• Journal of Multimedia Information System
• /
• 제3권2호
• /
• pp.1-8
• /
• 2016

In this paper, we propose a method to automatically diagnose various diseases. The input data consists of electrocardiograph (ECG) recordings. We extract R-to-R interval (RRI) signals from ECG recordings, which are preprocessed to remove trends and ectopic beats, and to keep the signal stationary. After that, we perform some prospective analysis to extract time-domain parameters, frequency-domain parameters, and nonlinear parameters of the signal. Those parameters are unique for each disease and can be used as the statistical symptoms for each disease. Then, we perform feature selection to improve the performance of the diagnosis classifier. We utilize the selected features to diagnose various diseases using machine learning. We subsequently measure the performance of the machine learning classifier to make sure that it will not misdiagnose the diseases. The first two steps, which are R-to-R extraction and preprocessing, have been successfully implemented with satisfactory results.

• Journal of Welding and Joining
• /
• 제19권2호
• /
• pp.208-214
• /
• 2001

In this study, we constructed a visual sensor system for weld seam tracking in real time in GMA welding. A sensor part consists of a CCD camera, a band-pass filter, a diode laser system with a cylindrical lens, and a vision board for inter frame process. We used a commercialized robot system which includes a GMA welding machine. To extract the weld seam we used a inter frame process in vision board from that we could remove the noise due to the spatters and fume in the image. Since the image was very reasonable by using the inter frame p개cess, we could use the simplest way to extract the weld seam from the image, such as first differential and central difference method. Also we used a moving average method to the successive position data or weld seam for reducing the data fluctuation. In experiment the developed robot system with visual sensor could be able to track a most popular weld seam. such as a fillet-joint, a V-groove, and a lap-joint of which weld seam include planar and height directional variation.

• 산업기술연구
• /
• 제29권A호
• /
• pp.19-25
• /
• 2009

The proper orthogonal decomposition (POD) analysis of vibration of a steel frame structure is performed to extract modal parameters. The theoretical background of the POD method is introduced briefly, and this technique is further applied to free vibration displacements of one bay-two story steel frame structure to extract the modal parameters. From the POD analysis of the steel frame structure, it is found that important modal parameters such as true mode shapes, modal kinematic energy, natural frequencies, and damping ratios can be obtained for the building efficiently and in detail. Therefore, it is concluded that the POD method could be one of the useful techniques in analysis of vibration of structures.

• IEIE Transactions on Smart Processing and Computing
• /
• 제4권4호
• /
• pp.265-271
• /
• 2015

This study proposes an algorithm for recognizing apple trees in images and detecting apples to measure the number of apples on the trees. The proposed algorithm explores whether there are apple trees or not based on the number of image block-unit edges, and then it detects apple areas. In order to extract colors appropriate for apple areas, the CIE $L^*a^*b^*$ color space is used. In order to extract apple characteristics strong against illumination changes, modified census transform (MCT) is used. Then, using the AdaBoost learning algorithm, characteristics data on the apples are learned and generated. With the generated data, the detection of apple areas is made. The proposed algorithm has a higher detection rate than existing pixel-based image processing algorithms and minimizes false detection.

• 대한수학회논문집
• /
• 제16권3호
• /
• pp.459-485
• /
• 2001

The aim of EIT (electrical impedance tomography) system is to image cross-section conductivity distribution of a human body by means of both generating and sensing electrodes attached on to the surface of the body, where currents are injected and voltages are measured. EIT has been suffered from the severe ill-posedness which is caused by the inherent low sensitivity of boundary measurements to any changes of internal tissue conductivity values. With a limited set of current-to-voltage data, figuring out full structure of the conductivity distribution could be extremely difficult at present time, so it could be worthwhile to extract some necessary partial information of the internal conductivity. We try to extract some key patterns of current-to-voltage data that furnish some core information on the conductivity distribution such s location and size. This overview provides our recent observation on the location search and the size estimation.

• Bulletin of the Korean Chemical Society
• /
• 제22권5호
• /
• pp.455-462
• /
• 2001

The time-dependent tracking inversion method is studied to extract the potential energy surface of the electronic excited state in the photodissociation of triatomic molecules. Based on the relay of the regularized inversion procedure and time-dependent wave packet propagation, the algorithm extracts the underlying potential energy surface piece by piece by tracking the time-dependent data, which can be synthesized from Raman excitation profiles. We have demonstrated the algorithm to extract the potential energy surface of electronic excited state for NO2 molecule where the wave packet split on a saddle-shaped surface. Finally, we describe the merits of the time-dependent tracking inversion method compared with the time-independent inversion method and discussed several extensions of the algorithm.

