基于深度学习的人脸识别技术以数据为驱动,对输入图像的质量要求较高。在铁路刷脸进/出站场景下,为滤除因各种因素导致的成像异常的人脸图像,提升人脸识别精度,文章研究人脸图像正常的特征分布,通过知识迁移,提出无须针对异常样本建模...基于深度学习的人脸识别技术以数据为驱动,对输入图像的质量要求较高。在铁路刷脸进/出站场景下,为滤除因各种因素导致的成像异常的人脸图像,提升人脸识别精度,文章研究人脸图像正常的特征分布,通过知识迁移,提出无须针对异常样本建模的人脸图像异常检测算法。理想情况下,该算法对人脸图像异常检测的ROC曲线下面积(AUROC,Aera Under Receiver Operating Characteristic)可达到0.979。实验结果表明,该算法在计算精度与运行成本的组合上具有较高的自由度,可实现不同场景、硬件条件下的算法适配,为优化旅客人脸识别的输入环节,提高各场景下的旅客人脸识别率提供了技术支撑。展开更多
In order to improve the transmission accuracy and efficiency of sensing and actuating signals in Internet of Things （loT） and ensure the system stability, an adaptive resource allocation algorithm is proposed, which...In order to improve the transmission accuracy and efficiency of sensing and actuating signals in Internet of Things （loT） and ensure the system stability, an adaptive resource allocation algorithm is proposed, which dynami- cally assigns the network bandwidth and priority among components according to their signals＇ frequency domain characteristics. A remote sensed and controlled unmanned ground vehicle （UGV） path tracking test-bed was devel- oped and multiple UGV＇s tracking error signals were measured in the simulation for performance evaluation. Results show that with the same network bandwidth constraints, the proposed algorithm can reduce,, the accumulated and maximum errors of UGV path tracking by over 60% compared with the conventional static algorithm.展开更多
n this paper an adaptive robust algorithm for pole-placement design is proposed. It consists of the refined--optimal IV parameter estimator and a robust pole--placement controller. The robustness of the algorithm mean...n this paper an adaptive robust algorithm for pole-placement design is proposed. It consists of the refined--optimal IV parameter estimator and a robust pole--placement controller. The robustness of the algorithm means that the output of the controlled plant can be stabilized in the presence of unmodelled dynamics and bounded unmeasurable output noise. Simulation results show the effeciency of the algorithm.展开更多
To preserve the original signal as much as possible and filter random noises as many as possible in image processing,a threshold optimization-based adaptive template filtering algorithm was proposed.Unlike conventiona...To preserve the original signal as much as possible and filter random noises as many as possible in image processing,a threshold optimization-based adaptive template filtering algorithm was proposed.Unlike conventional filters whose template shapes and coefficients were fixed,multi-templates were defined and the right template for each pixel could be matched adaptively based on local image characteristics in the proposed method.The superiority of this method was verified by former results concerning the matching experiment of actual image with the comparison of conventional filtering methods.The adaptive search ability of immune genetic algorithm with the elitist selection and elitist crossover(IGAE) was used to optimize threshold t of the transformation function,and then combined with wavelet transformation to estimate noise variance.Multi-experiments were performed to test the validity of IGAE.The results show that the filtered result of t obtained by IGAE is superior to that of t obtained by other methods,IGAE has a faster convergence speed and a higher computational efficiency compared with the canonical genetic algorithm with the elitism and the immune algorithm with the information entropy and elitism by multi-experiments.展开更多
With its rapid development in the wireless markets, IEEE 802.11 WLAN is experiencing a huge popularity. However, due to the limitation of frequency bandwidth of WLANs, it is essential that the available radio resource...With its rapid development in the wireless markets, IEEE 802.11 WLAN is experiencing a huge popularity. However, due to the limitation of frequency bandwidth of WLANs, it is essential that the available radio resource should be fully utilized to offer different services to multiple users. In order to maximize system throughput while still guaranteeing the fairness among users, a proportional fairness based algorithm is proposed in this work. Since most of the previous resource allocation algorithms were simply based on the channel conditions without taking into account user's demand, in this paper, we introduce the theory of fuzzy synthetic evaluation(FSE) which also allows us to consider user's demand as an important factor. As such, the fairness among users can be improved based on different users' requirements for services. In addition, a channel state information based rate adaptation scheme is also proposed. Through simulation studies, the results clearly validate that our proposed scheme shows advantages on providing user fairness while still improving the system throughput.展开更多
