http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
손창식,정환묵 한국지능시스템학회 2006 한국지능시스템학회 학술발표 논문집 Vol.16 No.1
구간값 퍼지집합은 일반적인 퍼지집합보다 언어적인 의사결정 절차에서 매핑의 정확성과 계산의 효율성이 뛰어나고, 규칙의 가중치는 패턴 분류문제에서 분류 경계를 효율적으로 조정할 수 있다는 장점을 가지고 있다. 따라서 본 논문에서는 퍼지규칙 기반 분류방법을 구간값 퍼지규칙 기반 분류방법으로 확장하고 규칙의 가중치를 고려한 분류방법을 제안한다. 모의실험에서는 일반 퍼지집합에서 규칙 가중치를 고려한 분류방법과 구간값 퍼지집합에서 규칙 가중치를 고려한 분류방법을 비교하였다.
손창식,최인훈,박용주,Son, Chang-Sik,Choi, In-Hoon,Park, Young-Ju 한국재료학회 2003 한국재료학회지 Vol.13 No.11
One-dimensional array of InAs quantum dots (QDs) have been grown on V-grooved GaAs substrates by low-pressure metalorganic chemical vapor deposition. Atomic force microscope images show that InAs QDs are aligned in one-dimensional rows along the [011]oriented bottom of V-grooves and no QDs are formed on the sidewalls and the surface of mesa top. Capability to grow one-dimensional InAs QDs array would feasible for the single electron tunneling devices and other novel quantum-confined devices.
Red Emission from Eu-Implanted GaN
손창식,김성일,Akihiro Wakahara,Hisao Tanoue,최인훈,Mustuo Ogura,Yong Tae Kim,김영환 한국물리학회 2004 THE JOURNAL OF THE KOREAN PHYSICAL SOCIETY Vol.45 No.3
Eu ions were implanted into GaN epilayers on sapphire substrates. Sharp visible red emission lines due to inner 4f shell transitions for Eu3+ can be observed from the photoluminescence of Eu-implanted GaN. The 5D0 !7F2 transition produces the strongest red emission line. Minor lines are observed in the given spectral range. The lines at 546, 603, 624, and 667 nm are assigned to 5D1 !7F1 and 5D0 !7F1;2;3 transitions, respectively. These emission lines are little changed with varying temperature. Eu-implanted GaN can be a suitable material for application in red emission devices.
러프 하한 근사를 갖는 로컬 커버링 기반 규칙 획득 기법을 이용한 섬망 환자의 분류 방법
손창식,강원석,이종하,문경자,Son, Chang Sik,Kang, Won Seok,Lee, Jong Ha,Moon, Kyoung Ja 한국정보처리학회 2020 정보처리학회논문지. 소프트웨어 및 데이터 공학 Vol.9 No.4
Delirium is among the most common mental disorders encountered in patients with a temporary cognitive impairment such as consciousness disorder, attention disorder, and poor speech, particularly among those who are older. Delirium is distressing for patients and families, can interfere with the management of symptoms such as pain, and is associated with increased elderly mortality. The purpose of this paper is to generate useful clinical knowledge that can be used to distinguish the outcomes of patients with delirium in long-term care facilities. For this purpose, we extracted the clinical classification knowledge associated with delirium using a local covering rule acquisition approach with the rough lower approximation region. The clinical applicability of the proposed method was verified using data collected from a prospective cohort study. From the results of this study, we found six useful clinical pieces of evidence that the duration of delirium could more than 12 days. Also, we confirmed eight factors such as BMI, Charlson Comorbidity Index, hospitalization path, nutrition deficiency, infection, sleep disturbance, bed scores, and diaper use are important in distinguishing the outcomes of delirium patients. The classification performance of the proposed method was verified by comparison with three benchmarking models, ANN, SVM with RBF kernel, and Random Forest, using a statistical five-fold cross-validation method. The proposed method showed an improved average performance of 0.6% and 2.7% in both accuracy and AUC criteria when compared with the SVM model with the highest classification performance of the three models respectively. 섬망은 의식 장애, 주의력 장애 및 언어력 장애와 같은 일시적인 인지 장애가 있는 환자, 특히 노인에서 나타나는 가장 흔한 정신 장애 중 하나이다. 섬망은 환자와 가족에게 고통을 주고, 통증과 같은 증상의 관리를 방해할 수 있으며 노인 사망률 증가와 관련이 있다. 본 논문의 목적은 장기 요양 시설에서 섬망 환자를 구별하는데 사용될 수 있는 유용한 임상적 지식을 생성하는데 있다. 이러한 목적을 위해, 러프 하한 근사 영역을 갖는 로컬 커버링 규칙 기법을 활용하여 섬망과 관련된 임상적 분류 지식을 추출하였다. 제안된 방법의 임상적 적용 가능성은 전향적 코호트 연구로부터 수집된 데이터를 활용하여 확인하였다. 연구 결과, 섬망 기간이 12일 이상 지속될 수 있는 6가지 유용한 임상적 증거를 발견하였고, 체질량 지수, 동반질환 지수, 입원경로, 영양결핍, 감염, 수면박탈, 욕창, 기저귀 사용과 같은 8가지 인자들이 섬망 결과를 구별하는 데 중요한 요인이라는 것을 확인하였다. 제안된 방법의 분류 성능은 통계적 5-겹 교차검정 방법을 사용하여 3가지 벤치마킹 모델, 즉 ANN, RBF 커널 함수를 활용한 SVM, 랜덤 포레스트와 비교하여 검증하였다. 제안된 방법은 3가지 모델 중 가장 높은 성능을 제공한 SVM 모델과 비교했을 때 정확도와 AUC 기준에서 평균 0.6%와 2.7% 개선된 성능을 보였다.
