• 한방재활의학과학회지
• /
• 제33권3호
• /
• pp.79-96
• /
• 2023

Objectives This study was designed to review the effect of Jakyakkamchobuja-tang on rat model with rheumatoid arthritis. Methods We used seven databases (PubMed, EMBASE, Cochrane CENTRAL, China National Knowledge Infrastructure, Oriental Medicine Advanced Searching Integrated System, Korean studies Information Service System, National Digital Science Library) from their inception to May 2023 without language restrictions. Systematic Review Centre for Laboratory Animal Experimentation's tool was used to evaluate the risk of bias. RevMan software (V5.4) was used for the meta-analysis. Results Five studies were selected following our inclusion criteria. The arthritis index decreased significantly (standardized mean difference=-2.06; 95% confidence interval=-3.07 to -1.04; p<0.0001) in Jakyakkamchobuja-tang group. Also, serum cytokines in serum and paw swelling degree decreased in Jakyakkamchobuja-tang group. Conclusions Jakyakkamchobuja-tang may be effective in treating rheumatoid arthritis. Although there is a limitation that the design of drug dosage varies between papers, it can be expected to be applied as an alternative to Western medicine, and it is believed to contribute to the standardization of herbal treatment for rheumatoid arthritis.

• Journal of Electrical Engineering and Technology
• /
• 제1권3호
• /
• pp.279-286
• /
• 2006

A method for estimating the instantaneous phasor of a fault current signal is proposed for high-speed distance protection that is immune to a DC-offset. The method uses a modified notch filter in order to eliminate the power frequency component from the fault current signal. Since the output of the modified notch filter is the delayed DC-offset, delay compensation results in the same waveform as the original DC-offset. Subtracting the obtained DC-offset from the fault current signal yields a sinusoidal waveform, which becomes the real part of the instantaneous phasor. The imaginary part of the instantaneous phasor is based on the first difference of the fault current signal. Since a DC-offset also appears in the first difference, the DC-offset is removed trom the first difference using the results of the delay compensation. The performance of the proposed method was evaluated for a-phase to ground faults on a 345kV 100km overhead transmission line. The Electromagnetic Transient Program was utilized to generate fault current signals for different fault locations and fault inception angles. The performance evaluation showed that the proposed method can estimate the instantaneous phasor of a fault current signal with high speed and high accuracy.

• 한국전기전자재료학회논문지
• /
• 제24권3호
• /
• pp.208-214
• /
• 2011

In this thesis, the partial discharge according to applied voltage and variations of cross-sectional area and length of the conductor related to general condition for using cable was measured in order to study degradation diagnosis for 2-Core cable of the PVC insulator used in industrial fields for other safety installations. Also the thermal degradation conditions under various installation circumstances of cables were studied by assuming degradation conditions with each different degradation rate (50%, 67%, 100%) such as variation in degradated temperature, thermal exposure time, normal state, partially degradated state and overall degradated state for thermal degradation diagnosis. The quantity of electric discharge (V-Q) according to applied voltage was measured for measurement of inception voltage and extinction voltage. The quantity of electric discharge and the number of electric discharge (Q-N) were measured with applied voltage kept constantly. In addition, pictures were taken using SEM (scanning electron microscope) to compare the surface of external insulator to degradated state of internal insulator according to thermal degradation temperature and also compare the surface of external insulator to degradated surface state of internal insulator according exposure time of cables to thermal stress.

