• International Journal of Contents
• /
• 제14권4호
• /
• pp.24-29
• /
• 2018

EEG-based brain-computer interfaces has focused on explicitly expressed intentions to assist physically impaired patients. For EEG-based-computer interfaces to function effectively, it should be able to understand users' implicit information. Since it is hard to gather EEG signals of human brains, we do not have enough training data which are essential for proper classification performance of implicit intention. In this paper, we improve the subject independent classification of implicit intention through the generation of additional training data. In the first stage, we perform the PCA (principal component analysis) of training data in a bid to remove redundant components in the components within the input data. After the dimension reduction by PCA, we train ICA (independent component analysis) network whose outputs are statistically independent. We can get additional training data by adding Gaussian noises to ICA outputs and projecting them to input data domain. Through simulations with EEG data provided by CNSL, KAIST, we improve the classification performance from 65.05% to 66.69% with Gamma components. The proposed sample generation method can be applied to any machine learning problem with fewer samples.

• 한국군사과학기술학회지
• /
• 제26권5호
• /
• pp.392-399
• /
• 2023

This research paper investigates the effectiveness of using computer graphics(CG) based synthetic data for deep learning in military vehicle detection. In particular, we explore the use of synthetic image generation techniques to train deep neural networks for object detection tasks. Our approach involves the generation of a large dataset of synthetic images of military vehicles, which is then used to train a deep learning model. The resulting model is then evaluated on real-world images to measure its effectiveness. Our experimental results show that synthetic training data alone can achieve effective results in object detection. Our findings demonstrate the potential of CG-based synthetic data for deep learning and suggest its value as a tool for training models in a variety of applications, including military vehicle detection.

• The Journal of Asian Finance, Economics and Business
• /
• 제7권10호
• /
• pp.443-450
• /
• 2020

This study aims to add insight into the effectiveness of e-training, e-leadership, work-life balance, and work motivation on millennial generation employees' performance in today's work life amid the outbreak of the COVID-19 pandemic that requires to work more online. Unlike previous generations, millennials are technology-literate, intent on succeeding quickly, give up easily, and seek instantaneous gratification. The population in this study are millennial generation employees at one of Honda motorcycle dealers in Jakarta, Indonesia. The number of samples collected was 200. The sampling technique used is the side probability method, with proportional random sampling technique. The research method used is an associative quantitative approach through survey methods and Structural Equation Modeling. Data were collected through questionnaires distributed to millennial generation employees, with results then processed through the Lisrel 8.5 program. The results of this study show, first, that e-training, e-leadership, and work-life balance have positive effect on work motivation. Second, e-training, e-leadership, work-life balance, and work motivation have positive effect on employees' performance. The findings indicate that companies must pay attention to the factors of e-training, e-leadership, and work-life balance to keep employees motivated and to maintain optimal employee performance, especially during the COVID-19 pandemic through working online.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 춘계학술대회
• /
• pp.458-459
• /
• 2021

최근, 실내 위치 기반 서비스에서 정확한 서비스를 위해 Wi-Fi 핑거프린트 기반의 딥러닝 기술을 이용한 연구가 이루어지고 있다. 딥러닝 모델 중에서 과거의 정보를 기억할 수 있는 RNN 모델은 실내측위에서 연속된 움직임을 기억할 수 있어 측위 오차를 줄일 수 있다. 이때 학습 데이터로서 연속적인 순차 데이터를 필요로 한다. 그러나 일반적으로 Wi-Fi 핑거프린트 데이터의 경우 특정 위치에 대한 신호들만으로 관리되기 때문에 RNN 모델의 학습데이터로 사용이 부적절하다. 본 논문은 RNN 모델의 순차적인 입력 데이터의 생성을 위해 클러스터링을 통한 영역 데이터로 확장된 Wi-Fi 핑거프린트 데이터 기반 이동 경로의 예측을 통한 경로 생성 방법에 대해 제안한다.

• 융합보안논문지
• /
• 제20권4호
• /
• pp.71-80
• /
• 2020

사이버전 훈련 시스템에 현실감 있는 트래픽을 제공하기 위해서는 사전에 트래픽 유통계획 작성과 정상/위협 데이터셋을 이용한 훈련데이터셋 생성이 필요하다. 본 논문은 사이버전 훈련 시스템에 실제 환경과 같은 배경 트래픽을 제공하기 위한 트래픽 유통계획 저작과 훈련데이터셋을 생성하는 방법의 설계와 구현 결과를 제시한다. 트래픽 유통계획은 트래픽을 유통할 훈련 환경의 네트워크 토폴로지와 실제 및 모의환경에서 수집한 트래픽 속성 정보를 이용하여 저작하는 방법을 제안한다. 트래픽 유통계획에 따라 훈련데이터셋을 생성하는 방법은 단위트래픽을 이용하는 방법과 프로토콜의 비율을 이용하는 혼합트래픽 양상 방법을 제안한다. 구현한 도구를 이용하여 트래픽 유통계획을 저작하고, 유통계획에 따른 훈련데이터셋 생성결과를 확인하였다.

