• Title/Summary/Keyword: continuous speech

Search Result 319, Processing Time 0.023 seconds

The Correlation between Asthma and Oral and Mental Health (천식과 구강건강 및 정신건강과의 관련성)

  • Yoon, Soo-Yeon;Lee, Kyung-Hee
    • Journal of The Korean Society of Integrative Medicine
    • /
    • v.9 no.3
    • /
    • pp.47-58
    • /
    • 2021
  • Purpose : This study aimed to investigate the association between asthma and oral health and factors influencing asthma in adults. We also investigated whether asthma is related to mental health and physiological factors of blood. Methods : Data from 12,639 adults was taken from the 7th period (2016~2018) Korea National Health and Nutrition Examination Survey and analyzed using with SPSS 22.0 statistical program. Statistical analysis of data included frequency analysis, cross-analysis, and logistic regression analysis. For continuous data, an independent sample t-test was performed. The statistical significance level was defined as 0.05. Results : The probability of asthma occurrence was statistically different within general characteristics (gender, age, school grade, income, and drinking). By independent variables in a logistic regression analysis, the asthma diagnosis group had more people with speech discomfort (OR=1.37), chewing discomfort (OR=1.29), and oral pain (OR=.73). We found that people with asthma had a more unfavorable perception of their health (OR=1.73), suffered more depression (OR=.45), stress (OR=.66), and limited activity (OR=2.38). Moreover, the white blood cell count (OR=1.10) and high sensitivity C-reactive protein test (OR=1.06) also showed higher values than the control group. Conclusion : Our study showed that oral health and mental health were associated with the asthma, and influencing factors were oral health and behavior and mental health-related characteristics. Therefore, it is necessary to understand asthma-related risk factors for oral health and recognize the importance of systematic oral care education and regular dental visits for patients receiving asthma treatment. Thus, this study provides valuable insights on appropriate oral health management and prevention of asthma in patients.

Research on Improvement of Patient Quality and Perception of Hospital Operation Effect after Medical Institution Certification - For Nursing Hospitals and Western Hospitals - (의료기관 인증 후 환자의 질 향상과 병원운영효과 인식도 조사연구 - 요양병원과 양방병원 대상 -)

  • Lee, Hye-Seung;Park, Hyun-Rin
    • Journal of Korea Entertainment Industry Association
    • /
    • v.14 no.7
    • /
    • pp.559-570
    • /
    • 2020
  • The purpose of this study was to classify the internal members of nursing hospitals and Western hospitals that received the certification system of medical institutions, and to examine the effect of certification on member satisfaction, job stress, hospital operation effect, and improvement of medical services. In nursing hospitals, the certification system was higher in member satisfaction, hospital operation effect, and medical service effect than in Western hospitals, and members of Western hospitals were higher in job stress. In both nursing hospitals and Western hospitals, the satisfaction of members, hospital operation effect, and medical service effect according to certification showed positive (+) results. It is believed that the effect of the certification system has been empirically high in nursing hospitals as mandatory certification from 2013. Therefore, this study aims to contribute to the efficiency of hospital management and improvement of patient satisfaction through continuous quality management of medical care by analyzing the effect of certification system on medical service improvement.

Development of smartphone-based voice therapy program (스마트폰기반 음성치료 프로그램 개발연구)

