• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.111-124
• /
• 2018

This study aims to develop a classification model for predicting the occurrence of hyperlipidemia, one of the chronic diseases. Prior studies applying data mining techniques for predicting disease can be classified into a model design study for predicting cardiovascular disease and a study comparing disease prediction research results. In the case of foreign literatures, studies predicting cardiovascular disease were predominant in predicting disease using data mining techniques. Although domestic studies were not much different from those of foreign countries, studies focusing on hypertension and diabetes were mainly conducted. Since hypertension and diabetes as well as chronic diseases, hyperlipidemia, are also of high importance, this study selected hyperlipidemia as the disease to be analyzed. We also developed a model for predicting hyperlipidemia using SVM and meta learning algorithms, which are already known to have excellent predictive power. In order to achieve the purpose of this study, we used data set from Korea Health Panel 2012. The Korean Health Panel produces basic data on the level of health expenditure, health level and health behavior, and has conducted an annual survey since 2008. In this study, 1,088 patients with hyperlipidemia were randomly selected from the hospitalized, outpatient, emergency, and chronic disease data of the Korean Health Panel in 2012, and 1,088 nonpatients were also randomly extracted. A total of 2,176 people were selected for the study. Three methods were used to select input variables for predicting hyperlipidemia. First, stepwise method was performed using logistic regression. Among the 17 variables, the categorical variables(except for length of smoking) are expressed as dummy variables, which are assumed to be separate variables on the basis of the reference group, and these variables were analyzed. Six variables (age, BMI, education level, marital status, smoking status, gender) excluding income level and smoking period were selected based on significance level 0.1. Second, C4.5 as a decision tree algorithm is used. The significant input variables were age, smoking status, and education level. Finally, C4.5 as a decision tree algorithm is used. In SVM, the input variables selected by genetic algorithms consisted of 6 variables such as age, marital status, education level, economic activity, smoking period, and physical activity status, and the input variables selected by genetic algorithms in artificial neural network consist of 3 variables such as age, marital status, and education level. Based on the selected parameters, we compared SVM, meta learning algorithm and other prediction models for hyperlipidemia patients, and compared the classification performances using TP rate and precision. The main results of the analysis are as follows. First, the accuracy of the SVM was 88.4% and the accuracy of the artificial neural network was 86.7%. Second, the accuracy of classification models using the selected input variables through stepwise method was slightly higher than that of classification models using the whole variables. Third, the precision of artificial neural network was higher than that of SVM when only three variables as input variables were selected by decision trees. As a result of classification models based on the input variables selected through the genetic algorithm, classification accuracy of SVM was 88.5% and that of artificial neural network was 87.9%. Finally, this study indicated that stacking as the meta learning algorithm proposed in this study, has the best performance when it uses the predicted outputs of SVM and MLP as input variables of SVM, which is a meta classifier. The purpose of this study was to predict hyperlipidemia, one of the representative chronic diseases. To do this, we used SVM and meta-learning algorithms, which is known to have high accuracy. As a result, the accuracy of classification of hyperlipidemia in the stacking as a meta learner was higher than other meta-learning algorithms. However, the predictive performance of the meta-learning algorithm proposed in this study is the same as that of SVM with the best performance (88.6%) among the single models. The limitations of this study are as follows. First, various variable selection methods were tried, but most variables used in the study were categorical dummy variables. In the case with a large number of categorical variables, the results may be different if continuous variables are used because the model can be better suited to categorical variables such as decision trees than general models such as neural networks. Despite these limitations, this study has significance in predicting hyperlipidemia with hybrid models such as met learning algorithms which have not been studied previously. It can be said that the result of improving the model accuracy by applying various variable selection techniques is meaningful. In addition, it is expected that our proposed model will be effective for the prevention and management of hyperlipidemia.

