scholarly journals Populational Super-Resolution Sparse M/EEG Sources and Connectivity Estimation

2018 ◽  
Author(s):  
E. Gonzalez-Moreira ◽  
D. Paz-Linares ◽  
E. Martinez-Montes ◽  
P. Valdes-Hernandez ◽  
Jorge Bosch-Bayard ◽  
...  
Keyword(s):  
Frequency Domain ◽  
Graphical Model ◽  
State Of The Art ◽  
Super Resolution ◽  
Inverse Solution ◽  
Joint Estimation ◽  
Stationary Time Series ◽  
Simulation Framework ◽  
Identification Approach ◽  
Inverse Crime

SUMMARYIn this paper, we describe a novel methodology, BC-VARETA, for estimating the Inverse Solution (sources activity) and its Precision Matrix (connectivity parameters) in the frequency domain representation of Stationary Time Series. The aims of this method are three. First: Joint estimation of Source Activity and Connectivity as a frequency domain linear dynamical system identification approach. Second: Achieve super high resolution in the connectivity estimation through Sparse Hermitian Sources Graphical Model. Third: To be a populational approach, preventing the Inverse Solution and Connectivity statistical analysis across subjects as a postprocessing, by modeling population features of Source Activity and Connectivity. Our claims are supported by a wide simulation framework using realistic head models, realistic Sources Setup, and Inverse Crime effects evaluation. Also, a fair quantitative analysis is performed, based on a diversification of quality measures on which state of the art Inverse Solvers were tested.

A State-of-the-art Elliptic Curve Cryptographic Processor Operating in the Frequency Domain

2007 ◽  
Vol 12 (4) ◽  
pp. 259-270 ◽  
Author(s):  
Selçuk Baktır ◽  
Sandeep Kumar ◽  
Christof Paar ◽  
Berk Sunar
Keyword(s):  
Elliptic Curve ◽  
Frequency Domain ◽  
State Of The Art

scholarly journals Fast Estimation Method of Space-Time Two-Dimensional Positioning Parameters Based on Hadamard Product

2018 ◽  
Vol 2018 ◽  
pp. 1-9 ◽  
Author(s):  
Haiwen Li ◽  
Nae Zheng ◽  
Xiyu Song ◽  
Yinghua Tian
Keyword(s):  
Frequency Domain ◽  
Orthogonal Frequency Division Multiplexing ◽  
Hadamard Product ◽  
Estimation Method ◽  
Space Time ◽  
Joint Estimation ◽  
Two Dimensional ◽  
Music Algorithm ◽  
Fast Estimation ◽  
Response Vector

The estimation speed of positioning parameters determines the effectiveness of the positioning system. The time of arrival (TOA) and direction of arrival (DOA) parameters can be estimated by the space-time two-dimensional multiple signal classification (2D-MUSIC) algorithm for array antenna. However, this algorithm needs much time to complete the two-dimensional pseudo spectral peak search, which makes it difficult to apply in practice. Aiming at solving this problem, a fast estimation method of space-time two-dimensional positioning parameters based on Hadamard product is proposed in orthogonal frequency division multiplexing (OFDM) system, and the Cramer-Rao bound (CRB) is also presented. Firstly, according to the channel frequency domain response vector of each array, the channel frequency domain estimation vector is constructed using the Hadamard product form containing location information. Then, the autocorrelation matrix of the channel response vector for the extended array element in frequency domain and the noise subspace are calculated successively. Finally, by combining the closed-form solution and parameter pairing, the fast joint estimation for time delay and arrival direction is accomplished. The theoretical analysis and simulation results show that the proposed algorithm can significantly reduce the computational complexity and guarantee that the estimation accuracy is not only better than estimating signal parameters via rotational invariance techniques (ESPRIT) algorithm and 2D matrix pencil (MP) algorithm but also close to 2D-MUSIC algorithm. Moreover, the proposed algorithm also has certain adaptability to multipath environment and effectively improves the ability of fast acquisition of location parameters.

EDPANs: Enhanced Dual Path Attention Networks for Single Image Super-Resolution

2021 ◽  
pp. 2150300
Author(s):  
Guoan Cheng ◽  
Ai Matsune ◽  
Huaijuan Zang ◽  
Toru Kurihara ◽  
Shu Zhan
Keyword(s):  
State Of The Art ◽  
Super Resolution ◽  
Single Image ◽  
Residual Network ◽  
Dense Structure ◽  
Attention Networks ◽  
Residual Structure ◽  
Quantitative Results ◽  
Image Super Resolution ◽  
Single Image Super Resolution

In this paper, we propose an enhanced dual path attention network (EDPAN) for image super-resolution. ResNet is good at implicitly reusing extracted features, DenseNet is good at exploring new features. Dual Path Network (DPN) combines ResNets and DenseNet to create a more accurate architecture than the straightforward one. We experimentally show that the residual network performs best when each block consists of two convolutions, and the dense network performs best when each micro-block consists of one convolution. Following these ideas, our EDPAN exploits the advantages of the residual structure and the dense structure. Besides, to deploy the computations for features more effectively, we introduce the attention mechanism into our EDPAN. Moreover, to relieve the parameters burden, we also utilize recursive learning to propose a lightweight model. In the experiments, we demonstrate the effectiveness and robustness of our proposed EDPAN on different degradation situations. The quantitative results and visualization comparison can sufficiently indicate that our EDPAN achieves favorable performance over the state-of-the-art frameworks.

scholarly journals Multi-Channel Convolutional Neural Networks Architecture Feeding for Effective EEG Mental Tasks Classification

