In this paper, a multi-sensor based perception network for vehicle driving assistance is described. The network could reconstruct the 3D real world from the data obtained by the sensors, recognize dangerous occasions ...
详细信息
Gene selection, a key procedure of the discriminant analysis of microarray data, is to select the most informative genes from the whole gene set. Rough set theory is a mathematical tool for further reducing redundancy...
详细信息
This paper presents a novel unsupervised learning framework named image retrieval based on manifold learning and incorporate clustering. The dimensionality of image descriptors used in image retrieval applications is ...
详细信息
This paper presents a novel unsupervised learning framework named image retrieval based on manifold learning and incorporate clustering. The dimensionality of image descriptors used in image retrieval applications is quite high. Given a query image, our algorithm first makes use of manifold learning (LPP) for dimensionality reduction and manifold ranking algorithm to explore the relationship among all the data points in the feature space, and then measures relevance between the query and all the images in the database accordingly. Then we use the similarities among target images for improving the performance of the image retrieval systems by cluster-based retrieval of images by unsupervised learning. Our algorithm retrieves image clusters as retrieval results by applying K-means clustering algorithm to a collection of images collected by manifold ranking algorithm. Experimental results on a general-purpose image database show that our algorithm attains a significant improvement over existing systems.
When the high occlusion occurs in crowded scene, face detection is a better substitute for detecting pedestrian. In this paper, we present a novel crowd analysis method based on discriminative descriptor of faces and ...
详细信息
When the high occlusion occurs in crowded scene, face detection is a better substitute for detecting pedestrian. In this paper, we present a novel crowd analysis method based on discriminative descriptor of faces and support vector machine (SVM) ensemble. Through manipulating the input features in the same sample set, the different input features of faces are extracted to train two SVM classifiers. The classification scores of two generated classifiers are combined adaptively to make a collective decision. The first SVM, as the principal classifier gives out most of face hypotheses, while the second SVM serves as secondary one to rejecting the false positive. We present experiment to test the proposed method in crowded subway video, and the result shows that the SVM ensemble outperforms the single SVM in counting the pedestrian.
In the literature of traffic flow theory, the research on the effect on stability of traffic flow for cooperative driving control possesses an important significance. However, presently the the study on the problem is...
详细信息
ISBN:
(纸本)9781424435036
In the literature of traffic flow theory, the research on the effect on stability of traffic flow for cooperative driving control possesses an important significance. However, presently the the study on the problem is unsatisfactory because it is difficult to determine the impact qualitatively or quantitatively in real traffic experiment. In this paper, some efforts have been made for better understanding the effect on stability of traffic flow for cooperative driving control by investigating the stability for lattice traffic models, which are presented here by incorporating motion information of cars preceding. From linear stability analysis and direct simulations validation, we learn some properties of the effect on the stability and congestion waves by using the information of many other cars. First, cooperative driving behavior of many cars preceding can efficiently stabilize the traffic flow. Second, cooperative driving behavior of the cars nearby plays a prominent role in stability. Third, when the car number participating in cooperative driving policy exceeds a certain value, the congestion waves will disappear.
The coverage of Wireless Sensor Networks (WSNs) is one of the most important measurement criteria of Qos. Optimal coverage of sensors is propitious to the maximum possible utilization of the available sensors. It can ...
详细信息
Aiming at the deficiency of the current meridian diagnosis algorithms, SVM is applied to meridian diagnosis system. The system structure is described firstly, then the model selection of SVM is discussed in detail by ...
详细信息
Aiming at the deficiency of the current meridian diagnosis algorithms, SVM is applied to meridian diagnosis system. The system structure is described firstly, then the model selection of SVM is discussed in detail by taking chronic pharyngitis as an example: one-against-one method is used to realize multi-class;the problem of non-symmetrical samples of C-SVM is solved by giving positive and negative samples of different weights;a margin-based bound on generalization method is used to search parameters of the model. Finally, test results show that the classifier, which is realized and tested using vc++6.0, possess a very high recognition rate and can be applied to meridian diagnosis system.
Pairwise testing, which requires that every combination of valid values of each pair of system factors be covered by at lease one test case, plays an important role in software testing since many faults are caused by ...
详细信息
Pairwise testing, which requires that every combination of valid values of each pair of system factors be covered by at lease one test case, plays an important role in software testing since many faults are caused by unexpected 2-way interactions among system factors. In real systems, constraints usually exist between values, which means that some values cannot coexist in a valid test. Although meta-heuristic strategies like simulated annealing can generally discover smaller pairwise test suite in the presence of constraints, they may cost more time to perform search, compared with greedy algorithms. We propose a new method, improved extremal optimization, for constructing constrained pairwise test suites. Experimental results show that improved extremal optimization gives similar size of resulting pairwise test suite and yields a 13% reduction in solution time over simulated annealing.
In today's web, more and more software and applications are wrapped as services. However interactions between services are not always perfectly completed because of mismatches among them. service mediation and ada...
详细信息
In today's web, more and more software and applications are wrapped as services. However interactions between services are not always perfectly completed because of mismatches among them. service mediation and adaptation problems obtain increasingly concerns. In this paper, we propose an extension of interface automata, labelled interface automata, to illustrate mismatching services and adaptation. We characterize the problem by classifying different kinds of adaptation scenarios. Then we focus on how to use labelled interface automata to illustrate the building of adaption service between mismatching services.
Pairwise testing, which requires that every combination of valid values of each pair of system factors be covered by at lease one test case, plays an important role in software testing since many faults are caused by ...
详细信息
Pairwise testing, which requires that every combination of valid values of each pair of system factors be covered by at lease one test case, plays an important role in software testing since many faults are caused by unexpected 2-way interactions among system factors. Although meta-heuristic strategies like simulated annealing can generally discover smaller pairwise test suite, they may cost more time to perform search, compared with greedy algorithms. We propose a new method, improved Extremal Optimization (EO) based on the Bak-Sneppen (BS) model of biological evolution, for constructing pairwise test suites and define fitness function according to the requirement of improved EO. Experimental results show that improved EO gives similar size of resulting pairwise test suite and yields an 85% reduction in solution time over SA.
暂无评论