A fast and effective Digital Radiography (DR) image fusion method is proposed. An image can be decomposed into a base layer and a detail layer with the average filtering. A quality measure called well-exposedness to the multi-voltage DR image is proposed, and then the weight maps of the source images can be got. Then the fused base layer can be got by weighted averaging. The weight maps of the detail layers can be obtained by the contrast. And the contrast on the false edge must be reduced so as to reduce the false edges in the fusion image. Experimental results show that the structure of the component can be seen clearly in the fusion image, and the details are clearer.
{"title":"An Algorithm for Multi-voltage Digital Radiography Image Fusion","authors":"Yanjie Qi","doi":"10.12733/JICS20105518","DOIUrl":"https://doi.org/10.12733/JICS20105518","url":null,"abstract":"A fast and effective Digital Radiography (DR) image fusion method is proposed. An image can be decomposed into a base layer and a detail layer with the average filtering. A quality measure called well-exposedness to the multi-voltage DR image is proposed, and then the weight maps of the source images can be got. Then the fused base layer can be got by weighted averaging. The weight maps of the detail layers can be obtained by the contrast. And the contrast on the false edge must be reduced so as to reduce the false edges in the fusion image. Experimental results show that the structure of the component can be seen clearly in the fusion image, and the details are clearer.","PeriodicalId":213716,"journal":{"name":"The Journal of Information and Computational Science","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123651817","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}
Relevance Vector Machine (RVM) has excellent classification performance for nonlinear, high dimensional and small data sets. Traditional One-against-One (OAO) is applied the most widely by it in multiclassification. However, it uses many classifiers which results in slow classification. In order to improve the classification speed, a new method based on OAO is proposed. The method finds the class corresponding to the test sample from a narrower class ranges through circular computation. At the classifying prediction stage, all the possible classes are put as a circle; each adjacent class is classified; the classes with most votes are the possible classes of next iteration. After repeating these processes, the last remaining one is the predicted class. Experiments show that the proposed method can ensure classification accuracy while enhancing the speed effectively.
{"title":"A Novel Multi-classification Method Based on One-against-One Relevance Vector Machine","authors":"Mingyan Wang, Wenhua Tu","doi":"10.12733/JICS20105629","DOIUrl":"https://doi.org/10.12733/JICS20105629","url":null,"abstract":"Relevance Vector Machine (RVM) has excellent classification performance for nonlinear, high dimensional and small data sets. Traditional One-against-One (OAO) is applied the most widely by it in multiclassification. However, it uses many classifiers which results in slow classification. In order to improve the classification speed, a new method based on OAO is proposed. The method finds the class corresponding to the test sample from a narrower class ranges through circular computation. At the classifying prediction stage, all the possible classes are put as a circle; each adjacent class is classified; the classes with most votes are the possible classes of next iteration. After repeating these processes, the last remaining one is the predicted class. Experiments show that the proposed method can ensure classification accuracy while enhancing the speed effectively.","PeriodicalId":213716,"journal":{"name":"The Journal of Information and Computational Science","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129085593","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}
{"title":"One-dimensional Cellular Automaton Traffic Flow Model Based on Driving Rules","authors":"Xiuzhen Qi","doi":"10.12733/JICS20105622","DOIUrl":"https://doi.org/10.12733/JICS20105622","url":null,"abstract":"","PeriodicalId":213716,"journal":{"name":"The Journal of Information and Computational Science","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122764458","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}
Large differences of seismic response may exist when the structure subject different frequency seismic ground motions, and the low frequency and the high frequency may control the seismic response of different stage for super tall structure. Three groups earthquake waves which have different frequency were selected as input for time history analysis of a designed super tall building structural model. The analysis software is PERFORM-3D. The results show that the gap is very large in displacement, base shear and the maximum story drift ratio. Meanwhile, the maximum vertex displacement of structure lagging behind the maximum base shear. Nevertheless, there are a lot research shows that the transient response of high frequency seismic ground motions may induce the bigger displacement than the resonance. But the mode decomposition response spectrum method could not make a reasonable estimate on the seismic response characteristic of super high-rise structure. Super high-rise building structures have their own unique response characteristics in different frequency component ground motions, so needing to consider the ground motion with different frequencies when choose a wave for time history analysis.
