• Journal of Broadcast Engineering
• /
• v.26 no.4
• /
• pp.419-428
• /
• 2021

Shadow removal plays a key role for the pre-processing of image processing techniques such as object tracking and detection. With the advances of image recognition based on deep convolution neural networks, researches for shadow removal have been actively conducted. In this paper, we propose a novel method for shadow removal, which utilizes self attention distillation to extract semantic features. The proposed method gradually refines results of shadow detection, which are extracted from each layer of the proposed network, via top-down distillation. Specifically, the training procedure can be efficiently performed by learning the contextual information for shadow removal without shadow masks. Experimental results on various datasets show the effectiveness of the proposed method for shadow removal under real world environments.

• Review of KIISC
• /
• v.29 no.6
• /
• pp.59-66
• /
• 2019

사물인터넷 환경은 무수히 많은 이기종의 기기가 연결되는 초연결 네트워크 구성을 갖는 특성이 있다. 본 논문에서는 이러한 특성을 갖는 사물인터넷 환경에 적합한 보안 기술로 네트워크를 통해 침입하는 위협의 효율적인 탐지 기술을 제안한다. 사물인터넷 환경에서의 대표적인 위협 행위를 분석하고 관련하여 공격 데이터를 수집하고 이를 토대로 특성 연구를 진행하였다. 이를 기반으로 인공신경망 기반의 오토인코더 알고리즘을 활용하여 심층학습 탐지 모델을 구축하였다. 본 논문에서 제안하는 탐지 모델은 비지도 학습 방식의 오토인코더를 지도학습 기반의 분류기로 확장하여 사물인터넷 환경에서의 대표적인 위협 유형을 식별할 수 있었다. 본 논문은 1. 서론을 통해 현재 사물인터넷 환경과 보안 기술 연구 동향을 소개하고 2. 관련연구를 통하여 머신러닝 기술과 위협 탐지 기술에 대해 소개한다. 3. 제안기술에서는 본 논문에서 제안하는 인공신경망 알고리즘 기반의 사물인터넷 위협 탐지 기술에 대해 설명하고, 4. 향후연구계획을 통해 추후 활용 방안 및 고도화에 대한 내용을 작성하였다. 마지막으로 5. 결론을 통하여 제안기술의 평가와 소회에 대해 설명하였다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.4
• /
• pp.220-227
• /
• 2021

PCT (Power Cable Tunnel) and UT (Utility Tunnel), which are non-transport underground infrastructures, are mostly RC (Reinforced Concrete) structures, and their durability decreases due to the deterioration caused by carbonation over time. In particular, since the rate of carbonation varies by use and region, a predictive model based on actual carbonation data is required for individual maintenance. In this study, a carbonation prediction model was developed for non-transport underground infrastructures, such as PCT and UT. A carbonation prediction model was developed using multiple regression analysis and deep neural network techniques based on the actual data obtained from a safety inspection. The structures, region, measurement location, construction method, measurement member, and concrete strength were selected as independent variables to determine the dependent variable carbonation rate coefficient in multiple regression analysis. The adjusted coefficient of determination (Ra2) of the multiple regression model was found to be 0.67. The coefficient of determination (R2) of the model for predicting the carbonation of non-transport underground infrastructures using a deep neural network was 0.82, which was superior to the comparative prediction model. These results are expected to help determine the optimal timing for repair on carbonation and preventive maintenance methodology for PCT and UT.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.1308-1310
• /
• 2022

소리 데이터 분류는 단순 소리를 통한 분류, 감정 인식등 다양한 연구가 진행중이다. 심층 신경망에서 데이터의 부족과 과적합 문제를 개선하는 방법으로 데이터 증강은 중요하다. 본 논문에서는 3가지의 소리데이터(UrbanSound8K, RAVDESS, IRMAS)를 사용하였으며, 소리데이터는 멜 스펙트로그램을 통한 변환과정을 거쳐 네트워크 망에 입력된다. 입력된 신호는 다양한 네크워크 신경망(Bidirection LSTM, Bidirection LSTM Attention, Multi-Head Attention, CNN)을 통해 학습되어지며, 각각의 네트워크 신경망에서 데이터 증강 전후의 분류 정확도를 확인 하였다. 다양한 데이터셋과 다양한 네트워크 망에서의 데이터 증강 방법의 결과 비교를 통한 통찰을 얻을수 있을 것이다.

• The Journal of the Acoustical Society of Korea
• /
• v.36 no.1
• /
• pp.70-77
• /
• 2017

Bandwidth extension is a technique to improve speech quality, intelligibility and naturalness, extending from the 300 ~ 3,400 Hz narrowband speech to the 50 ~ 7,000 Hz wideband speech. In this paper, an Artificial Bandwidth Extension (ABE) module embedded in the Opus audio decoder is designed using the information of narrowband speech to reduce the computational complexity of LPC (Linear Prediction Coding) and LSF (Line Spectral Frequencies) analysis and the algorithm delay of the ABE module. We proposed a spectral envelope extension method using DBN (Deep Belief Network), one of deep learning techniques, and the proposed scheme produces better extended spectrum than the traditional codebook mapping method.

