• Journal of East Asia Management
• /
• 제3권2호
• /
• pp.21-41
• /
• 2022

This study aims to analyze the characteristics of the management situation of the Korea Railroad Corporation(KORAIL) through the management innovation process of the KORAIL and to suggest its implications for military application. Despite stable demand, the railway passenger industry had the limitation of not being able to abolish deficit routes due to public service obligations. In addition, the launch of the Suseo High-Speed Line has introduced a competitive system, posing a threat to corporate management. KORAIL wanted to overcome this crisis by innovating its management through the utilization of big data, improvement of the freight business, decentralization of demand, the introduction of tourism railroads, and development of station influence areas. By utilizing big data, KORAIL was able to optimize the railway fare system while reducing fixed costs spent on railway maintenance. It also drastically reduced the station of cargo and created a base station to pursue economies of scale. On the other hand, the existing exclusive station system was abolished to solve the chronic saturation of the downtown area, and the railway demand was moved to Gwangmyeong Station and Suwon Station to optimize the passenger supply. In particular, it developed a new business model called the tourism railway by developing the mountain Byeokjin Line, which was a chronic deficit line, and sought to improve liquidity through the development of the station influence area. Such a process of innovation at KORAIL suggests an appropriate direction in seeking ways to innovate the military medical institutions. First of all, the necessity of improving organizational immersion through the development of a personnel structure suitable for the compulsory organization, while expanding the facilities of the division and corps, and reducing the time required for medical treatment and waiting through the establishment of a data-based medical system was suggested. Next, it was also discussed to integrate the National Health Medical College, which received accreditation as a medical facility through the designation of advanced general hospitals and is ultimately under discussion with the Medical Institution. Through this, we hope that the military medical institutions, which are facing various challenges, will overcome existing limitations and be re-lighted as innovative institution that provides comprehensive public health services.

• 중소기업융합학회논문지
• /
• 제3권1호
• /
• pp.15-22
• /
• 2013

현재 우리나라 중소기업은 혁신역량이 부족한 영세기업의 비중이 높고, 매출 규모가 건실한 기업군이 취약한 구조로 발전을 기대하기 어려운 상황이다. 따라서 정부 3.0을 기반으로 한 중소기업의 빅 데이터 활용방안을 제시한다. 정부 3.0을 기반으로 중소기업의 활성화를 위한 정부지원 빅 데이터 활용 방안을 제시한다. 정부3.0을 기반으로 빅 데이터 인프라를 중소기업과 중소 벤처들이 자유롭게 이용할 수 있는 개방형 빅 데이터 서비스 플랫폼의 구축이 반드시 필요하다.

• 한국전자통신학회논문지
• /
• 제13권5호
• /
• pp.1085-1092
• /
• 2018

최근에 의료, 군사, 스포츠 등의 다양한 분야에서 사물인터넷(IoT)와 빅데이터가 활용되고 있다. 나사렛대학교는 여러 형태의 장애 등급과 장애 유형을 가지고 있는 약 300여명의 장애학생이 있는 재활복지 중심대학이다. 본 논문은 캠퍼스 내에서 장애 학생들이 실내와 실외를 이동할 시에 BLE비콘과 3축 가속도 센서를 이용하여 이동경로 산정과 위험상황 회피를 위한 최적의 경로를 제공하는 스마트 캠퍼스를 제안한다. 이를 위하여 센서기반 IoT 기술을 이용한 장애학생 보행 데이터를 빅데이터로 관리한다.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2021년도 제33회 한글 및 한국어 정보처리 학술대회
• /
• pp.629-632
• /
• 2021

