Person re-identification （re-id） on robot platform is an important application for human-robot- interaction （HRI）, which aims at making the robot recognize the around persons in varying scenes. Although many effec...Person re-identification （re-id） on robot platform is an important application for human-robot- interaction （HRI）, which aims at making the robot recognize the around persons in varying scenes. Although many effective methods have been proposed for surveillance re-id in recent years, re-id on robot platform is still a novel unsolved problem. Most existing methods adapt the supervised metric learning offline to improve the accuracy. However, these methods can not adapt to unknown scenes. To solve this problem, an online re-id framework is proposed. Considering that robotics can afford to use high-resolution RGB-D sensors and clear human face may be captured, face information is used to update the metric model. Firstly, the metric model is pre-trained offline using labeled data. Then during the online stage, we use face information to mine incorrect body matching pairs which are collected to update the metric model online. In addition, to make full use of both appearance and skeleton information provided by RGB-D sensors, a novel feature funnel model （FFM） is proposed. Comparison studies show our approach is more effective and adaptable to varying environments.展开更多
Climatic and atmospheric properties vary significantly within a small area for a topographically diverse region like Nepal.Remote sensing can be used for large-scale monitoring of atmospheric parameters in such divers...Climatic and atmospheric properties vary significantly within a small area for a topographically diverse region like Nepal.Remote sensing can be used for large-scale monitoring of atmospheric parameters in such diverse terrains.This work evaluates the Landsat-based METRIC(Mapping Evapotranspiration at High Resolution with Internalized Calibration)model for estimating Evapotranspiration(ET)in Nepal.The slope and aspect of terrain are accounted for in our implementation,making the model suitable for regions with topographical variations.The estimations obtained from the model were compared with ground-based measurements.The root-meansquare error for hourly ET(daily ET)was 0.06 mm h-1(1.24 mm d-1),while the mean bias error was0.03 mm h-1(0.29 mm d-1).These results are comparable with results from other studies in the literature that have used the METRIC model for different regions of the world.Thus,this work validates the applicability of the METRIC model for ET estimation in a mountainous area like Nepal.Further,this implementation provides ET estimation at a very high resolution of 30 m compared to the best available resolution of 5 km in earlier works,without compromising on the accuracy.ET estimation with high resolution over a large region in Nepal has applications in agricultural planning and monitoring,among others.展开更多
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
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Person re-identification （re-id） on robot platform is an important application for human-robot- interaction （HRI）, which aims at making the robot recognize the around persons in varying scenes. Although many effective methods have been proposed for surveillance re-id in recent years, re-id on robot platform is still a novel unsolved problem. Most existing methods adapt the supervised metric learning offline to improve the accuracy. However, these methods can not adapt to unknown scenes. To solve this problem, an online re-id framework is proposed. Considering that robotics can afford to use high-resolution RGB-D sensors and clear human face may be captured, face information is used to update the metric model. Firstly, the metric model is pre-trained offline using labeled data. Then during the online stage, we use face information to mine incorrect body matching pairs which are collected to update the metric model online. In addition, to make full use of both appearance and skeleton information provided by RGB-D sensors, a novel feature funnel model （FFM） is proposed. Comparison studies show our approach is more effective and adaptable to varying environments.
基金funded by the Second Tibetan Plateau Scientific Expedition and Research Program grant number2019QZKK0103the Strategic Priority Research Program of the Chinese Academy of Sciences grant number XDA20060101the National Natural Science Foundation of China grant numbers 41830650,91737205,and 91837208。
文摘Climatic and atmospheric properties vary significantly within a small area for a topographically diverse region like Nepal.Remote sensing can be used for large-scale monitoring of atmospheric parameters in such diverse terrains.This work evaluates the Landsat-based METRIC(Mapping Evapotranspiration at High Resolution with Internalized Calibration)model for estimating Evapotranspiration(ET)in Nepal.The slope and aspect of terrain are accounted for in our implementation,making the model suitable for regions with topographical variations.The estimations obtained from the model were compared with ground-based measurements.The root-meansquare error for hourly ET(daily ET)was 0.06 mm h-1(1.24 mm d-1),while the mean bias error was0.03 mm h-1(0.29 mm d-1).These results are comparable with results from other studies in the literature that have used the METRIC model for different regions of the world.Thus,this work validates the applicability of the METRIC model for ET estimation in a mountainous area like Nepal.Further,this implementation provides ET estimation at a very high resolution of 30 m compared to the best available resolution of 5 km in earlier works,without compromising on the accuracy.ET estimation with high resolution over a large region in Nepal has applications in agricultural planning and monitoring,among others.
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.
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。