In open normative multi-agent communities,an agent is not usually and explicitly given the norms of the host agents.Thus,when it is not able to adapt the communities's norms,it is totally deprived of accessing res...In open normative multi-agent communities,an agent is not usually and explicitly given the norms of the host agents.Thus,when it is not able to adapt the communities's norms,it is totally deprived of accessing resources and services from the host.Such circumstance severely affects its performance resulting in failure to achieve its goal.Consequently,this study attempts to overcome this deficiency by proposing a technique that enables an agent to detect the host's potential norms via self-enforcement and update its norms even in the absence of sanctions from a third-party.The authors called this technique as the potential norms detection technique(PNDT).The PNDT consists of five components: Agent's belief base; observation process; potential norms mining algorithm(PNMA);verification process; and updating process.The authors demonstrate the operation of the PNMA algorithm by testing it on a typical scenario and analyzing the results on several perspectives.The tests' results show that the PNDT performs satisfactorily albeit the success rate depends on the environment variables settings.展开更多
Mobility and resource-limitedness pose challenging issues to service configuration for quality of service (QoS) management in ubiquitous computing environments. Previous configuration approaches, such as static resour...Mobility and resource-limitedness pose challenging issues to service configuration for quality of service (QoS) management in ubiquitous computing environments. Previous configuration approaches, such as static resource reservation, dynamic resource allocation and single service composition are not valid in the environments. In this study, we present an adaptive service configuration approach. Firstly, we reduce the dynamic configuration process to a control model which aims to achieve the variation of critical QoS on minimal level with less resource cost. Secondly, to deal with different QoS variations, we design two configuration strategies—service chain reconfiguration and QoS parameter adjustment—and implement them based on fuzzy logic control theory. Finally, a configuration algorithm is developed to flexibly employ the two configuration strategies in tune with the error of critical QoS in configuration process. The results of simulation experiments suggest that our approach outper- forms existing configuration approaches in both QoS improvement and resource utilization.展开更多
文摘基于深度学习的人脸识别技术以数据为驱动,对输入图像的质量要求较高。在铁路刷脸进/出站场景下,为滤除因各种因素导致的成像异常的人脸图像,提升人脸识别精度,文章研究人脸图像正常的特征分布,通过知识迁移,提出无须针对异常样本建模的人脸图像异常检测算法。理想情况下,该算法对人脸图像异常检测的ROC曲线下面积(AUROC,Aera Under Receiver Operating Characteristic)可达到0.979。实验结果表明,该算法在计算精度与运行成本的组合上具有较高的自由度,可实现不同场景、硬件条件下的算法适配,为优化旅客人脸识别的输入环节,提高各场景下的旅客人脸识别率提供了技术支撑。
基金Supported by Natural Science Foundation of Tianjin (No. 07JCZDJC05800)Science and Technology Supporting Plan of Tianjin (No. 09ZCKFGX29200)
文摘In order to improve the transmission accuracy and efficiency of sensing and actuating signals in Internet of Things （loT） and ensure the system stability, an adaptive resource allocation algorithm is proposed, which dynami- cally assigns the network bandwidth and priority among components according to their signals＇ frequency domain characteristics. A remote sensed and controlled unmanned ground vehicle （UGV） path tracking test-bed was devel- oped and multiple UGV＇s tracking error signals were measured in the simulation for performance evaluation. Results show that with the same network bandwidth constraints, the proposed algorithm can reduce,, the accumulated and maximum errors of UGV path tracking by over 60% compared with the conventional static algorithm.
