technique to charge the batteries of the EVs with no physical contact has been introduced. In this paper, an overview of WPT technologies for EVs charging has been presented including classification, compensation topologies, transformer structures and different charging control techniques. Then, A MATLAB Simulink model is used to simulate the load identification method in order to validate this technique which seeks to achieve a constant voltage charging through load identification depending only on the primary-side controller.
{"title":"Design of Wireless Power Charging System for Driverless Pod Application","authors":"Mahmoud S. Issa, A. Onsy, M. Hamad, A. El-Zonkoly","doi":"10.23919/IConAC.2018.8749074","DOIUrl":"https://doi.org/10.23919/IConAC.2018.8749074","url":null,"abstract":"Driverless Pods can be classified as Electric Vehicles (EVs) which possibly represent environmentally friendly transportations. However, the battery technology is the real restriction in accomplishing this concept due to its drawbacks, for example, high cost, scarce components, weak specific energy and physical contact with charging device requirements. Besides the pursuit of materials and energy density development, wireless power transfer (WPT) technology which is another technique to charge the batteries of the EVs with no physical contact has been introduced. In this paper, an overview of WPT technologies for EVs charging has been presented including classification, compensation topologies, transformer structures and different charging control techniques. Then, A MATLAB Simulink model is used to simulate the load identification method in order to validate this technique which seeks to achieve a constant voltage charging through load identification depending only on the primary-side controller.","PeriodicalId":121030,"journal":{"name":"2018 24th International Conference on Automation and Computing (ICAC)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125527507","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 : 2018-09-01DOI: 10.23919/IConAC.2018.8749021
Wajeeha Hamid, M. A. Shah
Open Source Mano is an open source ETSI (European Telecommunications Standards Institute) aligned orchestrator which is responsible for the management of NFV architecture. Monitoring module in OSM (Open Source Management and Orchestration) allows the user to monitor the resources configured in the underlying VIMs. This research is based on adding support of AWS cloud as a VIM in the monitoring module by implementing an AWS plugin. It involves the basic CRUD (create, read, update and delete) operations for the monitoring of VM level resources. Thus, improving the scalability, interoperability and automation.
开源Mano是一个开源的ETSI(欧洲电信标准协会)协调器，负责NFV架构的管理。OSM (Open Source Management and Orchestration)中的监控模块允许用户监控底层虚拟化环境中配置的资源。本研究是通过实现一个AWS插件，在监控模块中增加对AWS云作为VIM的支持。它涉及用于监视VM级资源的基本CRUD(创建、读取、更新和删除)操作。从而提高了可伸缩性、互操作性和自动化。
{"title":"AWS Support in Open Source Mano Monitoring Module","authors":"Wajeeha Hamid, M. A. Shah","doi":"10.23919/IConAC.2018.8749021","DOIUrl":"https://doi.org/10.23919/IConAC.2018.8749021","url":null,"abstract":"Open Source Mano is an open source ETSI (European Telecommunications Standards Institute) aligned orchestrator which is responsible for the management of NFV architecture. Monitoring module in OSM (Open Source Management and Orchestration) allows the user to monitor the resources configured in the underlying VIMs. This research is based on adding support of AWS cloud as a VIM in the monitoring module by implementing an AWS plugin. It involves the basic CRUD (create, read, update and delete) operations for the monitoring of VM level resources. Thus, improving the scalability, interoperability and automation.","PeriodicalId":121030,"journal":{"name":"2018 24th International Conference on Automation and Computing (ICAC)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127696065","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 : 2018-09-01DOI: 10.23919/IConAC.2018.8748947
Shuopeng Wang, Peng Yang, Hao Sun, Mai Liu
The fingerprint-based sound source localization (SSL) approach usually requires tremendous time and efforts for location fingerprints collection in sampling phase and reference points (RPs) matching in positioning phase. In this paper, we propose an iterative interpolation method based on cluster analysis to reduce such calibration efforts and matching computation works. Unlike conventional interpolation methods, the novel method can make further efforts in refining the interpolation scope and monitoring the interpolation process to reduce the required virtual RPs. The proposed method significantly outperforms the conventional interpolation methods in efficiency on the premise of achieving the same or similar accuracy.
{"title":"Fingerprint-based Sound Source Localization Using Iterative Interpolation Method","authors":"Shuopeng Wang, Peng Yang, Hao Sun, Mai Liu","doi":"10.23919/IConAC.2018.8748947","DOIUrl":"https://doi.org/10.23919/IConAC.2018.8748947","url":null,"abstract":"The fingerprint-based sound source localization (SSL) approach usually requires tremendous time and efforts for location fingerprints collection in sampling phase and reference points (RPs) matching in positioning phase. In this paper, we propose an iterative interpolation method based on cluster analysis to reduce such calibration efforts and matching computation works. Unlike conventional interpolation methods, the novel method can make further efforts in refining the interpolation scope and monitoring the interpolation process to reduce the required virtual RPs. The proposed method significantly outperforms the conventional interpolation methods in efficiency on the premise of achieving the same or similar accuracy.","PeriodicalId":121030,"journal":{"name":"2018 24th International Conference on Automation and Computing (ICAC)","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122408818","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 : 2018-09-01DOI: 10.23919/IConAC.2018.8749062
F. Malik, M. A. Shah, Hasan Ali Khattak
An intelligent transport system (ITS) is a vital part of smart cities in order to manage smooth traffic on highways. An active framework is required to manage a smooth traffic on the roads. An excessive growth in urban population is a big challenge for smart cities. Unorganized traffic shows current reality of cities. The current road infrastructure cannot cope with the increased number of vehicles on the roads. This problem can be tackled through the use of Information and the communication technologies (ICT). ITS will reduce delays, traffic congestions, energy consumption and the pollution emission caused by the long delays on roads. This paper presents a framework for intelligent traffic system that will reduce the waiting time for vehicles on the signal. The performance and the scalability of the proposed framework was evaluated through experiments. The results exhibit a significant amount of reduction in waiting time for vehicles on the signal. This will help in controlling the traffic problems efficiently and eventually reducing the number of casualties caused by road accidents.
