• Title/Summary/Keyword: Attention

Search Result 17,699, Processing Time 0.045 seconds

Deep Learning-based Super Resolution Method Using Combination of Channel Attention and Spatial Attention (채널 강조와 공간 강조의 결합을 이용한 딥 러닝 기반의 초해상도 방법)

  • Lee, Dong-Woo;Lee, Sang-Hun;Han, Hyun Ho
    • Journal of the Korea Convergence Society
    • /
    • v.11 no.12
    • /
    • pp.15-22
    • /
    • 2020
  • In this paper, we proposed a deep learning based super-resolution method that combines Channel Attention and Spatial Attention feature enhancement methods. It is important to restore high-frequency components, such as texture and features, that have large changes in surrounding pixels during super-resolution processing. We proposed a super-resolution method using feature enhancement that combines Channel Attention and Spatial Attention. The existing CNN (Convolutional Neural Network) based super-resolution method has difficulty in deep network learning and lacks emphasis on high frequency components, resulting in blurry contours and distortion. In order to solve the problem, we used an emphasis block that combines Channel Attention and Spatial Attention to which Skip Connection was applied, and a Residual Block. The emphasized feature map extracted by the method was extended through Sub-pixel Convolution to obtain the super resolution. As a result, about PSNR improved by 5%, SSIM improved by 3% compared with the conventional SRCNN, and by comparison with VDSR, about PSNR improved by 2% and SSIM improved by 1%.

Prediction of dam inflow based on LSTM-s2s model using luong attention (Attention 기법을 적용한 LSTM-s2s 모델 기반 댐유입량 예측 연구)

  • Lee, Jonghyeok;Choi, Suyeon;Kim, Yeonjoo
    • Journal of Korea Water Resources Association
    • /
    • v.55 no.7
    • /
    • pp.495-504
    • /
    • 2022
  • With the recent development of artificial intelligence, a Long Short-Term Memory (LSTM) model that is efficient with time-series analysis is being used to increase the accuracy of predicting the inflow of dams. In this study, we predict the inflow of the Soyang River dam, using the LSTM model with the Sequence-to-Sequence (LSTM-s2s) and attention mechanism (LSTM-s2s with attention) that can further improve the LSTM performance. Hourly inflow, temperature, and precipitation data from 2013 to 2020 were used to train the model, and validate and test for evaluating the performance of the models. As a result, the LSTM-s2s with attention showed better performance than the LSTM-s2s in general as well as in predicting a peak value. Both models captured the inflow pattern during the peaks but detailed hourly variability is limitedly simulated. We conclude that the proposed LSTM-s2s with attention can improve inflow forecasting despite its limits in hourly prediction.

Attention and Psychiatric Disorders (주의력과 정신장애)

  • Ha, Kyoo-Seob;Kang, Ung Gu;Kim, Jong-Hoon
    • Korean Journal of Biological Psychiatry
    • /
    • v.4 no.1
    • /
    • pp.19-23
    • /
    • 1997
  • Attention is a phenomenon hard to define, but can be conceptualized as a mental function ranging from sustaining readiness to perceive stimuli to understanding the nature and value and selecting stimuli that are most relevant to the given situation. Manifestations of attention include vigilance, and focused, directed, selective, divided, and sustained attentions. While basic attentional tone is controlled by the interaction among reticular activating system, thalamus and prefrontal cortex, direction and selection of attention is controlled by neural circuits of prefrontal, posterior parietal, and limbic cortex. It is expected that understanding of attention and its neural control could provide answers to the relationship between pathophysiology and clinical symptoms of some major psychiatric disorders. More efforts are required to develop tools to assess more detailed and various aspects of attention in Korea.

  • PDF

The effect of indoor temperature on occupants' attention abilities (실내 온도가 재실자의 주의집중력에 미치는 영향에 관한 연구)

  • Choi, Yoo-Rim;Chun, Chung-Yoon
    • Proceeding of Spring/Autumn Annual Conference of KHA
    • /
    • 2009.04a
    • /
    • pp.199-203
    • /
    • 2009
  • The purpose of this research is to investigate how the indoor temperature has influence on occupants' attention abilities as a basis of productivity. To achieve the purpose, the experiment in chamber was conducted. In the experiment, temperature was controlled according to two levels ($20^{\circ}C$ or $23^{\circ}C$) and other of factors were controlled uniformly. Subjects were exposed to those two different thermal environments. Each participant was asked to mark their answers on the state of attention measurement sheets (FAIR and Trail making test), in two conditions. Total 60 times of experiments were conducted. The main results are as follows. First, subjects showed the better attention abilities in relation to Q score at $20^{\circ}C$. But on the other hand attention abilities in relation to C score were better at $23^{\circ}C$. Second, subjects showed the better attention abilities in relation to concentrate on one task at $20^{\circ}C$.

  • PDF

Electroencephalogram Analysis on Learning Factors during Relaxed or Concentrated Attention according to the Color Temperatures of LED Illuminance (이완집중 및 긴장집중 시 LED 조명의 색온도에 따른 학습요인의 뇌파분석)

  • Jee, Soon-Duk;Kim, Chae-Bogk
    • Journal of the Korean Institute of Educational Facilities
    • /
    • v.21 no.6
    • /
    • pp.33-42
    • /
    • 2014
  • The objective of this study is to investigate learning factors (stability, attention and activation) in school by electroencephalogram (theta, alpha and beta waves) analysis during relaxed or concentrated. In order to measure electroencephalograms, MP 150 by Biopac and ECI Electro-Cap are employed. Three types of color temperatures (3000K, 5000K, 7000K) are used and 13 undergraduate and 12 graduate students are selected as experimental subjects. When subjects are relaxed during contemplation or concentrated during mental arithmetic, we compare with stability, attention and activation indices. The test results show that subjects were stable when color temperature is 5000K. Subjects gave best attention when color temperature is 7000K. Subjects activated well when color temperature is 3000K during relaxed attention. However, subjects activated rigorous when color temperature is 7000K during constrained attention.

