• Title/Summary/Keyword: 비전 검사기

Search Result 34, Processing Time 0.028 seconds

Build the nomogram by risk factors of chronic obstructive pulmonary disease (COPD) (만성 폐쇄성 폐질환의 위험요인 선별을 통한 노모그램 구축)

  • Seo, Ju-Hyun;Oh, Dong-Yep;Park, Yong-Soo;Lee, Jea-Young
    • The Korean Journal of Applied Statistics
    • /
    • v.30 no.4
    • /
    • pp.591-602
    • /
    • 2017
  • The concentration of fine dust has increased in Korea and people have become more concerned with respiratory diseases. This study selected risk factors for chronic obstructive pulmonary disease (COPD) through demographic and clinical features and constructed a nomogram. First, logistic regression analysis was performed using demographic and clinical feature and the pulmonary function test results of the Korean National Health and Nutrition Examination Survey (KNHANES) $6^{th}$ (2013-2015) and the nomogram was constructed to visualize the risk factors of chronic obstructive pulmonary disease in order to facilitate the interpretation of the analysis results. The ROC curve and calibration plot were also used to verify the nomogram of chronic obstructive pulmonary disease.

Laparoscopy-assisted Total Gastrectomy with Pancreas-preserving Splenectomy for Early Gastric Cancer: A Case Report (조기위암에서 복강경보조 위전절제술 및 췌장보존식 비전절제술 1예)

  • Park, Jong-Min;Kim, Do-Yoon;Lee, Jae-Man;Leem, Chai-Sun;Jin, Sung-Ho;Cho, Yong-Kwan;Han, Sang-Uk
    • Journal of Gastric Cancer
    • /
    • v.7 no.2
    • /
    • pp.97-101
    • /
    • 2007
  • We report our experience with a case of performing laparoscopy-assisted total gastrectomy along with pancreas-preserving splenectomy for treating early gastric cancer. laparoscopy-assisted total gastrectomy was planned for a 62-year-old male patient with a double early gastric cancer located in the upper and lower third of the stomach. Five trocars were placed and we used a harmonic scalpel to dissect the greater curvature. Enlarged splenic hilar lymph node was encountered and they were proved to be metastasis by frozen section biopsy. We then performed total gastrectomy with pancreas-preserving splenectomy for the purpose of completely dissecting the lymph nodes along the splenic artery and splenic hilum. We created a 4 cm sized longitudinal mini-laparotomy below the xiphoid process to remove the specimen, and anastomosis was done via the Roux-en-Y method. The patient was discharged on the 9th postoperative days after an uneventful recovery. Our experience shows that laparoscopy-assisted total gastrectomy with pancreas-preserving splenectomy is a relatively safe procedure for treating upper third early gastric cancer with metastatic splenic hilar lymph nodes.

  • PDF

Improving Test Accuracy on the MNIST Dataset using a Simple CNN with Batch Normalization

  • Seungbin Lee;Jungsoo Rhee
    • Journal of the Korea Society of Computer and Information
    • /
    • v.29 no.9
    • /
    • pp.1-7
    • /
    • 2024
  • In this paper, we proposes a Convolutional Neural Networks(CNN) equipped with Batch Normalization(BN) for handwritten digit recognition training the MNIST dataset. Aiming to surpass the performance of LeNet-5 by LeCun et al., a 6-layer neural network was designed. The proposed model processes 28×28 pixel images through convolution, Max Pooling, and Fully connected layers, with the batch normalization to improve learning stability and performance. The experiment utilized 60,000 training images and 10,000 test images, applying the Momentum optimization algorithm. The model configuration used 30 filters with a 5×5 filter size, padding 0, stride 1, and ReLU as activation function. The training process was set with a mini-batch size of 100, 20 epochs in total, and a learning rate of 0.1. As a result, the proposed model achieved a test accuracy of 99.22%, surpassing LeNet-5's 99.05%, and recorded an F1-score of 0.9919, demonstrating the model's performance. Moreover, the 6-layer model proposed in this paper emphasizes model efficiency with a simpler structure compared to LeCun et al.'s LeNet-5 (7-layer model) and the model proposed by Ji, Chun and Kim (10-layer model). The results of this study show potential for application in real industrial applications such as AI vision inspection systems. It is expected to be effectively applied in smart factories, particularly in determining the defective status of parts.

A CASE OF TREATMENT-RESISTANT CHILDHOOD-ONSET SCHIZOPHRENIA WITH LONG-TERM TRIAL OF CLOZAPINE (치료저항성 소아기 발병 정신분열증의 Clozapine 장기치험 1례)

  • Jang, Soon-Ah;Kim, Kyung-Hee;Lee, Hong-Shick;Song, Dong-Ho
    • Journal of the Korean Academy of Child and Adolescent Psychiatry
    • /
    • v.9 no.1
    • /
    • pp.98-104
    • /
    • 1998
  • A 12-year-old girl with a 6 year history of childhood-onset schizophrenia required 2 hospitalizations and long-term clozapine trial due to inadequate responses to combinations of typical neuroleptics and traditional treatments of schizophrenic disorder. On admission, she had continuous auditory and visual hallucinations, persecutory delusion, emotional instability, regression of behaviors including temper tantrums as well as specific developmental delays in learning, language, and motor coordination. The clozapine trial significantly reduced most of the positive symptoms, and facilitated in successful discharge from the hospital. During the 4 year clozapine treatment, no significant adverse reactions were noted, and she returned to a structured school setting with minimal degrees of schizophrenic symptoms. From this clinical experience, we suggest that clozapine might be safe and effective in treating treatment-refractory schizophrenic children.

  • PDF