Papers such as An Introduction to Machine Learning for Panel Data and Split Decisions: Practical Machine Learning for Empirical Legal Scholarship have recognized the tantalizing possibility that a single dataset, properly curated, can support the following methodological progression

1. 1.- Conventional linear methods, including:
1.   a) OLS
2.   b) Fixed effects
3.   c) Random effects
2. 2.-Machine-assisted regression methods, including:
1.   a) Local regression, both as:
1.     - A data preparation method
2.     - A tool for prediction and forecasting
2.   b) Regularized regression (incorporating ℓ2 and/or ℓ1 penalties)
3.   c) Robust regression (such as Huber and Theil-Sen)
3. 3.-Supervised machine learning, including:
1.   a) Random forests and extra trees
2.   b) Gradient boosting
3.   c) Support vector machines
4.   d) Simple neural networks
4. 4.-Stacking generalization
5. 5.-Unsupervised machine learning, including:
1.   a) Clustering of time series and panel data
2.   b) Manifold learning

Organizers:

Prof. Dr. James Ming Chen, is Justin Smith Morrill Chair in Law and Professor of Law at Michigan State University.

James Ming Chen is Justin Smith Morrill Chair in Law and Professor of Law at Michigan State University. Professor Chen holds a law degree from Harvard University and a master's degree in data science from Northwestern University. He is a member of the American Law Institute and a senior fellow of the Administrative Conference of the United States. Professor Chen's scholarship covers law, economics, and machine learning.

Resilient critical infrastructure is a must within Agenda 2030 where Sustainable Development Goals (SDG) recommend to “Build resilient infrastructure to promote sustainable industrialization and foster innovation”.

These systems, like energy, water and transport systems, are increasingly challenged by the frequency and intensity of natural adverse events. The availability of climate scenarios and environmental monitoring and forecast data, as well as the digitalization of the system control functions and processes, provide new opportunities for the development and application of analysis methods of time series: by allowing modelling the systems behaviour, time series analyses enable to evaluate operational risks and to support resilience enhancement. The application of theoretical methods to simulate the physical and functional performance of critical infrastructures is challenged by the complexity and availability of interdisciplinary domain knowledge, which is indeed required to build reliable models for the behaviour predictions and simulation of real systems.

This special session aims to present successful applications of time series modelling and forecast of series representing the behaviour of complex socio-technical systems such as critical infrastructures to increase their sustainability and resilience to natural hazards. Submissions are expected to reflect both advancement of theoretical methods based on real problems and experimental works in statistical analysis and soft computing applications to time series related to such domains.

Suggested topics of this special session include but are not limited to:

1. - Approaches for spatio-temporal data series modelling of safety-critical systems and their vulnerability to natural hazards.
2. - Critical evaluation and comparisons of alternative approaches for experimental time series modelling and analysis.
3. - Case studies for time series modelling and analysis to the aims of sustainable and resilient systems.
4. - New software environments, such as digital twins, for data analysis and applications for solving problems related to sustainable and resilient systems.
5. - Soft computing and fuzzy techniques for engineering time series data.
6. -Novel approaches for incorporating uncertainty and variability in time series analysis of critical infrastructures.
7. -Application of advanced sensor technologies for real-time data collection and its impact on the resilient infrastructure systems.
8. -Resilience-oriented optimization methods for critical infrastructure design and operation based on time series insights.

The participants will be invited to submit their extended articles to the following journals:

Sustainability (MDPI) indexed within Scopus, ESCI (Web of Science) – IF 3.9, Special issue:

Sustainable Cities: Smart Resilience against Natural Hazards - https://www.mdpi.com/journal/sustainability/special_issues/YJTUS8MZ18

Information (MDPI) - indexed within Scopus, ESCI (Web of Science) – IF 3.1, Special issue: IoT-Based Systems for Resilient Smart Cities https://www.mdpi.com/journal/information/special_issues/UC6BS60S2L

A discount fee might be granted based on the reviewers’ evaluations.

