Pub Date : 2017-11-01DOI: 10.1109/ICSAI.2017.8248480
Guanghua Chen, Qiang Zhang, Meiqian Chen, H. Yin
Log Diameter Classes 3D measurement with binocular stereo vision system was adopted. According to the log-end histogram feature, a region labeling method was proposed based on the maximum entropy threshold segmentation. Adopting the region labeling based on pixel labeled method of connecting area, each log could be precisely identified and counted by the system. Extraction of log edge using a Canny operator, completed stereo matching based on the epipolar line rectification, then obtained the matching 3D coordinate points. According to the quasi-circular of the log ends, selected the appropriate initial value to fit the elliptic boundary value. The smallest Euclidean distance between the boundary points and fitting points was calculated by using least squares principle, thus the best fitting ellipse and log diameter class parameters of major axis and minor axis were gotten. Experiment shows that the proposed algorithms can accurately and rapidly detect the log diameter classes.
{"title":"Rapid detection algorithms for log diameter classes based on stereo vision","authors":"Guanghua Chen, Qiang Zhang, Meiqian Chen, H. Yin","doi":"10.1109/ICSAI.2017.8248480","DOIUrl":"https://doi.org/10.1109/ICSAI.2017.8248480","url":null,"abstract":"Log Diameter Classes 3D measurement with binocular stereo vision system was adopted. According to the log-end histogram feature, a region labeling method was proposed based on the maximum entropy threshold segmentation. Adopting the region labeling based on pixel labeled method of connecting area, each log could be precisely identified and counted by the system. Extraction of log edge using a Canny operator, completed stereo matching based on the epipolar line rectification, then obtained the matching 3D coordinate points. According to the quasi-circular of the log ends, selected the appropriate initial value to fit the elliptic boundary value. The smallest Euclidean distance between the boundary points and fitting points was calculated by using least squares principle, thus the best fitting ellipse and log diameter class parameters of major axis and minor axis were gotten. Experiment shows that the proposed algorithms can accurately and rapidly detect the log diameter classes.","PeriodicalId":285726,"journal":{"name":"2017 4th International Conference on Systems and Informatics (ICSAI)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123333941","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 : 2017-11-01DOI: 10.1109/ICSAI.2017.8248507
Weimin Ouyang
Discovery of interesting effectiveness itemsets has been a hot topics in data mining and knowledge discovery. Most previous researches related to effectiveness mining in literature employ a individual minimal threshold of effectiveness to decide on if an item is a interesting effectiveness item. Nevertheless, a individual minimal threshold of effectiveness could not express the varied natures of diverse items. In this paper, the author put forward a algorithm to discover interesting effectiveness itemsets with several minimal thresholds using average constraint. The reports of tests demonstrated that our algorithm is better than other baseline algorithms in performance.
{"title":"Discovery of interesting effectiveness itemsets with several minimal thresholds using average constraint","authors":"Weimin Ouyang","doi":"10.1109/ICSAI.2017.8248507","DOIUrl":"https://doi.org/10.1109/ICSAI.2017.8248507","url":null,"abstract":"Discovery of interesting effectiveness itemsets has been a hot topics in data mining and knowledge discovery. Most previous researches related to effectiveness mining in literature employ a individual minimal threshold of effectiveness to decide on if an item is a interesting effectiveness item. Nevertheless, a individual minimal threshold of effectiveness could not express the varied natures of diverse items. In this paper, the author put forward a algorithm to discover interesting effectiveness itemsets with several minimal thresholds using average constraint. The reports of tests demonstrated that our algorithm is better than other baseline algorithms in performance.","PeriodicalId":285726,"journal":{"name":"2017 4th International Conference on Systems and Informatics (ICSAI)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123473588","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 : 2017-11-01DOI: 10.1109/ICSAI.2017.8248499
Minjun Wang, Zhihui Wang, Jinlin Li
This paper proposes a method combining local binary patterns (LBP) and deep convolution neural network. This paper extracts LBP features of face image as an input of CNN, and train the CNN network with the LBP features, then use the trained network for face recognition, so that we can get rid of disadvantages of poor stability of CNN gray scale and identify the trained CNN network more effectively. This algorithm has been experimented on several common face libraries, Indicating that its performance than the traditional methods and general deep learning methods have improved.
