Abstract
The rapid integration of Machine Learning (ML) in organizational practices has driven demand for substantial computational resources, incurring both high economic costs and environmental impact, particularly from energy consumption. This challenge is amplified in dynamic data environments, where ML models must be frequently retrained to adapt to evolving data patterns. To address this, more sustainable Machine Learning Operations (MLOps) pipelines are needed for reducing environmental impacts while maintaining model accuracy. In this paper, we propose a model reuse approach based on data similarity metrics, which allows organizations to leverage previously trained models where applicable. We introduce a tailored set of meta-features to characterize data windows, enabling efficient similarity assessment between historical and new data. The effectiveness of the proposed method is validated across multiple ML tasks using the cosine and Bray-Curtis distance functions, which evaluate both model reuse rates and the performance of reused models relative to newly trained alternatives. The results indicate that the proposed approach can reduce the frequency of model retraining by up to 70% to 90% while maintaining or even improving predictive performance, contributing to more resource-efficient and sustainable MLOps practices.

Abstract
This paper proposes a multi-objective stochastic optimization framework that can be used by governments to run auctions and select the best community energy storage system (CESS) projects to support. The framework enables CESS providers and energy community members to equitably benefit from the economic value generated by CESSs. The auction accepts offers from competing CESS providers that constitute the data of the CESS location, size, install time, technology, provider, investment cost, and energy trading price. The auction is run by a government agency which selects CESS projects that maximize the economic benefits and distribute them equitably among CESS providers and community members. The multi-objective stochastic optimization accounts for the multi-year uncertainties of photovoltaic (PV) generation, real and reactive energy consumption, energy trading prices, and PV installations. We exploit the Monte Carlo simulation and scenario trees to model the aforementioned uncertainties. The K-Means clustering method is used to reduce the number of scenarios, and thereby, lessen the computational burden of the optimization problem. Our experiments on an Australian low-voltage network with a community of prosumers and consumers demonstrate that government financial support can accelerate the installation of CESSs and enhance their business viability. This can be achieved by boosting the economic benefits shared between CESS providers and communities and ensuring these benefits are distributed equitably. Also, our experiments show that the economic benefits of all stakeholders are further improved with a high growth of the number of PV installations, and a slight reduction of energy import and export prices over the planning period.

Abstract

Abstract
AbstractNon-pharmaceutical interventions (NPIs), including measures such as lockdowns, travel limitations, and social distancing mandates, play a critical role in shaping human mobility, which subsequently influences the spread of infectious diseases. Using COVID-19 as a case study, this research examines the relationship between restrictions, mobility patterns, and the disease’s effective reproduction number (Rt) across 13 European countries. Employing clustering techniques, we uncover distinct national patterns, highlighting differences in social compliance between Northern and Southern Europe. While restrictions strongly correlate with mobility reductions, the relationship between mobility and Rtis more nuanced, driven primarily by the nature of social interactions rather than mere compliance. Additionally, employing XGBoost regression models, we demonstrate that missing mobility data can be accurately inferred from restrictions, and missing infection rates can be predicted from mobility data. These findings provide valuable insights for tailoring public health strategies in future crisis and refining analytical approaches.

Abstract
Synthetic data is gaining increasing popularity for face recognition technologies, mainly due to the privacy concerns and challenges associated with obtaining real data, including diverse scenarios, quality, and demographic groups, among others. It also offers some advantages over real data, such as the large amount of data that can be generated or the ability to customize it to adapt to specific problem-solving needs. To effectively use such data, face recognition models should also be specifically designed to exploit synthetic data to its fullest potential. In order to promote the proposal of novel Generative AI methods and synthetic data, and investigate the application of synthetic data to better train face recognition systems, we introduce the 2nd FRCSyn-onGoing challenge, based on the 2nd Face Recognition Challenge in the Era of Synthetic Data (FRCSyn), originally launched at CVPR 2024. This is an ongoing challenge that provides researchers with an accessible platform to benchmark (i) the proposal of novel Generative AI methods and synthetic data, and (ii) novel face recognition systems that are specifically proposed to take advantage of synthetic data. We focus on exploring the use of synthetic data both individually and in combination with real data to solve current challenges in face recognition such as demographic bias, domain adaptation, and performance constraints in demanding situations, such as age disparities between training and testing, changes in the pose, or occlusions. Very interesting findings are obtained in this second edition, including a direct comparison with the first one, in which synthetic databases were restricted to DCFace and GANDiffFace.

Abstract
The interaction between humans and technology has always been a key determinant factor of adoption and efficiency. This is true whether the interaction is with hardware, software or data. In the particular case of Information Retrieval (IR), recent developments in Deep Learning and Natural Language Processing (NLP) techniques opened the door to more natural and efficient IR means, no longer based on keywords or similarity metrics but on a distributed representation of meaning. In this paper we propose an agent-based architecture to serve as an interface with industrial systems, in which agents are powered by specific Large Language Models (LLMs). Its main goal is to make the interaction with such systems (e.g. data sources, production systems, machines) natural, allowing users to execute complex tasks with simple prompts. To this end, key aspects considered in the architecture are human-centricity and context-awareness. This paper provides a high-level description of this architecture, and then focuses on the development and evaluation of one of its key agents, responsible for information retrieval. For this purpose, we detail three application scenarios, and evaluate the ability of this agent to select the appropriate data sources to answer a specific prompt. Depending on the scenario and on the underlying model, results show an accuracy of up to 80%, showing that the proposed agent can be used to autonomously select from among several available data sources to answer a specific information need. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.