{"title":"Intelligent Transport System: An Important Aspect of Emergency Management in Smart Cities","authors":"F. Malik, M. A. Shah, Hasan Ali Khattak","doi":"10.23919/IConAC.2018.8749062","DOIUrl":"https://doi.org/10.23919/IConAC.2018.8749062","url":null,"abstract":"An intelligent transport system (ITS) is a vital part of smart cities in order to manage smooth traffic on highways. An active framework is required to manage a smooth traffic on the roads. An excessive growth in urban population is a big challenge for smart cities. Unorganized traffic shows current reality of cities. The current road infrastructure cannot cope with the increased number of vehicles on the roads. This problem can be tackled through the use of Information and the communication technologies (ICT). ITS will reduce delays, traffic congestions, energy consumption and the pollution emission caused by the long delays on roads. This paper presents a framework for intelligent traffic system that will reduce the waiting time for vehicles on the signal. The performance and the scalability of the proposed framework was evaluated through experiments. The results exhibit a significant amount of reduction in waiting time for vehicles on the signal. This will help in controlling the traffic problems efficiently and eventually reducing the number of casualties caused by road accidents.","PeriodicalId":121030,"journal":{"name":"2018 24th International Conference on Automation and Computing (ICAC)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122936370","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 : 2018-09-01DOI: 10.23919/IConAC.2018.8749079
M. Ali, M. A. Shah
Wireless Sensor Networks (WSNs) are usually comprised of a large number of sensor nodes which have limited power resources and require energy efficient routing algorithms. We have presented an Adaptive Transmission Power - Geographical and Energy Aware Routing (ATP-GEAR) algorithm in this paper, which routes the packet towards the destination by calculating the cost of the neighbors of a node in terms of their location and current battery level and transmitting the packet to the lowest costing node with the minimum required transmission power. We analyze the performance of our algorithm based on total power consumption and end-to-end delay from source to destination. Simulation results show that ATP-GEAR yields almost 25% less power consumption and 17% less end-to-end delay when compared with traditional Cluster Based Routing (CBR).
{"title":"Adaptive Transmission Power - Geographical and Energy Aware Routing Algorithm for Wireless Sensor Networks","authors":"M. Ali, M. A. Shah","doi":"10.23919/IConAC.2018.8749079","DOIUrl":"https://doi.org/10.23919/IConAC.2018.8749079","url":null,"abstract":"Wireless Sensor Networks (WSNs) are usually comprised of a large number of sensor nodes which have limited power resources and require energy efficient routing algorithms. We have presented an Adaptive Transmission Power - Geographical and Energy Aware Routing (ATP-GEAR) algorithm in this paper, which routes the packet towards the destination by calculating the cost of the neighbors of a node in terms of their location and current battery level and transmitting the packet to the lowest costing node with the minimum required transmission power. We analyze the performance of our algorithm based on total power consumption and end-to-end delay from source to destination. Simulation results show that ATP-GEAR yields almost 25% less power consumption and 17% less end-to-end delay when compared with traditional Cluster Based Routing (CBR).","PeriodicalId":121030,"journal":{"name":"2018 24th International Conference on Automation and Computing (ICAC)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124151837","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 : 2018-09-01DOI: 10.23919/IConAC.2018.8749069
Kai Zhou, Fei Long
In order to overcome the deficiency of sentiment analysis based on traditional machine learning, which difficulty of effective feature selection and inadequacy of marked training corpus will affect the performance of the classification system, we address the sentiment emotions analysis problem of Chinese product reviews text by combining convolutional neural network (CNN) with bidirectional long-short term memory network (BiLSTM) in this paper. The CNN can extract the sequence features from the global information, and it is able to consider the relationship among these features. The BiLSTM not only solves the long-term dependency problem, but also considers the context of the text at the same time. The result of numerical experiments shows that the proposed model achieves better metrics performance than the state-of-the-art methods.
{"title":"Sentiment Analysis of Text Based on CNN and Bi-directional LSTM Model","authors":"Kai Zhou, Fei Long","doi":"10.23919/IConAC.2018.8749069","DOIUrl":"https://doi.org/10.23919/IConAC.2018.8749069","url":null,"abstract":"In order to overcome the deficiency of sentiment analysis based on traditional machine learning, which difficulty of effective feature selection and inadequacy of marked training corpus will affect the performance of the classification system, we address the sentiment emotions analysis problem of Chinese product reviews text by combining convolutional neural network (CNN) with bidirectional long-short term memory network (BiLSTM) in this paper. The CNN can extract the sequence features from the global information, and it is able to consider the relationship among these features. The BiLSTM not only solves the long-term dependency problem, but also considers the context of the text at the same time. The result of numerical experiments shows that the proposed model achieves better metrics performance than the state-of-the-art methods.","PeriodicalId":121030,"journal":{"name":"2018 24th International Conference on Automation and Computing (ICAC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127230280","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：