• Title/Summary/Keyword: sigmoid

Search Result 481, Processing Time 0.024 seconds

Comparison of Different CNN Models in Tuberculosis Detecting

  • Liu, Jian;Huang, Yidi
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.14 no.8
    • /
    • pp.3519-3533
    • /
    • 2020
  • Tuberculosis is a chronic and delayed infection which is easily experienced by young people. According to the statistics of the World Health Organization (WHO), there are nearly ten million fell ill with tuberculosis and a total of 1.5 million people died from tuberculosis in 2018 (including 251000 people with HIV). Tuberculosis is the largest single infectious pathogen that leads to death. In order to help doctors with tuberculosis diagnosis, we compare the tuberculosis classification abilities of six popular convolutional neural network (CNN) models in the same data set to find the best model. Before training, we optimize three parts of CNN to achieve better results. We employ sigmoid function to replace the step function as the activation function. What's more, we use binary cross entropy function as the cost function to replace traditional quadratic cost function. Finally, we choose stochastic gradient descent (SGD) as gradient descent algorithm. From the results of our experiments, we find that Densenet121 is most suitable for tuberculosis diagnosis and achieve a highest accuracy of 0.835. The optimization and expansion depend on the increase of data set and the improvements of Densenet121.

Automatic Method for Contrast Enhancement of Natural Color Images

  • Lal, Shyam;Narasimhadhan, A. V.;Kumar, Rahul
    • Journal of Electrical Engineering and Technology
    • /
    • v.10 no.3
    • /
    • pp.1233-1243
    • /
    • 2015
  • The contrast enhancement is great challenge in the image processing when images are suffering from poor contrast problem. Therefore, in order to overcome this problem an automatic method is proposed for contrast enhancement of natural color images. The proposed method consist of two stages: in first stage lightness component in YIQ color space is normalized by sigmoid function after the adaptive histogram equalization is applied on Y component and in second stage automatic color contrast enhancement algorithm is applied on output of the first stage. The proposed algorithm is tested on different NASA color images, hyperspectral color images and other types of natural color images. The performance of proposed algorithm is evaluated and compared with the other existing contrast enhancement algorithms in terms of colorfulness metric and color enhancement factor. The higher values of colorfulness metric and color enhancement factor imply that the visual quality of the enhanced image is good. Simulation results demonstrate that proposed algorithm provides higher values of colorfulness metric and color enhancement factor as compared to other existing contrast enhancement algorithms. The proposed algorithm also provides better visual enhancement results as compared with the other existing contrast enhancement algorithms.

Effectiveness of incisions, and Dressing to increase Medical Quality : In Linear or Sigmoid Incisions, and Liquid Wound Dressing for Computer Image Guided Craniotomy (의료품질의 향상을 위한 두피절개 및 드레싱 방법의 개선 효과 분석 : CT영상안내에 의한 직선형 또는 S자형 두피절개와 액상 드레싱효과)

  • Cho, Joon;Eum, Kee-Soo;Lee, Dong-Kue;Park, Keun-Sang;Kim, Mi-Young
    • Journal of Korean Society for Quality Management
    • /
    • v.34 no.4
    • /
    • pp.40-50
    • /
    • 2006
  • The authors aimed to analyze the quality improvement efficiency of wound dressing with 2-octyl cyanoacrylate(2-OCA) in stereotactic image guided linear or sigmoid incisions in a cohort of consecutive craniotomy patients, and to compare clinical results with those of iodine-dressing and silk sutured patients underwent conventional craniotomy surgery with large pedicle flap incisions without stereotactic guidance. In methods, 26 patients were involved as the study group at one hospital. We retrospectively compared their results with those of 38 consecutive control patients at the same unit. The suggested new medical material, 2-octyl cyanoacrylate(2-OCA), resultantly decreased or prevented the contaminated fluid influx from scalp outside. The mean infection rate for the control group (7.89%) was relatively higher than that of the study group (3.85%). In addition, the use of stereotactic image guided craniotomy was significant to reduce operation time, to simplify operative procedures and to decrease potential risk factors.