• Journal of Intelligence and Information Systems
• /
• v.22 no.1
• /
• pp.83-105
• /
• 2016

Measuring an individual's subjective wellbeing in an accurate, unobtrusive, and cost-effective manner is a core success factor of the wellbeing support system, which is a type of medical IT service. However, measurements with a self-report questionnaire and wearable sensors are cost-intensive and obtrusive when the wellbeing support system should be running in real-time, despite being very accurate. Recently, reasoning the state of subjective wellbeing with conventional sentiment analysis and unstructured data has been proposed as an alternative to resolve the drawbacks of the self-report questionnaire and wearable sensors. However, this approach does not consider contextual polarity, which results in lower measurement accuracy. Moreover, there is no sentimental word net or ontology for the subjective wellbeing area. Hence, this paper proposes a method to extract keywords and their contextual polarity representing the subjective wellbeing state from the unstructured text in online websites in order to improve the reasoning accuracy of the sentiment analysis. The proposed method is as follows. First, a set of general sentimental words is proposed. SentiWordNet was adopted; this is the most widely used dictionary and contains about 100,000 words such as nouns, verbs, adjectives, and adverbs with polarities from -1.0 (extremely negative) to 1.0 (extremely positive). Second, corpora on subjective wellbeing (SWB corpora) were obtained by crawling online text. A survey was conducted to prepare a learning dataset that includes an individual's opinion and the level of self-report wellness, such as stress and depression. The participants were asked to respond with their feelings about online news on two topics. Next, three data sources were extracted from the SWB corpora: demographic information, psychographic information, and the structural characteristics of the text (e.g., the number of words used in the text, simple statistics on the special characters used). These were considered to adjust the level of a specific SWB. Finally, a set of reasoning rules was generated for each wellbeing factor to estimate the SWB of an individual based on the text written by the individual. The experimental results suggested that using contextual polarity for each SWB factor (e.g., stress, depression) significantly improved the estimation accuracy compared to conventional sentiment analysis methods incorporating SentiWordNet. Even though literature is available on Korean sentiment analysis, such studies only used only a limited set of sentimental words. Due to the small number of words, many sentences are overlooked and ignored when estimating the level of sentiment. However, the proposed method can identify multiple sentiment-neutral words as sentiment words in the context of a specific SWB factor. The results also suggest that a specific type of senti-word dictionary containing contextual polarity needs to be constructed along with a dictionary based on common sense such as SenticNet. These efforts will enrich and enlarge the application area of sentic computing. The study is helpful to practitioners and managers of wellness services in that a couple of characteristics of unstructured text have been identified for improving SWB. Consistent with the literature, the results showed that the gender and age affect the SWB state when the individual is exposed to an identical queue from the online text. In addition, the length of the textual response and usage pattern of special characters were found to indicate the individual's SWB. These imply that better SWB measurement should involve collecting the textual structure and the individual's demographic conditions. In the future, the proposed method should be improved by automated identification of the contextual polarity in order to enlarge the vocabulary in a cost-effective manner.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.18 no.1
• /
• pp.26-32
• /
• 2014

Purpose: As PET-MRI which has excellent soft tissue contrast is developed as integration system, many researches about clinical application are being conducted by comparing with existing display equipments. Because PET-MRI is actively used for head and neck cancer diagnosis in our hospital, lymph node metastasis before the patient's surgery was diagnosed and clinical usefulness of head and neck cancer PET-MRI scan was evaluated using pathological opinions and idiopathy surrounding tissue metastasis evaluation method. Materials and Methods: Targeting 100 head and neck cancer patients in SNUH from January to August in 2013. $^{18}F-FDG$ (5.18 MBq/kg) was intravenous injected and after 60 min of rest, torso (body TIM coil, Vibe-Dixon) and dedication (head-neck TIM coil, UTE, Dotarem injection) scans were conducted using $Bio-graph^{TM}$ mMR 3T (SIEMENS, Munich). Data were reorganized using iterative reconstruction and lymph node metastasis was read with Syngo.Via workstation. Subsequently, pathological observations and diagnosis before-and-after surgery were examined with