Pub Date : 2018-12-01DOI: 10.1109/ICSENG.2018.8638206
M. Z. Baig, M. Kavakli
Learning and usability of a 3D modelling system depend on direct and indirect human-dependent factors. These factors need to be studied in order to design a state-of-the-art computer tool or software. In this paper, we have presented a novice/expert analysis of a 3D modelling system in which user used two different sets of inputs i.e. keyboard/mouse and speech/gesture to draw the 3D object in AutoCAD. To analyse the user’s cognitive workload, we have used electroencephalography (EEG) signals and extracted various frequency bands and power spectral density (PSD) estimates. EEG signals and questionnaires were used to understand the user’s behaviour. The results showed that users find i t d ifficult to dr aw a 3D object using the multi-modal input speech/gesture compared to keyboard/mouse. A significant change in theta and alpha bands activity was observed during the analysis. We found that novice users were relatively comfortable in using multi-modal interface system then the expert users which indicates that novice users can learn to use the multi-modal input more quickly then the expert users.
{"title":"Analyzing Novice and Expert User’s Cognitive Load in using a Multi-Modal Interface System","authors":"M. Z. Baig, M. Kavakli","doi":"10.1109/ICSENG.2018.8638206","DOIUrl":"https://doi.org/10.1109/ICSENG.2018.8638206","url":null,"abstract":"Learning and usability of a 3D modelling system depend on direct and indirect human-dependent factors. These factors need to be studied in order to design a state-of-the-art computer tool or software. In this paper, we have presented a novice/expert analysis of a 3D modelling system in which user used two different sets of inputs i.e. keyboard/mouse and speech/gesture to draw the 3D object in AutoCAD. To analyse the user’s cognitive workload, we have used electroencephalography (EEG) signals and extracted various frequency bands and power spectral density (PSD) estimates. EEG signals and questionnaires were used to understand the user’s behaviour. The results showed that users find i t d ifficult to dr aw a 3D object using the multi-modal input speech/gesture compared to keyboard/mouse. A significant change in theta and alpha bands activity was observed during the analysis. We found that novice users were relatively comfortable in using multi-modal interface system then the expert users which indicates that novice users can learn to use the multi-modal input more quickly then the expert users.","PeriodicalId":356324,"journal":{"name":"2018 26th International Conference on Systems Engineering (ICSEng)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124992943","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 : 2018-12-01DOI: 10.1109/ICSENG.2018.8638240
Yongjian Zhu, Guangwen Qi
Image stitching is an important technology in machine vision inspection whose algorithms focus on the detection and match of feature points. For the solar panel images achieved by machine vision, it’s found that the available image stitching algorithms failed to detect enough valid feature points, which led to a large number of incorrect matching points. Here, we improve an algorithm to locate feature points and find dense match points. The proposed algorithm is based on SIFT. The improved algorithm (I-SIFT) can locate the position of feature points in every solar panel images, reducing the effect of invalid feature points on the experiment. Euclidean distance is used to preliminarily ensure the matching points, and then the relative horizontal position of every matching points is used to eliminate the mismatching points caused by the space similarity of the feature points, so that the matching accuracy is improved. Then the improved algorithm is used in the traditional Harris, SIFT and SURF stitching algorithm. The experimental results show that the success rate of I-SIFT algorithm can exceed 95% and the computation time has decreased by nearly 95% than that of the traditional algorithm. In conclusion, the improved algorithm implements accurately and rapidly stitching for solar panel images.
