We propose to leverage methods of machine learning to enhance robustness of feature detection algorithm. First, we use semi-supervised learning to develop strategies for guiding the selective refinement process based on training with the domain expert. Second, we propose to combine several local feature detection algorithm into a single, more robust compound classifier using AdaBoost that produces validated feature detection. The compound classifier would combine the best of all local classifiers as they respond to the underlying physical signal. The specific application of interest is vortex detection in turbulent flows. We applied our algorithms to fluid datasets to illustrate the efficacy of our approach.
{"title":"Enhanced Robust Vortex Detection","authors":"Li Zhang, Xiangxu Meng","doi":"10.1109/IHMSC.2012.149","DOIUrl":"https://doi.org/10.1109/IHMSC.2012.149","url":null,"abstract":"We propose to leverage methods of machine learning to enhance robustness of feature detection algorithm. First, we use semi-supervised learning to develop strategies for guiding the selective refinement process based on training with the domain expert. Second, we propose to combine several local feature detection algorithm into a single, more robust compound classifier using AdaBoost that produces validated feature detection. The compound classifier would combine the best of all local classifiers as they respond to the underlying physical signal. The specific application of interest is vortex detection in turbulent flows. We applied our algorithms to fluid datasets to illustrate the efficacy of our approach.","PeriodicalId":431532,"journal":{"name":"2012 4th International Conference on Intelligent Human-Machine Systems and Cybernetics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130971318","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}
With the increasing popularity of social tagging, services that assist the user in the task of tagging, such as tag recommenders, are more and more required. As we all known, crucial to the performance of a recommendation system is the accuracy of the user profiles used to represent the interests of the users. We propose a tag recommendation based on user profile which represents user preferences by taking user's ranking pairwise tag preferences. Although the dataset is obtained indirectly, the experiments show that the tag recommendation based on the proposed user profile has outperformed the baseline tag recommendation.
{"title":"A Collaborative Tag Recommendation Based on User Profile","authors":"Dihua Xu, Zhijian Wang, Yanli Zhang, Ping Zong","doi":"10.1109/IHMSC.2012.89","DOIUrl":"https://doi.org/10.1109/IHMSC.2012.89","url":null,"abstract":"With the increasing popularity of social tagging, services that assist the user in the task of tagging, such as tag recommenders, are more and more required. As we all known, crucial to the performance of a recommendation system is the accuracy of the user profiles used to represent the interests of the users. We propose a tag recommendation based on user profile which represents user preferences by taking user's ranking pairwise tag preferences. Although the dataset is obtained indirectly, the experiments show that the tag recommendation based on the proposed user profile has outperformed the baseline tag recommendation.","PeriodicalId":431532,"journal":{"name":"2012 4th International Conference on Intelligent Human-Machine Systems and Cybernetics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128721748","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}
Traditional blind detection techniques for BMP stego images mainly use a single feature set and a single classifier. However, a single feature set is difficult to completely reflect the differences caused by embedding, and a single classifier is also sensitive to samples. Therefore, we propose a blind detection algorithm based on feature fusion and ensemble classification to improve the accuracy of blind detection for BMP stego images. We firstly extract the features based on higher-order probability density function (PDF) moments of the decomposition subband coefficients and statistical moments of characteristic function (CF) of subband histograms, and then use serial feature fusion to construct a new feature set, adopt Bagging and RSM to train base classifiers and finally utilize the trained classifiers to detect images. The experiment results show that the proposed method can improve the accuracy of the common BMP steganographic methods, such as LSB replacement, LSB matching, SS, and QIM.
