• Environmental Analysis Health and Toxicology
• /
• 제24권2호
• /
• pp.95-105
• /
• 2009

Chemical Ranking and Scoring (CRS) system is a useful tool to screen priority chemicals of large body of substances. The relative ranking of chemicals based on CRS system has served as a decision-making support tools. Exposure potential and toxicity are significant parameters in CRS system, and there are differences in evaluating those parameters in each CRS system. In this study, the parameters of exposure potential, human toxicity, and ecotoxicity were extensively compared. In addition the scoring methods in each parameter were analyzed. The CRS systems considered in this study include the CHEMS-1 (Chemical Hazard Evaluation for Management Strategies), SCRAM (Scoring and Ranking Assessment Model), EURAM (European Union Risk Ranking Method), ARET (Accelerated Reduction/Elimination of Toxics), and CRS-Korea. An comparative analysis of the several CRS systems is presented based on their assessment parameters and scoring methods.

• Asian Pacific Journal of Cancer Prevention
• /
• 제15권16호
• /
• pp.6819-6822
• /
• 2014

Background: The aim of this study was to evaluate the accuracy of a new scoring system in Korean patients with hematuria at high risk of bladder cancer. Materials and Methods: A total of 319 consecutive patients presenting with painless hematuria without a history of bladder cancer were analyzed, from the period of August 2012 to February 2014. All patients underwent clinical examination, and 22 patients with incomplete data were excluded from the final validation data set. The scoring system included four clinical parameters: age (${\geq}50$ = 2 vs. <50 =1), gender (male = 2 vs. female = 1), history of smoking (smoker/ex-smoker = 4 vs. non-smoker = 2) and nature of the hematuria (gross = 6 vs. microscopic = 2). Results: The area under the receiver-operating characteristic curve (95% confidence interval) of the scoring system was 0.718 (0.655-0.777). The calibration plot demonstrated a slight underestimation of bladder cancer probability, but the model had reasonable calibration. Decision curve analysis revealed that the use of model was associated with net benefit gains over the treat-all strategy. The scoring system performed well across a wide range of threshold probabilities (15%-45%). Conclusions: The scoring system developed is a highly accurate predictive tool for patients with hematuria. Although further improvements are needed, utilization of this system may assist primary care physicians and other healthcare practitioners in determining a patient's risk of bladder cancer.

• 정보과학회 논문지
• /
• 제41권11호
• /
• pp.911-920
• /
• 2014

본 논문은 기계학습을 기반으로 하는 중등수준의 단문형 영어작문 자동채점시스템에 대해 제안한다. 본 논문에서는 기계학습을 이용한 영어 자동채점의 전반적인 수행 방법과 시스템의 구성 및 동작방식, 채점자질의 고려사항에 대해 논한다. 학생 답안의 내용 완성도를 평가하기 위하여 문서의 내용을 요약한 "개념답안"을 제안하여 사용하였다. 본 연구에서는 여러 개의 기계학습 알고리즘을 사용하여 자동평가를 수행한다. 자동평가의 성능을 향상시키기 위해 여러 개의 기계학습 알고리즘의 결과를 최적으로 결합하여 하나의 최종 결과를 도출할 수 있는 "최적조합" 결정과정을 제안한다. 실제 학생들의 작문 데이터를 이용하여 시스템을 구축하고 자동채점 시스템의 성능 평가를 수행하였다.