Organizers:

Dr. Maria Luisa Villani, Senior researcher at ENEA National Agency for New Technologies, Energy and Sustainable Economic Development, Rome, Italy

Maria Luisa Villani is a senior researcher at ENEA National Agency for New Technologies, Energy and Sustainable Economic Development, Rome, Italy. She holds a PhD in Mathematics at University of Warwick (England). Her research interests are on tools for risk assessment and resilience of critical infrastructures to natural hazards, also based on artificial intelligence methods, and IoT system architectures for smart cities. ORCID ID: https://orcid.org/0000-0002-7582-806X

Dr. Ebrahim Ehsanfar, Senior research fellow at the Fraunhofer Institute for Material Flow and Logistics in Dortmund, Germany

Ebrahim Ehsanfar is a senior research fellow at the Fraunhofer Institute for Material Flow and Logistics in Dortmund, Germany. Possessing expertise in machine learning, he holds a Master's degree in Computer Science and is currently pursuing a Ph.D. in Logistics at the Technical University of Dortmund. ORCID ID: https://orcid.org/0000-0002-6782-1503

Dr. Sonia Giovinazzi, Research project manager for ENEA, Rome, Italy

Sonia Giovinazzi is a research project manager for ENEA, Rome, Italy. She is Associate Professor in Civil Engineering, adjunct at Sapienza University of Rome, and acts as a consultant at the World Bank for climate change and disaster risk assessment for national infrastructure plans. Sonia holds a Ph.D. in Risk Management of Natural and Anthropogenic Hazards on the Built Environment. ORCID ID: https://orcid.org/0000-0003-0820-5003

Guaranteeing the availability of water in quantity and quality is essential not only to preserve and maintain the environment, but also to support socio-economic development. However, the increasing population and economic growth, the increasing demand for water and the more than evident modifications in the patterns of the hydrological cycle, due mainly to anthropogenic global warming, are seriously compromising the sustainability of water resources. This complexity also represents a challenge for the development of innovative approaches to capture and reveal the intrinsic nature of these induced modifications and to advance towards the sustainability of water resources. In this sense, approaches based on Artificial Intelligence and advanced statistical techniques can help to identify these modifications and to generate efficient and robust predictive models.

This special section, focused on enhancing the resilience of water systems, covers a range of suggested topics, including: innovative methodologies for time series analysis, spatio-temporal hydrological-hydraulic analysis, advancements in forest restoration and agriculture, the reuse of non-conventional water resources, techniques for improving water quality, the concept of water circularity, advances in water quality modelling, advances in the definition of new chemical and ecological water índices and modifications in water quality parameters due to climate change. Through this collaborative effort, the objetive is to make a significant contribution to the ongoing discussion on advancing the sustainability of water resources.

Guest Editors Profs. Dr. Santiago Zazo, Dr. José-Luis Molina, Dr. Fernando Espejo and Dr. Carmen Patino-Alonso Special Issue (SI): “Advances in water allocation and optimal reservoir operation: Artificial intelligence and statistical modelling in water resources sustainability”, in Journal Water MDPI.

www.mdpi.com/journal/water/special_issues/L1LP417CR3

Organizers:

Prof. Santiago Zazo del Dedo , IGA Research Group - University of Salamanca, Spain.

Prof. Santiago Zazo del Dedo, Dr. José-Luis Molina, Dra. Carmen Patino, Dr. Fernando Espejo and Dr. Juan Carlos García.

Organizer:

Prof. Dr. Hasanthi Pathberiya ,Senior Lecturer in Statistics Department of Statistics University of Sri Jayewardenepura.

The special session titled "Forecasting Financial Markets" at the upcoming conference on ITISE is designed to delve into the intricacies and evolving dynamics of financial markets prediction. This session aims to bring together leading academics, researchers, and practitioners to explore cutting-edge methodologies and innovations in forecasting financial markets. Participants will have the opportunity to discuss the application of traditional time series analysis techniques, and newer machine learning approaches, including neural networks and deep learning, to predict market movements, volatility, and trends. Emphasis will be placed on the challenges of modeling financial data, which is often non-linear, non-stationary, and influenced by a myriad of factors ranging from macroeconomic indicators to geopolitical events.