Constant State of Sigmoid Colon Cancer with Liver Metastasis by Herbal Medicine : A Case with an 8-year Follow-up (간 전이를 동반한 결장암 환자에서 한방치료의 효과 : 8년간의 추적조사를 통한 증례보고)

  • Kim, Jung-Sun;Yoo, Hwa-Seung;Cho, Chong-Kwan;Lee, Yeon-Weol
    • The Journal of Internal Korean Medicine
    • /
    • v.28 no.3
    • /
    • pp.662-669
    • /
    • 2007
  • Objectives : The aim of the present study is to derive further studies evaluating the effectiveness of oriental medical treatment on colon cancer patients. We present a case of a patient diagnosed with colon cancer with colon cancer with liver metastasis who has survived more than 8 years. Methods : We followed all of treatments and examination. We prescribed the patient to take HangAm-dan(HAD) three times a day for 5 years and 1 month from January, 2000 to February, 2005. Abdominal computed tomography(CT) was performed to evaluate the therapeutic efficacy and measuring concentration of carcinoembryonic antigen(CEA) in blood serum was also performed to monitor therapeutic response. Results : The patient was diagnosed with liver metastasis in September of 1999 but has survived for over 8 years since. Abdomen CT show no interval change. Conclusions : This case may give us a possibility that oriental medical treatment offers potential benefits for patients with colon cancer.

  • PDF

A Historical Review on Discrete Models of Population Changes and Illustrative Analysis Methods Using Computer Softwares (개체 수 변화에 대한 이산적 모델의 역사적 개요와 컴퓨터 소프트웨어를 이용하는 시각적 분석 방법)

  • Shim, Seong-A
    • Journal for History of Mathematics
    • /
    • v.27 no.3
    • /
    • pp.197-210
    • /
    • 2014
  • Species like insects and fishes have, in many cases, non-overlapping time intervals of one generation and their descendant one. So the population dynamics of such species can be formulated as discrete models. In this paper various discrete population models are introduced in chronological order. The author's investigation starts with the Malthusian model suggested in 1798, and continues through Verhulst model(the discrete logistic model), Ricker model, the Beverton-Holt stock-recruitment model, Shep-herd model, Hassell model and Sigmoid type Beverton-Holt model. We discuss the mathematical and practical significance of each model and analyze its properties. Also the stability properties of stationary solutions of the models are studied analytically and illustratively using GSP, a computer software. The visual outputs generated by GSP are compared with the analytical stability results.

A study on Iris Recognition using Wavelet Transformation and Nonlinear Function

  • Hur Jung-Youn;Truong Le Xuan;Lee Sang-Kyu
    • Journal of the Korean Institute of Intelligent Systems
    • /
    • v.15 no.3
    • /
    • pp.357-362
    • /
    • 2005
  • Iris recognition system is the one of the most reliable biometries recognition system. An algorithm is proposed to determine the localized iris from the iris image received from iris input camera in client. For the first step, the algorithm determines the center of pupil. For the second step, the algorithm determines the outer boundary of the iris and the pupillary boundary. The localized iris area is transformed into polar coordinates. After performing three times Wavelet transformation, normalization was done using a sigmoid function. The converting binary process performs normalized value of pixel from 0 to 255 to be binary value, and then the converting binary process is compared pairs of two adjacent pixels. The binary code of the iris is transmitted to the server by the network. In the server, the comparing process compares the binary value of presented iris to the reference value in the database. The process of recognition or rejection is dependent on the value of Hamming Distance. After matching the binary value of presented iris with the database stored in the server, the result is transmitted to the client.

Inferior Mesenteric Plexus Block for Lower Abdominal Cancer Pain (하복부 암성통증에 대한 하 장간막신경총 차단)

  • Oh, Hung-Kun;Yoon, Duck-Mi;Chung, So-Young
    • The Korean Journal of Pain
    • /
    • v.6 no.2
    • /
    • pp.199-203
    • /
    • 1993
  • Inferior mesenteric plexus block(IMPB) is a nerve block for lower abdominal pain originating from GI tract of distal transverse colon to sigmoid colon and other polvic organ where the inferior mesenteric plexus contains visceral afferent fibers of that organ. We performed IMPB on two patients with lower abdominal pain. Case I: 61 year old female diagnosed with cancer of stomach and uterine cervix and carcinomatosis, experienced complete relief from pain for a period of 7 months after IMPB. Case II: male, 28 years old, who had contracted cancer of the descending colon with obstructive jaundice and pancreatitis had complained of pain in the whole of the abdominal area. IMPB was performed for lower abdominal pain. Seven days after, a celiac plexus block was also performed for upper abdominal pain. The patient complained of recurring pain in the left & upper lower abdomen 30 days after the IMPB. The intensity of the pain was visual analogue scale 4 and it was managed by continuous epidural block. Conclusion: It is our recommendation that IMPB is a reliable method for treatment of lower abdominal pain originating from malignant condition of GI tract from distal transverse colon to sigmoid colon and urinary bladder.

