Pub Date : 2012-07-09DOI: 10.1109/ICNC.2012.6234714
Ding Lei
To improve the stability of the sensor and to reduce the non-goal parameter's influence, a new static error correction method of the sensor based on support vector machine for regression (SVR) is presented. Experimental results show that the proposed method can decrease the temperature sensitivity coefficient of pressure sensor and improve the measurement accuracy of pressure validly. And judging from it's stability, it proves to be much better than traditional error correction methods.
{"title":"Static error correction of the sensor based on SVR","authors":"Ding Lei","doi":"10.1109/ICNC.2012.6234714","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234714","url":null,"abstract":"To improve the stability of the sensor and to reduce the non-goal parameter's influence, a new static error correction method of the sensor based on support vector machine for regression (SVR) is presented. Experimental results show that the proposed method can decrease the temperature sensitivity coefficient of pressure sensor and improve the measurement accuracy of pressure validly. And judging from it's stability, it proves to be much better than traditional error correction methods.","PeriodicalId":404981,"journal":{"name":"2012 8th International Conference on Natural Computation","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129821093","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 the affection regulation process, quantitative regulation model between effectives and affection regulation ways cannot be established, thus the unit's effective problems cannot be regulated instantly, effectively and intelligently by computers. So an affection regulation strategic model based on partial least squares method was proposed. The model used GSR to recognize effectives, and the recognized effectives are mapped to the PAD effective space vector model to realize the quantization of effectives. Through Namely reappraisal and Suppression ways, the affection regulation strategy was achieved, which set up the theoretical principles for affection regulation system in man-computer interactive environment. And the strategy got the purpose of affective computing which can establish harmonious man-machine environment and endow computer with much higher and more comprehensive intelligence.
{"title":"The model about the affection regulation based on partial least regression in the Human-computer interaction","authors":"Fengru Liu, Guangyuan Liu, Xiangwei Lai, Wanhui Wen","doi":"10.1109/ICNC.2012.6234759","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234759","url":null,"abstract":"In the affection regulation process, quantitative regulation model between effectives and affection regulation ways cannot be established, thus the unit's effective problems cannot be regulated instantly, effectively and intelligently by computers. So an affection regulation strategic model based on partial least squares method was proposed. The model used GSR to recognize effectives, and the recognized effectives are mapped to the PAD effective space vector model to realize the quantization of effectives. Through Namely reappraisal and Suppression ways, the affection regulation strategy was achieved, which set up the theoretical principles for affection regulation system in man-computer interactive environment. And the strategy got the purpose of affective computing which can establish harmonious man-machine environment and endow computer with much higher and more comprehensive intelligence.","PeriodicalId":404981,"journal":{"name":"2012 8th International Conference on Natural Computation","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124795114","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 : 2012-07-09DOI: 10.1109/ICNC.2012.6234718
Wang Zhengchu, Xia Ruting
Complex system reliability function is nonlinear. It is difficult to design a system which is satisfied reliability condition and also has minimum cost. Many intelligent optimization algorithms are used to solve the problem. Many shortcomings still exist such as being trapped into the local optimal solution easily, low convergence efficiency, etc. In this paper, it presents a hybrid simulated annealing quantum evolutionary algorithms (HSAQEA). Adaptive simulated annealing algorithm is embedded in the quantum evolutionary algorithm, and it retains elitist in the evolution in order to accelerate search for efficiency and speed. The presented algorithm is described in detail. The solving strategy is proposed for the problem of complex system reliability optimization. It also analyzes the reliability distribution of bridge connection system. At last, by calculations of the example and comparison with other algorithms, it proves the algorithm has much stronger ability of local search and better search efficiency. It certifies that this method is feasible and valid.