{"title":"Deep convolutional neural network applies to face recognition in small and medium databases","authors":"Minjun Wang, Zhihui Wang, Jinlin Li","doi":"10.1109/ICSAI.2017.8248499","DOIUrl":"https://doi.org/10.1109/ICSAI.2017.8248499","url":null,"abstract":"This paper proposes a method combining local binary patterns (LBP) and deep convolution neural network. This paper extracts LBP features of face image as an input of CNN, and train the CNN network with the LBP features, then use the trained network for face recognition, so that we can get rid of disadvantages of poor stability of CNN gray scale and identify the trained CNN network more effectively. This algorithm has been experimented on several common face libraries, Indicating that its performance than the traditional methods and general deep learning methods have improved.","PeriodicalId":285726,"journal":{"name":"2017 4th International Conference on Systems and Informatics (ICSAI)","volume":"140 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123635200","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 : 2017-11-01DOI: 10.1109/ICSAI.2017.8248432
M. R. Silva, P. Machado, L. E. Souza, Carlos Waldecir de Souza
This paper presents a methodology to analyze the performance of a switched IEC 61850-9-2 network using the formalism of Colored Petri Nets (CPN). In order to decrease the complexity of the network analysis, it is assumed a model with distinct hierarchical levels, and this model allows describing the function and interaction of each element in an easy way. After the modeling process, the proposed methodology is validated by an implementation of an IEC 61850 scenario where the transfer of Sampled Value messages is put in a critical condition. As the simulations show, this methodology allows the evaluation of message latency and capacity limits using just modeling based on discrete events.
{"title":"Colored Petri Net modeling of communication systems based on IEC 61850","authors":"M. R. Silva, P. Machado, L. E. Souza, Carlos Waldecir de Souza","doi":"10.1109/ICSAI.2017.8248432","DOIUrl":"https://doi.org/10.1109/ICSAI.2017.8248432","url":null,"abstract":"This paper presents a methodology to analyze the performance of a switched IEC 61850-9-2 network using the formalism of Colored Petri Nets (CPN). In order to decrease the complexity of the network analysis, it is assumed a model with distinct hierarchical levels, and this model allows describing the function and interaction of each element in an easy way. After the modeling process, the proposed methodology is validated by an implementation of an IEC 61850 scenario where the transfer of Sampled Value messages is put in a critical condition. As the simulations show, this methodology allows the evaluation of message latency and capacity limits using just modeling based on discrete events.","PeriodicalId":285726,"journal":{"name":"2017 4th International Conference on Systems and Informatics (ICSAI)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121852676","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 : 2017-11-01DOI: 10.1109/ICSAI.2017.8248553
Yanjun Chen, Shitong Mao, Wenyan Jia, Mingui Sun
To help the cerebropathy patients and old people to count pills they have taken, a weighing capacitive sensor system is designed. Polydimethylsiloxane (PDMS) material is utilized to make springs between capacitive sensor plates. To convert the capacitance signal to the voltage signal, a circuit for small capacitance measurement is devised. Experiments show that the number of the pills from 0 to 100 can be measured by the proposed capacitive sensor accurately.
{"title":"A pills counting system based on the capacitive sensor","authors":"Yanjun Chen, Shitong Mao, Wenyan Jia, Mingui Sun","doi":"10.1109/ICSAI.2017.8248553","DOIUrl":"https://doi.org/10.1109/ICSAI.2017.8248553","url":null,"abstract":"To help the cerebropathy patients and old people to count pills they have taken, a weighing capacitive sensor system is designed. Polydimethylsiloxane (PDMS) material is utilized to make springs between capacitive sensor plates. To convert the capacitance signal to the voltage signal, a circuit for small capacitance measurement is devised. Experiments show that the number of the pills from 0 to 100 can be measured by the proposed capacitive sensor accurately.","PeriodicalId":285726,"journal":{"name":"2017 4th International Conference on Systems and Informatics (ICSAI)","volume":"236 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121574632","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 : 2017-11-01DOI: 10.1109/ICSAI.2017.8248437
Qinggang Su, Jingao Liu
With the rapid development of computer network application, it is increasingly important to detect abnormal behaviors and patterns in the field of network security. In this paper, a genetic algorithm is proposed to detect the network anomaly by using Management Information Base (MIB), which is based on the theory of classification using integrated IF-THEN rules. This paper presents a new chromosome coding scheme, and a new method of sufficiency function design is discussed too. Some experiments based on a big data set from real network environment were designed and tested, the results show that this algorithm is efficient in network anomaly detection.
