• 기술혁신학회지
• /
• 제10권2호
• /
• pp.183-205
• /
• 2007

본 연구는 기술력평가에 근거해서 중소기업 부실예측 가능성을 사전에 예측할 수 있는 최적 판별 모형을 개발 제안하였다. 판별모형에 포함될 설명변수는 요인분석과 판별모형의 단계별 선택방법에 의하여 선정되었다. 분석결과 선형판별모형이 로지스틱판별모형보다 임계확률 관점에서 적절한 것으로 나타났다. 최적 선형판별모형의 분류 정분류율은 70.4%, 분류 예측력은 67.5%로 나타났다. 최적 선형판별모형의 활용도를 높이기 위해서 확실 범주와 유보범주를 구분할 수 있는 경계값을 설정하였다. 분석결과를 활용하면 기술금융 취급기관은 부실위험 평가와 더불어 기술금융 신청기업의 순위를 부여할 때 유용하게 사용할 수 있을 것으로 기대된다.

• 품질경영학회지
• /
• 제32권2호
• /
• pp.191-200
• /
• 2004

Using the p chart is not adequate in case that there are lots of data and it is difficult to divide into products conforming or nonconforming because of obscurity of binary classification. So we need to design a new control chart which represents obscure situation efficiently. This study deals with the method to performing arithmetic operation representing fuzzy data into fuzzy set by applying fuzzy set theory and designs a new control chart taking account of a concept of classification on the term set and membership function associated with term set.

• Communications for Statistical Applications and Methods
• /
• 제15권4호
• /
• pp.543-549
• /
• 2008

Inspired by using a robust loss function in the support vector machine regression to control training error and the idea of robust template matching with M-estimator, Chen (2004) applies M-estimator techniques to gaussian radial basis functions and form a new class of robust kernels for the support vector machines. We are specially interested in the shape of the Huber's M-estimator in this context and propose a way to find the shape parameter of the Huber's M-estimating function. For simplicity, only the two-class classification problem is considered.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2007년도 가을 학술발표논문집 Vol.34 No.2 (C)
• /
• pp.485-489
• /
• 2007

Gaussian process classifiers (GPCs) are fully statistical kernel classification models which have a latent function with Gaussian process prior Recently, EP approximation method has been proposed to infer the posterior over the latent function. It can have a special hyperparameter which can treat outliers potentially. In this paper, we propose the outlier robust algorithm which alternates EP and the hyperparameter updating until convergence. We also show its usefulness with the simulation results.

• Molecules and Cells
• /
• 제19권1호
• /
• pp.1-15
• /
• 2005

Eukaryotes produce various types of small RNAs of 19-28 nt in length. With rapidly increasing numbers of small RNAs listed in recent years, we have come to realize how widespread their functions are and how diverse the biogenesis pathways have evolved. At the same time, we are beginning to grasp the common features and rules governing the key steps in small RNA pathways. In this review, I will summarize the current classification, biogenesis, action mechanism and function of these fascinating molecules.

• Imaging Science in Dentistry
• /
• 제32권3호
• /
• pp.129-134
• /
• 2002

Purpose : To implement the database system of oral and maxillofacial radiological images using a commercial medical image management software with personally developed classification code. Materials and methods : The image database was built using a slightly modified commercial medical image management software, Dr. Image v.2.1 (Bit Computer Co., Korea). The function of wild card '*' was added to the search function of this program. Diagnosis classification codes were written as the number at the first three digits, and radiographic technique classification codes as the alphabet right after the diagnosis code. 449 radiological films of 218 cases from January, 2000 to December, 2000, which had been specially stored for the demonstration and education at Dept. of OMF Radiology of Dankook University Dental Hospital, were scanned with each patient information. Results: Cases could be efficiently accessed and analyzed by using the classification code. Search and statistics results were easily obtained according to sex, age, disease diagnosis and radiographic technique. Conclusion : Efficient image management was possible with this image database system. Application of this system to other departments or personal image management can be made possible by utilizing the appropriate classification code system.

• ETRI Journal
• /
• 제42권1호
• /
• pp.67-77
• /
• 2020

Image captioning has received significant interest in recent years, and notable results have been achieved. Most previous approaches have focused on generating visual descriptions from images, whereas a few approaches have exploited visual descriptions for image classification. This study demonstrates that a good performance can be achieved for both description generation and image classification through an end-to-end joint learning approach with a loss function, which encourages each task to reach a consensus. When given images and visual descriptions, the proposed model learns a multimodal intermediate embedding, which can represent both the textual and visual characteristics of an object. The performance can be improved for both tasks by sharing the multimodal embedding. Through a novel loss function based on class activation mapping, which localizes the discriminative image region of a model, we achieve a higher score when the captioning and classification model reaches a consensus on the key parts of the object. Using the proposed model, we established a substantially improved performance for each task on the UCSD Birds and Oxford Flowers datasets.

