• Journal of the Korean Institute of Educational Facilities
• /
• v.20 no.3
• /
• pp.29-39
• /
• 2013

This study addresses the evaluation on the satisfaction of school illumination quality by applying SERVPERF model after extracting factors affecting school illumination quality. Three types of illumination systems (fluorescence light, general LED light and high color rendition LED light) were tested by students who have used each illumination system. Three factors such as effectiveness, esthetic sense and function were developed for evaluation. Satisfaction evaluation was performed based on applied SERVPERF model by comparing perceived levels. The differences of perceived levels of satisfaction on the illumination systems were analyzed by ANOVA. The results said respondents satisfy only the high color rendition LED light regardless of three factors. Especially, students who experienced high color rendition LED light have strong intention to recommend that illumination system to other schools. They also express their desire to use that system at home. Interestingly, there is not much satisfaction difference between fluorescence light and general LED light.

• Journal of Bio-Environment Control
• /
• v.23 no.4
• /
• pp.303-308
• /
• 2014

Reclaimed lands, expected as high-tech export horticultural complex, have unusual light environments due to sea fog. For adequate greenhouse design at reclaimed land, spatial light distributions in greenhouse should be required considering diffusive and direct lights. The objectives of this study were to analyze light environments and estimate spatial light distributions in greenhouse at reclaimed land by 3D greenhouse models. Total and diffusive lights were compared between reclaimed land and inland. For verification of the 3D greenhouse models, spatial light distributions and measured light intensities in greenhouse were compared with the estimated ones. Light environments at reclaimed land showed a higher diffusive irradiation than at inland, especially near sunrise and sunset. The estimated spatial light distributions in greenhouse showed good agreements with the measured ones. By using this method, we could estimate the average light intensity with time and spatial light distributions in greenhouse at specific outside light conditions. This result will be useful for analysis of light environments but also estimation of crop light inception in greenhouse at reclaimed land.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.3
• /
• pp.176-182
• /
• 2024

In this study, we compared and analyzed various methods of missing data handling to build a machine learning model that can effectively analyze and predict time series data with a high percentage of missing values. For this purpose, Predictive State Model Filtering (PSMF), MissForest, and Imputation By Feature Importance (IBFI) methods were applied, and their prediction performance was evaluated using LightGBM, XGBoost, and Explainable Boosting Machines (EBM) machine learning models. The results of the study showed that MissForest and IBFI performed the best among the methods for handling missing values, reflecting the nonlinear data patterns, and that XGBoost and EBM models performed better than LightGBM. This study emphasizes the importance of combining nonlinear imputation methods and machine learning models in the analysis and prediction of time series data with a high percentage of missing values, and provides a practical methodology.

• Journal of Korea Multimedia Society
• /
• v.20 no.11
• /
• pp.1729-1740
• /
• 2017

This paper describes a vision-based method that effectively recognize a traffic light. The method consists of two steps of traffic light detection and discrimination. Many related studies have used color information to detect traffic light, but color information is not robust to the varying illumination environment. This paper proposes a new method of traffic light detection based on intensity and saturation. When a traffic light is turned on, the light region usually shows values with high saturation and high intensity. However, when the light region is oversaturated, the region shows values of low saturation and high intensity. So this study proposes a method to be able to detect a traffic light under these conditions. After detecting a traffic light, it estimates the size of the body region including the traffic light and extracts the body region. The body region is compared with five models which represent specific traffic signals, then the region is discriminated as one of the five models or rejected as none of them. Experimental results show the performance of traffic light detection reporting the precision of 97.2%, the recall of 95.8%, and correct recognition rate of 94.3%. These results shows that the proposed method is effective.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.10a
• /
• pp.26-31
• /
• 2002

The recent machine tools are requested so high-quality processing and productivity increasing. Therefore, it is so necessary to develop technology fur high-speed and high-precision. This thesis touches on the development of high speed and intellectual line center. At first, the line center is necessary that strong structure, compact structure and light weight design for high-speed processing and transfer. So, it is necessary that examination of new materials and structures for light-weight and control devices for precision processing. So. it is going to make mention of the process of 1st model production for the above-mentioned based on test model production and evaluation.