随着计算机网络应用的迅速发展，异常行为和模式的检测在网络安全领域显得越来越重要。本文基于综合IF-THEN规则分类理论，提出了一种利用管理信息库(Management Information Base, MIB)检测网络异常的遗传算法。本文提出了一种新的染色体编码方案，并讨论了一种新的充分性函数设计方法。在实际网络环境的大数据集上进行了实验设计和测试，结果表明该算法在网络异常检测中是有效的。
{"title":"A network anomaly detection method based on genetic algorithm","authors":"Qinggang Su, Jingao Liu","doi":"10.1109/ICSAI.2017.8248437","DOIUrl":"https://doi.org/10.1109/ICSAI.2017.8248437","url":null,"abstract":"With the rapid development of computer network application, it is increasingly important to detect abnormal behaviors and patterns in the field of network security. In this paper, a genetic algorithm is proposed to detect the network anomaly by using Management Information Base (MIB), which is based on the theory of classification using integrated IF-THEN rules. This paper presents a new chromosome coding scheme, and a new method of sufficiency function design is discussed too. Some experiments based on a big data set from real network environment were designed and tested, the results show that this algorithm is efficient in network anomaly detection.","PeriodicalId":285726,"journal":{"name":"2017 4th International Conference on Systems and Informatics (ICSAI)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125188690","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 : 2017-11-01DOI: 10.1109/ICSAI.2017.8248495
Y. Long, Gangyao Kuang
This paper proposes a synthetic aperture radar (SAR) imaging method based on compressed sensing for ground moving target identification (GMTI). Since the targets are sparse or compressible in the area of interest, it is sufficient to reconstruct the image by only sampling a small number of receiving data randomly. Then, the moving targets can be obtained after the processing of displaced phase center antenna (DPCA) with different channels, which means that the limitations of strict balance between channels for GMTI can be relaxed. The minimum detectable velocity of moving objects can be reduced to a very small degree while the resolutions in both range and cross-range directions are maintained. Simulation results are presented in the paper to demonstrate the validity of the proposed method.
{"title":"A compressed sensing based method for SAR GMTI","authors":"Y. Long, Gangyao Kuang","doi":"10.1109/ICSAI.2017.8248495","DOIUrl":"https://doi.org/10.1109/ICSAI.2017.8248495","url":null,"abstract":"This paper proposes a synthetic aperture radar (SAR) imaging method based on compressed sensing for ground moving target identification (GMTI). Since the targets are sparse or compressible in the area of interest, it is sufficient to reconstruct the image by only sampling a small number of receiving data randomly. Then, the moving targets can be obtained after the processing of displaced phase center antenna (DPCA) with different channels, which means that the limitations of strict balance between channels for GMTI can be relaxed. The minimum detectable velocity of moving objects can be reduced to a very small degree while the resolutions in both range and cross-range directions are maintained. Simulation results are presented in the paper to demonstrate the validity of the proposed method.","PeriodicalId":285726,"journal":{"name":"2017 4th International Conference on Systems and Informatics (ICSAI)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125404546","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 : 2017-11-01DOI: 10.1109/ICSAI.2017.8248446
Gang Liu, Haobin Chen, Ruchao Fan
Traditional frequency warping algorithms in speech recognition mainly consider the spectrum offset caused by different vocal tract length. But in addition to the vocal tract length, the pronunciation diversity is also affected by the glottis difference. At the same time, the difference mentioned above is also interconnected. Although piecewise linear frequency warping considers the effect of the glottis and vocal tract, it will lose some information because it is not continuous and it only considers the effect of single factor. This paper proposes a two factor frequency warping algorithm based on the weighted fusion of the glottis resonant factor and the third formant factor. Compared with piecewise linear frequency warping, the method of spectrum aligned in this algorithm is smoother and takes the relationship between the glottis and vocal tract into account. Experimental results show that the recognition rate of the proposed algorithm is improved in the case of training data and testing data both matching and mismatching.