  • Lee, Ha-Na;Park, Jun-Hee;Yoo, Jae-Yeon
    • Phonetics and Speech Sciences
    • /
    • v.11 no.1
    • /
    • pp.51-61
    • /
    • 2019
  • The purpose of this study was to develop a smartphone based voice therapy program for patients with voice disorders. Contents of voice therapy were collected through analysis of mobile contents related to voice therapy in Korea, experts and users' demand survey, and the program was developed using Android Studio. Content needed for voice therapy was collected through analysis of mobile contents related to voice therapy. The user satisfaction evaluation for application was conducted for five patient with functional voice disorders. The results showed that the mobile contents related to voice therapy in Korea were mostly related to breathing, followed by voice and singing, but only 13 applications were practically practiced for voice therapy. Expert and user demand surveys showed that the patients and therapists both had a high need for content that could provide voice training in places other than the treatment room. Based on this analysis, 'Home Voice Trainer', an smartphone based voice therapy program, was developed. Home Voice Trainer is an application for voice therapy and management based on Android smartphones. It is designed to train voice therapy activities at home that have been trained offline. In addition, the records of voice training of patients were managed online so that patients can maintain voice improvement through continuous voice consulting even after the end of voice therapy. User evaluations show that patients are satisfied with the difficulty and content of voice therapy programs provided by home voice trainers, but lack of a portion of user interface, such as the portion of home button and interface between screens. Further study suggests the clinical application of home voice trainer to the patients with voice disorders. It is expected that the development study and the clinical application of smart contents related to voice therapy will be actively conducted.

A Study on Spoken Digits Analysis and Recognition (숫자음 분석과 인식에 관한 연구)

  • 김득수;황철준
    • Journal of Korea Society of Industrial Information Systems
    • /
    • v.6 no.3
    • /
    • pp.107-114
    • /
    • 2001
  • This paper describes Connected Digit Recognition with Considering Acoustic Feature in Korea. The recognition rate of connected digit is usually lower than word recognition. Therefore, speech feature parameter and acoustic feature are employed to make robust model for digit, and we could confirm the effect of Considering. Acoustic Feature throughout the experience of recognition. We used KLE 4 connected digit as database and 19 continuous distributed HMM as PLUs(Phoneme Like Units) using phonetical rules. For recognition experience, we have tested two cases. The first case, we used usual method like using Mel-Cepstrum and Regressive Coefficient for constructing phoneme model. The second case, we used expanded feature parameter and acoustic feature for constructing phoneme model. In both case, we employed OPDP(One Pass Dynamic Programming) and FSA(Finite State Automata) for recognition tests. When appling FSN for recognition, we applied various acoustic features. As the result, we could get 55.4% recognition rate for Mel-Cepstrum, and 67.4% for Mel-Cepstrum and Regressive Coefficient. Also, we could get 74.3% recognition rate for expanded feature parameter, and 75.4% for applying acoustic feature. Since, the case of applying acoustic feature got better result than former method, we could make certain that suggested method is effective for connected digit recognition in korean.

  • PDF

Exploratory Analysis of Consumer Responses to Korea-China Mobile Payment Service using Keyword Analysis -Focus on Kakao Pay and Alipay- (키워드 분석을 활용한 한·중 모바일 결제 서비스에 대한 소비자 반응 탐색적 분석 -카카오페이와 알리페이를 중심으로-)

  • Ke, Jung;Yoon, Donghwa;Ahn, Jinhyun
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.22 no.6
    • /
    • pp.514-523
    • /
    • 2021
  • Recently, the proliferation of mobile simple payment services has been increasingly affecting people's lives. In addition, the increase in research from both China and Korea shows that the continuous development of simple mobile payment services will be very important in the future. The blog posts mentioning Kakao Pay and Alipay were collected, and keyword analysis was performed to investigate differences in consumers' responses to Kakao Pay and Alipay on social media. The frequency of keywords for each part of speech and the frequency of co-occurred words mentioned in one sentence were analyzed. Specifically, common words that appear in both Kakao Pay and Alipay blogs were extracted. The cooccurred words were analyzed to examine how different reactions were made on the same subject. As a result of the analysis, there were concerns among consumers about the trust of Kakao Pay and Alipay's benefits. For a mobile payment service to become competitive, it is necessary to add various additional services or solve security problems.

