• ETRI Journal
• /
• v.43 no.5
• /
• pp.881-890
• /
• 2021

Photoplethysmography (PPG) is a noninvasive technique that can be used to conveniently measure heart rate (HR) and thus obtain relevant health-related information. However, developing an automated PPG system is difficult, because its waveforms are susceptible to motion artifacts and between-patient variation, making its interpretation difficult. We use deep neural network (DNN) filters to mimic the cognitive ability of a human expert who can distinguish the features of PPG altered by noise from various sources. Systolic (S), onset (O), and first derivative peaks (W) are recognized by three different DNN filters. In addition, the boundaries of uninformative regions caused by artifacts are identified by two different filters. The algorithm reliably derives the HR and presents recognition scores for the S, O, and W peaks and artifacts with only a 0.7-s delay. In the evaluation using data from 11 patients obtained from PhysioNet, the algorithm yields 8643 (86.12%) reliable HR measurements from a total of 10 036 heartbeats, including some with uninformative data resulting from arrhythmias and artifacts.

• Journal of Intelligence and Information Systems
• /
• v.9 no.1
• /
• pp.125-137
• /
• 2003

In eastern countries stamps have been used more commonly than signatures when approving contracts and documents. Unlike finger prints, stamp images do not share similar patterns to each other and the resolution of stamp images is determined by the input status such as pressure under which stamps are put. This paper discusses the development of a system for recognizing stamp images of Korean or Chinese characters. Recognition of stamp images consists of several steps: acquisition of stamp images from an input device, digitization, contrast stretching, noise removal, and matching. We tested the system on 50 stamp images (20 stamp images of Korean characters, 20 images of Chinese characters, and 10 similar images). There was little difference in discrimination rate between the stamp images of Korean character and those of Chinese characters. 46 stamps images out of 50 were successfully recognized, resulting in 92% discrimination rate. Orientation and pressure under which stamps are put played an important role in determining discrimination rate. Automated stamp image recognition can be made more practical and useful by extending the types of stamp images to ellipses and rectangles and by improving the discrimination rate.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.2
• /
• pp.122-129
• /
• 2022

In this paper, we propose a method to improve the performance of Transformer-based speech recognizers using data augmentation that locally adjusts the frame rate. First, the start time and length of the part to be augmented in the original voice data are randomly selected. Then, the frame rate of the selected part is changed to a new frame rate by using linear interpolation. Experimental results using the Wall Street Journal and LibriSpeech speech databases showed that the convergence time took longer than the baseline, but the recognition accuracy was improved in most cases. In order to further improve the performance, various parameters such as the length and the speed of the selected parts were optimized. The proposed method was shown to achieve relative performance improvement of 11.8 % and 14.9 % compared with the baseline in the Wall Street Journal and LibriSpeech speech databases, respectively.

• Journal of Family Resource Management and Policy Review
• /
• v.13 no.3
• /
• pp.181-205
• /
• 2009

The purpose of this study is to investigate some Influencing factors related to the wealth perception and property increase of 519 women in Seoul. The research was conducted from the end of February 15 to the beginning of January 20, 2009. The figures obtained were analyzed by frequency, percentage, mean, x-test, t-test, F-test, chi-square, and Duncan's F-test with SPSS pc+ The major findings of who study are summarized as follows: l.There were significant differences between the wealth recognition (economic plan affirmative and negative perception of wealth) for women according to social and psychological variables; economic plans have a higher value for married women, older women, those who have followed a postgraduate university course, those with higher income and expenditure, higher life satisfaction, and high and middle satisfaction with their economic life. In particular, economic plans varied significantly according to expectation of wealth in old age, and future economic prospects in the middle group. 2. Increased wealth and economic according to social and psychological variables (marital status, age, education, income, expenditure, life satisfaction, satisfaction with economic life, expectation of wealth in old age, future economic prospects) were shown to be associated with the following methods of increasing property: use of savings banks (p<.001) showed a rate of deposit of 20%-40% (p<.001) saving and thrift was a practice (p<001) that was related to the cost of living; and education expenditure (p<.001) as a property preparation period was exhibited in women aged 25-30 (p<.001). 3. There were significant differences in the recognition of wealth according to strategies for increasing wealth. There were no significant differences between mean of property acquisition and point of expenditure or the property preparation period in the perception of wealth. The related variables in rate of deposits were under 20% according to economic plan and negative wealth perception. In contrast, in the middle and high group, the economic plan and negative wealth perception were 20%-40% in relation to the rate of deposits. Variables related to the action of saving and thrift and property acquisition were practiced in the low and middle group of affirmative wealth recognition and the high group of negative wealth perception. The high group for wealthrecognition and the low group for wealthnegation exhibited little savings, thrift, and property accumulation. Those variables which point an expenditure the cost of living were education expenditure in all groups of negative wealth perception. The women in the study practiced more soundness economic planning according to their increased wealth and economic strategy. This study suggests that women should have positive wealth perception in their lives.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.18 no.10
• /
• pp.1422-1432
• /
• 1993