{"title":"Studies on Image Stitching Algorithms in Machine Vision Inspection of Solar Panel","authors":"Yongjian Zhu, Guangwen Qi","doi":"10.1109/ICSENG.2018.8638240","DOIUrl":"https://doi.org/10.1109/ICSENG.2018.8638240","url":null,"abstract":"Image stitching is an important technology in machine vision inspection whose algorithms focus on the detection and match of feature points. For the solar panel images achieved by machine vision, it’s found that the available image stitching algorithms failed to detect enough valid feature points, which led to a large number of incorrect matching points. Here, we improve an algorithm to locate feature points and find dense match points. The proposed algorithm is based on SIFT. The improved algorithm (I-SIFT) can locate the position of feature points in every solar panel images, reducing the effect of invalid feature points on the experiment. Euclidean distance is used to preliminarily ensure the matching points, and then the relative horizontal position of every matching points is used to eliminate the mismatching points caused by the space similarity of the feature points, so that the matching accuracy is improved. Then the improved algorithm is used in the traditional Harris, SIFT and SURF stitching algorithm. The experimental results show that the success rate of I-SIFT algorithm can exceed 95% and the computation time has decreased by nearly 95% than that of the traditional algorithm. In conclusion, the improved algorithm implements accurately and rapidly stitching for solar panel images.","PeriodicalId":356324,"journal":{"name":"2018 26th International Conference on Systems Engineering (ICSEng)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125110400","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 : 2018-12-01DOI: 10.1109/ICSENG.2018.8638199
T. Górski, Ewa Wojtach
The paper explores aspect of exposing data for public usage from technical point of view. The main aim of this paper is to consider and propose the way of exposing read-only APIs, where state management is minor or no issue, but in the same case, domain complexity can reach high levels. In the paper, the authors propose complete approach to the process of API exposing, from use-case definition and description, to usage of proposed architectural design pattern for read-only API exposure. The paper encompasses the following aspects which were taken into account in proposed design pattern: API usability, developer experience, unit and integration testing, architecture constraints. Moreover, the authors summarize the paper and outline directions for further work.
{"title":"Use Case API - design pattern for shared data","authors":"T. Górski, Ewa Wojtach","doi":"10.1109/ICSENG.2018.8638199","DOIUrl":"https://doi.org/10.1109/ICSENG.2018.8638199","url":null,"abstract":"The paper explores aspect of exposing data for public usage from technical point of view. The main aim of this paper is to consider and propose the way of exposing read-only APIs, where state management is minor or no issue, but in the same case, domain complexity can reach high levels. In the paper, the authors propose complete approach to the process of API exposing, from use-case definition and description, to usage of proposed architectural design pattern for read-only API exposure. The paper encompasses the following aspects which were taken into account in proposed design pattern: API usability, developer experience, unit and integration testing, architecture constraints. Moreover, the authors summarize the paper and outline directions for further work.","PeriodicalId":356324,"journal":{"name":"2018 26th International Conference on Systems Engineering (ICSEng)","volume":"3 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132227860","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 : 2018-12-01DOI: 10.1109/ICSENG.2018.8638019
Zhanwei Wu, Xilin Ji, Ying Wang, Xingyu Chen, Yibin Cai
Considering the energy-saving routing problem in data center network which employed SDN paradigm, a novel energy-aware routing approach was proposed. The approach added constraint of control traffic in traditional energy-saving routing problem statement. In addition, we proposed a heuristic algorithm using dynamic weight to compute the energy-aware routing path. At last, the approach is assessed by simulation experiments under realistic topologies and demands.
{"title":"An Energy-aware Routing for Optimizing Control and Data Traffic in SDN","authors":"Zhanwei Wu, Xilin Ji, Ying Wang, Xingyu Chen, Yibin Cai","doi":"10.1109/ICSENG.2018.8638019","DOIUrl":"https://doi.org/10.1109/ICSENG.2018.8638019","url":null,"abstract":"Considering the energy-saving routing problem in data center network which employed SDN paradigm, a novel energy-aware routing approach was proposed. The approach added constraint of control traffic in traditional energy-saving routing problem statement. In addition, we proposed a heuristic algorithm using dynamic weight to compute the energy-aware routing path. At last, the approach is assessed by simulation experiments under realistic topologies and demands.","PeriodicalId":356324,"journal":{"name":"2018 26th International Conference on Systems Engineering (ICSEng)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123589544","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 : 2018-12-01DOI: 10.1109/ICSENG.2018.8638230
Z. Wawrzyniak, S. Jankowski, Eliza Szczechla, Z. Szymanski, R. Pytlak, P. Michalak, G. Borowik
Prediction of future events over time is associated with a sequence of time series observational samples and other exogenous data. Different approaches connected with statistical learning techniques result in predictive databased models. The paper presents an attempt to develop techniques for predictive data-based modeling based on machine learning data-driven approaches. To reach a good level of prediction we use a deep learning architecture based on artificial neural network (ANN). The neural network (NN) structure for crime prediction and the appropriate inputs for crime prediction is performed through: Gram-Schmidt orthogonalization (GS) for the selection of network inputs and virtual leave-one-out test (VLOO) for the selection of the optimal number of hidden neurons. Spatiotemporal distribution of the hot-spots is conducted and a methodology is developed for short-term crime forecasting using the long short-term memory (LSTM) recurrent neural networks (RNN) and convolutional neural networks (CNN).