• 한방안이비인후피부과학회지
• /
• 제21권3호
• /
• pp.150-165
• /
• 2008

Objective : An adequate measurement for Atopic Dermatitis(AD) is essential for studies about the treatment of AD. To establish a new and adequate scoring system for AD in Korean medicine, we reviewed existing studies on AD outcome measurement in Korean medicine. Method : We searched for reviews on measurements of AD or studies which used an AD outcome measurement at the Korean Traditional Knowledge Portal from 1995 to June, 2008. And then we reviewed the pattern identification in AD patients and the outcome measurements for AD in each study. Results : 1. Among 25 studies, the most common measurement for AD was SCORAD(the severity SCORing of Atopic Dermatitis index), there were 16 studies. There was one study which used the Jakob T scoring system, one study which used ADSI(the Atopic Dermatitis Severity Index), and there were 7 studies which established or used a new severity scoring system for AD. 2. In Korean medicine, AD caused by Damp-Heat is accompanied by erythema, papulation, oozing and crust, Damp-Heat accompanied by Spleen-Gi deficiency is frequently found in pediatric patients, and in adults who have indigestion. Symptoms of AD caused by blood deficiency and Wind-Dryness include lichenification, dryness, scale and pigmentation. AD caused by toxic Heat in the blood system has symptoms similar to some Damp-Heat pattern along with symptoms of blood deficiency and Wind-Dryness. Conclusion : We need to establish a new severity scoring system which reflects pattern identifications and treatments with Korean medicine, and we should assess the validity, reliability, and sensitivity of the new scoring system.

• 인지과학
• /
• 제19권3호
• /
• pp.223-255
• /
• 2008

본 논문에서 우리는 문장의 문법성과 텍스트의 어휘 응집성 측정을 위주로 하는 영어 작문 자동평가시스템을 소개하려고 한다. 문법 검사를 위해서는 링크 파서를 사용하고 어휘 연쇄를 측정하기 위해서는 로제 시소러스를 사용한다. 자동 평가 시스템의 채점 신뢰도를 측정하기 위해서 자동 채점과 수동 채점의 결과를 통계적으로 비교한다. 카파 통계와 다국면 Rasch 모형에 따른 분석 결과 자동 채점은 수동 채점과 유사성이 크며 수동 채점과 비교해서 신뢰성에 특별한 문제가 없다는 결론을 내리게 된다. 본 연구의 가장 큰 의의는 다양한 종류의 기술과 도구를 바탕으로 신뢰할 만한 수준의 영작문 자동 평가 시스템을 개발했다는 것이다. 평가 대상이 문장 단위를 넘어 선 텍스트 단위이며, 단어나 문법 등의 형식적 측면만 검사하는 것이 아니라 내용적 측면도 평가한다.

• 동의생리병리학회지
• /
• 제20권1호
• /
• pp.235-244
• /
• 2006

There is much confusion in the field of Rhinitis regarding how to best measure disease severity objectively, Therefore, we aimed to establish a new adequate scoring system for Rhinitis, that should be based on comparison analysis of various scoring systems. We report as follows. We researched for data relating to severity scoring systems for rhinitis in Entrez PubMed from 1995 to 2005 and in Kiss Kstudy. Results and Conclusions: Properties of severity scoring systems were validity, sensitivity of change and ease of use. The essential items of severity scoring systems were subjective symptoms. The criterion of severity were divided into subjective symptoms and complication and Quality of Life. Intensity items are nasal obstruction, rhinorrhea, sneezing, itching, Postnasal drip, nasal mucosa swelling, nasal mucosa color, complication. Subjective symptoms is difficulty of Life. The significant items of severity scoring system are nasal symptoms. The whole score does with the maximum 30 scores. As it were, we assumed nasal symptoms accounted for around 80% of each total score, with complication and difficulty of Life representing 20%.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1997년도 춘계학술대회
• /
• pp.199-202
• /
• 1997

We are developing computer integrated polysomnography system. This system integrates conventional polysomnography with computer for data management, automatic analysis, scoring, and data transmission. In the first stage, we have developed the signal interface and user interface for the manual scoring and data management. For the automatic scoring of sleep stage, we have developed the protocol and have applied the analytic method in its primitive form. In the second stage we will develope a partially automatic scoring system, and finalize the fully automatic system in the final third stage.

