• Korean Journal of Cognitive Science
• /
• v.26 no.2
• /
• pp.147-165
• /
• 2015

Through short-answer questions, we can reflect the depth of students' understanding and higher-order thinking skills. Scoring for short-answer questions may take long time and may be an issue on consistency of grading. To alleviate such the suffering, automated scoring systems are widely used in Europe and America, but are in the initial stage in research in Korea. In this paper, we propose a semi-automatic scoring system for short Korean free-text responses using semi-supervised learning. First of all, based on the similarity score between students' answers and model answers, the proposed system grades students' answers and the scored answers with high reliability have been included in the model answers through the thorough test. This process repeats until all answers are scored. The proposed system is used experimentally in Korean and social studies in Nationwide Scholastic Achievement Test. We have confirmed that the processing time and the consistency of grades are promisingly improved. Using the system, various assessment methods have got to be developed and comparative studies need to be performed before applying to school fields.

• Proceedings of the KSPS conference
• /
• 2003.05a
• /
• pp.176-179
• /
• 2003

This study was conducted to extract the feature set of English writing error for suggesting adequate English writing program and making automated scoring system. The frequent committed error and the error across the level of writing proficiency were reported. Also, It is reported that the correlation between type of error and native speaker's rating score.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.14 no.3
• /
• pp.594-602
• /
• 1990

A computer-aided design system of involute cylindrical gears(spur and helical gears) for power transmission is developed, in which the volume of a gear unit is minimized with satisfying various design constraints. As the design constraints, bending strength and pitting resistance of AGMA 218.01, scoring of Dudley's flash temperature, contact ratio, and involute interference of pinion are considered and effective factors for strength calculation(life, reliability, hardness ratio, load distribution, velocity, etc.) are also included. This complicated nonlinear optimization problem is solved by using ALM(Augmented-Lagrange-Multiplier) method with self scaling BFGS(Broydon-Fletcher-Goldfarb-Shanno) method employed for unconstrained optimization programming. This design method can be easily applied to designing power transmission gear unit in the machines of various kinds. It is expected for the proposed method to be a contribution for an automated design of gear unit towards weight minimization, miniaturization and high strength of gear unit.

• Child Health Nursing Research
• /
• v.25 no.1
• /
• pp.56-64
• /
• 2019

Purpose: This study was conducted to obtain data for the development of an effective fall risk assessment tool for pediatric inpatients through a systematic review and meta-analysis of the diagnostic test accuracy of existing scales. Methods: A literature search using Medline, Science Direct, CINAHL, EMBASE, and the Cochrane Library was performed between March 1 and 31, 2018. Of 890 identified papers, 10 were selected for review. Nine were used in the meta-analysis. Stata version 14.0 was used to create forest plots of sensitivity and specificity. A summary receiver operating characteristic curve was used to compare all diagnostic test accuracies. Results: Four studies used the Humpty Dumpty Falls Scale. The most common items included the patient's diagnoses, use of sedative medications, and mobility. The pooled sensitivity and specificity of the nine studies were .79 and .36, respectively. Conclusion: Considering the low specificity of the pediatric fall risk assessment scales currently available, there is a need to subdivide scoring categories and to minimize items that are evaluated using nurses' subjective judgment alone. Fall risk assessment scales should be incorporated into the electronic medical record system and an automated scoring system should be developed.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.1
• /
• pp.45-56
• /
• 2015

In this paper, we present a method that can detect context-sensitive word errors and generate correction candidates. Spelling error detection is one of the most widespread research topics, however, the approach proposed in this paper is adjusted for an automated English scoring system. A common strategy in context-sensitive word error detection is using a pre-defined confusion set to generate correction candidates. We automatically generate a confusion set in order to consider the characteristics of sentences written by second-language learners. We define a word error that cannot be detected by a conventional grammar checker because of part-of-speech ambiguity, and propose how to detect the error and generate correction candidates for this kind of error. An experiment is performed on the English writings composed by junior-high school students whose mother tongue is Korean. The f1 value of the proposed method is 70.48%, which shows that our method is promising comparing to the current-state-of-the art.

• The Journal of the Korea Contents Association
• /
• v.13 no.3
• /
• pp.287-298
• /
• 2013

To develop a technique classifying patients based on computerized clinical data followed by validity verification by comparing with nurse's examination. Class scores were determined by nurses for a day on 348 resident patients in 7 wards of a general hospital according to KPCS-1. The class scores were simultaneously evaluated by reviewing the computerized clinical data acquired from the hospital management information system. These two class scores were both significantly different among different departments as well as disease patterns. Intraclass correlation analysis resulted a very high correlation coefficient of 0.96(p<0.01) between the two scoring methods, but the clinical data scores were somewhat higher. An automated patient classification system seemed possible to be developed in future with further enhancement of the present results based on computerized clinical data without manual scoring, which can be applied for performance evaluation as well as workforce planning.