{"title":"Data-driven models in machine learning for crime prediction","authors":"Z. Wawrzyniak, S. Jankowski, Eliza Szczechla, Z. Szymanski, R. Pytlak, P. Michalak, G. Borowik","doi":"10.1109/ICSENG.2018.8638230","DOIUrl":"https://doi.org/10.1109/ICSENG.2018.8638230","url":null,"abstract":"Prediction of future events over time is associated with a sequence of time series observational samples and other exogenous data. Different approaches connected with statistical learning techniques result in predictive databased models. The paper presents an attempt to develop techniques for predictive data-based modeling based on machine learning data-driven approaches. To reach a good level of prediction we use a deep learning architecture based on artificial neural network (ANN). The neural network (NN) structure for crime prediction and the appropriate inputs for crime prediction is performed through: Gram-Schmidt orthogonalization (GS) for the selection of network inputs and virtual leave-one-out test (VLOO) for the selection of the optimal number of hidden neurons. Spatiotemporal distribution of the hot-spots is conducted and a methodology is developed for short-term crime forecasting using the long short-term memory (LSTM) recurrent neural networks (RNN) and convolutional neural networks (CNN).","PeriodicalId":356324,"journal":{"name":"2018 26th International Conference on Systems Engineering (ICSEng)","volume":"146 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124683637","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 : 2018-12-01DOI: 10.1109/ICSENG.2018.8638170
Zi-li Li, Lu Tang
The non-contact measurement technology based on surface wave radar has a wide application prospect in river hydrology measurement. In this paper, the UHF is used to measure the water body of a specific river section. Based on the data received by remote sensing, the echo spectrum is effectively analyzed. And then, the velocity of surface flow information contained in the data is calculated by using the theory of surface velocity extraction. Finally, by comparing with the actual data, the rationality and effectiveness of the results are proved.
{"title":"A Study on the Detection of River speedBased on UHF Radar Data","authors":"Zi-li Li, Lu Tang","doi":"10.1109/ICSENG.2018.8638170","DOIUrl":"https://doi.org/10.1109/ICSENG.2018.8638170","url":null,"abstract":"The non-contact measurement technology based on surface wave radar has a wide application prospect in river hydrology measurement. In this paper, the UHF is used to measure the water body of a specific river section. Based on the data received by remote sensing, the echo spectrum is effectively analyzed. And then, the velocity of surface flow information contained in the data is calculated by using the theory of surface velocity extraction. Finally, by comparing with the actual data, the rationality and effectiveness of the results are proved.","PeriodicalId":356324,"journal":{"name":"2018 26th International Conference on Systems Engineering (ICSEng)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131506306","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 : 2018-12-01DOI: 10.1109/ICSENG.2018.8638168
Xiang Li, Du Qu Wei
In this paper, the synchronization between two chaotic permanent magnet synchronous motor (PMSM) is considered. Firstly, a general and simple controller is presented to realize the synchronization of chaotic PMSM according to sliding mode control method and Lyapunov stability theory. And then, numerical simulation results are used to proof the alidity and reliability of the control method derived in this paper. This study may help to solve the coordination problem of motors in industry manufacture.