{"title":"Influence of Seismic Ground Motions with Different Frequency on Super High-rise Building Structural Seismic Response","authors":"Q. Tan","doi":"10.12733/JICS20105621","DOIUrl":"https://doi.org/10.12733/JICS20105621","url":null,"abstract":"Large differences of seismic response may exist when the structure subject different frequency seismic ground motions, and the low frequency and the high frequency may control the seismic response of different stage for super tall structure. Three groups earthquake waves which have different frequency were selected as input for time history analysis of a designed super tall building structural model. The analysis software is PERFORM-3D. The results show that the gap is very large in displacement, base shear and the maximum story drift ratio. Meanwhile, the maximum vertex displacement of structure lagging behind the maximum base shear. Nevertheless, there are a lot research shows that the transient response of high frequency seismic ground motions may induce the bigger displacement than the resonance. But the mode decomposition response spectrum method could not make a reasonable estimate on the seismic response characteristic of super high-rise structure. Super high-rise building structures have their own unique response characteristics in different frequency component ground motions, so needing to consider the ground motion with different frequencies when choose a wave for time history analysis.","PeriodicalId":213716,"journal":{"name":"The Journal of Information and Computational Science","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126419163","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 recent years, Orthogonal Frequency Division Multiplexing (OFDM) has received widespread attention for high-data rate transmission. One drawback of OFDM is the high Peak-to-average Power Ratio (PAPR). A novel scheme referred to as Quantization Clipping (QC) is proposed to solve the high PAPR problem in OFDM-QAM system. For the QC scheme, we preset several different clipping thresholds, and then quantize the input signal to a group of preset thresholds. Simulation results show that the new scheme can significantly improve the BER performance while guaranteeing the improvement in the PAPR performance of the OFDM-QAM system.
{"title":"A Modified Clipping Scheme for PAPR Reduction of OFDM-QAM Signals Based on Quantization Method","authors":"Zhen He","doi":"10.12733/JICS20105631","DOIUrl":"https://doi.org/10.12733/JICS20105631","url":null,"abstract":"In recent years, Orthogonal Frequency Division Multiplexing (OFDM) has received widespread attention for high-data rate transmission. One drawback of OFDM is the high Peak-to-average Power Ratio (PAPR). A novel scheme referred to as Quantization Clipping (QC) is proposed to solve the high PAPR problem in OFDM-QAM system. For the QC scheme, we preset several different clipping thresholds, and then quantize the input signal to a group of preset thresholds. Simulation results show that the new scheme can significantly improve the BER performance while guaranteeing the improvement in the PAPR performance of the OFDM-QAM system.","PeriodicalId":213716,"journal":{"name":"The Journal of Information and Computational Science","volume":"273 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115819997","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, an combined evaluation process to evaluate the value of substation was proposed. Firstly, a substation function index system was established with consideration of the function structure and features of substation. Secondly, the Analytic Hierarchy Process (AHP) and entropy method were separately used to calculate the subjective and objective weights of the function indexes. Thirdly, the sum of squares of deviations method and Particle Swarm Optimization (PSO) method were used to get the function indexes’ combined weights. At last, the evaluation model was formed by function index compared with the cost index. The substation design data were used to test the evaluation model, the results showed it was feasible.
{"title":"Substation Design Optimization Research Based on PSO and Value Index Method","authors":"Jinchao Li, H. Yang","doi":"10.12733/JICS20105571","DOIUrl":"https://doi.org/10.12733/JICS20105571","url":null,"abstract":"In this paper, an combined evaluation process to evaluate the value of substation was proposed. Firstly, a substation function index system was established with consideration of the function structure and features of substation. Secondly, the Analytic Hierarchy Process (AHP) and entropy method were separately used to calculate the subjective and objective weights of the function indexes. Thirdly, the sum of squares of deviations method and Particle Swarm Optimization (PSO) method were used to get the function indexes’ combined weights. At last, the evaluation model was formed by function index compared with the cost index. The substation design data were used to test the evaluation model, the results showed it was feasible.","PeriodicalId":213716,"journal":{"name":"The Journal of Information and Computational Science","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126211631","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}
Quality of software requirements specications are key for developing high assurance software system. However, as there are lots of work have been done to ensure the quality of software system, most of these work are limited in treating software requirements specications manually, so we still lacking a trustworthy way to guarantee the quality of software automatically. On the basis of an abstract state transition model, we discuss an abstract state transition system which we will used in the checking of domain properties, some properties of CTL formula we will used in patterns are discussed. By classifying domain patterns into trigger relation patterns, response relations patterns and sequence patterns, some properties of these patterns are also discussed in detail.
