• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.31 no.4
• /
• pp.255-260
• /
• 2018

In recent years, increasing electricity use has led to considerable interest in green energy. In order to effectively supply, cut off, and operate an electric power system, many electric power facilities such as gas insulation switch (GIS), cable, and large substation facilities with higher densities are being developed to meet demand. However, because of the increased use of aging electric power facilities, safety problems are emerging. Electromagnetic wave and leakage current detection are mainly used as sensing methods to detect live-line partial discharges. Although electromagnetic sensors are excellent at providing an initial diagnosis and very reliable, it is difficult to precisely determine the fault point, while leakage current sensors require a connection to the ground line and are very vulnerable to line noise. The partial discharge characteristic in particular is accompanied by statistical irregularity, and it has been reported that proper statistical processing of data is very important. Therefore, in this paper, we present the results of analyzing ${\Phi}-q-n$ cluster distributions of partial discharge characteristics by using K-means clustering to develop an expert partial discharge diagnosis system generated in a GIS facility.

• Journal of Korean society of Dental Hygiene
• /
• v.5 no.2
• /
• pp.235-245
• /
• 2005

The changes in korean economic environment, from quantitative to qualitative growth of economy, go with making desperate efforts, that is, companies have put through many technical improvements, quality control, improvement of service, and so forth. Enterprises cut the number of employees through labor-management adjustment, so that a shortage of labor caused. An increase in intension of labor brought about growing the proportion of occupational diseases which is musculoskeletal diseases. Because of a rapid change in society and a change in our circumstances, we have many difficulties in examine a business disease closely. In support corroboration of relevance on admission of business, a criterion for dudging afford a basis for a causal relationship of medical science, take the state of working conditions into consideration, and at the same time, give a adaptable decision based on the purpose and point of "The Labor Standard Law" as well as "The Law about Industrial Accident Compensation insurance". In conclusion, it is necessary for the dental hygienists 10 reduce the on-duty hours a day, to make good postures in working, and to remove the stressful conditions in order to reduce the incidence of the lumbago. Good working postures, appropriate rest time, and early detection, care and education of the lumbago could be recommended for the dental hygienists.

• Journal of Game and Entertainment
• /
• v.2 no.2
• /
• pp.51-60
• /
• 2006

Recently, many streaming videos including drama, music videos, and movies have been extensively given on the web. Such video services are on negative lines in any service restriction depending on the age of users and then whole part of a video have been restricted considering the age of users. Therefore, in this paper, we will present a new method that provides the access depending on the ages of users and also sets the video rating of each scene in a video. To get this restricted access for video, we will first divide a streaming video into many scenes using histogram techniques. Each scene gets an access control depending on the nudity level. Finally, we will make the video indexing including the access level depending on its nudity level and then hide restricted scenes using several masks in playing that streaming video.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.8
• /
• pp.1564-1573
• /
• 2007

Bulk of toner residual quantity detection return trip conglutinated in toner of using printer current is comparative big state by using PCB substrate, therefore is incongruent to use in light weight print miniaturized more. Return trip this development miniaturizes such as this by doing one chip competitive product develop chip has to be conglutinated compulsorily in toner used to printer announced since 2005 years. Therefore, demand of chip to be used in forward revival market may be thriving. Production of revival toner is impossible by chip conglutinated to printer to meaning that manage information of toner cut ridge that universal laser printer makers are used in printer and do customer service. In this paper, we develops chip conglutinated compulsorily to produce revival toner.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.19 no.12
• /
• pp.80-86
• /
• 2020

With the exception of welding activities, it is forbidden to use electricity in shipyards, owing to safety concerns such as the possibility of fire, explosions, and short circuits. In this paper, an automatic chamfering machine using pneumatics is proposed for use in such environments. Customers specify their requirements and the machine derives the corresponding theoretical design conditions. The proposed machine was used to perform 3D modeling, and its suitability and performance were confirmed via cutting experiments of the manufactured device. Two types of sensors may be used in this system: contact and non-contact. In the case of the contact type, an end-stop switch that can recognize the end of the material is installed, and when the machine reaches the end of the material, the end-stop switch is operated to cut off the air pressure. In the non-contact type, four sensors were used: photonic, ultrasonic, metal detection, and encoder. The use of the four sensors was repeated 30 times, and the average error determined. Thus, the optimum sensor was identified.

• Journal of the Korean Wood Science and Technology
• /
• v.50 no.6
• /
• pp.490-498
• /
• 2022

The current study aimed to verify the image segmentation ability of rays in tangential thin sections of conifers using artificial intelligence technology. The applied model was Mask region-based convolutional neural network (Mask R-CNN) and softwoods (viz. Picea jezoensis, Larix gmelinii, Abies nephrolepis, Abies koreana, Ginkgo biloba, Taxus cuspidata, Cryptomeria japonica, Cedrus deodara, Pinus koraiensis) were selected for the study. To take digital pictures, thin sections of thickness 10-15 ㎛ were cut using a microtome, and then stained using a 1:1 mixture of 0.5% astra blue and 1% safranin. In the digital images, rays were selected as detection objects, and Computer Vision Annotation Tool was used to annotate the rays in the training images taken from the tangential sections of the woods. The performance of the Mask R-CNN applied to select rays was as high as 0.837 mean average precision and saving the time more than half of that required for Ground Truth. During the image analysis process, however, division of the rays into two or more rays occurred. This caused some errors in the measurement of the ray height. To improve the image processing algorithms, further work on combining the fragments of a ray into one ray segment, and increasing the precision of the boundary between rays and the neighboring tissues is required.