文摘n this paper an adaptive robust algorithm for pole-placement design is proposed. It consists of the refined--optimal IV parameter estimator and a robust pole--placement controller. The robustness of the algorithm means that the output of the controlled plant can be stabilized in the presence of unmodelled dynamics and bounded unmeasurable output noise. Simulation results show the effeciency of the algorithm.
基金Project(20040533035) supported by the National Research Foundation for the Doctoral Program of Higher Education of ChinaProject (60874070) supported by the National Natural Science Foundation of China
文摘To preserve the original signal as much as possible and filter random noises as many as possible in image processing,a threshold optimization-based adaptive template filtering algorithm was proposed.Unlike conventional filters whose template shapes and coefficients were fixed,multi-templates were defined and the right template for each pixel could be matched adaptively based on local image characteristics in the proposed method.The superiority of this method was verified by former results concerning the matching experiment of actual image with the comparison of conventional filtering methods.The adaptive search ability of immune genetic algorithm with the elitist selection and elitist crossover(IGAE) was used to optimize threshold t of the transformation function,and then combined with wavelet transformation to estimate noise variance.Multi-experiments were performed to test the validity of IGAE.The results show that the filtered result of t obtained by IGAE is superior to that of t obtained by other methods,IGAE has a faster convergence speed and a higher computational efficiency compared with the canonical genetic algorithm with the elitism and the immune algorithm with the information entropy and elitism by multi-experiments.
基金partially supported by the Academy of Finland (Decision No. 284748, 288473)
文摘With its rapid development in the wireless markets, IEEE 802.11 WLAN is experiencing a huge popularity. However, due to the limitation of frequency bandwidth of WLANs, it is essential that the available radio resource should be fully utilized to offer different services to multiple users. In order to maximize system throughput while still guaranteeing the fairness among users, a proportional fairness based algorithm is proposed in this work. Since most of the previous resource allocation algorithms were simply based on the channel conditions without taking into account user's demand, in this paper, we introduce the theory of fuzzy synthetic evaluation(FSE) which also allows us to consider user's demand as an important factor. As such, the fairness among users can be improved based on different users' requirements for services. In addition, a channel state information based rate adaptation scheme is also proposed. Through simulation studies, the results clearly validate that our proposed scheme shows advantages on providing user fairness while still improving the system throughput.
文摘In open normative multi-agent communities,an agent is not usually and explicitly given the norms of the host agents.Thus,when it is not able to adapt the communities's norms,it is totally deprived of accessing resources and services from the host.Such circumstance severely affects its performance resulting in failure to achieve its goal.Consequently,this study attempts to overcome this deficiency by proposing a technique that enables an agent to detect the host's potential norms via self-enforcement and update its norms even in the absence of sanctions from a third-party.The authors called this technique as the potential norms detection technique(PNDT).The PNDT consists of five components: Agent's belief base; observation process; potential norms mining algorithm(PNMA);verification process; and updating process.The authors demonstrate the operation of the PNMA algorithm by testing it on a typical scenario and analyzing the results on several perspectives.The tests' results show that the PNDT performs satisfactorily albeit the success rate depends on the environment variables settings.
基金Project (No. 05SN07114) supported by the International Cooperation Project of the Shanghai Science and Technology Commission of China and the National Research Council of Canada
文摘Mobility and resource-limitedness pose challenging issues to service configuration for quality of service (QoS) management in ubiquitous computing environments. Previous configuration approaches, such as static resource reservation, dynamic resource allocation and single service composition are not valid in the environments. In this study, we present an adaptive service configuration approach. Firstly, we reduce the dynamic configuration process to a control model which aims to achieve the variation of critical QoS on minimal level with less resource cost. Secondly, to deal with different QoS variations, we design two configuration strategies—service chain reconfiguration and QoS parameter adjustment—and implement them based on fuzzy logic control theory. Finally, a configuration algorithm is developed to flexibly employ the two configuration strategies in tune with the error of critical QoS in configuration process. The results of simulation experiments suggest that our approach outper- forms existing configuration approaches in both QoS improvement and resource utilization.
