• 실천공학교육논문지
• /
• 제8권2호
• /
• pp.103-109
• /
• 2016

철도 차량의 정상적 운행을 위한 정비 작업이 안전하게 이루어지기 위해서는 실제 열차 정비 환경을 직접 겪어 보며 경험을 쌓고 실무능력을 키워나가야 하지만 정비 절차에 따르는 운영상의 문제로 실제 정비를 경험하는 정비교육훈련은 어려운 상황이다. 그렇기 때문에 실제와 최대한 유사한 환경에서 체험하는 시뮬레이션을 열차 정비 교육에 적용한다면 안전한 상황에서 실제 정비 업무에 대한 지식과 경험을 쌓을 수 있고, 운영상의 교육훈련비용도 절감할 수 있다. 현재 국내와 해외에서 운용되고 있는 철도 분야의 시뮬레이션 프로그램의 경우 열차운행 위주의 교육훈련으로 설계 되어 있고, 정비관련 및 유지보수 내용에 대한 묘사는 부족한 상황이다. 본 연구에서는 열차 정비의 교육효과를 위해 교육공학이론 중 내용요소전시 이론, 상황학습 이론, 문제 중심 학습이론을 고찰하는 선행연구를 통해 열차 정비 교육 시뮬레이션을 설계한다.

• 비파괴검사학회지
• /
• 제18권1호
• /
• pp.27-32
• /
• 1998

비파괴검사를 이해하고 습득하기 위해 필수적인 실습 위주의 교육 환경을 대체할 수 있는 수단으로, 가상적인 실습 환경을 제공하는 지능형 교육 시스템을 설계하고, 이를 구현하였다. 용접부 및 다양한 제품을 검사하는데 필수적인 비파괴검사는 그 전문기술을 이해하기 위해 다양한 현장 경험을 필요로 할 뿐만 아니라, 기술지식의 지속적인 유지를 위해 반복적인 교육과 훈련을 필요로 한다. 이러한 문제를 해결하기 위해 개인용 컴퓨터를 이용하여 개별학습이 가능한 지능형 교육 시스템을 개발하였으며, 가상 실습 환경의 구축과 개별학습을 효율적으로 지원하기 위해 학습 결과를 자기진단 할 수 있는 평가 시스템의 연구가 필요하다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2005년도 추계종합학술대회
• /
• pp.1157-1160
• /
• 2005

The denoising and reconstruction of color images are increasingly studied in the field of computer vision and image processing. Especially, the denoising and reconstruction of color face images are more difficult than those of natural images because of the structural characteristics of human faces as well as the subtleties of color interactions. In this paper, we propose a denoising method based on PCA reconstruction for removing complex color noises on human faces, which is not easy to remove by using vectorial color filters. The proposed method is composed of the following five steps; training of canonical eigenface space using PCA, automatic extracting of face features using active appearance model, relighing of reconstructed color image using bilateral filter, extraction of noise regions using the variance of training data, and reconstruction using partial information of input images (except the noise regions) and blending of the reconstructed image with the original image. Experimental results show that the proposed denosing method efficiently removes complex color noises on input face images.

• Journal of Information Processing Systems
• /
• 제18권5호
• /
• pp.650-664
• /
• 2022

Mobile applications can be easily downloaded and installed via markets. However, malware and malicious applications containing unwanted advertisements exist in these application markets. Therefore, smartphone users install applications with reference to the application review to avoid such malicious applications. An application review typically comprises contents for evaluation; however, a false review with a specific purpose can be included. Such false reviews are known as fake reviews, and they can be generated using artificial intelligence (AI)-based text-generating models. Recently, AI-based text-generating models have been developed rapidly and demonstrate high-quality generated texts. Herein, we analyze the features of fake reviews generated from Generative Pre-Training-2 (GPT-2), an AI-based text-generating model and create a model to detect those fake reviews. First, we collect a real human-written application review from Kaggle. Subsequently, we identify features of the fake review using natural language processing and statistical analysis. Next, we generate fake review detection models using five types of machine-learning models trained using identified features. In terms of the performances of the fake review detection models, we achieved average F1-scores of 0.738, 0.723, and 0.730 for the fake review, real review, and overall classifications, respectively.

