23/09/2021 09:42:00

Accepted Special Sessions


Organisers of Special Sessions are responsible for:

  • Select a topic of interest to conference delegates.
  • Obtain papers on this topic, normally at least 5 for an invited special session, but often more. At least 60% of the papers must be by authors that are neither session chairs from their team nor reviewers for the session. 
  • If there are short papers, the final accepted papers will be moved to the general track.
  • Manage the review process for these papers on due time and deadlines.
  • Provide suitable reviewers for the reviews of the papers.
  • Ensure the final versions of the papers are uploaded before the deadline.
  • Attend the conference and chair the session.
  • Provide a list of international reviewers (name, affiliation, country) who have already accepted to review the papers.
  • Disseminate a call for papers for the special session widely.


Special Session 1

Time Series Forecasting in Industrial and Environmental Applications (TSF)

  • Federico Divina – Pablo de Olavide University of Seville, Spain.
  • Mario Giacobini – University of Torino, Italy.
  • Julio César Mello Román – Universidad Nacional de Asunción, Facultad Politécnica, Paraguay.
  • Miguel García Torres – Pablo de Olavide University of Seville, Spain.
  • José F. Torres – Pablo de Olavide University of Seville, Spain.

Time series can be found in almost all disciplines nowadays. Thus, time series forecasting is becoming a consolidated discipline that provides meaningful information in various application areas, making their efficient analysis relevant to the scientific community. This session pays attention to the extraction of useful knowledge from time series in the context of industrial and environmental applications. The analysis of extensive time series, given its relevance in the emergent context of big data, is also encouraged. Topics of interest for the special session, always in the context of industrial and environmental applications, include but are not limited to:

  1. Machine learning applied to time series forecasting.
  2. Deep learning applied to time series forecasting.
  3. New approaches for big data time series forecasting.
  4. Hybrid systems for time series analysis.
  5. Ensemble approaches for time series analysis.


Special Session 2

Technological Foundations and Advanced Applications of Drone Systems (TFAADS)

  • James Llinas – University at Buffalo, USA.
  • Jesús García – Universidad Carlos III de Madrid, Spain.
  • José Manuel Molina – Universidad Carlos III de Madrid, Spain.
  • Ana Bernardos – Universidad Politécnica de Madrid, Spain.
  • Juan Alberto Besada – Universidad Politécnica de Madrid, Spain.

Unmanned aerial systems (UAS), a.k.a. “drones,” have evolved rapidly in recent years thanks to advancements in navigation, perception, information fusion, and Artificial Intelligence (AI) technologies, allowing an increase in autonomous operations and evolving applications in defense and the civil areas. For example, among the most popular uses of drone systems is to inspect industrial infrastructure (oil refineries, telecommunications, power towers, wind turbines, solar plants, etc.). Development of such systemic capabilities requires associated research and development infrastructure to include novel simulation capabilities that allow the study of enriched simulation scenarios, such as GIS layers with information inferred from drone data, to enhance and extend GIS databases automatically. Technology advancements supporting these system applications are in a state of evolution. Key technologies to develop UAS and UAS systems include autonomous navigation (to execute missions autonomously integrating complementary sensors), machine vision and machine learning, and swarm coordination to achieve coherent behavior and mission objectives. In addition, defense applications require systems to detect, track, and monitor UAS and UAS swarms, an evolving area of concern to protect against possible threats. This session will cover technological advancements, infrastructure advancements, and applications based on UAS systems, including critical functions such as navigation, perception, and coordination.


Special Session 3

Soft Computing Methods in Manufacturing and Management Systems (SCMMMS)

  • Damian Krenczyk – Silesian University of Technology, Poland.
  • Anna Burduk – Wroclaw University of Science and Technology, Poland.
  • Bożena Skołud – Silesian University of Technology, Poland.
  • Wojciech Bożejko – Wroclaw University of Science and Technology, Poland.
  • Marek Placzek – Silesian University of Technology, Poland.

Management of manufacturing systems involves the development of detailed solutions related to decision-making and problem-solving processes. There are many important decisions and high-complexity problems to solve (NP-hard) related to, e.g., processes organization, planning, and control of manufacturing systems. Special attention is paid to inexact solutions for which no known algorithm can obtain an exact solution in polynomial time. Research into new production management methods is also driven by the need to increase the autonomy and flexibility of production systems. The answer to these needs is production focused on cyber-physical systems, which are one of the paradigms of the Industry 4.0 concept. This session aims to present the research results related to the management of production systems. Considering the complexity of production management problems, soft computing and intelligent methods may deliver adequate answers. The main covered topics are:

  1. Manufacturing Systems Integration
  2. Optimization of Manufacturing Systems
  3. Modelling and Design
  4. Control and Supervision
  5. Industry 4.0
  6. Production Planning and Scheduling
  7. Virtual Organisation
  8. Data Mining and Data Recognition
  9. Production System Organization
  10. Production Management
  11. Discrete Optimization
  12. Line Balancing
  13. Parallel Algorithms
  14. Artificial Intelligence


Special Session 4

Efficiency and Explainability in Machine Learning and Soft Computing (EEMLSC)

  • María del Mar Martínez Ballesteros – University of Seville, Spain.
  • Manuel Jesús Jiménez Navarro – University of Seville, Spain.
  • Manuel Carranza García – University of Seville, Spain.
  • Belén Vega Márquez – University of Seville, Spain.
  • José María Luna Romera – University of Seville, Spain.
  • David Gutiérrez Avilés – University of Seville, Spain.

