• 한국지능시스템학회논문지
• /
• 제15권4호
• /
• pp.505-510
• /
• 2005

제어 입력 선택 문제에 있어서 확률적 전략을 활용하는 RPO(randomized policy optimizer) 기법은 최근에 개발된 강화학습 기법으로써, 많은 적용 사례를 통해서 그 가능성이 입증되고 있다 본 논문에서는, 수정된 RPO 알고리즘을 제안하는데, 이 수정된 알고리즘의 크리틱 네트워크 부분은 RLS(recursive least square) 기법을 통하여 갱신된다. 수정된 RPO 기법의 효율성을 확인하기 위해 Kimura에 의해서 연구된 로봇에 적용하여 매우 우수한 성능을 관찰하였다. 또한, 매트랩 애니메이션 프로그램의 개발을 통해서, 로봇의 이동이 시간에 따라 가속되는 학습 알고리즘의 효과를 시각적으로 확인 할 수 있었다.

• 통합자연과학논문집
• /
• 제11권4호
• /
• pp.167-183
• /
• 2018

Electroencephalogram (EEG) recording provides a new way to support human-machine communication. It gives us an opportunity to analyze the neuro-dynamics of human cognition. Machine learning is a powerful for the EEG classification. In addition, machine learning can compensate for high variability of EEG when analyzing data in real time. However, the optimal EEG electrode location must be prioritized in order to extract the most relevant features from brain wave data. In this paper, we propose an intelligent system model for the extraction of EEG data by training the optimal electrode location of EEG in a specific problem. The proposed system is basically a fuzzy system and uses a neural network structurally. The fuzzy clustering method is used to determine the optimal number of fuzzy rules using the features extracted from the EEG data. The parameters and weight values found in the process of determining the number of rules determined here must be tuned for optimization in the learning process. Genetic algorithms are used to obtain optimized parameters. We present useful results by using optimal rule numbers and non - symmetric membership function using EEG data for four movements with the right arm through various experiments.

• 인터넷정보학회논문지
• /
• 제23권2호
• /
• pp.45-52
• /
• 2022

With the development of artificial intelligence analysis methods, especially machine learning, various fields are widely expanding their application ranges. However, in the case of classical music, there still remain some difficulties in applying machine learning techniques. Genre classification or music recommendation systems generated by deep learning algorithms are actively used in general music, but not in classical music. In this paper, we attempted to classify opera among classical music. To this end, an experiment was conducted to determine which criteria are most suitable among, composer, period of composition, and emotional atmosphere, which are the basic features of music. To generate emotional labels, we adopted zero-shot classification with four basic emotions, 'happiness', 'sadness', 'anger', and 'fear.' After embedding the opera libretto with the doc2vec processing model, the optimal number of clusters is computed based on the result of the elbow method. Decided four centroids are then adopted in k-means clustering to classify unsupervised libretto datasets. We were able to get optimized clustering based on the result of adjusted rand index scores. With these results, we compared them with notated variables of music. As a result, it was confirmed that the four clusterings calculated by machine after training were most similar to the grouping result by period. Additionally, we were able to verify that the emotional similarity between composer and period did not appear significantly. At the end of the study, by knowing the period is the right criteria, we hope that it makes easier for music listeners to find music that suits their tastes.

• 한국인공지능학회지
• /
• 제10권1호
• /
• pp.21-25
• /
• 2022

Korea has relatively less crime than other countries. However, the crime rate is steadily increasing. Many people think the crime rate is decreasing, but the crime arrest rate has increased. The goal is to check the relationship between CCTV and the crime rate as a way to lower the crime rate, and to identify the correlation between areas without CCTV and areas without CCTV. If you see a crime that can happen at any time, I think you should use a random forest algorithm. We also plan to use machine learning random forest algorithms to reduce the risk of overfitting, reduce the required training time, and verify high-level accuracy. The goal is to identify the relationship between CCTV and crime occurrence by creating a crime prevention algorithm using machine learning random forest techniques. Assuming that no crime occurs without CCTV, it compares the crime rate between the areas where the most crimes occur and the areas where there are no crimes, and predicts areas where there are many crimes. The impact of CCTV on crime prevention and arrest can be interpreted as a comprehensive effect in part, and the purpose isto identify areas and frequency of frequent crimes by comparing the time and time without CCTV.

• International Journal of Internet, Broadcasting and Communication
• /
• 제15권1호
• /
• pp.85-96
• /
• 2023

The number of traffic accidents caused by wet or icy road surface conditions is on the rise every year. Car crashes in such bad road conditions can increase fatalities and serious injuries. Historical data (from the year 2016 to the year 2020) on weather-related traffic accidents show that the fatality rates are fairly high in Korea. This requires accurate prediction and identification of hazardous road conditions. In this study, a forecasting model is developed to predict the chances of traffic accidents that can occur on roads affected by weather and road surface conditions. Multiple deep learning algorithms taking into account AlexNet and 2D-CNN are employed. Data on orthophoto images, automatic weather systems, automated synoptic observing systems, and road surfaces are used for training and testing purposes. The orthophotos images are pre-processed before using them as input data for the modeling process. The procedure involves image segmentation techniques as well as the Z-Curve index. Results indicate that there is an acceptable performance of prediction such as 65% for dry, 46% for moist, and 33% for wet road conditions. The overall accuracy of the model is 53%. The findings of the study may contribute to developing comprehensive measures for enhancing road safety.