{"title":"HSAQEA based reliability redundancy optimization for complex system","authors":"Wang Zhengchu, Xia Ruting","doi":"10.1109/ICNC.2012.6234718","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234718","url":null,"abstract":"Complex system reliability function is nonlinear. It is difficult to design a system which is satisfied reliability condition and also has minimum cost. Many intelligent optimization algorithms are used to solve the problem. Many shortcomings still exist such as being trapped into the local optimal solution easily, low convergence efficiency, etc. In this paper, it presents a hybrid simulated annealing quantum evolutionary algorithms (HSAQEA). Adaptive simulated annealing algorithm is embedded in the quantum evolutionary algorithm, and it retains elitist in the evolution in order to accelerate search for efficiency and speed. The presented algorithm is described in detail. The solving strategy is proposed for the problem of complex system reliability optimization. It also analyzes the reliability distribution of bridge connection system. At last, by calculations of the example and comparison with other algorithms, it proves the algorithm has much stronger ability of local search and better search efficiency. It certifies that this method is feasible and valid.","PeriodicalId":404981,"journal":{"name":"2012 8th International Conference on Natural Computation","volume":"39 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124850751","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 : 2012-05-29DOI: 10.1109/ICNC.2012.6234624
Xiao Wang, Zuoan Li
In this paper, a class of Cohen-Grossberg-type fuzzy neural networks with distributed delays and impulses is investigated. By employing differential inequality and M-matrix theory, some sufficient conditions ensuring the existence and global exponential stability of the periodic oscillatory solution for Cohen-Grossberg-type fuzzy neural networks with distributed delays and impulses are obtained. An examples is given to show the effectiveness of the obtained results.
{"title":"Periodicity of Cohen-Grossberg-type fuzzy neural networks with distributed delays and impulses","authors":"Xiao Wang, Zuoan Li","doi":"10.1109/ICNC.2012.6234624","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234624","url":null,"abstract":"In this paper, a class of Cohen-Grossberg-type fuzzy neural networks with distributed delays and impulses is investigated. By employing differential inequality and M-matrix theory, some sufficient conditions ensuring the existence and global exponential stability of the periodic oscillatory solution for Cohen-Grossberg-type fuzzy neural networks with distributed delays and impulses are obtained. An examples is given to show the effectiveness of the obtained results.","PeriodicalId":404981,"journal":{"name":"2012 8th International Conference on Natural Computation","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125199787","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 : 2012-05-29DOI: 10.1109/ICNC.2012.6234529
Shanfei Jiao, Chen He, Y. Dou, Hong Tang
At first the paper introduced the basic concept and mechanism of Hadoop architecture and the current parallel research situation of molecular dynamics simulation, then three solutions were proposed for implementing the parallel algorithm using atom-decomposition method on Hadoop to overcome shortcomings of fast iteration and communication among sub-tasks. After that tested and analyzed program's speed-up ratio, expansibility and cost-time of various parts, then did performance tuning in many ways, finally obtained good results as high as 28× speedup in large-scale system simulations. The test showing molecular dynamics simulation based on Hadoop is more economical and practical.
{"title":"Molecular dynamics simulation: Implementation and optimization based on Hadoop","authors":"Shanfei Jiao, Chen He, Y. Dou, Hong Tang","doi":"10.1109/ICNC.2012.6234529","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234529","url":null,"abstract":"At first the paper introduced the basic concept and mechanism of Hadoop architecture and the current parallel research situation of molecular dynamics simulation, then three solutions were proposed for implementing the parallel algorithm using atom-decomposition method on Hadoop to overcome shortcomings of fast iteration and communication among sub-tasks. After that tested and analyzed program's speed-up ratio, expansibility and cost-time of various parts, then did performance tuning in many ways, finally obtained good results as high as 28× speedup in large-scale system simulations. The test showing molecular dynamics simulation based on Hadoop is more economical and practical.","PeriodicalId":404981,"journal":{"name":"2012 8th International Conference on Natural Computation","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125035300","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 : 2012-05-29DOI: 10.1109/ICNC.2012.6234604
Ken Chen, Shoujian Yang, C. Batur
As a multi-layer forwarding network, the back propagation neural network (BPNN) with manifold derived structures has been most widely used in artificial intelligence applications. Based on the given non-linear system and the BPNNs of varying internal structures, this paper quantitatively reports the findings in the correlation between the number of hidden layers and the BPNN performance. The selection of learning rate is also investigated using the 3-layer BPNN and the same non-linear system. Through the simulation results in this probe it finds that the BPNN performance is not improved notably or even degraded with the increase of hidden layers, and 3-layer (or 1-1-1) BPNN is identified as the best performer.