Analysis of Generative AI Technology Trends Based on Patent Data (특허 데이터 기반 생성형 AI 기술 동향 분석)

  • Seongmu Ryu;Taewon Song;Minjeong Lee;Yoonju Choi;Soonuk Seol
    • The Journal of Korea Institute of Information, Electronics, and Communication Technology
    • /
    • v.17 no.1
    • /
    • pp.1-9
    • /
    • 2024
  • This paper analyzes the trends in generative AI technology based on patent application documents. To achieve this, we selected 5,433 generative AI-related patents filed in South Korea, the United States, and Europe from 2003 to 2023, and analyzed the data by country, technology category, year, and applicant, presenting it visually to find insights and understand the flow of technology. The analysis shows that patents in the image category account for 36.9%, the largest share, with a continuous increase in filings, while filings in the text/document and music/speech categories have either decreased or remained stable since 2019. Although the company with the highest number of filings is a South Korean company, four out of the top five filers are U.S. companies, and all companies have filed the majority of their patents in the U.S., indicating that generative AI is growing and competing centered around the U.S. market. The findings of this paper are expected to be useful for future research and development in generative AI, as well as for formulating strategies for acquiring intellectual property.

Maxillary complete denture with posterior zirconia occlusion and mandibular implant support fixed prostheses in completely edentulous patients with orofacial dystonia (구강안면 근긴장이상을 가진 완전 무치악 환자에서 구치부 지르코니아 교합면을 갖는 상악 총의치와 하악 임플란트 지지 고정성 보철물의 수복)

  • Jong-Min Seo;Chang-Mo Jeong;So-Hyoun Lee
    • Journal of Dental Rehabilitation and Applied Science
    • /
    • v.39 no.4
    • /
    • pp.237-249
    • /
    • 2023
  • Orofacial dystonia is a neuromotor disorder that causes irregular or repetitive movements of the face, lips, tongue, and jaw involuntarily, also called tic disorder. Edentulous patients with these symptoms experience functional and aesthetic problems, including difficulty using complete dentures, speech and swallowing difficulties, and orofacial pain. In this case, for a patient with orofacial dystonia who experienced complete edentulism at a relatively young age, restorative treatment was performed with a maxillary complete denture with bilateral posterior zirconia occlusal surfaces and a mandibular implant-supported fixed prosthesis, and continuous smile training was performed. The aim was to improve the aesthetics of facial muscles. As a result of the treatment, the patient was very satisfied with not only improved chewing function and aesthetics, but also regained psychological stability and was able to lead a normal daily life, so we would like to report this.

Sentiment Analysis of Korean Reviews Using CNN: Focusing on Morpheme Embedding (CNN을 적용한 한국어 상품평 감성분석: 형태소 임베딩을 중심으로)