Explainable Artificial Intelligence (AI) is a current focus in AI research, enabling humans to understand and trust the decision-making of this technology. Although traditional machine learning models have been considered black boxes, new techniques have been developed to extract knowledge from them locally and globally. However, AI has a significant carbon footprint, which is where Green AI comes in. Green AI uses algorithms that promote inclusivity and environmental friendliness, and the key is to balance the amount of data, time, and iterations necessary to train a model. Considering its ecological impact, it is crucial to consider the energy cost and carbon footprint from the beginning and decide how critical it is to create or improve a model. This session aims to address two main topics. Firstly, to propose new methodologies or apply existing explainable/interpretable AI techniques to Machine Learning and Soft Computing models. Secondly, to improve the efficiency of Machine Learning and Soft Computing models without compromising their effectiveness. In addition, the special session will cover assorted topics related to industrial and environmental applications, such as but not limited to:

  1. Applications of existing explainable AI methods.
  2. Efficient or explainable methods for black box models.
  3. Preprocessing techniques for efficiency improvement and explainability support.
  4. Novel Global and Local model-agnostic methods.
  5. Novel example-based explanations.
  6. Hardware/software design for energy-efficient models/explanations.
  7. Create human-friendly explanations and tools for non-technical users.
  8. Other relevant topics and applications related to efficiency and explainability in Machine learning and Soft Computing models, such as but not limited to: Blackbox models, Parallel computing, Federal learning, Decision support systems, Social impact, Health, Risk factors, Artificial vision, Natural language processing, Time series, Tabular data.


Special Session 5

Machine Learning and Computer Vision in Industry 4.0 (MLCVI)

  • Enrique Dominguez – University of Malaga, Spain.
  • Jose Garcia Rodriguez – University of Alicante, Spain.
  • Ramon Moreno Jiménez – Grupo Antolin, Spain.

In the coming years, the use of machine learning and computer vision in the industry is a trend that is changing not only large corporations but also small and medium-sized businesses. Thanks to these technologies, industrial innovation is giving rise to “smart factories,” allowing them to obtain multiple advantages. This special session provides a platform for academics, developers, and industry-related researchers to discuss, share experiences, and explore new technological advances. The objective is to integrate an international scientific community working on industrial applications of machine learning and computer vision for fruitful discussions and ideas on the evolution of these technologies. Topics:

  1. Computational intelligence
  2. Machine learning
  3. Deep learning
  4. Self-organization and self-adaptation
  5. Computer vision
  6. Video and image processing
  7. Biometric features extraction
  8. Pattern recognition
  9. Surveillance systems
  10. Hardware implementations
  11. Smart manufacturing
  12. Autonomous vehicles/machines
  13. Quality control
  14. Demand prediction
  15. Data visualization


Special Session 6

Genetic and Evolutionary Computation in Real World and Industry (GECRWI)

  • Camelia Chira – Babes-Bolyai University, Romania.
  • Dragan Simic – University of Novi-Sad, Serbia Republic.
  • Dominik Olszewski – Warsaw University of Technology, Poland.
  • Beatriz De la Iglesia – University of East Anglia, Norwich, UK.
  • Petrica Pop – Technological University of Cluj-Napoca, Romania.
  • Nashwa El-Bendary – Arab Academy for Science Technology and Maritime Transport College of Computing and Information Technology, Egypt.
  • Javier Sedano – Instituto Tecnológico de Castilla y León, Spain.
  • José R. Villar – University of Oviedo, Spain.

