• Journal of the Korea Society of Computer and Information
• /
• v.28 no.12
• /
• pp.167-174
• /
• 2023

This paper attempted to improve the accuracy of the colorectal cancer diagnosis model using image data augmentation in convolutional neural network. Image data augmentation was performed by flipping, rotation, translation, shearing and zooming with basic image manipulation method. This study split 4000 training data and 1000 test data for 5000 image data held, the model is learned by adding 4000 and 8000 images by image data augmentation technique to 4000 training data. The evaluation results showed that the clasification accuracy for 4000, 8000, and 12,000 training data were 85.1%, 87.0%, and 90.2%, respectively, and the improvement effect depending on the increase of image data was confirmed.

• Proceedings of the IEEK Conference
• /
• 2001.06d
• /
• pp.203-206
• /
• 2001

This Paper suggests real-time video streaming method by using DCT-based scalability, and evaluates and analyzes the function. It is similar to using lowpass filter. That is, as following figure, this method is to split the encoded data in splitter and transmit it, and to decode the data according to the situation. This method can be applied to any video CODEC which is based on DCT. Therefore, this thesis suggests easy video streaming method by using DCT-based scalability, and shows the result of experiment. By using suggested scalability, calculations are reduced, and spacial scalability is realized. Moreover, the objective data which meet user's need according to the network condition and choose the appropriate scalability according to the capability of terming can be extracted. And it is possible to apply any resources according to the specificity of image.

• Speech Sciences
• /
• v.9 no.1
• /
• pp.39-47
• /
• 2002

This paper proposes an effective method to remedy the acoustic modeling problem inherent in the usual log-normal Parallel Model Composition intended for achieving robust speech recognition. In particular, the Gaussian kernels under the prescribed log-normal PMC cannot sufficiently express the corrupted speech distributions. The proposed scheme corrects this deficiency by judiciously selecting the 'fairly' corrupted component and by re-estimating it as a mixture of two distributions using data-driven PMC. As a result, some components become merged while equal number of components split. The determination for splitting or merging is achieved by means of measuring the similarity of the corrupted speech model to those of the clean model and the noise model. The experimental results indicate that the suggested algorithm is effective in representing the corrupted speech distributions and attains consistent improvement over various SNR and noise cases.

• Journal of the Korean Society for Precision Engineering
• /
• v.19 no.6
• /
• pp.160-165
• /
• 2002

A study on digital processes of injection mold in reverse engineering are presented. Reverse engineering is useful fur several cases, where user has no geometry information of object. Laser scanner is used to obtaining 3D coordinates of object. Sequences to process cloud data are described; sampling to reduce number of points, sorting to adjust the point order, and fitting to curve and surface, and so on. Split slide structure of mold is used fur undercut part and high viscosity material. Flow of injection molding are analysed to correct cooling channel and simulate molding conditions. NC tool paths are generated to carve core and cavity. The processes are performed in digital data for reduction of lead time and consecutive geometry data.

• Communications for Statistical Applications and Methods
• /
• v.12 no.3
• /
• pp.713-727
• /
• 2005

Among different regression approaches, nonparametric procedures perform well under different conditions. In practice it is very hard to identify which is the best procedure for the data at hand, thus model combination is of practical importance. In this paper, we focus on one dimensional regression with fixed design. Polynomial regression, local regression, and smoothing spline are considered. The data are split into two parts, one part is used for estimation and the other part is used for prediction. Prediction performances are used to assign weights to different regression procedures. Simulation results show that the combined estimator performs better or similarly compared with the estimator chosen by cross validation. The combined estimator generates a similar risk to the best candidate procedure for the data.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2004.11a
• /
• pp.359-364
• /
• 2004

This paper deals with the comparison of signal processing techniques of ultrasonic data. The goal of signal processing is the ultrasonic speckle suppression and the visibility enhancement of flaw-reflected ultrasonic echo. The performance of conventional SSP(split spectrum processing) method and the wavelet denoising method are compared and discussed for tested ultrasonic data. Tested ultrasonic data obtained from the weld area of centrifugal-casted stainless steel material and safe-ending material with holes and notch of variable depths are presented. In experimental results, the outputs of wavelet-based denoising method show the clear and sharp peaks at the positions of flaw-reflected echos comparing with those of SSP method.

• Proceedings of the KSEEG Conference
• /
• 2002.04a
• /
• pp.159-162
• /
• 2002

We tried to obtain an initial velocity model for prestack depth migration via waveform inversion. For application of any field data we chose a smooth background layered velocity model (v=v0 + k x z) as an initial velocity model. Newton type waveform inversion needs to invert huge Hessian matrix. In order to compute full Hessian matrix arising from full aperture data and full illumination zone, we meet insurmountable difficulties of paying astronomical computing cost. For the layered media, approximate Hessian emerging from single shot aperture data can be used repeatedly for split spread source configuration. In our work of using this Hessian characteristic of layered media we attempted to obtain the approximate velocity model as close as possible to the true velocity model in first iteration.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.25 no.12
• /
• pp.1677-1685
• /
• 1988

In this paper, a new contour coding algorithm is investigated for use in region based image coding. Generally the contour data may be encoded by its chain codes or chain difference codes. But the data compression efficiency is low because of heavy burden for initial absolute coordinates of each chain. To alleviate this problem, the depth first search in graph traversal algorithm, is applied to the chain difference coding method. The proposed coding scheme is shown to be very efficient for contour images obtained by split-merge segmentation. Finally, we can reuce data about 60% in comparison with modified chain difference coding.

• Journal of the Korean Society for Precision Engineering
• /
• v.13 no.3
• /
• pp.150-157
• /
• 1996

In this paper, to develop a smart CAD/CAM system for systematically performing from the 3-D solid shape design of products to the CNC cutting operation of products by a machining center, a B-Rep solid modeler is realized based on the half edge data structure. Because the B-Rep solid modeler has the various capabilities related to the solid definition functions such as the creation operation of primitives and the translational and rotational sweep operation, the solid manipulation functions such as the split operation and the Boolean set operation, and the solid inversion function for effectively using the data structure, the 3-D solid shape of products can be easily designed and constructed. Also, besides the automatic generation of CNC code, the B-Rep solid modeler can be used as a powerful tool for realizing the automatic generation of finite elements, the interfer- ence check between solids, the structural design of machine tools and robots and so on.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.233-236
• /
• 2000

The acoustical response of fish depends on size and physical structure na, most important, on the presence or absence of a swimbladder. Acoustic scattering models for swimbladdered fish represent a fish by an ideal pressure-release surface having the size and shape as the swimbladder. Target strength experiments of red seabream (Chrysophrys major) have been conducted using 38 (split-beam), 120 (split-beam) and 200kHz (dual-beam) frequencies. At each start of each experiment, the live fish are placed in the cage at the surface, then the cage is lowed to about $4{\cal}m$ depth where it remains during the measurements. To test the acoustic models, predictions of target strength based on swimbladder morphometries of 10 red seabream offish total length from $103{\cal}mm{\;}to{\;}349{\cal}mm$ ($3 <$TL/\lambda$ < 45)are compared with conventional target strength measurements on the same, shock-frozen immediately after caged experiments. X-ray was projected along dorsal aspect to know the morphological construction of swimbladder. and fish body. At high frequencies, Helmholtz-kirchhoff(HK) approximation would greatly enhance swimbladdered fish modeling. Sound scattering model [HK-ray approximation model] for comparison to experimental target strength data was used to model backscatter measurements from individual fish. The scattering data can be used in the inverse method along with multiple frequency sonar systems to investigate the adequacy of classification and identification of fish