{"title":"Effect of multi-hidden-layer structure on performance of BP neural network: Probe","authors":"Ken Chen, Shoujian Yang, C. Batur","doi":"10.1109/ICNC.2012.6234604","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234604","url":null,"abstract":"As a multi-layer forwarding network, the back propagation neural network (BPNN) with manifold derived structures has been most widely used in artificial intelligence applications. Based on the given non-linear system and the BPNNs of varying internal structures, this paper quantitatively reports the findings in the correlation between the number of hidden layers and the BPNN performance. The selection of learning rate is also investigated using the 3-layer BPNN and the same non-linear system. Through the simulation results in this probe it finds that the BPNN performance is not improved notably or even degraded with the increase of hidden layers, and 3-layer (or 1-1-1) BPNN is identified as the best performer.","PeriodicalId":404981,"journal":{"name":"2012 8th International Conference on Natural Computation","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125287061","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}
Aiming at working out the problem that traditional GRA call admission control algorithm didn't consider the load state obviously in heterogeneous wireless network, a Strengthen Gray Relative Analysis based on load balance access selection algorithm was proposed. The algorithm took load state as a strengthen factor to adjust the resolution coefficient of GRA to achieve effective load balance in each network. The simulation results show that compared to MLB the algorithm it can balance the load of heterogeneous wireless effectively when guarantee the Qos, and decreased and balanced the block probability. Meanwhile, compared to traditional GRA which took load as one of its factor algorithm can balance load obviously when guarantee low blocking probability.
{"title":"Strengthen-Gray Relative Analysis access selection algorithm based on load balance in heterogeneous wireless networks","authors":"Yi-ting Luo, Bing Qi, Yuan-Yuan Chen, Liangrui Tang","doi":"10.1109/ICNC.2012.6234726","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234726","url":null,"abstract":"Aiming at working out the problem that traditional GRA call admission control algorithm didn't consider the load state obviously in heterogeneous wireless network, a Strengthen Gray Relative Analysis based on load balance access selection algorithm was proposed. The algorithm took load state as a strengthen factor to adjust the resolution coefficient of GRA to achieve effective load balance in each network. The simulation results show that compared to MLB the algorithm it can balance the load of heterogeneous wireless effectively when guarantee the Qos, and decreased and balanced the block probability. Meanwhile, compared to traditional GRA which took load as one of its factor algorithm can balance load obviously when guarantee low blocking probability.","PeriodicalId":404981,"journal":{"name":"2012 8th International Conference on Natural Computation","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122372537","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 : 2012-05-29DOI: 10.1109/ICNC.2012.6234746
Xin Liu, W. Yin, Luping Song
The present paper describes a case of severe acalculia derived from right-hemisphere lesion. The patient (LLS) did not merely present the symptoms expected after a right hemisphere lesion, such as a generic inability to deal with spatial material, or from other deficits, such as neglect; the patient was also unable to complete simple addition and multiplication but with preserved general verbal ability. The implications of these symptoms are discussed in the context of the noted theoretical models that have been proposed for the cognitive mechanisms underlying number processing and calculation skills.
