Human action recognition is very important in human computer interaction. In this article, we present a new method of recognizing human actions by using Microsoft Kinect sensor, k-means clustering and Hidden Markov Models (HMMs). Kinect is able to generate human skeleton information from depth images, in addition, features representing specific body parts are generated from the skeleton information and are used for recording actions. Then k-means clustering assigns the features into clusters and HMMs analyze the relationship between these clusters. By doing this, we achieved action learning and recognition. According to our experimental results, the average accuracy was 91.4 %.
{"title":"Human Action Recognition Based on Depth Images from Microsoft Kinect","authors":"Tong Liu, Yang Song, Yu Gu, A. Li","doi":"10.1109/GCIS.2013.38","DOIUrl":"https://doi.org/10.1109/GCIS.2013.38","url":null,"abstract":"Human action recognition is very important in human computer interaction. In this article, we present a new method of recognizing human actions by using Microsoft Kinect sensor, k-means clustering and Hidden Markov Models (HMMs). Kinect is able to generate human skeleton information from depth images, in addition, features representing specific body parts are generated from the skeleton information and are used for recording actions. Then k-means clustering assigns the features into clusters and HMMs analyze the relationship between these clusters. By doing this, we achieved action learning and recognition. According to our experimental results, the average accuracy was 91.4 %.","PeriodicalId":366262,"journal":{"name":"2013 Fourth Global Congress on Intelligent Systems","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131101454","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The paper describes an expert system that helps in a process of a map sheet creation. The expert system is based on ontology that describes basic elements of a map sheet and geodata used for map sheet creation. The paper describes mainly how is the ontology used for building knowledge base of the expert system. The expert system is based on DROOLS software. The ontology is created in Protege software.
{"title":"Expert System for Cartography Based on Ontology","authors":"J. Růžička, K. Růžičková, Radek Dostal","doi":"10.1109/GCIS.2013.31","DOIUrl":"https://doi.org/10.1109/GCIS.2013.31","url":null,"abstract":"The paper describes an expert system that helps in a process of a map sheet creation. The expert system is based on ontology that describes basic elements of a map sheet and geodata used for map sheet creation. The paper describes mainly how is the ontology used for building knowledge base of the expert system. The expert system is based on DROOLS software. The ontology is created in Protege software.","PeriodicalId":366262,"journal":{"name":"2013 Fourth Global Congress on Intelligent Systems","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125183096","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}
This paper proposes a powerful and robust local descriptor, called color Weber feature(CWF). The CWF descriptor consists of two components: color contrast ratio and color edge orientation. Inspired by Weber's Law, we propose color contrast ratio which implements hierarchical quantization of salience within an image to simulate the pattern perception of human beings. We embed the proposed CWF representation model in the mean shift tracking framework to perform object tracking. The experiments results demonstrate that CWF is a viable object representation for tracking even in the adverse scenarios such as heavy occlusions, illumination variations and similar objects interference.
{"title":"Robust Object Tracking Based on a Novel Feature","authors":"Wenlin Zou, S. Fei, Liuwen Li, Qi Li, Hong Lu","doi":"10.1109/GCIS.2013.25","DOIUrl":"https://doi.org/10.1109/GCIS.2013.25","url":null,"abstract":"This paper proposes a powerful and robust local descriptor, called color Weber feature(CWF). The CWF descriptor consists of two components: color contrast ratio and color edge orientation. Inspired by Weber's Law, we propose color contrast ratio which implements hierarchical quantization of salience within an image to simulate the pattern perception of human beings. We embed the proposed CWF representation model in the mean shift tracking framework to perform object tracking. The experiments results demonstrate that CWF is a viable object representation for tracking even in the adverse scenarios such as heavy occlusions, illumination variations and similar objects interference.","PeriodicalId":366262,"journal":{"name":"2013 Fourth Global Congress on Intelligent Systems","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127825049","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}
In this paper, we propose a new computational model of driver car-following control with lateral control based on the Queuing Network (QN) cognitive architecture. A driver car-following model within the framework of the QN cognitive architecture is first developed based on the time headway and then integrated with a QN-based driver lateral control model previously validated. The comparison between human driver data and the integrated model simulation data suggests that this computational model can perform car-following control with lateral control well, and its performance is in agreement with that of drivers under straight and curved roads. This proposed model can compute and simulate car-following behavior and thus has the potential to help develop driver assistance systems for the car-following scenario.
