http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
재난 대응용 독립 구동 시스템의 해석모델 개발 및 민감도 분석
노송연(Song Yeon Noh),장주섭(Joo Sup Jang) 유공압건설기계학회 2020 드라이브·컨트롤 Vol.17 No.4
The purpose of this study was to analyze the design sensitivity of an independent driving system for disaster response. The research procedure was as follows. First, an analysis model based on the circuit diagram of the driving system was developed. Second, to ensure the reliability of the analytical model, the load-free test results and analysis results were compared. Even if different loads acted on four independent motors, the system was confirmed to be implemented according to the design intent. Finally, the design variables of the analysis model were analyzed to obtain design variables with a significant impact on system performance and stability. The analysis program used simulation X.
이상국 ( Sang Kook Lee ),이상훈 ( Sang Hoon Lee ),김송이 ( Song Yee Kim ),이우경 ( Woo Kyung Lee ),신동호 ( Dong Ho Shin ),방우대 ( Woo Dae Bang ),노송미 ( Song Mi Noh ),심효섭 ( Hyo Sup Shim ),박병훈 ( Byung Hoon Park ),이경종 ( 대한결핵 및 호흡기학회 2011 Tuberculosis and Respiratory Diseases Vol.70 No.2
We report a case of Caplan`s Syndrome, which presented as multiple pulmonary nodules. A 58-year-old male was admitted to hospital due to multiple pulmonary nodules. In addition, the patient presented with multiple arthritis, and dyspnea on exertion. Rheumatoid arthritis had been diagnosed 35 years ago. The patient had worked as a stonemason for 20 years. Computed Tomography (CT) revealed numerous well-defined tiny nodules scattered in both lungs, which was suspicious of miliary tuberculosis or malignancy. The patient was started on antituberculous medications and referred to our hospital. First, a transbronchial lung biopsy was performed, which showed no evidence of granuloma. It was our opinion that the biopsy was insufficient, and a follow-up video-associated thoracoscopy was performed. The pathological report determined necrotizing granulomatous inflammation and silicosis on background. According to imaging studies, pathologic reports, and clinical symptoms, we concluded that the patient had Caplan`s syndrome. We controlled his rheumatic medications, and instructed him to avoid exposure to hazardous dust.
박세호 ( Se Ho Park ),김승일 ( Seung Il Kim ),박병우 ( Byeong Woo Park ),박형석 ( Hyung Seok Park ),이준상 ( Jun Sang Lee ),이종석 ( Jong Seok Lee ),노송미 ( Song Mi Noh ),구자승 ( Ja Seung Koo ),김민정 ( Min Jung Kim ),김은경 ( E 대한임상종양학회 2010 Korean Journal of Clinical Oncology Vol.6 No.2
유방의 과립세포 종양은 드물게 발생하는 양성 종양으로 말초 신경의 신경섬유초 세포에서 기원하는 것으로 알려져 있다. 과립세포종양의 임상적, 영상의학적 소견은 유방의 악성 종양 소견과 유사하여 양성 종양임에도 불구하고 악성 종양으로 오인되기 쉽다. 저자들은 갑상선 기능 항진증으로 추적 관찰 중인 54세 여자의 우측 유방에서 중심 침생검과 면역조직화학 염색으로 진단된 과립세포종양 1예를 경험하였기에 문헌 고찰과 함께 보고하는 바이다. Granular cell tumor (GCT) of the breast is an uncommon, usually benign tumor originating from Schwann cells of peripheral nerves. Clinical and radiological findings of GCTs are similar to those of malignant tumors, and GCTs of the breast are often confused with breast cancer clinically or radiologically. We experienced 1 case of GCT diagnosed by core needle biopsy and immunohistochemical staining in the right breast of 54-year-old woman with Graves`s disease and report the case with a review of the literature.
김인경 ( Inkyung Kim ),김대희 ( Daehee Kim ),노송 ( Song Noh ),이재구 ( Jaekoo Lee ) 한국정보처리학회 2021 정보처리학회논문지. 소프트웨어 및 데이터 공학 Vol.10 No.3
본 논문에서는 고령자를 위한 개별 웨어러블(Wearable) 기기를 이용한 낙상 감지에 대해 논한다. 신뢰할 수 있는 낙상 감지를 위한 저비용 웨어러블 기기를 설계하기 위해서 대표적인 두 가지 모델을 종합적으로 분석하여 제시한다. 기계 학습 모델인 의사결정 나무(Decision Tree), 랜덤포래스트(Random Forest), SVM(Support Vector Machine)과 심층 학습 모델인 일차원(One-Dimensional) 합성곱 신경망(Convolutional Neural Network)을 사용하여 낙상 감지 학습 능력을 정량화하였다. 또한 입력 데이터에 적용하기 위한 데이터 분할, 전처리, 특징 추출 방법 등을 고려하여 검토된 모델의 유효성을 평가한다. 실험 결과는 전반적인 성능 향상을 보여주며 심층학습 모델의 유효성을 검증한다. In this paper, fall detection using individual wearable devices for older people is considered. To design a low-cost wearable device for reliable fall detection, we present a comprehensive analysis of two representative models. One is a machine learning model composed of a decision tree, random forest, and Support Vector Machine(SVM). The other is a deep learning model relying on a one-dimensional(1D) Convolutional Neural Network(CNN). By considering data segmentation, preprocessing, and feature extraction methods applied to the input data, we also evaluate the considered models’ validity. Simulation results verify the efficacy of the deep learning model showing improved overall performance.