ABSTRACT The growing reliance on fossil fuels for energy generation has raised concerns about their significant contribution to global warming and the associated risks of supply instability. Anaerobic Digestion (AD) within Wastewater Treatment Plants (WWTPs) offers a renewable alternative by producing biogas, while effective operational optimisation requires accurate forecasting of biogas yields under varying conditions. This study addresses this challenge by developing, tuning and evaluating five Deep Learning (DL) architectures for biogas production prediction: one‐dimensional Convolutional Neural Network (1D‐CNN), Long Short‐Term Memory (LSTM), Gated Recurrent Unit (GRU), Transformers and Residual Encoding. Among these, the GRU model demonstrated superior performance, achieving a Root Mean Square Error (RMSE) of 139.1 m 3 /day and a Mean Absolute Error (MAE) of 135.9 m 3 /day. The adaptability of the GRU model to different datasets was examined through Transfer Learning (TL), revealing a clear difference in performance depending on the TL approach used: the retrained model achieved a RMSE of 230.1 m 3 /day and a MAE of 229.9 m 3 /day, whereas the model without retraining exhibited higher errors of 358.7 and 358.8 m 3 /day, respectively. A key contribution of this work lies in its comprehensive Explainable Artificial Intelligence (XAI) analysis, which applied both ante hoc attention mechanisms and post hoc interpretability techniques such as SHAP and LIME. The XAI methods consistently identified biogas production, the study's target variable, as the most influential feature in the model's predictions. Among the remaining features, some changes were observed in their impact on model predictions. Moreover, the study highlighted how TL affects prediction performance and the stability and consistency of feature importance, thereby improving the transparency and trustworthiness of the forecasting models.

With the increasing adoption of AI in safety-critical applications within urban environments, the interpretability of these systems is paramount. This study explores the application of Explainable Artificial Intelligence (XAI) techniques to enhance transparency in audio-based detection of emergency vehicle sirens, a crucial component in urban sound management. Adopting methods such as SHAP (SHapley Additive exPlanations) values, Permutation Feature Importance, and model-specific feature scores, this research identifies key audio features, including mid-frequency spectral contrasts and targeted chroma components, which significantly help in distinguishing siren sounds among urban noise. The study examines various machine learning models, identifying K-Nearest Neighbors (KNN) and XGBoost as top performers; KNN excelled in class-specific precision, while XGBoost demonstrated strong cross-class discrimination. The findings highlight the potential of XAI in improving both accuracy and accountability for sound detection systems in safety-critical urban applications, advancing the deployment of transparent AI within smart city infrastructures.

Abstract Violence recognition is challenging because it can be presented in very different forms. For example, it can be present in an image by a person hitting another person or present in audio by a person being rude to another. Thus, audio and video are essential features to be analysed. In the audio approach, speech processing, music, and ambient sound are some of the main points of this problem since finding similarities and differences between these domains is necessary. Human activity can be classified into four different categories in the video approach, depending on the complexity and the number of body parts involved in the action. Examples of Human activity categories are considered: gestures, actions, interactions and activities. Recognizing human actions in the video becomes a challenge with this varied set of human activities. Furthermore, in the last years, the growth of deep learning techniques applied to this area has been enormous, and the reason is that their results surpass traditional signal processing on a large scale. This article is based on audio and video signals inside a vehicle to detect violence. Furthermore, the architecture used was ResNet model with Mel‐spectrogram methodology for audio signals. The proposed method for video signal representation was RGB, which applied four different models: C2D, I3D, X3D, and Flow‐Gated. Finally, multimodal fusion was applied at the end of the process.

Abstract In recent years, we have seen a growing need for energy, which has had environmental consequences through the use of fossil fuels. Some of the sectors of our society make intensive use of energy, as is the case with wastewater treatment plants (WWTPs). Through anaerobic digestion, these infrastructures can produce energy, therefore improve energy efficiency and decrease the environmental footprint. This study aims to design, tune and evaluate a hybrid deep learning (DL) model, called incremental dual path network (IDPN), to forecast energy production in an anaerobic reactor for the next two days. The hybrid model’s performance was compared against five DL models conceived: long short-term memory (LSTMs), multi-layer perception (MLP), gated recurrent units (GRUs), Transformers and convolutional neural networks (CNNs). Furthermore, two data processing strategies were applied due to system failures and missing values. Four model evaluation metrics and the obtained results show that the hybrid model, which combines LSTMs and CNNs, presented the best performance in both approaches of data processing, with the best candidate model presenting a mean absolute error (MAE) of 312.1 kWh, root mean squared error (RMSE) of 341.6 kWh, mean absolute percentage error (MAPE) of 15.9% and R $$^{2}$$ 2 of 0.95. Following this, an ablation study was conducted, demonstrating that across several variations, the baseline IDPN consistently achieved the best results. Moreover, in both approaches, the removal or modification of the CNN led to a severe decline in performance, surpassing the impact of altering the LSTM, reinforcing its importance in the model’s architecture.

