• Journal of Korea Society of Industrial Information Systems
• /
• v.24 no.4
• /
• pp.1-8
• /
• 2019

Plant phenomics is a technique for observing and analyzing morphological features in order to select plant varieties of excellent traits. The conventional methods is difficult to apply to the phenomics system. because the color threshold value must be manually changed according to the detection target. In this paper, we propose the convolution neural network (CNN) structure that can automatically segment plants from the background for the phenomics system. The LeafNet consists of nine convolution layers and a sigmoid activation function for determining the presence of plants. As a result of the learning using the LeafNet, we obtained a precision of 98.0% and a recall rate of 90.3% for the plant seedlings images. This confirms the applicability of the phenomics system.

• Korean Chemical Engineering Research
• /
• v.57 no.5
• /
• pp.606-610
• /
• 2019

In this study, we demonstrated that the nonenzymatic glucose sensor based on the flexible carbon fiber bundle electrode with BDD nanocomposites (CF-BDD electrode). As a nano seeding method for the deposition of BDD on flexible carbon fiber, electrostatic self-assembly technique was employed. Surface morphology of BDD coated carbon fiber electrode was observed by scanning electron microscopy. And the electrochemical characteristics were investigated by cyclic voltammetry, electrochemical impedance spectroscopy and chronoamperometry. This CF-BDD electrode exhibited a large surface area, a direct electron transfer between the redox species and the electrode surface and a high catalytic activity, resulting in a wider linear range (3.75~50 mM), a faster response time (within 3 s) and a higher sensitivity (388.8 nA/mM) in comparison to a bare CF electrode. As a durable and flexible electrochemical sensing electrode, this brand new CF-BDD scheme has promising advantages on various electrochemical and wearable sensor applications.

• Korean Journal of Remote Sensing
• /
• v.35 no.3
• /
• pp.359-373
• /
• 2019

Bursaphelenchus xylophilus(Pine wilt disease) is a serious threat to the pine forest in Korea. However, dead wood observation by Pine wilt disease is based on field survey. Therefore, it is difficult to observe large-scale forests due to physical and economic problems. In this paper, high resolution images were obtained using the unmanned aerial vehicle (UAV) in the area where the pine wilt disease recurred. The damaged tree due to pine wilt disease was detected using Artificial Neural Network (ANN), Support Vector Machine (SVM) supervision classification technique. Also, the accuracy of supervised classification results was calculated. After conducting supervised classification on accessible forests, the reliability of the accuracy was verified by comparing the results of field surveys.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.510-512
• /
• 2019

Recently, there have been growing requirements in the public safety sector to ensure safety through detection of hazardous situations or preemptive predictions. It is noteworthy that various sensor data can be analyzed and utilized as a result of mobile device's dissemination, and many advantages can be used in terms of safety and security. An effective modeling technique is needed to combine sensor data generated by smart-phones and wearable devices to analyze users' moving patterns and behavioral patterns, and to ensure public safety by fusing location-based crime risk data provided.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.30 no.2
• /
• pp.177-180
• /
• 2019

To improve the accuracy rate of guided weapons, many studies have been conducted on the accurate detection and identification of targets from sea clutter. Because of the variety and complicated characteristics of both sea-clutter and target signals, an active target recognition technique is required. In this study, we propose an algorithm to distinguish clutter and recognize targets by applying a fractal signature(FS) classifier, which is a fractal dimension, and a high-resolution target image(HRTI) classifier, which applies scene matching to an image formed from a scanned image. Simulation results using the algorithm revealed that the HRTI classifier recognized targets 1 and 2 at a 100 % rate, whereas the FS classifier recognized targets 1 and 2 at rates of 90 % and 93 %, respectively.