{"title":"A Driver Lateral and Longitudinal Control Model Based on Queuing Network Cognitive Architecture","authors":"Luzheng Bi, Cuie Wang, Xuerui Yang","doi":"10.1109/GCIS.2013.50","DOIUrl":"https://doi.org/10.1109/GCIS.2013.50","url":null,"abstract":"In this paper, we propose a new computational model of driver car-following control with lateral control based on the Queuing Network (QN) cognitive architecture. A driver car-following model within the framework of the QN cognitive architecture is first developed based on the time headway and then integrated with a QN-based driver lateral control model previously validated. The comparison between human driver data and the integrated model simulation data suggests that this computational model can perform car-following control with lateral control well, and its performance is in agreement with that of drivers under straight and curved roads. This proposed model can compute and simulate car-following behavior and thus has the potential to help develop driver assistance systems for the car-following scenario.","PeriodicalId":366262,"journal":{"name":"2013 Fourth Global Congress on Intelligent Systems","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126713303","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}
Foraging is a benchmark problem for swarm robotics. It is inspired by swarms of insects cooperating to locate and/or transport food items that a single individual cannot move. The challenge is to program a swarm of simple robots, with minimal communication and individual capability, to search the environment for some search target and return it to their base collectively. In this paper we introduce a novel foraging algorithm: Tornado. The Tornado algorithm is inspired by the spiral tornado motion. The algorithm can scan an area with high speed given a large swarm. However, it can adapt in case of failure of some robots and successfully finish the job at a slower speed. Experimental results show that the algorithm provides better coverage and robustness compared to previous foraging algorithms.
{"title":"Tornado: A Robust Adaptive Foraging Algorithm for Swarm Robots","authors":"Dina Magdy, Y. Alkabani, H.S. Bedor","doi":"10.1109/GCIS.2013.48","DOIUrl":"https://doi.org/10.1109/GCIS.2013.48","url":null,"abstract":"Foraging is a benchmark problem for swarm robotics. It is inspired by swarms of insects cooperating to locate and/or transport food items that a single individual cannot move. The challenge is to program a swarm of simple robots, with minimal communication and individual capability, to search the environment for some search target and return it to their base collectively. In this paper we introduce a novel foraging algorithm: Tornado. The Tornado algorithm is inspired by the spiral tornado motion. The algorithm can scan an area with high speed given a large swarm. However, it can adapt in case of failure of some robots and successfully finish the job at a slower speed. Experimental results show that the algorithm provides better coverage and robustness compared to previous foraging algorithms.","PeriodicalId":366262,"journal":{"name":"2013 Fourth Global Congress on Intelligent Systems","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121743604","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The proliferation of malware has presented a serious threat to internet security, and made traditional signature-based methods unable to analyze and process the massive data timely and effectively. The development trend of malware motivates many research efforts in intelligent malware analysis, where machine learning is used for malware detection. Currently, most of machine learning methods on malware detection utilize file contents extracted from the file samples. However, besides file contents, relations among file samples can provide invaluable information about the properties of file samples, which may improve the malware detection accuracy. Social graph is a popular way to present a set of socially-relevant nodes connected by one or more relations. It can well present the relations/dependence among file samples. Therefore, we attempt to employ social graph to study the file relations as the feature representation of file samples, and combine machine learning methods to detect malware.
{"title":"A Feature Representation Method of Social Graph for Malware Detection","authors":"Q. Jiang, Nan Liu, Wei Zhang","doi":"10.1109/GCIS.2013.28","DOIUrl":"https://doi.org/10.1109/GCIS.2013.28","url":null,"abstract":"The proliferation of malware has presented a serious threat to internet security, and made traditional signature-based methods unable to analyze and process the massive data timely and effectively. The development trend of malware motivates many research efforts in intelligent malware analysis, where machine learning is used for malware detection. Currently, most of machine learning methods on malware detection utilize file contents extracted from the file samples. However, besides file contents, relations among file samples can provide invaluable information about the properties of file samples, which may improve the malware detection accuracy. Social graph is a popular way to present a set of socially-relevant nodes connected by one or more relations. It can well present the relations/dependence among file samples. Therefore, we attempt to employ social graph to study the file relations as the feature representation of file samples, and combine machine learning methods to detect malware.","PeriodicalId":366262,"journal":{"name":"2013 Fourth Global Congress on Intelligent Systems","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114972506","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：