• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2014년도 추계학술대회
• /
• pp.316-319
• /
• 2014

전 세계적으로 커피시장이 커짐에 따라서 커피에 대한 사람들의 관심도 또한 커지고 있는 추세이다. 이러한 추세 속에서 사람들의 입맛이 더욱 고급스러워지고 커피의 맛을 결정하는 커피 원두가 중요시 되고 있다. 하지만 현재는 불량원두를 사람이 직접 보고 검출을 하고 있는데, 이는 커피 원두에 대한 전문적 지식이 있는 사람만이 할 수가 있는 작업이다. 따라서 본 논문에서는 기계학습을 이용한 불량원두 검출 시스템을 제안한다. 이 시스템에서는 불량 원두의 종류 중 큰 비율을 차지하는 원두의 모양과 Insect Damage에 대한 불량 검출에 중점을 두었다. 기계학습의 방법으로 Convolutional Neural Network를 사용하였고, 원두의 모양을 검출할 신경망과 Insect Damage를 검출할 신경망 두 개로 구성되어 있다. Insect Damage에 대한 불량을 검출할 때에는 카메라의 노출시간을 길게 하여 원두의 어두운 구멍을 더 돋보이게 하여 데이터를 만들어 신경망을 구축하였다. 이 시스템의 개발로 인하여 사람이 직접 불량 원두를 검출하는 작업을 자동화 시스템으로 전환할 수 있는 시발점이 될 수 있을 것이고, 현재는 원두의 모양과 Insect Damage의 유무만을 중점으로 검출을 하고 있기 때문에, 추후에 다른 여러 가지의 불량에 대해 검출할 수 있는 연구가 필요하다.

• 한국IT서비스학회지
• /
• 제15권4호
• /
• pp.85-95
• /
• 2016

Recently, deep learning and machine learning have attracted considerable attention and many supporting frameworks appeared. In artificial intelligence field, a large body of research is underway to apply the relevant knowledge for complex problem-solving, necessitating the application of various learning algorithms and training methods to artificial intelligence systems. In addition, there is a dearth of performance evaluation of decision making agents. The decision making agent that can find optimal solutions by using reinforcement learning methods designed through this research can collect raw pixel data observed from dynamic environments and make decisions by itself based on the data. The decision making agent uses convolutional neural networks to classify situations it confronts, and the data observed from the environment undergoes preprocessing before being used. This research represents how the convolutional neural networks and the decision making agent are configured, analyzes learning performance through a value-based algorithm and a policy-based algorithm : a Deep Q-Networks and a Policy Gradient, sets forth their differences and demonstrates how the convolutional neural networks affect entire learning performance when using pixel data. This research is expected to contribute to the improvement of artificial intelligence systems which can efficiently find optimal solutions by using features extracted from raw pixel data.

• 한국산업융합학회 논문집
• /
• 제23권3호
• /
• pp.515-521
• /
• 2020

Deep learning methods have been effectively used to provide great improvement in various research fields such as machine learning, image processing and computer vision. One of the most frequently used deep learning methods in image processing is the convolutional neural networks. Compared to the traditional artificial neural networks, convolutional neural networks do not use the predefined kernels, but instead they learn data specific kernels. This property makes them to be used as feature extractors as well. In this study, we compared the quality of CNN features for traditional texture feature extraction methods. Experimental results demonstrate the superiority of the CNN features. Additionally, the recognition process and result of a pioneering CNN on MNIST database are presented.

• Journal of information and communication convergence engineering
• /
• 제18권2호
• /
• pp.75-81
• /
• 2020

Approximately 1.3 million people die from traffic accidents each year, and smartphone usage while driving is one of the main causes of such accidents. Therefore, detection of smartphone usage by drivers has become an important part of distracted driving detection. Previous studies have used single camera-based methods to collect the driver images. However, smartphone usage detection by employing a single camera can be unsuccessful if the driver occludes the phone. In this paper, we present a driver smartphone usage detection system that uses multiple cameras to collect driver images from different perspectives, and then processes these images with ensemble convolutional neural networks. The ensemble method comprises three individual convolutional neural networks with a simple voting system. Each network provides a distinct image perspective and the voting mechanism selects the final classification. Experimental results verified that the proposed method avoided the limitations observed in single camera-based methods, and achieved 98.96% accuracy on our dataset.

• Journal of Semiconductor Engineering
• /
• 제1권1호
• /
• pp.31-37
• /
• 2020

We present an approximate DRAM architecture for energy-efficient deep learning. Our key premise is that by bounding memory errors to non-critical information, we can significantly reduce DRAM refresh energy without compromising recognition accuracy of deep neural networks. To validate the key premise, we make extensive Monte-Carlo simulations for several well-known convolutional neural networks such as LeNet, ConvNet and AlexNet with the input of MINIST, CIFAR-10, and ImageNet, respectively. We assume that the highest-order 8-bits (in single precision) and 4-bits (in half precision) are protected from retention errors under the proposed architecture and then, randomly inject bit-errors to unprotected bits with various bit-error-rates. Here, recognition accuracies of the above convolutional neural networks are successfully maintained up to the 10^-5-order bit-error-rate. We simulate DRAM energy during inference of the above convolutional neural networks, where the proposed architecture shows the possibility of considerable energy saving up to 10 ~ 37.5% of total DRAM energy.

