• Journal of Sensor Science and Technology
• /
• v.24 no.4
• /
• pp.270-273
• /
• 2015

One of the main problems when working the chemical sensor is the lack of repeatability and reproducibility of the sensor response. If the problem is not properly taken into consideration, the stability and reliability of the system using chemical sensors would be decreased. In this paper we analyzed the sensor's drift of short term and proposed a compensation method for reducing the effects of the drift in order to improve the stability and the reliability of the chemical sensor. The sensor drift was analyzed by a trend line graph and CV(coefficient of variation) was used to quantify. And we compensated for the drift by using the internal normalization. As a result it was found that the value of CV was decreased after compensation.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.2 s.46
• /
• pp.103-109
• /
• 2007

In this paper, we detect shot boundaries using $X^2$-histogram comparison method which have enough spatial information that is more robust to the camera or object motion and produce more precise results. Also, we present normalization method to change Log-Formula and constant that is used for contrast enhancement of image in image processing and apply in difference value. And, present shot boundary detection algorithm to detect shot boundary based on general shot and abrupt shot's characteristic.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2004.05b
• /
• pp.591-594
• /
• 2004

In this paper, The identity distinction of the moving objects using distance among hue normalization levels was proposed. Moving objects are detected by using difference image method and integral projection method to background image and objects image only with hue area. Hue information of the detected moving area are normalized by 24 levels from 0$^{\circ}$ to 360$^{\circ}$. A distance in between normalized levels with a hue distribution chart of the normalized moving objects is used for the identity distinction feature parameters of the moving objects. To examine proposed method in this paper, image of moving cars are obtained by setting up three cameras at different places every 1 km on outer motorway. The simulation results of identity distinction show that it is possible to distinct the identity a distance in between normalization levels of a hue distribution chart without background.

• MALSORI
• /
• no.54
• /
• pp.63-72
• /
• 2005

The performance of speech recognition system is degraded by the mismatch between training and test environments. Many studies have been presented to compensate for noise components in the cepstral domain. Recently, higher order cepstral moment normalization method has been introduced to improve recognition accuracy. In this paper, we present real-time high order moment normalization method with post-processing smoothing filter to reduce the parameter estimation error in higher order moment computation. In experiments using Aurora2 database, we obtained error rate reduction of 44.7% with proposed algorithm in comparison with baseline system.

• Journal of the Semiconductor & Display Technology
• /
• v.19 no.4
• /
• pp.65-70
• /
• 2020

CNN's technologies that represent emotional detection include primitive CNN algorithms, deployment normalization, and drop-off. We present the methods and data of the three experiments in this paper. The training database and the test database are set up differently. The first experiment is to extract emotions using Batch Normalization, which complemented the shortcomings of distribution. The second experiment is to extract emotions using Dropout, which is used for rapid computation. The third experiment uses CNN using convolution and maxpooling. All three results show a low detection rate, To supplement these problems, We will develop a deep learning algorithm using feature extraction method specialized in image processing field.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.1
• /
• pp.166-179
• /
• 2021

Recently, with the development of technology, computer vision research based on the human visual system has been actively conducted. Saliency maps have been used to highlight areas that are visually interesting within the image, but they can suffer from low performance due to external factors, such as an indistinct background or light source. In this study, existing color, brightness, and contrast feature maps are subjected to multiple shape and orientation filters and then connected to a fully connected layer to determine pixel intensities within the image based on location-based weights. The proposed method demonstrates better performance in separating the background from the area of interest in terms of color and brightness in the presence of external elements and noise. Location-based weight normalization is also effective in removing pixels with high intensity that are outside of the image or in non-interest regions. Our proposed method also demonstrates that multi-filter normalization can be processed faster using parallel processing.