integrated medical information system (EMR, best-care) in SNUH. Patient's diagnostic information was entered in each category of $2{\times}2$ decision matrix and was classified into true positive (TP), true negative (TN), false positive (FP) and false negative (FN). Based on these classified test results, sensitivity, specificity, accuracy, false negative and false positive rate were calculated. Results: In PET-MRI scan results of head and neck cancer patients, positive and negative cases of lymph node metastasis were 49 and 51 cases respectively and positive and negative lymph node metastasis through before-and-after surgery pathological results were 46 and 54 cases respectively. In both tests, TP which received positive lymph node metastasis were analyzed as 34 cases, FP which received positive lymph node metastasis in PET-MRI scan but received negative lymph node metastasis in pathological test were 4 cases, FN which received negative lymph node metastasis but received positive lymph node metastasis in pathological test was 1 case, and TN which received negative lymph node metastasis in both two tests were 50 cases. Based on these data, sensitivity in PET-MRI scan of head and neck cancer patient was identified to be 97.8%, specificity was 92.5%, accuracy was 95%, FN rate was 2.1% and FP rate was 7.00% respectively. Conclusion: PET-MRI which can apply the acquired functional information using high tissue contrast and various sequences was considered to be useful in determining the weapons before-and-after surgery in head and neck cancer diagnosis or in the evaluation of recurrence and remote detection of metastasis and uncertain idiopathy cervical lymph node metastasis. Additionally, clinical usefulness of PET-MRI through pathological test and integrated diagnosis and follow-up scan was considered to be sufficient as a standard diagnosis scan of head and neck cancer, and additional researches about the development of optimum MR sequence and clinical application are required.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.24 no.1
• /
• pp.20-26
• /
• 2020

Purpose It is intended to figure out the errors derived from changes in depth and volume when measuring the Standard source and ^99mTc-pertechnetate by using a Dose calibrator. Then recommend appropriate measurement depth and volume. Materials and Methods As a Dose calibrator, CRC-15βeta and CRC-15R (Capintec, New Jersey, USA) was used, and the measurement sources were ⁵⁷Co, ¹³³Ba, ¹³⁷Cs and ^99mTc-pertechnetate was also adopted due to its high frequency of use. The Standard source was respectively measured the changes according to its depth without changing the volume, in a range of 0 cm to 15 cm from the bottom of the ion chamber. ^99mTc-pertechnetate was measured at each depth by changing the volume with 0.1 mL, 0.3 mL, 0.5 mL, 0.7 mL and 0.9 mL Respectively. And the depth range was from 0 cm to 15 cm at the bottom of the ion chamber. Results In the case of Standard source ⁵⁷Co, ¹³³Ba, ¹³⁷Cs and ^99mTc-pertechnetate, there were significant differences according to the measurement depth(p<0.05). ^99mTc-pertechnetate has a negative correlation coefficient according to the depth, and the error of the measured value was negligible at a depth from 0 cm to 7 cm at 0.3 mL and 0.5 mL, and the range of error increased as the volume increased. Conclusion In clinical practice, it is sometimes installed differently than the Standard depth recommended by the equipment company. If it's measured at the recommended depth and volume, it could be thought that unnecessary exposure of the operator and the patient will be reduced, and more accurate radiation exams will be possible in quantitative analysis.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.191-206
• /
• 2022

Recently, it is a de-facto approach to utilize a pre-trained language model(PLM) to achieve the state-of-the-art performance for various natural language tasks(called downstream tasks) such as sentiment analysis and question answering. However, similar to any other machine learning method, PLM tends to depend on the data distribution seen during the training phase and shows worse performance on the unseen (Out-of-Distribution) domain. Due to the aforementioned reason, there have been many efforts to develop domain-specified PLM for various fields such as medical and legal industries. In this paper, we discuss the training of a finance domain-specified PLM for the Korean language and its applications. Our finance domain-specified PLM, KB-BERT, is trained on a carefully curated financial corpus that includes domain-specific documents such as financial reports. We provide extensive performance evaluation results on three natural language tasks, topic classification, sentiment analysis, and question answering. Compared to the state-of-the-art Korean PLM models such as KoELECTRA and KLUE-RoBERTa, KB-BERT shows comparable performance on general datasets based on common corpora like Wikipedia and news articles. Moreover, KB-BERT outperforms compared models on finance domain datasets that require finance-specific knowledge to solve given problems.

