• International Journal of Advanced Culture Technology
• /
• v.9 no.3
• /
• pp.305-314
• /
• 2021

Currently, due to COVID-19, household waste has a lot of impact on the environment due to packaging of food delivery. In this paper, we design and implement Faster-RCNN, SSD, and YOLOv4 models for municipal waste detection and classification. The data set explores two types of plastics, which account for a large proportion of household waste, and the types of aluminum cans. To classify the plastic type and the aluminum can type, 1,083 aluminum can types and 1,003 plastic types were studied. In addition, in order to increase the accuracy, we compare and evaluate the loss value and the accuracy value for the detection of municipal waste classification using Faster-RCNN, SDD, and YoloV4 three models. As a final result of this paper, the average precision value of the SSD model is 99.99%, the average precision value of plastics is 97.65%, and the mAP value is 99.78%, which is the best result.

• Journal of international Conference on Electrical Machines and Systems
• /
• v.2 no.3
• /
• pp.336-341
• /
• 2013

Power converter plays a very important role in switched reluctance motor (SRM) systems, and it is also the easiest one to experience failures. Power converter faults will cause the motor to run in non equilibrium states, and a long time fault operation will lead to motor and other modules damaged, and make the system completely lose working stability. This paper uses an asymmetric bridge converter as the research object with three-phase SRM, employs the wavelet packet decomposition for the phase currents. It analyzes and studies the short circuit fault condition of IGBT, uses an energy discrete degree of the wavelet packet nodes as the fault characteristic, and conducts the corresponding experimental and simulation analysis to verify the effectiveness and practicality of the proposed method.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.201-203
• /
• 2022

Over the past five years, the number of patients treated for diabetes has increased by 27.7% to 3.22 million, and since blood sugar is still checked through finger blood collection, continuous blood glucose measurement and blood sugar peak confirmation are difficult and painful. To solve this problem, based on blood sugar data measured for 14 days, three months of blood sugar prediction data are provided to diabetics using artificial intelligence technology.

• Steel and Composite Structures
• /
• v.30 no.4
• /
• pp.315-325
• /
• 2019

Double skin composite walls offer structural and economic merits over conventional reinforced concrete counterparts in terms of higher capacity, greater stiffness, and better ductility. This paper investigated the axial behavior of double skin composite walls with steel truss connectors. Full-scaled tests were conducted on three specimens with different height-to-thickness ratios. Test results were evaluated in terms of failure mode, load-axial displacement response, buckling loading, axial stiffness, ductility, strength index, load-lateral deflection, and strain distribution. The test data were compared with AISC 360 and Eurocode 4 and it was found that both codes provided conservative predictions on the safe side.

• Steel and Composite Structures
• /
• v.46 no.5
• /
• pp.649-658
• /
• 2023

Although some scholars have studied the thermal post-buckling of graphene platelets strengthened metal foams (GPLRMFs) plates, they have not considered the influence of initial geometrical imperfection. Inspired by this fact, the present paper studies the thermal post-buckling characteristics of GPLRMFs plates with initial geometrical imperfection. Three kinds of graphene platelets (GPLs) distribution patterns including three patterns have been considered. The governing equations are derived according to the first-order plate theory and solved with the help of the Galerkin method. According to the comparison with published paper, the accuracy and correctness of the present research are verified. In the end, the effects of material properties and initial geometrical imperfection on the thermal post-buckling response of the GPLRMFs plates are examined. It can be found that the presence of initial geometrical imperfection reduces the thermal post-buckling strength. In addition, the present study indicates that GPL-A pattern is best way to improve thermal post-buckling strength for GPLRMFs plates, and the presence of foams can improve the thermal post-buckling strength of GPLRMFs plates, the Foam- II and Foam- I patterns have the lowest and highest thermal post-buckling strength. Our research can provide guidance for the thermal stability analysis of GPLRMFs plates.