• 대한토목학회논문집
• /
• 제39권5호
• /
• pp.631-636
• /
• 2019

최근 많은 연구자들이 대규모 현장에 투입된 건설자원의 유형과 위치를 자동 파악하는 영상분석기술을 활발히 개발하고 있다. 하지만 기존의 방법들은 인식하고자 하는 건설 물체(작업자, 중장비, 자재 등)를 학습용 이미지 데이터에 표시하는 Labeling 작업을 요구하고 이에 불필요한 시간과 노력이 낭비된다는 한계가 있다. 이러한 한계를 보완하기 위해서 본 연구는 액티브 러닝을 활용한 영상기반 건설현장 물체 자동 인식 프레임 워크를 제안함을 목표로 한다. 개발 프레임워크 검증을 목적으로 건설분야 Benchmark 데이터셋을 이용하여 실제 실험을 진행하였다. 그 결과, 액티브 러닝을 통해 학습한 모델은 다양한 특성을 지닌 건설물체를 성공적으로 인식할 수 있었고, 기존의 학습 DB 구축 방식과 비교할 때 더 적은 데이터 수와 반복학습 횟수로도 높은 성능을 가지는 영상분석모델을 개발할 수 있었다. 결과적으로 기존에 요구되던 학습 DB 구축을 위한 Labeling 작업을 줄일 뿐만 아니라 총 시간과 비용을 최소화할 수 있다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제6권10호
• /
• pp.2650-2662
• /
• 2012

Due to the semantic gap issue, the performance of automatic image annotation is still far from satisfactory. Active learning approaches provide a possible solution to cope with this problem by selecting most effective samples to ask users to label for training. One of the key research points in active learning is how to select the most effective samples. In this paper, we propose a novel active learning approach based on sparse graph. Comparing with the existing active learning approaches, the proposed method selects the samples based on two criteria: uncertainty and representativeness. The representativeness indicates the contribution of a sample's label propagating to the other samples, while the existing approaches did not take the representativeness into consideration. Extensive experiments show that bringing the representativeness criterion into the sample selection process can significantly improve the active learning effectiveness.

• International Journal of Control, Automation, and Systems
• /
• 제3권spc2호
• /
• pp.302-307
• /
• 2005

A novel neuro controller based simple neuro-structure with modified error function is introduced in this paper. This controller consists of two independent controllers, known as the voltage regulator and the angular controller. The voltage regulator is used to modify terminal voltage for the purpose of tracking a reference voltage. The angular controller is utilized to guarantee the stability of the system. In this structure each neuron uses a linear hard limit activation function that depends on the controlled variable and its derivatives. There is no need for parameter identification or any off-line training data. Two proposed controllers are merged by a smooth switch to build a complete controller. The effectiveness of the proposed novel control action is demonstrated through some computer simulations on a Single-Machine Infinite-Bus (SMIB) power system.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 하계종합학술대회 논문집
• /
• pp.452-455
• /
• 1999

We introduce an evolutionary approach to on-line learning for mobile robot control using reconfigurable hardware. We use genetic programming as an evolutionary engine. Control programs are encoded in tree structure. Genetic operators, such as node mutation, adapt the program trees based on a set of training cases. This paper discusses the advantages and constraints of the evolvable hardware approach to robot learning and describes a FPGA implementation of the presented genetic programming method.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2007년도 춘계종합학술대회
• /
• pp.153-156
• /
• 2007

In this paper, we propose a fast face detection approach using PCA and SVM. In our detection system, first we filter the face potential area using statistical feature which is generated by analyzing local histogram distribution. And then, we use SVM classifier to detect whether there are faces present in the test image. Support Vector Machine (SVM) has great performance in classification task. PCA is used for dimension reduction of sample data. After PCA transform, the feature vectors, which are used for training SVM classifier, are generated. Our tests in this paper are based on CMU face database.

• 전자공학회논문지B
• /
• 제33B권9호
• /
• pp.88-96
• /
• 1996

Computer vision-based gesture recognition systems consist of image segmentation, object tracking and decision. However, it is difficult to segment an object from image for gesture in computer systems because of vaious illuminations and backgrounds. In this paper, we describe a method to learn features for segmentation, which improves the performance of computer vision-based hand-gesture recognition systems. Systems interact with a user to acquire exact training data and segment information according to a predefined plan. System provides some models to the user, takes pictures of the user's response and then analyzes the pictures with models and a prior knowledge. The system sends messages to the user and operates learning module to extract information with the analyzed result.