  • Park, Hyun-jung;Song, Min-chae;Shin, Kyung-shik
    • Journal of Intelligence and Information Systems
    • /
    • v.24 no.2
    • /
    • pp.59-83
    • /
    • 2018
  • With the increasing importance of sentiment analysis to grasp the needs of customers and the public, various types of deep learning models have been actively applied to English texts. In the sentiment analysis of English texts by deep learning, natural language sentences included in training and test datasets are usually converted into sequences of word vectors before being entered into the deep learning models. In this case, word vectors generally refer to vector representations of words obtained through splitting a sentence by space characters. There are several ways to derive word vectors, one of which is Word2Vec used for producing the 300 dimensional Google word vectors from about 100 billion words of Google News data. They have been widely used in the studies of sentiment analysis of reviews from various fields such as restaurants, movies, laptops, cameras, etc. Unlike English, morpheme plays an essential role in sentiment analysis and sentence structure analysis in Korean, which is a typical agglutinative language with developed postpositions and endings. A morpheme can be defined as the smallest meaningful unit of a language, and a word consists of one or more morphemes. For example, for a word '예쁘고', the morphemes are '예쁘(= adjective)' and '고(=connective ending)'. Reflecting the significance of Korean morphemes, it seems reasonable to adopt the morphemes as a basic unit in Korean sentiment analysis. Therefore, in this study, we use 'morpheme vector' as an input to a deep learning model rather than 'word vector' which is mainly used in English text. The morpheme vector refers to a vector representation for the morpheme and can be derived by applying an existent word vector derivation mechanism to the sentences divided into constituent morphemes. By the way, here come some questions as follows. What is the desirable range of POS(Part-Of-Speech) tags when deriving morpheme vectors for improving the classification accuracy of a deep learning model? Is it proper to apply a typical word vector model which primarily relies on the form of words to Korean with a high homonym ratio? Will the text preprocessing such as correcting spelling or spacing errors affect the classification accuracy, especially when drawing morpheme vectors from Korean product reviews with a lot of grammatical mistakes and variations? We seek to find empirical answers to these fundamental issues, which may be encountered first when applying various deep learning models to Korean texts. As a starting point, we summarized these issues as three central research questions as follows. First, which is better effective, to use morpheme vectors from grammatically correct texts of other domain than the analysis target, or to use morpheme vectors from considerably ungrammatical texts of the same domain, as the initial input of a deep learning model? Second, what is an appropriate morpheme vector derivation method for Korean regarding the range of POS tags, homonym, text preprocessing, minimum frequency? Third, can we get a satisfactory level of classification accuracy when applying deep learning to Korean sentiment analysis? As an approach to these research questions, we generate various types of morpheme vectors reflecting the research questions and then compare the classification accuracy through a non-static CNN(Convolutional Neural Network) model taking in the morpheme vectors. As for training and test datasets, Naver Shopping's 17,260 cosmetics product reviews are used. To derive morpheme vectors, we use data from the same domain as the target one and data from other domain; Naver shopping's about 2 million cosmetics product reviews and 520,000 Naver News data arguably corresponding to Google's News data. The six primary sets of morpheme vectors constructed in this study differ in terms of the following three criteria. First, they come from two types of data source; Naver news of high grammatical correctness and Naver shopping's cosmetics product reviews of low grammatical correctness. Second, they are distinguished in the degree of data preprocessing, namely, only splitting sentences or up to additional spelling and spacing corrections after sentence separation. Third, they vary concerning the form of input fed into a word vector model; whether the morphemes themselves are entered into a word vector model or with their POS tags attached. The morpheme vectors further vary depending on the consideration range of POS tags, the minimum frequency of morphemes included, and the random initialization range. All morpheme vectors are derived through CBOW(Continuous Bag-Of-Words) model with the context window 5 and the vector dimension 300. It seems that utilizing the same domain text even with a lower degree of grammatical correctness, performing spelling and spacing corrections as well as sentence splitting, and incorporating morphemes of any POS tags including incomprehensible category lead to the better classification accuracy. The POS tag attachment, which is devised for the high proportion of homonyms in Korean, and the minimum frequency standard for the morpheme to be included seem not to have any definite influence on the classification accuracy.

Innovative approaches to the health problems of rural Korea (한국농촌보건(韓國農村保健)의 문제점(問題點)과 개선방안(改善方案))

