• 정보교육학회논문지
• /
• 제20권2호
• /
• pp.189-196
• /
• 2016

PATROL은 디지털교과서를 활용하여 플립클래스룸을 적용한 교수학습모형으로서 계획, 실행, 추적, 추천, 요구, 안내 단계로 구성되어 있다. 현재의 디지털교과서는 서책형교과서의 내용과 함께 추가적인 멀티미디어 자료를 보여주는 기능을 중심으로 개발되었기 때문에 교사들이 학생들의 가정 학습 결과를 파악하기가 어렵다. 따라서 본 연구에서는 학생들의 학습 상황을 분석하고, 진단하고, 처치할 수 있도록 PATROL 모형 기반의 디지털교과서 기능을 설계하였다. 디지털교과서 기반의 학습 분석 기능은 관계 분석, 평가 분석, 예측 분석, 적응 분석, 정보 분석 등 5단계로 구성하였으며, 이 기능을 SEE-PAD라 명명하였다. 또한, 단계별 기능을 구체화하기 위해 Use Case 다이어그램과 시퀀스 다이어그램을 제시하였다.

• 한국조리학회지
• /
• 제18권4호
• /
• pp.47-58
• /
• 2012

본 연구는 부산지역 K대학교 학생들을 대상으로 식생활 라이프스타일유형에 따른 군집을 도출하고 각 집단과 외식선택속성과 비만도와의 차이를 고찰하고자 연구를 진행하였다. 연구의 목적을 달성하기 위하여 통계프로그램 PASW Statistic 18.0(Predictive Analytics Software)을 이용하여 빈도분석, 요인분석 및 신뢰도분석, t-test, ${\chi}^2$-test, 비 계층적 군집분석과 ANOVA을 실시하였다. 남자 대학생들의 평균키는 175.59 cm, 체중은 69.53kg이고, 여자 대학생들의 평균키는 162.81 cm, 체중은 53.42kg으로 나타내었다. 남학생 체질량지수를 저체중이 1.7%, 정상체중은 64.6%, 과체중 19.7%이고, 비만은 14.0%로 나타났다. 여학생 체질량지수는 저체중이 22.9%. 정상체중은 62.7%, 과체중이 8.5%, 비만은 5.9%를 나타내었다. 식생활라이프스타일 항목은 건강추구, 안전성추구, 분위기추구, 미각추구, 서양음식추구요인으로 추출되었고, 외식선택속성은 음식의 질과 서비스, 합리적인가격, 접근성과 분위기, 먹어본 경험 요인으로 추출되었다. 식생활라이프스타일은 군집1은 [식생활 무관심형 집단] 군집2는 [건강지향형 집단] 군집3은 [건강무관심형 집단]으로 군집 명을 부여하였다. 식생활라이프스타일 군집과 외식선택속성 요인간의 차이분석에서 군집1은 먹어본 경험에서 높은 평균값을 나타내었고, 군집2는 음식과 서비스의 질에서 높은 평균값을 나타내었고, 군집3은 접근선과 이미지에서 높은 평균값을 나타내었다.

• 지능정보연구
• /
• 제24권4호
• /
• pp.155-170
• /
• 2018

기업의 금융 부도를 예측하는 것은 전통적으로 비즈니스 분석에서 가장 중요한 예측문제 중 하나이다. 선행연구에서 예측모델은 통계 및 기계학습 기반의 기법을 적용하거나 결합하는 방식으로 제안되었다. 본 논문에서는 잘 알려진 최적화기법 중 하나인 시뮬레이티드 어니일링에 기반한 새로운 지능형 예측모델을 제안한다. 시뮬레이티드 어니일링은 유전자알고리즘과 유사한 최적화 성능을 가진 것으로 알려져 있다. 그럼에도 불구하고, 시뮬레이티드 어니일링을 사용한 비즈니스 의사결정 문제의 예측과 분류에 관한 연구가 거의 없었기 때문에, 비즈니스 분석에서의 유용성을 확인하는 것은 의미가 있다. 본 연구에서는 시뮬레이티드 어니일링과 기계학습의 결합 모델을 사용하여 부도예측모델의 입력 특징을 선정한다. 최적화 기법과 기계학습기법을 결합하는 대표적인 유형은 특징 선택, 특징 가중치 및 사례 선택이다. 이 연구에서는 선행연구에서 가장 많이 연구된 특징 선택을 위한 결합모델을 제안한다. 제안하는 모델의 우수성을 확인하기 위하여 본 연구에서는 한국 기업의 실제 재무데이터를 이용하여 그 결과를 분석한다. 분석결과는 제안된 모델의 예측 정확도가 단순한 모델의 예측 정확성보다 우수하다는 것을 보여준다. 특히 기존의 의사결정나무, 랜덤포레스트, 인공신경망, SVM 및 로지스틱 회귀분석에 비해 분류성능이 향상되었다.