• 전자공학회논문지B
• /
• 제31B권7호
• /
• pp.170-178
• /
• 1994

The nearest neighbor classification rule is widely used because it is not only simple but the error rate is asymptotically less than twice Bayes theoretical minimum error. But the method basically use the whole training patterns as the reference vectors. so that both storage and classification time increase as the number of training patterns increases. LVQ(Learning Vector Quantization) resolved this problem by training the reference vectors instead of just storing the whole training patterns. But it is a heuristic algorithm which has no theoretic background there is no terminating condition and it requires a lot of iterations to get to meaningful result. This paper is to propose a new training method of the reference vectors. which minimize the given error function. The nearest neighbor network,the network version of the nearest neighbor classification rule is proposed. The network is funtionally identical to the nearest neighbor classification rule is proposed. The network is funtionally identical to the nearest neighbor classification rule and the reference vectors are represented by the weights between the nodes. The network is trained to minimize the error function with respect to the weights by the steepest descent method. The learning algorithm is derived and it is shown that the proposed method can adjust more reference vectors than LVQ in each iteration. Experiment showed that the proposed method requires less iterations and the error rate is smaller than that of LVQ2.

• 기록학연구
• /
• 제37호
• /
• pp.189-237
• /
• 2013

표준 기록관리시스템(이하 RMS)이 2007년 중앙행정기관의 도입을 시작으로 현재 지방자치단체, 그 밖의 공공기관에도 도입되어 사용되고 있다. RMS는 전자기록환경에서 기록을 관리하기 위한 필수도구이나, 실제 RMS의 기능들이 표준이나 실무를 잘 반영하고 있는지, 얼마만큼 업무에 활용되고 있는지는 잘 알려져 있지 않다. 본 연구는 이러한 문제의식에서 출발하여, 기록관리시스템에 구현된 기능 중 '기준관리'에 대한 평가와 그 의미를 분석하고자 하였다. '기준관리'는 RMS상 기록관리기준표 기준정보관리 분류체계지정 재분류로 구성되어 있는데, 이것은 기록관리기준표 관리와 관련된, 다시 말해 기록의 분류와 처분일정의 영역이다. 분류와 처분일정은 기록에 대한 지적 통제의 중심이자 기록관리의 핵심영역이므로, 이것이 시스템에서 그 역할을 제대로 하고 있는지 분석하는 것은 중요한 일이다. 본 연구에서는 RMS의 기준관리에 대하여 기능 평가와 이용 평가를 함께 실시하였다. 기능 평가는 국내외 표준에서 제시하는 기능요건을 RMS가 얼마나 구현하고 있는지를 비교분석한 것이다. 그리고 이용 평가는 그러한 기능들을 얼마만큼 실제로 사용하고 있는지, 문제점은 무엇인지 진단한 것이다. 중앙행정기관과 광역 및 기초 지자체를 대상으로 실시한 이러한 평가를 통해 얻은 시사점들을 제도적, 기능 이용적, 행정적 측면으로 구분하여 정리하였다. RMS 기준관리 기능이, 더 나아가 RMS 시스템 전체가 기록관리 실무에서 원활하게 사용되기 위해 중요한 것은 사용자를 비롯한 이해당사자들의 소통임이 연구과정에서 드러났다. 사용자들은 RMS를 이용하면서 발생하는 요구사항을 지속적으로 제기하여야 하며, 중앙기록물관리기관은 그들의 요구사항을 분석 파악하고 이를 시스템에 반영하여, 시스템을 고도화 시키고 개선하는데 많은 노력을 하여야 한다.

• 대한물리의학회지
• /
• 제12권4호
• /
• pp.19-28
• /
• 2017

PURPOSE: The purpose of this study was to describe the Proprioceptive Neuromuscular Facilitation (PNF) Intervention strategy applied International Classification of Functioning, Disability and Health (ICF) Tool about strength, range of motion, scapular stability, pain and function of shoulder for patients with adhesive capsulitis. METHODS: The data was collected by patient with adhesive capsulitis. The patient was a 50-year-old male diagnosed with right shoulder with adhesive capsulitis. We applied the PNF Intervention strategy applied ICF Tool to patient with adhesive capsulitis. PNF interventions were consisting of such as combination of isotonic and stabilizing reversal technique and various positions. PNF interventions were applied, such as those aiming at decreasing pain and disability and increasing range of motion and function for the four weeks. Parameters of result were collected for strength, range of motion, scapular stability, pain and function of shoulder using the hand held dynamometer, goniometer, lateral scapula slide test, and shoulder pain and disability index, respectively. RESULTS: Clinical benefits were observed the patient with adhesive capsulitis for strength, range of motion, scapular stability, pain, and function of shoulder. The patient with adhesive capsulitis improved strength, range of motion, scapular stability, pain, and function of shoulder. CONCLUSION: Patient reported improved strength, range of motion, scapular stability, pain, and function of shoulder after intervention.