• 한국정보기술학회 영문논문지
• /
• 제9권1호
• /
• pp.127-134
• /
• 2019

In terms of deep Reinforcement Learning (RL), exploration can be worked stochastically in the action of a state space. On the other hands, exploitation can be done the proportion of well generalization behaviors. The balance of exploration and exploitation is extremely important for better results. The randomly selected action with ε-greedy for exploration has been regarded as a de facto method. There is an alternative method to add noise parameters into a neural network for richer exploration. However, it is not easy to predict or detect over-fitting with the stochastically exploration in the perturbed neural network. Moreover, the well-trained agents in RL do not necessarily prevent or detect over-fitting in the neural network. Therefore, we suggest a novel design of a deep RL by the balance of the exploration with drop-out to reduce over-fitting in the perturbed neural networks.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.535-538
• /
• 2022

IoT 디바이스의 Plug & Play를 위하여 IoT 디바이스의 대표적인 유선 인터페이스인 USB의 종류를 이미지를 통하여 인식하는 모듈을 개발한다. IoT 디바이스를 구동시키기 위해서는 통신 및 디바이스 하드웨어를 구동하기 위한 드라이버가 필요하다. IoT 디바이스에 연결되는 유선 인터페이스를 스마트폰의 카메라 촬영을 통하여 얻은 이미지를 이용하여서 해당 통신 인터페이스를 인식한다. 대표적인 유선 인터페이스인 USB에 대하여 인공신경망 기반의 기계학습을 통하여 USB의 종류를 분류한다. 인공신경망의 충분한 학습을 위하여 인터넷을 통하여 USB 이미지를 수집하고, 이미지 처리를 통하여 추가적인 이미지 데이터 셋을 확보한다. 합성곱 신경망과 더불어서 다양한 심층 인공신경망으로 인식기를 구현하여서 그 성능을 비교, 평가한다.

• 전기전자학회논문지
• /
• 제22권4호
• /
• pp.1131-1139
• /
• 2018

본 논문에서는 합성곱 신경망을 이용한 유기된 물체 인식 방법을 제안한다. 유기된 물체 인식 방법은 영상 내에서 유기 물체에 대한 영역을 먼저 검출하며 검출된 영역이 있을 경우 해당 영역에 합성곱 신경망을 적용하여 어떤 물체를 나타내는지 인식하는 과정을 거친다. 실험은 쓰레기 무단투기를 검출하는 응용 시스템을 통해 진행되었다. 실험 결과, 유기 물체에 대한 영역을 효율적으로 검출하는 것을 볼 수 있었다. 검출된 영역은 합성곱 신경망으로 들어가 쓰레기인지 아닌지 분류되는 과정을 거쳤다. 이를 위해 자체적으로 수집한 쓰레기 데이터와 오픈 데이터베이스로 합성곱 신경망을 학습시켰다. 학습 결과, 학습에 포함되지 않은 테스트셋에 대해 약 97%의 정확도를 달성하였다.

• 스마트미디어저널
• /
• 제5권3호
• /
• pp.35-41
• /
• 2016

본 논문에서는 심층 학습 모델 방법을 이용하여 EPS(Electronic Potential Sensor) 기반의 손동작 신호를 인식하는 시스템을 제안한다. 전기장 기반 센서인 EPS로부터 추출된 신호는 다량의 잡음이 포함되어 있어 이를 제거하는 전처리과정을 거쳐야 한다. 주파수 대역 특징 필터를 이용한 잡음 제거한 후, 신호는 시간에 따른 전압(Voltage) 값만 가지는 1차원적 특징을 지닌다. 2차원 데이터를 입력으로 하여 컨볼루션 연산을 하는 알고리즘에 적합한 형태를 갖추기 위해 신호는 차원 변형을 통해 재구성된다. 재구성된 신호데이터는 여러 계층의 학습 층(layer)을 가지는 심층 학습 기반의 모델을 통해 분류되어 최종 인식된다. 기존 확률 기반 통계적 모델링 알고리즘은 훈련 후 모델을 생성하는 과정에서 초기 파라미터에 결과가 좌우되는 어려움이 있었다. 심층 학습 기반 모델은 학습 층을 쌓아 훈련을 반복하므로 이를 극복할 수 있다. 실험에서, 제안된 심층 학습 기반의 서로 다른 구조를 가지는 컨볼루션 신경망(Convolutional Neural Networks), DBN(Deep Belief Network) 알고리즘과 통계적 모델링 기반의 방법을 이용한 인식 결과의 성능을 비교하였고, 컨볼루션 신경망 알고리즘이 다른 알고리즘에 비해 EPS 동작신호 인식에서 보다 우수한 성능을 나타냄을 보였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권9호
• /
• pp.3583-3597
• /
• 2020

In this paper, a parallel deep learning model using a convolutional neural network and a dilated convolutional neural network is proposed to classify Alzheimer's disease with high accuracy in PET/CT images. The developed model consists of two pipelines, a conventional CNN pipeline, and a dilated convolution pipeline. An input image is sent through both pipelines, and at the end of both pipelines, extracted features are concatenated and used for classifying Alzheimer's disease. Complimentary abilities of both networks provide better overall accuracy than single conventional CNNs in the dataset. Moreover, instead of performing binary classification, the proposed model performs three-class classification being Alzheimer's disease, mild cognitive impairment, and normal control. Using the data received from Dong-a University, the model performs classification detecting Alzheimer's disease with an accuracy of up to 95.51%.

