The rapid growth and adaptation of medical information to identify significant health trends and help with timely preventive care have been recent hallmarks of the modern healthcare data system. Heart disease is the deadliest condition in the developed world. Cardiovascular disease and its complications, including dementia, can be averted with early detection. Further research in this area is needed to prevent strokes and heart attacks. An optimal machine learning model can help achieve this goal with a wealth of healthcare data on heart disease. Heart disease can be predicted and diagnosed using machine-learning-based systems. Active learning (AL) methods improve classification quality by incorporating user–expert feedback with sparsely labelled data. In this paper, five (MMC, Random, Adaptive, QUIRE, and AUDI) selection strategies for multi-label active learning were applied and used for reducing labelling costs by iteratively selecting the most relevant data to query their labels. The selection methods with a label ranking classifier have hyperparameters optimized by a grid search to implement predictive modelling in each scenario for the heart disease dataset. Experimental evaluation includes accuracy and F-score with/without hyperparameter optimization. Results show that the generalization of the learning model beyond the existing data for the optimized label ranking model uses the selection method versus others due to accuracy. However, the selection method was highlighted in regards to the F-score using optimized settings.

The growth of IoT, edge and mobile Artificial Intelligence (AI) is supporting urban authorities exploit the wealth of information collected by Connected and Autonomous Vehicles (CAV), to drive the development of transformative intelligent transport applications for addressing smart city challenges. A critical challenge is timely and efficient road infrastructure maintenance. This paper proposes an intelligent hierarchical framework for road infrastructure maintenance that exploits the latest developments in 6G communication technologies, deep learning techniques, and mobile edge AI training approaches. The proposed framework abides with the stringent requirements of training efficient machine learning applications for CAV, and is able to exploit the vast numbers of CAVs forecasted to be present on future road networks. At the core of our framework is a novel Convolution Neural Networks (CNN) model which fuses imagery and sensory data to perform pothole detection. Experiments show the proposed model can achieve state of the art performance in comparison to existing approaches while being simple, cost-effective and computationally efficient to deploy. The proposed system can form part of a federated learning framework for facilitating large scale real-time road surface condition monitoring and support adaptive resource allocation for road infrastructure maintenance.

Financial Technology (FinTech) has expanded beyond simple mobile banking to online money transfers, crowdfunding, and managing individual investments. This reinforces the importance of ensuring security and privacy in FinTech, e.g., using Blockchain (hereafter referred to as Blockchain-based FinTech applications). In this work, we will systematically summarize recent Blockchain-based FinTech applications. As a result of the advancement of BFinTech, several novel cyberattacks have been evolved to potentially impact BFinTech functionalities. Thus, this work highlights the open research challenges and future research directions in Blockchain-based FinTech applications.

Smart power grids suffer from electricity theft cyber-attacks, where malicious consumers compromise their smart meters (SMs) to downscale the reported electricity consumption readings. This problem costs electric utility companies worldwide considerable financial burdens and threatens power grid stability. Therefore, several machine learning (ML)-based solutions have been proposed to detect electricity theft; however, they have limitations. First, most existing works employ supervised learning that requires the availability of labeled datasets of benign and malicious electricity usage samples. Unfortunately, this approach is not practical due to the scarcity of real malicious electricity usage samples. Moreover, training a supervised detector on specific cyberattack scenarios results in a robust detector against those attacks, but it might fail to detect new attack scenarios. Second, although a few works investigated anomaly detectors for electricity theft, none of the existing works addressed consumers’ privacy. To address these limitations, in this paper, we propose a comprehensive federated learning (FL)-based deep anomaly detection framework tailored for practical, reliable, and privacy-preserving energy theft detection. In our proposed framework, consumers train local deep autoencoder-based detectors on their private electricity usage data and only share their trained detectors’ parameters with an EUC aggregation server to iteratively build a global anomaly detector. Our extensive experimental results not only demonstrate the superior performance of our anomaly detector compared to the supervised detectors but also the capability of our proposed FL-based anomaly detector to accurately detect zero-day attacks of electricity theft while preserving consumers’ privacy.

Room occupancy prediction based on indoor environmental quality may be the breakthrough to ensure energy efficiency and establish an interior ambience tailored to each user. Identifying whether temperature, humidity, lighting, and CO₂ levels may be used as efficient predictors of room occupancy accuracy is needed to help designers better utilize the readings and data collected in order to improve interior design, in an effort to better suit users. It also aims to help in energy efficiency and saving in an ever-increasing energy crisis and dangerous levels of climate change. This paper evaluated the accuracy of room occupancy recognition using a dataset with diverse amounts of light, CO₂, and humidity. As classification algorithms, K-nearest neighbors (KNN), hybrid Adam optimizer–artificial neural network–back-propagation network (AO–ANN (BP)), and decision trees (DT) were used. Furthermore, this research is based on machine learning interpretability methodologies. Shapley additive explanations (SHAP) improve interpretability by estimating the significance values for each feature for classifiers applied. The results indicate that the KNN performs better than the DT and AO-ANN (BP) classification models have 99.5%. Though the two classifiers are designed to evaluate variations in interpretations, we must ensure that they have accurate detection. The results show that SHAP provides successful implementation following these metrics, with differences detected amongst classifier models that support the assumption that model complexity plays a significant role when predictability is taken into account.

With the advancement of cyber threats, blockchain technology has evolved to have a significant role in providing secure and reliable decentralized applications. One of these applications is a remote voting system that allow voters to participate in elections remotely. This work proposes a privacy-preserving e-voting system supporting score voting using blockchain technology. The main challenge with score voting compared to the regular yes/no voting approach is that a voter is allowed to assign a score from a defined range for each candidate. To preserve privacy, votes shall be encrypted before submission to the Blockchain, however, a malicious voter can modify the score value before encrypting it to manipulate the elections result for the favor of a certain candidate. To address this challenge, the proposed scheme allows voters to first prove that the submitted score lies in the predefined range before the vote is added to the Blockchain to ensure fairness of the election. The performance of our scheme is evaluated against a set of comprehensive experiments designed to determine optimal bounds for workload and transaction send rates and measure the impact of exceeding these bounds on critical performance metrics. The results of these simulations and their implications therefore indicate that the proposed scheme is secure while being able to handle up to 10,000 transactions at a time.