• Journal of Biomedical Engineering Research
• /
• v.19 no.3
• /
• pp.251-260
• /
• 1998

The Holter monitoring system is a widely used noninvasive diagnostic tool for ambulatory patient who may be at risk from latent life-threatening cardiac abnormalities. In this paper, we design a high performance intelligent holter monitoring system which is characterized by the small-sized and the low-power consumption. The system hardware consists of one-chip microcontroller(68HC11E9), ECG preprocessing circuit, and flash memory card. ECG preprocessing circuit is made of ECG preamplifier with gain of 250, 500 and 1000, the bandpass filter with bandwidth of 0.05-100Hz, the auto-balancing circuit and the saturation-calibrating circuit to eliminate baseline wandering, ECG signal sampled at 240 samples/sec is converted to the digital signal. We use a linear recursive filter and preprocessing algorithm to detect the ECG parameters which are QRS complex, and Q-R-T points, ST-level, HR, QT interval. The long-term acquired ECG signals and diagnostic parameters are compressed by the MFan(Modified Fan) and the delta modulation method. To easily interface with the PC based analyzer program which is operated in DOS and Windows, the compressed data, that are compatible to FFS(flash file system) format, are stored at the flash memory card with SBF(symmetric block format).

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.6 no.8
• /
• pp.1352-1357
• /
• 2002

This Paper describes algorithm to extract license plates in vehicle images. Conventional methods perform preprocessing on the entire vehicle image to produce the edge image and binarize it. Hough transform is applied to the binary image to find horizontal and vertical lines, and the license plate area is extracted using the characteristics of license plates. Problems with this approach are that real-time processing is not feasible due to long processing time and that the license plate area is not extracted when lighting is irregular such as at night or when the plate boundary does not show up in the image. This research uses the gray level transition characteristics of license plates to verify the digit area by examining the digit width and the level difference between the background area the digit area, and then extracts the plate area by testing the distance between the verified digits. This research solves the problem of failure in extracting the license plates due to degraded plate boundary as in the conventional methods and resolves the problem of the time requirement by processing the real time such that practical application is possible. This paper Presents a power automated license plate recognition system, which is able to read license numbers of cars, even under circumstances, which are far from ideal. In a real-life test, the percentage of rejected plates wan 13%, whereas 0.4% of the plates were misclassified. Suggestions for further improvements are given.

• The Journal of the Convergence on Culture Technology
• /
• v.6 no.2
• /
• pp.509-514
• /
• 2020

The conventional TTS system consists of several modules, including text preprocessing, parsing analysis, grapheme-to-phoneme conversion, boundary analysis, prosody control, acoustic feature generation by acoustic model, and synthesized speech generation. But TTS system with deep learning is composed of Text2Mel process that generates spectrogram from text, and vocoder that synthesizes speech signals from spectrogram. In this paper, for the optimal Korean TTS system construction we apply Tacotron2 to Tex2Mel process, and as a vocoder we introduce the methods such as WaveNet, WaveRNN, and WaveGlow, and implement them to verify and compare their performance. Experimental results show that WaveNet has the highest MOS and the trained model is hundreds of megabytes in size, but the synthesis time is about 50 times the real time. WaveRNN shows MOS performance similar to that of WaveNet and the model size is several tens of megabytes, but this method also cannot be processed in real time. WaveGlow can handle real-time processing, but the model is several GB in size and MOS is the worst of the three vocoders. From the results of this study, the reference criteria for selecting the appropriate method according to the hardware environment in the field of applying the TTS system are presented in this paper.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.4
• /
• pp.109-116
• /
• 2021

In this paper, we propose a non-intrusive load monitoring(NILM) system which can find the power of each home appliance from the aggregated total power as the activation in the trading market of the distributed resource and the increasing importance of energy management. We transform the amount of appliances' power into a power on-off state by preprocessing. We use LSTM as a model for predicting states based on these data. Accuracy is measured by comparing predicted states with real ones after postprocessing. In this paper, the accuracy is measured with the different number of electronic products, data postprocessing method, and Time step size. When the number of electronic products is 6, the data postprocessing method using the Round function is used, and Time step size is set to 6, the maximum accuracy can be obtained.

• 전자공학회논문지 IE
• /
• v.43 no.4
• /
• pp.13-20
• /
• 2006

In the advanced country, It is forecasting farm prices using intelligence style of farming technique. In our country, It is offering basis research to prevent the prices rising and falling, But, It is impossible that no one can predict exactly for farming price. In this paper to improve forecasting farming price using neural network as a preprocessing. Also, we developed a fuzzy algorithm for real time forecasting as a postprocessing about unexpectable conditions. Computer simulation results preyed reducing pricing error which proposed farming price expecting system better than conventional demand forecasting system does not using fuzzy rules.