Sensors ◽  
2018 ◽  
Vol 18 (10) ◽  
pp. 3451 ◽  
Author(s):  
Sławomir Opałka ◽  
Bartłomiej Stasiak ◽  
Dominik Szajerman ◽  
Adam Wojciechowski
Keyword(s):  
Neural Network ◽  
Frequency Domain ◽  
Classification Accuracy ◽  
State Of The Art ◽  
Parameters Optimization ◽  
Alternative Methods ◽  
Signal Frequency ◽  
Eeg Signal ◽  
Mental Tasks Classification ◽  
Mental Tasks

Mental tasks classification is increasingly recognized as a major challenge in the field of EEG signal processing and analysis. State-of-the-art approaches face the issue of spatially unstable structure of highly noised EEG signals. To address this problem, this paper presents a multi-channel convolutional neural network architecture with adaptively optimized parameters. Our solution outperforms alternative methods in terms of classification accuracy of mental tasks (imagination of hand movements and speech sounds generation) while providing high generalization capability (∼5%). Classification efficiency was obtained by using a frequency-domain multi-channel neural network feeding scheme by EEG signal frequency sub-bands analysis and architecture supporting feature mapping with two subsequent convolutional layers terminated with a fully connected layer. For dataset V from BCI Competition III, the method achieved an average classification accuracy level of nearly 70%, outperforming alternative methods. The solution presented applies a frequency domain for input data processed by a multi-channel architecture that isolates frequency sub-bands in time windows, which enables multi-class signal classification that is highly generalizable and more accurate (∼1.2%) than the existing solutions. Such an approach, combined with an appropriate learning strategy and parameters optimization, adapted to signal characteristics, outperforms reference single- or multi-channel networks, such as AlexNet, VGG-16 and Cecotti’s multi-channel NN. With the classification accuracy improvement of 1.2%, our solution is a clear advance as compared to the top three state-of-the-art methods, which achieved the result of no more than 0.3%.

scholarly journals Mosaic Super-resolution via Sequential Feature Pyramid Networks

2019 ◽  
Author(s):  
Mehrdad Shoeiby ◽  
Mohammad Ali Armin ◽  
Sadegh Aliakbarian ◽  
Saeed Anwar ◽  
Lars petersson
Keyword(s):  
State Of The Art ◽  
Super Resolution ◽  
Autonomous Driving ◽  
Single Shot ◽  
Current State ◽  
Wide Range ◽  
Feature Pyramid ◽  
Novel Method ◽  
Convolutional Lstm ◽  
Mosaic Images

<div>Advances in the design of multi-spectral cameras have</div><div>led to great interests in a wide range of applications, from</div><div>astronomy to autonomous driving. However, such cameras</div><div>inherently suffer from a trade-off between the spatial and</div><div>spectral resolution. In this paper, we propose to address</div><div>this limitation by introducing a novel method to carry out</div><div>super-resolution on raw mosaic images, multi-spectral or</div><div>RGB Bayer, captured by modern real-time single-shot mo-</div><div>saic sensors. To this end, we design a deep super-resolution</div><div>architecture that benefits from a sequential feature pyramid</div><div>along the depth of the network. This, in fact, is achieved</div><div>by utilizing a convolutional LSTM (ConvLSTM) to learn the</div><div>inter-dependencies between features at different receptive</div><div>fields. Additionally, by investigating the effect of different</div><div>attention mechanisms in our framework, we show that a</div><div>ConvLSTM inspired module is able to provide superior at-</div><div>tention in our context. Our extensive experiments and anal-</div><div>yses evidence that our approach yields significant super-</div><div>resolution quality, outperforming current state-of-the-art</div><div>mosaic super-resolution methods on both Bayer and multi-</div><div>spectral images. Additionally, to the best of our knowledge,</div><div>our method is the first specialized method to super-resolve</div><div>mosaic images, whether it be multi-spectral or Bayer.</div><div><br></div>

Frequency domain based super-resolution method for mixed-resolution multi-view images

2016 ◽  
Vol 27 (6) ◽  
pp. 1303-1314 ◽  
Author(s):  
Zhizhong Fu ◽  
◽  
Yawei Li ◽  
Yuan Li ◽  
Lan Ding ◽  
...  
Keyword(s):  
Frequency Domain ◽  
Super Resolution ◽  
Resolution Method ◽  
Mixed Resolution

scholarly journals Transferred Multi-Perception Attention Networks for Remote Sensing Image Super-Resolution

2019 ◽  
Vol 11 (23) ◽  
pp. 2857 ◽  
Author(s):  
Xiaoyu Dong ◽  
Zhihong Xi ◽  
Xu Sun ◽  
Lianru Gao
Keyword(s):  
Remote Sensing ◽  
Learning Strategy ◽  
State Of The Art ◽  
Spatial Scales ◽  
Super Resolution ◽  
Natural Image ◽  
Training Procedure ◽  
Remote Sensing Images ◽  
Objective Criterion ◽  
Image Super Resolution

Image super-resolution (SR) reconstruction plays a key role in coping with the increasing demand on remote sensing imaging applications with high spatial resolution requirements. Though many SR methods have been proposed over the last few years, further research is needed to improve SR processes with regard to the complex spatial distribution of the remote sensing images and the diverse spatial scales of ground objects. In this paper, a novel multi-perception attention network (MPSR) is developed with performance exceeding those of many existing state-of-the-art models. By incorporating the proposed enhanced residual block (ERB) and residual channel attention group (RCAG), MPSR can super-resolve low-resolution remote sensing images via multi-perception learning and multi-level information adaptive weighted fusion. Moreover, a pre-train and transfer learning strategy is introduced, which improved the SR performance and stabilized the training procedure. Experimental comparisons are conducted using 13 state-of-the-art methods over a remote sensing dataset and benchmark natural image sets. The proposed model proved its excellence in both objective criterion and subjective perspective.

Sign in / Sign up

Export Citation Format

Share Document