• Korean Journal of Remote Sensing
• /
• v.36 no.5_4
• /
• pp.1179-1194
• /
• 2020

This study investigates the feasibility of three algorithms, K-Nearest Neighbors (K-NN), Random Forest (RF) and Neural Network (NN), for estimating the air temperature of an unobserved area where the weather station is not installed. The satellite image were obtained from Landsat-8 and MODIS Aqua/Terra acquired in 2019, and the meteorological ground weather data were from AWS/ASOS data of Korea Meteorological Administration and Korea Forest Service. In addition, in order to improve the estimation accuracy, a digital surface model, solar radiation, aspect and slope were used. The accuracy assessment of machine learning methods was performed by calculating the statistics of R² (determination coefficient) and Root Mean Square Error (RMSE) through 10-fold cross-validation and the estimated values were compared for each target area. As a result, the neural network algorithm showed the most stable result among the three algorithms with R² = 0.805 and RMSE = 0.508. The neural network algorithm was applied to each data set on Landsat imagery scene. It was possible to generate an mean air temperature map from June to September 2019 and confirmed that detailed air temperature information could be estimated. The result is expected to be utilized for national disaster safety management such as heat wave response policies and heat island mitigation research.

• Journal of Bio-Environment Control
• /
• v.7 no.4
• /
• pp.290-297
• /
• 1998

In this study an optimization of greenhouse roof shape was performed to maximize solar light transmission which is one of the most important elements in greenhouse environment. To determine roof shape that maximize the total light transmissivity, a computer model for analysing light transmissivity was composed and the Genetic Algorithms was applied for solving optimization problems. By setting composite model as objective function(fitness function), the optimum combination of design variables(roof inclination angle, width ratio) was searched using Genetic Algorithms. The optimum combination of input variables for the maximum light transmissivity at Suwon in winter was found 40 degree root angle , 0.5 width ratio, for two span greenhouses and 37 $_。 / roof angle, 0.7 width ratio, for single span greenhouses.es.

• Journal of Digital Convergence
• /
• v.20 no.4
• /
• pp.389-396
• /
• 2022

Deep Learning is based on a perceptron, and is currently being used in various fields such as image recognition, voice recognition, object detection, and drug development. Accordingly, a variety of learning algorithms have been proposed, and the number of neurons constituting a neural network varies greatly among researchers. This study analyzed the learning characteristics according to the number of neurons of the currently used SGD, momentum methods, AdaGrad, RMSProp, and Adam methods. To this end, a neural network was constructed with one input layer, three hidden layers, and one output layer. ReLU was applied to the activation function, cross entropy error (CEE) was applied to the loss function, and MNIST was used for the experimental dataset. As a result, it was concluded that the number of neurons 100-300, the algorithm Adam, and the number of learning (iteraction) 200 would be the most efficient in deep learning learning. This study will provide implications for the algorithm to be developed and the reference value of the number of neurons given new learning data in the future.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.10a
• /
• pp.71-74
• /
• 2004

이족보행로봇을 실생활에 적용하기 위해서는 비평탄지형에서의 안정적인 자율보행 및 자세 안정화는 반드시 필요한 기능이다. 본 논문에서는 계단, 경사지형, 다양한 형태의 장애물에 대처가능한 이족보행로봇의 기구설계 및 원격제어 가능한 제어시스템 구현에 대하여 설명하고, 이러한 비평탄지형에서 발에 부착된 적외선센서 및 FSR센서, 머리에 장착될 카메라를 사용한 안정된 자율보행 알고리즘을 제안하였다. 또한 발바닥에 장착된 FSR센서를 사용하여 외부에서 들어오는 외력에 대처하는 자세안정화 알고리즘도 제안하였다. 제안한 자율보행 및 자세안정화 알고리즘들은 이족보행로봇을 제작하여 다양한 환경에서 실험으로 검증하였다.