• 대한의용생체공학회:의공학회지
• /
• 제44권3호
• /
• pp.182-189
• /
• 2023

CT is a medical device that acquires medical images based on Attenuation coefficient of human organs related to X-rays. In addition, using this theory, it can acquire sagittal and coronal planes and 3D images of the human body. Then, CT is essential device for universal diagnostic test. But Exposure of CT scan is so high that it is regulated and managed with special medical equipment. As the special medical equipment, CT must implement quality control. In detail of quality control, Spatial resolution of existing phantom imaging tests, Contrast resolution and clinical image evaluation are qualitative tests. These tests are not objective, so the reliability of the CT undermine trust. Therefore, by applying an artificial intelligence classification model, we wanted to confirm the possibility of quantitative evaluation of the qualitative evaluation part of the phantom test. We used intelligence classification models (VGG19, DenseNet201, EfficientNet B2, inception_resnet_v2, ResNet50V2, and Xception). And the fine-tuning process used for learning was additionally performed. As a result, in all classification models, the accuracy of spatial resolution was 0.9562 or higher, the precision was 0.9535, the recall was 1, the loss value was 0.1774, and the learning time was from a maximum of 14 minutes to a minimum of 8 minutes and 10 seconds. Through the experimental results, it was concluded that the artificial intelligence model can be applied to CT implements quality control in spatial resolution and contrast resolution.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권2호
• /
• pp.631-653
• /
• 2020

Sign language is a natural, visually oriented and non-verbal communication channel between people that facilitates communication through facial/bodily expressions, postures and a set of gestures. It is basically used for communication with people who are deaf or hard of hearing. In order to understand such communication quickly and accurately, the design of a successful sign language translation system is considered in this paper. The proposed system includes object detection and classification stages. Firstly, Single Shot Multi Box Detection (SSD) architecture is utilized for hand detection, then a deep learning structure based on the Inception v3 plus Support Vector Machine (SVM) that combines feature extraction and classification stages is proposed to constructively translate the detected hand gestures. A sign language fingerspelling dataset is used for the design of the proposed model. The obtained results and comparative analysis demonstrate the efficiency of using the proposed hybrid structure in sign language translation.

• 한국멀티미디어학회논문지
• /
• 제23권6호
• /
• pp.729-737
• /
• 2020

Screening with low-dose spiral computed tomography (LDCT) has been shown to reduce lung cancer mortality by about 20% when compared to standard chest radiography. One of the problems arising from screening programs is that large amounts of CT image data must be interpreted by radiologists. To solve this problem, automated detection of pulmonary nodules is necessary; however, this is a challenging task because of the high number of false positive results. Here we demonstrate detection of pulmonary nodules using six off-the-shelf convolutional neural network (CNN) models after modification of the input/output layers and end-to-end training based on publicly databases for comparative evaluation. We used the well-known CNN models, LeNet-5, VGG-16, GoogLeNet Inception V3, ResNet-152, DensNet-201, and NASNet. Most of the CNN models provided superior results to those of obtained using customized CNN models. It is more desirable to modify the proven off-the-shelf network model than to customize the network model to detect the pulmonary nodules.

• International Journal of Computer Science & Network Security
• /
• 제23권8호
• /
• pp.91-94
• /
• 2023

According to most experts and health workers, a living creature's body heat is little understood and crucial in the identification of disorders. Doctors in ancient medicine used wet mud or slurry clay to heal patients. When either of these progressed throughout the body, the area that dried up first was called the infected part. Today, thermal cameras that generate images with electromagnetic frequencies can be used to accomplish this. Thermography can detect swelling and clot areas that predict cancer without the need for harmful radiation and irritational touch. It has a significant benefit in medical testing because it can be utilized before any observable symptoms appear. In this work, machine learning (ML) is defined as statistical approaches that enable software systems to learn from data without having to be explicitly coded. By taking note of these heat scans of breasts and pinpointing suspected places where a doctor needs to conduct additional investigation, ML can assist in this endeavor. Thermal imaging is a more cost-effective alternative to other approaches that require specialized equipment, allowing machines to deliver a more convenient and effective approach to doctors.

