Multi-channel fusion convolutional neural network to classify syntactic anomaly from language-related ERP components

Khan, Aisha Urooj; Sung, Jee Eun; Kang, Je Won

doi:10.1016/j.inffus.2018.10.008

Cited by 20 publications

(12 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We connect the convolution layer to the deconvolution layer to effectively deliver the trained features in the lower layers to the higher layers, motivated by the symmetric U-net structure [20] and the skip connection. The skip connection is known to improve overall performance with slight increments of computational complexity [19].…”

Section: Proposed Crack Detection Networkmentioning

confidence: 99%

“…We use a two-branched CNN architecture to efficiently distinguish the relevant crack and the other components such as noise and edge-like image components on the concrete surfaces. The intuition behind the proposed model is to use noise-suppression and region detection, inspired by old wisdom on conventional edge detection methods and multi-channel network architecture [18,19]. Specifically, a branch of the proposed network is to detect edge or contours that are considered as the most prominent components in cracks, and the other branch is to identify a region-of-interest as in semantic segmentation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Learning to Detect Cracks on Damaged Concrete Surfaces Using Two-Branched Convolutional Neural Network

Lee

Kim

et al. 2019

Sensors

Self Cite

View full text Add to dashboard Cite

Image sensors are widely used for detecting cracks on concrete surfaces to help proactive and timely management of concrete structures. However, it is a challenging task to reliably detect cracks on damaged surfaces in the real world due to noise and undesired artifacts. In this paper, we propose an autonomous crack detection algorithm based on convolutional neural network (CNN) to solve the problem. To this aim, the proposed algorithm uses a two-branched CNN architecture, consisting of sub-networks named a crack-component-aware (CCA) network and a crack-region-aware (CRA) network. The CCA network is to learn gradient component regarding cracks, and the CRA network is to learn a region-of-interest by distinguishing critical cracks and noise such as scratches. Specifically, the two sub-networks are built on convolution-deconvolution CNN architectures, but also they are comprised of different functional components to achieve their own goals efficiently. The two sub-networks are trained in an end-to-end to jointly optimize parameters and produce the final output of localizing important cracks. Various crack image samples and learning methods are used for efficiently training the proposed network. In the experimental results, the proposed algorithm provides better performance in the crack detection than the conventional algorithms.

show abstract

Section: Proposed Crack Detection Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Learning to Detect Cracks on Damaged Concrete Surfaces Using Two-Branched Convolutional Neural Network

Lee

Kim

et al. 2019

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Ensemble methods has been widely used for classification tasks due to the generalization capability [36], [37]. Thus, there is no wonder why the researchers pay attention to the ensemble methods to the adversarial problems.…”

Section: B Ensemble Trainingmentioning

confidence: 99%

“…During the training, the replicas of the CNNs in an ensemble are simultaneously trained, where the same batch input is used for all the CNNs per weight update at the same time [37].…”

Section: Trainingmentioning

confidence: 99%

Ensemble of Random Binary Output Encoding for Adversarial Robustness

Mun

Kang

2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

Despite the excellent classification performance, recent research has revealed that the Convolutional Neural Network (CNN) could be readily deceived by only the small adversarial perturbation. Its imperceptible to human eyes and transferability from one model to another actually threaten the security of a CNN-based system. In this paper, we propose to create multiple and independent random binary codes per input class and train ensemble of homogeneous CNN classifiers with these codes to improve the adversarial robustness of the networks. The proposed ensemble structure consists of replicas of the same learning architecture, but each network is trained with different random target outputs. The network model is simultaneously trained with their own unique binary codes, and optimized through a single and common objective function in an end-to-end manner. It is demonstrated with experimental results that assigning different encoded labels for each classifier in ensemble leverages the diversity and eventually improves the classification performance on adversarial attacks. We also conduct several performance analysis to understand how the different aspects can contribute to the robustness of the proposed algorithm. The proposed algorithm provides significantly improved classification accuracies as compared to the recent relevant studies, verified with various network architectures, datasets, and adversarial attacks. INDEX TERMSDeep learning, convolutional neural network, adversarial attack, image classification, output encoding, ensemble.

show abstract

“…Deep ConvNets [9] and EEGNet [23] can be applied to MI classification [17,18,24], P300 detection [25,26], workload estimation [27][28][29], and error-or event-related potential decoding [30], and they become common approaches to learn the selective preprocessed handcraft data. The work in [9] followed a famous method of FBCSP [10] to construct the input data and then trained the data onto CNN with known training features.…”

Section: Introductionmentioning

confidence: 99%

Dual Head and Dual Attention in Deep Learning for End-to-End EEG Motor Imagery Classification

Yao

Ni³

2021

Applied Sciences

View full text Add to dashboard Cite

Event-Related Desynchronization (ERD) or Electroencephalogram (EEG) wavelet is essential for motor imagery (MI) classification and BMI (Brain–Machine Interface) application. However, it is difficult to recognize multiple tasks for non-trained subjects that are indispensable for the complexities of the task or the uncertainties in the environment. The subject-independent scenario, where an inter-subject trained model can be directly applied to new users without precalibration, is particularly desired. Therefore, this paper focuses on an effective attention mechanism which can be applied to a subject-independent set to learn EEG motor imagery features. Firstly, a custom form of sequence inputs with spatial and temporal dimensions is adopted for dual headed attention via deep convolution net (DHDANet). Secondly, DHDANet simultaneously learns temporal and spacial features. The features of spacial attention on each input head are divided into two parts for spatial attentional learning subsequently. The proposed model is validated based on the EEG-MI signals collected from 54 subjects in two sessions with 200 trials in each sessions. The classification of left and right hand motor imagery in this paper achieves an average accuracy of 75.52%, a significant improvement compared to state-of-the-art methods. In addition, the visualization of the frequency analysis method demonstrates that the temporal-convolution and spectral-attention is capable of identifying the ERD for EEG-MI. The proposed machine learning structure enables cross-session and cross-subject classification and makes significant progress in the BMI transfer learning problem.

show abstract

Multi-channel fusion convolutional neural network to classify syntactic anomaly from language-related ERP components

Cited by 20 publications

References 23 publications

Learning to Detect Cracks on Damaged Concrete Surfaces Using Two-Branched Convolutional Neural Network

Learning to Detect Cracks on Damaged Concrete Surfaces Using Two-Branched Convolutional Neural Network

Ensemble of Random Binary Output Encoding for Adversarial Robustness

Dual Head and Dual Attention in Deep Learning for End-to-End EEG Motor Imagery Classification

Contact Info

Product

Resources

About