• The Journal of the Korean bone and joint tumor society
• /
• v.14 no.2
• /
• pp.79-85
• /
• 2008

Soft tissue tumor classifications should be an important part of radiology, oncology and, for orthopedic clinicians and pathologists, they provide diagnostic instruction and prognostic guidelines. In soft tissue tumor classification systems, the World Health Organization (WHO) classifications have become dominant, enabled by the timely publication of new blue books which included detailed text and numerous good illustrations. The new WHO classification of soft tissue tumors was introduced in 2002. Because the classification represents a broad consensus concept, it has gained widespread acceptance around the globe. This article reviews the changes which were introduced the vascular tumors, chondroid-osseous tumors and tumors of uncertain differentiation which have been first recognized or properly classified during the past decade.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.5
• /
• pp.568-573
• /
• 2019

In the diagnosis of pulmonary diseases, auscultation technique is simpler than the other methods, and lung sounds can be used for predicting the types of pulmonary diseases as well as identifying patients with pulmonary diseases. Therefore, in this paper, we identify patients with pulmonary diseases and classify lung sounds according to their sound characteristics using various convolutional neural networks, and compare the classification performance of each neural network method. First, lung sounds over affected areas of the chest with pulmonary diseases are collected by using a single-channel lung sound recording device, and spectral features are extracted from the collected sounds in time domain and applied to each neural network. As classification methods, we use general, parallel, and residual convolutional neural network, and compare lung sound classification performance of each neural network through experiments.

• Proceedings of the KIEE Conference
• /
• 2002.11a
• /
• pp.228-229
• /
• 2002

접지설계시, 과도상태와 정상상태의 접지진단을 위해서는 무엇보다도 접지전류의 분류상태를 정확히 측정하는 기술의 확립이 필요하며, 필드측정의 타당성 검증을 위해서는 시뮬레이션이 병형되어야 한다. 따라서, 본 논문에서는 접지임피던스 및 접지전류 분류율 계산을 정확하게 실행하여 필드측정치에 대한 검증과 접지설계의 안정성과 경제성을 도모하기 위한 효과적인 프로그램을 개발하였다.

• Phonetics and Speech Sciences
• /
• v.14 no.4
• /
• pp.45-56
• /
• 2022

This paper proposes an optimal methodology for automatically diagnosing and predicting the severity of the chronic kidney disease (CKD) using patients' utterances. In patients with CKD, the voice changes due to the weakening of respiratory and laryngeal muscles and vocal fold edema. Previous studies have phonetically analyzed the voices of patients with CKD, but no studies have been conducted to classify the voices of patients. In this paper, the utterances of patients with CKD were classified using the variety of utterance types (sustained vowel, sentence, general sentence), the feature sets [handcrafted features, extended Geneva Minimalistic Acoustic Parameter Set (eGeMAPS), CNN extracted features], and the classifiers (SVM, XGBoost). Total of 1,523 utterances which are 3 hours, 26 minutes, and 25 seconds long, are used. F1-score of 0.93 for automatically diagnosing a disease, 0.89 for a 3-classes problem, and 0.84 for a 5-classes problem were achieved. The highest performance was obtained when the combination of general sentence utterances, handcrafted feature set, and XGBoost was used. The result suggests that a general sentence utterance that can reflect all speakers' speech characteristics and an appropriate feature set extracted from there are adequate for the automatic classification of CKD patients' utterances.

• Review of KIISC
• /
• v.27 no.3
• /
• pp.33-41
• /
• 2017

기계 학습(machine-learning) 분야의 분류 알고리즘(classification algorithms)은 의료 진단, 유전자 정보 해석, 스팸 탐지, 얼굴 인식 및 신용 평가와 같은 다양한 응용 서비스에서 사용되고 있다. 이와 같은 응용 서비스에서의 분류 알고리즘은 사용자의 민감한 정보를 포함하는 데이터를 이용하여 학습을 수행하는 경우가 많으며, 분류 결과도 사용자의 프라이버시와 연관된 경우가 많다. 따라서 학습에 필요한 데이터의 소유자, 응용 서비스 사용자, 그리고 서비스 제공자가 서로 다른 보안 도메인에 존재할 경우, 프라이버시 보호 문제가 발생할 수 있다. 본 논문에서는 이러한 문제를 해결하면서도 분류 서비스를 제공할 수 있도록 도와주는 프라이버시 보존 분류 프로토콜(privacy-preserving classification protocol: PPCP) 에 대해 소개한다. 구체적으로 PPCP의 프라이버시 보호 요구사항을 분석하고, 기존의 연구들이 프라이버시 보호를 위해 사용하는 암호학적 기본 도구(cryptographic primitive)들에 대해 소개한다. 최종적으로 그러한 암호학적 기본 도구를 사용하여 설계된 프라이버시 보존 분류 프로토콜에 대한 기존 연구들을 소개하고 분석한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10a
• /
• pp.1-3
• /
• 2003