기계 번역(machine translation)은 자연 언어로 된 텍스트를 다른 언어로 자동 번역 하는 기술로, 최근에는 주로 신경망 기계 번역(Neural Machine Translation) 모델에 대한 연구가 진행되었다. 신경망 기계 번역은 일반적으로 자기회귀(autoregressive) 모델을 이용하며 기계 번역에서 좋은 성능을 보이지만, 병렬화할 수 없어 디코딩 속도가 느린 문제가 있다. 비자기회귀(non-autoregressive) 모델은 단어를 독립적으로 생성하며 병렬 계산이 가능해 자기회귀 모델에 비해 디코딩 속도가 상당히 빠른 장점이 있지만, 멀티모달리티(multimodality) 문제가 발생할 수 있다. 본 논문에서는 단어 정렬(word alignment)을 이용한 비자기회귀 신경망 기계 번역 모델을 제안하고, 제안한 모델을 한국어-영어 기계 번역에 적용하여 단어 정렬 정보가 어순이 다른 언어 간의 번역 성능 개선과 멀티모달리티 문제를 완화하는 데 도움이 됨을 보인다.

• 한국인공지능학회지
• /
• 제11권3호
• /
• pp.29-34
• /
• 2023

Recently, the rapid development of artificial intelligence technology, many studies are being conducted to predict the risk of heart disease in order to lower the mortality rate of cardiovascular diseases worldwide. This study presents exercise or dietary improvement contents in the form of a software app or web to patients with cardiovascular disease, and cardiovascular disease through digital devices such as mobile phones and PCs. LR, LDA, SVM, XGBoost for the purpose of developing "Life style Improvement Contents (Digital Therapy)" for cardiovascular disease care to help with management or treatment We compared and analyzed cardiovascular disease prediction models using machine learning algorithms. Research Results XGBoost. The algorithm model showed the best predictive model performance with overall accuracy of 80% before and after. Overall, accuracy was 80.0%, F1 Score was 0.77~0.79, and ROC-AUC was 80%~84%, resulting in predictive model performance. Therefore, it was found that the algorithm used in this study can be used as a reference model necessary to verify the validity and accuracy of cardiovascular disease prediction. A cardiovascular disease prediction analysis algorithm that can enter accurate biometric data collected in future clinical trials, add lifestyle management (exercise, eating habits, etc.) elements, and verify the effect and efficacy on cardiovascular-related bio-signals and disease risk. development, ultimately suggesting that it is possible to develop lifestyle improvement contents (Digital Therapy).

• 한국중재학회지:중재연구
• /
• 제31권2호
• /
• pp.119-135
• /
• 2021

South Korea has the most advanced technology in the Fourth Industrial Revolution era because of its high-speed Internet commercialization. However, the industry is shrinking due to its various regulations in building and its utilization of personal information as big data. Currently, South Korea's personal data utilization business is in its early stages. In the era of the 4th Industrial Revolution, it is difficult for startups to use data. There are various causes here. Above all, legal regulations to protect personal information are emphasized. This study confirms that transactions of personal medical records through My Data can be made. Moreover, it confirms that there is a need for a mediating role between stakeholders. This study lacks statistical access in the process of performing stakeholder roles. However, personal medical records will be traded safely in the future, and new subjects will enter the market. Furthermore, the domestic bio-industry will develop. Through this study, various problems were derived in establishing Medical MyData in Korea. Moreover, it looks forward to continuing various studies in the health care sector in the future.

• 한국인터넷방송통신학회논문지
• /
• 제19권1호
• /
• pp.187-195
• /
• 2019

최근 빅데이터 관련 기술들이 발전함에 따라 다양한 분야에서 생성되는 데이터들을 수집하여 저장하고 처리 및 분석할 수 있게 되었다. 이러한 빅데이터 기술들을 임상 결과 분석에 활용하고, 임상시험 설계 최적화를 통해 보건의료분야에 투입되는 막대한 비용을 절감할 수 있을 것으로 전망된다. 따라서 본 논문에서는 임상 결과를 분석하여 임상시험 기간과 비용 등을 줄일 수 있는 가이드 정보를 제시하고자 한다. 먼저 Sqoop을 사용하여 임상 결과 데이터가 저장된 관계형 데이터 베이스로부터 HDFS에 수집하여 저장하고, 하둡을 기반으로 동작하는 처리 도구인 Hive를 이용하여 데이터를 처리한다. 공공분야, 기업 등 각 분야에서 많이 활용되고 있는 빅데이터 분석 도구인 R을 이용하여 연관성 분석을 한다.

