• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.07a
• /
• pp.39-41
• /
• 2011

본 논문에서는 깊이 영상의 해상도와 품질을 향상시키는 방법을 제안한다. 일반적으로 2D-plus-Depth 구조의 3D 콘텐츠에서는 깊이 영상의 품질이 매우 중요하다. 최근 들어 Time-of-Flight (TOF) 방식의 깊이 센서가 깊이 영상 획득에 많이 사용되고 있는데 TOF 깊이 센서가 제공하는 깊이 영상은 저해상도이기 때문에 고해상도 3D 콘텐츠를 제작하기 위해서는 깊이 영상의 해상도를 상향 변환하는 것이 필수적이다. 또한 고품질의 깊이 영상을 얻기 위해서는 물체 간의 경계를 정교하게 보존하는 것이 중요하다. 최근에는 깊이 영상의 해상도 상향 변환을 위해서 Joint Bilateral Upsampling(JBU) 방식이 많이 사용되고 있다. 본 논문은 깊이 영상의 해상도를 높임에 있어서 우선 보간법을 수행하여 영상의 상향 변환 시에 생긴 빈 홀들의 값을 채워준 후 Bilateral Filtering을 수행함으로써 성능을 높인다. 일반적으로 영상을 상향 변환을 할 때 다양한 방법들이 있는데 본 논문에서는 Nearest Neighborhood(NN), Gaussian과 경계 보존 보간법, 경계 보존 보간법과 Fast Curvature Based Interpolation(FCBI)를 결합한 보간법을 사용하였다. 실험 결과 제안 방법이 기존 방법보다 우수한 성능을 가짐을 보여준다. 또한 경계 보존 보간법과 FCBI를 결합한 보간법을 이용해서 상향 변환을 수행한 결과가 다른 보간법들에 의한 결과보다 우수하다는 점을 알 수 있다.

• Bulletin of the Korean Mathematical Society
• /
• v.51 no.6
• /
• pp.1841-1850
• /
• 2014

It is known that the ranks of the semigroups $\mathcal{SOP}_n$, $\mathcal{SPOP}_n$ and $\mathcal{SSPOP}_n$ (the semigroups of orientation preserving singular self-maps, partial and strictly partial transformations on $X_n={1,2,{\ldots},n}$, respectively) are n, 2n and n + 1, respectively. The idempotent rank, defined as the smallest number of idempotent generating set, of $\mathcal{SOP}_n$ and $\mathcal{SSPOP}_n$ are the same value as the rank, respectively. Idempotent can be seen as a special case (with m = 1) of m-potent. In this paper, we investigate the m-potent ranks, defined as the smallest number of m-potent generating set, of the semigroups $\mathcal{SOP}_n$, $\mathcal{SPOP}_n$ and $\mathcal{SSPOP}_n$. Firstly, we characterize the structure of the minimal generating sets of $\mathcal{SOP}_n$. As applications, we obtain that the number of distinct minimal generating sets is $(n-1)^nn!$. Secondly, we show that, for $1{\leq}m{\leq}n-1$, the m-potent ranks of the semigroups $\mathcal{SOP}_n$ and $\mathcal{SPOP}_n$ are also n and 2n, respectively. Finally, we find that the 2-potent rank of $\mathcal{SSPOP}_n$ is n + 1.

• Journal of Information Technology Applications and Management
• /
• v.18 no.3
• /
• pp.1-30
• /
• 2011

InnovVizwas designed and developed anew as avisualization and simulationtool to present innovation and strategy information. The InnovViz system employs two key types of technology, namely mixed reality (MR) and neural network (NN). An experiment was conducted to examine the usability, acceptance and possible adoption of this new system. Participants comprised 4 experts from 4 top performing entrepreneurial firms and 161 master degree students from 2 leading universities. The study used a modified UTAUT model and a cognition and perception model. The results revealed that when the InnovViz was introduced, the key drivers to adoption are Facilitating Conditions (FC) and Voluntary to Use (VOL). Adequate knowledge and sufficient resources were found to strongly affect FC construct. The expert's rating of a firm's innovation and performance was more congruent with senior students with a technology-background than with a finance and accounting-background. InnovViz was seen as providing complex information with an ease of use and usefulness for showing data and assessment. Among the three types of visuals depicted by InnovViz, experts rated their usefulness in descending order as follows: Cube, Tetrahedron and Saturn. Finally, experts found backward simulation to be slightly more useful for assessment than forward simulation.

• Proceedings of the KIEE Conference
• /
• 2004.07d
• /
• pp.2580-2582
• /
• 2004

In this paper, a Neural Network(NN) based approach for classification of two dimensions images. The proposed algorithm is able to apply in the actual industry. The described diagnostic algorithm is presented to defect surface failures on tiles. A way to get data for a digital image process is several kinds of it. The tiles are scanned and the digital images are preprocessed and classified using neural networks. It is important to reduce the amount of input data with problem specific preprocessing. The auto-associative neural network is used for feature generation and selection while the probabilistic neural network is used for classification. The proposed algorithm is evaluated experimentally using one hundred of the real tile images. Sample image data to preprocess have histogram. The histogram is used as input value of probabilistic neural network. Auto-associative neural network compress input data and compressed data is classified using probabilistic neural network. Classified sample images are determined by human state. So it is intervened human subjectivity. But digital image processing and neural network are better than human classification ability. Therefore it is very useful of quality control improvement.

