complexsystem configuration problems are the problems of appropriately assigning system parameter values for optimizing some aspect of complexsystem performance. In this paper, we first cast complexsystem configura...
详细信息
complexsystem configuration problems are the problems of appropriately assigning system parameter values for optimizing some aspect of complexsystem performance. In this paper, we first cast complexsystem configuration problems as mixed-variable parameter optimization problems where mensurable system simulation responses are used for evaluation. Then we present a simulation-based ant colony optimization algorithm (sACO MV ) to tackle the problems. In sACO MV the decision variables of the complexsystem configuration problems can be clearly declared as continuous, ordinal, or categorical and let the algorithm treat them adequately. Finally, sACO MV is tested on mixed-variable complex engineering system configuration problems. The effectiveness and robustness of sACO MV are demonstrated by the comparisons with results from the literature.
This paper proposes an approach to moving vehicle tracking in surveillance videos based on conditional random fields(CRF).The key idea is to integrate a variety of relevant knowledge about vehicle tracking into a unif...
详细信息
This paper proposes an approach to moving vehicle tracking in surveillance videos based on conditional random fields(CRF).The key idea is to integrate a variety of relevant knowledge about vehicle tracking into a uniform probabilistic framework by using the CRF *** this work,the CRF model integrates spatial and temporal contextual information of vehicle motion,and the appearance information of the *** approximate inference algorithm,loopy belief propagation,is used to recursively estimate the vehicle region from the history of observed ***,the background model is updated adaptively to cope with non-stationary background *** results show that the proposed approach is able to accurately track moving vehicles in monocular image ***,region-level tracking realizes precise localization of vehicles.
Space launch is a complex project with high risk, and failure of space launch may cause a great loss to people's life, property and important facilities. Thus a resonable and effective emergency response program i...
详细信息
ISBN:
(纸本)9781479960590
Space launch is a complex project with high risk, and failure of space launch may cause a great loss to people's life, property and important facilities. Thus a resonable and effective emergency response program is critical and important for space launch. First, a Decision Network Planning (DNP) method is proposed to describe logic relations of emergency response procedures, based on which the logical reasonability and rigor, coordination of several involved departments, timeliness of emergency measures and sufficiency of resources guarantee are evaluated. Then, the critical path and resource guaranteed rate are calculated to analyze the degree of control in the emergency process of space launch failure. Last, a case of filling leakage is used to show the helpfulness of the proposed method.
In this paper, a novel vision-based method for roll angle estimation of the robot is proposed. Inspired by biological visual cortex, scales and shapes of local patterns whose directions may contribute to the judgment ...
详细信息
In this paper, a novel vision-based method for roll angle estimation of the robot is proposed. Inspired by biological visual cortex, scales and shapes of local patterns whose directions may contribute to the judgment of the scenes' gravity and horizon are determined. On this basis, a local direction detector is designed and all the detected local directions in an image are summed up into the direction function. Then the precise directions of gravity and horizon may be easily obtained by using statistical techniques. Experiments illustrate the generalization and effectiveness of the proposed method.
In this paper,an effective approach to vehicle license plate recognition based on Extremal Regions(ERs) and Self-adaptive Evolutionary Extreme Learning Machine(Sa EELM) is *** the license plate detection step,some com...
详细信息
In this paper,an effective approach to vehicle license plate recognition based on Extremal Regions(ERs) and Self-adaptive Evolutionary Extreme Learning Machine(Sa EELM) is *** the license plate detection step,some computations including morphological operations,various filters,different contours and validations are sequentially performed to extract some image regions as candidate license ***,accurate character segmentation is achieved through a proper selection of *** the character recognition step,the HOG(histogram of oriented gradients) feature vector in each character region is extracted,and then the characters are recognized using an offline trained pattern classifier of Sa *** results show that our approach works quite well in complex traffic environments.
Although optimal fusion algorithms of systemstate estimation have been proposed and studied for FAST in the past years, multi-sample-rate measurements and observation time-delay have always been restrictive factors t...