• The Journal of the Korean life insurance medical association
• /
• v.24
• /
• pp.49-78
• /
• 2005

Ⅰ. 연구(硏究) 배경(背景) 및 목적(目的) o 우리나라 보험시장의 세대가입율은 86%로 보험시장 성숙기에 진입하였으며 기존의 전통적인 전업채널에서 방카슈랑스의 도입, 온라인전문보험사의 출현, TM 영업의 성장세 等멀티채널로 진행되고 있음 o LTC(장기간병), CI(치명적질환), 실손의료보험 등(等)선 진형 건강상품의 잇따른 출시로 보험리스크 관리측면에서 언더라이팅의 대비가 절실한 시점임 o 상품과 마케팅 等언더라이팅 측면에서 매우 밀접한 영역의 변화에 발맞추어 언더라이팅의 인수기법의 선진화가 시급히 요구되는 상황하에서 위험을 적절히 분류하고 평가하는 선진적 언더라이팅 기법 구축이 필수 적임 o 궁극적으로 고객의 다양한 보장니드 충족과 상품, 마케팅, 언더라이팅의 경쟁력 강화를 통한 보험사의 종합이익 극대화에 기여할 수 있는 방안을 모색하고자 함 Ⅱ. 선진보험시장(先進保險市場)Risk 세분화사례(細分化事例) 1. 환경적위험(環境的危險)에 따른 보험료(保險料) 차등(差等) (1) 위험직업 보험료 할증 o 미국, 유럽등(等) 대부분의 선진시장에서는 가입당시 피보험자의 직업위험도에 따라 보험료를 차등 적용중(中)임 o 가입하는 보장급부에 따라 직업 분류방법 및 할증방식도 상이하며 일반사망과 재해사망,납입면제, DI에 대해서 별도의 방법을 사용함 o 할증적용은 표준위험율의 일정배수를 적용하여 할증 보험료를 산출하거나, 가입금액당 일정한 추가보험료를 적용하고 있음 - 광부의 경우 재해사망 가입시 표준위험율의 300% 적용하며, 일반사망 가입시 $1,000당 $2.95 할증보험료 부가 (2) 위험취미 보험료 할증 o 취미와 관련 사고의 지속적 다발로 취미활동도 위험요소로 인식되어 보험료를 차등 적용중(中)임 o 할증보험료는 보험가입금액당 일정비율로 부가(가입 금액과 무관)하며, 신종레포츠 등(等)일부 위험취미는 통계의 부족으로 언더라이터가 할증율 결정하여 적용함 - 패러글라이딩 년(年)$26{\sim}50$회(回) 취미생활의 경우 가입금액 $1,000당 재해사망 $2, DI보험 8$ 할증보험료 부가 o 보험료 할증과는 별도로 위험취미에 대한 부담보를 적용함. 위험취미 활동으로 인한 보험사고 발생시 사망을 포함한 모든 급부에 대한 보장을 부(不)담보로 인수함. (3) 위험지역 거주/ 여행 보험료 할증 o 피보험자가 거주하고 있는 특정국가의 임시 혹은 영구적 거주시 기후위험, 거주지역의 위생과 의료수준, 여행위험, 전쟁과 폭동위험 등(等)을 고려하여 평가 o 일반사망, 재해사망 등(等)보장급부별로 할증보험료 부가 또는 거절 o 할증보험료는 보험全기간에 대해 동일하게 적용 - 러시아의 경우 가입금액 $1,000당 일반사망은 2$의 할증보험료 부가, 재해사망은 거절 (4) 기타 위험도에 대한 보험료 차등 o 비행관련 위험은 세가지로 분류(항공운송기, 개인비행, 군사비행), 청약서, 추가질문서, 진단서, 비행이력 정보를 바탕으로 할증보험료를 부가함 - 농약살포비행기조종사의 경우 가입금액 $1,000당 일반사망 6$의 할증보험료 부가, 재해사망은 거절 o 미국, 일본등(等)서는 교통사고나 교통위반 관련 기록을 활용하여 무(無)사고운전자에 대해 보험료 할인(우량체 위험요소로 활용) 2. 신체적위험도(身體的危險度)에 따른 보험료차등(保險料差等) (1) 표준미달체 보험료 할증 1) 총위험지수 500(초과위험지수 400)까지 인수 o 300이하는 25점단위, 300점 초과는 50점 단위로 13단계로 구분하여 할증보험료를 적용중(中)임 2) 삭감법과 할증법을 동시 적용 o 보험금 삭감부분만큼 할증보험료가 감소하는 효과가 있어 청약자에게 선택의 기회를 제공할수 있으며 고(高)위험 피보험자에게 유용함 3) 특정암에 대한 기왕력자에 대해 단기(Temporary)할증 적용 o 질병성향에 따라 가입후 $1{\sim}5$년간 할증보험료를 부가하고 보험료 할증 기간이 경과한 후에는 표준체보험료를 부가함 4) 할증보험료 반환옵션(Return of the extra premium)의 적용 o 보험계약이 유지중(中)이며, 일정기간 생존시 할증보험료가 반환됨 (2) 표준미달체 급부증액(Enhanced annuity) o 영국에서는 표준미달체를 대상으로 연금급부를 증가시킨 증액형 연금(Enhanced annuity) 상품을 개발 판매중(中)임 o 흡연, 직업, 병력 등(等)다양한 신체적, 환경적 위험도에 따라 표준체에 비해 증액연금을 차등 지급함 (3) 우량 피보험체 가격 세분화 o 미국시장에서는 $8{\sim}14$개 의적, 비(非)의적 위험요소에 대한 평가기준에 따라 표준체를 최대 8개 Class로 분류하여 할인보험료를 차등 적용 - 기왕력, 혈압, 가족력, 흡연, BMI, 콜레스테롤, 운전, 위험취미, 거주지, 비행력, 음주/마약 등(等) o 할인율은 회사, Class, 가입기준에 따라 상이(최대75%)하며, 가입연령은 최저 $16{\sim}20$세, 최대 $65{\sim}75$세, 최저보험금액은 10만달러(HIV검사가 필요한 최저 금액) o 일본시장에서는 $3{\sim}4$개 위험요소에 따라 $3{\sim}4$개 Class로 분류 우량체 할인중(中)임 o 유럽시장에서는 영국 등(等)일부시장에서만 비(非)흡연할인 또는 우량체할인 적용 Ⅲ. 국내보험시장(國內保險市場) 현황(現況)및 문제점(問題點) 1. 환경적위험도(環境的危險度)에 따른 가입한도제한(加入限度制限) (1) 위험직업 보험가입 제한 o 업계공동의 직업별 표준위험등급에 따라 각 보험사 자체적으로 위험등급별 가입한도를 설정 운영중(中)임. 비(非)위험직과의 형평성, 고(高)위험직업 보장 한계, 수익구조 불안정화 등(等)문제점을 내포하고 있음 - 광부의 경우 위험1급 적용으로 사망 최대 1억(億), 입원 1일(日) 2만원까지 제한 o 금융감독원이 2002년(年)7월(月)위험등급별 위험지수를 참조 위험율로 인가하였으나, 비위험직은 70%, 위험직은 200% 수준으로 산정되어 현실적 적용이 어려움 (2) 위험취미 보험가입 제한 o 해당취미의 직업종사자에 준(準)하여 직업위험등급을 적용하여 가입 한도를 제한하고 있음. 