• The KIPS Transactions:PartB
• /
• v.11B no.2
• /
• pp.169-176
• /
• 2004

This paper presents a new color correction method for color reproduction on LCD-based monitor by means of high-order multilayer neural networks. LCD monitors have nonlinear characteristics from various displaying system components. To overcome these nonlinearities and produce quality image, we need a nonlinear transformer for color coordinate transformation between the LCD monitor coordinates and the input color stimulus values. A high-order multilayer neural network is effectively trained to learn a mapping to determine the required color value of monitors for producing a given color stimulus. From the experimental results, the proposed method is effective in reproducing the color images.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_2
• /
• pp.1743-1747
• /
• 2022

Sentinel-2 can be used as proxy data for the Korean Compact Advanced Satellite 500-4 (CAS500-4), also known as Agriculture and Forestry Satellite, in terms of spectral wavelengths and spatial resolution. This letter examined cloud detection for later use in the CAS500-4 based on deep learning technologies. DeepLabV3+, a traditional Convolutional Neural Network (CNN) model, and Shifted Windows (Swin) Transformer, a state-of-the-art (SOTA) Transformer model, were compared using 22,728 images provided by Radiant Earth Foundation (REF). Swin Transformer showed a better performance with a precision of 0.886 and a recall of 0.875, which is a balanced result, unbiased between over- and under-estimation. Deep learning-based cloud detection is expected to be a future operational module for CAS500-4 through optimization for the Korean Peninsula.

• Phonetics and Speech Sciences
• /
• v.12 no.3
• /
• pp.55-63
• /
• 2020

Voice conversion can be applied to various voice processing applications. It can also play an important role in data augmentation for speech recognition. The conventional method uses the architecture of voice conversion with speech synthesis, with Mel filter bank as the main parameter. Mel filter bank is well-suited for quick computation of neural networks but cannot be converted into a high-quality waveform without the aid of a vocoder. Further, it is not effective in terms of obtaining data for speech recognition. In this paper, we focus on performing voice-to-voice conversion using only the raw spectrum. We propose a deep learning model based on the transformer network, which quickly learns the voice conversion properties using an attention mechanism between source and target spectral components. The experiments were performed on TIDIGITS data, a series of numbers spoken by an English speaker. The conversion voices were evaluated for naturalness and similarity using mean opinion score (MOS) obtained from 30 participants. Our final results yielded 3.52±0.22 for naturalness and 3.89±0.19 for similarity.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2004.11a
• /
• pp.87-90
• /
• 2004

This paper describes development of power transformer maintenance system using intelligent dissolved gases in oil analysis. The used gases are acetylene(C2H2), hydrogen(H2), ethylene(C2H4), methane(CH4), ethane(C2H6), carbon monoxide(CO) and carbon dioxide(CO2). The rule and neural network based gas analysis methods are used for artificial intelligent diagnosis. It is indicated that this program is efficient for diagnosis of oil immersed transformers diagnosis from application of gas analysis data of serviced transformer which has local overheating

• Annual Conference of KIPS
• /
• 2023.05a
• /
• pp.363-365
• /
• 2023

본 논문에서는 어텐션(Attention) 메커니즘을 이미지 처리에 적용한 연구가 진행되면서 등장한 비전 트랜스포머 (Vision Transformer, ViT)의 한계를 극복하기 위해 ViT 기반의 딥 클러스터링(Deep Clustering) 기법을 제안한다. ViT는 완전히 트랜스포머(Transformer)만을 사용하여 입력 이미지의 패치(patch)들을 벡터로 변환하여 학습하는 모델로, 합성곱 신경망(Convolutional Neural Network, CNN)을 사용하지 않으므로 입력 이미지의 크기에 대한 제한이 없으며 높은 성능을 보인다. 그러나 작은 데이터셋에서는 학습이 어렵다는 단점이 있다. 제안하는 딥 클러스터링 기법은 처음에는 입력 이미지를 임베딩 모델에 통과시켜 임베딩 벡터를 추출하여 클러스터링을 수행한 뒤, 클러스터링 결과를 임베딩 벡터에 반영하도록 업데이트하여 클러스터링을 개선하고, 이를 반복하는 방식이다. 이를 통해 ViT 모델의 일반적인 패턴 파악 능력을 개선하고 더욱 정확한 클러스터링 결과를 얻을 수 있다는 것을 실험을 통해 확인하였다.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.7
• /
• pp.11-18
• /
• 2023

