Deep sequential (DS) models are extensively employed for forecasting time series data since the dawn of the deep learning era, and they provide forecasts for the values required in subsequent time steps. DS models, unlike other traditional statistical models for forecasting time series data, can learn hidden patterns in temporal sequences and have the memorizing data from prior time points. Given the widespread usage of deep sequential models in several domains, a comprehensive study describing their applications is necessary. This work presents a comprehensive review of contemporary deep learning time series models, their performance in diverse domains, and an investigation of the models that were employed in various applications. Three deep sequential models, namely, artificial neural network (ANN), long short-term memory (LSTM), and temporal-conventional neural network (TCNN) along with their applications for forecasting time series data, are elaborated. We showed a comprehensive comparison between such models in terms of application fields, model structure and activation functions, optimizers, and implementation, with a goal of learning more about the optimal model used. Furthermore, the challenges and perspectives of future development of deep sequential models are presented and discussed. We conclude that the LSTM model is widely employed, particularly in the form of a hybrid model, in which the most accurate predictions are made when the shape of hybrids is used as the model.

Over the past few decades, face recognition has become the most effective biometric technique in recognizing people’s identity, as it is widely used in many areas of our daily lives. However, it is a challenging technique since facial images vary in rotations, expressions, and illuminations. To minimize the impact of these challenges, exploiting information from various feature extraction methods is recommended since one of the most critical tasks in face recognition system is the extraction of facial features. Therefore, this paper presents a new approach to face recognition based on the fusion of Gabor-based feature extraction, Fast Independent Component Analysis (FastICA), and Linear Discriminant Analysis (LDA). In the presented method, first, face images are transformed to grayscale and resized to have a uniform size. After that, facial features are extracted from the aligned face image using Gabor, FastICA, and LDA methods. Finally, the nearest distance classifier is utilized to recognize the identity of the individuals. Here, the performance of six distance classifiers, namely Euclidean, Cosine, Bray-Curtis, Mahalanobis, Correlation, and Manhattan, are investigated. Experimental results revealed that the presented method attains a higher rank-one recognition rate compared to the recent approaches in the literature on four benchmarked face datasets: ORL, GT, FEI, and Yale. Moreover, it showed that the proposed method not only helps in better extracting the features but also in improving the overall efficiency of the facial recognition system.

Deep Learning (DL) has significantly contributed to the field of medical imaging in recent years, leading to advancements in disease diagnosis and treatment. In the case of Diabetic Retinopathy (DR), DL models have shown high efficacy in tasks such as classification, segmentation, detection, and prediction. However, DL model's opacity and complexity lead to errors in decision-making, particularly in complex cases, making it necessary to estimate the model's uncertainty in predictions. Therefore, there is a need to estimate uncertainty in the model's predictions, which cannot be estimated by classical DL models alone. To address this issue, Bayesian DL methods have been proposed, and their use is increasing in the field. In this paper, we developed a straightforward architecture for the classification of DR using a Convolutional Neural Network (CNN) model. We then applied the Bayesian CNN twice, once using Variational Inference (VI) and once using Monte Carlo dropout (MC-dropout) methods, to the same CNN architecture. This allowed us to gain the posterior predictive distributions for each of them. The performance of the proposed models was evaluated on two benchmark datasets, namely APTOS 2019 and Messidor-2. Experimental findings demonstrated that the proposed models surpassed other state-of-the-art models, achieving a test accuracy of 94.70 % and 77.00 % for CNN, 94.00 % and 86.00 % for BCNN-VI, and 93.30 % and 81.00 % for BCNN-MC-dropout on the APTOS dataset and Messidor-2 dataset, respectively. Finally, we computed the entropy and standard deviation on the obtained predictive distribution to quantify the model uncertainty. This research highlights the potential benefits of using Bayesian DL methods in medical image analysis to improve the accuracy and reliability of diagnosing disease and treatment.

Imbalanced data classification is a common issue in data mining where the classifiers are skewed towards the larger data class. Classification of high-dimensional skewed (imbalanced) data is of great interest to decision-makers as it is more difficult to. The dimension reduction method, a process in which variables are reduced, allows high dimensional datasets to be interpreted more easily with a certain loss. This study, a method combining SMOTE oversampling with principal component analysis is proposed to solve the imbalance problem in high dimensional data. Three classification algorithms consisting of Logistic Regression, K-Nearest Neighbor, Decision Tree methods and two separate datasets were utilized to evaluate the suggested method's efficacy and determine the classifiers' performance. Respectively, raw datasets, converted datasets by PCA, SMOTE and SMOTE+PCA (SMOTE and PCA) methods, were analyzed with the given algorithms. Analyzes were made using WEKA. Analysis results suggest that almost all classification algorithms improve their classification performance using PCA, SOMTE, and SMOTE+PCA methods. However, the SMOTE method gave more efficient results than PCA and PCA+SMOTE methods for data rebalancing. Experimental results also suggest that K-Nearest Neighbor classifier provided higher classification performance compared to other algorithms.

Classification of diabetes data with existing data mining and machine learning algorithms is challenging and the predictions are not always accurate. We aim to build a model that effectively addresses these challenges (misclassification) and can accurately diagnose and classify diabetes. In this study, we investigated the use of Bayesian Logistic Regression (BLR) for mining such data to diagnose and classify various diabetes conditions. This approach is fully Bayesian suited for automating Markov Chain Monte Carlo (MCMC) simulation. Using Bayesian methods in analysing medical data is useful because of the rich hierarchical models, uncertainty quantification, and prior information they provide. The analysis was done on a real medical dataset created for 909 patients in Zakho city with a binary class label and seven independent variables. Three different prior distributions (Gaussian, Laplace and Cauchy) were investigated for our proposed model implemented by MCMC. The performance and behaviour of the Bayesian approach were illustrated and compared with the traditional classification algorithms on this dataset using 10-fold cross-validation. Experimental results show overall that classification under BLR with informative Gaussian priors performed better in terms of various accuracy metrics. It provides an accuracy of 92.53%, a recall of 94.85%, a precision of 91.42% and an F1 score of 93.11%. Experimental results suggest that it is worthwhile to explore the application of BLR to predictive modelling tasks in medical studies using informative prior distributions.