This study explores the potential of RGB image data for forest fire detection using deep learning models, evaluating their advantages and limitations, and discussing potential integration within a multi-modal data context. The research introduces a uniquely comprehensive wildfire dataset, capturing a broad array of environmental conditions, forest types, geographical regions, and confounding elements, aiming to reduce high false alarm rates in fire detection systems. To ensure integrity, only public domain images were included, and a detailed description of the dataset’s attributes, URL sources, and image resolutions is provided. The study also introduces a novel multi-task learning approach, integrating multi-class confounding elements within the framework. A pioneering strategy in the field of forest fire detection, this method aims to enhance the model’s discriminatory ability and decrease false positives. When tested against the wildfire dataset, the multi-task learning approach demonstrated significantly superior performance in key metrics and lower false alarm rates compared to traditional binary classification methods. This emphasizes the effectiveness of the proposed methodology and the potential to address confounding elements. Recognizing the need for practical solutions, the study stresses the importance of future work to increase the representativeness of training and testing datasets. The evolving and publicly available wildfire dataset is anticipated to inspire innovative solutions, marking a substantial contribution to the field.

Contribution: Stereotypes and immediate environment are the reasons for low enrollment of women in STEM studies. Background: The low number of women in STEM degree courses has been the subject of much research, which has found that the lack of female enrollment is not evenly distributed across all STEM studies. In some areas, such as computing, communications, and electrical and electronic engineering (CCEEE), not only has the number of women not increased, it has even fallen. Research Questions: Is there a stereotype for women taking STEM studies? Is this stereotype different between women taking CCEEE and non-CCEEE degrees? What are the main reasons that lead women to enroll in STEM studies? Methodology: A survey was sent to 3699 female students and STEM graduates belonging to the authors' university in six schools with a lowest level of enrollment, and 1060 replies were received. A qualitative study based on data analysis triangulation was performed. Findings: The women surveyed consider social stereotypes (31.47%) and the immediate environment (14.5%) as the main reasons for the low enrollment of women in STEM studies. Surprisingly, the third reason (11.03%) is that women do not like engineering. New knowledge concerning what motivates female students to enroll in STEM studies, what stereotypes they must struggle against, and the existence of possible differences between CCEEE and STEM but non-CCEEE female students could help policy makers and academia to improve female enrollment in STEM and, in particular, in CCEEE studies.

Learning through digital media is currently considered as a mixture of methodologies that aim to approach the reality of students to motivate them. Gamification emerges as one of the pedagogical methodologies on the rise in digital classrooms, but is it really practical? What are its effects? A gamification longitudinal case-study experience was carried out in the subject: complements for disciplinary training in technology of the master’s degree of secondary school teachers (technology specialty) that is taught at the Universitat Politècnica de Catalunya, where gamified activities and alternatives to traditional master teaching have been introduced in a progressive way throughout three academic years (2016/17 to 2018/19). The results show that there is a negative correlation between the numerical scores of the different components of the evaluation and the marks obtained in the activities of gamification. It is surprising that the group less involved in the gamification obtained better academic results, although gamification improved the motivation and the valuations of the subject, due to the inclusion of more games in the course. This raises doubts on whether the positive effects of gamification on the climate of the classroom and on motivation are opposed to academic results.

Forest fires pose a significant threat to ecosystems, property, and human life, making their early and accurate detection crucial for effective intervention. This study presents a novel, lightweight approach to real-time forest fire detection that is optimized for resource-constrained devices like drones. The method integrates multi-task knowledge distillation, transferring knowledge from a high-performance DenseNet201 teacher model that was trained on a hierarchically structured wildfire dataset. The dataset comprised primary classes (fire vs. non-fire) and detailed subclasses that account for confounding elements such as smoke, fog, and reflections. The novelty of this approach lies in leveraging knowledge distillation to transfer the deeper insights learned by the DenseNet201 teacher model—specifically, the auxiliary task of recognizing the confounding elements responsible for false positives—into a lightweight student model, enabling it to achieve a similar robustness without the need for complex architectures. Using this distilled knowledge, we trained a MobileNetV3-based student model, which was designed to operate efficiently in real-time while maintaining a low computational overhead. To address the challenge of false positives caused by visually similar non-fire elements, we introduced the Confounding Element Specificity (CES) metric. This novel metric, made possible by the hierarchical structure of the wildfire dataset, is unique in its focus on evaluating how well the model distinguishes actual fires from the confounding elements that typically result in false positives within the negative class. The proposed approach outperformed the baseline methods—including single-task learning and direct multi-task learning—achieving a primary accuracy of 93.36%, an F1-score of 91.57%, and a higher MES score, demonstrating its enhanced robustness and reliability in diverse environmental conditions. This work bridges the gap between advanced deep learning techniques and practical, scalable solutions for environmental monitoring. Future research will focus on integrating multi-modal data and developing adaptive distillation techniques to further enhance the model’s performance in real-time applications.

The need to incorporate the gender dimension in higher education is a central element of gender equality policies within the European Union (EU). When most institutions of higher education have already strengthened and consolidated their curricula, the next challenge is to include and ensure that all people have the same opportunities to progress in education. This study intends to incorporate the gender dimension in teaching through a guide providing recommendations for the introduction of changes that will allow its effective incorporation in STEM (Science, Technology, Engineering and Mathematics) areas. It will take into account the administration in charge of formulating policies in the field of education, the students, and, mainly, the teaching staff. Its objective is to cover aspects related to the principles of equal opportunities and gender equality in STEM higher education disciplines. For this purpose, 41 volunteer teachers from 8 degrees and master’s degrees from the Universitat Politècnica de Catalunya in Spain participated. To achieve the results of this study, aspects related to social and gender relevance of the subjects, inclusive methodology, classroom management and assessment were considered. As a preliminary step to the development of the guide of recommendations, a teacher’s self-assessment tool and a questionnaire for students to analyze the perception of the gender dimension were developed.