• 한국전자통신학회논문지
• /
• 제15권3호
• /
• pp.465-472
• /
• 2020

최근 들어, 오디오 이벤트 검출을 위하여 다양한 딥뉴럴네트워크 기반의 방법들이 제안되어 왔다. 본 연구에서는 베이스라인 CRNN(Convolutional Recurrent Neural Network) 구조에 attention 방식을 도입함으로서 오디오 이벤트 검출의 성능을 향상시키고자 하였다. 베이스라인 CRNN의 입력단에 context gating을 적용하고 출력단에 attention layer을 추가하였다. 또한, 프레임(frame) 단위의 강전사 레이블(strong label)정보 뿐만 아니라 클립(clip) 단위의 약전사 레이블(weakly label) 오디오 데이터를 이용한 학습을 통하여 보다 나은 성능을 이루고자 하였다. DCASE 2018/2019 Challenge Task 4 데이터를 이용한 오디오 이벤트 검출 실험에서 제안된 attention 기반의 CRNN을 통하여 기존의 CRNN 방식에 비해서 최대 66%의 상대적 F-score 향상을 얻을 수 있었다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2019년도 추계학술발표대회
• /
• pp.1023-1025
• /
• 2019

Coal and Natural gas are two biggest contributors to a generation of energy throughout the world. Most of these resources create environmental pollution while making energy affecting the natural habitat. Many approaches have been proposed as alternatives to these sources. One of the leading alternatives is Solar Energy which is usually harnessed using solar farms. In artificial intelligence, the most researched area in recent times is machine learning. With machine learning, many tasks which were previously thought to be only humanly doable are done by machine. Neural networks have two major subtypes i.e. Convolutional neural networks (CNN) which are used primarily for classification and Recurrent neural networks which are utilized for time-series predictions. In this paper, we predict energy generated by solar fields and optimal angles for solar panels in these farms for the upcoming seven days using environmental and historical data. We experiment with multiple configurations of RNN using Vanilla and LSTM (Long Short-Term Memory) RNN. We are able to achieve RSME of 0.20739 using LSTMs.

• 스마트미디어저널
• /
• 제6권3호
• /
• pp.41-48
• /
• 2017

Event detection using social media has been widespread since social network services have been an active communication channel for connecting with others, diffusing news message. Especially, the real-time characteristic of social media has created the opportunity for supporting for real-time applications/systems. Social network such as Twitter is the potential data source to explore useful information by mining messages posted by the user community. This paper proposed a novel system for temporal event detection by analyzing social data. As a result, this information can be used by first responders, decision makers, or news agents to gain insight of the situation. The proposed approach takes advantages of deep learning methods that play core techniques on the main tasks including informative data identifying from a noisy environment and temporal event detection. The former is the responsibility of Convolutional Neural Network model trained from labeled Twitter data. The latter is for event detection supported by Recurrent Neural Network module. We demonstrated our approach and experimental results on the case study of earthquake situations. Our system is more adaptive than other systems used traditional methods since deep learning enables to extract the features of data without spending lots of time constructing feature by hand. This benefit makes our approach adaptive to extend to a new context of practice. Moreover, the proposed system promised to respond to acceptable delay within several minutes that will helpful mean for supporting news channel agents or belief plan in case of disaster events.

• 한국멀티미디어학회논문지
• /
• 제25권2호
• /
• pp.440-449
• /
• 2022

In recent years, the air pollution and Air Quality Index (AQI) has been a pivotal point for researchers due to its effect on human health. Various research has been done in predicting the AQI but most of these studies, either lack dense temporal data or cover one or two air pollutant elements. In this paper, a hybrid Convolutional Neural approach integrated with recurrent neural network architecture (CNN-LSTM), is presented to find air pollution inference using a multivariate air pollutant elements dataset. The aim of this research is to design a robust and real-time air pollutant forecasting system by exploiting a neural network. The proposed approach is implemented on a 24-month dataset from Seoul, Republic of Korea. The predicted results are cross-validated with the real dataset and compared with the state-of-the-art techniques to evaluate its robustness and performance. The proposed model outperforms SVM, SVM-Polynomial, ANN, and RF models with 60.17%, 68.99%, 14.6%, and 6.29%, respectively. The model performs SVM and SVM-Polynomial in predicting O3 by 78.04% and 83.79%, respectively. Overall performance of the model is measured in terms of Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and the Root Mean Square Error (RMSE).

