• 한국습지학회지
• /
• 제5권2호
• /
• pp.1-13
• /
• 2003

In Korea, most of the rainfalls have been concentrated in the flood season and the flood study has received more attention than low flow analysis. One of the reasons that the analysis of low flows has less attention is the lacks of the required data like daily rainfall and so we have used the stochastic processes such as pulse noise, exponential distribution, and state model of Markov chain for the rainfall simulation in short term such as daily. Especially this study will pay attention to the state model of Markov chain. The previous study had performed the simulation study by the state model without considerations of the flood and non-flood periods and without consideration of the frequency of rainfall for the period of a state. Therefore this study considers afore mentioned two cases and compares the results with the known state model. As the results, the RMSEs of the suggested and known models represent the similar results. However, the PRE(relative percentage error) shows the suggested model is better results.

• 한국음향학회지
• /
• 제42권6호
• /
• pp.544-551
• /
• 2023

잡음 음성의 지각적 품질과 명료도 향상을 위해 활용되는 음성 향상은 크기 스펙트럼을 이용한 방법에서 크기와 위상을 같이 향상시킬 수 있는 복소 스펙트럼을 이용한 방법으로 연구되어왔다. 본 논문에서는 잡음 음성의 명료도와 품질을 더욱 향상시키기 위해 복소 스펙트럼 기반 음성 향상 시스템에 어텐션 기법을 적용하는 방안에 관해 연구를 수행하였다. 어텐션 기법은 additive attention을 기반으로 수행하며 복소 스펙트럼의 특성을 고려하여 어텐션 가중치를 계산할 수 있도록 하였다. 또한 특징 맵의 중요도를 고려하기 위해 전역 평균 풀링 연산을 같이 사용하였다. 복소 스펙트럼 기반 음성 향상은 Deep Complex U-Net(DCUNET) 모델을 기반으로 수행하였으며, additive attention은 Attention U-Net 모델에서 제안된 방법을 기반으로 연구를 수행하였다. 거실 환경의 잡음 데이터에 대해 음성 향상을 수행한 결과, 제안한 방법이 Source to Distortion Ratio(SDR), Perceptual Evaluation of Speech Quality(PESQ), Short Time Objective Intelligibility(STOI) 평가 지표에서 기준 모델보다 개선된 성능을 보였으며, 낮은 Signal-to-Noise Ratio(SNR) 조건의 다양한 배경 잡음 환경에 대해서도 일관된 성능 향상을 보였다. 이를 통해 제안한 음성 향상 시스템이 효과적으로 잡음 음성의 명료도와 품질을 향상시킬 수 있음을 보여주었다.

• ETRI Journal
• /
• 제44권3호
• /
• pp.438-449
• /
• 2022

This study proposes a dependency grammar-based self-attention multilayered bidirectional long short-term memory (DG-M-Bi-LSTM) model for subject-predicate-object (SPO) tuple recognition from natural language (NL) sentences. To add recent knowledge to the knowledge base autonomously, it is essential to extract knowledge from numerous NL data. Therefore, this study proposes a high-accuracy SPO tuple recognition model that requires a small amount of learning data to extract knowledge from NL sentences. The accuracy of SPO tuple recognition using DG-M-Bi-LSTM is compared with that using NL-based self-attention multilayered bidirectional LSTM, DG-based bidirectional encoder representations from transformers (BERT), and NL-based BERT to evaluate its effectiveness. The DG-M-Bi-LSTM model achieves the best results in terms of recognition accuracy for extracting SPO tuples from NL sentences even if it has fewer deep neural network (DNN) parameters than BERT. In particular, its accuracy is better than that of BERT when the learning data are limited. Additionally, its pretrained DNN parameters can be applied to other domains because it learns the structural relations in NL sentences.

• 한국의류학회지
• /
• 제44권5호
• /
• pp.789-809
• /
• 2020

Growth in online channels has created fierce competition; consequently, retailers have to invest an increasing amount of effort into attracting consumers. In this study, eye-tracking technology examined consumers' visual behavior to gain an understanding of information searching behavior in exploring product information for fashion products. Product attribute information was classified into two image-based elements (model image information and detail image information) and two text-based elements (basic text information, detail text information), after which consumers' visual behavior for each information element was analyzed. Furthermore, whether involvement affects consumers' information search behavior was investigated. The results demonstrated that model image information attracted visual attention the quickest, while detail text information and model image information received the most visual attention. Additionally, high-involvement consumers tended to pay more attention to detailed information while low-involvement consumers tended to pay more attention to image-based and basic information. This study is expected to help broaden the understanding of consumer behavior and provide implications for establishing strategies on how to efficiently organize product information for online fashion stores.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권8호
• /
• pp.2552-2570
• /
• 2022

Underwater images usually have various problems, such as the color cast of underwater images due to the attenuation of different lights in water, the darkness of image caused by the lack of light underwater, and the haze effect of underwater images because of the scattering of light. To address the above problems, the channel attention mechanism, strengthen-operate-subtract (SOS) boosting mechanism and gated fusion module are introduced in our paper, based on which, an underwater image recovery network is proposed. First, for the color cast problem of underwater images, the channel attention mechanism is incorporated in our model, which can well alleviate the color cast of underwater images. Second, as for the darkness of underwater images, the similarity between the target underwater image after dehazing and color correcting, and the image output by our model is used as the loss function, so as to increase the brightness of the underwater image. Finally, we employ the SOS boosting module to eliminate the haze effect of underwater images. Moreover, experiments were carried out to evaluate the performance of our model. The qualitative analysis results show that our method can be applied to effectively recover the underwater images, which outperformed most methods for comparison according to various criteria in the quantitative analysis.