• Database Research
• /
• v.34 no.3
• /
• pp.58-68
• /
• 2018

Distributed computing helps to efficiently store and process large data on a cluster of multiple machines. The performance of distributed computing is greatly influenced depending on the state of the servers constituting the distributed system. In this paper, we propose a self-diagnosis system that collects log data in a distributed system, detects anomalies and visualizes the results in real time. First, we divide the self-diagnosis process into five stages: collecting, delivering, analyzing, storing, and visualizing stages. Next, we design a real-time self-diagnosis system that meets the goals of real-time, scalability, and high availability. The proposed system is based on Apache Flume, Apache Kafka, and Apache Storm, which are representative real-time distributed techniques. In addition, we use simple but effective moving average and 3-sigma based anomaly detection technique to minimize the delay of log data processing during the self-diagnosis process. Through the results of this paper, we can construct a distributed real-time self-diagnosis solution that can diagnose server status in real time in a complicated distributed system.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.4
• /
• pp.587-604
• /
• 2021

Because the library cannot be run independently and used by many applications, it is important to detect vulnerabilities in the library. Fuzzing, which is a dynamic analysis, is used to discover vulnerabilities for the library. Although this fuzzing technique shows excellent results in terms of code coverage and unique crash counts, it is difficult to apply its effects to library fuzzing. In particular, a fuzzing executable and a seed corpus are needed that execute the library code by calling a specific function sequence and passing the input of the fuzzer to reproduce the various states of the library. Generating the fuzzing environment such as fuzzing executable and a seed corpus is challenging because it requires both understanding about the library and fuzzing knowledge. We propose a novel method to improve the ease of library fuzzing and enhance code coverage and crash detection performance by using a test framework. The systems's performance in this paper was applied to nine open-source libraries and was verified through comparison with previous studies.

• Journal of Convergence for Information Technology
• /
• v.11 no.1
• /
• pp.20-27
• /
• 2021

Eye tracking is one of the NUI technologies, and it finds out where the user is gazing. This technology allows users to input text or control GUI, and further analyzes the user's gaze so that it can be applied to commercial advertisements. In the eye tracking system, the allowable range varies depending on the quality of the image and the degree of freedom of movement of the user. Therefore, there is a need for a method of estimating the accuracy of eye tracking in advance. The accuracy of eye tracking is greatly affected by how the eye tracking algorithm is implemented in addition to hardware variables. Accordingly, in this paper, we propose a method to estimate how many degrees of gaze changes when the pupil center moves by one pixel by estimating the maximum possible movement distance of the pupil center in the image.

• Journal of the Korea Convergence Society
• /
• v.12 no.1
• /
• pp.49-55
• /
• 2021

Recently, with the development of database, it is possible to store a lot of data generated in finance, security, and networks. These data are being analyzed through classifiers based on machine learning. The main problem at this time is data imbalance. When we train imbalanced data, it may happen that classification accuracy is degraded due to over-fitting with majority class data. To overcome the problem of data imbalance, oversampling strategy that increases the quantity of data of minority class data is widely used. It requires to tuning process about suitable method and parameters for data distribution. To improve the process, In this study, we propose a strategy to explore and optimize oversampling combinations and ratio based on various methods such as synthetic minority oversampling technique and generative adversarial networks through genetic algorithms. After sampling credit card fraud detection which is a representative case of data imbalance, with the proposed strategy and single oversampling strategies, we compare the performance of trained classifiers with each data. As a result, a strategy that is optimized by exploring for ratio of each method with genetic algorithms was superior to previous strategies.

• Applied Chemistry for Engineering
• /
• v.31 no.6
• /
• pp.585-590
• /
• 2020

Successful early diagnosis of cancer diseases such as lung, prostate, liver and adrenocortical carcinoma is a key step in determining the cost of treatment, survival rate, and cure rate. Most of current cancer diagnosis systems including biopsy, computed tomography (CT), positron emission tomography (PET)-CT, magnetic resonance imaging (MRI), ultrasonography, etc., require expensive and complicated equipment with highly trained human resources. Global medical and scientific communities have thus made numerous efforts on developing effective but rapid disease management system via introducing a wide spectrum of point-of-care medical diagnosis devices. Among them, a lateral flow immunoassay strip technique has gained a great attention due to many advantages such as cost-effectiveness, short inspection time, and user friendly accessibility. In this mini-review, we will highlight recent research trend on the development of colorimetry based LFIA strips for cancer diagnosis and discuss the future research direction and potential applications.