• 실천공학교육논문지
• /
• 제15권1호
• /
• pp.31-38
• /
• 2023

본 논문에서는 비전공자들을 위한 기초 머신러닝 모델 학습 및 활용교육 커리큘럼을 제안하고, Orange 머신러닝 모델 학습 및 분석 도구를 활용한 교육 방법을 제안하였다. Orange는 오픈 소스기반 머신러닝 및 데이터 시각화 도구로서, 복잡한 프로그래밍 없이 시각적인 위젯을 사용하여, 데이터를 학습시켜 머신러닝 모델을 만들 수 있다. Orange는 비전공자 학부생부터 전문가 그룹까지 다양하게 사용되는 플랫폼이다. 본 논문에서는 한 학기 분량의 기초 머신러닝 모델 학습 및 활용교육 커리큘럼과 주별 실습 내용을 제시하였다. 그리고, 머신러닝 모델 학습 및 활용에 대한 교육 내용 실체를 실증하기 위해, Orange 도구를 활용하여, 분류 데이터(Categorical Data) 표본과 수치 데이터(Numerical Data) 표본으로부터 머신러닝 모델을 학습시키고, 모델을 활용하여 모집단의 결과를 예측하는 활용 사례들을 제안하였다. 마지막으로 본 커리큘럼에 대한 교육 만족도를 비전공자 대상으로 조사 및 분석하였다.

• Journal of Information Technology Applications and Management
• /
• 제9권2호
• /
• pp.1-16
• /
• 2002

Recently, neural network methods have been studied to find out more valuable information in data bases. But the supervised learning methods of neural networks have an overfitting problem, which leads to errors of target patterns. And the unsupervised learning methods can distort important information in the process of regularizing data. Thus they can't efficiently classify data, To solve the problems, this paper introduces a hybrid neural networks HACAB(Hybrid Algorithm combining a Competition learning model And BP Algorithm) combining a competition learning model and 8P algorithm. HACAB is designed for cases which there is no target patterns. HACAB makes target patterns by adopting a competition learning model and classifies input patterns using the target patterns by BP algorithm. HACAB is evaluated with random input patterns and Iris data In cases of no target patterns, HACAB can classify data more effectively than BP algorithm does.

• 전자공학회논문지CI
• /
• 제48권3호
• /
• pp.36-45
• /
• 2011

소셜러닝의 대표적 학습인 협력학습에서의 에이전트란 학습자에게 현황이든, 환경이든, 과제이든 설명해 줄 수 있거나, 보편적이고 일반적인 방법으로 독립적인 기능을 수행할 수 있는 것이다, 이를 위해서는 에이전트 사이에서의 의사소통에 관한 정보기술 표준화 방법이 요구된다. 본 연구는 협력학습에서 사용되는 각종 에이전트들의 의사소통에 관한 데이터 모델에 관한 기술을 제시한다. 따라서 이러닝 협력학습 환경을 지원하는 많은 에이전트들의 유형을 파악하고, 이 에이전트들 간의 상호 의사소통에 관한 규칙을 갖는 데이터 모델을 설계하여 그 요소들을 정의하고자 한다. 이렇게 제시된 표준화된 데이터 모델을 기반으로 하는 다중 에이전트 시스템은 여러 응용 에이전트가 독립된 프로세스로 활동할 수 있도록 정의된 통신 데이터모델에 의해 메시지 상호 교환이 가능해진다. 본 연구는 소셜러닝에서 주를 이루는 학습방법인 협력학습 중에서 다양한 에이전트를 활용하는 경우 이를 지원하는 에이전트간의 통신에 관한 의사소통 모델 응용을 통해 원활한 협력학습이 구현되도록 기여할 것으로 기대한다.

• 한국항행학회논문지
• /
• 제25권6호
• /
• pp.569-575
• /
• 2021

딥러닝은 데이터의 품질과 모델에 따라 예측 성능에 차이를 보인다. 본 연구는 발전량 예측에 가장 영향을 주는 일사량 예측을 위한 최적의 딥러닝 모델을 구축하기 위해 다양한 입력 데이터와 다중 딥러닝 모델을 사용하였다. 입력 데이터는 기상청의 기상 데이터와 천리안 기상영상을 기상청 지역의 영상을 분할하여 사용하였다, 본 연구는 기본적인 딥러닝 모델인 DNN, LSTM, CNN 모델에 대해 중간층의 깊이와 노드를 변경하여 일사량을 예측하여, 비교 평가하였다, 또한, 각 모델에서 가장 좋은 오차율을 가진 모델을 연결한 다증 딥러닝 모델을 구축하여 일사량을 예측하였다. 실험 결과로서 다중 딥러닝 모델인 모델 A의 RMSE는 0.0637이며, 모델 B의 RMSE는 0.07062이며, 모델 C의 RMSE는 0.06052로서 단일 모델보다 모델 A 그리고 모델 C의 오차율이 좋았다. 본 연구는 실험을 통해 두 개 이상의 모델을 연결한 모델이 향상된 예측률과 안정된 학습 결과를 보였다.