• Computers and Concrete
• /
• 제25권5호
• /
• pp.433-445
• /
• 2020

A method is proposed in this paper to estimate the workability of self-compacting concrete (SCC) in different mixing conditions with different mixers and mixing volumes by recording the mixing process based on deep learning (DL). The SCC mixing videos were transformed into a series of image sequences to fit the DL model to predict the SF and VF values of SCC, with four groups in total and approximately thirty thousand image sequence samples. The workability of three groups SCC whose mixing conditions were learned by the DL model, was estimated. One additionally collected group of the SCC whose mixing condition was not learned, was also predicted. The results indicate that whether the SCC mixing condition is included in the training set and learned by the model, the trained model can estimate SCC with different workability effectively at the same time. Our goal to estimate SCC workability in different mixing conditions is achieved.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2021년도 추계학술대회
• /
• pp.91-94
• /
• 2021

As deep learning technologies becoming developed, realistic fake videos synthesized by deep learning models called "Deepfake" videos became even more difficult to distinguish from original videos. As fake news or Deepfake blackmailing are causing confusion and serious problems, this paper suggests a novel model detecting Deepfake videos. We chose Residual Convolutional Neural Network (Resnet50) as an extraction model and Long Short-Term Memory (LSTM) which is a form of Recurrent Neural Network (RNN) as a classification model. We adopted cosine similarity with hinge loss to train our extraction model in embedding the features of Deepfake and original video. The result in this paper demonstrates that temporal features in the videos are essential for detecting Deepfake videos.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권9호
• /
• pp.3204-3220
• /
• 2021

We perform the task of video object segmentation by incorporating a conditional random field (CRF) and convolutional neural networks (CNNs). Most methods employ a CRF to refine a coarse output from fully convolutional networks. Others treat the inference process of the CRF as a recurrent neural network and then combine CNNs and the CRF into an end-to-end model for video object segmentation. In contrast to these methods, we propose a novel higher-order CRF model to solve the problem of video object segmentation. Specifically, we use CNNs to establish a higher-order dependence among pixels, and this dependence can provide critical global information for a segmentation model to enhance the global consistency of segmentation. In general, the optimization of the higher-order energy is extremely difficult. To make the problem tractable, we decompose the higher-order energy into two parts by utilizing auxiliary variables and then solve it by using an iterative process. We conduct quantitative and qualitative analyses on multiple datasets, and the proposed method achieves competitive results.

• 한국음향학회지
• /
• 제39권6호
• /
• pp.600-605
• /
• 2020

본 논문에서는 청각 장애인을 위한 소리 감지 홈 모니터링을 위해 다채널 다중 스케일 신경망을 사용한 사운드 이벤트 검출 방식을 제안한다. 제안하는 시스템에서는 홈 내의 여러 무선 마이크 센서들로부터 높은 신호 품질을 갖는 두 개의 채널을 선택하고, 그 신호들로부터 도착신호 지연시간, 피치 범위, 그리고 다중 스케일 합성 곱 신경망을 로그멜 스펙트로그램에 적용하여 추출한 특징들을 양방향 게이트 순환 신경망 기반의 분류기에 적용함으로써 사운드 이벤트 검출의 성능을 더욱 향상시킨다. 검출된 사운드 이벤트 결과는 선택된 채널의 센서 위치와 함께 텍스트로 변환되어 청각 장애인에게 제공된다. 실험결과는 제안한 시스템의 사운드 이벤트 검출 방식이 기존 방식보다 우수하며 청각 장애인에게 효과적으로 사운드 정보를 전달할 수 있음을 보인다.

• 디지털융복합연구
• /
• 제19권2호
• /
• pp.215-220
• /
• 2021

최근 국내 미세먼지 발생의 증가에 따라 발생하는 인체에 유해한 영향을 줄이기 위하여, 미세먼지 수치를 예측하고 사전 조치를 취할 수 있도록 돕는 기술이 필요해지고 있다. 본 논문에서는 국내 미세먼지 위험 수준을 예측하기 위한 1D Convolutional to Recurrent Neural Network (1-D CRNN) 모델을 제안한다. 제안 된 모델은 딥러닝 신경망의 CNN과 RNN을 결합한 구조이며, 다른 종류의 데이터로 구성된 시계열 데이터 세트에서 데이터 예측을 수행 할 수 있다. 데이터 예측을 위해 국내·외 미세먼지, 풍향, 풍속 데이터를 사용한다. 제안된 모델은 약 76%(부분 최대 84%)의 정확도를 달성했으며, 일반 RNN 모델(53%)보다 정확한 예측 결과를 얻었을 수 있었다. 제안된 모델은 향후 여러 개의 시계열 데이터 세트를 고려해야 하는 데이터 예측 모델 학습 및 실험을 목표로 한다.

• 한국전자통신학회논문지
• /
• 제16권3호
• /
• pp.401-406
• /
• 2021

최근 들어, 음향 이벤트 검출을 위하여 CRNN(: Convolutional Recurrent Neural Network) 구조에 기반 한 평균-교사 모델이 대표적으로 사용되고 있다. 평균-교사 모델은 두 개의 병렬 형태의 CRNN을 가진 구조이며, 이들의 출력들의 일치성을 학습 기준으로 사용함으로서 약-전사 레이블(label)과 비-전사 레이블 음향 데이터에 대해서도 효과적인 학습이 가능하다. 본 연구에서는 최신의 평균-교사 모델에 로그-멜 스펙트럼에 대한 차분 특징을 추가적으로 사용함으로서 보다 나은 성능을 이루고자 하였다. DCASE 2018/2019 Challenge Task 4용 학습 및 테스트 데이터를 이용한 음향 이벤트 검출 실험에서 제안된 차분특징을 이용한 평균-교사모델은 기존의 방식에 비해서 최대 8.1%의 상대적 ER(: Error Rate)의 향상을 얻을 수 있었다.