{"title":"On Using Domain Patterns to Validate Domain Related Properties of Software Requirements Specifications","authors":"Beibei Wen, Xuefeng Zhu","doi":"10.12733/JICS20104785","DOIUrl":"https://doi.org/10.12733/JICS20104785","url":null,"abstract":"Quality of software requirements specications are key for developing high assurance software system. However, as there are lots of work have been done to ensure the quality of software system, most of these work are limited in treating software requirements specications manually, so we still lacking a trustworthy way to guarantee the quality of software automatically. On the basis of an abstract state transition model, we discuss an abstract state transition system which we will used in the checking of domain properties, some properties of CTL formula we will used in patterns are discussed. By classifying domain patterns into trigger relation patterns, response relations patterns and sequence patterns, some properties of these patterns are also discussed in detail.","PeriodicalId":213716,"journal":{"name":"The Journal of Information and Computational Science","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130732816","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}
A kind of risk evaluation method based on Analytic Hierarchy Process (AHP) and improved BP neural network is proposed in this paper. Importance degree of risk evaluation indexes is sorted by using the analytic hierarchy process and the risk evaluation index system is simplified, and then the simplified index acts as the input of improved BP neural network to evaluate the risk. This method simplifies the network model and improves the performance and calculation accuracy of the network. The risk of the power grid project is evaluated based on this method, indicating that this method is feasible and effective for the risk evaluation of the power grid project.
{"title":"Risk Evaluation of Power Grid Project Based on Analytic Hierarchy Process and Improved BP Neural Network","authors":"Shuguo Zhang","doi":"10.12733/JICS20105585","DOIUrl":"https://doi.org/10.12733/JICS20105585","url":null,"abstract":"A kind of risk evaluation method based on Analytic Hierarchy Process (AHP) and improved BP neural network is proposed in this paper. Importance degree of risk evaluation indexes is sorted by using the analytic hierarchy process and the risk evaluation index system is simplified, and then the simplified index acts as the input of improved BP neural network to evaluate the risk. This method simplifies the network model and improves the performance and calculation accuracy of the network. The risk of the power grid project is evaluated based on this method, indicating that this method is feasible and effective for the risk evaluation of the power grid project.","PeriodicalId":213716,"journal":{"name":"The Journal of Information and Computational Science","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129661322","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 systematically discuss the financial characteristics of the companies that get the loans from the bank under different financial ecological environments with Exploratory Data Analysis. Based on our prior work which introduced the designed Exploratory Data Analysis integrating visualization, outliers processing and Principal Component Analysis et al. [1], we get that, the bank pays more attention to the company’s solvency in credit decision under different financial ecological environments. Moreover, the company’s cash flow is more important for the bank in bad financial ecological environment, while the company’s growth potential in good financial ecological environment. This study presents a novel schema for accounting data analysis with Exploratory Data Analysis in a systematical way. The result is useful for the bank to get better credit decision with less risk. It also illustrates that it is necessary for the government to build better financial ecological environment to develop the economy.
{"title":"Exploratory Data Analysis of Bank's Credit Decision-making ⋆","authors":"Guangming Gong, Jing Huang, En-Li Shen","doi":"10.12733/JICS20105655","DOIUrl":"https://doi.org/10.12733/JICS20105655","url":null,"abstract":"In this paper, we systematically discuss the financial characteristics of the companies that get the loans from the bank under different financial ecological environments with Exploratory Data Analysis. Based on our prior work which introduced the designed Exploratory Data Analysis integrating visualization, outliers processing and Principal Component Analysis et al. [1], we get that, the bank pays more attention to the company’s solvency in credit decision under different financial ecological environments. Moreover, the company’s cash flow is more important for the bank in bad financial ecological environment, while the company’s growth potential in good financial ecological environment. This study presents a novel schema for accounting data analysis with Exploratory Data Analysis in a systematical way. The result is useful for the bank to get better credit decision with less risk. It also illustrates that it is necessary for the government to build better financial ecological environment to develop the economy.","PeriodicalId":213716,"journal":{"name":"The Journal of Information and Computational Science","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125904653","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 order to facilitate periodic membrane oscillations in brain, continuous attractors with periodic shape has been studied in the CANN. This paper will extend one-dimensional continuous attractors with periodic shape to two-dimensional ones in Recurrent Neural Networks (RNN). Under a certain condition, the RNN can possess the stable and unstable two-dimensional (2D) continuous attractors. Finally, a example is used to illustrate the 2D periodic continuous attractors.
{"title":"Two-dimensional Continuous Attractors of Recurrent Neural Networks","authors":"Li Yan, Weigen Wu, Xing Yin","doi":"10.12733/JICS20105643","DOIUrl":"https://doi.org/10.12733/JICS20105643","url":null,"abstract":"In order to facilitate periodic membrane oscillations in brain, continuous attractors with periodic shape has been studied in the CANN. This paper will extend one-dimensional continuous attractors with periodic shape to two-dimensional ones in Recurrent Neural Networks (RNN). Under a certain condition, the RNN can possess the stable and unstable two-dimensional (2D) continuous attractors. Finally, a example is used to illustrate the 2D periodic continuous attractors.","PeriodicalId":213716,"journal":{"name":"The Journal of Information and Computational Science","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122874188","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：