Furthermore, this session will explore the practical implications of financial market forecasting on portfolio management, risk assessment, algorithmic trading, and regulatory compliance. We will examine case studies that demonstrate the successful application of forecasting models in real-world scenarios, as well as discuss the ethical considerations and potential biases in model development and implementation. The goal is to foster a rich dialogue on the future direction of financial markets forecasting, encouraging collaboration and innovation among participants. This session promises to provide valuable insights into how emerging technologies and analytical techniques can enhance our understanding and prediction of complex financial systems, ultimately contributing to more robust and resilient financial markets.

Organizer:

Prof. Nengxiang Ling ,Hefei University of Technology, Hefei, China.

This special session is set to provide a comprehensive overview of the latest advancements and methodologies in the analysis of functional data observed over time. Functional time series analysis extends beyond traditional time series by considering data that are functions or curves at each time point, enabling a more nuanced understanding of complex dynamics in various fields.

Participants will delve into the theoretical underpinnings of functional data analysis (FDA) and discuss how these methods can be applied to capture the intrinsic variability in datasets.

Moreover, the session will highlight the practical applications of functional time series analysis across a diverse range of disciplines such as finance, meteorology, environmental science, and health sciences. Presentations and discussions will focus on how these techniques are used to model and forecast complex phenomena, such as intraday price curves in financial markets, daily temperature profiles, pollution levels over time, and growth curves in biostatistics. The goal is to foster an interdisciplinary exchange of ideas, promoting the integration of FDA techniques into mainstream time series analysis and encouraging collaboration between statisticians, data scientists, and domain experts. By exploring both the methodological innovations and their applications, this session aims to provide attendees with a deeper understanding of the potential of functional time series analysis to address contemporary challenges in data analysis and prediction.

Forecasting high-dimensional data and analysis of time series with hundreds/thousand of attributesinations) is challenging problem, with application in multiple problems of real life (problems in economy, energy, climate, etc). Real problems in which you have to predict / analyze or treat large volumes of data are welcome to this session.

Organizers:

Prof. Fernando Rojas and Prof. Luis Javier Herrera ,University of Granada, Spain.

This session is designed to address the growing challenges and opportunities presented by the analysis of high-dimensional and complex datasets. In an era where big data has become ubiquitous across various industries, from finance and marketing to healthcare and environmental studies, the need for sophisticated forecasting methods that can effectively handle the volume, variety, and velocity of such data is more critical than ever. This session aims to explore the latest developments in statistical and machine learning techniques tailored for high-dimensional time series forecasting. Topics will include dimensionality reduction, regularization methods, and advances in computational algorithms that enable the extraction of meaningful patterns and predictions from large datasets.

In addition, this session will provide a platform to discuss the application of these advanced forecasting methods in real-world scenarios and illustrate how they can uncover insights and support decision making in complex systems. Attendees will hear from experts who have successfully overcome the challenges of working with big data, including dealing with sparsity and dependency structures in high-dimensional spaces, integrating heterogeneous data sources, and ensuring the interpretability and robustness of models. The discussions emphasise innovative approaches such as the use of deep learning and ensemble models to improve prediction accuracy and reliability. Through a combination of theoretical insights and practical case studies, this session aims to equip participants with the knowledge and tools to harness the power of big data for forecasting in their respective fields, paving the way for breakthrough advances in time series analysis.

Within the field of science and engineering, it is very common to have data arranged in the form of time series data which must be subsequently analyzed, modeled and classified with the eventual goal of predicting future values. The literature shows that all these tasks related to time series can be undertaken using computational intelligence methods. In fact, new and further computational intelligence approaches, their efficiency and their comparison to statistical methods and other fact-checked computational intelligence methods, is a significant topic in academic and professional projects and works. Therefore, this special session aims at showing to our research community high quality and state of the art computational intelligence (and statistical) related works, applied to time series data and their tasks: analysis, forecasting, classification, and clustering. Furthermore, the experts can, from the starting point that the works shown provide, discuss different solutions and research issues for these topics.

Organizer:

Prof. Hector Pomares ,University of Granada, Spain.

