• Journal of Bio-Environment Control
• /
• 제6권1호
• /
• pp.55-65
• /
• 1997

This study was conducted to develop a robotic transplanter for bedding plants. The robotic transplanter consisted of machine vision system, manipulator attached with the specially designed gripper, and plug tray transfer system. Results of this study were as follows. 1. A machine vision system for a robotic transplanter was developed. The success rates of detecting empty cells and bad seedlings in 72-cell and 128-cell plug-trays for cucumber seedlings were 98.8％ and 94.9％ respectively. The success rates of identifying leaf orientation for 72- cell and 128-cell plug-trays were 93.5% and 91.0%, respectively. 2. A cartesian coordinate manipulator for a robotic transplanter with 3 degrees of freedom was constructed. The accuracy of position control was $\pm$ 1mm. 3. The robotic transplanter was tested with a shovel-type finger. Without considering leaf orientation, the success rates of transplanting healthy cucumber seedlings for 72-cell and 128-cell plug-trays were 95.5% and 94.5%, respectively. Considering leaf orientation, the success rates of transplanting healthy cucumber seedling in 72-cell and 128-cell plug-trays were 96.0% and 95.0%, respectively.

• Journal of the Institute of Convergence Signal Processing
• /
• 제12권2호
• /
• pp.150-156
• /
• 2011

Smart Highway is a next generation highway that significantly improves a traffic safety, reduces incidence of traffic accidents, and supports intelligent and convenient driving environments so that drivers can drive at high speeds in safety. In order to implement smart highway, it is required to gather a large amount of data including conditions of a road and the status of vehicles, and other useful data. To provide situation information of highway, it has been gathered traffic information using optical sensors(CCTV, etc.). However, this technique has problems such as the problem of information gathering, lack of accuracy depending on weather conditions and limitation of maintenance. It needs radar system which has not effect on environmental change and algorithm processing technique in order to provide information for a safety driving to driver and car. In this paper, it is used radar with 9.4GHz to test performance of a road surface and developed radar system for detecting test. And we compared and analyzed a performance of data acquired from each radar through computer simulation.

• Journal of the Institute of Electronics and Information Engineers
• /
• 제52권11호
• /
• pp.47-54
• /
• 2015

The number of users of SNS such as Twitter and Facebook increases due to the development of internet and the spread of supply of mobile devices such as smart phone. Moreover, there are also an increasing number of content pollution problems that pollute SNS by posting a product advertisement, defamatory comment and adult contents, and so on. This paper proposes an improved method of extracting the feature of content polluter for detecting a content polluter in SNS. In particular, this paper presents a method of extracting the feature of content polluter on the basis of incremental approach that considers only increment in data, not batch processing system of entire data in order to efficiently extract the feature value of new user data at the stage of predicting and classifying a content polluter. And it comparatively assesses whether the proposed method maintains classification accuracy and improves time efficiency in comparison with batch processing method through experiment.

• Smart Structures and Systems
• /
• 제25권3호
• /
• pp.285-299
• /
• 2020

Long term structural health monitoring has gained wide attention among civil engineers in recent years due to the scale and severity of infrastructure deterioration. Establishing effective damage indicators and proposing enhanced monitoring methods are of great interests to the engineering practices. In the case of bridge health monitoring, long term structural vibration measurement has been acknowledged to be quite useful and utilized in the planning of maintenance works. Previous researches are majorly concentrated on linear time series models for the measurement, whereas nonlinear dependences among the measurement are not carefully considered. In this paper, a new bridge health monitoring method is proposed based on the use of long term vibration measurement. A combination of the fundamental ARMA model and copula theory is investigated for the first time in detecting bridge structural damages. The concept is applied to a real engineering practice in Japan. The efficiency and accuracy of the copula based damage indicator is analyzed and compared in different window sizes. The performance of the copula based indicator is discussed based on the damage detection rate between the intact structural condition and the damaged structural condition.

• Journal of Korean Medical Science
• /
• 제33권52호
• /
• pp.337.1-337.14
• /
• 2018

Background: Mitochondrial heteroplasmy, the co-existence of different mitochondrial polymorphisms within an individual, has various forensic and clinical implications. But there is still no guideline on the application of massively parallel sequencing (MPS) in heteroplasmy detection. We present here some critical issues that should be considered in heteroplasmy studies using MPS. Methods: Among five samples with known innate heteroplasmies, two pairs of mixture were generated for artificial heteroplasmies with target minor allele frequencies (MAFs) ranging from 50% to 1%. Each sample was amplified by two-amplicon method and sequenced by Ion Torrent system. The outcomes of two different analysis tools, Torrent Suite Variant Caller (TVC) and mtDNA-Server (mDS), were compared. Results: All the innate heteroplasmies were detected correctly by both analysis tools. Average MAFs of artificial heteroplasmies correlated well to the target values. The detection rates were almost 90% for high-level heteroplasmies, but decreased for low-level heteroplasmies. TVC generally showed lower detection rates than mDS, which seems to be due to their own computation algorithms which drop out some reference-dominant heteroplasmies. Meanwhile, mDS reported several unintended low-level heteroplasmies which were suggested as nuclear mitochondrial DNA sequences. The average coverage depth of each sample placed on the same chip showed considerable variation. The increase of coverage depth had no effect on the detection rates. Conclusion: In addition to the general accuracy of the MPS application on detecting heteroplasmy, our study indicates that the understanding of the nature of mitochondrial DNA and analysis algorithm would be crucial for appropriate interpretation of MPS results.