• The Korean Journal of Cytopathology
• /
• v.9 no.2
• /
• pp.139-146
• /
• 1998

The AutoPap 300 QC System is an automated device for the analysis and classification of conventional cervical cytology slides for quality control purpose. These studies evaluated the sensitivity of the AutoPap 300 QC System, and estimated morphologic features other than epithelial abnormality to identify a high quality control(QC) score with the AutoPap 300 QC System. The sensitivity of the AutoPap 300 QC System at 10% review rate for 210 cases of cervicovaginal cytology with low grade squamous intraepithelial lesion(LSIL) and higher grade lesion was assessed, and compared with a 10% random rescreening. The morphologic features, such as presence of endocervical component, dirty background, atrophy, abnormal ceil size, and celluiarity of single atypical cells were estimated in 45 cases of no review and 30 cases of QC review cases. The AutoPap 300 QC System identified 119(56.7%) out of 210 cases with LSIL and higher grade lesion at 10% review rate. It was more sensitive to squamous cell lesions$(50{\sim}62%)$ than to glandular lesions(10%). The dirty background and the scanty cellularity of single atypical cells were significantly related to low QC score. Conclusively, AutoPap 300 QC System is superior to human random rescreen for the identification of false negative smears. The upgrading of this device is required to enhance the defection of glandular lesion and certain Inadequate conditions of the slides.

• Journal of KIISE
• /
• v.42 no.9
• /
• pp.1124-1132
• /
• 2015

In order to train a supervised machine learning algorithm, it is necessary to have non-biased labels and a sufficient amount of training data. However, it is difficult to collect the required non-biased labels and a sufficient amount of training data to develop an automatic English Composition scoring system. In addition, an English writing assessment is carried out using a multi-faceted evaluation of the overall level of the answer. Therefore, it is difficult to choose an appropriate machine learning algorithm for such work. In this paper, we show that it is possible to alleviate these problems through ensemble learning. The results of the experiment indicate that the ensemble technique exhibited an overall performance that was better than that of other algorithms.

• 한국어정보학회:학술대회논문집
• /
• 2016.10a
• /
• pp.181-185
• /
• 2016

최근 교육과정에서 학생들의 능력 평가는 단순 암기보다 학생들의 종합적인 사고력을 판단할 수 있는 서답형 문항을 늘리는 방향으로 변하고 있다. 그러나 서답형 문항의 경우 채점하는 데 시간과 비용이 많이 들고, 채점자의 주관에 따라 채점 결과의 일관성과 신뢰성을 보장하기 어렵다는 문제가 있다. 이런 점을 해결하기 위해 해외의 사례를 참고하여 국내에서도 서답형 문항에 자동채점 시스템을 적용하는 연구를 진행하고 있다. 본 논문에서는 2014년도에 개발된 '한국어 문장 수준 서답형 문항 자동채점 시스템'의 성능분석을 바탕으로 언어 처리 기능과 자동채점 성능을 개선한 2015년도 자동채점 시스템을 간략하게 소개하고, 각 자동채점 시스템의 성능을 비교 분석한다. 성능 분석 대상으로는 2014년도 국가수준 학업성취도평가의 서답형 문항을 사용했다. 실험 결과, 개선한 시스템의 평균 완전 일치도와 평균 정확률이 기존의 시스템보다 각각 9.4%p, 8.9%p 증가했다. 자동채점 시스템의 목적은 가능한 채점 시간을 단축하면서 채점 기준의 일관성과 신뢰성을 확보하는 데 있으므로, 보완한 2015년 자동채점 시스템의 성능이 향상되었다고 판단할 수 있다.

• Annual Conference on Human and Language Technology
• /
• 2014.10a
• /
• pp.112-116
• /
• 2014

서답형 문항은 학생들의 종합적인 사고능력을 판단하는데 매우 유용하지만 채점할 때, 시간과 비용이 매우 많이 소요되고 채점자의 공정성을 확보해야 하는 어려움이 있다. 이러한 문제를 개선하기 위해 본 논문에서는 서답형 문항에 대한 자동채점 시스템을 제안한다. 본 논문에서 제안하는 시스템은 크게 언어 처리 단계와 채점 단계로 나뉜다. 첫 번째로 언어 처리 단계에서는 형태소 분석과 같은 한국어 정보처리 시스템을 이용하여 학생들의 답안을 분석한다. 두 번째로 채점 단계를 진행하는데 이 단계는 아래와 같은 순서로 진행된다. 1) 첫 번째 단계에서 분석 결과가 완전히 일치하는 답안들을 하나의 유형으로 간주하여 각 유형에 속한 답안의 빈도수가 높은 순서대로 정렬하여 인간 채점자가 고빈도 학생 답안을 수동으로 채점한다. 2) 현재까지 채점된 결과와 모범답안을 학습말뭉치로 간주하여 자질 추출 및 자질 가중치 학습을 수행한다. 3) 2)의 학습 결과를 토대로 미채점 답안들을 군집화하여 분류한다. 4) 분류된 결과 중에서 신뢰성이 높은 채점 답안에 대해서 인간 채점자가 확인하고 학습말뭉치에 추가한다. 5) 이와 같은 방법으로 미채점 답안이 존재하지 않을 때까지 반복한다. 제안된 시스템을 평가하기 위해서 2013년 학업성취도 평가의 사회(중3) 및 국어(고2) 과목의 서답형 문항을 사용하였다. 각 과목에서 1000개의 학생 답안을 추출하여 채점시간과 정확률을 평가하였다. 채점시간을 전체적으로 약 80% 이상 줄일 수 있었고 채점 정확률은 사회 및 국어 과목에 대해 각각 98.7%와 97.2%로 나타났다. 앞으로 자동 채점 시스템의 성능을 개선하고 인간 채점자의 집중도를 높일 수 있도록 인터페이스를 개선한다면 국가수준의 대단위 평가에 충분히 활용할 수 있을 것으로 생각한다.