In the last decade, Deep Learning (DL) has revolutionized the use of artificial intelligence, and it has been deployed in different fields of healthcare applications such as image processing, natural language processing, and signal processing. DL models have also been intensely used in different tasks of healthcare such as disease diagnostics and treatments. Deep learning techniques have surpassed other machine learning algorithms and proved to be the ultimate tools for many state-of-the-art applications. Despite all that success, classical deep learning has limitations and their models tend to be very confident about their predicted decisions because it does not know when it makes mistake. For the healthcare field, this limitation can have a negative impact on models predictions since almost all decisions regarding patients and diseases are sensitive. Therefore, Bayesian deep learning (BDL) has been developed to overcome these limitations. Unlike classical DL, BDL uses probability distributions for the model parameters, which makes it possible to estimate the whole uncertainties associated with the predicted outputs. In this regard, BDL offers a rigorous framework to quantify all sources of uncertainties in the model. This study reviews popular techniques of using Bayesian deep learning with their benefits and limitations. It also reviewed recent deep learning architecture such as Convolutional Neural Networks and Recurrent Neural Networks. In particular, the applications of Bayesian deep learning in healthcare have been discussed such as its use in medical imaging tasks, clinical signal processing, medical natural language processing, and electronic health records. Furthermore, this paper has covered the deployment of Bayesian deep learning for some of the widespread diseases. This paper has also discussed the fundamental research challenges and highlighted some research gaps in both the Bayesian deep learning and healthcare perspective.

Bayesian deep learning (BDL) has emerged as a powerful technique for quantifying uncertainty in classification tasks, surpassing the effectiveness of traditional models by aligning with the probabilistic nature of real-world data. This alignment allows for informed decision-making by not only identifying the most likely outcome but also quantifying the surrounding uncertainty. Such capabilities hold great significance in fields like medical diagnoses and autonomous driving, where the consequences of misclassification are substantial. To further improve uncertainty quantification, the research community has introduced Bayesian model ensembles, which combines multiple Bayesian models to enhance predictive accuracy and uncertainty quantification. These ensembles have exhibited superior performance compared to individual Bayesian models and even non-Bayesian counterparts. In this study, we propose a novel approach that leverages the power of Bayesian ensembles for enhanced uncertainty quantification. The proposed method exploits the disparity between predicted positive and negative classes and employes it as a ranking metric for model selection. For each instance or sample, the ensemble's output for each class is determined by selecting the top ‘k' models based on this ranking. Experimental results on different medical image classifications demonstrate that the proposed method consistently outperforms or achieves comparable performance to conventional Bayesian ensemble. This investigation highlights the practical application of Bayesian ensemble techniques in refining predictive performance and enhancing uncertainty evaluation in image classification tasks.

Convolutional neural networks (CNNs) have become a popular choice for various image classification applications. However, the multi-layer perceptron mixer (MLP-Mixer) architecture has been proposed as a promising alternative, particularly for large datasets. Despite its advantages in handling large datasets and models, MLP-Mixer models have limitations when dealing with small datasets. This study aimed to quantify and evaluate the uncertainty associated with MLP-Mixer models for small datasets using Bayesian deep learning (BDL) methods to quantify uncertainty and compare the results to existing CNN models. In particular, we examined the use of variational inference and Monte Carlo dropout methods. The results indicated that BDL can improve the performance of MLP-Mixer models by 9.2 to 17.4% in term of accuracy across different mixer models. On the other hand, the results suggest that CNN models tend to have limited improvement or even decreased performance in some cases when using BDL. These findings suggest that BDL is a promising approach to improve the performance of MLP-Mixer models, especially for small datasets.

Data hiding or steganography has been used ever since a secret message was needed to be transferred. Data hiding methods need a medium to be cover for secret message that is to be sent. Different mediums are used such as image, video, audio, and last decade the deoxyribose nucleic acid (DNA). In this paper, a new data hiding approach based on the DNA sequence is proposed. Unlike many existing methods, the proposed method does not change the biological functionality of the DNA reference sequence when the sequence is translated into amino acids. The proposed method is consisting of two steps: the first step is encrypting the message using the Toffoli quantum gate. The second step is embedding the encrypted message into DNA sequence by taking one codon at a time and considering amino acids' biological functionality during the embedding process. Experimental results show that the proposed method outperforms the existing schemes preserving biological functionality in terms of cracking probability, and hiding capacity for bit per nucleotide.

As the use of technology is increasing rapidly, the amount of shared, sent, and received information is also increas-ing in the same way. As a result, this necessitates the need for finding techniques that can save and secure the information over the net. There are many methods that have been used to protect the information such as hiding information and encryption. In this study, we propose a new encryption method making use of amino acid and DNA sequences. In addition, several criteria including data size, key size and the probability of cracking are used to evaluate the proposed method. The results show that the performance of the proposed method is better than many common encryption methods, such as RSA in terms of evaluation criteria.

A linear stability analysis is performed for the onset of Marangoni convection in a horizontal layer of a nanofluid heated from below and affected by rotation. The top boundary of the layer is assumed to be impenetrable to nanoparticles with their distribution being determined from a conservation condition while the bottom boundary is assumed to be a rigid surface with fixed temperature. The motion of the nanoparticles is characterized by the effects of thermophoresis and Brownian diffusion. A modification model is used in which the effects of Brownian diffusion and thermophoresis are taken into consideration by new expressions in the nanoparticle mass flux. Also, material properties of the nanofluid are modelled by non-constant constitutive expressions depending on nanoparticle volume fraction. The steady-state solution is shown to be well approximated by an exponential distribution of the nanoparticle volume fraction. The Chebyshev-Tau method is used to obtain the critical thermal and nanoparticle Marangoni numbers. Different stability boundaries are obtained using the modified model and the rotation.