• Investigative Magnetic Resonance Imaging
• /
• v.21 no.4
• /
• pp.199-209
• /
• 2017

Purpose: Caffeine is the most widely consumed psychostimulant. It is often adopted as a tool to modulate brain activations in fMRI studies. However, its pharmaceutical effect on task-induced deactivation has not been fully examined in fMRI. Therefore, the purpose of this study was to examine the effect of caffeine on both activation and deactivation under sustained attention. Materials and Methods: Task fMRI was acquired from 26 caffeine naive healthy volunteers before and after taking caffeine pill (200 mg). Results: Statistical analysis showed an increase in cognition-load dependent task activation but a decrease in load dependent de-activation after caffeine ingestion. Increase of attention and memory task activation and its load-dependence suggest a beneficial effect of caffeine on the brain even though it has no overt behavior improvement. The reduction of deactivation by caffeine and its load-dependence indicate reduced facilitation from task-negative networks. Conclusion: Caffeine affects brain activity in a load-dependent manner accompanied by a disassociation between task-positive network and task-negative network.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.5
• /
• pp.483-489
• /
• 2020

This paper proposes acoustic model training using self-attention for low-resource speech recognition. In low-resource speech recognition, it is difficult for acoustic model to distinguish certain phones. For example, plosive /d/ and /t/, plosive /g/ and /k/ and affricate /z/ and /ch/. In acoustic model training, the self-attention generates attention weights from the deep neural network model. In this study, these weights handle the similar pronunciation error for low-resource speech recognition. When the proposed method was applied to Time Delay Neural Network-Output gate Projected Gated Recurrent Unit (TNDD-OPGRU)-based acoustic model, the proposed model showed a 5.98 % word error rate. It shows absolute improvement of 0.74 % compared with TDNN-OPGRU model.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.11
• /
• pp.1477-1485
• /
• 2021

Recently, super-resolution has been intensively studied only on upscaling models with integer magnification. However, the need to expand arbitrary magnification is emerging in representative application fields of actual super-resolution, such as object recognition and display image quality improvement. In this paper, we propose a model that can support arbitrary magnification by using the weights of the existing integer magnification model. This model converts super-resolution results into the DCT spectral domain to expand the space for arbitrary magnification. To reduce the loss of high-frequency information in the image caused by the expansion by the DCT spectral domain, we propose a high-frequency attention network for arbitrary magnification so that this model can properly restore high-frequency spectral information. To recover high-frequency information properly, the proposed network utilizes channel attention layers. This layer can learn correlations between RGB channels, and it can deepen the model through residual structures.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.6
• /
• pp.2115-2127
• /
• 2021

Although significant progress has been made in synthesizing visually realistic face images by Generative Adversarial Networks (GANs), there still lacks effective approaches to provide fine-grained control over the generation process for semantic facial attribute editing. In this work, we propose a novel cross channel self-attention based generative adversarial network (CCA-GAN), which weights the importance of multiple channels of features and archives pixel-level feature alignment and conversion, to reduce the impact on irrelevant attributes while editing the target attributes. Evaluation results show that CCA-GAN outperforms state-of-the-art models on the CelebA dataset, reducing Fréchet Inception Distance (FID) and Kernel Inception Distance (KID) by 15~28% and 25~100%, respectively. Furthermore, visualization of generated samples confirms the effect of disentanglement of the proposed model.

• International Journal of Computer Science & Network Security
• /
• v.22 no.10
• /
• pp.413-422
• /
• 2022

The present study aimed to investigate the extent to which ordinary classrooms teachers are informed are familiar with Attention Deficit Hyperactivity Disorder 'ADHD'. The researcher adopted the descriptive approach. The sample of the study consisted of (89) male and female teachers who teach students from grade (1) to grade (6) at public primary schools in Northern Mazar Directorate of Education in Jordan. A questionnaire was employed as the primary tool for collecting the data. The findings of the current study indicated an average level of knowledge of ordinary classroom teachers about ADHD. The findings also indicated that there were no statistically significant differences in the extent of ordinary classroom teachers' knowledge of ADHD due to the variables (gender, qualification, professional experience, grade level being taught).