{"title":"Blind Detection Algorithm for BMP Stego Images Based on Feature Fusion and Ensemble Classification","authors":"Qiaofen Xu, Shangping Zhong","doi":"10.1109/IHMSC.2012.141","DOIUrl":"https://doi.org/10.1109/IHMSC.2012.141","url":null,"abstract":"Traditional blind detection techniques for BMP stego images mainly use a single feature set and a single classifier. However, a single feature set is difficult to completely reflect the differences caused by embedding, and a single classifier is also sensitive to samples. Therefore, we propose a blind detection algorithm based on feature fusion and ensemble classification to improve the accuracy of blind detection for BMP stego images. We firstly extract the features based on higher-order probability density function (PDF) moments of the decomposition subband coefficients and statistical moments of characteristic function (CF) of subband histograms, and then use serial feature fusion to construct a new feature set, adopt Bagging and RSM to train base classifiers and finally utilize the trained classifiers to detect images. The experiment results show that the proposed method can improve the accuracy of the common BMP steganographic methods, such as LSB replacement, LSB matching, SS, and QIM.","PeriodicalId":431532,"journal":{"name":"2012 4th International Conference on Intelligent Human-Machine Systems and Cybernetics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114327134","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 performance of the Dendritic Cell Algorithm (DCA) is promising in the ordered data set, however, with the context changing multiple times in quick succession there will be a sudden drop in the accuracy, and the rate of false positives and false negatives will increase significantly. A Multiplying and Merging Dendritic Cell Algorithm (MMDCA) is proposed in the light of the unordered data set in anomaly detection. Firstly the data set is multiplied n times, i.e., n instances are generated for each type of antigen, then each instance is assessed, and finally the n assessments of each type of antigen will be merged to get the final result. Experiments show that the algorithm presented has considerable detection accuracy and stable detection performance.
{"title":"Dendritic Cell Algorithm for Anomaly Detection in Unordered Data Set","authors":"Song Yuan, Qi-juan Chen","doi":"10.1109/IHMSC.2012.69","DOIUrl":"https://doi.org/10.1109/IHMSC.2012.69","url":null,"abstract":"The performance of the Dendritic Cell Algorithm (DCA) is promising in the ordered data set, however, with the context changing multiple times in quick succession there will be a sudden drop in the accuracy, and the rate of false positives and false negatives will increase significantly. A Multiplying and Merging Dendritic Cell Algorithm (MMDCA) is proposed in the light of the unordered data set in anomaly detection. Firstly the data set is multiplied n times, i.e., n instances are generated for each type of antigen, then each instance is assessed, and finally the n assessments of each type of antigen will be merged to get the final result. Experiments show that the algorithm presented has considerable detection accuracy and stable detection performance.","PeriodicalId":431532,"journal":{"name":"2012 4th International Conference on Intelligent Human-Machine Systems and Cybernetics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122661282","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}
Scientific prediction has an important significance for establishing industrial policy and making plan in economic market. For the purpose of forecasting mineral commodity price accurately, an ARIMA-Markov chain method is proposed based on the study of time series methods and stochastic process theory. In order to test the prediction effect of the proposed method, a case study is carried out through using mineral molybdenum price values as research data. The results of the case study indicate that the prediction precision of our proposed method is much higher and less limitation to prediction step length than ARIMA model. It is proven that ARIMA-Markov chain performs an excellent property for mineral molybdenum price prediction.
{"title":"Forecasting Mineral Commodity Prices with ARIMA-Markov Chain","authors":"Yong Li, N. Hu, Guoqing Li, Xulong Yao","doi":"10.1109/IHMSC.2012.18","DOIUrl":"https://doi.org/10.1109/IHMSC.2012.18","url":null,"abstract":"Scientific prediction has an important significance for establishing industrial policy and making plan in economic market. For the purpose of forecasting mineral commodity price accurately, an ARIMA-Markov chain method is proposed based on the study of time series methods and stochastic process theory. In order to test the prediction effect of the proposed method, a case study is carried out through using mineral molybdenum price values as research data. The results of the case study indicate that the prediction precision of our proposed method is much higher and less limitation to prediction step length than ARIMA model. It is proven that ARIMA-Markov chain performs an excellent property for mineral molybdenum price prediction.","PeriodicalId":431532,"journal":{"name":"2012 4th International Conference on Intelligent Human-Machine Systems and Cybernetics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127586644","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 conventional learning algorithm based on BP method may converge to a local minimum, slowly converging speed and is shock before and after the Convergence point. A algorithm based on BP and PID techniques for wavelet network learning was proposed. And PIDBP algorithm can significantly reduce the probability of the emergence of local minimum after adding momentum term, At the same time introduction of the inertia term, Can be in the larger learning parameters to speed up the convergence and divergence and to reduce the possibility of oscillation, And avoid conventional BP algorithm in the convergence region Insensitivity to accelerate the convergence.