• Transactions on Electrical and Electronic Materials
• /
• 제11권1호
• /
• pp.42-47
• /
• 2010

Polymer insulating materials such as cross linked polyethylene (XLPE) are employed in electric cables used for extra high voltage. These materials can degrade due to chemical, mechanical and electric stress, possibly caused by voids, the presence of extrinsic materials and protrusions. Therefore, this study measured discharge patterns, discharge phase angle, quantity and occurrence frequency as well as changes in XLPE under different temperatures and applied voltages. To quantitatively analyze the irregular partial discharge patterns measured, the discharge patterns were examined using a statistical program. A three layer sample was fabricated, wherein the upper and lower layers were composed of non-void XLPE, while the middle layer was composed of an air void and copper particles. After heating to room temperature and $50^{\circ}C$ and $80^{\circ}C$ in silicone oil, partial discharge characteristics were studied by increasing the voltage from the inception voltage to the breakdown voltage. Partial discharge statistical analysis showed that when the K-means clustering was carried out at 9 kV to determine the void discharge characteristics, the amount discharged at low temperatures was small but when the temperature was increased to $80^{\circ}C$, the discharge amount increased to be 5.7 times more than that at room temperature because electric charge injection became easier. An analysis of the kurtosis and the skewness confirmed that positive and negative polarity had counterclockwise and clockwise clustering distribution, respectively. When 5 kV was applied to copper particles, the K-means was conducted as the temperature changed from $50^{\circ}C$ to $80^{\circ}C$. The amount of charge at a positive polarity increased 20.3% and the amount of charge at a negative polarity increased 54.9%. The clustering distribution of a positive polarity and negative polarity showed a straight line in the kurtosis and skewness analyses.

• 대한의용생체공학회:의공학회지
• /
• 제39권5호
• /
• pp.213-219
• /
• 2018

Stomach cancer is the most diagnosed cancer in Korea. When gastric cancer is detected early, the 5-year survival rate is as high as 90%. Gastroscopy is a very useful method for early diagnosis. But the false negative rate of gastric cancer in the gastroscopy was 4.6~25.8% due to the subjective judgment of the physician. Recently, the image classification performance of the image recognition field has been advanced by the convolutional neural network. Convolutional neural networks perform well when diverse and sufficient amounts of data are supported. However, medical data is not easy to access and it is difficult to gather enough high-quality data that includes expert annotations. So This paper evaluates the efficacy of transfer learning in gastroscopy classification and diagnosis. We obtained 787 endoscopic images of gastric endoscopy at Gil Medical Center, Gachon University. The number of normal images was 200, and the number of abnormal images was 587. The image size was reconstructed and normalized. In the case of the ResNet50 structure, the classification accuracy before and after applying the transfer learning was improved from 0.9 to 0.947, and the AUC was also improved from 0.94 to 0.98. In the case of the InceptionV3 structure, the classification accuracy before and after applying the transfer learning was improved from 0.862 to 0.924, and the AUC was also improved from 0.89 to 0.97. In the case of the VGG16 structure, the classification accuracy before and after applying the transfer learning was improved from 0.87 to 0.938, and the AUC was also improved from 0.89 to 0.98. The difference in the performance of the CNN model before and after transfer learning was statistically significant when confirmed by T-test (p < 0.05). As a result, transfer learning is judged to be an effective method of medical data that is difficult to collect good quality data.

• 한국농공학회논문집
• /
• 제61권3호
• /
• pp.55-65
• /
• 2019

Although crack on concrete exists from its early formation, crack requires attention as it affects stiffness of structure and can lead demolition of structure as it grows. Detecting cracks on concrete is needed to take action prior to performance degradation of structure, and deep learning can be utilized for it. In this study, transfer learning, one of the deep learning techniques, was used to detect the crack, as the amount of crack's image data was limited. Pre-trained Inception-v3 was applied as a base model for the transfer learning. Web scrapping was utilized to fetch images of concrete wall with or without crack from web. In the recognition of crack, image post-process including changing size or removing color were applied. In the visualization of crack, source images divided into 30px, 50px or 100px size were used as input data, and different numbers of input data per category were applied for each case. With the results of visualized crack image, false positive and false negative errors were examined. Highest accuracy for the recognizing crack was achieved when the source images were adjusted into 224px size under gray-scale. In visualization, the result using 50 data per category under 100px interval size showed the smallest error. With regard to the false positive error, the best result was obtained using 400 data per category, and regarding to the false negative error, the case using 50 data per category showed the best result.