• Journal of the Korea Society for Simulation
• /
• v.33 no.2
• /
• pp.27-35
• /
• 2024

We aimed to shed light on the issue of perpetuating societal disparities by analyzing the impact of inherent biases present in datasets used for training artificial intelligence models on the predictions generated by Artificial Intelligence(AI). Therefore, to examine the influence of data bias on AI models, we constructed an original dataset containing biases related to gender wage gaps and subsequently created a de-identified dataset. Additionally, by utilizing the decision tree algorithm, we compared the outputs of AI models trained on both the original and de-identified datasets, aiming to analyze how data de-identification affects the biases in the results produced by artificial intelligence models. Through this, our goal was to highlight the significant role of data de-identification not only in safeguarding individual privacy but also in addressing biases within the data.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.5
• /
• pp.471-477
• /
• 2002

Recently, lip-reading has been studied actively as an auxiliary method of automatic speech recognition(ASR) in noisy environments. However, almost of research results were obtained based on the database constructed in indoor condition. So, we dont know how developed lip-reading algorithms are robust to dynamic variation of image. Currently we have developed a lip-reading system based on image-transform based algorithm. This system recognize 22 words and this word recognizer achieves word recognition of up to 53.54%. In this paper we present how stable the lip-reading system is in environmental variance and what the main variant factors are about dropping off in word-recognition performance. For studying lip-reading robustness we consider spatial valiance (translation, rotation, scaling) and illumination variance. Two kinds of test data are used. One Is the simulated lip image database and the other is real dynamic database captured in car environment. As a result of our experiment, we show that the spatial variance is one of degradations factors of lip reading performance. But the most important factor of degradation is not the spatial variance. The illumination variances make severe reduction of recognition rates as much as 70%. In conclusion, robust lip reading algorithms against illumination variances should be developed for using lip reading as a complementary method of ASR.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.7 no.3
• /
• pp.74-81
• /
• 2008

The control system of high-precision AC power is important in traffic management lighting and beaconing of aerodromes, etc. To control AC power supply in these load characteristics, inverter systems of AC/DC/AC conversion are widely used in high-precision current control. Therefore, in this paper, a inverter system of constant current regulation using improved measuring technique of feedback current is proposed. Proposed measuring techniques improve response and precision in that it use moving average method of instantaneous RMS for measuring current sensing. Results of the computer simulation and experiment prove the effects of proposed system.

• Journal of the Korea Safety Management & Science
• /
• v.15 no.3
• /
• pp.93-103
• /
• 2013

In recently, a growing concern for the health of urban residents increased interests in a variety of outdoor activities simply be done in terms of cost and time. They are specially interested in low-impact and safe exercises around residential or working area. Walking is the one of easily doing exercise in daytime or nighttime near residential area. The sidewalks of boulevard near the residential area is the best place for exercise because of easy access and the green space with roadside trees. However, if the nighttime is not guaranteed the proper lighting condition, the possibility of exposure to crime and the threat to pedestrian safety can be increased. Because roadside trees are one of the potential obstacle for lighting condition, supplementary lightings are important to mitigate interruption for safety. To meet such a need, the purpose of this study is to propose a simulation approach which improves lighting condition on sidewalks of boulevard with variety of roadside trees. To do so, the simulation approach is applied for analyzing the interrupted condition by classified five standard types of roadside trees considering the growth of them and finding optimal layout of supplementary luminaires by lighting types. The results of this approach shows that it is useful for assessing the safety of pedestrian in nighttime.