• Convergence Security Journal
• /
• v.22 no.4
• /
• pp.17-24
• /
• 2022

Recently, machine learning-based cyber attack detection and classification research has been actively conducted, achieving a high level of detection accuracy. However, low-spec IoT devices and large-scale network traffic make it difficult to apply machine learning-based detection models in IoT environment. Therefore, In this paper, we propose an efficient IoT attack detection and classification method through PCA(Principal Component Analysis) and LightGBM(Light Gradient Boosting Model) using datasets collected in a MQTT(Message Queuing Telementry Transport) IoT protocol environment that is also used in the defense field. As a result of the experiment, even though the original dataset was reduced to about 15%, the performance was almost similar to that of the original. It also showed the best performance in comparative evaluation with the four dimensional reduction techniques selected in this paper.

• Journal of the korean Society of Automotive Engineers
• /
• v.12 no.5
• /
• pp.97-106
• /
• 1990

A method of weight evaluation of the load-bearing structural elements of cars is presented and the weight ratio of the analysis model is investigated. Replacing the materials of floor elements of the car into the high-strength steel, a considerable weight-reduction of the model has been obtained. The 1500cc model is selected for the present study and the stick model analysis is employed for the structural analysis. The torsional stiffness of the weight-reduced model is also evaluated and it is shown it has a reasonable rigidity. The ratio of the weight of the load-bearing structural elements to the unladen vehicle weight of cars is about 0.12for the 1500cc model and the weight-reduction of this study can be obtained around 17% of the weight of the load-bearing structural elements.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.44 no.2
• /
• pp.7-12
• /
• 2007

A SPICE-based 3-dimensional circuit model of LED(Light-Emitting Diode) was developed for the design optimization and analysis of high-brightness LEDs. An LED is represented as an array of pixel LEDs with small preassigned areas, and each of the pixel LEDs is composed of circuit networks representing the thin-film layers(n-metal, n- and p-type semiconductor layers, and p-metal), ohmic contacts, and pn-junctions. Each of the thin-film layers and contact resistances is modeled by a resistance network, and the pn-junction is modeled by a conventional pn-junction diode. It has been found that the simulation results using the model and the corresponding parameters precisely fit the measured LED characteristics.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.1
• /
• pp.83-90
• /
• 2019

LED lighting is spreading on the strength of LED lighting, and various government policies are being implemented. VLC research which is a wireless communication technology using lighting has been actively conducted, and it has been proven through many studies that a general LED light source such as a high-speed data transmitter can be used. But from now on, one of the main problems is the noise from side lights, which can be compared to the noise of radio broadcasts. So in this paper, we proposed a noise canceling model to remove the interference of ambient light by using an optical filter for a detachable VLC channel. In order to verify the proposed model, various high brightness RGB LED modules were used for comparative analysis. In addition, the applicability was verified through experiments using High Luminance LED lighting which is applied in real life.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.3
• /
• pp.173-182
• /
• 2022

In this paper, we propose a machine learning model that can prevent fraudulent transactions in advance and interpret them using the XAI approach. For the experiment, we collected a real data set of 12,258 mobile phone sales posts from Joonggonara, a major domestic online C2C resale trading platform. Characteristics of the text corresponding to the post body were extracted using Doc2vec, dimensionality was reduced through PCA, and various derived variables were created based on previous research. To mitigate the data imbalance problem in the preprocessing stage, a complex sampling method that combines oversampling and undersampling was applied. Then, various machine learning models were built to detect fraudulent postings. As a result of the analysis, LightGBM showed the best performance compared to other machine learning models. And as a result of SHAP, if the price is unreasonably low compared to the market price and if there is no indication of the transaction area, there was a high probability that it was a fraudulent post. Also, high price, no safe transaction, the more the courier transaction, and the higher the ratio of 0 in the price also led to fraud.