• Journal of the Korea Society of Computer and Information
• /
• v.23 no.11
• /
• pp.51-57
• /
• 2018

In this paper, we studied about the extraction of the parameter and implementation of speechreading system to recognize the Korean 8 vowel. Face features are detected by amplifying, reducing the image value and making a comparison between the image value which is represented for various value in various color space. The eyes position, the nose position, the inner boundary of lip, the outer boundary of upper lip and the outer line of the tooth is found to the feature and using the analysis the area of inner lip, the hight and width of inner lip, the outer line length of the tooth rate about a inner mouth area and the distance between the nose and outer boundary of upper lip are used for the parameter. 2400 data are gathered and analyzed. Based on this analysis, the neural net is constructed and the recognition experiments are performed. In the experiment, 5 normal persons were sampled. The observational error between samples was corrected using normalization method. The experiment show very encouraging result about the usefulness of the parameter.

• Journal of KIISE:Software and Applications
• /
• v.29 no.11
• /
• pp.818-825
• /
• 2002

Depth information is one of the most important factor for the recognition of a digital face image. Range images are very useful, when comparing one face with other faces, because of implicating depth information. As the processing for the whole fare produces a lot of calculations and data, face images ran be represented in terms of a vector of feature descriptors for a local area. In this paper, depth areas of a 3 dimensional(3D) face image were extracted by the contour line from some depth value. These were resampled and stored in consecutive location in feature vector using multiple feature method. A comparison between two faces was made based on their distance in the feature space, using Euclidian distance. This paper reduced the number of index data in the database and used fewer feature vectors than other methods. Proposed algorithm can be highly recognized for using local depth information and less feature vectors or the face.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.12B
• /
• pp.2359-2368
• /
• 1999

In this paper we propose a 2D FLIR image-based 3D target recognition system which performs group-to-ground vehicle recognition using the target contour and its degree of reliability extracted from FLIR image. First we extract target from background in FLIR image. Then we define contour points of the extracted target which have high edge gradient magnitude and brightness value as reliable contour point and make reliable contour by grouping all reliable contour points. After that we extract corresponding reliable contours from model contour image and perform comparison between scene and model features which are calculated by DST(discrete sine transform) of reliable contours. Experiment shows that the proposed algorithm work well and even in case of imperfect target extraction it showed better performance then conventional 2D contour-based matching algorithms.

• Speech Sciences
• /
• v.10 no.3
• /
• pp.213-224
• /
• 2003

Spoken sound includes not only speaker's source but the characteristics of vocal tract and speech radiation. This paper is based on the theory of Park[1], who proposes the Phonation Type Index k; a variable that shows the characteristic of speaker's source excluding those of speaker's vocal tract and speech radiation. With Park's theory, we collect data by changing recording environments and expanding experimental data, and analyze the data collected to see whether or not the PTI k shows good discriminating power as a variable for speaker recognition. In the experiment, we repeatedly record 8 sentences ten times for each of 5 males in the environment of a recording room and an office, extract PTI k for each speaker, and measure the discriminating power for each speaker by using the value of PTI k. The result shows that PTI k has the excellent discriminating power of speakers. We also confirm that, even if the recording environment is changed, PTI k shows similar results.