{"title":"Improved Wavelet Networks Algorithm Research and its Application","authors":"Yin Jin-tian, Tang Jie, Liu Li","doi":"10.1109/IHMSC.2012.10","DOIUrl":"https://doi.org/10.1109/IHMSC.2012.10","url":null,"abstract":"The conventional learning algorithm based on BP method may converge to a local minimum, slowly converging speed and is shock before and after the Convergence point. A algorithm based on BP and PID techniques for wavelet network learning was proposed. And PIDBP algorithm can significantly reduce the probability of the emergence of local minimum after adding momentum term, At the same time introduction of the inertia term, Can be in the larger learning parameters to speed up the convergence and divergence and to reduce the possibility of oscillation, And avoid conventional BP algorithm in the convergence region Insensitivity to accelerate the convergence.","PeriodicalId":431532,"journal":{"name":"2012 4th International Conference on Intelligent Human-Machine Systems and Cybernetics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127888416","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 identifies and analyses the factors and characteristics of human thinking structure based on the background training, and work field. We propose the conceptual graph to represent the Knowledge Competencies (KC) for the specific area of Digital Media Design. The scope of the Knowledge Competencies is represented visually using graphs, illustrating the relevance of different subjects to Digital Media Design. The paper provides a reference basis for learners and scholars in the general area of Digital Media Design, and thereby promote the new interdisciplinary area of Digital Media Design. The paper finally uses a case study to evaluate the knowledge requirements of Digital Media Design for different subject areas.
{"title":"Research on Knowledge Competencies for Digital Media Design","authors":"Renming Qiao, Dong Han, Shasha Wang","doi":"10.1109/IHMSC.2012.175","DOIUrl":"https://doi.org/10.1109/IHMSC.2012.175","url":null,"abstract":"The paper identifies and analyses the factors and characteristics of human thinking structure based on the background training, and work field. We propose the conceptual graph to represent the Knowledge Competencies (KC) for the specific area of Digital Media Design. The scope of the Knowledge Competencies is represented visually using graphs, illustrating the relevance of different subjects to Digital Media Design. The paper provides a reference basis for learners and scholars in the general area of Digital Media Design, and thereby promote the new interdisciplinary area of Digital Media Design. The paper finally uses a case study to evaluate the knowledge requirements of Digital Media Design for different subject areas.","PeriodicalId":431532,"journal":{"name":"2012 4th International Conference on Intelligent Human-Machine Systems and Cybernetics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116987989","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}
LonWorks technology is a kind of field bus technology that launched by the Echelon company of United States in the 90s. It is a complete technical platform that used to develop the monitoring network system, and it has all the characteristics of field bus technology. LonWorks network system is composed by intelligent node, every intelligent node has many types of I/O function, those nodes can communicate through different transmission media, it also abides by the ISO/OSI seven layer model agreement. LonWorks technology is made up of monitoring network design, development, installation and debugging of methodology. This paper had analysised the building automation system of control network requirements and building automation control system that based on the structure of construction and LonWorks bus network structure. It had got the specific hardware realization and the software of building air conditioning control system.
