In a competitive digital age where data volumes are increasing with time, the ability to extract meaningful knowledge from high-dimensional data using machine learning (ML) and data mining (DM) techniques and making d...In a competitive digital age where data volumes are increasing with time, the ability to extract meaningful knowledge from high-dimensional data using machine learning (ML) and data mining (DM) techniques and making decisions based on the extracted knowledge is becoming increasingly important in all business domains. Nevertheless, high-dimensional data remains a major challenge for classification algorithms due to its high computational cost and storage requirements. The 2016 Demographic and Health Survey of Ethiopia (EDHS 2016) used as the data source for this study which is publicly available contains several features that may not be relevant to the prediction task. In this paper, we developed a hybrid multidimensional metrics framework for predictive modeling for both model performance evaluation and feature selection to overcome the feature selection challenges and select the best model among the available models in DM and ML. The proposed hybrid metrics were used to measure the efficiency of the predictive models. Experimental results show that the decision tree algorithm is the most efficient model. The higher score of HMM (m, r) = 0.47 illustrates the overall significant model that encompasses almost all the user’s requirements, unlike the classical metrics that use a criterion to select the most appropriate model. On the other hand, the ANNs were found to be the most computationally intensive for our prediction task. Moreover, the type of data and the class size of the dataset (unbalanced data) have a significant impact on the efficiency of the model, especially on the computational cost, and the interpretability of the parameters of the model would be hampered. And the efficiency of the predictive model could be improved with other feature selection algorithms (especially hybrid metrics) considering the experts of the knowledge domain, as the understanding of the business domain has a significant impact.展开更多
Remotely sensing images are now available for monitoring vegetation dynamics over large areas.In this paper,an improved logistic model that combines double logistic model and global function was developed.Using this m...Remotely sensing images are now available for monitoring vegetation dynamics over large areas.In this paper,an improved logistic model that combines double logistic model and global function was developed.Using this model with SPOT/NDVI data,three key vegetation phenology metrics,the start of growing season (SOS),the end of growing season (EOS) and the length of growing season (LOS),were extracted and mapped in the Changbai Mountains,and the relationship between the key phenology metrics and elevation were established.Results show that average SOS of forest,cropland and grassland in the Changbai Mountains are on the 119th,145th,and 133rd day of year,respectively.The EOS of forest and grassland are similar,with the average on the 280th and 278th,respectively.In comparison,average EOS of the cropland is relatively earlier.The LOS of forest is mainly from the 160th to 180th,that of the grassland extends from the 140th to the 160th,and that of cropland stretches from the 110th to the 130th.As the latitude increases for the same land cover in the study area,the SOS significantly delays and the EOS becomes earlier.The SOS delays approximately three days as the elevation increases 100 m in the areas with elevation higher than 900 m above sea level (a.s.l.).The EOS is slightly earlier as the elevation increases especially in the areas with elevation below 1200 m a.s.l.The LOS shortens approximately four days as the elevation increases 100 m in the areas with elevation higher than 900 m a.s.l.The relationships between vegetation phenology metrics and elevation may be greatly influenced by the land covers.Validation by comparing with the field data and previous research results indicates that the improved logistic model is reliable and effective for extracting vegetation phenology metrics.展开更多
The algorithm of fingerprint constructing for still images based on weighted image structure model is proposed. The error correcting codes that are perfect in weighted Hamming metric are used as a base for fingerprint...The algorithm of fingerprint constructing for still images based on weighted image structure model is proposed. The error correcting codes that are perfect in weighted Hamming metric are used as a base for fingerprint constructing.展开更多
双母管式机组较为广泛地应用于热电联产机组中,但由于多炉多机和2根大容量母管互相影响,导致热电负荷跟踪不及时,母管压力控制自动化水平较低。为此,针对双母管系统的非线性、强耦合、大迟延特性,设计了基于广义扩张状态观测器的多模型...双母管式机组较为广泛地应用于热电联产机组中,但由于多炉多机和2根大容量母管互相影响,导致热电负荷跟踪不及时,母管压力控制自动化水平较低。为此,针对双母管系统的非线性、强耦合、大迟延特性,设计了基于广义扩张状态观测器的多模型预测控制(generalized extended state observer based muti-model predictive control,GESOMMPC)方法。首先,建立了基于间隙度量(gap-metric)的多模型控制对象用于逼近非线性系统;其次,设计了扩张状态观测器估计系统耦合的集总扰动,并作为前馈信号输入到预测控制器中;最后,设计基于扰动前馈的多模型预测控制器实现对双母管系统的控制。实验结果表明,相对于PID方法,所提方法在满足电热负荷的同时,可以在允许范围内保持母管压力稳定,且动态偏差更小,过渡过程时间更短。展开更多
基金This work is supported by the National Natural Science Foundation of China （NSFC, nos. 61340046）, the National High Technology Research and Development Programme of China （863 Programme, no. 2006AA04Z247）, the Scientific and Technical Innovation Commission of Shenzhen Municipality （nos. JCYJ20130331144631730）, and the Specialized Research Fund for the Doctoral Programme of Higher Education （SRFDP, no. 20130001110011）.