• Women's Health Nursing
• /
• v.6 no.1
• /
• pp.142-152
• /
• 2000

This study is a descriptive study to offer an actual basic data as Nursing intervention strategy of nurses before delivery in order that pregnant women in Korea may effectively practice Taekyo by examining the relation after apprehending level of recognition and practice of our pregnant women about Taekyo. This study collected questionnaires from 801 pregnant women who visited general hospitals in 10 areas(Seoul, Daejon, chunan, Daegu, Kummi, $Ky{\check{o}}ngju$, $P{\ddot{o}}hang$, Busan, $J{\ddot{o}}nju$, and $Y{\ddot{o}}nkwang$) for prenatal care through an outpatient obstetrics and gynecology from July 15 to August 30, 1999. This study used the tool of lee, Ki Young(1993) revised an complemented by investigator to measure recognition of Taekyo and the tool of Jang, Shun Buk and Park, Young Ju(1996) revised and complemented by investigator to measure practice of Taekyo. The Cronbach's alpha value of each tool was .88 in recognition of Taekyo, while the value was .90 in practice of Taekyo. For data analysis, this study used the descriptive and statistical analysis, Pearson correlation, t-test, ANOVA, Tukey's post hoc contrast, and Stepwise multiple regression in accordance with the purpose of this study with using SPSS Win 7.5 program. The results were as follows ; 1. The practice of Taekyo was low in comparison with recognition of Teakyo by showing average 4.28 points and standard deviation 0.48 at level of recognition of pregnant women about Taekyo on the basis of 5 points and showing to show average 2.81 points and standard deviation 0.36 at practice level on the basis of 4 points. 2. They showed the higher level of recognition on Taekyo at high educational background of pregnant woman(F=3.735, p=.005), Roman catholicism (F=4.570, p=.002), satisfied married life(F=5.448, p=.004), high monthly income(F=6.096, p=.000) and cases of hoping pregnancy(F=2.525, p=.012). 3. They showed the higher level of practice on Taekyo at high educational background of pregnant woman(F=2.883, P=.022), Roman catholicism(F=3.616, p=.032), satisfied married life(F=19.924, p=.000), good health condition(F=2.386, p=.017), cases of hoping pregnancy(F=0.677, p=.000), cases of planning pregnancy with husband(F=3.024, p=.001), cases of regular prenatal care before delivery(F=0.241, p=.005), cases of maternal breast feeding (F=9.132, p=.000), and the number of less children(F=2.763, p=.041). 4. In result of examining correlation between recognition and practice of Taekyo, they showed high level of practice on Taekyo under high level of recognition of pregnant women on Taekyo by showing the statistically significant correlation. 5. In result of examining the related factors that affect recognition and practice of Taekyo y the object, practice of Taekyo had 16.8 percents of explanatory range, purpose of practicing Taekyo 8.5 percents of explanatory range, and monthly income 1.9 percent of explanatory range as variables of affecting recognition of Taekyo. The total explanatory range was 27.2 percents, Recognition of Taekyo had 16.1 percents of explanatory ragne, time of starting Taekyo 3.2 percents, health condition 2.2 percents of explanatory range, condition of hoping pregnancy 1.1 percent of explanatory range, satisfaction of married life 0.8 percent of explanatory range, and religion 0.6 percent of explanatory range as variables of affecting practice of Taekyo. The total explanatory range was 24.0 percents.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.14 no.4
• /
• pp.157-163
• /
• 2014

User's sensitivity is recognized as a very important parameter for communication between company, government and personnel. Especially in many studies, researchers use voice tone, voice speed, facial expression, moving direction and speed of body, and gestures to recognize the sensitivity. Multiplex modality is more precise than single modality however it has limited recognition rate and overload of data processing according to multi-sensing also an excellent algorithm is needed to deduce the sensing value. That is as each modality has different concept and property, errors might be happened to convert the human sensibility to standard values. To deal with this matter, the sensibility expression modality is needed to be extracted using technologies like analyzing of relational network, understanding of context and digital filter from multiplex modality. In specific situation to recognize the sensibility if the priority modality and other surrounding modalities are processed to implicit values, a robust system can be composed in comparison to the consuming of computer resource. As a result of this paper, it is proposed how to assign the weight of multiplex modality using implicit data.