• The Korean Journal of Applied Statistics
• /
• v.17 no.3
• /
• pp.605-617
• /
• 2004

One of the best important thing in data mining process is the quality of data used. When we perform the mining on data with excellent quality, the potential value of data mining can be improved. In this paper, we propose the data fusion technique for data enrichment that one phase can improve data quality in KDD process. We attempted to add k-NN technique to the regression technique, to improve performance of fusion technique through reduction of the loss of information. Simulations were performed to compare the proposed data fusion technique with the regression technique. As a result, the newly proposed data fusion technique is characterized with low MSE in continuous fusion variables.

• Journal of Acupuncture Research
• /
• v.27 no.2
• /
• pp.11-21
• /
• 2010

Objectives : We tried to investigate the effects of Carthami Semen(CF) pharmacopuncture and Bovis Calculus Fei Ursi(BU) pharmacopuncture on the heart rate variability(HRV) in adult men. As well as we tried to observe how CF pharmacopuncture and BU pharmacopuncture effect on the balance of the autonomic nervous system. Methods : We investigated on 40 healthy volunteers consisted of 20 subjects in CF pharmacopuncture group and 20 subjects in BU pharmacopuncture group respectively. We ruled out subjects whose vital sign isn't in normal range, yet they had taken a rest. The study established by a randomized, single-blind clinical trial. CF pharmacopuncture and BU pharmacopuncture was applied on each group. We measured HRV 7 times : baseline measurement and every 5 minutes for 30 minutes after injection. The SPSS 15.0 for Windows was used to analyze the data by the paired t-test(in group) and Independent sample t-test(between the groups). Results 1. After injection of CF pharmacopuncture, SDNN, Ln(TP), Ln(VLF) and Ln(LF) increased significantly, and Complexity, pNN50 decreased significantly. 2. After injection of BU pharmacopuncture, RMSSD, SDSD and HRV-index increased significantly. Conclusions : We suggest that CF pharmacopuncture activate sympathetic nervous system and BU pharmacopuncture tend to activate the autonomic nervous system.

• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10c
• /
• pp.384-386
• /
• 1998

The use of hand gesture provides an attractive alternative to cumbersome interface devices for human-computer interaction(HCI). Many methods hand gesture recognition using visual analysis have been proposed such as syntactical analysis, neural network(NN), Hidden Markov Model(HMM) and so on. In our research, a HMMs is proposed for alphabetical hand gesture recognition. In the preprocessing stage, the proposed approach consists of three different procedures for hand localization, hand tracking and gesture spotting. The hand location procedure detects the candidated regions on the basis of skin-color and motion in an image by using a color histogram matching and time-varying edge difference techniques. The hand tracking algorithm finds the centroid of a moving hand region, connect those centroids, and thus, produces a trajectory. The spotting a feature database, the proposed approach use the mesh feature code for codebook of HMM. In our experiments, 1300 alphabetical and 1300 untrained gestures are used for training and testing, respectively. Those experimental results demonstrate that the proposed approach yields a higher and satisfying recognition rate for the images with different sizes, shapes and skew angles.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.22 no.3
• /
• pp.136-142
• /
• 2014

Distinct features in heart rate signals during the driver's wake and sleep states could provide an initiative for the development of a safe driving systems such as drowsiness detecting sensor in a smart wheel. We measured ECG from health subjects ($23.5{\pm}2.5$ in age) during the wake and drowsiness states. The proposed method is able to detect R waves and R-R interval calculation in the ECG even when the signal includes in abnormal signals. Heart rate variability(HRV) was investigated for the time domain and frequency domains. The STD HR(0.029), NN50(0.044) and VLF power(0.0018) of the RR interval series of the subjects were significantly different from those of the control group (p < 0.05). In conclusion, there are changes in heart rate from wake to drowsiness that are potentially to be detected. The results in our study could be useful for the development of drowsiness detection sensors for effective real-time monitoring.

• Proceedings of the KSRS Conference
• /
• 2007.10a
• /
• pp.286-289
• /
• 2007

This study is to develop a cloud detection algorit1un for COMS and it is currently tested by using MODIS level 2B and MTSAT-1R satellite radiance data. Unlike many existing cloud detection schemes which use a threshold method and traditional statistical methods, in this study a feed-forward neural network method with back-propagation algorit1un is used. MODIS level 2B products are matched with feature information of five-band MTSAT 1R image data to form the training dataset. The neural network is trained over the global region for the period of January to December in 2006 with 5 km spatial resolution. The main results show that this model is capable to detect complex cloud phenomena. And when it is applied to seasonal images, it shows reliable results to reflect seasonal characteristics except for snow cover of winter. The cloud detection by the neural network method shows 90% accuracy compared to the MODIS products.

• International Journal of Aeronautical and Space Sciences
• /
• v.9 no.1
• /
• pp.100-110
• /
• 2008

It is not easy to monitor and identify all engine faults and conditions using conventional fault detection approaches like the GPA (Gas Path Analysis) method due to the nature and complexity of the faults. This study therefore focuses on a model based diagnostic method using Neural Network algorithms proposed for fault detection on a turbo shaft engine (PW 206C) selected as the power plant for a tilt rotor type unmanned aerial vehicle (Smart UAV). The model based diagnosis should be performed by a precise performance model. However component maps for the performance model were not provided by the engine manufacturer. Therefore they were generated by a new component map generation method, namely hybrid method using system identification and genetic algorithms that identifies inversely component characteristics from limited performance deck data provided by the engine manufacturer. Performance simulations at different operating conditions were performed on the PW206C turbo shaft engine using SIMULINK. In order to train the proposed BPNN (Back Propagation Neural Network), performance data sets obtained from performance analysis results using various implanted component degradations were used. The trained NN system could reasonably detect the faulted components including the fault pattern and quantity of the study engine at various operating conditions.