• 건축역사연구
• /
• 제31권1호
• /
• pp.41-50
• /
• 2022

Traditional wooden buildings deform over time and are vulnerable to fire or earthquakes. Therefore, traditional wooden buildings require continuous management and repair, and securing architectural drawings is essential for repair and restoration. Unlike modernized CAD drawings, traditional wooden building drawings scan and store hand-drawn drawings, and in this process, many noise is included due to damage to the drawing itself. These drawings are digitized, but their utilization is poor due to noise. Difficulties in systematic management of traditional wooden buildings are increasing. Noise removal by existing algorithms has limited drawings that can be applied according to noise characteristics and the performance is not uniform. This study presents deep artificial neural network based noised reduction for architectural drawings. Front/side elevation drawings, floor plans, detail drawings of Korean wooden treasure buildings were considered. First, the noise properties of the architectural drawings were learned with both a cycle generative model and heuristic image fusion methods. Consequently, a noise reduction network was trained through supervised learning using training sets prepared using the noise models. The proposed method provided effective removal of noise without deteriorating fine lines in the architectural drawings and it showed good performance for various noise types.

• Nuclear Engineering and Technology
• /
• 제55권5호
• /
• pp.1708-1717
• /
• 2023

The grade analysis of lead-zinc ore is the basis for the optimal development and utilization of deposits. In this study, a method combining Prompt Gamma Neutron Activation Analysis (PGNAA) technology and machine learning is proposed for lead-zinc mine borehole logging, which can identify lead-zinc ores of different grades and gangue in the formation, providing real-time grade information qualitatively and semi-quantitatively. Firstly, Monte Carlo simulation is used to obtain a gamma-ray spectrum data set for training and testing machine learning classification algorithms. These spectra are broadened, normalized and separated into inelastic scattering and capture spectra, and then used to fit different classifier models. When the comprehensive grade boundary of high- and low-grade ores is set to 5%, the evaluation metrics calculated by the 5-fold cross-validation show that the SVM (Support Vector Machine), KNN (K-Nearest Neighbor), GNB (Gaussian Naive Bayes) and RF (Random Forest) models can effectively distinguish lead-zinc ore from gangue. At the same time, the GNB model has achieved the optimal accuracy of 91.45% when identifying high- and low-grade ores, and the F₁ score for both types of ores is greater than 0.9.

• Geomechanics and Engineering
• /
• 제37권3호
• /
• pp.253-262
• /
• 2024

Dynamic properties are pivotal in soil analysis, yet their experimental determination is hampered by complex methodologies and the need for costly equipment. This study aims to predict dynamic soil properties using static properties that are relatively easier to obtain, employing machine learning techniques. The static properties considered include soil cohesion, friction angle, water content, specific gravity, and compressional strength. In contrast, the dynamic properties of interest are the velocities of compressional and shear waves. Data for this study are sourced from 26 boreholes, as detailed in a geotechnical investigation report database, comprising a total of 130 data points. An importance analysis, grounded in the random forest algorithm, is conducted to evaluate the significance of each dynamic property. This analysis informs the prediction of dynamic properties, prioritizing those static properties identified as most influential. The efficacy of these predictions is quantified using the coefficient of determination, which indicated exceptionally high reliability, with values reaching 0.99 in both training and testing phases when all input properties are considered. The conventional method is used for predicting dynamic properties through Standard Penetration Test (SPT) and compared the outcomes with this technique. The error ratio has decreased by approximately 0.95, thereby validating its reliability. This research marks a significant advancement in the indirect estimation of the relationship between static and dynamic soil properties through the application of machine learning techniques.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제33권12호
• /
• pp.1052-1061
• /
• 2006

본 논문에서는 베이지안 네트워크를 기반으로 생성하고 평가한 가상예제를 활용하여 범주 속성 데이타에 대한 분류 성능을 향상시키는 방안을 제안한다. 가상예제를 활용하는 종래의 연구들은 주로 수치 속성 데이타를 대상으로 하였고, 대상 도메인에 특화된 지식을 활용하여 특정 학습 알고리즘의 성능을 향상시키는 것을 목표로 하였다. 본 연구에서는 도메인에 특화된 지식을 활용하는 대신 주어진 훈련 집합을 기반으로 만든 베이지안 네트워크로부터 범주 속성 가상예제를 생성하고, 그 예제가 네트워크의 조건부 우도를 증가시키는데 기여할 경우 유용한 것으로 선별한다. 이러한 생성 및 선별과정을 반복하여 적절한 크기의 가상예제 집합을 수집하여 사용한다. 범주 속성 데이타를 대상으로 한 실험 결과, 여러 가지 학습 모델의 성능이 향상됨을 확인하였다.

• 전기전자학회논문지
• /
• 제23권4호
• /
• pp.1302-1308
• /
• 2019

본 논문은 CNN (Convolutional Neural Network)와 2D Lidar 센서에서 획득한 위치 데이터를 이용하여 이미지를 분류하는 방법을 제시한다. Lidar 센서는 데이터 정확도, 형상 왜곡 및 광 변화에 대한 강인성 측면에서의 이점으로 인해 무인 장치에 널리 사용되어 왔다. CNN 알고리즘은 하나 이상의 컨볼루션 및 풀링 레이어로 구성되며 이미지 분류에 만족스러운 성능을 보여 왔다. 본 논문에서는 학습 방법에 따라 다른 유형의 CNN 아키텍처들인 Gradient Descent (GD) 및 Levenberg-arquardt (LM)를 구현하였다. LM 방법에는 학습 파라메터를 업데이트하는 요소 중 하나인 Hessian 행렬 근사 빈도에 따라 두 가지 유형이 있다. LM 알고리즘의 시뮬레이션 결과는 GD 알고리즘보다 이미지 데이터의 분류 성능이 우수하였다. 또한 Hessian 행렬 근사가 더 빈번한 LM 알고리즘은 다른 유형의 LM 알고리즘보다 작은 오류를 보여주었다.