• Journal of the Korean Society of School Health
• /
• v.8 no.1
• /
• pp.117-131
• /
• 1995

The purpose of this study is to grasp the nature of health behavior to pactice in order to keep and improve the optimal health in the current status of the cancer patients. The subjects were 21 cancer patients, who knew about their disease for themselves, could communicate without mental disease history, and could understand the purpose of this study and cooperate, in a university hospital in Seoul. The data were collected by direct interview from July 15 to Oct. 17, 1994. The interview took about 1~2hours per one time for each paitent by unstructural and open questions. And they were classified into some similar contents on the basis of the phenomenological analysis and categorized. The analyzed results are as follows: 1) In the daily life before and after diagnosis as cancer patients, they were categorized into 6 areas-the state of movement, sleeping, nutrition and diet, society and economy, drinking and somking, and recognition of their health. 2) In the experience of health behavior of cancer patents, they were categorized into 7 areas-the state of movement, sleeping, nutrition and diet, society and economy, drinking and smoking, recognition of their health, and psychology etc. According to the analyzed results of daily life before diagnosis as cancer patients, it turned out that they didn't recognize the problems for their health habit and made their disease state bad by irresolute characteristics which hesitated to practice rightly, renunciation, and irresponsibility and so on, even if they had much interests in their health and were motivated. Therefore, it is necessary to recognize and have an individual-centric interests in order to change the pattern of life for optimal health state to some extent. In the health behavior of cancer patients, it turned out that they had interests in the state of nutrition and diet the most. Even though they experienced the change of serious nutritive state due to the bad gastroenteric trouble by anticancer treatment, they were trying to have a regular eating habit refraining from irritant food and use folk remedies or healthy food temperating the taste food thoroughly, they also showed the sensitive response for nutrition. In addition, they appeared to use the traditional medical treatment or the folk remedies very seriously without abuse. In consideration of it, it is desirable to use them together with the modern medical treatment intercomplementarily and necessary to look into the types for cancer patients and their benefits.

• Journal of the Korean Society for information Management
• /
• v.34 no.1
• /
• pp.51-71
• /
• 2017

This study conducted a survey to measure recognition distance between the materials which are located separately in a children's library targeting 200 elementary school lower grade students, higher grade students, and school parents(adults). And compared recognition distance between the elements of materials of individual visitor group with multidimensional scaling and K-mean group analysis. Multidimensional Scaling (MDS) is a technique for projecting the cognitive state in space by evaluating the similarity or attribute of the analysis target. Even though it is mainly used for market diagnosis in marketing, It can also be applied to present an ideal physical layout plan by analyzing the distance. As a result of analysis, the main discoveries are as follows. First, elementary school students cognize child, baby and computer materials should be adjacent as a same group. But recognition of adults(school parents) is reflected by differing from elementary school students vastly. They cognize that computer materials should be formed as a special group separated from child and baby's materials. Second, elementary school higher graders and adults(school parents) groups also want to separate their main reading materials from baby's book, therefore They both want to secure silent reading space separating from baby. Third, as a result to confirming how this recognition distance system of materials is reflected in a real children's library through three children's libraries in Y-gu, Incheon, there is no library with structure according perfectly with a recognition system of a particular class, but a recognition system of adults and elementary school students is partially reflected because baby, child and computer materials, and baby and child materials are commonly separated and placed. It is difficult to insist that a recognition system of a visitor group, especially a recognition system of children is absolute consideration conditions in material placement of a children's library. However, understanding cognition of the user groups can be an important evidentiary factors to offer differentiated service space according to visitors and effective placement of the elements of library resources.

• ETRI Journal
• /
• v.42 no.1
• /
• pp.90-100
• /
• 2020

Named entity recognition (NER) continues to be an important task in natural language processing because it is featured as a subtask and/or subproblem in information extraction and machine translation. In Urdu language processing, it is a very difficult task. This paper proposes various deep recurrent neural network (DRNN) learning models with word embedding. Experimental results demonstrate that they improve upon current state-of-the-art NER approaches for Urdu. The DRRN models evaluated include forward and bidirectional extensions of the long short-term memory and back propagation through time approaches. The proposed models consider both language-dependent features, such as part-of-speech tags, and language-independent features, such as the "context windows" of words. The effectiveness of the DRNN models with word embedding for NER in Urdu is demonstrated using three datasets. The results reveal that the proposed approach significantly outperforms previous conditional random field and artificial neural network approaches. The best f-measure values achieved on the three benchmark datasets using the proposed deep learning approaches are 81.1%, 79.94%, and 63.21%, respectively.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2005.06a
• /
• pp.1958-1962
• /
• 2005

A driver's emotion is a very important factor of safe driving. This paper classified a driver's emotion into 3 major emotions, can be occur when driving a car: Surprise, Joy, Tired. And It evaluated the classifier using Hidden Markov Models, which have observation sequence as bio-signals. It used the 2-D emotional plane to classfiy a human's general emotion state. The 2-D emotional plane has 2 axes of pleasure-displeasure and arsual-relaxztion. The used bio-signals are Galvanic Skin Response(GSR) and Heart Rate Variability(HRV), which are easy to acquire and reliable. We classified several moving pictures into 3 major emotions to evaluate our HMM system. As a result of driving simulations for each emotional situations, we can get recognition rates of 67% for surprise, 58% for joy and 52% for tired.