• 대한통합의학회지
• /
• 제5권1호
• /
• pp.19-24
• /
• 2017

Purpose : The purpose of this study was to find out the difference motion of hip, knee and ankle joint during walking according to using walker on older people. Method : Korean older people of 34 subjects was participated in this study. Participants was measured joint motion on hip, knee and ankle joint during both conditions (walking with walker and without walker). The measured data were analyzed using independent t-test to investigate the difference of joint motion on the both condition. The statistical analyses were performed using Predictive Analytics Soft Ware (PASW) for windows(Ver. 19) and p-value less than .05 were considered significant for all cases. Result : The study showed that more joint motion on hip flexion and ankle pronation is increased by using walker. And hip extension, knee external rotation and ankle plantar flexion is decreased by using walker. Conclusion : This study suggest that using walker on older people was change the motion of the lower limb joint during walking. Therefore, It is necessary to develop a new walker that can reduce dependency and ensure stability on older people during walking.

• 보건교육건강증진학회지
• /
• 제30권1호
• /
• pp.27-39
• /
• 2013

Objectives: The purpose of the study was to test a model of physical activity of elderly living in Korea, determine significant factors contributing the physical activity, and examine significant paths in the model. Methods: A cross-sectional study was conducted using a convenience sample of 207 elderly men and women, aged 60 and older, residing in Busan Metropolitan City. Data were collected from July to August 2009 and analyzed using Predictive Analytics Software (PASW) and Analysis of a Moment Structures (AMOS). Results: The fitness of the modified model was confirmed to be appropriate (${\chi}^2$ = 55.61, ${\chi}^2$/df = 1.32, p = .078, RMSEA = .04, GFI = .96, AGFI = .91, NFI = .90, NNFI = .94, CFI = .97, PNFI = .48). The elder's age, previous exercise behavior, and self-efficacy were significant in explaining the variance in their physical activity. We found that (a) perceived health status, perceived benefits, perceived barriers, and social support directly affected self-efficacy; (b) previous exercise behavior and perceived health status directly affected perceived benefits; (c) previous exercise behavior directly affected perceived barriers; and (d) and education level, extent of pocket money, and economic level directly affected social support. Conclusions: The younger the age, the more previous exercise experience, and the higher the self-efficacy, the more S. Korean elders demonstrated improved physical activity.

• Genomics & Informatics
• /
• 제11권4호
• /
• pp.186-190
• /
• 2013

The advances in electronic medical records (EMRs) and bioinformatics (BI) represent two significant trends in healthcare. The widespread adoption of EMR systems and the completion of the Human Genome Project developed the technologies for data acquisition, analysis, and visualization in two different domains. The massive amount of data from both clinical and biology domains is expected to provide personalized, preventive, and predictive healthcare services in the near future. The integrated use of EMR and BI data needs to consider four key informatics areas: data modeling, analytics, standardization, and privacy. Bioclinical data warehouses integrating heterogeneous patient-related clinical or omics data should be considered. The representative standardization effort by the Clinical Bioinformatics Ontology (CBO) aims to provide uniquely identified concepts to include molecular pathology terminologies. Since individual genome data are easily used to predict current and future health status, different safeguards to ensure confidentiality should be considered. In this paper, we focused on the informatics aspects of integrating the EMR community and BI community by identifying opportunities, challenges, and approaches to provide the best possible care service for our patients and the population.

