• International Journal of Internet, Broadcasting and Communication
• /
• 제15권3호
• /
• pp.166-175
• /
• 2023

Reinforcement learning can be applied to a wide variety of problems. However, the fundamental limitation of reinforcement learning is that it is difficult to derive an answer within a given time because the problems in the real world are too complex. Then, with the development of neural network technology, research on deep reinforcement learning that combines deep learning with reinforcement learning is receiving lots of attention. In this paper, two types of neural networks are combined with reinforcement learning and their characteristics were compared and analyzed with existing value-based reinforcement learning algorithms. Two types of neural networks are FNN and CNN, and existing reinforcement learning algorithms are SARSA and Q-learning.

• 문화기술의 융합
• /
• 제9권6호
• /
• pp.301-307
• /
• 2023

딥러닝은 심층신경망(Deep Neural Network)을 구축하고 대량의 훈련 데이터를 수집한 후, 구축된 신경망을 오랫동안 학습 시켜야 한다. 만약, 학습이 제대로 진행되지 않거나 과적합이 발생하면, 학습은 실패하게 된다. 현재까지 개발되고 있는 딥러닝 도구들을 사용할 경우, 훈련데이터 수집과 학습에 많은 시간이 소요된다. 하지만, 모바일 환경의 급격한 도래와 센서 데이터의 증가로 인해, 신경망 학습에 걸리는 시간을 획기적으로 줄일 수 있는 실시간 증강형 딥러닝 기술에 대한 요구가 급격하게 증가하고 있다. 본 연구에서는 미세먼지 센서를 장착한 아두이노 시스템을 사용하여 실시간 증강형 딥러닝 시스템을 구현 하였다. 구현된 시스템에서는 미세먼지 데이터를 5초마다 측정하고 최대 120개가 축적이 되면, 기존에 축적된 데이터와 새로이 축적된 데이터를 데이터셋으로 사용하여 학습을 수행하도록 하였다. 학습 수행을 위한 신경망은 입력층 1개, 은닉층 1개, 출력등 1개로 구성하였다. 구현된 시스템에 대한 성능을 평가하기 위해 학습 시간과 평균 제곱근 오차(root mean square error, RMSE)를 측정 하였다. 실험 결과, 평균 학습 오차는 0.04053796이었으며, 학습주기당(1 에포크) 평균 학습 시간은 3,447 초 정도의 시간이 걸렸다.

• International journal of advanced smart convergence
• /
• 제8권2호
• /
• pp.147-154
• /
• 2019

In this paper, we conducted a study that utilizes deep learning to calculate appropriate physical exercise information when basic human factors such as sex, age, height, and weight of users come in. To apply deep learning, a method was applied to calculate the amount of fat needed to calculate the amount of one repetition maximum by utilizing the structure of the basic Deep Neural Network. By applying Accuracy improvement methods such as Relu, Weight initialization, and Dropout to existing deep learning structures, we have improved Accuracy to derive a lean body weight that is closer to actual results. In addition, the results were derived by applying a formula for calculating the one repetition maximum load on upper and lower body movements for use in actual physical exercise. If studies continue, such as the way they are applied in this paper, they will be able to suggest effective physical exercise options for different conditions as well as conditions for users.

• Journal of information and communication convergence engineering
• /
• 제21권1호
• /
• pp.9-16
• /
• 2023

The natural language on social network platforms has a certain front-to-back dependency in structure, and the direct conversion of Chinese text into a vector makes the dimensionality very high, thereby resulting in the low accuracy of existing text classification methods. To this end, this study establishes a deep learning model that combines a big data ultra-deep convolutional neural network (UDCNN) and long short-term memory network (LSTM). The deep structure of UDCNN is used to extract the features of text vector classification. The LSTM stores historical information to extract the context dependency of long texts, and word embedding is introduced to convert the text into low-dimensional vectors. Experiments are conducted on the social network platforms Sogou corpus and the University HowNet Chinese corpus. The research results show that compared with CNN + rand, LSTM, and other models, the neural network deep learning hybrid model can effectively improve the accuracy of text classification.

• 한국전자통신학회논문지
• /
• 제15권1호
• /
• pp.85-92
• /
• 2020

심층학습은 많은 양의 데이터셋을 학습에 활용하여 객체 분류, 검출, 분할 등의 영상 분석에 탁월한 성능을 나타내고 있다. 본 논문에서는 데이터셋의 종류가 다양한 얼굴 표정인식 데이터셋들을 활용하여 학습 데이터셋의 특성이 심층학습 성능에 영향을 줄 수 있음을 확인하고, 각 학습 데이터셋에 적합한 심층학습 모델의 구성 요소를 설정하는 방법을 제안한다. 제안하는 방법은 심층학습 모델의 성능에 영향을 주는 구성 요소인 활성함수, 그리고 최적화 알고리즘을 유전 알고리즘을 이용하여 선정한다. CK+, MMI, KDEF 데이터셋에 대해서 널리 활용되고 있는 심층학습 모델의 각 구성 요소별 다양한 알고리즘을 적용하여 성능을 비교 분석하고, 유전 알고리즘을 적용하여 최적의 구성 요소를 선정할 수 있음을 시뮬레이션을 통하여 확인한다.