• The Journal of the Acoustical Society of Korea
• /
• v.3 no.1
• /
• pp.25-35
• /
• 1984

This paper analysis the Dynamic Time Warping algorithms for time normalization of speech pattern and discusses the Dynamic Programming algorithm for spoken Korean isolated digits recognition. In the DP matching, feature vectors of the reference and test pattern are consisted of first three formant frequencies extracted by power spectrum density estimation algorithm of the ARMA model. The major differences in the various DTW algorithms include the global path constrains, the local continuity constraints on the path, and the distance weighting/normalization used to give the overall minimum distance. The performance criterias to evaluate these DP algorithms are memory requirement, speed of implementation, and recognition accuracy.

• Journal of The Korean Society of Inherited Metabolic disease
• /
• v.16 no.3
• /
• pp.135-140
• /
• 2016

Purpose: Galactose is metabolized to galactose-1-phosphate by galactokinase (GALK), galactose-1-phosphate uridyltransferase (GALT) and UDP-galactose-4-epimerase (GALE), and galactosemia occurs when each enzyme is deficient. In Korea, unlike foreign countries, classic galactosemia is rare and transient galactosemia due to GALK hyperactivity is reported, but studies on frequency, clinical significance, and genetic variation are lacking. In this study, we analyzed the clinical characteristics of patients with galactosemia due to GALK hyperactivity. Methods: We investigated 85 patients who had an elevated galactose level in the neonatal screening test without deficiency of enzymes at Department of Pediatrics, Seoul & Bucheon Soonchunhyang University Hospital from January 2008 to June 2016. We investigated the level of galactose, galactose-1-phosphate, GALK and duration of galactose normalization, and analyzed the correlation between GALK elevation and galactose, galactose-1-phosphate and duration of galactose normalization. And the levels of galactose, galactose-1-phosphate, and duration of galactose normalization were compared between the galactose-free formula feeding group and non-feeding group. Results: Mean age of visit was $26.7{\pm}16.1days$. Duration of galactose normalization was $35.3{\pm}20.5days$. Mean galactose level was $18.5{\pm}7.3mg/dL$ in the neonatal screening and follow-up galactose level in serum was $2.3{\pm}5.4mg/dL$. The mean value of galactose-1-phosphate was $6.0{\pm}4.7mg/dL$ and the mean GALK level was $3.84{\pm}1.28{\mu}mol/Hr/gHb$. There was no significant correlation between GALK levels and galactose levels in the neonatal screening test (P=0.351), and we analyzed the correlation between GALK levels and follow-up galactose levels in serum, there was no significant correlation (P=0.101). There was a significant correlation between GALK levels and galactose-1-phosphate (P=0.015), and the correlation between GALK levels and duration of galactose normalization was not statistically significant (P=0.176). 49% of the patients were fed galactose-free formula, and 45% were not. Galactose and galactose-1-phosphate levels in the neonatal screening test were statistically significantly higher (P=0.004, 0.034) in using galactose-free formula group. Duration of galactose normalization was not related to the use of galactose-free formula (P=0.266, 0.249). Conclusion: Galactosemia due to GALK hyperactivity seems to be a temporary phenomenon and may not require galactose restriction. More research is needed on the role of the nuclear protein, racial traits and genetic variations in Korean patients.

• Journal of applied mathematics & informatics
• /
• v.10 no.1_2
• /
• pp.1-15
• /
• 2002

In this paper an important stability property of the extremes under power normalizations is discussed. It is proved that the restricted convergence of the Power normalized extremes on an arbitrary nondegenerate interval implies the weak convergence. Moreover, this implication, in an important practical situation, is obtained when the sample size is considered as a random variable distributed geometrically with mean n.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.199-200
• /
• 2011

Load forecasting is very important for power system analysis and planning. This paper suggests yearly load forecasting of considering weekly normalization and seasonal load characteristics. Each weekly peak load is normalized and the average value is calculated. The new hourly peak load is seasonally collected. This method was used for yearly load forecasting. The results of the actual data and forecast data were calculated error rate by comparing.