• 컴퓨터교육학회논문지
• /
• 제17권2호
• /
• pp.39-51
• /
• 2014

서답형 문항이 포함된 대규모 평가에서 학생들의 답안이 어떻게 채점자들에게 분배되고 어떠한 체계적인 채점 과정을 거쳐야 하는 지에 대한 채점의 효율성은 전반적인 평가의 성공에 중요한 사안이다. 서답형 문항 채점에서 채점자 신뢰도를 확보하기 위해 채점자의 채점 결과가 얼마나 일관성이 있으며, 또한 채점자 간의 채점 결과 또한 서로 일관성을 유지해야하는 것이 중요하다. 이 연구의 목적은 지필 평가로 시행된 서답형 문항 채점을 위한 온라인 채점 시스템을 설계하고 개발한 후, 이를 시행한 결과를 기반으로 온라인 채점 시스템에 대한 신뢰도를 확인하고자 하였다. 이러한 서답형 문항 온라인 채점은 채점자들의 채점 과정에 대한 정보로, 기존의 전통적인 채점 방식과의 비교와 함께 채점자 내 및 채점자 간의 신뢰도를 제공하고 있다. 그 결과로 온라인 채점 시스템이 신뢰롭고 타당한 서답형 문항 채점 결과를 얻는데 효과적이었다는 것을 알 수 있었다.

• Clinics in Shoulder and Elbow
• /
• 제18권4호
• /
• pp.206-210
• /
• 2015

Background: Assessment of the clinical outcomes after rotator cuff repair is essential for their effectiveness on treatment. The Korean Shoulder and Elbow Society devised the Korean Shoulder Scoring System (KSS) for patients with rotator cuff disorder. The purpose of this study was to evaluate the availability of the KSS for assessment of clinical outcomes in patients after arthroscopic rotator cuff repair, and for comparison with other appraisal scoring systems. Methods: A total of 130 patients with partial-thickness or full-thickness rotator cuff tear who underwent arthroscopic repair using a single row or double row suture bridge technique were enrolled. The average follow-up period was 25.9 months. All patients were classified according to various factors. Comparison within corresponding categories was performed, and the correlation between the KSS and other shoulder assessment methods including University of California Los Angeles (UCLA), Constant and American Shoulder and Elbow Surgeons (ASES) score was analyzed. Results: Total score of the KSS response had increased from 59.6 preoperatively to 88.96 at last follow-up. All KSS domains, including function, pain, satisfaction, range of motion, and muscle power had improved up to 24 months postoperatively. Statistical significance was observed mainly in preoperative measurements with number and size of torn tendons, and greater than or equal to grade 3 of fatty infiltration. The KSS was best correlated with the UCLA scoring system in both preoperative (r=0.785) and postoperative (r=0.951) measurements. Conclusions: The KSS was highly reliable and valid as a discriminative instrument, and it showed strong correlation with ASES and UCLA scoring systems.

• The Journal of the Acoustical Society of Korea
• /
• 제13권2E호
• /
• pp.58-67
• /
• 1994

HMM을 이용한 알고리즘은 대용량 음성인식 시스템을 비롯하여 많은 시스템에 적용되어 왔다. 음성인식 시스템을 범용의 프로세서들을 가지고 구현할 경우 많은 계산량과 데이터들로 말미암아 실시간의 성능을 얻을 수 없다. 따라서 실시간 음성인식을 위해서는 인식을 가속화 시키기 위한 전용 하드웨어를 개발하는 것이 요구되어진다. 본 논문에서는 HMM을 이용한 격리단어 인식 시스템을 구현하는 내용을 다루고 있다. 음성인식 시스템은 호스트 컴퓨터와 DSP 보드 그리고 프로토타입 Viterbi scoring 보드로 이루어져 있다. 음성신호로부터 특징 벡터를 추출하는 과정은 DSP 보드에서 이루어지고, Viterbi scoring 보드는 세 개의 field-programmable gate array 칩들을 사용하여 설계되었다. Viterbi scoring 보드는 하드웨어적으로 효율적인 Viterbi scoring 구조를 채택하고 있고 음성인식을 위한 Viterbi 알고리즘을 수행한다. 제작된 시스템은 10MHz로 동작하고, 한 프레임 즉 10ms 동안에 100.000 스테이트를 처리할 수 있다.