Genetic and Evolutionary Computation (GEC) has been extensively used for solving a wide variety of problems in industry and real-world applications. These techniques have also been proposed for enhancing the learning processes in machine learning and other data mining algorithms. Their applicability has been gathering the research community’s focus for decades, with applications to almost every human activity: business, management, design optimization, operational research, etc. The design and practical issues related to applying GEC in industry or real-world problems represent a challenge that must be solved to obtain a feasible solution. In this context, efficiency, low-cost procedures, and the needed problem formulation simplifications are some of the main aspects to consider when designing and developing solutions. Besides, introducing and cohabitating techniques, such as multi-objective or reinforcement learning, added potential uses to these optimization techniques, widening their applicability and capabilities. This special session aims to gather the latest developments of GEC applications in industry and real-world problems. Therefore, contributions to GEC applications in industrial processes, business, management, or engineering are welcomed. Moreover, theoretical studies are also accepted, as they directly impact the design and practical issues on GEC applied to natural world systems. The list of topics of interest includes (but does not limit to):

  1. Operation management
  2. Supply chain management
  3. Planning and scheduling problem
  4. Maintenance and monitoring optimization
  5. Design optimization
  6. Optimizing transportation systems
  7. Cyber-physical system design
  8. Large-scale real-world systems
  9. Multi-objective real-world problems
  10. Reinforcement Learning and Optimization
  11. Hyper-heuristics
  12. Evolutionary machine learning and swarm intelligence
  13. Evolutionary robotics


Special Session 7

Soft Computing Applied to Renewable Wind and Wave Energy Systems (SCARWWES)

  • J. Enrique Sierra García – University of Burgos,Spain.
  • Matilde Santos Peñas – Complutense University of Madrid, Spain.
  • Fares M’zoughi – University of the Basque Country, Spain.
  • Payam Aboutalebi – Norwegian University of Science and Technology, Norway.
  • Bowen Zhou – Northeastern University, China.
  • Guangdi Li – Northeastern University, China.

Coal-fired power plants have been identified as one of the significant causes of climate change. Although CO2 emissions are mainly produced by thermal power plants, these energy sources are still widely used nowadays. As a result, there is a widespread consensus that renewable energy sources such as wind, marine, hydro, and solar must be considered to mitigate climate change and reduce air pollution. Consequently, research on renewable energies, particularly the control and efficiency of wind and wave energy systems, are encouraged to contribute to this sustainable global energy transformation. Expert systems, fuzzy control, neural networks, metaheuristic algorithms, artificial immune networks, swarming particle techniques, ACO, reinforcement learning, and other soft computing techniques are effective in many fields. Moreover, they can be applied to tackle complex problems where conventional methods are less efficient or unsuccessful. This special session aims to provide a platform for researchers, engineers, and industry professionals from different fields to share and exchange their innovative ideas, research results, and experiences in soft computing techniques applied to renewable energy systems. Contributions to this special session are welcome to present and discuss novel methods, algorithms, control techniques, frameworks, architectures, platforms, and applications. Session topics include, but are not limited to, the following strategies and approaches applied to renewable energy systems:

  • Intelligent control: fuzzy control, neuro-control, neuro-fuzzy, intelligent-PID control, …
  • Learning systems: reinforcement learning, machine learning, and deep learning applications to renewable energy systems
  • Optimization by heuristic techniques in system engineering and control
  • Modelling and identification by Soft Computing techniques
  • Identification and control by hybrid intelligent strategies


Special Session 8

Soft Computing and Hard Computing for a Data Science Process Model (SCHC-PM)

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

Data science projects may be face with a few different methodologies. Going back to the roots, KDD is the first approach, moving ahead newer names have been coined like CRISP-DM, DMME, etc. and more recently DASC-PM (Data Science Process Model). Data generation speed is continuously being increased and their storage is an important matter whereas the data processing is done. Different terms have been mentioned starting from the initial byte crossing through gigabyte, terabyte and so on; yottabyte is up to now the highest magnitude defined to store the information. A machine learning task is required to process the data, which may include different kinds of pre-processing. The support of soft computing and hard computing is crucial for any stage of the DASC-PM methodology. This special session welcomes works concerning any real-world application or part of it where soft computing or hard computing are a tool to achieve the final prediction or the last product of the data provision phase. The scope may be concerning supervised, unsupervised or semi-supervised learning. The topics of interest for this thematic session comprise, but are not limited to:

  • Data provision<\li>
  • Data preparation<\li>
  • Data management<\li>
  • Exploratory analysis<\li>
  • Analysis phase<\li>
  • Deployment phase<\li>
  • Utilization phase<\li>
  • Data integration<\li>
  • Data transformation<\li>
  • Data storage<\li>
  • Feature selection<\li>
  • Outlier detection<\li>
  • Outlier removal<\li>
  • Noise smoothing<\li>
  • Instance selection<\li>
  • Data rebalancing<\li>
  • Missing values imputation<\li>
  • Random projection<\li>
  • Informative projection<\li>
  • Data normalization<\li>
  • Text-based user interfaces to pre-process big data<\li>
  • Medical data analysis<\li>
  • Finance<\li>
  • Social sciences<\li>
  • Education<\li>
  • Science applications<\li>
  • Communication<\li>
  • Instrumentation<\li>
  • Electronic technology<\li>
  • Signal processing<\li>
  • Audio processing<\li>
  • Video processing<\li>
  • Automation<\li>
  • Networks of any type<\li>