• Journal of Environmental Health Sciences
• /
• v.21 no.4
• /
• pp.63-74
• /
• 1995

The objective of this study were to identify the state of re. cognition and attitude of residents in Seoul city about air environment and to identify factors affecting attitude toward air environment. Study object was residents in Seoul city sampled by multistage random proportional sampling. Sample size was 0.0067%(500 persons) of total residents in Seoul city. The results were divided into two parts: (1) descriptive results of recognition and attitude toward air environment, (2) results of factor analysis to classify categories of attitudes toward air environment and regression analysis to identify factors affecting attitude toward air environment. Most of resident in Seoul city recognized that air environment in Seoul city was highly polluted and was not satisfactory. Experience of damage of air pollution was reported in about 70% of residents in Seoul city. More than 60% of residents in Seoul city had concern about air environment. Attitude toward air environment were classified into four categories using factor analysis: Necessity of intervention of local government for air environment conservation, Participation of residents and enterprises for air environment conservation, Optimistic attitude about air pollution, Preference of economy. Factors affecting the above attitudes were knowledge about air pollution, knowledge about policies and institutions related air environment conservation, concern about air environment, educational level, subjective assessment of air environment, sex, marital status. In conclusion this study suggested providing information of air environment in Seoul city to the residents and to educating residents for making positive attitude about air environment conservation.

• Journal of IKEEE
• /
• v.24 no.2
• /
• pp.523-528
• /
• 2020

With a widespread of sensor-rich mobile devices, the analysis of human activities becomes more general and simpler than ever before. In this paper, we propose two deep neural networks that efficiently and accurately perform human activity recognition (HAR) using tri-axial accelerometers. In combination with powerful modern deep learning techniques like batch normalization and LSTM networks, our model outperforms baseline approaches and establishes state-of-the-art results on WISDM dataset.

• Journal of Photoscience
• /
• v.6 no.4
• /
• pp.165-170
• /
• 1999

Asymmetric recognition of chiral alcohol by fluorenone derivatives with chiral substituents through intermolecular hydrogen bonding interaction in the singlet excited state was attempted. 1-((1S, 2R, 5S)-(+)-Menthyloxycarbonyl)aminofluoren-9-one (1-MAF) and 1-((1S, 2R, 5S)-(+)-menthyloxycarbonyl)oxyfluoren-9-one (1-MOF) were synthesized and their photophysical behaviors were characterized by the measurement of absorption and fluorescence spectra, as well as the quantum yield and the lifetime of fluorescence. The excited singlet states of 1-MAF and 1-MOF were revealed to have characteristics similar to those of fluorenone, though the intramolecular CT nature was fairly suppressed as compared with 3- and 4-substituted aminofluorenones. Fluorescences of 1-MAF and 1-MOF in acetonitrile were quenched by the addition of alcohols. Differences in fluorescence quenching efficiency were hardly observe for rather small chiral alcohols such as (R)-(-)- or (S)-(+)-2-butanol, while bulky alcohols such as menthol and isopinocampheol showed chiral recognition effects in their fluorescence quenching of 1-MAF in either acetonitrile or butyronitrile.

• Speech Sciences
• /
• v.15 no.2
• /
• pp.67-77
• /
• 2008

In this paper, we implemented a robust speech recognizer using the TMS320VC33 DSP. For this implementation, we had built speech and noise database suitable for the recognizer using spectral subtraction method for noise removal. The recognizer has an explicit structure in aspect that a speech signal is enhanced through spectral subtraction before endpoints detection and feature extraction. This helps make the operation of the recognizer clear and build HMM models which give minimum model-mismatch. Since the recognizer was developed for the purpose of controlling car facilities and voice dialing, it has two recognition engines, speaker independent one for controlling car facilities and speaker dependent one for voice dialing. We adopted a conventional DTW algorithm for the latter and a continuous HMM for the former. Though various off-line recognition test, we made a selection of optimal conditions of several recognition parameters for a resource-limited embedded recognizer, which led to HMM models of the three mixtures per state. The car noise added speech database is enhanced using spectral subtraction before HMM parameter estimation for reducing model-mismatch caused by nonlinear distortion from spectral subtraction. The hardware module developed includes a microcontroller for host interface which processes the protocol between the DSP and a host.

• Journal of the Korea Computer Graphics Society
• /
• v.24 no.4
• /
• pp.1-9
• /
• 2018

We propose an emotional training framework that can determine the initial symptom of schizophrenia by using emotional analysis method through facial expression change. We use Emotion API in Microsoft to obtain facial expressions and emotion values at the present time. We analyzed these values and recognized subtle facial expressions that change with time. The emotion states were classified according to the peak analysis-based variance method in order to measure the emotions appearing in facial expressions according to time. The proposed method analyzes the lack of emotional recognition and expressive ability by using characteristics that are different from the emotional state changes classified according to the six basic emotions proposed by Ekman. As a result, the analyzed values are integrated into the image color transfer framework so that users can easily recognize and train their own emotional changes.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.9C
• /
• pp.756-760
• /
• 2010

This paper is proposed to an novel facial behavior recognition system for driver's fatigue detection. Facial behavior is shown in various facial feature such as head expression, head pose, gaze, wrinkles. But it is very difficult to clearly discriminate a certain behavior by the obtained facial feature. Because, the behavior of a person is complicated and the face representing behavior is vague in providing enough information. The proposed system for facial behavior recognition first performs detection facial feature such as eye tracking, facial feature tracking, furrow detection, head orientation estimation, head motion detection and indicates the obtained feature by AU of FACS. On the basis of the obtained AU, it infers probability each state occur through Bayesian network.