Multiclass Classification of Visual Electroencephalogram Based on Channel Selection, Minimum Norm Estimation Algorithm, and Deep Network Architectures.

This work addresses the challenge of classifying multiclass visual EEG signals into 40 classes for brain-computer interface applications using deep learning architectures. The visual multiclass classification approach offers BCI applications a significant advantage since it allows the supervision of more than one BCI interaction, considering that each class label supervises a BCI task. However, because of the nonlinearity and nonstationarity of EEG signals, using multiclass classification based on EEG features remains a significant challenge for BCI systems. In the present work, mutual information-based discriminant channel selection and minimum-norm estimate algorithms were implemented to select discriminant channels and enhance the EEG data. Hence, deep EEGNet and convolutional recurrent neural networks were separately implemented to classify the EEG data for image visualization into 40 labels. Using the k-fold cross-validation approach, average classification accuracies of 94.8% and 89.8% were obtained by implementing the aforementioned network architectures. The satisfactory results obtained with this method offer a new implementation opportunity for multitask embedded BCI applications utilizing a reduced number of both channels (<50%) and network parameters (<110 K).

Motor Imagery Multi-Tasks Classification for BCIs Using the NVIDIA Jetson TX2 Board and the EEGNet Network.

Nowadays, Brain-Computer Interfaces (BCIs) still captivate large interest because of multiple advantages offered in numerous domains, explicitly assisting people with motor disabilities in communicating with the surrounding environment. However, challenges of portability, instantaneous processing time, and accurate data processing remain for numerous BCI system setups. This work implements an embedded multi-tasks classifier based on motor imagery using the EEGNet network integrated into the NVIDIA Jetson TX2 card. Therefore, two strategies are developed to select the most discriminant channels. The former uses the accuracy based-classifier criterion, while the latter evaluates electrode mutual information to form discriminant channel subsets. Next, the EEGNet network is implemented to classify discriminant channel signals. Additionally, a cyclic learning algorithm is implemented at the software level to accelerate the model learning convergence and fully profit from the NJT2 hardware resources. Finally, motor imagery Electroencephalogram (EEG) signals provided by HaLT's public benchmark were used, in addition to the k-fold cross-validation method. Average accuracies of 83.7% and 81.3% were achieved by classifying EEG signals per subject and motor imagery task, respectively. Each task was processed with an average latency of 48.7 ms. This framework offers an alternative for online EEG-BCI systems' requirements, dealing with short processing times and reliable classification accuracy.

Improving convolutional neural network learning based on a hierarchical bezier generative model for stenosis detection in X-ray images.

BACKGROUND AND OBJECTIVE: Automatic detection of stenosis on X-ray Coronary Angiography (XCA) images may help diagnose early coronary artery disease. Stenosis is manifested by a buildup of plaque in the arteries, decreasing the blood flow to the heart, increasing the risk of a heart attack. Convolutional Neural Networks (CNNs) have been successfully applied to identify pathological, regular, and featured tissues on rich and diverse medical image datasets. Nevertheless, CNNs find operative and performing limitations while working with small and poorly diversified databases. Transfer learning from large natural image datasets (such as ImageNet) has become a de-facto method to improve neural networks performance in the medical image domain. METHODS: This paper proposes a novel Hierarchical Bezier-based Generative Model (HBGM) to improve the CNNs training process to detect stenosis. Herein, artificial image patches are generated to enlarge the original database, speeding up network convergence. The artificial dataset consists of 10,000 images containing 50% stenosis and 50% non-stenosis cases. Besides, a reliable Fréchet Inception Distance (FID) is used to evaluate the generated data quantitatively. Therefore, by using the proposed framework, the network is pre-trained with the artificial datasets and subsequently fine-tuned using the real XCA training dataset. The real dataset consists of 250 XCA image patches, selecting 125 images for stenosis and the remainder for non-stenosis cases. Furthermore, a Convolutional Block Attention Module (CBAM) was included in the network architecture as a self-attention mechanism to improve the efficiency of the network. RESULTS: The results showed that the pre-trained networks using the proposed generative model outperformed the results concerning training from scratch. Particularly, an accuracy, precision, sensitivity, and F1-score of 0.8934, 0.9031, 0.8746, 0.8880, 0.9111, respectively, were achieved. The generated artificial dataset obtains a mean FID of 84.0886, with more realistic visual XCA images. CONCLUSIONS: Different ResNet architectures for stenosis detection have been evaluated, including attention modules into the network. Numerical results demonstrated that by using the HBGM is obtained a higher performance than training from scratch, even outperforming the ImageNet pre-trained models.

Multi-Stroke handwriting character recognition based on sEMG using convolutional-recurrent neural networks.

Despite the increasing use of technology, handwriting has remained to date as an efficient means of communication. Certainly, handwriting is a critical motor skill for childrens cognitive development and academic success. This article presents a new methodology based on electromyographic signals to recognize multi-user free-style multi-stroke handwriting characters. The approach proposes using powerful Deep Learning (DL) architectures for feature extraction and sequence recognition, such as convolutional and recurrent neural networks. This framework was thoroughly evaluated, obtaining an accuracy of 94.85%. The development of handwriting devices can be potentially applied in the creation of artificial intelligence applications to enhance communication and assist people with disabilities.

Comparison of Efficiency and Image Quality of Photostimulable Phosphor Plate and Charge-Coupled Device Receptors in Dental Radiography.

The photostimulable phosphor (PSP) plate and charge-coupled device (CCD) are receptors commonly used for intraoral radiography in U.S. dental schools. However, it is unclear which receptor is more beneficial for radiology education and patient care in an academic setting. The aim of this study was to compare the time efficiency, image quality, and operator performance for student-operated PSP plate and CCD receptors. At one U.S. dental school in 2018, 20 dental hygiene and dental students (n=10 each) were recruited as operators. They each exposed anterior and posterior periapical and bitewing radiographs on dental radiograph teaching and training replica using the PSP plate and CCD as receptors. The time taken to expose the radiographs was recorded. Image sharpness/definition, brightness/contrast, and technical errors, including placement, angulation, and cone cut errors, were evaluated on a three-point scale with 0=non-diagnostic, 1=diagnostic acceptable with minor errors, and 2=perfect diagnostic quality. The results showed that it was generally faster for the students to expose intraoral radiographs with CCDs than with PSP plates, although the difference was not significant (p>0.05). Image quality and technical accuracy, especially angulation, were significantly superior for PSP relative to CCD (p<0.05). This study found that PSP imaging was of higher quality and accuracy than CCD, whereas CCD was more efficient. Dental and dental hygiene students would benefit from being trained on both receptors to be able to adapt to a diversified workplace.

Cursive word recognition based on interactive activation and early visual processing models.

We present an off-line cursive word recognition system based completely on neural networks: reading models and models of early visual processing. The first stage (normalization) preprocesses the input image in order to reduce letter position uncertainty; the second stage (feature extraction) is based on the feedforward model of orientation selectivity; the third stage (letter pre-recognition) is based on a convolutional neural network, and the last stage (word recognition) is based on the interactive activation model.