Nonlinear mapping function of the HCNN( Hidden Control Neural Network ) can change over time to model the temporal variability of a speech signal by combining the nonlinear prediction of conventional neural networks with the segmentation capability of HMM. We have two things in this paper. first, we showed that the performance of the HCNN is better than that of HMM. Second, the HCNN with its prediction error measure given by weighted distance is proposed to use suitable distance measure for the HCNN, and then we showed that the superiority of the proposed system for speaker-independent speech recognition tasks. Weighted distance considers the differences between the variances of each component of the feature vector extraced from the speech data. Speaker-independent Korean digit recognition experiment showed that the recognition rate of 95%was obtained for the HCNN with Euclidean distance. This result is 1.28% higher than HMM, and shows that the HCNN which models the dynamical system is superior to HMM which is based on the statistical restrictions. And we obtained 97.35% for the HCNN with weighted distance, which is 2.35% better than the HCNN with Euclidean distance. The reason why the HCNN with weighted distance shows better performance is as follows : it reduces the variations of the recognition error rate over different speakers by increasing the recognition rate for the speakers who have many misclassified utterances. So we can conclude that the HCNN with weighted distance is more suit-able for speaker-independent speech recognition tasks.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.4
• /
• pp.57-63
• /
• 1997

In this paper, we study the efficient feature vector extraction method and front-end processing to improve the performance of the speech recognition system using KT(Korea Telecommunication) database collected through various telephone channels. First of all, we compare the recognition performances of the feature vectors known to be robust to noise and environmental variation and verify the performance enhancement of the recognition system using weighted cepstral distance measure methods. The experiment result shows that the recognition rate is increasedby using both PLP(Perceptual Linear Prediction) and MFCC(Mel Frequency Cepstral Coefficient) in comparison with LPC cepstrum used in KT recognition system. In cepstral distance measure, the weighted cepstral distance measure functions such as RPS(Root Power Sums) and BPL(Band-Pass Lifter) help the recognition enhancement. The application of the spectral subtraction method decrease the recognition rate because of the effect of distortion. However, RASTA(RelAtive SpecTrAl) processing, CMS(Cepstral Mean Subtraction) and SBR(Signal Bias Removal) enhance the recognition performance. Especially, the CMS method is simple but shows high recognition enhancement. Finally, the performances of the modified methods for the real-time implementation of CMS are compared and the improved method is suggested to prevent the performance degradation.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.1
• /
• pp.126-136
• /
• 2014

In the Advanced Driver Assistance Systems (ADAS) of smart vehicle and Intelligent Transportation System (ITS) for to detect the boundary of lane is being studied a lot of Hough Transform. This method detects correctly recognition the lane. But recognition rate can fall due to detecting straight lines outside of the lane. In order to solve this problems, this paper proposed an algorithm to recognize the lane boundaries and the accumulator cells in Hough space. Based on proposed algorithm, we develop application for Android was developed by H/W verification. Users of smart phone devices could use lane detection and lane departure warning systems for driver's safety whenever and wherever. Software verification using the OpenCV showed efficiency recognition correct rate of 93.8% and hardware real-time verification for an application development in the Android phone showed recognition correct rate of 70%.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.1
• /
• pp.127-133
• /
• 2020

