• Journal of the Korean Association of Geographic Information Studies
• /
• v.15 no.4
• /
• pp.162-174
• /
• 2012

To visualize the characteristics of vertical seawater temperature data, in the ocean having 3D spatial characteristics, 2D thematic maps like horizontal seawater temperature distribution map at each depth layer and 3D volume model using 3D spatial interpolation are used. Although these methods are useful to understand oceanographic phenomena visually, there is a limit to analyze the spatial pattern of vertical temperature distribution or the relationship between vertical temperature characteristics and other oceanic factors (seawater chemistry, marine organism, climate change, etc). Therefore, this study aims to determine the spatial distribution characteristics of vertical temperature profiles in the South Sea of Jeju by quantifying the characteristics of vertical temperature profiles by using an algorithm that can extract the thermocline parameters, such as mixed layer depth, maximum temperature gradient and thermocline thickness. For this purpose spatial autocorrelation index (Moran's I) was calculated including mapping of spatial distribution for three parameters representing the vertical temperature profiles. Also, after grouping study area as four regions by using cluster analysis with three parameters, the characteristics of vertical temperature profiles were defined for each region.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.7
• /
• pp.23-35
• /
• 2013

This paper proposes an effective technique that is used to automatically extract feature vectors from vibration signals for fault classification systems. Conventional mel-frequency cepstral coefficients (MFCCs) are sensitive to noise of vibration signals, degrading classification accuracy. To solve this problem, this paper proposes spectral envelope cepstral coefficients (SECC) analysis, where a 4-step filter bank based on spectral envelopes of vibration signals is used: (1) a linear predictive coding (LPC) algorithm is used to specify spectral envelopes of all faulty vibration signals, (2) all envelopes are averaged to get general spectral shape, (3) a gradient descent method is used to find extremes of the average envelope and its frequencies, (4) a non-overlapped filter is used to have centers calculated from distances between valley frequencies of the envelope. This 4-step filter bank is then used in cepstral coefficients computation to extract feature vectors. Finally, a multi-layer support vector machine (MLSVM) with various sigma values uses these special parameters to identify faulty types of induction motors. Experimental results indicate that the proposed extraction method outperforms other feature extraction algorithms, yielding more than about 99.65% of classification accuracy.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.49 no.10
• /
• pp.60-68
• /
• 2012

Current wireless sensor networks are considered to support more complex operations ranging from military to health care which require energy-efficient and timely transmission of large amounts of data. In this paper, we propose an adaptive temporal suppression algorithm which exploits a temporal correlation among sensor readings. The proposed scheme can significantly reduce the number of transmitted sensor readings by sensor node, and consequently decrease the energy consumption and delay. Instead of transmitting all sensor readings from sensor node to sink node, the proposed scheme is to selectively transmit some elements of sensor readings using the adaptive temporal suppression, and the sink node is able to reconstruct the original data without deteriorating data quality by linear interpolation. In our proposed scheme, sensing data stream at sensor node is divided into many small sensing windows and the transmission ratio in each window is decided by the window complexity. It is defined as the number of a fluctuation point which has greater absolute gradient than threshold value. We have been able to achieve up about 90% communication reduction while maintaining a minimal distortion ratio 6.5% in 3 samples among 4 ones.

• Korean Journal of Cognitive Science
• /
• v.7 no.1
• /
• pp.57-74
• /
• 1996

This paper presents a comparison of recognition performance of the features used inthe recent handwritten korean character recognition.This research aims at providing the basis for feature selecion in order to improve not only the recognition rate but also the efficiency of recognition system.For the comparison of feature performace,we analyzed the characteristics of theose features and then,classified them into three rypes:global feature(image transformation)type,statistical feature type,and local/ topological feature type.For each type,we selected four or five features which seem more suitable to represent the characteristics of korean alphabet,and performed recongition experiments for the first consonant,horizontal vowel,and vertical vowel of a korean character, respectively.The classifier used in our experiments is a multi-layered perceptron with one hidden layer which is trained with backpropagation algorithm.The training and test data in the experiment are taken from 30sets of PE92. Experimental results show that 1)local/topological features outperform the other two type features in terms of recognition rates 2)mesh and projection features in statical feature type,walsh and DCT features in global feature type,and gradient and concavity features in local/topological feature type outperform the others in each type, respectively.

• Radiation Oncology Journal
• /
• v.12 no.1
• /
• pp.109-115
• /
• 1994

The purpose of this paper is to develop an efficient method for the quick determination of multiple isocenters plans to provide optimal dose distribution in sterotactic radiosurgery. A Spherical dose model was developed through the use of fit to the exact dose data calculated in a 18cm diameter of spherical head phantom. It computes dose quickly for each spherical part and is useful to estimate dose distribution for multiple isocenters. An automatic computer search algorithm was developed using the relationship between the isocenter move and the change of dose shape, and adapted with a spherical dose model to determine isocenter separation and cellimator sizes quickly and automatically. A spheric81 dose model shows a comparable isodose distribution with exact dose data and permits rapid calculations of 3-D isodoses. the computer search can provide reasonable isocenter settings more quickly than trial and error types of plans, while producing steep dose gradient around target boundary. A spherical dose model can be used for the quick determination of the multiple isocenter plans with 3 computer automatic search. Our guideline is useful to determine the initial multiple isocenter plans.

