• Journal of Information Processing Systems
• /
• 제18권6호
• /
• pp.794-802
• /
• 2022

The recovery of reasonable depth information from different scenes is a popular topic in the field of computer vision. For generating depth maps with better details, we present an efficacious monocular depth prediction framework with coordinate attention and feature fusion. Specifically, the proposed framework contains attention, multi-scale and feature fusion modules. The attention module improves features based on coordinate attention to enhance the predicted effect, whereas the multi-scale module integrates useful low- and high-level contextual features with higher resolution. Moreover, we developed a feature fusion module to combine the heterogeneous features to generate high-quality depth outputs. We also designed a hybrid loss function that measures prediction errors from the perspective of depth and scale-invariant gradients, which contribute to preserving rich details. We conducted the experiments on public RGBD datasets, and the evaluation results show that the proposed scheme can considerably enhance the accuracy of depth prediction, achieving 0.051 for log10 and 0.992 for δ<1.25³ on the NYUv2 dataset.

• 한국산업정보학회논문지
• /
• 제20권2호
• /
• pp.1-9
• /
• 2015

데이터 스트림 마이닝에서 대부분의 정보 중요성 차별화 기법들은 오래된 정보에 비해 최근에 발생한 정보에 보다 큰 가중치를 부여한다. 하지만, 오래 전에 발생한 정보 중에도 매우 중요한 의미를 갖는 정보들이 존재하기도 한다. 예를 들어, 도소매 상점에서 과거에는 단골 고객이었으나 일정 기간 동안 방문하지 않은 경우, 해당 고객의 구매 기록 등이 포함된 오래된 정보들은 집중 마케팅을 통한 판매실적 증대에 매우 중요한 자료가 될 수 있다. 본 논문에서는 하나의 데이터 스트림에서 최근에는 자주 발생되지 않으나 과거에 빈번히 발생했던 것으로서 관심도가 큰 항목집합을 의미하는 고관심 정보 HAI(Highly Attention Itemsets)를 정의하고, 이를 효율적으로 탐색하기 위한 양방향 감쇠 기법 및 데이터 스트림 마이닝 기법을 제안한다.

• 인지과학
• /
• 제10권3호
• /
• pp.1-15
• /
• 1999

시각적 선택에 대한 과거 정신물리학적, 신경 생리학적 연구결과를 토대로 Feature Gate 라는 신경 망 모형을 제안하였다. 이 모형에는 공간 배치도가 위계 적으로 구성되어 있으며, 정보의 흐름이 위계의 각 수준으로부터 그 다음 수준으로 넘어갈 때 주의 게이트에 의해 조절되도록 되어 있다. 주의 게이트들은 독특한 세부 특징을 가진 위치에 반응하는 상향식 시스템과 표적 세부 특징이 있는 위치에 반응하는 하향식 기제 모두에 의해 조절된다. 본 연구는 Feature Gate 모형의 하향식 기제에 초점을 맞추어 모형을 설명하고, 현재 다른 모형들이 설명하지 못하는 Moran & Desimone(1985)의 연구결과를 이 모형이 어떻게 설명하는지를 제시하고자 한다. Feature Gate 모형은 병렬 적인 세부특징 검색, 계열 적 접합표적 검색, 단서에 의한 주의의 점진적 감소 모형, 세부특징-주도적인 공간적 선택, 주의의 분할, 방해자극 위치의 억제, 주변 억제 등을 포함한 시각적 주의 연구의 여러 가지 많은 현상들을 설명하는데 하나의 일관적인 해석을 제공해 준다. 앞으로 이 모형을 더욱 확장, 발전 시켜 세부특징의 조합된 배열에 반응하는 상위 수준의 유닛을 사용한다면 시각적 선택과정이 포함된 형태 재인 모형으로 개발될 수 있다.

• 한국음향학회지
• /
• 제41권5호
• /
• pp.518-524
• /
• 2022

본 논문에서는 합성곱 신경망과 주의집중 메커니즘을 결합하여 뇌파 신호로부터 감정적 스트레스 인식 성능을 향상시키는 방식을 제안한다. 제안하는 방식에서는 뇌파 신호를 5개의 주파수 영역으로 분해하고, 각 주파수 영역에 합성곱 신경망 계층을 사용하여 뇌파 특징의 공간정보를 획득한 후에 게이트 트랜스포머를 이용한 주의집중 메커니즘을 사용하여 각 주파수 대역에서 두드러진 주파수 정보를 학습하고, 주파수 간 대역 매핑을 통해 보완 주파수 정보를 학습하여 최종 주의집중 표현에 반영한다. DEAP 데이터세트와 6명의 피 실험자가 참여한 뇌파 스트레스 인식 실험을 통해, 제안된 방식이 기존 방식과 비교하여 뇌파 기반 스트레스 인식 성능 향상에 효과가 있음을 보여준다.

