• Journal of Korea Multimedia Society
• /
• v.11 no.11
• /
• pp.1501-1514
• /
• 2008

The face shape extracted by the depth values has different appearance as the most important facial information. The face images decomposed into frequency subband are signified personal features in detail. In this paper, we develop a method for recognizing the range face images by multiple frequency domains for each depth image using the modified fuzzy c-mean algorithm. For the proposed approach, the first step tries to find the nose tip that has a protrusion shape on the face from the extracted face area. And the second step takes into consideration of the orientated frontal posture to normalize. Multiple contour line areas which have a different shape for each person are extracted by the depth threshold values from the reference point, nose tip. And then, the frequency component extracted from the wavelet subband can be adopted as feature information for the authentication problems. The third step of approach concerns the application of eigenface to reduce the dimension. And the linear discriminant analysis (LDA) method to improve the classification ability between the similar features is adapted. In the last step, the individual classifiers using the modified fuzzy c-mean method based on the K-NN to initialize the membership degree is explained for extracted coefficient at each resolution level. In the experimental results, using the depth threshold value 60 (DT60) showed the highest recognition rate among the extracted regions, and the proposed classification method achieved 98.3% recognition rate, incase of fuzzy cluster.

• The KIPS Transactions:PartB
• /
• v.15B no.1
• /
• pp.1-8
• /
• 2008

Generally, moving objects in surveillance video are extracted by background subtraction or frame difference method. However, moving cast shadows on object distort extracted figures which cause serious detection problems. Especially, analyzing vehicle information in video frames from a fixed surveillance camera on road, we obtain inaccurate results by shadow which vehicle causes. So, Shadow Elimination is essential to extract right objects from frames in surveillance video. And we use shadow removal algorithm for vehicle classification. In our paper, as we suppress moving cast shadow in object, we efficiently discriminate vehicle types. After we fit new object of shadow-removed object as three dimension object, we use extracted attributes for supervised learning to classify vehicle types. In experiment, we use 3 learning methods {IBL, C4.5, NN(Neural Network)} so that we evaluate the result of vehicle classification by shadow elimination.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.3
• /
• pp.562-569
• /
• 2019

Raman spectroscopy has been receiving increased attention as a standoff explosive detection technique. In addition, there is a growing need for a fast search method that can identify raman spectrum for measured chemical substances compared to known raman spectra in large database. By far the most simple and widely used method is to calculate and compare the Euclidean distance between the given spectrum and the spectra in a database. But it is non-trivial problem because of the inherent high dimensionality of the data. One of the most serious problems is the high computational complexity of searching for the closet spectra. To overcome this problem, we presented the MPS Sort with Sorted Variance+PDS method for the fast algorithm to search for the closet spectra in the last paper. the proposed algorithm uses two significant features of a vector, mean values and variance, to reject many unlikely spectra and save a great deal of computation time. In this paper, we present two new methods for the fast algorithm to search for the closet spectra. the PCA+PDS algorithm reduces the amount of computation by reducing the dimension of the data through PCA transformation with the same result as the distance calculation using the whole data. the Hierarchical Cluster Tree algorithm makes a binary hierarchical tree using PCA transformed spectra data. then it start searching from the clusters closest to the input spectrum and do not calculate many spectra that can not be candidates, which save a great deal of computation time. As the Experiment results, PCA+PDS shows about 60.06% performance improvement for the MPS Sort with Sorted Variance+PDS. also, Hierarchical Tree shows about 17.74% performance improvement for the PCA+PDS. The results obtained confirm the effectiveness of the proposed algorithm.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1485-1490
• /
• 2004

Recently, we have remarkable developments in intelligent robot systems. The remarkable features of intelligent robot are that it can track user, does face recognition and vital for many surveillance based systems. Advantage of face recognition when compared with other biometrics recognition is that coerciveness and contact that usually exist when we acquire characteristics do not exist in face recognition. However, the accuracy of face recognition is lower than other biometric recognition due to decrease in dimension from of image acquisition step and various changes associated with face pose and background. Factors that deteriorate performance of face recognition are many such as distance from camera to face, lighting change, pose change, and change of facial expression. In this paper, we implement a new 3D active camera system to prevent various pose variation that influence face recognition performance and propose face recognition algorithm for intelligent surveillance system and mobile robot system.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.20 no.4
• /
• pp.46-51
• /
• 2012

Injection pressure, an important factor in filling process, should be minimized to enhance injection molding quality. Injection pressure can be controlled by valve gate open timing. In this work, we decided the valve gate open timing to minimize the injection pressure. To solve this design problem, we integrated MAPS-3D (Mold Analysis and Plastic Solution-3Dimension), a commercial injection molding CAE tool, to PIAnO (Process Integration, Automation and Optimization), a commercial PIDO (Process Integration, and Design Optimization) tool using the file parsing method. In order to reduce computational cost, we performed an approximate optimization using meta-models that replaced expensive computer simulations. At first, we carried out DOE (Design of Experiments) using OLHD (Optimal Latin Hypercube Design) available in PIAnO. Then, we built Kriging models using the simulation results at the sampling points. Finally, we used micro GA (Genetic Algorithm) available in PIAnO. Using the proposed design approach, the injection pressure has been reduced by 13.7% compared to the initial one. This design result clearly shows the validity of the proposed design approach.