  • Loh, In-Kyu
    • Journal of agricultural medicine and community health
    • /
    • v.1 no.1
    • /
    • pp.5-9
    • /
    • 1976
  • The categories of national health problems may be mainly divided into health promotion, problems of diseases, and population-economic problems which are indirectly related to health. Of them, the problems of diseases will be exclusively dealt with this speech. Rurality and Disease Problems There are many differences between rural and urban areas. In general, indicators of rurality are small size of towns, dispersion of the population, remoteness from urban centers, inadequacy of public transportation, poor communication, inadequate sanitation, poor housing, poverty, little education lack of health personnels and facilities, and in-accessibility to health services. The influence of such conditions creates, directly or indirectly, many problems of diseases in the rural areas. Those art the occurrence of preventable diseases, deterioration and prolongation of illness due to loss of chance to get early treatment, decreased or prolonged labour force loss, unnecessary death, doubling of medical cost, and economic loss. Some Considerations of Innovative Approach The followings art some considerations of innovative approaches to the problems of diseases in the rural Korea. 1. It would be essential goal of the innovative approaches that the damage and economic loss due to diseases will be maintained to minimum level by minimizing the absolute amount of the diseases, and by moderating the fee for medical cares. The goal of the minimization of the disease amount may be achieved by preventive services and early treatment, and the goal of moderating the medical fee may be achieved by lowering the prime cost and by adjusting the medical fees to reasonable level. 2. Community health service or community medicine will be adopted as a innovative means to disease problems. In this case, a community is defined as an unit area where supply and utilization of primary service activities can be accomplished within a day. The essential nature o the community health service should be such activities as health promotion, preventive measures, medical care, and rehabilitation performing efficiently through the organized efforts of the residents in a community. Each service activity should cover all members of the residents in a community in its plan and performance. The cooperation of the community peoples in one of the essential elements for success of the service program, The motivations of their cooperative mood may be activated through several ways: when the participation of the residents in service program of especially the direct participation of organized cooperation of the area leaders art achieved through a means of health education: when the residents get actual experience of having received the benefit of good quality services; and when the health personnels being armed with an idealism that they art working in the areas to help health problems of the residents, maintain good human relationships with them. For the success of a community health service program, a personnel who is in charge of leadership and has an able, a sincere and a steady characters seems to be required in a community. The government should lead and support the community health service programs of the nation under the basis of results appeared in the demonstrative programs so as to be carried out the programs efficiently. Moss of the health problems may be treated properly in the community levels through suitable community health service programs but there might be some problems which art beyond their abilities to be dealt with. To solve such problems each community health service program should be under the referral systems which are connected with health centers, hospitals, and so forth. 3. An approach should be intensively groped to have a physician in each community. The shortage of physicians in rural areas is world-wide problem and so is the Korean situation. In the past the government has initiated a system of area-limited physician, coercion, and a small scale of scholarship program with unsatisfactory results. But there might be ways of achieving the goal by intervice, broadened, and continuous approaches. There will be several ways of approach to motivate the physicians to be settled in a rural community. They are, for examples, to expos the students to the community health service programs during training, to be run community health service programs by every health or medical schools and other main medical facilities, communication activities and advertisement, desire of community peoples to invite a physician, scholarship program, payment of satisfactory level, fulfilment of military obligation in case of a future draft, economic growth and development of rural communities, sufficiency of health and medical facilities, provision of proper medical care system, coercion, and so forth. And, hopefully, more useful reference data on the motivations may be available when a survey be conducted to the physicians who are presently engaging in the rural community levels. 4. In communities where the availability of a physician is difficult, a trial to use physician extenders, under certain conditions, may be considered. The reason is that it would be beneficial for the health of the residents to give them the remedies of primary medical care through the extenders rather than to leave their medical problems out of management. The followings are the conditions to be considered when the physician extenders are used: their positions will be prescribed as a temporary one instead of permanent one so as to allow easy replacement of the position with a physician applicant; the extender will be under periodic direction and supervision of a physician, and also referral channel will be provided: legal constraints will be placed upon the extenders primary care practice, and the physician extenders will used only under the public medical care system. 5. For the balanced health care delivery, a greater investment to the rural areas is needed to compensate weak points of a rurality. The characteristics of a rurality has been already mentioned. The objective of balanced service for rural communities to level up that of urban areas will be hard to achieve without greater efforts and supports. For example, rural communities need mobile powers more than urban areas, communication network is extremely necessary at health delivery facilities in rural areas as well as the need of urban areas, health and medical facilities in rural areas should be provided more substantially than those of urban areas to minimize, in a sense, the amount of patient consultation and request of laboratory specimens through referral system of which procedures are more troublesome in rural areas, and more intensive control measures against communicable diseases are needed in rural areas where greater numbers of cases are occurred under the poor sanitary conditions.

  • PDF