{"title":"Frequency warping based on two factor weighted fusion","authors":"Gang Liu, Haobin Chen, Ruchao Fan","doi":"10.1109/ICSAI.2017.8248446","DOIUrl":"https://doi.org/10.1109/ICSAI.2017.8248446","url":null,"abstract":"Traditional frequency warping algorithms in speech recognition mainly consider the spectrum offset caused by different vocal tract length. But in addition to the vocal tract length, the pronunciation diversity is also affected by the glottis difference. At the same time, the difference mentioned above is also interconnected. Although piecewise linear frequency warping considers the effect of the glottis and vocal tract, it will lose some information because it is not continuous and it only considers the effect of single factor. This paper proposes a two factor frequency warping algorithm based on the weighted fusion of the glottis resonant factor and the third formant factor. Compared with piecewise linear frequency warping, the method of spectrum aligned in this algorithm is smoother and takes the relationship between the glottis and vocal tract into account. Experimental results show that the recognition rate of the proposed algorithm is improved in the case of training data and testing data both matching and mismatching.","PeriodicalId":285726,"journal":{"name":"2017 4th International Conference on Systems and Informatics (ICSAI)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125561415","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 : 2017-11-01DOI: 10.1109/ICSAI.2017.8248354
Haiyan Gong, Shengling Geng, Ping Xie
Qualitative spatial reasoning is a key spotlight in the domains of artificial intelligence, geographic information system, and robotics and so on. In this paper, we proposed a hierarchical qualitative spatial reasoning method for the spatial relations among multiple components in complex region. Firstly, an adjacency hierarchy matrix is defined based on adjacency link graph, which can be mutually exclusive and fully represent the connection relation among n components. Secondly, the heuristic reasoning on the binary hierarchical relations and the algorithm are proposed. Finally we simulate the relations of the robot and obstacles, and provide a basis for making the robot obstacle avoidance scheme, then the validity of this method is proved from theory and practice.
{"title":"A method of qualitative spatial heuristic reasoning and application for complex region","authors":"Haiyan Gong, Shengling Geng, Ping Xie","doi":"10.1109/ICSAI.2017.8248354","DOIUrl":"https://doi.org/10.1109/ICSAI.2017.8248354","url":null,"abstract":"Qualitative spatial reasoning is a key spotlight in the domains of artificial intelligence, geographic information system, and robotics and so on. In this paper, we proposed a hierarchical qualitative spatial reasoning method for the spatial relations among multiple components in complex region. Firstly, an adjacency hierarchy matrix is defined based on adjacency link graph, which can be mutually exclusive and fully represent the connection relation among n components. Secondly, the heuristic reasoning on the binary hierarchical relations and the algorithm are proposed. Finally we simulate the relations of the robot and obstacles, and provide a basis for making the robot obstacle avoidance scheme, then the validity of this method is proved from theory and practice.","PeriodicalId":285726,"journal":{"name":"2017 4th International Conference on Systems and Informatics (ICSAI)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125571192","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 : 2017-11-01DOI: 10.1109/ICSAI.2017.8248282
X. Wu, Xiao Lin, Linhua Jiang, Dongfang Zhao
This paper present an improved Manifold ranking based saliency detection method. Our method constructs a similarity matrix to represent the connection between each superpixel of image. To achieve the optimization, we select some foreground regions as the foreground labels, by using the objective likelihood map technique, and a part of boundary regions as background labels, by using color distinction measure. Based on these prior information, we generate the rough results by manifold ranking algorithm, and merge the results, obtaining our final saliency map. To verify the robustness of our proposed algorithm, we conduct extensive experiments.
{"title":"An improved manifold ranking based method for saliency detection","authors":"X. Wu, Xiao Lin, Linhua Jiang, Dongfang Zhao","doi":"10.1109/ICSAI.2017.8248282","DOIUrl":"https://doi.org/10.1109/ICSAI.2017.8248282","url":null,"abstract":"This paper present an improved Manifold ranking based saliency detection method. Our method constructs a similarity matrix to represent the connection between each superpixel of image. To achieve the optimization, we select some foreground regions as the foreground labels, by using the objective likelihood map technique, and a part of boundary regions as background labels, by using color distinction measure. Based on these prior information, we generate the rough results by manifold ranking algorithm, and merge the results, obtaining our final saliency map. To verify the robustness of our proposed algorithm, we conduct extensive experiments.","PeriodicalId":285726,"journal":{"name":"2017 4th International Conference on Systems and Informatics (ICSAI)","volume":"740 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128247615","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：