• International Journal of Contents
• /
• v.7 no.3
• /
• pp.13-18
• /
• 2011

Oriental medicine statistics are essential in research planning, research evaluation, and policy decision based on objective data. However, integrated administration of such statistics is not presently possible in the oriental medicine field, which has been slow in incorporating information communication technology. In an effort to address this problem, the Korea Institute of Oriental Medicine (KIOM) developed an oriental medicine statistical system in 2009, and the system has been offered in the traditional medicine information portal of OASIS. However, according to a 2010 survey targeting OASIS users, those surveys reported that needs for a system where various statistical data can be extracted via an interactive approach to multidimensional data. As a result of an analysis of the functions of the existing system, it was found that it is necessary to array and arithmetically analyze Stats Value, Drill Up & Drill Down, and Pivot. To this end, the existing DB schema should be redesigned. Based on our analysis result, we redesigned the database into a structure that is applicable to the reverse pivot algorithm. We used J2EE/JSP and a Flex framework to design and develop an oriental medicine statistical system that can provide multidimensional statistical data. Considering that the improved oriental medicine statistical system is planned to be offered by OASIS of KIOM, utilization and value of oriental medicine statistical data are expected to be enhanced.

• Science of Emotion and Sensibility
• /
• v.1 no.1
• /
• pp.69-78
• /
• 1998

Sleep deprivation may affect the brain functions such as cognition and consequently, dynamics of the BEG. We examined the effects of sleep deprivation on chaoticity of the EEG. Five volunteers were sleep-deprived over a period of 24 hours They were checked by EEG during two days. thc first day of baseline period and the second day of total sleep deprivation period. EEGs were recorded from 16 channels for nonlinear analysis. We employed a method of minimum embedding dimension to calculate the first positive Lyapunov exponent. Fer limited noisy data, this algorithm was strikingly faster and more accurate than previous ones. Our results show that the sleep deprived volunteers had lower values of the first positive Lyapunov exponent at ten channels (Fp1, F4. F8. T4, T5. C3, C4. P3. P4. O1) compared with the values of baseline periods. These results suggested that sleep deprivation leads to decrease of chaotic activity in brain and impairment of the information processing in the brain. We suggested that nonlinear analysis of the EEG before and after sleep deprivation may offer fruitful perspectives for understanding the role if sleep and the effects of sleep deprivation on the brain function.

• Steel and Composite Structures
• /
• v.33 no.3
• /
• pp.319-332
• /
• 2019

This study is aimed to predict the behaviour of channel shear connectors in composite floor systems at different temperatures. For this purpose, a soft computing approach is adopted. Two novel intelligence methods, including an Extreme Learning Machine (ELM) and a Genetic Programming (GP), are developed. In order to generate the required data for the intelligence methods, several push-out tests were conducted on various channel connectors at different temperatures. The dimension of the channel connectors, temperature, and slip are considered as the inputs of the models, and the strength of the connector is predicted as the output. Next, the performance of the ELM and GP is evaluated by developing an Artificial Neural Network (ANN). Finally, the performance of the ELM, GP, and ANN is compared with each other. Results show that ELM is capable of achieving superior performance indices in comparison with GP and ANN in the case of load prediction. Also, it is found that ELM is not only a very fast algorithm but also a more reliable model.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.5
• /
• pp.141-147
• /
• 2021

In this paper, in order to improve the utilization of hyperspectral large-capacity data feature information by reducing complex computations by dimension reduction of neural network inputs in embedded systems, the band selection algorithm is applied in each subset. Among feature extraction and feature selection techniques, the feature selection aim to improve the optimal number of bands suitable for datasets, regardless of wavelength range, and the time and performance, more than others algorithms. Through this experiment, although the time required was reduced by 1/3 to 1/9 times compared to the others band selection technique, meaningful results were improved by more than 4% in terms of performance through the K-neighbor classifier. Although it is difficult to utilize real-time hyperspectral data analysis now, it has confirmed the possibility of improvement.

• Korean Journal of Remote Sensing
• /
• v.34 no.5
• /
• pp.811-827
• /
• 2018

The purpose of this study is to compare machine learning algorithm and deep learning algorithm in crop classification using multi-temporal remote sensing data. For this, impacts of machine learning and deep learning algorithms on (a) hyper-parameter and (2) training sample size were compared and analyzed for Haenam-gun, Korea and Illinois State, USA. In the comparison experiment, support vector machine (SVM) was applied as machine learning algorithm and convolutional neural network (CNN) was applied as deep learning algorithm. In particular, 2D-CNN considering 2-dimensional spatial information and 3D-CNN with extended time dimension from 2D-CNN were applied as CNN. As a result of the experiment, it was found that the hyper-parameter values of CNN, considering various hyper-parameter, defined in the two study areas were similar compared with SVM. Based on this result, although it takes much time to optimize the model in CNN, it is considered that it is possible to apply transfer learning that can extend optimized CNN model to other regions. Then, in the experiment results with various training sample size, the impact of that on CNN was larger than SVM. In particular, this impact was exaggerated in Illinois State with heterogeneous spatial patterns. In addition, the lowest classification performance of 3D-CNN was presented in Illinois State, which is considered to be due to over-fitting as complexity of the model. That is, the classification performance was relatively degraded due to heterogeneous patterns and noise effect of input data, although the training accuracy of 3D-CNN model was high. This result simply that a proper classification algorithms should be selected considering spatial characteristics of study areas. Also, a large amount of training samples is necessary to guarantee higher classification performance in CNN, particularly in 3D-CNN.