• ETRI Journal
• /
• 제44권2호
• /
• pp.327-338
• /
• 2022

Classification models for human action recognition require robust features and large training sets for good generalization. However, data augmentation methods are employed for imbalanced training sets to achieve higher accuracy. These samples generated using data augmentation only reflect existing samples within the training set, their feature representations are less diverse and hence, contribute to less precise classification. This paper presents new data augmentation and action representation approaches to grow training sets. The proposed approach is based on two fundamental concepts: virtual video generation for augmentation and representation of the action videos through robust features. Virtual videos are generated from the motion history templates of action videos, which are convolved using a convolutional neural network, to generate deep features. Furthermore, by observing an objective function of the genetic algorithm, the spatiotemporal features of different samples are combined, to generate the representations of the virtual videos and then classified through an extreme learning machine classifier on MuHAVi-Uncut, iXMAS, and IAVID-1 datasets.

• 한국인지과학회:학술대회논문집
• /
• 한국인지과학회 2010년도 춘계학술대회
• /
• pp.60-65
• /
• 2010

Language learning involves linguistic environments around the learner. So the variation in training input to which the learner is exposed has been linked to their language learning. We explore how linguistic experiences can cause differences in learning linguistic structural features, as investigate in a probabilistic graphical model. We manipulate the amounts of training input, composed of natural linguistic data from animation videos for children, from holistic (one-word expression) to compositional (two- to six-word one) gradually. The recognition and generation of sentences are a "probabilistic" constraint satisfaction process which is based on massively parallel DNA chemistry. Random sentence generation tasks succeed when networks begin with limited sentential lengths and vocabulary sizes and gradually expand with larger ones, like children's cognitive development in learning. This model supports the suggestion that variations in early linguistic environments with developmental steps may be useful for facilitating language acquisition.

• 한국가시화정보학회지
• /
• 제21권1호
• /
• pp.119-126
• /
• 2023

Acquiring experimental data for PIV verification or machine learning training data is resource-demanding, leading to an increasing interest in synthetic particle images as simulation data. Conventional synthetic particle image generation algorithms do not follow physical laws, and the use of CFD is time-consuming and requires computing resources. In this study, we propose a new method for synthetic particle image generation, based on a Physics-Informed Neural Networks(PINN). The PINN is utilized to infer the flow fields, enabling the generation of synthetic particle images that follow physical laws with reduced computation time and have no constraints on spatial resolution compared to CFD. The proposed method is expected to contribute to the verification of PIV algorithms.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 춘계학술대회
• /
• pp.456-457
• /
• 2021

최근, 실내 위치 기반 서비스를 보다 정확하게 제공하기 위해서 Wi-Fi 핑거프린트와 딥러닝을 이용한 기술이 연구되고 있다. 딥러닝 모델 중에서 과거의 정보를 기억할 수 있는 RNN 모델은 실내측위에서 연속된 움직임을 기억할 수 있어 측위 오차를 줄일 수 있다. 실내 측위에서 RNN 모델을 사용하는 경우 수집된 학습 데이터가 연속적인 순차 데이터이어야 한다. 그러나 특정 위치 정보를 판단하기 위해 수집된 Wi-Fi 핑거프린트 데이터는 특정 위치에 대한 RSSI만 기록되었기 때문에 RNN 모델의 학습 데이터로 사용이 불가능하다. 본 논문은 Wi-Fi 핑거프린트 데이터를 기반으로 RNN 모델의 순차적인 입력 데이터의 생성을 위한 영역 클러스터링 방법에 대해 제안한다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2003년도 하계학술대회 논문집 B
• /
• pp.1392-1394
• /
• 2003

This paper presents the actual test data of 3 phase, 9 pole, 3.6 [kw] synchronized wind-power generator controlled by hinged vane system and the possibilities of the small mount wind-power generations at the south-east coast of Ul-san. It also shows the data of the wind-velocity acquired by wind-direction sensor, calculation and analysis of the estimated electrical generation power, energy storage systems, and the efficient usages of the wind-power system.