This paper deals with the development of a smart mirror to support changing hair styles. A key function of the service is the ability to synthesize the image into the user's face when the user chooses a desired hair image and virtually styling the hair. To check the effectiveness of the hair image synthesis function, the success rate measurement experiment of Haar-cascade algorithm's facial recognition was conducted. Experiments have confirmed that the facial recognition succeeds with a 95 percent probability, with both eyes and eyebrows visible to the subjects. It is the highest success rate. It confirmed that if either of the eyebrows of the subjects are not visible or one eyeball is covered, the success rate of facial recognition is 50% and 0% respectively.

• Korean Journal of Health Education and Promotion
• /
• v.21 no.1
• /
• pp.243-257
• /
• 2004

Alcohol consumption is a major source of health problems, for example, alchol consumption is related to liver diseases. In addition, the social and economic costs related to alcohol consumption are enormous. This study was conducted to evaluate the current status and influencing factors related to the recognition and behavioral intention for both drinking and alcohol-reduction programs. Three effective alcohol-reduction programs of clinic program, mass education, and alliance were considered. To explain the health behavior for drinking and alcohol-reduction programs, a five-stage behavioral intention model was built and 500 questionnaires were completed through a telephone survey. Stages of the model composed of recognition of the programs, past experiences, present drinking status, intention for drinking, and behavioral intention for alcohol-reduction programs. As a result, recognition rates of the programs were low in general, therefore the strategies of education, public relations, and advertisement need to be pursued. The alcohol dependency resulted in the fact that success rate was 30％ although trial rate of alcohol-reducing was 23％. The necessity of alcohol-reduction programs were suggested. In addition, significant factors related to the intention for alcohol-reducing were individual attitude and reluctancy to pay their time and money. An insignificant factor was the attitude to their alcohol-reduction by other people. Behavioral intention rates for alcohol-reducing clinics were 4％, and those for mass education were 8％. There were very low purchase rates for clinic program, mass education, and alliance. In conclusion, evidenced-based and effective alcohol-reduction programs need to be encouraged to drinkers by medical doctors, and the strategies of education, public relations, and advertisement are also recommended. In addition, continuing legal and systematic support for alcohol-reducing would lower the drinking rate and ultimately contribute to the nation's health promotion.

• Korean Journal of Community Nutrition
• /
• v.16 no.5
• /
• pp.548-558
• /
• 2011

The purpose of this study was to compare eating habits and food attitudes between depressed and normal adults. The subjects were selected (n = 6217) from those who participated in the 2008 Korean National Health and Nutrition Examination Survey (KNHANES IV). The subjects were divided into the depressed (DG, n = 841) and normal groups (NG, n = 3969). DG was those who have depression now or who have experienced depressing feelings more than two weeks or per year. The general characteristics, anthropometric measurement, eating habits, the dietary guideline recognition and practices were compared by using chi-square test and t-test. Also the partial correlations were analyzed by SAS (Statistical analysis system, version 9.1) program. There was a significantly higher rate of DG among the female (74.32%), with low education (44.6%) and low-income (32.0%) subjects (p < 0.001). DG showed significantly lower snacking and dining out. There was significantly higher rate of DG who responded "none" in frequency of snack (27.10%) and dining out (29.50%) (p < 0.001). Also DG showed significantly lower rate of the subjects who ate with the family than NG. Also, DG showed significantly lower dietary guideline recognition level and practice than NG. Correlation between depression symptom and various factors showed that positive correlation with low snack intake and dining out frequencies. However, correlation was relatively weak. In conclusion, eating habits and recognition levels and practice of dietary guidelines of DG were significantly different from NG. DG showed significantly lower frequencies of snack, dining out, and eating with family.