• 한국BIM학회 논문집
• /
• 제9권1호
• /
• pp.22-31
• /
• 2019

In this paper, we construct a prototype model for city data prediction by using time series data of floating population, and use machine learning to analyze urban data of complex structure. A correlation prediction model was constructed using three of the 10 data (total flow population, male flow population, and Monday flow population), and the result was compared with the actual data. The results of the accuracy were evaluated. The results of this study show that the predicted model of the floating population predicts the correlation between the predicted floating population and the current state of commerce. It is expected that it will help efficient and objective design in the planning stages of architecture, landscape, and urban areas such as tree environment design and layout of trails. Also, it is expected that the dynamic population prediction using multivariate time series data and collected location data will be able to perform integrated simulation with time series data of various fields.

• 한국멀티미디어학회논문지
• /
• 제24권7호
• /
• pp.868-879
• /
• 2021

PCB (Printed Circuit Board) inspection using a deep learning model requires a large amount of data and storage. When the amount of stored data increases, problems such as learning time and insufficient storage space occur. In this study, the existing object detection model is changed to a continual learning model to enable the recognition and classification of PCB components that are constantly increasing. By changing the structure of the object detection model to a knowledge distillation model, we propose a method that allows knowledge distillation of information on existing classified parts while simultaneously learning information on new components. In classification scenario, the transfer learning model result is 75.9%, and the continual learning model proposed in this study shows 90.7%.

• Journal of the Korean Data and Information Science Society
• /
• 제18권3호
• /
• pp.629-636
• /
• 2007

A kernel type semi-supervised estimate is proposed. The proposed estimate is based on the penalized least squares loss and the principle of Gaussian Random Fields Model. As a result, we can estimate the label of new unlabeled data without re-computation of the algorithm that is different from the existing transductive semi-supervised learning. Also our estimate is viewed as a general form of Gaussian Random Fields Model. We give experimental evidence suggesting that our estimate is able to use unlabeled data effectively and yields good classification.

• International Journal of Computer Science & Network Security
• /
• 제21권11호
• /
• pp.23-30
• /
• 2021

Sentiment Analysis has become very important field of research because posting of reviews is becoming a trend. Supervised, unsupervised and semi supervised machine learning methods done lot of work to mine this data. Feature engineering is complex and technical part of machine learning. Deep learning is a new trend, where this laborious work can be done automatically. Many researchers have done many works on Deep learning Convolutional Neural Network (CNN) and Long Shor Term Memory (LSTM) Neural Network. These requires high processing speed and memory. Here author suggested two models simple & bidirectional deep leaning, which can work on text data with normal processing speed. At end both models are compared and found bidirectional model is best, because simple model achieve 50% accuracy and bidirectional deep learning model achieve 99% accuracy on trained data while 78% accuracy on test data. But this is based on 10-epochs and 40-batch size. This accuracy can also be increased by making different attempts on epochs and batch size.

• 디지털산업정보학회논문지
• /
• 제19권3호
• /
• pp.233-244
• /
• 2023

Although artificial intelligence and machine learning technologies have been used in various fields, problems with personal information protection have arisen based on centralized data collection and processing. Federated learning has been proposed to solve this problem. Federated learning is a process in which clients who own data in a distributed data environment learn a model using their own data and collectively create an artificial intelligence model by centrally collecting learning results. Unlike the centralized method, Federated learning has the advantage of not having to send the client's data to the central server. In this paper, we quantitatively present the performance improvement when federated learning is applied using the building change detection learning data. As a result, it has been confirmed that the performance when federated learning was applied was about 29% higher on average than the performance when it was not applied. As a future work, we plan to propose a method that can effectively reduce the number of federated learning rounds to improve the convergence time of federated learning.

• International journal of advanced smart convergence
• /
• 제7권1호
• /
• pp.24-32
• /
• 2018

An outlier detection method using mixed prediction model has been described in this paper. The mixed prediction model consists of time-series model and regression model. The parameter estimation of the prediction model was performed using supervised learning and a genetic algorithm is adopted for a learning method. The experiments were performed in artificial and real data set. The prediction performance is compared with the existing prediction methods using artificial data. Outlier detection is conducted using the real sensor measurements in a dam. The validity of the proposed method was shown in the experiments.