详细信息
Although optimal fusion algorithms of systemstate estimation have been proposed and studied for FAST in the past years, multi-sample-rate measurements and observation time-delay have always been restrictive factors to derive a glorious fusion results for state estimation. Based on the optimal fusion algorithm in the minimum mean square error sense, an iterated extended Kalman filter is investigated for discrete-time systems with multi-sample-rate measurements and delayed measurements in this paper, re-sampling observations from high sampling frequency channel and reducing the usage rate of observations with greater noises to investigate the estimation problem. The performance and improvement is clearly demonstrated through the numerical example. This study is manifestly advantageous for the feed supporting system of FAST.
This paper proposes a simple but effective bio-inspired approach for skew detection of different kinds of images including nature images, documents, paintings etc., which requires no parameter tuning. Without relying ...
详细信息
This paper proposes a simple but effective bio-inspired approach for skew detection of different kinds of images including nature images, documents, paintings etc., which requires no parameter tuning. Without relying on local visual cues, the proposed approach exploits the global statistics of an image. Orientation perceptron is designed in the inspiration of biological simple cells for local orientation detection. Statistics of their outputs are processed and then transferred by orientation transform into a curve whose maximum value is used to determine the skew angle. The effectiveness of the proposed approach is verified by experiments.
The intersection models,such as delay models and queuing length models,are the foundations of optimal signal timing for urban *** of the field data of intersection,it is highly difficult to calibrate parameters of the...
详细信息
The intersection models,such as delay models and queuing length models,are the foundations of optimal signal timing for urban *** of the field data of intersection,it is highly difficult to calibrate parameters of the intersection *** to the effects of intersection topology,channelization and traffic conditions on these models,obviously it is impossible for single model to be suitable for optimal control of various *** is emerging technique for Intelligent Traffic systems(ITS).It provides an effective means for problem-solving of complex traffic issues by constructing artificial system which is consistent with corresponding real *** on ACP approach,we propose a self-learning optimal control strategy for typical *** this approach,optimal control policy is found by systematic interaction with the traffic environment,so as to adapt dynamic traffic conditions and different intersection ***,according to traffic characteristics analysis of intersection,joint control of all approaches can be reduced to optimal control of only one ***,the computational and storage complexities are decreased *** experiment results demonstrate that our approach has considerably lower average delay and higher traffic capacity of intersection than these optimal control methods which are respectively based on HCM2000 and Webster models.
This paper addresses the problem of task allocation in real-time distributed systems with the goal of maximizing the system reliability, it has been shown to be NP-hard. Many studies have been made to solve this probl...
详细信息
This paper addresses the problem of task allocation in real-time distributed systems with the goal of maximizing the system reliability, it has been shown to be NP-hard. Many studies have been made to solve this problem without considering the real-time constraint. We first take account of the deadline constraint in order to formulate this problem, and then propose an improved simulated annealing algorithm call adaptive memory-based simulated annealing (AMSA) to solve the problem. The AMSA introduces adaptive factors to reduce the total computation time, and adds memory function to save the recently visited solutions and best solution by now. The effectiveness of AMSA is evaluated by comparing with traditional simulated annealing algorithm. The results show that AMSA can produce “good enough” solution in much less time.
Revealing underlying causal structure in social media is critical to understanding how users interact, on which a lot of security intelligence applications can be built. Existing causal inference methods for social me...
详细信息
Revealing underlying causal structure in social media is critical to understanding how users interact, on which a lot of security intelligence applications can be built. Existing causal inference methods for social media usually rely on limited explicit causal context, pre-assume certain user interaction model, or neglect the nonlinear nature of social interaction, which could lead to bias estimations of causality. Inspired from recent advance in causality detection in complex ecosystems, we propose to take advantage of a novel nonlinear state space reconstruction based approach, namely Convergent Cross Mapping, to perform causal inference in social media. Experimental results on real world social media datasets show the effectiveness of the proposed method in causal inference and user behavior prediction in social media.
暂无评论