• 한국인공지능학회지
• /
• 제12권1호
• /
• pp.25-29
• /
• 2024

In this study, research was conducted to predict the probability of cervical cancer occurrence associated with the use of hormonal contraceptives. Cervical cancer is influenced by various environmental factors; however, the human papillomavirus (HPV) is detected in 99% of cases, making it the primary attributed cause. Additionally, although cervical cancer ranks 10th in overall female cancer incidence, it is nearly 100% preventable among known cancers. Early-stage cervical cancer typically presents no symptoms but can be detected early through regular screening. Therefore, routine tests, including cytology, should be conducted annually, as early detection significantly improves the chances of successful treatment. Thus, we employed artificial intelligence technology to forecast the likelihood of developing cervical cancer. We utilized the logistic regression algorithm, a predictive model, through Microsoft Azure. The classification model yielded an accuracy of 80.8%, a precision of 80.2%, a recall rate of 99.0%, and an F1 score of 88.6%. These results indicate that the use of hormonal contraceptives is associated with an increased risk of cervical cancer. Further development of the artificial intelligence program, as studied here, holds promise for reducing mortality rates attributable to cervical cancer.

• 한국의료질향상학회지
• /
• 제8권1호
• /
• pp.56-72
• /
• 2001

Background : To shorten processing time for variety of medical affairs of the patient at the outpatient clinic of a big hospital is very important to qualify medical care of the patient. Therefore, patient's waiting time for medical examination is often utilized as a strong tool to evaluate patient satisfaction with a medical care provided. We performed this study to investigate factors delaying related with waiting time for medical examination. Methods : The data were collected from June 26 to July 30, 1999. A total 275 case of medical treatment and 5,634 patients who visited outpatient clinics of a tertiary hospital were subjected to evaluate the waiting time. The data were analyzed using frequency, t-test, ANOVA, $X^2$-test by SPSS Windows 7.5 program. Results : The mean patient's waiting time objectively evaluated ($30.9{\pm}33.9$ min) was longer than that subjectively by patient evaluated ($25.1{\pm}26.2$ min). Patient waiting time objectively evaluated was influenced by the starting time of medical examination, consultation hours, patients arriving time etc, as expected. The time discrepancy between two evaluations was influenced by several causative factors. Regarding the degree of patients accepted waiting time with the medical examination is 20 min. Conclusion : The results show that, besides the starting time of medical examination, consultation hours and patients arriving time, influence the patient's subjective evaluation of waiting time for medical examination and his satisfaction related with the service in the big hospital. In order to improve patient satisfaction related with waiting time for medical examination, it will be effective examination rather than to shorten the real processing time within the consultation room.

• 한국인터넷방송통신학회논문지
• /
• 제20권3호
• /
• pp.163-170
• /
• 2020

정보통신기술의 발전과 함께 데이터의 생산량이 기하급수적으로 증가하면서 빅데이터에 대한 관심이 높아지고 있다. 빅데이터 관련 기술들도 발전함에 따라 여러 분야에서 빅데이터가 수집, 저장, 처리, 분석, 활용되고 있다. 특히 보건의료 분야에서의 빅데이터 분석은 사회경제적으로도 큰 영향력을 발휘할 수 있기 때문에 큰 주목을 받고 있다. 빅데이터 기술을 환자 진단 데이터 분석에 활용하여 간단한 병원 진료에 투여되는 막대한 비용을 절감할 수 있을 것으로 전망된다. 따라서 본 논문에서는 환자 데이터를 분석하여 병원에 가기 어려운 환자나 의학적인 전문 지식이 없는 간병인들에게 의사의 진단과 가까운 간병 가이드 정보를 제시하고자 한다. 먼저 수집된 환자 데이터를 HDFS에 저장하고, 하둡 환경에서 빅데이터 처리 및 분석 도구인 R을 이용하여 데이터를 처리한 후 분류분석을 한다. R의 다양한 기능들을 웹에 구현하기 위해 활용되는 R Shiny를 이용하여 웹 서버에 시각화를 한다.