Abstract Object detection is one of the most fundamental problems to tackle in the computer vision research area. Recent advances in multimodal data streams and deep learning architectures have prompted a fast growth in the field of multimodal learning, which brings several advantages over single-modality approaches for object detection, such as improved accuracy, robustness to noise and ambiguity, handling of complex scenarios and adaptability to diverse data. Some of the biggest challenges when implementing a multimodal learning approach are the selection of the fusion strategy, design of processing architecture, modality alignment/synchronization and interpretability of such high-dimensional representations. To address this challenge, we propose a feature-level fusion architecture for object detection based on extracting YOLO features from images, spectral and rhythm features from sound using Mel-frequency cepstral coefficients, and general descriptors from radar modalities that, after timestamp and homography transformation matrix alignment, are combined with an attention mechanism into a single classification network. Preliminary experiments indicate that the proposed architecture can constitute itself as a base pipeline for several different multimodal object detection tasks in real-world applications.

In recent years, in the field of education, there has been a progressive trend towards teaching that is more personalised to students' characteristics and some models of prediction failure that are more accurate. In this sense, machine learning techniques have contributed to this realisation. This transformation has been significantly influenced by the integration of machine learning techniques, which have played a crucial role in harnessing data to enhance educational practices. This paper investigates the transformative potential of Artificial Intelligence (AI) within secondary education, focusing on the utilization of student assessment data and socioeconomic contextual information. The primary objective of this paper is to investigate the transformative potential of Artificial Intelligence (AI) within secondary education, with a specific focus on the utilization of student assessment data and socioeconomic contextual information. So, this paper explores the application of AI algorithms to create tailored learning pathways, adaptive support mechanisms, and targeted interventions that accommodate diverse student backgrounds. The integration of AI in secondary education is envisioned not only as a means to enhance academic outcomes but also as a tool to promote social equity and inclusivity. By leveraging data insights, educators can identify and respond to the unique needs of each student, fostering an environment where learning is optimized for individual growth. Furthermore, the paper scrutinizes the ethical considerations and challenges inherent in deploying AI systems in educational settings, emphasizing the pivotal role of equity, transparency, and data privacy in these implementations. This research aims to offer educators, policymakers, and stakeholder's insights into harnessing AI to foster adaptable, student-centric learning environments that bridge educational gaps and promote holistic academic development in secondary schools. Ethical guidelines and frameworks are discussed to ensure responsible AI deployment in educational contexts, safeguarding the rights and privacy of students. The data explored is taken from the management system of a secondary school in the municipality of Braga, relating to students taking Maths A, Maths B or Maths Applied to the Social Sciences (MACS). A total of 621 students were analysed, of which: 520 students attended Mathematics A in the Science and Technology and Socio-Economic Sciences courses, 20 attended Mathematics B in the Visual Arts course and 81 attended Mathematics Applied to Social Sciences in the Languages and Humanities course. The different maths subjects were analysed separately and at the end a comparative study was carried out between the three strands. Grounded in the analysis of these integrated datasets, the study sheds light on the pivotal role of AI in revolutionizing secondary school education. By closely examining student assessment data alongside socioeconomic indicators, such as academic performance and behavioral patterns, the paper identifies opportunities for AI integration to personalize learning experiences, address educational disparities, and cultivate inclusive learning environments. In Maths A there are 268 female and 252 male students. In Maths B there are 18 females and 2 males (most of the arts subjects are taken by women). In MACS the distribution is as follows: 45 female and 36 male. All these students, regardless of the area they chose at the start of secondary school, have in common the choice of Maths, however Maths A will be taken throughout secondary school, while the other two strands are only taken in the first two years of secondary school. Data fusuion techniques have achieved better performance in this type of study, since the models themselves combine the predictions of two or more base models.

Abstract Nowadays, the world is getting increasingly competitive and the quality and the amount of the work presented are one of the decisive factors when choosing an employee. It is no longer necessary to only perform but, to achieve a product with quality, on time, at the lowest possible cost and with the minimum resources. For this reason, the employee must have a high score of attention when performing a task, and the factors that influence attention negatively must be reduced. This is true in many different domains, from the workplace to the classroom. In this paper, we present a nonintrusive smart environment for monitoring people's attention when working in teams. The presented system provides real time information about each individual and information about the team. It can be very useful for team managers to identify potentially distracting events or individuals because when the attention of an individual is not at its best when performing the proposed task, her/his performance will be negatively affected, with consequences for the individual and for the organization.