Special Sessions

Description:

Federated Learning, a rapidly evolving field in Machine Learning, revolutionizes the way models are trained by fostering collaboration without the need for data transfer between devices. This innovative approach empowers machine learning models to be trained on decentralized data sources, eliminating the requirement for centralized data storage. 

Moreover, a current trend gaining significant attention pertains to (pre) aggregation functions and their versatile applications. This domain encompasses the study of aggregation operators and explores how their strategic implementation can enhance system quality and performance.

In light of these compelling advancements, the primary objective of this special session is to establish a dynamic platform for esteemed researchers to showcase their cutting-edge research in Federated Learning and (pre) aggregation functions. The session specifically aims to explore their theory and practical applications in the domains of classification problems.

Topics of interest:

This special session on Federated Learning will cover a broad range of topics, including but

not limited to:

• Federated Learning: concepts and theory.

• Privacy in Federated Learning: Techniques for preserving privacy and security in Federated Learning.

• Applications in classification problems: Research on the use of Federated Learning for classification problems, such as image classification, speech recognition, information retrieval, natural language processing and related.

• Applications in computer vision: Research on the use of Federated Learning for computer vision problems, such as object detection, segmentation, and tracking. 

• (pre) Aggregation: theory and applications.

• Fuzzy logic and uncertainty management.

• Distributed Learning in Robotics.

Organizers:

• Jaime Andrés Rincon - Universitat Politècnica de València, Spain

• Cedric Marco-Detchart - Universitat Politècnica de València, Spain

• Vicente Julian - Universitat Politècnica de València, Spain

• Carlos Carrascosa - Universitat Politècnica de València, Spain

• Giancarlo Lucca - Universidade Federal do Rio Grande, Brazil

• Graçaliz P. Dimuro - Universidade Federal do Rio Grande, Brazil

Description:

CO2 emissions have been identified as one of the significant causes of climate change. These emissions are mainly produced by non-renewable energy production systems and non-sustainable transport means, still widely used nowadays. As a result, there is a widespread consensus that renewable energy sources such as wind, marine, hydro and solar as well as green transport systems must be considered to mitigate climate change and reduce air pollution. Consequently, research on renewable energies and green transport, particularly, on control and efficiency is encouraged to contribute to this sustainable trend. 

Expert systems, fuzzy control, neural networks, genetic algorithms, artificial immune networks, swarming particle techniques, ACO, reinforcement learning, and other intelligent techniques have been shown to be effective in many different fields. They can be applied to tackle complex problems where conventional methods are less efficient or unsuccessful.

The goal of this special session is to provide a platform for researchers, engineers, and industrial practitioners from different fields to share and exchange their ideas, research results, and experiences in the field of intelligent techniques applied to renewable energy and green transport. Contributions to this special session are welcome to present and discuss novel methods, algorithms,  frameworks, architectures, platforms, and applications.

Topics of interest:

Session topics include but are not limited to:

• Intelligent control: fuzzy control, neuro-control, neuro-fuzzy, intelligent-PID control, ...

• Optimization by heuristic techniques in system engineering and control

• Modelling and identification by learning techniques

• Identification and control by hybrid intelligent strategies

• Real-world applications on wind, marine, and hydro renewable energy

• Real-world applications on transport and smart industry: AGVs and autonomous vehicles

Organizers:

• J. Enrique Sierra García, University of Burgos (Spain)

• Matilde Santos Peñas, Complutense University of Madrid (Spain)

• Payam Aboutalebi, Department of Marine Technology, NTNU, 7491 (Norway)

• Bowen Zhou, Northeastern University, Shenyang, (China)

Scope and topics:

Data selection focuses on reducing the training time and, at the same time, taking advantage to do better predictions. Too much information is not handy at all since uninformative samples or features may be learnt and consequently the ability to generalize could be hindered. Addressing any problem may mean not having prior knowledge and even to become able, through data selection and even transformation measure, to learn the important data for the forthcoming prediction on unseen data. Depending on the followed methodology to conduct the process model for data mining, the data selection may be named with different names although the core is the same. Tools based on graphical user interfaces are of particular interest in the sense that may make easier the procedure to refine the raw data and eventually to get the ready data to face the mining phase. Data pre-processing deals with many tasks such as data cleansing, attribute selection, instance selection, noise reduction and detecting wrong or distorted labels. Visual data analytics is on the rise especially in multi-dimensional business applications. It is not uncommon to require any data imputation task prior to the application of the data selection stage. We encourage to submit very recent applications and if possible unprecedented. Additionally, new theoretical or empirical approaches are welcome. 

Topics of interest for this session include but are not limited to:   

• Data selection

• Data pre-processing

• Data cleansing

• Data engineering

• Attribute selection

• Instance selection

• Data fusing

• Data mining

• Text mining

• Speech mining

• Signal mining

• Stream mining

• Motif mining

• Itemset mining

• Sequential pattern mining

• Frequent pattern mining

• Infrequent pattern mining

• Rare pattern mining       

Organisers/chairs:

• Antonio J. Tallón-Ballesteros, University of Huelva (Spain)

• Ireneusz Czarnowski, Gdynia Maritime University (Poland)