A novel approach based on Bayesian networks for short-term traffic flow forecasting is proposed. A Bayesian network is originally used to model the causal relationship of time series of traffic flows among a chosen li...
详细信息
A novel approach based on Bayesian networks for short-term traffic flow forecasting is proposed. A Bayesian network is originally used to model the causal relationship of time series of traffic flows among a chosen link and its adjacent links in a road network. Then, a Gaussian mixture model (GMM), whose parameters are estimated through competitive expectation maximization (CEM) algorithm, is applied to approximate the joint probability distribution of all nodes in the constructed Bayesian network. Finally, traffic flow forecasting of the current link is performed under the rule of minimum mean square error (MMSE). To further improve the forecasting performance, principal component analysis (PCA) is also adopted before carrying out the CEM algorithm. Experiments show that, by using a Bayesian network for short-term traffic flow forecasting, one can improve the forecasting accuracy significantly, and that the Bayesian network is an attractive forecasting method for such kinds of forecasting problems.
In this paper, we propose classifier combination based on active learning, which deals with the design of classifier combination systems as training a combiner at the aggregation level and introduces SVM active learni...
详细信息
ISBN:
(纸本)0769521282
In this paper, we propose classifier combination based on active learning, which deals with the design of classifier combination systems as training a combiner at the aggregation level and introduces SVM active learning into the design of this multi-category decision combiner. This algorithm greatly reduces the number of labeled data the classifier system needs in order to achieve satisfactory performance. This algorithm consists of two main steps: firstly, designing and training first level classifiers which can output posterior probability vectors as the input of the second level combiner, secondly, designing second level combiner based on SVM active learning and classifying testing samples with this combiner. Experiments on standard database show that our algorithm performs better than current classifier combination rules when considering both labeling cost and classification accuracy.
作者:
E.W. FlickDepartment of Computer Science and Technology
Tsinghua University State Key Laboratory of Intelligent Technology and Systems Tsinghua National Laboratory for Information Science and Technology (TNList) Beijing China
We propose a novel method for glasses detection. The glasses detectors are learned by using a variation of boosting algorithm, called real Adaboost, to boost simple wavelet feature based Look-Up-Table type weak classi...
详细信息
ISBN:
(纸本)0769521282
We propose a novel method for glasses detection. The glasses detectors are learned by using a variation of boosting algorithm, called real Adaboost, to boost simple wavelet feature based Look-Up-Table type weak classifiers. Two types of wavelet features, Haar and Gabor, have been investigated. Experiments results are reported to show that our method has very high correctness and extremely fast running speed. Based on this method we have developed a glasses detection system which can detect the glasses in facial images automatically.
Small UAVs are now used for variety activities, such as rescuing, reconnaissance and surveillance. Then, more and more fully autonomous small UAVs are expected. In this paper, system identification for a small UAVs ta...
详细信息
ISBN:
(纸本)0780388739
Small UAVs are now used for variety activities, such as rescuing, reconnaissance and surveillance. Then, more and more fully autonomous small UAVs are expected. In this paper, system identification for a small UAVs take-off process based on operator's control is carried out. The small UAV with fixed gear speeds up on the runway before take-off, in order to keep the vehicle's heading, the drift angle of front wheel should be adjusted in real time. Using input and output data of actual flying test, system identification results are shown through numerical analysis. Validated by input and output data of other actual flying test, the result model is acceptable.
We consider the problem of tracking the output of an unmanned tandem helicopter. We investigate the dynamic model and analyze the exact linearization. We present the approximate linearization to design the controller ...
详细信息
ISBN:
(纸本)0780382730
We consider the problem of tracking the output of an unmanned tandem helicopter. We investigate the dynamic model and analyze the exact linearization. We present the approximate linearization to design the controller for output tracking based on dynamic extension method. Simulation results show the effectiveness of the method.
In this paper, we propose a novel method for facial expression recognition. The facial expression is extracted from human faces by an expression classifier that is learned from boosting Haar feature based look-up-tabl...
详细信息
ISBN:
(纸本)0769521282
In this paper, we propose a novel method for facial expression recognition. The facial expression is extracted from human faces by an expression classifier that is learned from boosting Haar feature based look-up-table type weak classifiers. The expression recognition system consists of three modules, face detection, facial feature landmark extraction and facial expression recognition. The implemented system can automatically recognize seven expressions in real time that include anger, disgust, fear, happiness, neutral, sadness and surprise. Experimental results are reported to show its potential applications in human computer interaction.
This paper presents an open controller which is designed for bending the hull steel plates. It is an industrial robot that is based on the SERCOS bus and carries out a so-called "bending by line heating" pro...
详细信息
ISBN:
(纸本)0780382730
This paper presents an open controller which is designed for bending the hull steel plates. It is an industrial robot that is based on the SERCOS bus and carries out a so-called "bending by line heating" procedure in China. To treat with the diversity of the original steel plates' shapes, we designed an open controller for it. The controller is open because it provides a set of instructions with which the end user can compile different programs according to the different working procedures. A positioning method used in the saddle type plate forming is also introduced.
The insertion of the communication network in the feedback control loop makes some problems about the QoS. One important issue is the network-induced delay that occurs while exchanging data among devices connected to ...
详细信息
The insertion of the communication network in the feedback control loop makes some problems about the QoS. One important issue is the network-induced delay that occurs while exchanging data among devices connected to the shared medium. The purpose of this paper is to design an improved internal model controller to control a plant with time delays. Compared with ordinary internal model controllers, there is an additional feedback loop in the new architecture. The simulation results demonstrate that the control system has satisfied robustness performance.
A method of learning the intrinsic facial expression space for expression tracking is proposed. First, a partial 3D face model is constructed from a trinocular image and the expression space is parameterized using MPE...
详细信息
ISBN:
(纸本)0769521223
A method of learning the intrinsic facial expression space for expression tracking is proposed. First, a partial 3D face model is constructed from a trinocular image and the expression space is parameterized using MPEG4 FAP. Then an algorithm of learning the intrinsic expression space from the parameterized FAP space is derived. The resulted intrinsic expression space reduces even to 5 dimensions. We will show that the obtained expression space is superior to the space obtained by PCA. Then the dynamical model is derived and trained on this intrinsic expression space. Finally, the learned tracker is developed in a particle-filter-style tracking framework. Experiments on both synthetic and real videos show that the learned tracker performs stably over a long sequence and the results are encouraging.
暂无评论