• Smart Media Journal
• /
• v.11 no.4
• /
• pp.9-18
• /
• 2022

Recently, research and system using AI is rapidly increasing in various fields. Smart farm using artificial intelligence and information communication technology is also being studied in agriculture. In addition, data-based precision agriculture is being commercialized by convergence various advanced technology such as autonomous driving, satellites, and big data. In Korea, the number of commercialization cases of facility agriculture among smart agriculture is increasing. However, research and investment are being biased in the field of facility agriculture. The gap between research and investment in facility agriculture and open-air agriculture continues to increase. The fields of fruit trees and plant factories have low research and investment. There is a problem that the big data collection and utilization system is insufficient. In this paper, we are proposed the system for determining the fruit tree growth stage using a deep learning-based object detection model. The system was proposed as a hybrid app for use in agricultural sites. In addition, we are implemented an object detection function for the fruit tree growth stage determine.

• Journal of Digital Convergence
• /
• v.15 no.7
• /
• pp.213-222
• /
• 2017

This paper proposes a new service design which is deep learning-based image retrieval system for product search on O2O shopping mall platform. We have implemented deep learning technology that provides more convenient retrieval service for diverse images of many products that are sold in the internet shopping malls. In order to implement this retrieval system, real data used by shopping mall companies were used as experimental data. However, result from several experiments have confirmed deterioration of retrieval performance due to data components. In order to improve the performance, the learning data that interferes with the retrieval is revised several times, and then the values of experimental result are quantified with the verification data. Using the numerical values of these experiments, we have applied them to the new service design in this system.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.477-480
• /
• 2021

본 논문에서는 딥러닝 기술을 활용한 객체 검출(object detection) 모델인 YOLO를 기반으로 하는 감정에 따른 표정 인식 시스템을 활용하여 상담 시 보조 도구로 사용하는 방법을 제공한다. 또한, 머신러닝 기술 기반의 툴킷인 dlib 라이브러리를 사용하여 마스크 착용자의 눈 형태 관측을 통한 표정 인식 및 감정 분석의 정확도 상승을 도모하였다. 이 기술은 코로나19의 장기화로 온라인 수업이나 화상회의를 지원하는 플랫폼들이 전성기를 누리고 있는 현시점에서 다양한 분야로 확장할 수 있을 것으로 기대한다.

• Annual Conference of KIPS
• /
• 2021.05a
• /
• pp.459-462
• /
• 2021

본 연구는 반도체 제조 공정중 발생하는 센서 데이터를 활용하여 딥러닝기반으로 불량을 예측하는 모델을 제안한다. 반도체 공장에서는 FDC((Fault Detection and Classification)라는 불량을 예측하는 시스템이 있지만, 공정의 복잡도가 높고 센서의 종류가 많아 공정 관리자가 모든 센서의 기준을 설정 및 관리하는데 한계가 있다. 이를 해결하기 위해 공정 설비의 센서 데이터를 딥러닝을 활용하여 학습시켜 센서 기준정보로 임계치를 제공하고, 가공중 발생하는 센서 데이터가 입력되면 정상 여부를 판정하는 모델을 제안한다.

• KIPS Transactions on Computer and Communication Systems
• /
• v.10 no.2
• /
• pp.39-46
• /
• 2021

Damages by malware have recently been increasing. Conventional signature-based antivirus solutions are helplessly vulnerable to unprecedented new threats such as Zero-day attack and ransomware. Despite that, many enterprises have retained signature-based antivirus solutions as part of the multiple endpoints security strategy. They do recognize the problem. This paper proposes a solution using the blockchain and deep learning technologies as the next-generation antivirus solution. It uses the antivirus software that updates through an existing DB server to supplement the detection unit and organizes the blockchain instead of the DB for deep learning using various samples and forms to increase the detection rate of new malware and falsified malware.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.01a
• /
• pp.9-10
• /
• 2022