• Proceedings of the KIEE Conference
• /
• 2002.07d
• /
• pp.2755-2757
• /
• 2002

In this paper, we propose a now architecture for hardware implementation of digital neural network. By adopting flexible ladder-style bus and internal connection network into traditional SIMD-type digital neural network architecture, the proposed architecture enables fast processing that is based on parallelism, while does not abandon the flexibility and extensibility of the traditional approach. In the proposed architecture, users can change the network topology by setting configuration registers. Such reconfigurability on hardware allows enough usability like software simulation. We implement the proposed design on real FPGA, and configure the chip to multi-layer perceptron with back propagation for alphabet recognition problem. Performance comparison with its software counterpart shows its value in the aspect of performance and flexibility.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.6
• /
• pp.1530-1544
• /
• 2023

Data monitoring is an important foundation of modern science. In most cases, the monitoring data is time-series data, which has high application value. The deep learning algorithm has a strong nonlinear fitting capability, which enables the recognition of time series by capturing anomalous information in time series. At present, the research of time series recognition based on deep learning is especially important for data monitoring. Deep learning algorithms require a large amount of data for training. However, abnormal sample is a small sample in time series, which means the number of abnormal time series can seriously affect the accuracy of recognition algorithm because of class imbalance. In order to increase the number of abnormal sample, a data augmentation method called GANBATS (GAN-based Bi-LSTM and Attention for Time Series) is proposed. In GANBATS, Bi-LSTM is introduced to extract the timing features and then transfer features to the generator network of GANBATS.GANBATS also modifies the discriminator network by adding an attention mechanism to achieve global attention for time series. At the end of discriminator, GANBATS is adding averagepooling layer, which merges temporal features to boost the operational efficiency. In this paper, four time series datasets and five data augmentation algorithms are used for comparison experiments. The generated data are measured by PRD(Percent Root Mean Square Difference) and DTW(Dynamic Time Warping). The experimental results show that GANBATS reduces up to 26.22 in PRD metric and 9.45 in DTW metric. In addition, this paper uses different algorithms to reconstruct the datasets and compare them by classification accuracy. The classification accuracy is improved by 6.44%-12.96% on four time series datasets.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.6
• /
• pp.107-115
• /
• 2008

Face feature detection plays an important role in application such as automatic speechreading, human computer interface, face recognition, and face image database management. We proposed a automatic speechreading feature detection algorithm for color image using color information. Face feature pixels is represented for various value because of the luminance and chrominance in various color space. Face features are detected by amplifying, reducing the value and make a comparison between the represented image. The eye and nose position, inner boundary of lips and the outer line of the tooth is detected and show very encouraging result.

• Journal of the Korean Home Economics Association
• /
• v.42 no.9
• /
• pp.111-134
• /
• 2004

The purpose of this dissertation is firstly to examine the level of pro-environmental behavior of urban employed wives depending on their life style type and secondly to identify effective ways to promote their pro-environmental behavior. A structured questionnaire interview was conducted with 700 urban employed wives who lived in the Seoul Metropolitan area, and 566 of the responses were valid for analysis. For statistical analysis, this research reviewed the frequencies, percentage, mean, standard deviation(SD), Pearson's correlations, Cronbach's u, factor analysis, cluster analysis, ANOVA, $\chi$$^2$-test, Duncan's Multiple Range Test, and multiple regression using SPSS/PC WIN. The findings of analysis of the study are as follows: 1. Among life style types of employed wives, the order of ecological value was orientation type (37.3%), followed by economical value orientation type (25.8%), uninterested type (18.7%), and convenience-centric value orientation type (18.2%).Pro-environmental behavior scored relatively highly at 3.45 in average. 2. In the analysis of the relationship between life style and background variations, every variation except environmental knowledge was meaningful. 3. In the relationship between pro-environment behavior and background variations, every variation was meaningful except housing types, having helper or not, and environmental knowledge. 4. The recognition level of environmental pollution was important among the variations affecting pro-environmental behavior. 5. There was a difference in pro-environmental behaviors by the following life style types: ecological value orientation, economical value orientation, convenience centric orientation and uninterested. 6. For the relative contribution comparison of background variations (socio-economic variation and environmental variation) and life style variations to the pro-environmental behavior of urban empolyed wives, this research additionally applied each independent variable group. As a result, the explanation level drastically increased in the third step that analyzed the relationship with life style.