In the rapidly evolving field of time series analysis, the integration of computational intelligence (CI) methods represents a frontier of innovation and exploration. The special session on "Computational Intelligence Methods for Time Series" will address the synergies between AI techniques and time series analysis, focusing on how artificial intelligence, machine learning and evolutionary algorithms can improve predictive modelling and analysis. This convergence aims to tackle complex and dynamic time series data by utilising AI's adaptability, learning ability and robustness to noise and uncertainty.

This session is not only about presenting novel AI methods, but also about demonstrating their practical effectiveness in various areas such as finance, healthcare, environmental monitoring and energy forecasting. The focus will be on the use of neural networks, fuzzy systems, genetic algorithms and hybrid models to extract patterns, make predictions and uncover hidden structures in time series data. The focus is on overcoming challenges such as non-linearity, high dimensionality and prediction of rare events. Through a combination of technical presentations, case studies and interactive discussions, participants will learn how AI methods can be used creatively to advance the field of time series analysis and provide solutions that are not only computationally efficient, but also interpretable and scalable.

This special session aims to present the latest research on the study of risk in financial markets through econometric modelling of financial market trends. A wide range of studies applying econometric methods to financial issues are collected, covering topics such as interest rate fluctuations, volatility modelling, factor model analysis, risk and portfolio management, and the exploration of uncertainty in a financial framework. Moreover, as sustainable investment and financial products linked to sustainability, together with the different uses of cryptocurrencies, are a current trend, several of the papers presented in this special session will focus on these topics.

Organizers:

Prof. María de la O González and Prof. Marta Tolentino, University of Castilla-La Mancha, Spain.

Recent advances in remote sensing techniques have created a great opportunity to effectively and continuously monitor the land surface. These techniques include Interferometric Synthetic Aperture Radar (InSAR), Persistent Scatterer InSAR (PS-InSAR), Light Detection And Ranging (LiDAR), Global Navigation Satellite Systems (GNSS), Close-Range Photogrammetry (CRP), Robotic Total Station (RTS), and Spectral Indices, such as NDVI, EVI, NDWI, etc. by remote sensing satellites, such as MODIS, Landsat, Sentinel 2, etc. Spatio-temporal land surface monitoring can be rigorously carried out by analyzing the time series acquired from these techniques. Processing such time series can also be very challenging for several reasons, such as non-uniform sampling, biases as a result of preprocessing, and atmospheric/environmental noise. The aim of this Special Session is to collect papers (original research articles and review papers) that offer insights into effectively monitoring and measuring land cover changes and land deformation using remotely sensed time series data.

Prof. Ebrahim Ghaderpour is serving as an Associate Editor of Discover Applied Sciences (Springer Nature), formerly known as SN Applied Sciences (2.6 2022 Impact Factor).

Prof. Ebrahim Ghaderpour is currently running a Special Issue in my section Earth and Environmental Sciences. The title of my special issue is "Earth Surface Monitoring Using Remote Sensing Data and Artificial Intelligence". Please find more detail about this special issue here: https://link.springer.com/collections/hejdcjdahe

Organizers:

Prof. Ebrahim Ghaderpour, Department of Earth Sciences, Sapienza University of Rome, P.le Aldo Moro, 5, 00185 Rome, Italy 2. Department of Geomatics Engineering, University of Calgary, Calgary, AB 2TN 1N4, Canada.

Environmental and civil engineering are closely related disciplines that collaborate to address the environmental impacts of infrastructure development, promote sustainability, and protect natural resources. Their interdisciplinary approach is essential for addressing complex environmental challenges and creating a more sustainable built environment. With increasing concerns about environmental sustainability, civil engineers are tasked with incorporating environmentally friendly practices into their designs. This includes using environmentally friendly materials, utilising energy-efficient technologies, and designing structures that minimize their impact on the environment.

Soft computing techniques, such as neural networks, fuzzy logic, and genetic algorithms, have become indispensable in various fields of engineering, especially in civil engineering, as they are able to process complex and uncertain data effectively, especially in time series analysis. Time series data is widely used in civil engineering applications such as structural health monitoring, traffic flow prediction, and environmental monitoring. By employing soft computing methods, engineers can analyze and predict time series data, enabling flexible and robust approaches in these applications. In environmental monitoring and management, for example, soft computing techniques are used to analyse time series data relating to parameters such as air quality, water levels and temperature. This enables engineers to recognise trends, predict future environmental conditions and make informed decisions about the environmental management of construction projects.