• Journal of architectural history
• /
• v.25 no.2
• /
• pp.45-56
• /
• 2016

The purpose of this study is to analyze the evolutionary process of Ddeulzip. The subject of this study is a clan family of Andong Kwon in Andong Area. Ddeulzip's evolutionary process of the construction and management is divided into largely three periods in Josun Dynasty. The establishment and changing process of Ddeulzip for Andong Kwon's family are analyzed according to three periods called the early(15~16C), mid(17~18C) and late(19~20C). The characteristics of the early and mid period are that they created their own ancestral building form of Ddeulzip. Those of the late period are in their strong will to make similar scale of Ddeulzip. And during the late period, although the construction of new Ddeulzip was started in the early stage, no more formation of Ddeulzip was made as it approached toward the late stage. And most important point is similar constructional space(gan) of first time. The residential Ddeulzip of Andong Kwon's family created at the 19C can be regarded as an representative example of large space that shows a typical form of housing by noble residents at the time.

• Journal of architectural history
• /
• v.23 no.2
• /
• pp.25-37
• /
• 2014

The purpose of this study is to analyze the evolutionary process of Ddeulzip. The subject of this study is a clan family of Euisung Kim in Andong Area. Ddeulzip's evolutionary process in the construction and management is divided into largely three periods. The establishment and changing process of Ddeulzip for Euisung Kim's family are analyzed according to three periods called the early (15~16C), mid(17~18C) and late(19~20C). The characteristics of the early period are that they created their own ancestral building form of Ddeulzip. Those of the mid period are in their strong will not only to preserve their on ancesteral housing but also to make additional construction of Ddeulzip. And during the late period, although the construction of new Ddeulzip was started in the early stage, no more formation of Ddeulzip was made as it approached toward the late stage. And most important point is smaller construction space (gan) dan first time. The residential Ddeulzip of Euisung Kim's family created at the start of Chosun Dynasty can be regarded as an representative example that shows a typical form of housing by noble residents at the time.

• Journal of the Korean Society of Industry Convergence
• /
• v.26 no.1
• /
• pp.35-46
• /
• 2023

A model test is performed to measure the sloshing impact pressure in the liquid tank. A preprocessing is performed to learn the model test results applied with various environmental conditions. In this study, we propose a method for generating data similar to the total pressure data using Generative Adversarial Networks. In addition, after approximating the generated result to the three parameter Weibull distribution, the difference of the three parameters was compared through the RMSE and SMAPE calculation results. As a result, the distribution of the generated data showed similar results to the total pressure data distribution.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.53-62
• /
• 2022

The deployment of advanced structural health monitoring (SHM) systems in large-scale civil structures collects large amounts of data. Note that these data may contain multiple types of anomalies (e.g., missing, minor, outlier, etc.) caused by harsh environment, sensor faults, transfer omission and other factors. These anomalies seriously affect the evaluation of structural performance. Therefore, the effective analysis and mining of SHM data is an extremely important task. Inspired by the deep learning paradigm, this study develops a novel generative adversarial network (GAN) and convolutional neural network (CNN)-based data anomaly detection approach for SHM. The framework of the proposed approach includes three modules : (a) A three-channel input is established based on fast Fourier transform (FFT) and Gramian angular field (GAF) method; (b) A GANomaly is introduced and trained to extract features from normal samples alone for class-imbalanced problems; (c) Based on the output of GANomaly, a CNN is employed to distinguish the types of anomalies. In addition, a dataset-oriented method (i.e., multistage sampling) is adopted to obtain the optimal sampling ratios between all different samples. The proposed approach is tested with acceleration data from an SHM system of a long-span bridge. The results show that the proposed approach has a higher accuracy in detecting the multi-pattern anomalies of SHM data.

• Journal of Sasang Constitutional Medicine
• /
• v.16 no.2
• /
• pp.122-127
• /
• 2004

1. Objectives The Excessive sweating or Hyperhidrosis is a state of abnormal sweating on palm, sole and axillary region. But we do not know the exact cause and the healing method of that. It is known that the only treatment of Excessive sweating is surgical sympathectomy and a thoracic sympathetic gan-glion block with neurolytics. 2. Methods We have three case-reports of the patients who have the excessive sweating. 3. Results In this study the patients classified by Sasang constitutional medicine had a notable medical effects. And in the result, any symptom is not remained. 4. Conclusions So we report the healing processes and results of these patients in this study.