최근 생물정보 기술이 암 진단의 새로운 방법으로 관심을 모으고 있다. 다양한 기계학습 기법을 적용하여 우수한 결과를 얻고 있지만, 의학 분양에서는 정확률이 높은 분류기의 획득과 동시에 획득된 분류규칙을 분석하고 이해할 수 있어야 한다. 생물정보 기술에서 많이 사용되는 유전발현 데이터는 데이터내에 수천 내지 수만의 변수가 존재하여 직접 이들 사이의 복잡한 관계를 표현하고 이해하는 것은 매우 어렵다. 본 논문에서는 이러한 어려움을 극복하기 위해 유전발현 데이터에서 분류에 유용한 특징들을 추출하고 유전자 프로그래밍으로 추출된 특징들을 이용한 암 분류규칙을 생성한다. 림프종 유전발현 데이터에 대하여 실험해본 결과, 90% 수준의 인식 성능을 보였고, 또한 모든 샘플을 완벽하게 분류하는 산술 분류규칙을 발견하였다.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.4 no.2
• /
• pp.96-102
• /
• 2011

In this study, we performed algorithm development of automatic symptom degree for patient with hallux valgus one of the representative foot disease of morden. And this study proposes an efficient automated technique that is different from the original analog diagnosis for treatment and surgery of hallux valgus using digital image process. And we used X-Ray images of both a normal and a patient with hallux valgus in the procedure. First, we marked the standard angle on the X-Ray image of normal through Overlap & Add technique. Then we created a standard image through thinning filter and roberts filter(edge detection algorithm). Second, we used sobel filter of edge detection algorithm on the X-Ray image of patient. Moreover, we went another overlap & add technique procedure with both normal and patient image that we made. With the output, we projected the display detection image onto the screen. Finally, with the display detection image, we could measure and project the diagnosis angle of hallux valgus. And this confirms that this method is much more practical and applicable for another orthopedics disease than the prior one.

• Sleep Medicine and Psychophysiology
• /
• v.8 no.1
• /
• pp.37-44
• /
• 2001

Background: Sleep disorders are prevalent in the general population and in medical practice. Three diagnostic classifications for sleep disorders have been developed recently: The International Classification of Sleep Disorders (ICSD), The Diagnostic and Statistical Manual, 4th edition (DSM-IV) and The International Classification of Diseases, 10th edition (ICD-10). Few data have yet been published regarding how the diagnostic systems are related to each other. To address these issues, we evaluated the frequency of sleep disorder diagnoses by DSM-IV and ICSD and compared the DSM-IV with the ICSD diagnoses. Method: Two interviewers assessed 284 inpatients who had been referred for sleep problems in general units of Anam Hospital, holding an unstructured clinical interview with each patient and assigning clinical diagnoses using ICSD and DSM-IV classifications. Results: The most frequent DSM-IV primary diagnoses were "insomnia related to another mental disorder (61.1% of cases)" and "delirium due to general medical condition (26.8%)". "Sleep disorder associated with neurologic disorder (38.4% of cases)" was the most frequent ICSD primary diagnosis, followed by "sleep disorder associated with mental disorder (33.1%)". In comparing the DSM-IV diagnoses with the ICSD diagnoses, sleep disorder unrelated with general medical condition or another mental disorder in DSM-IV categories corresponded with these in ICSD categories. But DSM-IV "primary insomnia" fell into two major categories of ICSD, "psychophysiologic insomni" and "inadequate sleep hygiene". Of 269 subjects, 62 diagnosed with DSM-IV sleep disorder related to general medical condition or another mental disorder disagreed with ICSD diagnoses, which were sleep disorders not associated with general medical condition or mental disorder, i. e., "inadequate sleep hygiene", "environmental sleep disorder", "adjustment sleep disorder" and "insufficient sleep disorder". Conclusion: In this study, we found not only a similar pattern between DSM-IV and ICSD diagnoses but also disagreements, which should not be overlooked by clinicians and resulted from various degrees of understanding of the pathophysiology of the sleep disorders among clinicians. Non-diagnosis or mis-diagnosis leas to inappropriate treatment, therefore the clinicians' understanding of the classification and pathophysiology of sleep disorders is important.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.12
• /
• pp.29-40
• /
• 2022

In this paper, we studied a system that detects and analyzes the pathological features of diabetic retinopathy using Mask R-CNN and a Random Forest classifier. Those are one of the deep learning techniques and automatically diagnoses diabetic retinopathy. Diabetic retinopathy can be diagnosed through fundus images taken with special equipment. Brightness, color tone, and contrast may vary depending on the device. Research and development of an automatic diagnosis system using artificial intelligence to help ophthalmologists make medical judgments possible. This system detects pathological features such as microvascular perfusion and retinal hemorrhage using the Mask R-CNN technique. It also diagnoses normal and abnormal conditions of the eye by using a Random Forest classifier after pre-processing. In order to improve the detection performance of the Mask R-CNN algorithm, image augmentation was performed and learning procedure was conducted. Dice similarity coefficients and mean accuracy were used as evaluation indicators to measure detection accuracy. The Faster R-CNN method was used as a control group, and the detection performance of the Mask R-CNN method through this study showed an average of 90% accuracy through Dice coefficients. In the case of mean accuracy it showed 91% accuracy. When diabetic retinopathy was diagnosed by learning a Random Forest classifier based on the detected pathological symptoms, the accuracy was 99%.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.9 no.2
• /
• pp.113-120
• /
• 2005

The purpose of this study is to suggest a method of concrete safety inspection management system for safety inspection. this research investigates the process of building safety inspection with IDEF0(Integration DEFinition) process modeling method, focusing on concrete durability inspection, and then suggests a data management system, which allows user communications between site and related unit with RDBMS(Relational Database Management System). The suggested system is expected to provide more efficient data sharing tools and consequently improve safety inspection's quality.