文摘In a competitive digital age where data volumes are increasing with time, the ability to extract meaningful knowledge from high-dimensional data using machine learning (ML) and data mining (DM) techniques and making decisions based on the extracted knowledge is becoming increasingly important in all business domains. Nevertheless, high-dimensional data remains a major challenge for classification algorithms due to its high computational cost and storage requirements. The 2016 Demographic and Health Survey of Ethiopia (EDHS 2016) used as the data source for this study which is publicly available contains several features that may not be relevant to the prediction task. In this paper, we developed a hybrid multidimensional metrics framework for predictive modeling for both model performance evaluation and feature selection to overcome the feature selection challenges and select the best model among the available models in DM and ML. The proposed hybrid metrics were used to measure the efficiency of the predictive models. Experimental results show that the decision tree algorithm is the most efficient model. The higher score of HMM (m, r) = 0.47 illustrates the overall significant model that encompasses almost all the user’s requirements, unlike the classical metrics that use a criterion to select the most appropriate model. On the other hand, the ANNs were found to be the most computationally intensive for our prediction task. Moreover, the type of data and the class size of the dataset (unbalanced data) have a significant impact on the efficiency of the model, especially on the computational cost, and the interpretability of the parameters of the model would be hampered. And the efficiency of the predictive model could be improved with other feature selection algorithms (especially hybrid metrics) considering the experts of the knowledge domain, as the understanding of the business domain has a significant impact.
基金Under the auspices of Major State Basic Research Development Program of China (No.2009CB426305)Cultivation Foundation of Science and Technology Innovation Platform of Northeast Normal University (No.106111065202)
文摘Remotely sensing images are now available for monitoring vegetation dynamics over large areas.In this paper,an improved logistic model that combines double logistic model and global function was developed.Using this model with SPOT/NDVI data,three key vegetation phenology metrics,the start of growing season (SOS),the end of growing season (EOS) and the length of growing season (LOS),were extracted and mapped in the Changbai Mountains,and the relationship between the key phenology metrics and elevation were established.Results show that average SOS of forest,cropland and grassland in the Changbai Mountains are on the 119th,145th,and 133rd day of year,respectively.The EOS of forest and grassland are similar,with the average on the 280th and 278th,respectively.In comparison,average EOS of the cropland is relatively earlier.The LOS of forest is mainly from the 160th to 180th,that of the grassland extends from the 140th to the 160th,and that of cropland stretches from the 110th to the 130th.As the latitude increases for the same land cover in the study area,the SOS significantly delays and the EOS becomes earlier.The SOS delays approximately three days as the elevation increases 100 m in the areas with elevation higher than 900 m above sea level (a.s.l.).The EOS is slightly earlier as the elevation increases especially in the areas with elevation below 1200 m a.s.l.The LOS shortens approximately four days as the elevation increases 100 m in the areas with elevation higher than 900 m a.s.l.The relationships between vegetation phenology metrics and elevation may be greatly influenced by the land covers.Validation by comparing with the field data and previous research results indicates that the improved logistic model is reliable and effective for extracting vegetation phenology metrics.
文摘The algorithm of fingerprint constructing for still images based on weighted image structure model is proposed. The error correcting codes that are perfect in weighted Hamming metric are used as a base for fingerprint constructing.
文摘双母管式机组较为广泛地应用于热电联产机组中,但由于多炉多机和2根大容量母管互相影响,导致热电负荷跟踪不及时,母管压力控制自动化水平较低。为此,针对双母管系统的非线性、强耦合、大迟延特性,设计了基于广义扩张状态观测器的多模型预测控制(generalized extended state observer based muti-model predictive control,GESOMMPC)方法。首先,建立了基于间隙度量(gap-metric)的多模型控制对象用于逼近非线性系统;其次,设计了扩张状态观测器估计系统耦合的集总扰动,并作为前馈信号输入到预测控制器中;最后,设计基于扰动前馈的多模型预测控制器实现对双母管系统的控制。实验结果表明,相对于PID方法,所提方法在满足电热负荷的同时,可以在允许范围内保持母管压力稳定,且动态偏差更小,过渡过程时间更短。