• 대한영양사협회학술지
• /
• 제25권1호
• /
• pp.44-58
• /
• 2019

Predicting the number of meals in a foodservice organization is an important decision-making process that is essential for successful food production, such as reducing the amount of residue, preventing menu quality deterioration, and preventing rising costs. Compared to other demand forecasts, the menu of dietary personnel includes diverse menus, and various dietary supplements include a range of side dishes. In addition to the menus, diverse subjects for prediction are very difficult problems. Therefore, the purpose of this study was to establish a method for predicting the number of meals including predictive modeling and considering various factors in addition to menus which are actually used in the field. For this purpose, 63 variables in eight categories such as the daily available number of people for the meals, the number of people in the time series, daily menu details, weekdays or seasons, days before or after holidays, weather and temperature, holidays or year-end, and events were identified as decision variables. An ensemble model using six prediction models was then constructed to predict the number of meals. As a result, the prediction error rate was reduced from 10%~11% to approximately 6~7%, which was expected to reduce the residual amount by approximately 40%.

• 문화기술의 융합
• /
• 제8권5호
• /
• pp.507-513
• /
• 2022

본 연구는 영화 산업에서 온라인 시장인 IPTV의 VOD 이용 건수 예측 모델을 개발하였다. 한국영화진흥위원회에서 수집한 2017년부터 2021년까지 VOD 이용건수 데이터를 활용하여 머신러닝 기반 예측모델을 구축했다. 문헌조사와 군집분석을 통하여 오프라인 시장과 온라인 시장의 차이를 밝히고, VOD 이용 건수의 새로운 범주를 제안한다. 머신러닝 기반의 VOD 이용 건수 예측 모델 개발을 통해 IPTV 기업들의 의사결정 지원 뿐 아니라 마케팅 전략 수립을 돕는 것을 목적으로 한다.

• Asia pacific journal of information systems
• /
• 제29권1호
• /
• pp.35-49
• /
• 2019

The paper attempts to document the application of relevant Machine Learning (ML) models on Yelp (a crowd-sourced local business review and social networking site) dataset to analyze, predict and recommend business. Strategically using two cloud platforms to minimize the effort and time required for this project. Seven machine learning algorithms in Azure ML of which four algorithms are implemented in Databricks Spark ML. The analyzed Yelp business dataset contained 70 business attributes for more than 350,000 registered business. Additionally, review tips and likes from 500,000 users have been processed for the project. A Recommendation Model is built to provide Yelp users with recommendations for business categories based on their previous business ratings, as well as the business ratings of other users. Classification Model is implemented to predict the popularity of the business as defining the popular business to have stars greater than 3 and unpopular business to have stars less than 3. Text Analysis model is developed by comparing two algorithms, uni-gram feature extraction and n-feature extraction in Azure ML studio and logistic regression model in Spark. Comparative conclusions have been made related to efficiency of Spark ML and Azure ML for these models.

• 한국산업융합학회 논문집
• /
• 제27권3호
• /
• pp.635-644
• /
• 2024

Although the business model(BM) patents act as a creative bridge between technology and the marketplace, limited scholarly attention has been paid to the content analysis of BM patents. This study aims to contextualize converging BM patents by employing topic modeling technique and clustering highly marketable topics, which are expressed through a topic-market impact matrix. We relied on BM patent data filed between 2010 and 2022 to derive empirical insights into the commercial potential of emerging business models. Subsequently, nine topics were identified, including but not limited to "Data Analytics and Predictive Modeling" and "Mobile-Based Digital Services and Advertising." The 2x2 matrix allows to position topics based on the variables of topic growth rate and market impact, which is useful for prioritizing areas that require attention or are promising. This study differentiates itself by going beyond simple topic classification based on topic modeling, reorganizing the findings into a matrix format. T he results of this study are expected to serve as a valuable reference for companies seeking to innovate their business models and enhance their competitive positioning.