Applied Mechanics and Materials Vols. 713-715

Abstract: Clinical data are inevitably incomplete, and most knowledge discovery algorithms lack the capability to contend with missing data. Flow-graph confers some distinct advantages in data mining and knowledge discovery. However, flow-graph methodology is not able to comprehensively solve the incomplete data problem. This paper proposes a flow-graph network approach for extracting knowledge from incomplete medical data. The concept of incomplete-medical-diagnosis-flow-graph (IMDFG) was defined. To evaluate the diagnosis rules within the IMDFG, the computing method for the certainty factor and coverage factor are presented. Moreover, the application of flow-graph network can be useful for extracting comprehensibility knowledge from the incomplete medical data. In an illustrative medical example, the clinical diagnosis rules are induced and interpreted in accordance to the generated flow graphs.

Abstract: Credibility is the key performance index and the lifeline for system simulation. Verification, validation and accreditation (VV&A) of all system simulation life can insure the credibility, and credibility evaluation is a very necessary approach to obtain the credibility. Combat simulation is a special simulation for its many characteristics of multi-level, more elements, overall emergence, uncertainty, morbid and multi-granularity model, and so on. Credibility is vital to combat simulation. The evaluation method is one of the aspects of credibility evaluation. In this paper, the methods of credibility evaluation are researched. The common evaluation methods are analyzed and compared. Aiming at the characteristics of combat simulation system, the subjective comprehensive evaluation method based on subject matter expert (SME) is put forward, which is applied to a combat simulation. The practice shows that the subjective comprehensive evaluation method is very effective. The results are sufficiently credible to support the application.

Abstract: This thesis mainly discusses the basic theory of the real-time lighting and shadow and the application of virtual simulation system in the virtual simulation field, introduces the light model and shadow generation algorithm more detailedly which are applied in virtual simulation field virtual simulation system according to the actual situation finally.

Abstract: Geographic Information Service is open service based on the network environment. DEM should be protected because of its significance. This paper gives three methods for DEM information protecting, they are DEM encrypting, DEM information hiding and DEM Information disguising, and researches their theories and techniques. Then, this paper analyses their differences and relation. This paper could provide theory support for DEM information security research in Geographic Information Service.

Abstract: According to the problem that achieves robust human actions recognition from image sequences in computer vision, using the Iterative Querying Heuristic algorithm as a guide, a improved Multiple Instance Learning (MIL) method is proposed for human action recognition in video image sequences. Experiments show that the new method can quickly recognize human actions and achieve high recognition rates, and on the Weizmann database validate our analysis.

Abstract: Hand gesture of rotation, scaling and translation is the key problem of gesture recognition. This paper proposes a gesture recognition algorithm based on Hausdorff-like distance template matching of gesture main direction. Firstly, we segment hand gesture from video stream. Secondly, we calculate the main direction of gesture in the image, and build a 2D rectangular coordinate system. Then, we clockwise divide the gesture into eight sub-image area along the main direction of gesture and calculate the coordinates of target pixel points in each sub-image area in the 2D rectangular coordinate system. Finally, the algorithm of Hausdorff-like distance template matching is used to recognize the final gesture. Experimental results show that this algorithm can achieve real-time correct recognition of gestures in relatively stable light conditions. The overall recognition rate can reach 95%.

Abstract: A new similarity measurement standard is proposed, namely background similarity matching. Learning algorithm based on kernel function is utilized in the method for feature extraction and classification of face image. Meanwhile, a real-time video face recognition method is proposed, image binary algorithm in similarity calculation is introduced, and a video face recognition system is designed and implemented [1-2]. The system is provided with a camera to obtain face images, and face recognition is realized through image preprocessing, face detection and positioning, feature extraction, feature learning and matching. Design, image preprocessing, feature positioning and extraction, face recognition and other major technologies of face recognition systems are introduced in details. Lookup mode from top down is improved, thereby improving lookup accuracy and speed [3-4]. The experimental results showed that the method has high recognition rate. Higher recognition rate still can be obtained even for limited change images of face images and face gesture with slightly uneven illumination. Meanwhile, training speed and recognition speed of the method are very fast, thereby fully meeting real-time requirements of face recognition system [5]. The system has certain face recognition function and can well recognize front faces.

Abstract: The color, shape and texture are the basic intrinsic features of visual scene and important features for scene recognition and visual salient feature. The recognition of four targets of “bird”, “ball”, “butterfly” and “flower” under the color image, gray image, edge image and low-pass blurred image was completed in the paper through psychology experiment, and the experimental result showed that the speed to recognize the color image was quickest, it was a little slower to recognize the gray image with the same accuracy of the color image, the edge image had a great impact on the recognition of certain object, thus increasing the recognition time, the blurred image increased the time to recognize various objects while reduced the recognition accuracy. The cognitive research on the scene image’s visual feature is helpful to reveal the secrets of human information processing and explore the law for the formulation of human visual saliency.

Abstract: In order to improve the speed and accuracy of lithology identification with logging data, according to the advantage of the recognition of linear distribution with SOM network, a identification model was established to recognize lithology in northern Qaidam basin. Firstly, the input data of logging curves are normalized, and then continuously trained network separately for 30 times, 50 times, 100 times, 200 times, 500 times, 1000 times, and the final results had shown that it did the best when it’s on 200 times, and the accuracy almostly reached 93 percent. Finally, the model was applied in other district which had the same geology background, and it also apparently displayed more efficient than other traditional method.

Abstract: In this paper a method of bar code detection and recognition is introduced, and discussed a combination of machine vision technology and virtual instrument, on this account, USB camera is used to capture images and detection and information extraction of the image of bar code, so user can store the function of product information. This method has very high recognition accuracy, speed and better practicality.