본 논문에서는 딥러닝을 활용하여 취업준비생들의 데이터에 의하여 취업 가능 여부와 그에 따른 유용한 정보들을 얻기 위한 시스템을 제안한다. 취업 가능성이 성공적으로 평가된다면 예비 사회인, 취업준비생, 대학생들이 미리 취업 준비가 어느 정도 이루어졌는지 본인의 위치를 평가할 수 있으며 강점과 약점을 파악할 수 있을 것이다. 본 연구를 위해 취업생 및 취업준비생 데이터를 포함하는 CSV파일을 생성하였고, 딥러닝을 활용하여 유용한 정보들을 추출해내는데 성공했다. 이를 통해 취업 가능성 예측 프로그램은 취업준비생들과 기업의 인사관리자들에게 커다란 이점을 제공할 수 있을 것으로 보인다. 더 나아가 이 프로그램은 기업 구성원들의 업무능력을 평가할 수 있는 프로그램으로도 활용할 수 있을 것으로 사료된다.

• Journal of Software Assessment and Valuation
• /
• v.15 no.1
• /
• pp.63-70
• /
• 2019

These days, as Interest in Image recognition with deep learning is increasing, there has been a lot of research in image recognition using deep learning. In this study, we propose a system for classifying rocks through rock images of 18 types of rock(6 types of igneous, 6 types of metamorphic, 6 types of sedimentary rock) which are addressed in the high school curriculum, using CNN model based on Tensorflow, deep learning open source framework. As a result, we developed a classifier to distinguish rocks by learning the images of rocks and confirmed the classification performance of rock classifier. Finally, through the mobile application implemented, students can use the application as a learning tool in classroom or on-site experience.

• Korean Journal of Remote Sensing
• /
• v.40 no.4
• /
• pp.351-361
• /
• 2024

Satellite imagery contains various elements such as clouds, cloud shadows, and terrain shadows. Accurately identifying and eliminating these factors that complicate satellite image analysis is essential for maintaining the reliability of remote sensing imagery. For this reason, satellites such as Landsat-8, Sentinel-2, and Compact Advanced Satellite 500-1 (CAS500-1) provide Usable Data Masks(UDMs)with images as part of their Analysis Ready Data (ARD) product. Precise detection of clouds and their shadows is crucial for the accurate construction of these UDMs. Existing cloud and their shadow detection methods are categorized into threshold-based methods and Artificial Intelligence (AI)-based methods. Recently, AI-based methods, particularly deep learning networks, have been preferred due to their advantage in handling large datasets. This study aims to analyze the applicability of constructing UDMs for high-resolution satellite images through deep learning-based cloud and their shadow detection using open-source datasets. To validate the performance of the deep learning network, we compared the detection results generated by the network with pre-existing UDMs from Landsat-8, Sentinel-2, and CAS500-1 satellite images. The results demonstrated that high accuracy in the detection outcomes produced by the deep learning network. Additionally, we applied the network to detect cloud and their shadow in KOMPSAT-3/3A images, which do not provide UDMs. The experiment confirmed that the deep learning network effectively detected cloud and their shadow in high-resolution satellite images. Through this, we could demonstrate the applicability that UDM data for high-resolution satellite imagery can be constructed using the deep learning network.

• Journal of Korea Water Resources Association
• /
• v.54 no.8
• /
• pp.599-606
• /
• 2021

Water Distribution Networks, one of the social infrastructures buried underground, has the function of transporting and supplying purified water to customers. In recent years, as measurement capability is improved, a number of studies related to leak recognition and detection by applying a deep learning technique based on flow rate data have been conducted. In this study, a cognitive model for leak occurrence was developed using an LSTM-based deep learning algorithm that has not been applied to the waterworks field until now. The model was verified based on the assumed data, and it was found that all cases of leaks of 2% or more can be recognized. In the future, based on the proposed model, it is believed that more precise results can be derived in the prediction of flow data.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.3
• /
• pp.75-81
• /
• 2024

In this paper, we proposes a method for real-time processing of inter-floor noise problems by embedding TinyML, which includes a deep learning model, into ultra-low-power systems. The reason this method is feasible is because of lightweight deep learning model technology, which allows even systems with small computing resources to perform inference autonomously. The conventional method proposed to solve inter-floor noise problems was to send data collected from sensors to a server for analysis and processing. However, this centralized processing method has issues with high costs, complexity, and difficulty in real-time processing. In this paper, we address these limitations by employing On-Sensor AI using TinyML. The method presented in this paper is simple to install, cost-effective, and capable of processing problems in real-time.