  • PDF

A STUDY ON SIALOGRAPHIC IMAGE OF NORMAL PAROTID GLANDS BY PANORAMIC VIEW (Panorama 촬영술에 의한 정상 성인 이하선 조영상에 관한 연구)

  • Kim Jae-Duk
    • Journal of Korean Academy of Oral and Maxillofacial Radiology
    • /
    • v.26 no.2
    • /
    • pp.7-17
    • /
    • 1996
  • This study was performed to determine the postitional relationships of two lobes of parenchyma and to analysis the anatomical feature and its variations of duct on the panoramic views of the normal parotid glands in adults. Materials included 66 panoramic views and anterioposterior views of sialograms of selected persons and the radiograms of the gland experimentally reproduced on dry skull with lead foil and the reference images of computed tomograms of normal persons. Results were as follows : 1. On panoramic view of sialogram, the superficial lobe was revealed with totally being superimposed with the mandibular ramus and condyle and its tail portion superimposed with mandibular angle area, the deep lobe was revealed between the posterior border of the ramus and the mastoid process, and the isthmus was begin from the marked furcation off main duct and superimposed partially with the medial part of the deep lobe. 2, The mean length and the lateral extension of parenchyma was 63.18±8.05mm and 21.78±4.87mm respectively on panoramic view and showed no statistical relationship between them. 3. The main duct was generally perpendicular to the posterior border of ramus at middle portion and its configurations revealed 57,58% of curvilinear type, 21.21% sigmoid type, 15.15% reverse sigmoid type. 4, The interlobular ducts of the deep lobe showed relatively well defined features between the mandibular ramus and the mastoid process.

  • PDF

A ROENTGENOGRAPHIC STUDY OF NORMAL PAROTID GLANDS USING ISOBARIC SIALOGRAPHY (등압타액선조영촬영법을 이용한 정상성인의 이하선에 관한 연구)

  • Ahn Hee Moon;Lee Sang Rae
    • Journal of Korean Academy of Oral and Maxillofacial Radiology
    • /
    • v.20 no.1
    • /
    • pp.91-102
    • /
    • 1990
  • The aim of this study was to establish the diagnostic criteria of normal parotid glands in adults revealing the anatomical shape, its variations and the postitional relationships of the gland. Materials included 96 lateral and anterior-posterior sialograms of selected person from 23 to 28 years of age. Results were as follows: 1. The average length and lateral displacement of main duct was 48.43㎜ and l6.88㎜. The mean lumen diameter of that was 0.91㎜ in distal end and 1.40㎜ in hilar end in parotid glands. 2. The average angle of main duct to the inferior border of mandib was 34.32 degree. In configurations of main duct, modified curvilinear type was. most prevalent and followed by curvilinear, reverse sigmoid, sigmoid type. 3. The mean caliber of parotid gland was the longest in superior-inferior. 4. The interlobar ducts showed relatively well defined in all cases, its average number was 5.72. Arrangement of these ducts showed at random. Accessory lobe showed 87.5% in the all cases, its average number was 1.7. 5. There were no difference between the well and poorly defined acinar fillings in the glandular parenchyme. 6. There were no differences between right and left parotid glands in size and shape of main duct and parenchymal portion, but there were great variations in each individuals.

  • PDF

Study on the Reconstruction of Pressure Field in Sloshing Simulation Using Super-Resolution Convolutional Neural Network (심층학습 기반 초해상화 기법을 이용한 슬로싱 압력장 복원에 관한 연구)

  • Kim, Hyo Ju;Yang, Donghun;Park, Jung Yoon;Hwang, Myunggwon;Lee, Sang Bong
    • Journal of the Society of Naval Architects of Korea
    • /
    • v.59 no.2
    • /
    • pp.72-79
    • /
    • 2022
  • Deep-learning-based Super-Resolution (SR) methods were evaluated to reconstruct pressure fields with a high resolution from low-resolution images taken from a coarse grid simulation. In addition to a canonical SRCNN(super-resolution convolutional neural network) model, two modified models from SRCNN, adding an activation function (ReLU or Sigmoid function) to the output layer, were considered in the present study. High resolution images obtained by three models were more vivid and reliable qualitatively, compared with a conventional super-resolution method of bicubic interpolation. A quantitative comparison of statistical similarity showed that SRCNN model with Sigmoid function achieved best performance with less dependency on original resolution of input images.