• Journal of Broadcast Engineering
• /
• v.23 no.3
• /
• pp.383-394
• /
• 2018

In this paper, we investigate image and video compression techniques based on deep learning which are actively studied recently. The deep learning based image compression technique inputs an image to be compressed in the deep neural network and extracts the latent vector recurrently or all at once and encodes it. In order to increase the image compression efficiency, the neural network is learned so that the encoded latent vector can be expressed with fewer bits while the quality of the reconstructed image is enhanced. These techniques can produce images of superior quality, especially at low bit rates compared to conventional image compression techniques. On the other hand, deep learning based video compression technology takes an approach to improve performance of the coding tools employed for existing video codecs rather than directly input and process the video to be compressed. The deep neural network technologies introduced in this paper replace the in-loop filter of the latest video codec or are used as an additional post-processing filter to improve the compression efficiency by improving the quality of the reconstructed image. Likewise, deep neural network techniques applied to intra prediction and encoding are used together with the existing intra prediction tool to improve the compression efficiency by increasing the prediction accuracy or adding a new intra coding process.

• The Journal of the Korea Contents Association
• /
• v.21 no.3
• /
• pp.616-625
• /
• 2021

Deep neural networks are an approximation method that approximates an arbitrary function to a linear model and then repeats additional approximation using a nonlinear active function. In this process, the method of evaluating the performance of approximation uses the loss function. Existing in-depth learning methods implement approximation that takes into account loss functions in the linear approximation process, but non-linear approximation phases that use active functions use non-linear transformation that is not related to reduction of loss functions of loss. This study proposes parametric activation functions that introduce scale parameters that can change the scale of activation functions and location parameters that can change the location of activation functions. By introducing parametric activation functions based on scale and location parameters, the performance of nonlinear approximation using activation functions can be improved. The scale and location parameters in each hidden layer can improve the performance of the deep neural network by determining parameters that minimize the loss function value through the learning process using the primary differential coefficient of the loss function for the parameters in the backpropagation. Through MNIST classification problems and XOR problems, parametric activation functions have been found to have superior performance over existing activation functions.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.43-45
• /
• 2021

The short-term quantitative precipitation prediction (QPF) system is important socially and economically to prevent damage from severe weather. Recently, many studies for short-term QPF model applying the Deep Neural Network (DNN) has been conducted. These studies require the sophisticated pre-processing because the mistreatment of various and vast meteorological data sets leads to lower performance of QPF. Especially, for more accurate prediction of the non-linear trends in precipitation, the dataset needs to be carefully handled based on the physical and dynamical understands the data. Thereby, this paper proposes the following approaches: i) refining and combining major factors (weather radar, terrain, air temperature, and so on) related to precipitation development in order to construct training data for pattern analysis of precipitation; ii) producing predicted precipitation fields based on Convolutional with ConvLSTM. The proposed algorithm was evaluated by rainfall events in 2020. It is outperformed in the magnitude and strength of precipitation, and clearly predicted non-linear pattern of precipitation. The algorithm can be useful as a forecasting tool for preventing severe weather.

• Broadcasting and Media Magazine
• /
• v.25 no.1
• /
• pp.20-27
• /
• 2020

최근 모바일 기기를 위한 카메라 관련 기술이 발전하면서 취득할 수 있는 영상의 화질 또한 크게 향상되고 있다. 그러나, 일상 생활에서 빈번히 발생하는 다양한 실내외 불규칙한 조명 조건 및 저조도 환경은 여전히 영상 화질 저하를 야기한다. 본 고에서는 이러한 문제를 해결하기 위해 최근 널리 연구되고 있는 심층신경망 기반 영상 화질 개선 연구의 최신 동향을 소개하고자 한다. 먼저, 다양한 최적화 기법을 바탕으로 영상 내 조명 성분을 추정하고, 이를 개선하는 방법들에 대해 간략히 설명한다. 또한, 영상 인식, 객체 검출 등에서 뛰어난 성능을 입증한 합성곱 신경망 구조를 기반으로 영상의 잠재적 특징을 효과적으로 검출한 후 이를 바탕으로 개선된 영상을 생성하는 방법에 대해 설명한다. 다양한 데이터셋에 대한 실험 결과를 통해 인공지능 기반 영상 화질 개선의 우수성을 보인다.

• Database Research
• /
• v.34 no.3
• /
• pp.3-13
• /
• 2018

Text classification is one of the text mining technologies that classifies a given textual document into its appropriate categories and is used in various fields such as spam email detection, news classification, question answering, emotional analysis, and chat bot. In general, the text classification system utilizes machine learning algorithms, and among a number of algorithms, naïve Bayes and support vector machine, which are suitable for text data, are known to have reasonable performance. Recently, with the development of deep learning technology, several researches on applying deep neural networks such as recurrent neural networks (RNN) and convolutional neural networks (CNN) have been introduced to improve the performance of text classification system. However, the current text classification techniques have not yet reached the perfect level of text classification. This paper focuses on the fact that the text data is expressed as a vector only with the word dimensions, which impairs the semantic information inherent in the text, and proposes a neural network architecture based upon the semantic tensor space model.