• Smart Media Journal
• /
• v.1 no.1
• /
• pp.10-16
• /
• 2012

Stereo and multi-view cameras have been used to capture the three-dimensional (3D) scene for 3D contents generation. Besides, depth sensors are frequently used to obtain 3D information of the captured scene in real time. In order to generate 3D contents from captured images, we need several preprocessing operations to reduce noises and distortions in the images. 3D contents are considered as the basic media for realistic broadcasting that provides photo-realistic and immersive feeling to users. In this paper, we show technical trends of 3D image capturing and contents generation, and explain some core techniques for 3D image processing for realistic 3DTV broadcasting.

• International journal of advanced smart convergence
• /
• v.8 no.4
• /
• pp.104-112
• /
• 2019

This study proposed a robust detection algorithm. It detects face more stably with respect to changes in light and rotation forthe identification of a face shape. The proposed algorithm uses face shape asinput information in a single camera environment and divides only face area through preprocessing process. However, it is not easy to accurately recognize the face area that is sensitive to lighting changes and has a large degree of freedom, and the error range is large. In this paper, we separated the background and face area using the brightness difference of the two images to increase the recognition rate. The brightness difference between the two images means the difference between the images taken under the bright light and the images taken under the dark light. After separating only the face region, the face shape is recognized by using the self-organization feature map (SOFM) algorithm. SOFM first selects the first top neuron through the learning process. Second, the highest neuron is renewed by competing again between the highest neuron and neighboring neurons through the competition process. Third, the final top neuron is selected by repeating the learning process and the competition process. In addition, the competition will go through a three-step learning process to ensure that the top neurons are updated well among neurons. By using these SOFM neural network algorithms, we intend to implement a stable and robust real-time face shape recognition system in face shape recognition.

• IEIE Transactions on Smart Processing and Computing
• /
• v.1 no.1
• /
• pp.8-16
• /
• 2012

An image obtained from a low light environment results in a low-exposure problem caused by non-ideal camera settings, i.e. aperture size and shutter speed. Of particular note, the multiple color-filter aperture (MCA) system inherently suffers from low-exposure problems and performance degradation in its image classification and registration processes due to its finite size of the apertures. In this context, this paper presents a novel method for the color enhancement of low-exposure images and its application to color shift model-based MCA system for image refocusing. Although various histogram equalization (HE) approaches have been proposed, they tend to distort the color information of the processed image due to the range limits of the histogram. The proposed color enhancement algorithm enhances the global brightness by analyzing the basic cause of the low-exposure phenomenon, and then compensates for the contrast degradation artifacts by using an adaptive histogram specification. We also apply the proposed algorithm to the preprocessing step of the refocusing technique in the MCA system to enhance the color image. The experimental results confirm that the proposed method can enhance the contrast of any low-exposure color image acquired by a conventional camera, and is suitable for commercial low-cost, high-quality imaging devices, such as consumer-grade camcorders, real-time 3D reconstruction systems, digital, and computational cameras.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.21 no.8
• /
• pp.1339-1347
• /
• 1997

The automation of final inspection and tuning process in the manufacturing of electric products is hot issue now, because it is the only part that has not been wholey automized yet, mainly due to the difficulties to handle so small size of VR which is the final tuning point in the most of electric products. For the automation of this process, at first the accurate measurement of position and orientation of SMD VR on PCB in real time is strongly needed. In this paper, a new image processing algorithm to detect the center position and orientation of target VR by using machine vision is proposed for automatic final tuning of the 8mm camcoder's performance. In the method, the outline feature of object is used actively. The usefulness of the proposed methods were tested by several experiments, and the results showed enough accuracy for both of position and orientation. Additatively, we discussed about the total visual system construction and preprocessing of image.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.1952-1953
• /
• 2011

본 논문에서는 다항식 기반 Radial Basis Function(RBF)신경회로망(Polynomial based Radial Basis function Neural Network)을 설계하고 이를 n-클래스 패턴 분류 문제에 적용한다. 제안된 다항식기반 RBF 신경회로망은 입력층, 은닉층, 출력층으로 이루어진다. 입력층은 입력 벡터의 값들을 은닉층으로 전달하는 기능을 수행하고 은닉층과 출력층사이의 연결가중치는 상수, 선형식 또는 이차식으로 이루어지며 경사 하강법에 의해 학습된다. Networks의 최종 출력은 연결가중치와 은닉층 출력의 곱에 의해 퍼지추론의 결과로서 얻어진다. 패턴분류기의 최적화는 PSO(Particle Swarm Optimization)알고리즘을 통해 이루어진다. 그리고 제안된 패턴분류기는 실제 얼굴인식 시스템으로 응용하여 직접 CCD 카메라로부터 입력받은 데이터를 영상 보정, 얼굴 검출, 특징 추출 등과 같은 처리 과정을 포함하여 서로 다른 등록인물의 n-클래스 분류 문제에 적용 및 평가되어 분류기로써의 성능을 분석해본다.