• Journal of Digital Contents Society
• /
• v.19 no.4
• /
• pp.749-756
• /
• 2018

In this study, we developed a prediction model for greenhouse control using machine learning technique. The prediction model was developed using measured data (2016) on greenhouse in the Protected Horticulture Research Institute. In order to improve the predictive performance of model and to ensure the reliability of data, the dimension of the data was reduced by correlation analysis. The dataset were divided into spring, summer, autumn, and winter considering the seasonal characteristics. An artificial neural network, recurrent neural network, and multiple regression model were constructed as a machine leaning based prediction model and evaluated by comparative analysis with real dataset. As a result, ANN showed good performance in selected dataset, while MRM showed good performance in full dataset.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.6
• /
• pp.1331-1336
• /
• 2023

In text-based fish disease classification using machine learning, there is a problem that the input parameters of the machine learning model are too many, but due to performance problems, the input parameters cannot be arbitrarily reduced. This paper proposes a method of optimizing input parameters specialized for Paralichthys olivaceus disease classification using SHAP analysis techniques to solve this problem,. The proposed method includes data preprocessing of disease information extracted from the halibut disease questionnaire by applying the SHAP analysis technique and evaluating a machine learning model using AutoML. Through this, the performance of the input parameters of AutoML is evaluated and the optimal input parameter combination is derived. In this study, the proposed method is expected to be able to maintain the existing performance while reducing the number of input parameters required, which will contribute to enhancing the efficiency and practicality of text-based Paralichthys olivaceus disease classification.

• The Journal of Bigdata
• /
• v.5 no.2
• /
• pp.53-67
• /
• 2020

This study employees a supervised learning prediction model to detect nonconformity in advance of processed food manufacturing and processing businesses. The study was conducted according to the standard procedure of machine learning, such as definition of objective function, data preprocessing and feature engineering and model selection and evaluation. The dependent variable was set as the number of supervised inspection detections over the past five years from 2014 to 2018, and the objective function was to maximize the probability of detecting the nonconforming companies. The data was preprocessed by reflecting not only basic attributes such as revenues, operating duration, number of employees, but also the inspections track records and extraneous climate data. After applying the feature variable extraction method, the machine learning algorithm was applied to the data by deriving the company's risk, item risk, environmental risk, and past violation history as feature variables that affect the determination of nonconformity. The f1-score of the decision tree, one of ensemble models, was much higher than those of other models. Based on the results of this study, it is expected that the official food control for food safety management will be enhanced and geared into the data-evidence based management as well as scientific administrative system.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.441-444
• /
• 2016

Peace on the Korean Peninsula is threatened by physical aggressions and cyber terrors such as nuclear tests, missile launchings, senior government officials' smart phone hackings and DDos attacks to banking systems. Cyber attacks such as vulnerability for the hackings, malware distributions are generally defended by passive defense through the detecting signs of first invasion and attack, data analysis, adding library and updating vaccine programs. In this paper the concept of security program based on Google TensorFlow machine learning ability to perform adding libraries and solving security vulnerabilities by itself is researched and proposed.

• Journal of the Korea Convergence Society
• /
• v.12 no.6
• /
• pp.9-16
• /
• 2021

In the past, there have been various studies on predicting the stock market by machine learning techniques using stock price data and financial big data. As stock index ETFs that can be traded through HTS and MTS are created, research on predicting stock indices has recently attracted attention. In this paper, machine learning models for KOSPI's up and down predictions are implemented separately. These models are optimized through a grid search of their control parameters. In addition, a hybrid machine learning model that combines individual models is proposed to improve the precision and increase the ETF trading return. The performance of the predictiion models is evaluated by the accuracy and the precision that determines the ETF trading return. The accuracy and precision of the hybrid up prediction model are 72.1 % and 63.8 %, and those of the down prediction model are 79.8% and 64.3%. The precision of the hybrid down prediction model is improved by at least 14.3 % and at most 20.5 %. The hybrid up and down prediction models show an ETF trading return of 10.49%, and 25.91%, respectively. Trading inverse×2 and leverage ETF can increase the return by 1.5 to 2 times. Further research on a down prediction machine learning model is expected to increase the rate of return.