• Corrosion Science and Technology
• /
• 제18권6호
• /
• pp.253-257
• /
• 2019

A deep learning based real-time painting surface inspection algorithm is proposed herein, designed for developing an autonomous inspection drone. The painting surface inspection is usually conducted manually. However, the manual inspection has a limitation in obtaining accurate data for correct judgement on the surface because of human error and deviation of individual inspection experiences. The best method to replace manual surface inspection is the vision-based inspection method with a camera, using various image processing algorithms. Nevertheless, the visual inspection is difficult to apply to surface inspection due to diverse appearances of material, hue, and lightning effects. To overcome technical limitations, a deep learning-based pattern recognition algorithm is proposed, which is specialized for painting surface inspections. The proposed algorithm functions in real time on the embedded board mounted on an autonomous inspection drone. The inspection results data are stored in the database and used for training the deep learning algorithm to improve performance. The various experiments for pre-inspection of painting processes are performed to verify real-time performance of the proposed deep learning algorithm.

• 한국측량학회지
• /
• 제35권5호
• /
• pp.423-430
• /
• 2017

Recently, data analysis research has been carried out using the deep learning technique in various fields such as image interpretation and/or classification. Various types of algorithms are being developed for many applications. In this paper, we propose a precipitation prediction algorithm based on deep learning with high accuracy in order to take care of the possible severe damage caused by climate change. Since the geographical and seasonal characteristics of Korea are clearly distinct, the meteorological factors have repetitive patterns in a time series. Since the LSTM (Long Short-Term Memory) is a powerful algorithm for consecutive data, it was used to predict precipitation in this study. For the numerical test, we calculated the PWV (Precipitable Water Vapor) based on the tropospheric delay of the GNSS (Global Navigation Satellite System) signals, and then applied the deep learning technique to the precipitation prediction. The GNSS data was processed by scientific software with the troposphere model of Saastamoinen and the Niell mapping function. The RMSE (Root Mean Squared Error) of the precipitation prediction based on LSTM performs better than that of ANN (Artificial Neural Network). By adding GNSS-based PWV as a feature, the over-fitting that is a latent problem of deep learning was prevented considerably as discussed in this study.

• 제어로봇시스템학회논문지
• /
• 제22권10호
• /
• pp.797-802
• /
• 2016

This paper proposes a noble voice recognition method based on an adaptive MFCC and deep learning for embedded systems. To enhance the recognition ratio of the proposed voice recognizer, ambient noise mixed into the voice signal has to be eliminated. However, noise filtering processes, which may damage voice data, diminishes the recognition ratio. In this paper, a filter has been designed for the frequency range within a voice signal, and imposed weights are used to reduce data deterioration. In addition, a deep learning algorithm, which does not require a database in the recognition algorithm, has been adapted for embedded systems, which inherently require small amounts of memory. The experimental results suggest that the proposed deep learning algorithm and HMM voice recognizer, utilizing the proposed adaptive MFCC algorithm, perform better than conventional MFCC algorithms in its recognition ratio within a noisy environment.

• 한국인터넷방송통신학회논문지
• /
• 제18권4호
• /
• pp.55-60
• /
• 2018

본 논문은 전력선 통신에서 딥 러닝 기술 적용시킨 연구의 초기 결과를 보여준다. 본 논문에서는 전력선 통신의 성능을 감소시키는 원인인 잡음을 제거하기 위해 딥 러닝 기술을 적용시켜 효과적인 잡음 제거를 목표로 하고 수신 단에서 딥 러닝 모델을 추가하여 잡음을 효과적으로 제거하는 시스템을 제안한다. 딥 러닝 모델을 학습시키기 위해서는 데이터가 필요하므로 기존의 데이터들을 저장하고 있다고 가정하고 제안하는 시스템에 대해 시뮬레이션을 진행하여 부가 백색 가우시안 잡음 채널의 이론적 결과와 비트 에러률을 비교하여 제안하는 시스템 모델이 잡음을 제거하여 통신 성능을 향상시킨 것을 확인한다.

• 한국멀티미디어학회논문지
• /
• 제20권5호
• /
• pp.769-781
• /
• 2017

Deep learning networks like Convolutional Neural Networks (CNNs) show successful performances in many computer vision applications such as image classification, object detection, and so on. For implementation of deep learning networks in embedded system with limited processing power and memory, deep learning network may need to be simplified. However, simplified deep learning network cannot learn every possible scene. One realistic strategy for embedded deep learning network is to construct a simplified deep learning network model optimized for the scene images of the installation place. Then, automatic training will be necessitated for commercialization. In this paper, as an intermediate step toward automatic training under fisheye camera environments, we study more precise human localization in fisheye images, and propose an accurate human localization method, Automatic Ground-Truth Labelling Method (AGTLM). AGTLM first localizes candidate human object bounding boxes by utilizing GoogLeNet-LSTM approach, and after reassurance process by GoogLeNet-based CNN network, finally refines them more correctly and precisely(tightly) by applying saliency object detection technique. The performance improvement of the proposed human localization method, AGTLM with respect to accuracy and tightness is shown through several experiments.