{"title":"The Application of LonWorks in the Building Air Conditioner Intelligent Control System","authors":"Huang Xiao-ping, Li Jian-liang","doi":"10.1109/IHMSC.2012.58","DOIUrl":"https://doi.org/10.1109/IHMSC.2012.58","url":null,"abstract":"LonWorks technology is a kind of field bus technology that launched by the Echelon company of United States in the 90s. It is a complete technical platform that used to develop the monitoring network system, and it has all the characteristics of field bus technology. LonWorks network system is composed by intelligent node, every intelligent node has many types of I/O function, those nodes can communicate through different transmission media, it also abides by the ISO/OSI seven layer model agreement. LonWorks technology is made up of monitoring network design, development, installation and debugging of methodology. This paper had analysised the building automation system of control network requirements and building automation control system that based on the structure of construction and LonWorks bus network structure. It had got the specific hardware realization and the software of building air conditioning control system.","PeriodicalId":431532,"journal":{"name":"2012 4th International Conference on Intelligent Human-Machine Systems and Cybernetics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121060120","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}
Ping Zuo, Shichun Pang, Xue Feng, Ya Gao, Dandan Qin
The main problem in the spectrum analysis technology is the difficulty in locating the target which will affect the predication and the analysis. How to choose the right mathematic model becomes the key point in the spectrum analysis. This paper designs the practical manual neural network model to locate the target and predicate. This paper uses error backward direction propagation calculation method and establishes three-layer neural network to solve the problems such as the spectrum peaks overlap seriously and noise is big in the spectrum analysis. When the quantity of samples to be located the target is significant, employ manual neural network method to analyze and discuss the corn's protein content and near-infrared spectrum. By analyzing the experimental result this paper concludes that manual neural network method performs better than linear regression method and partial least-squares method and obtains ideal result.
{"title":"Application of Neural Network in the Analysis of Near-Infrared Spectra","authors":"Ping Zuo, Shichun Pang, Xue Feng, Ya Gao, Dandan Qin","doi":"10.1109/IHMSC.2012.45","DOIUrl":"https://doi.org/10.1109/IHMSC.2012.45","url":null,"abstract":"The main problem in the spectrum analysis technology is the difficulty in locating the target which will affect the predication and the analysis. How to choose the right mathematic model becomes the key point in the spectrum analysis. This paper designs the practical manual neural network model to locate the target and predicate. This paper uses error backward direction propagation calculation method and establishes three-layer neural network to solve the problems such as the spectrum peaks overlap seriously and noise is big in the spectrum analysis. When the quantity of samples to be located the target is significant, employ manual neural network method to analyze and discuss the corn's protein content and near-infrared spectrum. By analyzing the experimental result this paper concludes that manual neural network method performs better than linear regression method and partial least-squares method and obtains ideal result.","PeriodicalId":431532,"journal":{"name":"2012 4th International Conference on Intelligent Human-Machine Systems and Cybernetics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121420932","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 puts forward a control method of vehicle rear-end anti-collision security system from the point of view of ensuring the traffic safety. The system makes full use of the electromagnetic devices which are installed on the trail of leading vehicle and the head of following vehicle. It uses the principle of electromagnetic repulsion of the same. When the leading vehicle suddenly slows down or has an emergency stopping, the devices open at the same time to increase the deceleration of following vehicle to set up an automatic auxiliary braking system. The purpose of the method is to avoid the driver's reaction delay and ensure the car safety immediately. Meanwhile, it can improve the efficiency of deceleration. This paper analyses the feasibility of the method from two aspects: safety distance and deceleration efficiency.
{"title":"A Control System of Vehicle Rear-end Anti-collision","authors":"Meng Chen, Fasheng Liu, Chuanxiang Ren, Zhimin Gao","doi":"10.1109/IHMSC.2012.107","DOIUrl":"https://doi.org/10.1109/IHMSC.2012.107","url":null,"abstract":"This paper puts forward a control method of vehicle rear-end anti-collision security system from the point of view of ensuring the traffic safety. The system makes full use of the electromagnetic devices which are installed on the trail of leading vehicle and the head of following vehicle. It uses the principle of electromagnetic repulsion of the same. When the leading vehicle suddenly slows down or has an emergency stopping, the devices open at the same time to increase the deceleration of following vehicle to set up an automatic auxiliary braking system. The purpose of the method is to avoid the driver's reaction delay and ensure the car safety immediately. Meanwhile, it can improve the efficiency of deceleration. This paper analyses the feasibility of the method from two aspects: safety distance and deceleration efficiency.","PeriodicalId":431532,"journal":{"name":"2012 4th International Conference on Intelligent Human-Machine Systems and Cybernetics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126585024","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：