• 한국정보기술학회 영문논문지
• /
• 제8권2호
• /
• pp.119-127
• /
• 2018

Training a very large deep neural network can be painfully slow and prone to overfitting. Many researches have done for overcoming the problem. In this paper, a combination of early stopping and ADAM based deep neural network was presented. This form of deep network is useful for handling the big data because it automatically stop the training before overfitting occurs. Also generalization ability is better than pure deep neural network model.

• Journal of Information Technology Applications and Management
• /
• 제26권6호
• /
• pp.89-101
• /
• 2019

Many researchers have been focused on designing beauty product recommendation system for a long time because of increased need of customers for personalized and customized recommendation in beauty product domain. In addition, as the application of the deep neural network technique becomes active recently, various collaborative filtering techniques based on the deep neural network have been introduced. In this context, this study proposes a deep neural network model suitable for beauty product recommendation by applying Neural Collaborative Filtering and Generalized Matrix Factorization (NCF + GMF) to beauty product recommendation. This study also provides an implementation of web API system to commercialize the proposed recommendation model. The overall performance of the NCF + GMF model was the best when the beauty product recommendation problem was defined as the estimation rating score problem and the binary classification problem. The NCF + GMF model showed also high performance in the top N recommendation.

• 반도체디스플레이기술학회지
• /
• 제20권1호
• /
• pp.64-69
• /
• 2021

In this paper, a method for improving the defect classification performance in low contrast, ununiformity and featureless steel plate surfaces has been studied based on deep convolution neural network and transfer-learning neural network. The steel plate surface images have low contrast, ununiformity, and featureless, so that the contrast between defect and defect-free regions are not discriminated. These characteristics make it difficult to extract the feature of the surface defect image. A classifier based on a deep convolution neural network is constructed to extract features automatically for effective classification of images with these characteristics. As results of the experiment, AlexNet-based transfer-learning classifier showed excellent classification performance of 99.43% with less than 160 seconds of training time. The proposed classification system showed excellent classification performance for low contrast, ununiformity, and featureless surface images.

• Journal of information and communication convergence engineering
• /
• 제19권4호
• /
• pp.241-247
• /
• 2021

Particulate matter has emerged as a serious global problem, necessitating highly reliable information on the matter. Therefore, various algorithms have been used in studies to predict particulate matter. In this study, we compared the prediction performance of neural network models that have been actively studied for particulate matter prediction. Among the neural network algorithms, a deep neural network (DNN), a recurrent neural network, and long short-term memory were used to design the optimal prediction model using a hyper-parameter search. In the comparative analysis of the prediction performance of each model, the DNN model showed a lower root mean square error (RMSE) than the other algorithms in the performance comparison using the RMSE and the level of accuracy as metrics for evaluation. The stability of the recurrent neural network was slightly lower than that of the other algorithms, although the accuracy was higher.

• International Journal of Advanced Culture Technology
• /
• 제6권4호
• /
• pp.262-265
• /
• 2018

Deep learning, a sub-field of machine learning changing the prospects of artificial intelligence (AI) because of its recent advancements and application in various field. Deep learning deals with algorithms inspired by the structure and function of the brain called artificial neural networks. This works reviews basic architecture and recent advancement of deep structured learning. It also describes contemporary applications of deep structured learning and its advantages over the treditional learning in artificial interlligence. This study is useful for the general readers and students who are in the early stage of deep learning studies.

• International Journal of Advanced Culture Technology
• /
• 제7권4호
• /
• pp.327-333
• /
• 2019

Wind speed data constitute important weather information for aircrafts flying at low altitudes, such as drones. Currently, the accuracy of low altitude wind predictions is much lower than that of high-altitude wind predictions. Deep neural networks are proposed in this study as a method to improve wind speed forecast information. Deep neural networks mimic the learning process of the interactions among neurons in the brain, and it is used in various fields, such as recognition of image, sound, and texts, image and natural language processing, and pattern recognition in time-series. In this study, the deep neural network model is constructed using the wind prediction values generated by the numerical model as an input to improve the wind speed forecasts. Using the ground wind speed forecast data collected at the Boseong Meteorological Observation Tower, wind speed forecast values obtained by the numerical model are compared with those obtained by the model proposed in this study for the verification of the validity and compatibility of the proposed model.

• 한국항행학회논문지
• /
• 제25권5호
• /
• pp.409-414
• /
• 2021

미세먼지에 대한 심각성이 사회적으로 대두됨에 따라 대중들은 미세먼지 예보에 대한 정보의 높은 신뢰성을 요구하고 있다. 이에 따라 다양한 신경망 알고리즘을 이용하여 미세먼지 예측을 위한 연구가 활발히 진행되고 있다. 본 논문에서는 미세먼지 예측을 위해 다양한 알고리즘으로 연구되고 있는 신경망 알고리즘들 중 대표적인 알고리즘들의 예측 성능 비교를 진행하였다. 신경망 알고리즘 중 DNN(deep neural network), RNN(recurrent neural network), LSTM(long short-term memory)을 이용하였으며, 하이퍼 파라미터 탐색을 이용하여 최적의 예측 모델을 설계하였다. 각 모델의 예측 성능 비교 분석 결과, 실제 값과 예측 값의 변화 추이는 전반적으로 좋은 성능을 보였다. RMSE와 정확도를 기준으로 한 분석에서는 DNN 예측 모델이 다른 예측 모델에 비해 예측 오차에 대한 안정성을 갖는 것을 확인하였다.

• 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.

• 한국음향학회지
• /
• 제35권2호
• /
• pp.143-148
• /
• 2016

깊은 신경망은 데이터의 특성을 효과적으로 나타낼 수 있는 방법으로 최근 많은 응용 분야에서 활용되고 있다. 하지만, 제한적인 양의 데이터베이스는 깊은 신경망을 훈련하는 과정에서 과적합 문제를 야기할 수 있다. 본 논문에서는 풍부한 양의 음성 혹은 음악 데이터를 이용한 전이학습을 통해 제한적인 양의 사운드 이벤트에 대한 깊은 신경망을 효과적으로 훈련하는 방법을 제안한다. 일련의 실험을 통해 제안하는 방법이 적은 양의 사운드 이벤트 데이터만으로 훈련된 깊은 신경망에 비해 현저한 성능 향상이 있음을 확인하였다.

• 방송공학회논문지
• /
• 제24권2호
• /
• pp.227-233
• /
• 2019

본 논문은 가상현실 음향 구현을 위한 심층신경망 기반 사운드 보간 방법에 관한 것으로서, 이를 통해 두 지점에서 취득한 음향 신호들을 사용하여 두 지점 사이의 음향을 생성한다. 산술평균이나 기하평균 같은 통계적 방법으로 사운드 보간을 수행할 수 있지만 이는 실제 비선형 음향 특성을 반영하기에 미흡하다. 이러한 문제를 해결하기 위해서 본 연구에서는 두 지점과 목표 지점의 음향신호를 기반으로 심층신경망을 훈련하여 사운드 보간을 시도하였으며, 실험결과 통계적 방법에 비해 심층신경망 기반 사운드 보간 방법의 성능이 우수함을 보였다.