• 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.

• International Journal of Computer Science & Network Security
• /
• v.22 no.11
• /
• pp.127-136
• /
• 2022

The present study aimed to investigate the extent to which ordinary classrooms teachers are informed are familiar with Attention Deficit Hyperactivity Disorder 'ADHD'. The researcher adopted the descriptive approach. The sample of the study consisted of (89) male and female teachers who teach students from grade (1) to grade (6) at public primary schools in Northern Mazar Directorate of Education in Jordan. A questionnaire was employed as the primary tool for collecting the data. The findings of the current study indicated an average level of knowledge of ordinary classroom teachers about ADHD. The findings also indicated that there were no statistically significant differences in the extent of ordinary classroom teachers' knowledge of ADHD due to the variables (gender, qualification, professional experience, grade level being taught).

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.28-31
• /
• 2021

전세계적으로 우울증은 정신 건강 질환으로써 문제가 되고 있으며, 이를 해결하기 위해 일상생활에서의 우울증 탐지에 대한 연구가 진행되고 있다. 따라서 본 논문에서는 일상생활에 밀접하게 연관되어 있는 AI 스피커를 사용한 어텐션 메커니즘(Attention Mechanism) 기반 멀티모달 우울증 감지 시스템을 제안한다. 제안된 방법은 AI 스피커로부터 수집할 수 있는 음성 및 텍스트 데이터를 수집하고 CNN(Convolutional Neural Network)과 BiLSTM(Bidirectional Long Short-Term Memory Network)를 통해 각 데이터에서의 학습을 진행한다. 학습과정에서 Self-Attention 을 적용하여 특징 벡터에 추가적인 가중치를 부여하는 어텐션 메커니즘을 사용한다. 최종적으로 음성 및 텍스트 데이터에서 어텐션 가중치가 추가된 특징들을 합하여 SoftMax 를 통해 우울증 점수를 예측한다.

• Journal of Broadcast Engineering
• /
• v.25 no.1
• /
• pp.1-12
• /
• 2020

In the medical field, numerical imbalance of data due to differences in disease prevalence is a common problem. It reduces the performance of a artificial intelligence network, leading to difficulties in learning a network with good performance. Recently, generative adversarial network (GAN) technology has been introduced as a way to address this problem, and its ability has been demonstrated by successful applications in various fields. However, it is still difficult to achieve good results in solving problems with performance degraded by numerical imbalances because the image resolution of the previous studies is not yet good enough and the structure in the image is modeled locally. In this paper, we propose a multi-scale conditional generative adversarial network based on attention mechanism, which can produce high resolution images to solve the numerical imbalance problem of chest X-ray image data. The network was able to produce images for various diseases by controlling condition variables with only one network. It's efficient and effective in that the network don't need to be learned independently for all disease classes and solves the problem of long distance dependency in image generation with self-attention mechanism.

• ETRI Journal
• /
• v.43 no.5
• /
• pp.775-786
• /
• 2021

To translate in real time, a simultaneous translation system should determine when to stop reading source tokens and generate target tokens corresponding to a partial source sentence read up to that point. However, conventional attention-based neural machine translation (NMT) models cannot produce translations with adequate latency in online scenarios because they wait until a source sentence is completed to compute alignment between the source and target tokens. To address this issue, we propose a reinforced learning (RL)-based attention mechanism, the reinforced attention mechanism, which allows a neural translation model to jointly train the stopping criterion and a partial translation model. The proposed attention mechanism comprises two modules, one to ensure translation quality and the other to address latency. Different from previous RL-based simultaneous translation systems, which learn the stopping criterion from a fixed NMT model, the modules can be trained jointly with a novel reward function. In our experiments, the proposed model has better translation quality and comparable latency compared to previous models.