• Nuclear Engineering and Technology
• /
• 제53권12호
• /
• pp.4014-4021
• /
• 2021

If safety injection systems (SISs) do not work in the event of a loss-of-coolant accident (LOCA), the accident can progress to a severe accident in which the reactor core is exposed and the reactor vessel fails. Therefore, it is considered that a technology that provides recoverable maximum time for SIS actuation is necessary to prevent this progression. In this study, the corresponding time was defined as the golden time. To achieve the objective of accurately predicting the golden time, the prediction was performed using the deep fuzzy neural network (DFNN) with rule-dropout. The DFNN with rule-dropout has an architecture in which many of the fuzzy neural networks (FNNs) are connected and is a method in which the fuzzy rule numbers, which are directly related to the number of nodes in the FNN that affect inference performance, are properly adjusted by a genetic algorithm. The golden time prediction performance of the DFNN model with rule-dropout was better than that of the support vector regression model. By using the prediction result through the proposed DFNN with rule-dropout, it is expected to prevent the aggravation of the accidents by providing the maximum remaining time for SIS recovery, which failed in the LOCA situation.

• Journal of Information Processing Systems
• /
• 제17권2호
• /
• pp.411-425
• /
• 2021

In this paper, a vehicle recognition algorithm based on deep convolutional neural network and compression dictionary is proposed. Firstly, the network structure of fine vehicle recognition based on convolutional neural network is introduced. Then, a vehicle recognition system based on multi-scale pyramid convolutional neural network is constructed. The contribution of different networks to the recognition results is adjusted by the adaptive fusion method that adjusts the network according to the recognition accuracy of a single network. The proportion of output in the network output of the entire multiscale network. Then, the compressed dictionary learning and the data dimension reduction are carried out using the effective block structure method combined with very sparse random projection matrix, which solves the computational complexity caused by high-dimensional features and shortens the dictionary learning time. Finally, the sparse representation classification method is used to realize vehicle type recognition. The experimental results show that the detection effect of the proposed algorithm is stable in sunny, cloudy and rainy weather, and it has strong adaptability to typical application scenarios such as occlusion and blurring, with an average recognition rate of more than 95%.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권1호
• /
• pp.334-349
• /
• 2022

The effectiveness of Wi-Fi networks is greatly influenced by the optimization of contention window (CW) parameters. Unfortunately, the conventional approach employed by IEEE 802.11 wireless networks is not scalable enough to sustain consistent performance for the increasing number of stations. Yet, it is still the default when accessing channels for single-users of 802.11 transmissions. Recently, there has been a spike in attempts to enhance network performance using a machine learning (ML) technique known as reinforcement learning (RL). Its advantage is interacting with the surrounding environment and making decisions based on its own experience. Deep RL (DRL) uses deep neural networks (DNN) to deal with more complex environments (such as continuous state spaces or actions spaces) and to get optimum rewards. As a result, we present a new approach of CW control mechanism, which is termed as contention window threshold (CW_Threshold). It uses the DRL principle to define the threshold value and learn optimal settings under various network scenarios. We demonstrate our proposed method, known as a smart exponential-threshold-linear backoff algorithm with a deep Q-learning network (SETL-DQN). The simulation results show that our proposed SETL-DQN algorithm can effectively improve the throughput and reduce the collision rates.

• 한국멀티미디어학회논문지
• /
• 제22권12호
• /
• pp.1376-1384
• /
• 2019

The cosmetic and behavioral aspects of aging have become increasingly evident over the years. Physical aging in people can easily be observed on their face, posture, voice, and gait. In contrast, bone aging only becomes apparent once significant bone degeneration manifests through degenerative bone diseases. Therefore, a more accurate and timely assessment of bone aging is needed so that the determinants and its mechanisms can be more effectively identified and ultimately optimized. This study proposed a deep learning approach to assess the bone age of an adult using whole-body bone scintigraphy. The proposed approach uses multiple inputs deep neural network architectures using a loss function, called mean-variance loss. The data set was collected from Chonnam National University Hwasun Hospital. The experiment results show the effectiveness of the proposed method with a mean absolute error of 3.40 years.

• Journal of Information Processing Systems
• /
• 제17권2호
• /
• pp.337-351
• /
• 2021

Automatically recognizing facial expressions in video sequences is a challenging task because there is little direct correlation between facial features and subjective emotions in video. To overcome the problem, a video facial expression recognition method using spatiotemporal recurrent neural network and feature fusion is proposed. Firstly, the video is preprocessed. Then, the double-layer cascade structure is used to detect a face in a video image. In addition, two deep convolutional neural networks are used to extract the time-domain and airspace facial features in the video. The spatial convolutional neural network is used to extract the spatial information features from each frame of the static expression images in the video. The temporal convolutional neural network is used to extract the dynamic information features from the optical flow information from multiple frames of expression images in the video. A multiplication fusion is performed with the spatiotemporal features learned by the two deep convolutional neural networks. Finally, the fused features are input to the support vector machine to realize the facial expression classification task. The experimental results on cNTERFACE, RML, and AFEW6.0 datasets show that the recognition rates obtained by the proposed method are as high as 88.67%, 70.32%, and 63.84%, respectively. Comparative experiments show that the proposed method obtains higher recognition accuracy than other recently reported methods.