• The KIPS Transactions:PartB
• /
• v.9B no.3
• /
• pp.327-336
• /
• 2002

Texture analysis is an important technique in many image understanding areas, such as perception of surface, object, shape and depth. But the previous works are intend to the issue of only texture segment, that is not capable of acquiring recognition information. No unsupervised method is basased on the recognition of texture in image. we propose a novel approach for efficient texture image analysis that uses unsupervised learning schemes for the texture recognition. The self-organization neural network for multiple texture image identification is based on block-based clustering and merging. The texture features used are the angle and magnitude in orientation-field that might be different from the sample textures. In order to show the performance of the proposed system, After we have attempted to build a various texture images. The final segmentation is achieved by using efficient edge detection algorithm applying to block-based dilation. The experimental results show that the performance of the system Is very successful.

• Journal of Korea Multimedia Society
• /
• v.15 no.5
• /
• pp.606-614
• /
• 2012

Face detection using AdaBoost algorithm is one of the fastest and the most robust face detection algorithm so many improvements or extensions of this method have been proposed. However, almost all previous approaches deal with only frontal face and suffer from limited discriminant capability for inclined face because these methods apply the same features for both frontal and inclined face. Also conventional approaches for detecting inclined face which apply frontal face detecting method to inclined input image or make different detectors for each angle require heavy computational complexity and show low detection rate. In order to overcome this problem, a method for detecting inclined face using JointBoost is proposed in this paper. The computational and sample complexity is reduced by finding common features that can be shared across the classes. Simulation results show that the detection rate of the proposed method is at least 2% higher than that of the conventional AdaBoost method under the learning condition with the same iteration number. Also the proposed method not only detects the existence of a face but also gives information about the inclined direction of the detected face.

• Journal of Korean Neurosurgical Society
• /
• v.42 no.4
• /
• pp.293-299
• /
• 2007

Objective : Thoracoscopic spinal surgery provides minimally invasive approaches for effective vertebral decompression and reconstruction of the thoracic and thoracolumbar spine, while surgery related morbidity can be significantly lowered. This study analyzes clinical results of thoracoscopic spinal surgery performed at our institute. Methods : Twenty consecutive patients underwent video-assisted thoracosopic surgery (VATS) to treat various thoracic and thoracolumbar pathologies from April 2000 to July 2006. The lesions consisted of spinal trauma (13 cases), thoracic disc herniation (4 cases), tuberculous spondylitis (1 case), post-operative thoracolumbar kyphosis (1 case) and thoracic tumor (1 case). The level of operation included upper thoracic lesions (3 cases), midthoracic lesions (6 cases) and thoracolumbar lesions (11 cases). We classified the procedure into three groups: stand-alone thoracoscopic discectomy (3 cases), thoracoscopic fusion (11 cases) and video assisted mini-thoracotomy (6 cases). Results : Analysis on the Frankel performance scale in spinal trauma patients (13 cases), showed a total of 7 patients who had neurological impairment preoperatively : Grade D (2 cases), Grade C (2 cases), Grade B (1 case), and Grade A (2 cases). Four patients were neurologically improved postoperatively, two patients were improved from C to E, one improved from grade D to E and one improved from grade B to grade D. The preoperative Cobb's and kyphotic angle were measured in spinal trauma patients and were $18.9{\pm}4.4^{\circ}$ and $18.8{\pm}4.6^{\circ}$, respectively. Postoperatively, the angles showed statistically significant improvement, $15.1{\pm}3.7^{\circ}$ and $11.3{\pm}2.4^{\circ}$, respectively(P<0.001). Conclusion : Although VATS requires a steep learning curve, it is an effective and minimally invasive procedure which provides biomechanical stability in terms of anterior column decompression and reconstruction for anterior load bearing, and preservation of intercostal muscles and diaphragm.