• Nuclear Engineering and Technology
• /
• v.55 no.2
• /
• pp.506-515
• /
• 2023

This study is to find a method to learn engine sound after the start-up of a diesel generator installed in nuclear power plant with an unsupervised deep learning algorithm (CNN autoencoder) and a new method to predict the failure of a diesel generator using it. In order to learn the sound of a diesel generator with a deep learning algorithm, sound data recorded before and after the start-up of two diesel generators was used. The sound data of 20 min and 2 h were cut into 7 s, and the split sound was converted into a spectrogram image. 1200 and 7200 spectrogram images were created from sound data of 20 min and 2 h, respectively. Using two different deep learning algorithms (CNN autoencoder and binary classification), it was investigated whether the diesel generator post-start sounds were learned as normal. It was possible to accurately determine the post-start sounds as normal and the pre-start sounds as abnormal. It was also confirmed that the deep learning algorithm could detect the virtual abnormal sounds created by mixing the unusual sounds with the post-start sounds. This study showed that the unsupervised anomaly detection algorithm has a good accuracy increased about 3% with comparing to the binary classification algorithm.

• Journal of the Korean Society for Precision Engineering
• /
• v.12 no.10
• /
• pp.78-88
• /
• 1995

For producing iron or steel products with good quality, the concentration of the material components should be analyzed quickly with high relability using XRF(Fluorescent X-Ray Spectrometer). Since the analysis results are much dependent upon the surface con- dition, the samples have to be prepared to have good test condition. This study presents an image processing system for inspecting the surface condition of the iron test sample. In order to use thd computer vision system, we need to develop a lighting device and image processing algorithm. For the adequate lighting device of inspection system, the indirect lighting device is contrived to cut the external light and provide uniform, stable and cold light. The image processing algorithm is aimed to reduce inspection time and to get similar analyzing results to those of the experienced operators. At first, the image processing algorithm checks whether the surface of the iron sample is ground well or not. Then, the defects; hole or dig are conted and surface condition is evaluated. In addition, the algorithm gives the reliability of the analyzing results in order to help operator's decision.

• Journal of the Korean Society of Radiology
• /
• v.81 no.1
• /
• pp.147-156
• /
• 2020

Purpose The objective of this study was to evaluate the diagnostic value and threshold levels of cytokeratin fragment 21-1 (CYFRA 21-1) in fine-needle aspiration (FNA) washouts for detection of lymph node (LN) recurrence in postoperative breast cancer patients. Materials and Methods FNA cytological assessments and CYFRA 21-1 measurement in FNA washouts were performed for 64 axillary LNs suspicious for recurrence in 64 post-operative breast cancer patients. Final diagnosis was made on the basis of FNA cytology and follow-up data over at least 2 years. The concentration of CYFRA 21-1 was compared between recurrent LNs and benign LNs. Diagnostic performance and cut-off value were evaluated using a receiver operating characteristic curve. Results Regardless of the non-diagnostic results, the median concentration of CYFRA 21-1 in recurrent LNs was significantly higher than that in benign LNs (p < 0.001). The optimal diagnostic cut-off value was 1.6 ng/mL. The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of CYFRA 21-1 for LN recurrence were 90.9%, 100%, 100%, 98.1%, and 98.4%, respectively. Conclusion Measurement of CYFRA 21-1 concentration from ultrasound-guided FNA biopsy aspirates showed excellent diagnostic performance with a cut-off value of 1.6 ng/mL. These results indicate that measurement of CYFRA 21-1 concentration in FNA washouts is useful for the diagnosis of axillary LN recurrence in post-operative breast cancer patients.

• Journal of Korea Multimedia Society
• /
• v.13 no.5
• /
• pp.663-673
• /
• 2010

As a tool used for video maintenance, Video segmentation divides videos in hierarchical and structural manner. This technique can be considered as a core technique that can be applied commonly for various applications such as indexing, abstraction or retrieval. Conventional video segmentation used adaptive threshold to split video by calculating difference between consecutive frames and threshold value in window with fixed size. In this case, if the time difference between occurrences of cuts is less than the size of a window or there is much difference in neighbor feature, accurate detection is impossible. In this paper, Improved Adaptive threshold algorithm which enables determination of window size according to video format and reacts sensitively on change in neighbor feature is proposed to solve the problems above. Post-Processing method for decrement in error caused by camera flash and fast movement of large objects is applied. Evaluation result showed that there is 3.7% improvement in performance of detection compared to conventional method. In case of application of this method on modified video, the result showed 95.5% of reproducibility. Therefore, the proposed method is more accurated compared to conventional method and having reproducibility even in case of various modification of videos, it is applicable in various area as a video maintenance tool.