• 전자공학회논문지 IE
• /
• v.43 no.1
• /
• pp.32-38
• /
• 2006

When induction motor moves, power quality decline of line is risen seriously because provoking voltage drop the moment to system power supply by excessive moving current as well as power-factor drop in case drive by light-load because current reaches in 6 times $\sim$ 8 times of rated current. In this paper, a modeling did an distribution system 13 bus type model and induction machine load presents in IEEE using a PSCAD/EMTDE package, and it displayed an accident conspiracy and a compensating factor of DSTATCOM through simulation show.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.11 no.10
• /
• pp.935-940
• /
• 2016

Recently, wireless power transmission system is gradually extended to technology in various fields such as lighting field, electric vehicles and smartphones wireless charging system. The largest of the two elements for high transmission efficiency of the wireless power transmission system are resonant coils and power amplifiers. In this paper, in order to build a high efficient wireless power transmission system, we introduce the resonance coil manufacturing method and high efficiency power amplifier design method that operates at 6.78MHz.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.19 no.6
• /
• pp.834-840
• /
• 2010

Photo lithography process is very important technology to fabricate highly integrated micro patterns with high precision for semiconductor and display industries. Up to now, mask type lithography process has been generally used for this purpose; however, it is not efficient for small quantity and/or frequently changing products. Therefore, in order to obtain higher productivity and lower manufacturing cost, the mask type lithography process should be replaced. In this study, a maskless lithography system using the DMD(Digital Micromirror Device) is developed, and the exposure condition and optical properties are analyzed and simulated for a single beam case. From the proposed experimental conditions, required exposure experiments were preformed, and the results were investigated. As a results, 10${\mu}m$ spots can be generated at optimal focal length.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.7
• /
• pp.117-125
• /
• 2011

In this paper, it was segmented the face color distribution using YCbCr color model, which is one of the feature-based methods, and preprocessing stage was to be insensitive to the sensitivity for light which is one of the disadvantages for the feature-based methods by the quantization. In addition, it has raised the accuracy of image synthesis with characteristics which is selected the object of the most same image as the shape of pattern using rough set. In this paper, the detection rates of the proposed face detection algorithm was confirmed to be better about 2~3% than the conventional algorithms regardless of the size and direction on the various faces by simulation.

• Journal of Satellite, Information and Communications
• /
• v.9 no.4
• /
• pp.69-72
• /
• 2014

Recently, lighting systems using audio signal of audible frequency and frequency spectrum of visible lighting are studied. And various related products are being sold and released commercially. Also demands of emotional matching algorithm and system which includes effective and methodical designs are being increased. And the importance related with this scheme has increased. In this Paper, we configures a system for digital sound source based LED color control. And we develop algorithm to control LED color for the system configuration. Also we demonstrated the usefulness of the algorithm through experiment with simulation using LED color control system. We expected to be useful in a variety of fields and applications using proposed digital music based LED color control system.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.733-735
• /
• 2018

최근의 차량 주차관리 시설, 출입통제가 필요한 장소 그리고 도로 방범카메라를 통한 단속 등 다양한 곳에서 차량 번호판 자동 인식 기술들이 활용되고 있다. 하지만 현재 사용되고 있는 LPR(License Plate Recognition) 시스템에는 많은 장비와 비용이 들어간다는 큰 단점이 존재한다. 본 논문에서는 하나의 컴퓨터와 최소의 카메라를 가지고 할 수 있는 기계학습을 통한 영상처리를 제안하려 한다. 먼저 딥러닝 프레임워크 중 하나인 YOLO(You Only Look Once) [4]를 활용하여 자동차의 번호판 부분의 영역을 검출하고 Grayscale를 통해 햇빛 또는 조명 등의 영향을 감소시켜 번호판의 특징을 보존시킨다. 전처리 작업이 끝난 후 번호판에서 숫자를 인식 하는 부분에서는 k-NN(k-Nearest Neighbor) 알고리즘을 사용하였으며 한글 문자 인식부분은 Template Matching을 이용하였다. 제안한 알고리즘을 사용하여 기존 LPR 시스템에서 획득한 차량이미지를 대상으로 시뮬레이션 한 결과 좋은 결과를 얻을 수 있어 향후 연구 방향의 시스템 확장성의 가능성을 발견할 수 있었다.