{"title":"Synchronization of chaotic permanent magnet synchronous motor system via sliding mode control","authors":"Xiang Li, Du Qu Wei","doi":"10.1109/ICSENG.2018.8638168","DOIUrl":"https://doi.org/10.1109/ICSENG.2018.8638168","url":null,"abstract":"In this paper, the synchronization between two chaotic permanent magnet synchronous motor (PMSM) is considered. Firstly, a general and simple controller is presented to realize the synchronization of chaotic PMSM according to sliding mode control method and Lyapunov stability theory. And then, numerical simulation results are used to proof the alidity and reliability of the control method derived in this paper. This study may help to solve the coordination problem of motors in industry manufacture.","PeriodicalId":356324,"journal":{"name":"2018 26th International Conference on Systems Engineering (ICSEng)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120965350","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 : 2018-12-01DOI: 10.1109/icseng.2018.8638215
{"title":"ICSEng 2018 TOC","authors":"","doi":"10.1109/icseng.2018.8638215","DOIUrl":"https://doi.org/10.1109/icseng.2018.8638215","url":null,"abstract":"","PeriodicalId":356324,"journal":{"name":"2018 26th International Conference on Systems Engineering (ICSEng)","volume":"221 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133765920","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 : 2018-12-01DOI: 10.1109/ICSENG.2018.8638180
Qiaosong Chen, Wen Li, Xiaomin Meng, Lexin Li, Ling Zheng, Jin Wang, Xin Deng
Aiming at existing problems about Supervised Descent Method (SDM), such as inaccurate facial feature extraction and the poor final alignment effect resulted by local optimum, an improved SDM (ISDM) based face align- ment algorithm is proposed. Firstly, an improved multi-scale Histograms of Gradient (IMHOG) feature extraction method based on multi-layers is raised, which expresses more refined facial features and makes faces be recognized more easily. Meanwhile, the social spider optimization (SSO) is applied to op- timize the estimated shape in iteration globally, which can avoid the local opti- mal. And it makes the estimated shape closer to the real shape so that the final alignment effect is more precise. Experiments have shown that the proposed al- gorithm can get better results than previous algorithms in LFPW, AFLW and 300-W datasets.
{"title":"An Improved Supervised Descent Method based Face Alignment Algorithm","authors":"Qiaosong Chen, Wen Li, Xiaomin Meng, Lexin Li, Ling Zheng, Jin Wang, Xin Deng","doi":"10.1109/ICSENG.2018.8638180","DOIUrl":"https://doi.org/10.1109/ICSENG.2018.8638180","url":null,"abstract":"Aiming at existing problems about Supervised Descent Method (SDM), such as inaccurate facial feature extraction and the poor final alignment effect resulted by local optimum, an improved SDM (ISDM) based face align- ment algorithm is proposed. Firstly, an improved multi-scale Histograms of Gradient (IMHOG) feature extraction method based on multi-layers is raised, which expresses more refined facial features and makes faces be recognized more easily. Meanwhile, the social spider optimization (SSO) is applied to op- timize the estimated shape in iteration globally, which can avoid the local opti- mal. And it makes the estimated shape closer to the real shape so that the final alignment effect is more precise. Experiments have shown that the proposed al- gorithm can get better results than previous algorithms in LFPW, AFLW and 300-W datasets.","PeriodicalId":356324,"journal":{"name":"2018 26th International Conference on Systems Engineering (ICSEng)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130617943","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 : 2018-12-01DOI: 10.1109/ICSENG.2018.8638218
Muhong Wang, Du Qu Wei
The adaptive synchronization problem of chaotic Brushless DC motors with uncertain system parameters via controller and update law is investigated by using Lyapunov stability theory. The adaptive control are firstly proposed, and then by using numerical simulations we proofed the validity and reliability of the control method. Our study can solve the synchronization and the motors coordination problem in manufacturing industry.
{"title":"Adaptive Synchronization of Chaotic Brushless DC Motors with Uncertain System Parameters Based on Lyapunov Stability theory","authors":"Muhong Wang, Du Qu Wei","doi":"10.1109/ICSENG.2018.8638218","DOIUrl":"https://doi.org/10.1109/ICSENG.2018.8638218","url":null,"abstract":"The adaptive synchronization problem of chaotic Brushless DC motors with uncertain system parameters via controller and update law is investigated by using Lyapunov stability theory. The adaptive control are firstly proposed, and then by using numerical simulations we proofed the validity and reliability of the control method. Our study can solve the synchronization and the motors coordination problem in manufacturing industry.","PeriodicalId":356324,"journal":{"name":"2018 26th International Conference on Systems Engineering (ICSEng)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127835318","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：