추가질문서를 활용하여 자격증 유무, 동호회 가입등(等)에 대한 세부정보를 입수하지 않음 - 패러글라이딩의 경우 위험2급을 적용, 사망보장 최대 2 억(億)까지 제한 (3) 거주지역/ 해외여행 보험가입 제한 o 각(各)보험사별로 지역적 특성상 사고재해 다발 지역에 대해 보험가입을 제한하고 있음 - 강원, 충청 일부지역 상해보험 가입불가 - 전북, 태백 일부지역 입원급여금 1일(日)2만원이내 o 해외여행을 포함한 해외체류에 대해서는 일정한 가입 요건을 정하여 운영중(中)이며, 가입한도 설정 보험가입을 제한하거나 재해집중보장 상품에 대해 거절함 - 러시아의 경우 단기체류는 위험1급 및 상해보험 가입 불가, 장기 체류는 거절처리함 2. 신체적위험도(身體的危險度)에 따른 인수차별화(引受差別化) (1) 표준미달체 인수방법 o 체증성, 항상성 위험에 대한 초과위험지수를 보험금삭감법으로 전환 사망보험에 적용(최대 5년(年))하여 5년(年)이후 보험 Risk노출 심각 o 보험료 할증은 일부 회사에서 주(主)보험 중심으로 사용중(中)이며, 총위험지수 300(8단계)까지 인수 - 주(主)보험 할증시 특약은 가입 불가하며, 암 기왕력자는 대부분 거절 o 신체부위 39가지, 질병 5가지에 대해 부담보 적용(입원, 수술 등(等)생존급부에 부담보) (2) 비(非)흡연/ 우량체 보험료 할인 o 1999년(年)최초 도입 이래 $3{\sim}4$개의 위험요소로 1개 Class 운영중(中)임 S생보사의 경우 비(非)흡연우량체, 비(非)흡연표준체의 2개 Class 운영 o 보험료 할인율은 회사, 상품에 따라 상이하며 최대 22%(영업보험료기준)임. 흡연여부는 뇨스틱을 활용 코티닌테스트를 실시함 o 우량체 판매는 신계약의 $2{\sim}15%$수준(회사의 정책에 따라 상이) Ⅳ. 언더라이팅 기법(技法) 선진화(先進化) 방안(方案) 1. 직업위험도별 보험료 차등 적용 o 생 손보 직업위험등급 일원화와 연계하여 3개등급으로 위험지수개편, 비위험직 기준으로 보험요율 차별적용 2. 위험취미에 대한 부담보 적용 o 해당취미를 원인으로 보험사고(사망포함) 발생시 부담보 제도 도입 3. 표준미달체 인수기법 선진화를 통한 인수범위 대폭 확대 o 보험료 할증법 적용 확대를 통한 Risk 헷지로 총위험지수 $300{\rightarrow}500$으로 확대(거절건 최소화) 4. 보험료 할증법 보험금 삭감 병행 적용 o 삭감기간을 적용한 보험료 할증방식 개발, 고객에게 선택권 제공 5. 기한부 보험료할증 부가 o 위암, 갑상선암 등(等)특정암의 성향에 따라 위험도가 높은 가입초기에 평준할증보험료를 적용하여 인수 6. 보험료 할증법 부가특약 확대 적용, 부담보 병행 사용 o 정기특약 등(等)사망관련 특약에 할증법 확대, 생존급부 특약은 부담보 7. 표준체 고객 세분화 확대 o 콜레스테롤, HDL 등(等)위험평가요소 확대를 통한 Class 세분화 Ⅴ. 기대효과(期待效果) 1. 고(高)위험직종사자, 위험취미자, 표준미달체에 대한 보험가입 문호개방 2. 보험계약자간 형평성 제고 및 다양한 고객의 보장니드에 부응 3. 상품판매 확대 및 Risk헷지를 통한 수입보험료 증대 및 사차익 개선 4. 본격적인 가격경쟁에 대비한 보험사 체질 개선 5. 회사 이미지 제고 및 진단 거부감 해소, 포트폴리오 약화 방지 Ⅵ. 결론(結論) o 종래의 소극적이고 일률적인 인수기법에서 탈피하여 피보험자를 다양한 측면에서 위험평가하여 적정 보험료 부가와 합리적 가입조건을 제시하는 적절한 위험평가 수단을 도입하고, o 언더라이팅 인수기법의 선진화와 함께 언더라이팅 인력의 전문화, 정보입수 및 시스템 인프라의 구축 등이 병행함으로써, o 보험사의 사차손익 관리측면에서 뿐만 아니라 보험시장 개방 및 급변하는 보험환경에 대비한 한국 생보언더라이팅 경쟁력 강화 및 언더라이터의 글로벌화에도 크게 기여할 것임.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.1-19
• /
• 2019

Artificial intelligence (AI) is one of the main driving forces leading the Fourth Industrial Revolution. The technologies associated with AI have already shown superior abilities that are equal to or better than people in many fields including image and speech recognition. Particularly, many efforts have been actively given to identify the current technology trends and analyze development directions of it, because AI technologies can be utilized in a wide range of fields including medical, financial, manufacturing, service, and education fields. Major platforms that can develop complex AI algorithms for learning, reasoning, and recognition have been open to the public as open source projects. As a result, technologies and services that utilize them have increased rapidly. It has been confirmed as one of the major reasons for the fast development of AI technologies. Additionally, the spread of the technology is greatly in debt to open source software, developed by major global companies, supporting natural language recognition, speech recognition, and image recognition. Therefore, this study aimed to identify the practical trend of AI technology development by analyzing OSS projects associated with AI, which have been developed by the online collaboration of many parties. This study searched and collected a list of major