Feature subset selection is a fundamental problem of data mining. The mutual information of feature subset is a measure for feature subset containing class feature information. A hashing mechanism is proposed to calcu...
详细信息
Feature subset selection is a fundamental problem of data mining. The mutual information of feature subset is a measure for feature subset containing class feature information. A hashing mechanism is proposed to calculate the mutual information of feature subset. The feature relevancy is defined by mutual information. Redundancy-synergy coefficient, a novel redundancy and synergy measure for features to describe the class feature, is defined. In terms of information maximization rule, a bidirectional heuristic feature subset selection method based on mutual information and redundancy-synergy coefficient is presented. This study's experiments show the good performance of the new method.
In this paper we discuss landmark based absolute localization of tiny autonomous mobile robots in a known environment. Landmark features are naturally occurring as it is not allowed to modify the environment with spec...
详细信息
In this paper, we proposed a robot self position identification method by active sound localization. This method can be used for autonomous security robots working in room environments. A system using a AIBO robot equ...
详细信息
In this paper, we proposed a robot self position identification method by active sound localization. This method can be used for autonomous security robots working in room environments. A system using a AIBO robot equipped with two microphones and wireless network is constructed and is used for position identification experiments. Arrival time differences to the microphones of robot are used as localization cues. To overcome the ambiguity of front-back confusion, a three-head position measurement method was proposed. The robot position can be identified by the intersection of circles restricted by the azimuth differences to different speaker pairs. By localizing three or four speakers as sound beacons positioned on known locations, the robot can identify its self position with an average error of about 7 cm in a 2.5 times 3.0 m 2 working space
In this paper, we apply a multiple regression method based on canonical correlation analysis (CCA) to face data modelling. CCA is a factor analysis method which exploits the correlation between two high dimensional si...
详细信息
In this paper, we apply a multiple regression method based on canonical correlation analysis (CCA) to face data modelling. CCA is a factor analysis method which exploits the correlation between two high dimensional signals. We first use CCA to perform 3D face reconstruction and in a separate application we predict near-infrared (NIR) face texture. In both cases, the input data are color (RGB) face images. Experiments show, that due to the correlation between input and output signal, only a small number of canonical factors are needed to describe the functional relation of RGB images to the respective output (NIR images and 3D depth maps) with reasonable accuracy
The principles of Traditional Chinese Medical (TCM) diagnosis are based on the information obtained from four diagnostic processes, which are inspection, listening and smelling, inquiry and palpation. These diagnosis ...
详细信息
The principles of Traditional Chinese Medical (TCM) diagnosis are based on the information obtained from four diagnostic processes, which are inspection, listening and smelling, inquiry and palpation. These diagnosis methods mainly rely on the experiences of the doctors. With the development of information technology, computerization of the diagnosis method is urgent. However, there are so many challenges in this field. This paper will provide detailed introduction of these contents. Through it, the state of arts of the computerization of TCM and the existing challenge of this field can be gotten.
Human tongue is the only organ of human, which can be laid out. It takes an important role in Traditional Chinese Medicine (TCM) because of its abundant biomedical information. With the progress of modernization of TC...
详细信息
Human tongue is the only organ of human, which can be laid out. It takes an important role in Traditional Chinese Medicine (TCM) because of its abundant biomedical information. With the progress of modernization of TCM,computerization of tongue diagnosis attracts the researchers'interesting. Thus, how to get an accurate tongue region becomes a key of automatic tongue diagnosis. However, tongue images segmentation is difficult for some physiological properties: tongue is non-rigid and has a high degree of variability in size, shape, color and texture. This paper presents a novel tongue detection method based on *** this method to tongue image, we can get the satisfying results with the respect to robust and veracity.
The requirement of algorithm for detecting small target in infrared image sequences is not only a high rate to identify the true target and a low false alarm rate, but also the computation efficiency. By employing the...
详细信息
ISBN:
(纸本)0780393953
The requirement of algorithm for detecting small target in infrared image sequences is not only a high rate to identify the true target and a low false alarm rate, but also the computation efficiency. By employing the selective attention mechanism, biological visual system can interpret a complex incoming image in real time with limited hardware resources. Much evidence has suggested that the biological visual system processes information in a serial strategy which rapidly selects a small relevant region in scene for further complex and time consuming analysis. In this paper, a two component computation scheme is proposed to detect dim targets in infrared image sequences. In the first process stage, an efficient method is applied to extract the potential targets which are further identified in second phase, the true targets are detected, and the spurious objects are rejected. The attention-based approach reduces the computation complexity, while the other performance aspects are not traded off. Experimental results indicate that the proposed extraction and recognition modules exhibit excellent performance of detecting small target in infrared image sequences, especially in process speed aspect.
This paper attempts to introduce a velocity-separation difference model that modifies the previous models in the literature. The improvement of this new model over the previous ones lies in that it performs more reali...
详细信息
This paper attempts to introduce a velocity-separation difference model that modifies the previous models in the literature. The improvement of this new model over the previous ones lies in that it performs more realistically than others in the dynamical evolution of congestion. Furthermore, the proposed model is investigated with analytic and numerical method, with the finding that this model can demonstrate some complex physical features observed in real traffic such as the existence of three phases: free flow, coexisting flow, and jam flow; sudden flow drop; traffic hysteresis in transition between the free and the coexisting flow
We propose a classification method based on a decision tree whose nodes consist of linear support vector machines (SVMs). Each node defines a decision hyperplane that classifies part of the feature space. For large cl...
详细信息
We propose a classification method based on a decision tree whose nodes consist of linear support vector machines (SVMs). Each node defines a decision hyperplane that classifies part of the feature space. For large classification problems (with many support vectors (SVs)) it has the advantage that the classification time does not depend on the number of SVs. Here, the classification of a new sample can be calculated by the dot product with the orthogonal vector of each hyperplane. The number of nodes in the tree has shown to be much smaller than the number of SVs in a non-linear SVM, thus, a significant speedup in classification time can be achieved. For non-linear separable problems, the trivial solution (zero vector) of a linear SVM is analyzed and a new formulation of the optimization problem is given to avoid it
暂无评论