In this paper, we evaluate deep learning time series forecasting models. Recent studies show that those models perform better than the traditional prediction model such as ARIMA. Among them, recurrent neural networks to store previous information in the hidden layer are one of the prediction models. In order to solve the gradient vanishing problem in the network, LSTM is used with small memory inside the recurrent neural network along with BI-LSTM in which the hidden layer is added in the reverse direction of the data flow. In this paper, we compared the performance of Informer by comparing with other models (LSTM, BI-LSTM, and Transformer) for real Nitrogen dioxide (NO2) data. In order to evaluate the accuracy of each method, mean square root error and mean absolute error between the real value and the predicted value were obtained. Consequently, Informer has improved prediction accuracy compared with other methods.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2002.07b
• /
• pp.894-899
• /
• 2002

In this papers, we proposed the new method in order to diagnosis partial discharge type of transformers. For wavelet transform, Daubechies filter is used, we can obtain wavelet coefficients which is used to extract feature of statistical parameters (maximum value, average value, dispersion, skewness, kurtosis) about high frequency current signal per 3-electrode type (needle-plane electrode, IEC electrode and Void electrode.). Also. these coefficients are used to identify Signal of internal partial discharge in transformer. As a result. from compare of high frequency current signal amplitude and average value. we are obtained results of IEC electrode> Void electrode> Needle-Plane electrode. otherwise. In case of skewness and kurtosis, we are obtained results of Void electrode> IEC electrode > Needle-Plane electrode. As Improved method in order to diagnosis partial discharge type of transformers, we use neural network.

• The Journal of Korea Robotics Society
• /
• v.17 no.4
• /
• pp.425-430
• /
• 2022

As robots are considered one of the mainstream digital transformations, robots with machine vision becomes a main area of study providing the ability to check what robots watch and make decisions based on it. However, it is difficult to find a small object in the image mainly due to the flaw of the most of visual recognition networks. Because visual recognition networks are mostly convolution neural network which usually consider local features. So, we make a model considering not only local feature, but also global feature. In this paper, we propose a detection method of a small marker on the object using deep learning and an algorithm that considers global features by combining Transformer's self-attention technique with a convolutional neural network. We suggest a self-attention model with new definition of Query, Key and Value for model to learn global feature and simplified equation by getting rid of position vector and classification token which cause the model to be heavy and slow. Finally, we show that our model achieves higher mAP than state of the art model YOLOr.

• Journal of Intelligence and Information Systems
• /
• v.28 no.3
• /
• pp.119-137
• /
• 2022

Recent recommendation system studies apply various deep learning models to represent user and item interactions better. One of the noteworthy studies is ONCF(Outer product-based Neural Collaborative Filtering) which builds a two-dimensional interaction map via outer product and employs CNN (Convolutional Neural Networks) to learn high-order correlations from the map. However, ONCF has limitations in recommendation performance due to the problems with CNN and the absence of side information. ONCF using CNN has an inductive bias problem that causes poor performances for data with a distribution that does not appear in the training data. This paper proposes to employ a Vision Transformer (ViT) instead of the vanilla CNN used in ONCF. The reason is that ViT showed better results than state-of-the-art CNN in many image classification cases. In addition, we propose a new architecture to reflect side information that ONCF did not consider. Unlike previous studies that reflect side information in a neural network using simple input combination methods, this study uses an independent auxiliary classifier to reflect side information more effectively in the recommender system. ONCF used a single latent vector for user and item, but in this study, a channel is constructed using multiple vectors to enable the model to learn more diverse expressions and to obtain an ensemble effect. The experiments showed our deep learning model improved performance in recommendation compared to ONCF.

• Phonetics and Speech Sciences
• /
• v.13 no.3
• /
• pp.71-78
• /
• 2021

Most neural-network-based speech synthesis models utilize neural vocoders to convert mel-scaled spectrograms into high-quality, human-like voices. However, neural vocoders combined with mel-scaled spectrogram prediction models demand considerable computer memory and time during the training phase and are subject to slow inference speeds in an environment where GPU is not used. This problem does not arise in linear spectrogram prediction models, as they do not use neural vocoders, but these models suffer from low voice quality. As a solution, this paper proposes a Tacotron 2 and Transformer-based linear spectrogram prediction model that produces high-quality speech and does not use neural vocoders. Experiments suggest that this model can serve as the foundation of a high-quality text-to-speech model with fast inference speed.