Two-dimensional attention-based multi-input LSTM for time series prediction

  • Kim, Eun Been;Park, Jung Hoon;Lee, Yung-Seop;Lim, Changwon
    • Communications for Statistical Applications and Methods
    • /
    • v.28 no.1
    • /
    • pp.39-57
    • /
    • 2021
  • Time series prediction is an area of great interest to many people. Algorithms for time series prediction are widely used in many fields such as stock price, temperature, energy and weather forecast; in addtion, classical models as well as recurrent neural networks (RNNs) have been actively developed. After introducing the attention mechanism to neural network models, many new models with improved performance have been developed; in addition, models using attention twice have also recently been proposed, resulting in further performance improvements. In this paper, we consider time series prediction by introducing attention twice to an RNN model. The proposed model is a method that introduces H-attention and T-attention for output value and time step information to select useful information. We conduct experiments on stock price, temperature and energy data and confirm that the proposed model outperforms existing models.

Computer Vision System using the mechanisms of human visual attention (인간의 시각적 주의 능력을 이용한 컴퓨터 시각 시스템)

  • 최경주;이일병
    • Proceedings of the IEEK Conference
    • /
    • 2001.06d
    • /
    • pp.239-242
    • /
    • 2001
  • As systems for real time computer vision are confronted with prodigious amounts of visual information, it has become a priority to locate and analyze just that information essential to the task at hand, while ignoring the vast flow of irrelevant detail. A method of achieving this is to using human visual attention mechanism. In this paper, short review of human visual attention mechanisms and some computation models of visual attention were shown. This paper can be used as the basic data for researches on development of visual attention system that can perform various complex tasks more efficiently.

  • PDF

Stride Length Estimation Using LSTM-Attention (LSTM-Attention을 이용한 보폭 추정)

  • Tae, Min-Woo;Kang, Kyung-Hoon;Choi, Sang-Il
    • Proceedings of the Korean Society of Computer Information Conference
    • /
    • 2022.07a
    • /
    • pp.331-332
    • /
    • 2022
  • 본 논문에서는 3축 가속도와 3축 각속도 센서로 구성된 관성 측정 장치(IMU)와 압력센서가 내장되어있는 스마트 인솔을 착용하여 얻어진 보행 데이터를 통해 보폭을 추정하는 방법을 제안한다. 먼저 압력센서를 활용하여 한 걸음 주기로 나눈 뒤 나누어진 가속도와 각속도 센서 데이터를 LSTM과 Attention 계층을 결합한 딥러닝 모델에 학습하여 보폭 추정을 시행하였다. LSTM-Attention 모델은 기존 LSTM 모델보다 약 1.14%의 성능 향상을 보였다.

  • PDF

An Analysis of Elementary Students' Attention Characteristics through Attention Test and the Eye Tracking on Real Science Classes (실제 과학수업에서 시선추적과 주의력 검사를 통한 초등학생들의 주의 특성 분석)

  • Shin, Won-Sub;Shin, Dong-Hoon
    • Journal of The Korean Association For Science Education
    • /
    • v.36 no.4
    • /
    • pp.705-715
    • /
    • 2016
  • The purpose of this research is to analyze elementary students' attention characteristics through attention test and eye tracking on real science classes. The SMI's ETG(eye tracker glasses) mobile eye tracker was used to analyze the attention process of elementary students'. The sampling rate of the ETG is 30Hz. The participants of attention test were elementary 155 6th-grade elementary students and the participants for the eye-tracker were six 6th-grade male students. The eye movements were analyzed using the 'BeGaze Mobile Video Analysis Package' program. The results of this research are as follows. First, the attention test results of elementary students showed high correlation between selective attention and sustained attention (.85) and low correlation between selective attention and self-regulation (.32). Second, the attention types of elementary students were divided into four; attention, inattention, easygoing and hasty. Third, elementary students' attention were divided into top-down, bottom-up, default mode network through analysis of elementary students′ eye-movements during real science classes. Also their attention shift occurred frequently due to various reasons in real class situation. There were three reasons that made elementary students fail to handle knowledge-dependent top-down attention; 1) the cognitive failure of target caused by failing to focus attention, 2) the absence of prior knowledge on target object, 3) the analogical failure of prior knowledge. Finally, elementary students' attention process were schematized based on the analysis of students' eye movements and attention test. This research is expected to be utilized as basic data for developing effective teaching strategies, teaching-learning models and instructional materials.

Visual Attention Model Based on Particle Filter

  • Liu, Long;Wei, Wei;Li, Xianli;Pan, Yafeng;Song, Houbing
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.10 no.8
    • /
    • pp.3791-3805
    • /
    • 2016
  • The visual attention mechanism includes 2 attention models, the bottom-up (B-U) and the top-down (T-D), the physiology of which have not yet been accurately described. In this paper, the visual attention mechanism is regarded as a Bayesian fusion process, and a visual attention model based on particle filter is proposed. Under certain particular assumed conditions, a calculation formula of Bayesian posterior probability is deduced. The visual attention fusion process based on the particle filter is realized through importance sampling, particle weight updating, and resampling, and visual attention is finally determined by the particle distribution state. The test results of multigroup images show that the calculation result of this model has better subjective and objective effects than that of other models.