호흡곤란환자의 입-퇴원 분석을 위한 규칙가중치 기반 퍼지 분류모델
손창식,신아미,이영동,박형섭,박희준,김윤년,Son, Chang-Sik,Shin, A-Mi,Lee, Young-Dong,Park, Hyoung-Seob,Park, Hee-Joon,Kim, Yoon-Nyun 대한의용생체공학회 2010 의공학회지 Vol.31 No.1
A rule weight -based fuzzy classification model is proposed to analyze the patterns of admission-discharge of patients as a previous research for differential diagnosis of dyspnea. The proposed model is automatically generated from a labeled data set, supervised learning strategy, using three procedure methodology: i) select fuzzy partition regions from spatial distribution of data; ii) generate fuzzy membership functions from the selected partition regions; and iii) extract a set of candidate rules and resolve a conflict problem among the candidate rules. The effectiveness of the proposed fuzzy classification model was demonstrated by comparing the experimental results for the dyspnea patients' data set with 11 features selected from 55 features by clinicians with those obtained using the conventional classification methods, such as standard fuzzy classifier without rule weights, C4.5, QDA, kNN, and SVMs.
A Nutrition Evaluation System Based on Hierarchical Fuzzy Approach
손창식,정구보 한국지능시스템학회 2008 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.8 No.2
In this paper, we propose a hierarchical fuzzy based nutrition evaluation system that can analyze the individuals' nutrition status through the inference results generated by each layer. Moreover, a method to minimize the uncertainty of inference in the evaluated nutrition status is discussed. To show the effect of the uncertainty in fuzzy inference, we compared the results of nutrition evaluation with/without the certainty factor of rules on 132 people over the age of 65. From the experimental results, we can see that the evaluation method with the modified certainty factor provides better reliability than that of the general evaluation method without the certainty factor.
연관 분류 마이닝 기법을 활용한 지식기반 신체활동 평가 모델
손창식,최락현,강원석,Son, Chang-Sik,Choi, Rock-Hyun,Kang, Won-Seok 대한임베디드공학회 2018 대한임베디드공학회논문지 Vol.13 No.4
Recently, as interest of wearable devices has increased, commercially available smart wristbands and applications have been used as a tool for personal healthy management. However most previous studies have focused on evaluating the accuracy and reliability of the technical problems of wearable devices, especially step counts, walking distance, and energy consumption measured from the smart wristbands. In this study, we propose a physical activity evaluation model using classification rules, induced from the associative classification mining approach. These rules associated with five physical activities were generated by considering activities and walking times in target heart rate zones such as 'Out-of Zone', 'Fat Burn Zone', 'Cardio Zone', and 'Peak Zone'. In the experiment, we evaluated the prediction power of classification rules and verified its effectiveness by comparing classification accuracies between the proposed model and support vector machine.
손창식,Son, Chang-Sik 한국재료학회 2003 한국재료학회지 Vol.13 No.11
Heavily $p^{ +}$-typed ($10^{20}$ $cm^{-3}$ ) GaAs epilayers have been grown on high-index GaAs substrates with various crystallographic orientations from (100) to (111)A by a low-pressure metalorganic chemical vapor deposition. Carbon (C) tetrabromide (CBr$_4$) was used as a C source. At moderate growth temperatures and high V/III ratios, the hole concentration of C-doped GaAs epilayers shows the crystallographic orientation dependence. The bonding strength of As sites on a growing surface plays an important role in the C incorporation into the high-index GaAs substrates.