• Journal of information and communication convergence engineering
• /
• 제21권1호
• /
• pp.9-16
• /
• 2023

The natural language on social network platforms has a certain front-to-back dependency in structure, and the direct conversion of Chinese text into a vector makes the dimensionality very high, thereby resulting in the low accuracy of existing text classification methods. To this end, this study establishes a deep learning model that combines a big data ultra-deep convolutional neural network (UDCNN) and long short-term memory network (LSTM). The deep structure of UDCNN is used to extract the features of text vector classification. The LSTM stores historical information to extract the context dependency of long texts, and word embedding is introduced to convert the text into low-dimensional vectors. Experiments are conducted on the social network platforms Sogou corpus and the University HowNet Chinese corpus. The research results show that compared with CNN + rand, LSTM, and other models, the neural network deep learning hybrid model can effectively improve the accuracy of text classification.

• 국제학술발표논문집
• /
• The 6th International Conference on Construction Engineering and Project Management
• /
• pp.97-100
• /
• 2015

Analysis of construction tender documents in overseas projects is a very important issue from a risk management point of view. Unfortunately, majority of construction firms are biased by winning contracts without in-depth analysis of tender documents. As a result, many contractors have incurred loss in overseas projects. Although a lot of risk analysis techniques have been introduced, most of them focus project's external unexpected risks such as country conditions and owner's financial standing. However, because those external risks are difficult to control and take preemptive action, we need to concentrate on project inherent risks. Based on this premise, this paper proposes a project-oriented risk mining approach which could detect and extract project risk factors automatically before they are materialized and assess them. This study presents a methodology regarding how to extract potential risks which exist in owner's project requirements and project tender documents using state of the art data analysis method such as text mining, data mining, and information visualization. The project-oriented risk mining approach is expected to effectively reflect project characteristics to the project risk management and could provide construction firms with valuable business intelligence.

• 한국식품영양학회지
• /
• 제33권1호
• /
• pp.91-97
• /
• 2020

The purpose of this study was to provide the basic data of butternut squash (Cucurbita moschata) according to the drying methods. The proximate composition and chromaticity of freeze-dried and hot air-dried Cucurbita moschata powders were evaluated, and the antioxidant effects of these ethanolic extracts were analyzed by DPPH, ABTS, FRAP, reducing power activity, total phenolic, and flavonoid content. As a result, Cucurbita moschata was revealed to have high carbohydrate and crude protein contents, while crude ash and crude fat contents were relatively low. Also, it was confirmed that the hot air-dried Cucurbita moschata had lower L, a, and b values than the freeze-dried Cucurbita moschata. Additionally, as a result of analyzing the antioxidant activity of Cucurbita moschata ethanolic extracts, hot air-dried Cucurbita moschata ethanolic extract showed significantly superior antioxidant activity than freeze-dried Cucurbita moschata ethanolic extract. Also, hot air-dried Cucurbita moschata ethanolic extract was revealed to have a higher polyphenol content, but slightly lower flavonoid content than freeze-dried Cucurbita moschata ethanolic extract. Based on the data from this study, further experiments on Cucurbita moschata material are necessary.

• 한방재활의학과학회지
• /
• 제30권2호
• /
• pp.153-164
• /
• 2020

Objectives This study is designed to evaluate the safety of Soshihotang soft extract in healthy male volunteers. Methods 12 healthy male volunteers were recruited and this study was carried out by a single center. Laboratory test results, vital signs of the volunteers were collected to evaluate safety. According to registration order, the 12 subjects were allocated by serial number. To evaluate safety, blood samples were taken and vital signs were checked 4 times-screening, pre administration, post administration and follow up-during the whole trial. The incidence of all adverse effects are shown in percentage. The mean and standard deviation were used to to describe and summarize continuous data. To evalate the effectiveness of the intervention, data of blood tests was analyzed by Wilcoxon signed rank test or paired T-test (p<0.05). Results In the case of red blood cell, hemoglobin, hematocrit, neutrophils, protein, albumin, alkaline phosphatase, aspartate aminotransferase, alanine aminotransferase, γ-glutamyl transpeptidase values, the normality test result of the variable for the difference value before and after the dosing has a significance level <0.05. But most of values did not deviate from the normal range, and the deviation from the normal range could not be regarded as the significance associated with this clinical trial. And adverse event wasn't observed associated with the clinical trial drug. Conclusions Soshihotang soft extract were considered to be safe for healthy male volunteers.