• 디지털콘텐츠학회 논문지
• /
• 제19권9호
• /
• pp.1819-1824
• /
• 2018

본 논문에서는 사용자의 스트레스 해소와 주의력 향상에 도움이 될 수 있는 ASMR(autonomous sensory meridian response) 콘텐츠 제어 기법을 제안한다. 제안된 기법은 뇌파 측정 디바이스로부터 EEG(electroencephalography), 집중도, 명상도, 눈 깜빡임 데이터를 측정하고 안드로이드 IoT(internet of things) 앱을 통해 oneM2M 표준을 준용한 IoT 서버 플랫폼으로 전송한다. 서버 플랫폼에 수집된 EEG, 집중도 및 명상도 데이터를 사용하여 사용자의 정신건강상태를 분류하기 위한 SVM(support vector machine) 모델을 생성하고, 이 모델을 통해 분류된 사용자의 정신건강상태와 눈 깜빡임 데이터에 따라 ASMR 콘텐츠를 제어한다. 데이터 사용형태에 따라 SVM 모델을 비교한 결과, 집중도와 명상도 데이터를 사용하는 SVM 모델이 85.7%의 정확도를 나타내었고 이 SVM 모델이 분류한 정신건강상태와 눈 깜빡임 데이터의 변화에 따라 ASMR 콘텐츠 제어 알고리즘이 정상적으로 동작하는 것을 확인하였다.

• 정보과학회 컴퓨팅의 실제 논문지
• /
• 제22권12호
• /
• pp.625-631
• /
• 2016

포인터 네트워크는 어텐션 메커니즘(Attention mechanism)을 기반으로 입력열에 대응되는 위치를 결과 리스트로 출력하는 모델이다. 포인터 네트워크를 수행할 때 입력열의 크기를 N이라고 하면, 각 입력에 대한 어텐션(attention)을 계산하기 때문에 시간복잡도는 $O(N^2)$이 되어 디코딩 시간이 길어진다. 이에 따라, 본 논문에서는 포인터 네트워크의 디코딩 시간을 줄이기 위하여 디코딩 시에 필요한 입력 정보만을 확인하는 스킵 포인팅 모델 기반 포인터 네트워크를 제안한다. 본 논문에서 제안한 방법을 이용하여 대명사 상호참조해결에 대한 실험을 수행한 결과, 일반 포인터 네트워크에 비하여 문장당 처리 시간이 약 1.15배 빠른 속도와, MUC F1 값이 약 2.17% 향상된 83.60%의 성능을 보였다.

• 한국음향학회지
• /
• 제39권2호
• /
• pp.137-142
• /
• 2020

문장 종속 짧은 발화에서 문장 독립 긴 발화까지 다양한 환경에서 I-vector 특징에 기반을 둔 많은 연구가 수행되었다. 본 논문에서는 원거리 잡음 환경에서 녹음한 데이터에서 Probabilistic Linear Discriminant Analysis(PLDA)를 적용한 I-vector와 주의 집중 기법을 접목한 Long Short Term Memory(LSTM) 기반의 화자 임베딩을 추출하여 결합한 화자 검증 알고리즘을 소개한다. LSTM 모델의 Equal Error Rate(EER)이 15.52 %, Attention-LSTM 모델이 8.46 %로 7.06 % 성능이 향상되었다. 이로써 본 논문에서 제안한 기법이 임베딩을 휴리스틱 하게 정의하여 사용하는 기존 추출방법의 문제점을 해결할 수 있는 것을 확인하였다. PLDA를 적용한 I-vector의 EER이 6.18 %로 결합 전 가장 좋은 성능을 보였다. Attention-LSTM 기반 임베딩과 결합하였을 때 EER이 2.57 %로 기존보다 3.61 % 감소하여 상대적으로 58.41 % 성능이 향상되었다.

• Asia pacific journal of information systems
• /
• 제30권4호
• /
• pp.719-740
• /
• 2020

The stock market changes continuously as new information emerges, affecting the judgments of investors. Online news articles are valued as a traditional window to inform investors about various information that affects the stock market. This paper proposed new ways to utilize online news articles with technical indicators. The suggested hybrid model consists of three models. First, a self-attention-based convolutional neural network (CNN) model, considered to be better in interpreting the semantics of long texts, uses news content as inputs. Second, a self-attention-based, bi-long short-term memory (bi-LSTM) neural network model for short texts utilizes news titles as inputs. Third, a bi-LSTM model, considered to be better in analyzing context information and time-series models, uses 19 technical indicators as inputs. We used news articles from the previous day and technical indicators from the past seven days to predict the share price of the next day. An experiment was performed with Korean stock market data and news articles from 33 top companies over three years. Through this experiment, our proposed model showed better performance than previous approaches, which have mainly focused on news titles. This paper demonstrated that news titles and content should be treated in different ways for superior stock price prediction.

• Journal of Information Processing Systems
• /
• 제19권4호
• /
• pp.427-438
• /
• 2023

Plenty of works have indicated that single image super-resolution (SISR) models relying on synthetic datasets are difficult to be applied to real scene text image super-resolution (STISR) for its more complex degradation. The up-to-date dataset for realistic STISR is called TextZoom, while the current methods trained on this dataset have not considered the effect of multi-scale features of text images. In this paper, a multi-scale and attention fusion model for realistic STISR is proposed. The multi-scale learning mechanism is introduced to acquire sophisticated feature representations of text images; The spatial and channel attentions are introduced to capture the local information and inter-channel interaction information of text images; At last, this paper designs a multi-scale residual attention module by skillfully fusing multi-scale learning and attention mechanisms. The experiments on TextZoom demonstrate that the model proposed increases scene text recognition's (ASTER) average recognition accuracy by 1.2% compared to text super-resolution network.