Deep learning has been the answer to many machine learning problems during the past two decades. However, it comes with two significant constraints: dependency on extensive labeled data and training costs. Transfer learning in deep learning, known as Deep Transfer Learning (DTL), attempts to reduce such reliance and costs by reusing obtained knowledge from a source data/task in training on a target data/task. Most applied DTL techniques are network/model-based approaches. These methods reduce the dependency of deep learning models on extensive training data and drastically decrease training costs. Moreover, the training cost reduction makes DTL viable on edge devices with limited resources. Like any new advancement, DTL methods have their own limitations, and a successful transfer depends on specific adjustments and strategies for different scenarios. This paper reviews the concept, definition, and taxonomy of deep transfer learning and well-known methods. It investigates the DTL approaches by reviewing applied DTL techniques in the past five years and a couple of experimental analyses of DTLs to discover the best practice for using DTL in different scenarios. Moreover, the limitations of DTLs (catastrophic forgetting dilemma and overly biased pre-trained models) are discussed, along with possible solutions and research trends.

This study examines the efficacy of Random Forest and XGBoost classifiers in conjunction with three upsampling techniques—SMOTE, ADASYN, and Gaussian noise upsampling (GNUS)—across datasets with varying class imbalance levels, ranging from moderate to extreme (15% to 1% churn rate). Employing metrics such as F1 score, ROC AUC, PR AUC, Matthews Correlation Coefficient (MCC), and Cohen’s Kappa, this research provides a comprehensive evaluation of classifier performance under different imbalance scenarios, focusing on applications in the telecommunications domain. The findings highlight that tuned XGBoost paired with SMOTE (Tuned_XGB_SMOTE) consistently achieves the highest F1 score and robust performance across all imbalance levels. SMOTE emerged as the most effective upsampling method, particularly when used with XGBoost, whereas Random Forest performed poorly under severe imbalance. ADASYN showed moderate effectiveness with XGBoost but underperformed with Random Forest, and GNUS produced inconsistent results. This study underscores the impact of data imbalance, with MCC, Kappa, and F1 scores fluctuating significantly, whereas ROC AUC and PR AUC remained relatively stable. Moreover, rigorous statistical analyses employing the Friedman test and Nemenyi post hoc comparisons confirmed that the observed improvements in F1 score, PR-AUC, Kappa, and MCC were statistically significant (p < 0.05), with Tuned_XGB_SMOTE significantly outperforming Tuned_RF_GNUS. While differences in ROC-AUC were not significant, the consistency of these results across multiple performance metrics underscores the reliability of our framework, offering a statistically validated and attractive solution for model selection in imbalanced classification scenarios.

In recent years, the Internet of Things (IoT) has gained convincing research ground as a new research topic in a wide variety of academic and industrial disciplines, especially in healthcare. The IoT revolution is reshaping modern healthcare systems by incorporating technological, economic, and social prospects. It is evolving healthcare systems from conventional to more personalized healthcare systems through which patients can be diagnosed, treated, and monitored more easily. The current global challenge of the pandemic caused by the novel severe respiratory syndrome coronavirus 2 presents the greatest global public health crisis since the pandemic influenza outbreak of 1918. At the time this paper was written, the number of diagnosed COVID-19 cases around the world had reached more than 31 million. Since the pandemic started, there has been a rapid effort in different research communities to exploit a wide variety of technologies to combat this worldwide threat, and IoT technology is one of the pioneers in this area. In the context of COVID-19, IoT-enabled/linked devices/applications are utilized to lower the possible spread of COVID-19 to others by early diagnosis, monitoring patients, and practicing defined protocols after patient recovery. This paper surveys the role of IoT-based technologies in COVID-19 and reviews the state-of-the-art architectures, platforms, applications, and industrial IoT-based solutions combating COVID-19 in three main phases, including early diagnosis, quarantine time, and after recovery.

Methodologies that utilize Deep Learning offer great potential for applications that automatically attempt to generate captions or descriptions about images and video frames. Image and video captioning are considered to be intellectually challenging problems in imaging science. The application domains include automatic caption (or description) generation for images and videos for people who suffer from various degrees of visual impairment; the automatic creation of metadata for images and videos (indexing) for use by search engines; general-purpose robot vision systems; and many others. Each of these application domains can positively and significantly impact many other task-specific applications. This paper is not meant to be a comprehensive review of image captioning; rather, it is a concise review of both image captioning and video captioning methodologies based on deep learning. This study treats both image and video captioning by emphasizing the algorithmic overlap between the two.

This paper explores the application of various machine learning techniques for predicting customer churn in the telecommunications sector. We utilized a publicly accessible dataset and implemented several models, including Artificial Neural Networks, Decision Trees, Support Vector Machines, Random Forests, Logistic Regression, and gradient boosting techniques (XGBoost, LightGBM, and CatBoost). To mitigate the challenges posed by imbalanced datasets, we adopted different data sampling strategies, namely SMOTE, SMOTE combined with Tomek Links, and SMOTE combined with Edited Nearest Neighbors. Moreover, hyperparameter tuning was employed to enhance model performance. Our evaluation employed standard metrics, such as Precision, Recall, F1-score, and the Receiver Operating Characteristic Area Under Curve (ROC AUC). In terms of the F1-score metric, CatBoost demonstrates superior performance compared to other machine learning models, achieving an outstanding 93% following the application of Optuna hyperparameter optimization. In the context of the ROC AUC metric, both XGBoost and CatBoost exhibit exceptional performance, recording remarkable scores of 91%. This achievement for XGBoost is attained after implementing a combination of SMOTE with Tomek Links, while CatBoost reaches this level of performance after the application of Optuna hyperparameter optimization.