• Journal of Korea Multimedia Society
• /
• v.9 no.8
• /
• pp.1045-1053
• /
• 2006

We introduce a new method of painterly rendering. Instead of using the gradient direction of the source image to generate a brush stroke, we extract regions that can be drawn in one stroke using MHN filtering followed by identification of connected components, and make a brush stroke from each, based on an approximation to the medial axis. This method results in realistic-looking brush strokes of varying width that have an irregular directions where necessary.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.5
• /
• pp.56-62
• /
• 2008

This paper proposes the use of decision tree classification for the measuring pattern recognition from industrial Computed Radiography(CR) images used in nondestructive evaluation(NDE) of steel-tubes. It appears that NDE problems are naturally desired to have machine learning techniques identify patterns and their classification. The attributes of decision tree are taken from NDE test procedure. Geometric features, such as radiative angle, gradient and distance, are estimated from the analysis of input image data. These factors are used to make it easy and accurate to classify an input object to one of the pre-specified classes on decision tree. This algerian is to simplify the characterization of NDE results and to facilitate the determination of features. The experimental results verify the usefulness of proposed algorithm.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.31 no.5
• /
• pp.385-391
• /
• 2013

As a solution for environmental problems caused by increasing number of vehicles, it is encouraged to use a bicycle as an environment-friendly transportation method. To vitalize the bicycle usage, it is a necessary to construct bicycle roads that are safe and suitable for users. Based on the previous research results, we assume the main purposes of bicycle usages are mainly local leisure activity and school commuting. Thus, the proposed method finds the shortest link between the existing bicycle road network and bicycle usage facilities such as leisure activity places or schools over public road network. Then, we carry out the RTK DGPS survey for the candidate links, and analyze the slopes of them. When the slope of a found link is larger than a threshold, an alternative link is re-found for the safety and convenience of a bicycle user. The proposed method is applied to the real bicycle road network in Mokpo, Chunnam and the results are discussed.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.1
• /
• pp.19-25
• /
• 2011

A vehicle fuel economy is very important issue in view of fuel cost and environmental regulation. The technology development for the fuel economy improvement improved the engine, power train and many components of vehicle. So, the fuel economy is much improved, but up to now the measurement of it tests the given mode(LA-4, FTP-75, etc) within computer simulation program and engine dynamo. In this paper, to deduct the method of its improvement of real road, the test vehicle ran 213Km Youngdong real highway using 3 different algorithms in computer simulation. For this, I extracted the distance and altitude data from received GPS data and calculated the grade angle, road load and accomplished the velocity profiles according to algorithms in all 213Km distance. The vehicle runs in computer with AVL Cruise simulation program using velocity profile. I calculate the fuel economy using AVL Cruise simulation result and propose the Eco-driving method of them.

• Journal of Korean Society for Geospatial Information Science
• /
• v.21 no.3
• /
• pp.3-9
• /
• 2013

As interest in green growth picks up, the importance of bicycles which are an environment friendly means of communication has been magnified. However, bicycle routes which are the base of bicycles are designed without considering topographic elements and thus many users are experiencing inconvenience in using bicycles. The present study presents a routing technique to select optimal routes when selecting routes in commuting to school utilizing bicycles. To this end, a formula for optimum route calculation considering slope and intersections was drawn and a method to select optimum routes by applying modified Dijkstra Algorithms was studied. According to the results, the bicycle routes for commuting to school should be selected by the shortest time rather than the shortest distances to the destination, because it required reach the destination faster. Therefore when selecting the routes, it must be based on the shortest time considering waiting time due to crosswalks or crossroads and speed variations due to slopes.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.5
• /
• pp.364-371
• /
• 2016

We developed a prediction model of assistance force for the opening/closing of an automobile door depending on the condition of the parking ground. The candidates of the learning models for the operating assistance force were compared to determine the proper force according to the slope and user's force, etc. The reduced experimental model was developed to obtain learning data for the estimation model. The learning algorithm was composed to predict the assistance force to incorporate real assistance force data. Among these algorithms, an Artificial Neural Network (ANN) and Support Vector Machine(SVM) were applied and the adaptability was compared between these models. The SVM provided more adaptability for the learning process of the door assistance force prediction. This paper proposes a system for determining the assistance force to control a door motor to compensate for the deviation of required door force in the slope condition, as needed in the plane condition.