• Journal of the Korea Safety Management & Science
• /
• v.12 no.1
• /
• pp.51-57
• /
• 2010

Cycling that transform human energy into mechanical energy is one of the man-machine systems out of sports fields. Benchmarking means "improving ourselves by learning from others', therefore benchmarking toward dominant cyclist is necessary on field. The goals of this study were to provide important factors on multi-disciplines (kinematics, physiology, power, psychology) for a tailored-training program that is suitable to individual characteristics. Two cyclists participated in this study and gave consent to the experimental procedure. One was dominant cyclist (years: 21 yrs, height: 177 cm, mass: 70 kg), and the other was non-dominant cyclist (years: 21, height: 176, mass: 70). Kinematic data were recorded using six infrared cameras (240Hz) and QTM (software). Physiological data (VO2max, AT) were acquired according to graded exercising test with cycle ergometer and power with Wingate test used by Bar-Or et. al (1977) and to evaluate muscle function with Cybex. Psychological data were collected with competitive state anxiety inventory (CSAI-2) that was devised by Martens et. al (1990) and athletes' self-management questionnaire (ASMQ) of Huh (2003). It appears that the dominant's CV of ankle joint angle was higher than non-dominant's CV and dominant's pedaling pattern was consistent in biomechanics domain, which the dominant's values for all factors ware higher than non-dominant's values in physical, and physiological domain, and their values between cognitive anxiety and somatic anxiety were contrary to each other in psychology. Further research on multi-disciplines may lead to the development of tailored-optimal training programs applicable with key factors to enhance athletic performance by means of research including athlete, coach and parents.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.10a
• /
• pp.433-436
• /
• 2004

In this paper, we introduce a new Fuzzy Polynomial Neural Networks (FPNNS)-like structure whose neuron is based on the Fuzzy Set-based Fuzzy Inference System (FS-FIS) and is different from that of FPNNS based on the Fuzzy relation-based Fuzzy Inference System (FR-FIS) and discuss the ability of the new FPNNS-like structure named Fuzzy Set-based Polynomial Neural Networks (FSPNN). The premise parts of their fuzzy rules are not identical, while the consequent parts of the both Networks (such as FPNN and FSPNN) are identical. This difference results from the angle of a viewpoint of partition of input space of system. In other word, from a point of view of FS-FIS, the input variables are mutually independent under input space of system, while from a viewpoint of FR-FIS they are related each other. The proposed design procedure for networks architecture involves the selection of appropriate nodes with specific local characteristics such as the number of input variables, the order of the polynomial that is constant, linear, quadratic, or modified quadratic functions being viewed as the consequent part of fuzzy rules, and a collection of the specific subset of input variables. On the parameter optimization phase, we adopt Information Granulation (IC) based on HCM clustering algorithm and a standard least square method-based learning. Through the consecutive process of such structural and parametric optimization, an optimized and flexible fuzzy neural network is generated in a dynamic fashion. To evaluate the performance of the genetically optimized FSPNN (gFSPNN), the model is experimented with using the time series dataset of gas furnace process.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.2
• /
• pp.186-191
• /
• 2003

Skills in tracing of the MR divide into following, approaching, avoiding and warning and so on. It is difficult to have all these skills learned as neural network. To make this up for, skills consisted of each module, and Mobile Robot was controlled by the output of module adequate for the situation. A mobile Robot was equipped multi-ultrasonic sensor and a USB Camera, which can be in place of human sense, and the measured environment information data is learned through Modular Neural Network. MNN consisted of optimal combination of activation function in the Expert Network and its structure seemed to improve learning time and errors. The Gating Network(GN) used to control output values of the MNN by switching for angle and speed of the robot. In the paper, EN of Modular Neural network was designed optimal combination. Traveling with a real MR was performed repeatedly to verity the usefulness of the MNN which was proposed in this paper. The robot was properly controlled and driven by the result value and the experimental is rewarded with good fruits.