• Nuclear Engineering and Technology
• /
• 제55권6호
• /
• pp.2276-2282
• /
• 2023

We deploy artificial neural networks to unfold neutron spectra from measured energy-integrated quantities. These neutron spectra represent an important parameter allowing to compute the absorbed dose and the kerma to serve radiation protection in addition to nuclear safety. The built architectures are inspired from convolutional neural networks. The first architecture is made up of residual transposed convolution's blocks while the second is a modified version of the U-net architecture. A large and balanced dataset is simulated following "realistic" physical constraints to train the architectures in an efficient way. Results show a high accuracy prediction of neutron spectra ranging from thermal up to fast spectrum. The dataset processing, the attention paid to performances' metrics and the hyper-optimization are behind the architectures' robustness.

• 한국정보통신학회논문지
• /
• 제22권5호
• /
• pp.728-733
• /
• 2018

단백질을 구성하는 아미노산의 서열 정보만으로 단백질 이차 구조를 예측하기 위하여 심층 학습이 활발히 연구되고 있다. 본 논문에서는 단백질 이차 구조를 예측하기 위하여 다양한 구조의 합성곱 신경망의 성능을 비교하였다. 단백질 이차 구조의 예측에 적합한 신경망의 층의 깊이를 알아내기 위하여 층의 개수에 따른 성능을 조사하였다. 또한 이미지 분류 분야의 많은 방법들이 기반 하는 GoogLeNet과 ResNet의 구조를 적용하였는데, 이러한 방법은 입력 자료에서 다양한 특성을 추출하거나, 깊은 층을 사용하여도 학습과정에서 그래디언트 전달을 원활하게 한다. 합성곱 신경망의 여러 구조를 단백질 자료의 특성에 적합하게 변경하여 성능을 향상시켰다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권11호
• /
• pp.5427-5445
• /
• 2019

While deep neural networks have achieved remarkable performance in representation learning, a huge amount of labeled training data are usually required by supervised deep models such as convolutional neural networks. In this paper, we propose a new representation learning method, namely generative adversarial networks (GAN) based bagging deep convolutional autoencoders (GAN-BDCAE), which can map data to diverse hierarchical representations in an unsupervised fashion. To boost the size of training data, to train deep model and to aggregate diverse learning machines are the three principal avenues towards increasing the capabilities of representation learning of neural networks. We focus on combining those three techniques. To this aim, we adopt GAN for realistic unlabeled sample generation and bagging deep convolutional autoencoders (BDCAE) for robust feature learning. The proposed method improves the discriminative ability of learned feature embedding for solving subsequent pattern recognition problems. We evaluate our approach on three standard benchmarks and demonstrate the superiority of the proposed method compared to traditional unsupervised learning methods.

• 한국IT서비스학회지
• /
• 제16권4호
• /
• pp.149-160
• /
• 2017

Sentiment analysis is the process of determining whether a piece of document, text or conversation is positive, negative, neural or other emotion. Sentiment analysis has been applied for several real-world applications, such as chatbot. In the last five years, the practical use of the chatbot has been prevailing in many field of industry. In the chatbot applications, to recognize the user emotion, sentiment analysis must be performed in advance in order to understand the intent of speakers. The specific emotion is more than describing positive or negative sentences. In light of this context, we propose deep learning models for conducting multi-class sentiment analysis for identifying speaker's emotion which is categorized to be joy, fear, guilt, sad, shame, disgust, and anger. Thus, we develop convolutional neural network (CNN), long short term memory (LSTM), and multi-layer neural network models, as deep neural networks models, for detecting emotion in a sentence. In addition, word embedding process was also applied in our research. In our experiments, we have found that long short term memory (LSTM) model performs best compared to convolutional neural networks and multi-layer neural networks. Moreover, we also show the practical applicability of the deep learning models to the sentiment analysis for chatbot.

• 한국인터넷방송통신학회논문지
• /
• 제17권5호
• /
• pp.97-102
• /
• 2017

최근 고해상도 원격탐사 자료의 분류방안으로 컨볼루션 신경망(Convolutional Neural Networks)을 비롯한 딥 러닝 기법들이 소개되고 있다. 본 논문에서는 드론으로 촬영된 농경지 영상의 작물 분류를 위해 컨볼루션 신경망을 적용하여 가능성을 검토하였다. 농경지를 논, 고구마, 고추, 옥수수, 깻잎, 과수, 비닐하우스로 총 7가지 클래스로 나누고 수동으로 라벨링 작업을 완료했다. 컨볼루션 신경망 적용을 위해 영상 전처리와 정규화 작업을 수행하였으며 영상분류 결과 98%이상 높은 정확도를 확인할 수 있었다. 본 논문을 통해 기존 영상분류 방법들에서 딥 러닝 기반 영상분류 방법으로의 전환이 빠르게 진행될 것으로 예상되며, 그 성공 가능성을 확신할 수 있었다.