The current advancement towards retinal disease detection mainly focused on distinct feature extraction using either a convolutional neural network (CNN) or a transformer-based end-to-end deep learning (DL) model. The individual end-to-end DL models are capable of only processing texture or shape-based information for performing detection tasks. However, extraction of only texture- or shape-based features does not provide the model robustness needed to classify different types of retinal diseases. Therefore, concerning these two features, this paper developed a fusion model called ‘Conv-ViT’ to detect retinal diseases from foveal cut optical coherence tomography (OCT) images. The transfer learning-based CNN models, such as Inception-V3 and ResNet-50, are utilized to process texture information by calculating the correlation of the nearby pixel. Additionally, the vision transformer model is fused to process shape-based features by determining the correlation between long-distance pixels. The hybridization of these three models results in shape-based texture feature learning during the classification of retinal diseases into its four classes, including choroidal neovascularization (CNV), diabetic macular edema (DME), DRUSEN, and NORMAL. The weighted average classification accuracy, precision, recall, and F1 score of the model are found to be approximately 94%. The results indicate that the fusion of both texture and shape features assisted the proposed Conv-ViT model to outperform the state-of-the-art retinal disease classification models.

Current deep learning-assisted brain tumor classification models sustain inductive bias and parameter dependency problems for extracting texture-based image information. Thereby concerning these problems, the recent development of the vision transformer model has substituted the DL model for classification tasks. However, the high performance of the vision transformer model depends on a large-scale dataset as well as self-attention calculations between the number of image patches which result in a quadratic computational complexity. To address these problems, the vision transformer must be data-efficient to be well-trained with a limited amount of data, and the computational complexity must be linear with the number of image patches. Consequently, this paper presents a novel linear-complexity data-efficient image transformer called LCDEiT for training with small-size datasets by using a teacher-student strategy and linear computational complexity concerning the number of patches using an external attention mechanism. The teacher model comprised a custom gated-pooled convolutional neural network to provide knowledge to the transformer-based student model for the classification of MRI brain tumors. The average classification accuracy and F1-score for two benchmark datasets including Figshare and BraTS-21 are found 98.11% and 97.86% and 93.69% and 93.68% respectively. The results indicate that the proposed model could have a great impact on medical imaging-based diagnosis where data availability and faster computations are the main concern.

By using computer-aided arrhythmia diagnosis tools, electrocardiogram (ECG) signal plays a vital role in lowering the fatality rate associated with cardiovascular diseases (CVDs) and providing information about the patient’s cardiac health to the specialist. Current advancements in deep-learning-based multivariate time series data analysis, such as ECG data classification include LSTM, Bi-LSTM, CNN, with Bi-LSTM, and other sequential networks. However, these networks often struggle to accurately determine the long-range dependencies among data instances, which can result in problems such as vanishing or exploding gradients for longer data sequences. To address these shortcomings of sequential models, a hybrid arrhythmia classification system using recurrence along with a self-attention mechanism is developed. This system utilizes convolutional layers as a part of representation learning, designed to capture the salient features of raw ECG data. Then, the latent embedded layer is fed to a self-attention-assisted transformer encoder model. Because the ECG data are highly influenced by absolute order, position, and proximity of time steps due to interdependent relationships among immediate neighbors, a component of recurrence using Bi-LSTM is added to the encoder model to address this characteristic of the data. The model performance indices such as classification accuracy and F1-score were found to be 99.2%. This indicates that the combination of recurrence along with self-attention-assisted architecture produces improved classification of arrhythmia from raw ECG signal when compared with the state-of-the-art models.

Recently, the transformer-based model e.g., the vision transformer (ViT) has been extensively used in computer vision tasks. The superior performance of the ViT leads to the requirement of an enormous dataset and the complexity of calculating self-attention between patches is quadratic in nature. To acknowledge these two concerns, this paper proposes a novel shifted patch tokenization swin transformer (SPT-Swin) for the image classification task. The shifted patch tokenization (SPT) compensates for the data deficiency by increasing the data samples based on spatial information of the image patches while the swin transformer provides linear computational complexity by calculating self-attention between the shifted window based patches. For model validation, the SPT-Swin framework is trained on popular benchmark image datasets such as ImageNet-1K, CIFAR-10 and CIFAR-100, and the classification accuracies are found 89.45%, 95.67% and 92.95% respectively. Moreover, the comparative analysis of the proposed model with the existing state-of-the-art models shows that the classification performances are improved by 7.05%, 4.14%, and 8.30% for the ImageNet-1K, CIFAR-10 and CIFAR-100 datasets respectively. Therefore, our proposed SPT-based data augmentation technique with the core swin transformer model could be a data-efficient linear complex-able model for future computer vision tasks.

Visual Question Answering (VQA) is a challenging problem of Artificial Intelligence (AI) that requires an understanding of natural language and computer vision to respond to inquiries based on visual content within images. Research on VQA has gained immense traction due to its wide range of applications in aiding visually impaired individuals, enhancing human-computer interaction, facilitating content-based image retrieval systems, etc. While there has been extensive research on VQA, most were predominantly focused on English, often overlooking the complexity associated with low-resource languages, especially in Bengali. To facilitate research in this arena, we have developed a large scale Bengali Visual Question Answering (BVQA) dataset by harnessing the in-context learning abilities of the Large Language Model (LLM). Our BVQA dataset encompasses around 17,800 diverse open-ended QA Pairs generated from the human-annotated captions of ≈3,500 images. Replicating existing VQA systems for a low-resource language poses significant challenges due to the complex nature of their architectures and adaptations for particular languages. To overcome this challenge, we proposedMultimodal CRoss-Attention Network (MCRAN), a novel framework that leverages pretrained transformer architectures to encode the visual and textual information. Furthermore, our method utilizes a multi-head attention mechanism to generate three distinct vision-language representations and fuses them using a sophisticated gating mechanism to answer the query regarding an image. Extensive experiments on BVQA dataset show that the proposed method outperformed the existing baseline across various answer categories. The benchmark and source code is available at https://github.com/Bengali-VQA.

This article proposes a deep neural network (DNN) model to predict the electric field induced by a transcranial magnetic stimulation (TMS) coil under high-amplitude and low-frequency current pulse conditions. The DNN model is comprised of an input layer with 6 neurons, three non-linear hidden layers with a total of 1088 neurons, and a linear single output layer. The model is developed in Google Colaboratory environment with TensorFlow framework using six features including coil turns of single wing, coil thickness, coil diameter, distance between two wings, distance between head and coil position, and angle between two wings of coil as the inputs and electric field as the output. The model performance is evaluated based on four verification statistic metrics such as coefficient of determination (R2), mean squared error (MSE), mean absolute error (MAE), and root mean squared error (RMSE) between the simulated and predicted values. The proposed model provides an adequate performance with R2 = 0.766, MSE = 0.184, MAE = 0.262, and RMSE = 0.429 in the testing stage. Therefore, the model can successfully predict the electric field in an assembly TMS coil without the aid of electromagnetic simulation software that suffers from an extensive computational cost.