{"title":"A case of severe acalculia derived from a right hemisphere lesion","authors":"Xin Liu, W. Yin, Luping Song","doi":"10.1109/ICNC.2012.6234746","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234746","url":null,"abstract":"The present paper describes a case of severe acalculia derived from right-hemisphere lesion. The patient (LLS) did not merely present the symptoms expected after a right hemisphere lesion, such as a generic inability to deal with spatial material, or from other deficits, such as neglect; the patient was also unable to complete simple addition and multiplication but with preserved general verbal ability. The implications of these symptoms are discussed in the context of the noted theoretical models that have been proposed for the cognitive mechanisms underlying number processing and calculation skills.","PeriodicalId":404981,"journal":{"name":"2012 8th International Conference on Natural Computation","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129604704","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 : 2012-05-29DOI: 10.1109/ICNC.2012.6234623
S. Mun, J. Son, W. Jo, W. Lee
Nowadays maritime data communications are mainly performed by satellite and radio media. But these media have limits on economics or data rate. Future ships at sea would need broad and stable maritime data communication system like that of land. In this paper, we propose Automatic Identification System (AIS)-based ad hoc network model and AIS-based Ad hoc routing protocol (AAR) newly for ship to ship, ship to shore data communications. The protocol has been implemented to verify the functionality of that.
{"title":"An implementation of AIS-based Ad hoc routing(AAR) protocol for maritime data communication networks","authors":"S. Mun, J. Son, W. Jo, W. Lee","doi":"10.1109/ICNC.2012.6234623","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234623","url":null,"abstract":"Nowadays maritime data communications are mainly performed by satellite and radio media. But these media have limits on economics or data rate. Future ships at sea would need broad and stable maritime data communication system like that of land. In this paper, we propose Automatic Identification System (AIS)-based ad hoc network model and AIS-based Ad hoc routing protocol (AAR) newly for ship to ship, ship to shore data communications. The protocol has been implemented to verify the functionality of that.","PeriodicalId":404981,"journal":{"name":"2012 8th International Conference on Natural Computation","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128503783","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 : 2012-05-29DOI: 10.1109/ICNC.2012.6234521
Haixia Long, Xiuzhen Hu
The authors use three methods, including matrix scoring algorithm, increment of diversity algorithm and Random Forest algorithm. They are used to predict β-hairpin motifs in the ArchDB-EC and ArchDB40 dataset. In the ArchDB-EC dataset, we obtain the accuracy of 68.5%, 79.8% and 84.3%, respectively. Matthew's correlation coefficient are 0.17, 0.61 and 0.63, respectively. Using same three methods in the ArchDB40 dataset, we obtain the accuracy and Matthew's correlation coefficient of 67.9% and 0.39, 75.2% and 0.51, 83.5% and 0.60, respectively. Experiments show that Random Forest algorithm for predicting β-hairpin motifs is best and the predictive results in ArchDB40 dataset are better than previous results.
{"title":"Prediction β-hairpin motifs in enzyme protein using three methods","authors":"Haixia Long, Xiuzhen Hu","doi":"10.1109/ICNC.2012.6234521","DOIUrl":"https://doi.org/10.1109/ICNC.2012.6234521","url":null,"abstract":"The authors use three methods, including matrix scoring algorithm, increment of diversity algorithm and Random Forest algorithm. They are used to predict β-hairpin motifs in the ArchDB-EC and ArchDB40 dataset. In the ArchDB-EC dataset, we obtain the accuracy of 68.5%, 79.8% and 84.3%, respectively. Matthew's correlation coefficient are 0.17, 0.61 and 0.63, respectively. Using same three methods in the ArchDB40 dataset, we obtain the accuracy and Matthew's correlation coefficient of 67.9% and 0.39, 75.2% and 0.51, 83.5% and 0.60, respectively. Experiments show that Random Forest algorithm for predicting β-hairpin motifs is best and the predictive results in ArchDB40 dataset are better than previous results.","PeriodicalId":404981,"journal":{"name":"2012 8th International Conference on Natural Computation","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128773107","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：