• Journal of Korea Entertainment Industry Association
• /
• v.15 no.4
• /
• pp.349-357
• /
• 2021

Recently, drones are rapidly becoming common and expanding. There is a great need for diversity in whether drone flight data can be used as entertainment technology analysis data. In particular, it is necessary to check whether it is possible to analyze and utilize the flight and operation process of entertainment drones, which are developing through autonomous and intelligent methods, through data analysis and machine learning. In this paper, it was confirmed whether it can be used as a machine learning technology by using FC data in the evaluation of drones for entertainment. As a result, FC data from DJI and Parrot such as Mavic2 and Anafi were unable to analyze machine learning for entertainment. It is because data is collected at intervals of 0.1 second or more, so that it is impossible to find correlation with other data with GCS. On the other hand, it was found that machine learning technologies can be applied in the case of Fixhawk, which used an ARM processor and operates with the Nuttx OS. In the future, it is necessary to develop technologies capable of analyzing the characteristics of entertainment by dividing fixed-wing and rotary-wing flight information. For this, a model shoud be developed, and systematic big data collection and research should be conducted.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.05a
• /
• pp.547-550
• /
• 2020

노인인구의 급증에 따라 노인 건강에 대한 관심이 증가하였고 노인 낙상을 발견하는 방법에 대한 관심도 함께 대두되기 시작하였다. 낙상 사고의 경우 낙상을 일으킨 원인보다 낙상이 제때 감지되지 않아 발생하는 이후의 상황이 더욱 심각한 결과를 초래한다. 따라서 낙상이 발생했을 때, 바로 낙상을 감지할 수 있는 시스템 구축이 필요하다. 다양한 낙상 검출을 위한 방법이 존재하지만 그 중 착용이 쉽고 원격지에서 관찰 및 관리가 가능한 웨어러블(Wearable) 기기의 센서 데이터를 사용한 낙상 검출을 진행하였다. 본 논문에서는 머신 러닝 모델들을 사용해서 낙상 검출 성능 비교 및 적절한 모델을 제안한다. 기계 학습 기반의 모델인 결정 트리(Decision Tree), 랜덤 포래스트(Random Forest), SVM(Support Vector Machine)을 사용하여 실제 측정된 데이터에 낙상 검출 학습 능력을 정량화하였다. 또한, 모델의 입력 값에 적용한 데이터 분할, 전처리 및 특징 추출 방법을 통해서 효율적인 낙상 검출을 위한 기계학습 관점에서의 타당성을 판단하고자 한다.

• The Journal of Society for e-Business Studies
• /
• v.24 no.3
• /
• pp.99-110
• /
• 2019

As the 4th industrial revolution progressing, manufacturers are trying to apply intelligent information technologies such as IoT(internet of things) and machine learning. In the semiconductor/LCD/tire manufacturing process, schedule plan that minimizes setup change and due date violation is very important in order to ensure efficient production. Therefore, in this paper, we suggest the deep learning based scheduling generation model minimizes setup change and due date violation in parallel machines. The proposed model learns patterns of minimizing setup change and due date violation depending on considered order using the amount of historical data. Therefore, the experiment results using three dataset depending on levels of the order list, the proposed model outperforms compared to priority rules.

• Journal of the Korea Convergence Society
• /
• v.10 no.11
• /
• pp.15-21
• /
• 2019

The fourth industrial revolution is noted. It is a smarter factory. At present, research on CNC (Computerized Numeric Controller) is actively underway in the manufacturing field. Domestic CNC equipment, acoustic sensors, vibration sensors, etc. This study can improve efficiency through CNC. Collect various data such as X-axis, Y-axis, Z-axis force, moving speed. Data exploration of the characteristics of the collected data. You can use your data as Random Forest (RF), Extreme Gradient Boost (XGB), and Support Vector Machine (SVM). The result of this study is CNC equipment.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.10a
• /
• pp.323-326
• /
• 2016

웹 서비스를 기반으로 이루어진 MOOC(Massive Open Online Course)는 대규모 학습자에게 공개된 온라인 교육이다. MOOC는 교수와 학습자 사이 커뮤니티를 통해 상호 참여적으로 수업을 진행한다. 그러나 무료로 강의를 들을 수 있고 성적을 내지 않기 때문에 학습자들에게 큰 동기 부여가 되지 않아 등록하는 학습자는 많지만 수료하는 학습자는 현저히 적게 나타났다. 본 논문은 이러한 문제 해결 방안 마련을 위해 KDD Cup 2015에서 제공한 MOOC 데이터를 통해 중도 포기와 관련된 변수들을 선정하였으며, Decision Tree, KNN, Logistic Regression, Naive Bayesian, SVM, Neural Network인 6가지 머신 러닝 알고리즘을 통해 데이터 예측의 정확률을 확인하였다. 그 결과 Naive Bayesian이 89.3%로 가장 높은 정확률을 보였다. 본 연구를 통해 중도포기를 정확히 예측하며, 향후 학습자들에게 특정 동기부여의 효과로 학습을 수료하는 결과를 기대할 수 있다.