projects related to AI, which were generated from 2000 to July 2018 on Github. This study confirmed the development trends of major technologies in detail by applying text mining technique targeting topic information, which indicates the characteristics of the collected projects and technical fields. The results of the analysis showed that the number of software development projects by year was less than 100 projects per year until 2013. However, it increased to 229 projects in 2014 and 597 projects in 2015. Particularly, the number of open source projects related to AI increased rapidly in 2016 (2,559 OSS projects). It was confirmed that the number of projects initiated in 2017 was 14,213, which is almost four-folds of the number of total projects generated from 2009 to 2016 (3,555 projects). The number of projects initiated from Jan to Jul 2018 was 8,737. The development trend of AI-related technologies was evaluated by dividing the study period into three phases. The appearance frequency of topics indicate the technology trends of AI-related OSS projects. The results showed that the natural language processing technology has continued to be at the top in all years. It implied that OSS had been developed continuously. Until 2015, Python, C ++, and Java, programming languages, were listed as the top ten frequently appeared topics. However, after 2016, programming languages other than Python disappeared from the top ten topics. Instead of them, platforms supporting the development of AI algorithms, such as TensorFlow and Keras, are showing high appearance frequency. Additionally, reinforcement learning algorithms and convolutional neural networks, which have been used in various fields, were frequently appeared topics. The results of topic network analysis showed that the most important topics of degree centrality were similar to those of appearance frequency. The main difference was that visualization and medical imaging topics were found at the top of the list, although they were not in the top of the list from 2009 to 2012. The results indicated that OSS was developed in the medical field in order to utilize the AI technology. Moreover, although the computer vision was in the top 10 of the appearance frequency list from 2013 to 2015, they were not in the top 10 of the degree centrality. The topics at the top of the degree centrality list were similar to those at the top of the appearance frequency list. It was found that the ranks of the composite neural network and reinforcement learning were changed slightly. The trend of technology development was examined using the appearance frequency of topics and degree centrality. The results showed that machine learning revealed the highest frequency and the highest degree centrality in all years. Moreover, it is noteworthy that, although the deep learning topic showed a low frequency and a low degree centrality between 2009 and 2012, their ranks abruptly increased between 2013 and 2015. It was confirmed that in recent years both technologies had high appearance frequency and degree centrality. TensorFlow first appeared during the phase of 2013-2015, and the appearance frequency and