Machine and Deep Learning architectures and methodologies
Exploring the design and development of new deep learning architectures that can address specific challenges in areas like computer vision, natural language processing, or reinforcement learning. This involves designing new layers, optimizing existing architectures, or combining multiple architectures to improve performance.

• Artificial intelligence and healthcare: Forecasting of medical bookings through multi-source time-series fusion
• A robust ensemble technique in forecasting workload of local healthcare departments
• ENCODE – Ensemble neural combination for optimal dimensionality encoding in time-series forecasting
• A Deep Learning Approach Considering Image Background for Pneumonia Identification Using Explainable AI (XAI)
• Investigating Random Variations of the Forward-Forward Algorithm for Training Neural Networks
• An accurate and dynamic predictive model for a smart M-Health system using machine learning
• A deep learning approach for facility patient attendance prediction based on medical booking data
• Advanced Machine-Learning Methods for Brain-Computer Interfacing
• Deep end-to-end learning for price prediction of second-hand items

Federated Learning
Federated learning (FL) is a distributed machine learning (ML) approach that enables models to be trained on client devices while ensuring the privacy of user data. Model aggregation, also known as model fusion, plays a vital role in FL. It involves combining locally generated models from client devices into a single global model while maintaining user data privacy.

• Model aggregation techniques in federated learning: A comprehensive survey
• FL-FD: Federated learning-based fall detection with multimodal data fusion
• FL-Enhance: A federated learning framework for balancing non-IID data with augmented and shared compressed samples

Deep Learning applications: Smart City, Smart Mobility, Industry 4.0, Medicine and Healthcare, Seismology, Cultural Heritage
Dive into a curated collection of scientific papers that showcase the transformative power of deep learning across diverse sectors. From streamlining city infrastructures in Smart City applications to advancing next-generation mobility solutions in Smart Mobility, deep learning is at the forefront of technological evolution. Discover how Industry 4.0 is integrating intelligent algorithms for automation, quality control, and predictive maintenance. Explore groundbreaking strides in Medicine and Healthcare, where deep learning aids in accurate diagnoses, treatment planning, and patient care. Finally, understand the pivotal role of this technology in Seismology, enhancing our ability to predict, monitor, and understand seismic activities.

• A blockchain-based secure Internet of medical things framework for stress detection
• A data-driven artificial neural network model for the prediction of ground motion from induced seismicity: The case of The Geysers geothermal field
• Predictive maintenance for offshore oil wells by means of deep learning features extraction
• Predictive Medicine for Salivary Gland Tumours Identification Through Deep Learning
• A Deep Learning approach for Path Prediction in a Location-based IoT system
• Predictive Analytics for Smart Parking: A Deep Learning Approach in Forecasting of IoT Data
• A Framework for Pandemic Prediction Using Big Data Analytics
• A Deep Learning Approach for Long-Term Traffic Flow Prediction With Multifactor Fusion Using Spatiotemporal Graph Convolutional Network
• The Impact of Adversarial Attacks on Interpretable Semantic Segmentation in Cyber–Physical Systems
• From Artificial Intelligence to Explainable Artificial Intelligence in Industry 4.0: A Survey on What, How, and Where
• Cut the peaches: image segmentation for utility pattern mining in food processing

Generative Learning
Generative machine and deep learning involves using algorithms to generate new data that is similar to a training dataset. This type of research activity involves developing models that can learn the underlying patterns and relationships in the training data, and then use that knowledge to generate new data that is similar in structure and content. Machine and deep learning methods, such as generative adversarial networks and variational autoencoders, are often used to build these generative models, as they are well-suited for modeling complex data distributions. The ultimate goal of this research is to produce novel data that can be used in a variety of applications, such as image and text synthesis, data augmentation, and anomaly detection.

• An Attention Based Cycle-Consistent Generative Adversarial Network for IoT Data Generation and Its Application in Smart Energy Systems
• An Efficient Deep Learning Approach Using Improved Generative Adversarial Networks for Incomplete Information Completion of Self-driving Vehicles
• Neural networks generative models for time series
• SWCGAN: Generative Adversarial Network Combining Swin Transformer and CNN for Remote Sensing Image Super-Resolution
• Incomplete vehicle information completion using generative adversarial network to enhance the safety of autonomous driving

Scientific Machine Learning and Physics-Informed Neural Networks Physics-informed neural networks (PINNs) are a type of machine learning technique that combines physics-based modeling with deep learning. These algorithms can be used to solve complex physical problems, such as fluid dynamics or heat transfer, by incorporating physical laws and constraints into the neural network architecture.

• Modelling the COVID-19 infection rate through a Physics-Informed learning approach
• Solving groundwater flow equation using physics-informed neural networkss
• Meshless methods for American option pricing through Physics-Informed Neural Networks
• A physics-informed learning approach to Bernoulli-type free boundary problems
• Scientific Machine Learning Through Physics–Informed Neural Networks: Where we are and What’s Next
• Physics-informed neural networks approach for 1D and 2D Gray-Scott systems

Mathematical Modelling and Numerical Analysis
Machine learning and deep learning techniques can greatly enhance mathematical modeling by improving model selection and optimization, data preprocessing, simulation and optimization, uncertainty quantification, and model interpretability. These techniques can help to increase the accuracy and robustness of models, reduce computational complexity, and provide insights into complex systems.

• Kernel-based models for influence maximization on graphs based on Gaussian process variance minimization
• Effects of spatial decomposition on the efficiency of kNN search in spatial interpolations
• Remarks on the numerical approximation of Dirac delta functions
• RBF methods in a Stochastic Volatility framework for Greeks computation
• ARBF: adaptive radial basis function interpolation algorithm for irregularly scattered point sets