• Current Optics and Photonics
• /
• 제7권3호
• /
• pp.237-247
• /
• 2023

In middle- and long-distance imaging systems, due to the atmospheric turbulence caused by temperature, wind speed, humidity, and so on, light waves propagating in the air are distorted, resulting in image-quality degradation such as geometric deformation and fuzziness. In remote sensing, astronomical observation, and traffic monitoring, image information loss due to degradation causes huge losses, so effective restoration of degraded images is very important. To restore images degraded by atmospheric turbulence, an image-restoration method based on improved compound multibranch feature fusion (CMFNetPro) was proposed. Based on the CMFNet network, an efficient channel-attention mechanism was used to replace the channel-attention mechanism to improve image quality and network efficiency. In the experiment, two-dimensional random distortion vector fields were used to construct two turbulent datasets with different degrees of distortion, based on the Google Landmarks Dataset v2 dataset. The experimental results showed that compared to the CMFNet, DeblurGAN-v2, and MIMO-UNet models, the proposed CMFNetPro network achieves better performance in both quality and training cost of turbulent-image restoration. In the mixed training, CMFNetPro was 1.2391 dB (weak turbulence), 0.8602 dB (strong turbulence) respectively higher in terms of peak signal-to-noise ratio and 0.0015 (weak turbulence), 0.0136 (strong turbulence) respectively higher in terms of structure similarity compared to CMFNet. CMFNetPro was 14.4 hours faster compared to the CMFNet. This provides a feasible scheme for turbulent-image restoration based on deep learning.

• ETRI Journal
• /
• 제43권6호
• /
• pp.1081-1092
• /
• 2021

Electroencephalography (EEG) recordings taken during the perception of music tempo contain information that estimates the tempo of a music piece. If information about this tempo stimulus in EEG recordings can be extracted and classified, it can be effectively used to construct a music-based brain-computer interface. This study proposes a novel convolutional recurrent attention model (CRAM) to extract and classify features corresponding to tempo stimuli from EEG recordings of listeners who listened with concentration to the tempo of musics. The proposed CRAM is composed of six modules, namely, network inputs, two-dimensional convolutional bidirectional gated recurrent unit-based sample encoder, sample-level intuitive attention, segment encoder, segment-level intuitive attention, and softmax layer, to effectively model spatiotemporal features and improve the classification accuracy of tempo stimuli. To evaluate the proposed method's performance, we conducted experiments on two benchmark datasets. The proposed method achieves promising results, outperforming recent methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권3호
• /
• pp.721-739
• /
• 2023

Rating prediction is an important issue in recommender systems, and its accuracy affects the experience of the user and the revenue of the company. Traditional recommender systems use Factorization Machinesfor rating predictions and each feature is selected with the same weight. Thus, there are problems with inaccurate ratings and limited data representation. This study proposes a deep recommendation model based on self-attention Factorization (SAFMR) to solve these problems. This model uses Convolutional Neural Networks to extract features from user and item reviews. The obtained features are fed into self-attention mechanism Factorization Machines, where the self-attention network automatically learns the dependencies of the features and distinguishes the weights of the different features, thereby reducing the prediction error. The model was experimentally evaluated using six classes of dataset. We compared MSE, NDCG and time for several real datasets. The experiment demonstrated that the SAFMR model achieved excellent rating prediction results and recommendation correlations, thereby verifying the effectiveness of the model.

• The Korean Journal of Ceramics
• /
• 제5권1호
• /
• pp.35-39
• /
• 1999

For many years, alkali activated blast furnace slag cement containing no ordinary portland cement has received much attention in the view of energy saving and its many excellent properties. We examined the structural change of slag glass which was activated by alkali metal compounds using IR spectroscopy. The properties of hydrated products and unhydrated slag grains was characterized by XRD and micro-conduction calorimeter. Ion concentration change in the liquid during the hydration of blast furnace slag was also studied to investigated the hydration mechanism.

• 한국군사과학기술학회지
• /
• 제25권3호
• /
• pp.219-230
• /
• 2022

In implementing a robust automatic target recognition(ATR) system with synthetic aperture radar(SAR) imagery, one of the most important issues is accurate classification of target variants, which are the same targets with different serial numbers, configurations and versions, etc. In this paper, a deep learning network with channel attention modules is proposed to cope with the recognition problem for target variants based on the previous research findings that the channel attention mechanism selectively emphasizes the useful features for target recognition. Different from other existing attention methods, this paper employs the channel attention modules without dimensionality reduction along the channel direction from which direct correspondence between feature map channels can be preserved and the features valuable for recognizing SAR target variants can be effectively derived. Experiments with the public benchmark dataset demonstrate that the proposed scheme is superior to the network with other existing channel attention modules.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권2호
• /
• pp.486-503
• /
• 2023

Logs play an important role in mastering the health of the system, experienced operation and maintenance engineer can judge which part of the system has a problem by checking the logs. In recent years, many system architectures have changed from single application to distributed application, which leads to a very huge number of logs in the system and manually check the logs to find system errors impractically. To solve the above problems, we propose a method based on Message Middleware and ATT-GRU (Attention Gate Recurrent Unit) to detect the logs anomaly of distributed systems. The works of this paper mainly include two aspects: (1) We design a high-performance distributed logs collection architecture to complete the logs collection of the distributed system. (2)We improve the existing GRU by introducing the attention mechanism to weight the key parts of the logs sequence, which can improve the training efficiency and recognition accuracy of the model to a certain extent. The results of experiments show that our method has better superiority and reliability.