• Journal of Biomedical Engineering Research
• /
• v.32 no.3
• /
• pp.237-244
• /
• 2011

In this paper, a feature-based registration technique is proposed for pre-contrast and post-contrast lung CT images. It utilizes three dimensional(3-D) features with their descriptors and estimates feature correspondences by nearest neighborhood matching in the feature space. We design a transformation model between the input image pairs using a free form deformation(FFD) which is based on B-splines. Registration is achieved by minimizing an energy function incorporating the smoothness of FFD and the correspondence information through a non-linear gradient conjugate method. To deal with outliers in feature matching, our energy model integrates a robust estimator which discards outliers effectively by iteratively reducing a radius of confidence in the minimization process. Performance evaluation was carried out in terms of accuracy and efficiency using seven pairs of lung CT images of clinical practice. For a quantitative assessment, a radiologist specialized in thorax manually placed landmarks on each CT image pair. In comparative evaluation to a conventional feature-based registration method, our algorithm showed improved performances in both accuracy and efficiency.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.9 no.2
• /
• pp.161-168
• /
• 2015

In this paper, we present an inertial sensor-based gait distance measurement system using accelerometer, gyroscope, and magnetometer. To minimize offset and gain error of inertial sensors, we performed the calibration using the self-made calibration jig with 9 degrees of freedom. For measuring accurate gait distance, we used gradient descent algorithm to remove gravity error and used analysis of gait pattern to remove drift error. Finally, we measured a gait distance by double-integration of the error-removed acceleration data. To evaluate the performance of our system, we walked 10m in a straight line indoors to observe the improvement of removing error which compared un-calibrated to calibrated data. Also, the gait distance measured by the system was compared to the measurement of the Vicon motion capture system. The evaluation resulted in the improvement of $31.4{\pm}14.38%$(mean${\pm}$S.D.), $78.64{\pm}10.84%$ and $69.71{\pm}26.25%$ for x, y and z axis, respectively when walked in a straight line, and a root mean square error of 0.10m, 0.16m, and 0.12m for x, y and z axis, respectively when compared to the Vicon motion capture system.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.6
• /
• pp.67-78
• /
• 2017

Traffic congestion cost is increasing annually. Specifically congestion caused by the CDB traffic contains more than a half of the total congestion cost. Recent advancement in the field of Big Data, AI paved the way to industry revolution 4.0. And, these new technologies creates tremendous changes in the traffic information dissemination. Eventually, accurate and timely traffic information will give a positive impact on decreasing traffic congestion cost. This study, therefore, focused on developing both recurrent and non-recurrent congestion prediction models on urban roads by adopting Recurrent Neural Network(RNN), a tribe in machine learning. Two hidden layers with scaled conjugate gradient backpropagation algorithm were selected, and tested. Result of the analysis driven the authors to 25 meaningful links out of 33 total links that have appropriate mean square errors. Authors concluded that RNN model is a feasible model to predict congestion.

• Journal of Biomedical Engineering Research
• /
• v.27 no.5
• /
• pp.203-209
• /
• 2006

The aim of this study is to investigate the feasibility of ex vivo MR diffusion tensor imaging technique in order to observe the diffusion-contrast characteristics of human gastric tissues. On normal and pathologic gastric tissues, which have been fixed in a polycarbonate plastic tube filled with 10% formalin solution, laboratory made 3D diffusion tensor Turbo FLASH pulse sequence was used to obtain high resolution MR images with voxel size of $0.5{\times}0.5{\times}0.5mm^3\;using\;64{\times}32{\times}32mm^3$ field of view in conjunction with an acquisition matrix of $128{\times}64{\times}64$. Diffusion weighted- gradient pulses were employed with b values of 0 and $600s/mm^2$ in 6 orientations. The sequence was implemented on a clinical 3.0-T MRI scanner(Siemens, Erlangen, Germany) with a home-made quadrature-typed birdcage Tx/Rx rf coil for small specimen. Diffusion tensor values in each pixel were calculated using linear algebra and singular value decomposition(SVD) algorithm. Apparent diffusion coefficient(ADC) and fractional anisotropy(FA) map were also obtained from diffusion tensor data to compare pixel intensities between normal and abnormal gastric tissues. The processing software was developed by authors using Visual C++(Microsoft, WA, U.S.A.) and mathematical/statistical library of GNUwin32(Free Software Foundation). This study shows that 3D diffusion tensor Turbo FLASH sequence is useful to resolve fine micro-structures of gastric tissue and both ADC and FA values in normal gastric tissue are higher than those in abnormal tissue. Authors expect that this study also represents another possibility of gastric carcinoma detection by visualizing diffusion characteristics of proton spins in the gastric tissues.

• Korean Journal of Remote Sensing
• /
• v.20 no.4
• /
• pp.261-274
• /
• 2004

The feature extraction using remotely sensed imagery has been recognized one of the important tasks in remote sensing applications. As the high-resolution imagery are widely used to the engineering purposes, need of more accurate feature information also is increasing. Especially, in case of the automatic extraction of linear feature such as road using mid or low-resolution imagery, several techniques was developed and applied in the mean time. But quantitatively comparative analysis of techniques and case studies for high-resolution imagery is rare. In this study, we implemented a computer program to perform and compare GDPA (Gradient Direction Profile Analysis) algorithm and Hough transformation. Also the results of applying two techniques to some images were compared with road centerline layers and boundary layers of digital map and presented. For quantitative comparison, the ranking method using commission error and omission error was used. As results, Hough transform had high accuracy over 20% on the average. As for execution speed, GDPA shows main advantage over Hough transform. But the accuracy was not remarkable difference between GDPA and Hough transform, when the noise removal was app]ied to the result of GDPA. In conclusion, it is expected that GDPA have more advantage than Hough transform in the application side.