• Journal of IKEEE
• /
• v.22 no.2
• /
• pp.362-368
• /
• 2018

This paper has implemented a mutual conversion system that mutually converts between body motion signals and both visual and auditory signals. The present study is based on intentional synesthesia that can be perceived by learning. The Euler's angle was used in body movements as the output of a wearable armband(Myo). As a muscle sense, roll, pitch and yaw signals were used in this study. As visual and auditory signals, MIDI(Musical Instrument Digital Interface) signals and HSI(Hue, Saturation, Intensity) color model were used respectively. The method of mutual conversion between body motion signals and both visual and auditory signals made it easy to infer by applying one-to-one correspondence. Simulation results showed that input motion signals were compared with output simulation ones using ROS(Root Operation System) and Gazebo which is a 3D simulation tool, to enable the mutual conversion between body motion information and both visual and auditory information.

• Journal of Korean Society for Geospatial Information Science
• /
• v.14 no.4 s.38
• /
• pp.71-77
• /
• 2006

Support Vector Machine (SVM) which has roots in a statistical learning theory is a training algorithm based on structural risk minimization. Generally, SVM algorithm uses the kernel for determining a linearly non-separable boundary and classifying the data. But, classical kernels can not apply to effectively the hyperspectral image classification because it measures similarity using vector's dot-product or euclidian distance. So, This paper proposes the spectral similarity kernel to solve this problem. The spectral similariy kernel that calculate both vector's euclidian and angle distance is a local kernel, it can effectively consider a reflectance property of hyperspectral image. For validating our algorithm, SVM which used polynomial kernel, RBF kernel and proposed kernel was applied to land cover classification in Hyperion image. It appears that SVM classifier using spectral similarity kernel has the most outstanding result in qualitative and spatial estimation.

• The Journal of the Korea Contents Association
• /
• v.10 no.2
• /
• pp.306-319
• /
• 2010

Recently, crime prevention is away of important criminal justice policy and police activity also pursuit different change compare to the present times. After modern times, as get to know crime control change, eventually on the basis of experience that crime prevention is best way of crime control, what come out with new sight angle for the role of police is community policing. And emphasis points in police activity are variety of police activity, positive entry of community. In relation to this, we are learning crime prevention of the U.S.A and the program of community policing through crime prevention theory books that published in domestic. Then, there are misunderstanding possibilities that the programs which introduced relation books are doing someways all around the U.S.A In this research two cities san mateo county. california, of the U.S.A made a choice, and is going to search main crime present condition of these cities and really done community policing program or crime prevention program operation case.

• The Journal of Korean Physical Therapy
• /
• v.22 no.4
• /
• pp.29-33
• /
• 2010

Purpose: The purpose of this study was to assess and compare the reliability of the Modified Tardieu Scale (MTS) with the Modified Ashworth Scale (MAS) in patients with hemiplegia. Methods: Two experienced physical therapists examined twenty six patients (17 male and 9 female) with an age range of 19-83 years (mean=51.9 SD=15.2). They assessed the elbow flexor/extensor muscle spasticity in the affected side. Interand intra-rater reliability of the MAS and the MTS were calculated using kappa statistics. Intraclass correlation coefficient (ICC) was calculated to determine the inter- and intra-rater reliability of the angle of muscle reactions (R2-R1). Results: The intra-rater reliability of the MAS (K=0.39-0.55) and MTS (K=0.33-0.55) was fair to moderate. The inter-rater reliability was significantly higheras measured with MTS (K=0.54-0.66) in comparison with MAS (K=0.52). Intra-rater reliability of R2-R1 was moderate to almost perfect (ICC=0.52-0.86), and inter-rater reliability was substantial (ICC=0.74-0.76). Conclusion: The MTS provides higher inter-rater reliability compared with the MAS in hemiplegia patient analysis, but intra-rater reliability of both scales was not significantly different. Thus further research is needed to examine not only reliability, but also validity of these measurement systems.