• Nutrition Research and Practice
• /
• 제13권6호
• /
• pp.521-528
• /
• 2019

BACKGROUND/OBJECTIVES: The aim of this study was to develop Korean food image detection and recognition model for use in mobile devices for accurate estimation of dietary intake. MATERIALS/METHODS: We collected food images by taking pictures or by searching web images and built an image dataset for use in training a complex recognition model for Korean food. Augmentation techniques were performed in order to increase the dataset size. The dataset for training contained more than 92,000 images categorized into 23 groups of Korean food. All images were down-sampled to a fixed resolution of $150{\times}150$ and then randomly divided into training and testing groups at a ratio of 3:1, resulting in 69,000 training images and 23,000 test images. We used a Deep Convolutional Neural Network (DCNN) for the complex recognition model and compared the results with those of other networks: AlexNet, GoogLeNet, Very Deep Convolutional Neural Network, VGG and ResNet, for large-scale image recognition. RESULTS: Our complex food recognition model, K-foodNet, had higher test accuracy (91.3%) and faster recognition time (0.4 ms) than those of the other networks. CONCLUSION: The results showed that K-foodNet achieved better performance in detecting and recognizing Korean food compared to other state-of-the-art models.

• Journal of the Korea Society of Computer and Information
• /
• 제25권4호
• /
• pp.19-27
• /
• 2020

In this paper, we propose a machine learning method for diagnosing the failure of a gas pressure regulator. Originally, when implementing a machine learning model for detecting abnormal operation of a facility, it is common to install sensors to collect data. However, failure of a gas pressure regulator can lead to fatal safety problems, so that installing an additional sensor on a gas pressure regulator is not simple. In this paper, we propose various machine learning approach for diagnosing the abnormal operation of a gas pressure regulator with only the flow rate and gas pressure data collected from a gas pressure regulator itself. Since the fault data of a gas pressure regulator is not enough, the model is trained in all classes by applying the over-sampling method. The classification model was implemented using Gradient boosting, 1D Convolutional Neural Networks, and LSTM algorithm, and gradient boosting model showed the best performance among classification models with 99.975% accuracy.

• Journal of Korean Society for Quality Management
• /
• 제49권3호
• /
• pp.327-340
• /
• 2021

Purpose: The purpose of this study is to propose a system predicting whether an electricity distribution system is abnormal by analyzing the temperature of the deteriorated system. Traditional electricity distribution system abnormality diagnosis was mainly limited to post-inspection. This research presents a remote monitoring system for detecting thermal images of the deteriorated electricity distribution system efficiently hereby providing safe and efficient abnormal diagnosis to electricians. Methods: In this study, an object detection algorithm (YOLOv5) is performed using 16,866 thermal images of electricity distribution systems provided by KEPCO(Korea Electric Power Corporation). Abnormality/Normality of the extracted system images from the algorithm are classified via the limit temperature. Each classification model, Random Forest, Support Vector Machine, XGBOOST is performed to explore 463,053 temperature datasets. The process capability index is employed to indicate the quality of the electricity distribution system. Results: This research performs case study with transformers representing the electricity distribution systems. The case study shows the following states: accuracy 100%, precision 100%, recall 100%, F1-score 100%. Also the case study shows the process capability index of the transformers with the following states: steady state 99.47%, caution state 0.16%, and risk state 0.37%. Conclusion: The sum of caution and risk state is 0.53%, which is higher than the actual failure rate. Also most transformer abnormalities can be detected through this monitoring system.

• Journal of Plant Biotechnology
• /
• 제47권4호
• /
• pp.309-315
• /
• 2020

Advances in biotechnology have led to progress in crop genetic engineering to improve agricultural productivity. The use of genetically modified (GM) crops has increased, as have consumers' and regulators' concerns about the safety of GM crops to human health, and ecological biodiversity. As such, the identification of GM crops is a critical issue for developers and distributors, and their labeling is mandatory. Multiplex polymerase chain reaction (PCR) has been developed and its use validated for the detection and identification of GM crops in quarantine. Herein, we established a simultaneous detection method to identify four GM maize events. Event-specific primers were designed between the junction region of transgene and genome of four GM maize lines, namely 5307, DAS-40278-9, MON87460, and MON87427. To verify the efficiency and accuracy of the multiplex PCR we used specificity analysis, limit of detection evaluation, and mixed certified reference materials identification. The multiplex PCR method was applied to analyze 29 living, modified maize volunteers collected in South Korea in 2018 and 2019. We performed multiplex PCR analysis to identify events and confirmed the result by simplex PCR using each event-specific primer. As a result, rather than detecting each event individually, the simultaneous detection PCR method enabled the rapid analysis of 29 GM maize volunteers. Thus, the novel multiplex PCR method is applicable for living modified organism volunteer identification.

• Journal of the Korea Society of Computer and Information
• /
• 제26권12호
• /
• pp.123-132
• /
• 2021

Malicious activities of Botnets are responsible for huge financial losses to Internet Service Providers, companies, governments and even home users. In this paper, we try to confirm the possibility of detecting botnet traffic by applying the deep learning model Convolutional Neural Network (CNN) using the CTU-13 botnet traffic dataset. In particular, we classify three classes, such as the C&C traffic between bots and C&C servers to detect C&C servers, traffic generated by bots other than C&C communication to detect bots, and normal traffic. Performance metrics were presented by accuracy, precision, recall, and F1 score on classifying both known and unknown botnet traffic. Moreover, we propose a stackable botnet detection system that can load modules for each botnet type considering scalability and operability on the real field.