One significant application of soft computing in civil engineering is in structural health monitoring, where techniques like neural networks and fuzzy logic systems are used to analyze structural responses captured by sensors over time. These methods enable the real-time assessment of structural integrity, detection of anomalies, identification of damage, and prediction of future structural behavior, facilitating timely maintenance and repair decisions to ensure safety and longevity. Moreover, soft computing methods play a crucial role in predictive maintenance by analyzing historical sensor data to predict potential failures and prioritize maintenance activities, optimizing maintenance schedules, minimizing downtime, and extending the lifespan of critical infrastructure assets. Additionally, in construction project planning and management, soft computing techniques are employed to optimize schedules, resource allocation, and cost estimation, providing accurate planning and proactive management, while in construction monitoring, real-time sensor data analysis enables engineers to monitor progress, safety, and quality, ensuring project success through timely decision-making.

In collaboration with colleagues from several countries as part of the IM4StEM project (https://im4stem.eu/en/home/), we emphasize the crucial link between the environment and civil engineering. The fields of civil engineering and the environment are closely linked. Civil engineers have a major responsibility to design and monitor infrastructure in a way that minimizes environmental degradation and promotes sustainability.

Organizers:

Prof. Marijana Hadzima-Nyarko, Marijana Hadzima-Nyarko is a Full Professor at the Faculty of Civil Enigneering and Architecture Osijek, Josip Juraj Strossmayer University of Osijek, Croatia. Her scientific and professional fields include seismic engineering, seismic risk and structural engineering of concrete and masonry structures. She is a member of several scientific committees of domestic and international journals, conference organizing committees and a reviewer for several domestic and international journals. https://orcid.org/0000-0002-9500-7285

Prof. Francisco Martínez-Álvarez, Francisco Martínez-Álvarez is a Full Professor in the Data Science and Big Data Lab at Pablo de Olavide University. His main research lines include time series forecasting, deep learning and big data analytics. He has led a great number of research projects, both national and international. Moreover, he has been the principal investigator in industrial projects involved in IoT, machine learning, data mining and artificial intelligence. ORCID ID: https://orcid.org/0000-0002-6309-1785

Prof. Dorin Radu, Dorin Radu is an Associate Professor at the Faculty of Civil Engineering at Transilvania University of Brașov. He holds a PhD in Civil Engineering - Structural Integrity of Steel Structures and has teaching and research activities in Civil Engineering since 2003. His research interests are on structural integrity, optimization of structural elements, neural networks applied in civil engineering, and new materials for sustainable constructions. ORCID ID: https://orcid.org/0000-0001-5043-2723

Prof. Borko Bulajić, Borko Bulajić is an Associate Professor at the Faculty of Technical Sciences, University of Novi Sad, Serbia. He has given lectures on a variety of topics, including Natural Hazards, Risk Analysis Methods, Civil Engineering Design Fundamentals, and Earthquake Engineering. His academic work focuses on how deep geological site surroundings affect surface strong motion. He participated in a number of seismic microzonation studies as a member of an international team of experts from the USA, Serbia, Croatia, Bosnia and Hercegovina, North Macedonia, and India, being the person in charge of the geological zoning. In addition to working in academia, he has more than 18 years of expertise as a civil engineer. ORCID ID: https://orcid.org/0000-0002-9241-1469

Prof. Emmanuel Karlo Nyarko, Emmanuel Karlo Nyarko is an Associate Professor at the Department of Computer Engineering and Automation at the Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Josip Juraj Strossmayer University of Osijek. He teaches various professional, (under)graduate and postgraduate courses in automation, programming, artificial intelligence (machine learning, soft computing) and robot vision.His research interests include robot vision, artificial intelligence and the application of machine learning methods in various fields. ORCID ID: https://orcid.org/0000-0001-8041-3646