degree centrality of it soared between 2016 and 2018 to be at the top of the lists after deep learning, python. Computer vision and reinforcement learning did not show an abrupt increase or decrease, and they had relatively low appearance frequency and degree centrality compared with the above-mentioned topics. Based on these analysis results, it is possible to identify the fields in which AI technologies are actively developed. The results of this study can be used as a baseline dataset for more empirical analysis on future technology trends that can be converged.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.20 no.2
• /
• pp.32-35
• /
• 2016

Purpose The goal for this study is to figure out that medical staff except Nuclear Medicine Department could be exposed to radiation from the patients who take Nuclear Medicine examination. Materials and Methods Total 250 patients (Bone scan 100, Myocardial SPECT 100, PET/CT 50) were involved from July to October in 2015, and we measured patient dose rate two times for every patients. First, we checked radiation dose rate right after injecting an isotope (radiopharmaceutical). Secondly, we measured radiation dose rate after each examination. Results In the case of Bone scan, dose rate were $0.0278{\pm}0.0036mSv/h$ after injection and $0.0060{\pm}0.0018mSv/h$ after examination (3 hrs 52 minutes after injection on average). For Myocardial SPECT, dose rate were $0.0245{\pm}0.0027mSv/h$ after injection and $0.0123{\pm}0.0041mSv/h$ after examination (2 hrs 09 minutes after injection on average). Lastly, for PET/CT, dose rate were $0.0439{\pm}0.0087mSv/h$ after examination (68 minutes after injection on average). Conclusion Compared to Nuclear Safety Commission Act, there was no significant harmful effect of the exposure from patients who have been administered radiopharmaceuticals. However, we should strive to keep ALARA(as low as reasonably achievable) principle for radiation protection.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.37 no.1
• /
• pp.97-101
• /
• 2010

The practice pattern of pediatric dentistry in the university dental hospital has been changing for the last several decades, due to socioeconomic changes, developments in dental materials and increasing number of private pediatric dental clinics. The purpose of this study is to survey the changing patterns of pediatric dental treatment in the university dental hospital and to present the future direction for pediatric dentistry. Patient distribution and practice trends were reviewed based on the OCS (order communication system) records of the department of pediatric dentistry, Seoul National University Dental Hospital from 2001 to 2008. Results were as follows; 1. The number of patients increased up to 2005 and decreased in 2006, and has remained constant up to 2008. 2. The proportion of preventive and orthodontic treatment increased and the proportion of restorative and pulpal treatment decreased. 3. In restorative treatment, amalgam restoration decreased and resin restoration increased. 4. Frequency of sedation decreased in 2006, 2007 and increased in 2008. 5. Frequency of general anesthesia increased up to 2008.