Conference Agenda

The advance of artificial intelligence and its integration into education has enabled the development of intelligent assistants that improve teaching and learning in various disciplines. In engineering, these technologies optimise the personalisation of learning, facilitate the understanding of complex concepts and improve interaction between students and teachers. However, the adoption of these systems faces challenges such as the digital divide, technological infrastructure and resistance to change in academic environments. This study analyses the impact of the use of intelligent assistants in engineering education, identifying their benefits, challenges and applications in different pedagogical models. A document review methodology was employed based on the analysis of previous research and case studies that demonstrate the effectiveness of these tools in higher education. In addition, various platforms and applications that have integrated artificial intelligence to personalise teaching and enhance the learning experience for students were examined. The results indicate that intelligent assistants can enhance adaptive learning, improve knowledge retention and facilitate task automation in educational environments. Their integration with innovative methodologies such as gamification, problem-based learning and STEM education has proven to be effective in improving academic performance and fostering the development of technical and analytical skills in engineering students. However, their implementation requires adequate teacher training, improvements in technological infrastructure and strategies to reduce the digital divide to ensure equitable access to these tools.

This paper presents the design, implementation, and evaluation of a cyber-physical laboratory station for thermal fluids online experiments. The system integrates advanced remote-control technologies using a structured methodology to create an accessible and practical learning environment for engineering education. It leverages state-of-the-art hardware, including NI-myRIO, industrial controllers, and relay modules, along with software solutions based on LabVIEW and MQTT. The station enables real-time control and precise data acquisition in a remote setting. A detailed Piping and Instrumentation Diagram (P&ID) and a modular control unit form the backbone of the system, ensuring accurate monitoring and regulation of thermal and flow variables. The laboratory station is integrated with the RemoteLabo platform, which utilizes computational notebooks to provide seamless remote access. This integration allows students to perform experiments simulating realistic thermal processes, reinforcing theoretical concepts in heat transfer and fluid dynamics. Extensive experimental evaluations were conducted to verify system performance. Sensor calibration procedures, including controlled thermal baths for RTD sensors and calibrated electronic devices for flow measurements, confirmed data reliability. The performance of various heat exchangers was assessed under controlled conditions, demonstrating effective thermal regulation and the attainment of steady-state operation. The experimental results highlight the system’s capability to support remote experimentation while maintaining high accuracy and reproducibility.This study advances remote laboratory technologies and provides a scalable framework for practical training in thermal fluids engineering. The findings contribute to improving engineering education by enabling realistic, high-fidelity experimentation.

The present study addresses the need to detect potato diseases such as early blight, late blight. The objective is to evaluate the performance and accuracy of the Deep Learning technique using in particular the ResNet-9 model convolutional neural network architecture for the identification of diseases on potato leaves. A dataset from the PlantVillage repository on Kaggle was used, which
includes 12,009 images of potato leaves classified into three categories: early blight, late blight, and healthy leaves. The model was trained on Google Colab, achieving an accuracy of 99.55% at the final stage. The research highlights the importance of early disease detection to reduce losses in agricultural production, especially in a context where the world population is increasing and the demand for food is growing. Traditional diagnostic techniques, such as visual inspection, are limited and often inaccurate, making the use of Deep Learning a promising solution. This approach not only improves the accuracy of disease identification, but also offers an affordable alternative for low-income farmers who lack the resources for expensive diagnostic techniques. The study concludes that the implementation of Deep Learning algorithms, such as ResNet-9, can be highly effective for disease detection in crops, contributing to more efficient and sustainable agriculture.

Artificial intelligence (AI) is profoundly transforming the educational landscape by enabling personalized learning experiences, fostering inclusivity, and equipping students with the skills required to navigate an increasingly dynamic job market. This study investigates the integration of AI within vocational and inclusive education through a comprehensive methodological framework, encompassing a SWOT (Strengths, Weaknesses, Opportunities, and Threats) analysis and the development of an assistive educational prototype. The findings reveal AI's significant potential to customize educational content, streamline administrative processes, and introduce innovative pedagogical approaches that cater to diverse learning needs. Nonetheless, the study identifies persistent challenges, including the high costs associated with implementation, heightened concerns about data privacy, and the exacerbation of the digital divide in under-resourced communities. To address these challenges, the research emphasizes the necessity of ethical guidelines, and the establishment of robust policies aimed at balancing innovation with equity and security. Furthermore, the study highlights the transformative role AI can play in fostering accessibility and inclusivity while cultivating a skilled and competitive workforce capable of meeting future labor market demands. The conclusions underscore the need for ongoing research into the responsible application of AI in education, particularly in adapting to rapid technological advancements. Future efforts should focus on scalable, cost-effective solutions that bridge educational disparities and promote the equitable integration of AI technologies across diverse educational contexts.

The objective of this systematic literature review (RSL) is to evaluate the impact of the implementation of intelligent chatbots compared to traditional customer service methods in telecommunications companies, analyzing its influence on customer satisfaction, resolution efficiency of problems and reduction of operating costs. An exhaustive search was carried out in academic databases and research repositories, following the guidelines of the PRISMA method. Studies published between 2019 and 2024 were included, addressing the use of chatbots in customer services in relevant sectors, with a focus on specific performance metrics and user perception. The selected articles were evaluated for relevance, methodological quality and contribution to the topic. The results highlight that chatbots improve operational efficiency by reducing response times and resolving common queries without human intervention, Furthermore, personalizing interactions and using anthropomorphic communication styles increases customer satisfaction. However, limitations related to privacy and acceptance have been identified, particularly in interactions involving sensitive data. From an economic perspective, chatbots have proven to be effective in reducing operational costs, especially in small and medium-sized companies. In conclusion, intelligent chatbots represent an innovative and efficient solution for customer service in the telecommunications sector. However, its success depends on user-centered design, personalization of interactions, and proper privacy management. These findings can guide companies in implementing technology strategies that balance operational efficiency and customer experience

The aim of this systematic literature review (SLR) is to analyze graphic design in optimizing interactive learning, with a particular focus on rural contexts. The methodology used was PICO and PRISMA, encompassing a comprehensive analysis of studies published between 2020 and 2024 in academic databases. The review explores previous research related to visual interfaces, immersive technologies such as augmented reality (AR) and virtual reality (VR), as well as hybrid methodologies, including problem-based learning (PBL) and gamification. The results show that these tools have significantly contributed to improving accessibility, student motivation and the understanding of complex concepts. But there are critical gaps, such as the long-term sustainability of these solutions and their personalization for students with diverse cognitive abilities. In technical disciplines such as engineering and computer-aided design (CAD), virtual laboratories and online learning platforms have proven effective in improving information retention. It is concluded that interactive graphic design is positioned as a key tool for creating participatory educational environments. It is recommended to develop accessible and culturally relevant technologies, design inclusive tools for students with diverse abilities, and foster institutional collaborations to ensure sustainable implementation.

The incorporation of technology in educational settings is one of the most relevant challenges in university education, in addition to fostering a collaborative environment among its participants. The purpose of the study was to determine the influence of virtual learning environments on collaborative learning following the project-based model in Peruvian university students. A quantitative, applied, explanatory level and non-experimental design approach was used. The population was Industrial Engineering students from a private Peruvian university, and the sample consisted of 62 7th cycle students, taking the Product Engineering course. Two questionnaires were used, one for virtual environments and another for collaborative learning. In the statistical analysis, the frequencies of occurrence were calculated, and the Kolmogorov-Smirnov and Ordinal Logistic Regression tests were used to check the normality of the data and the existence of significant differences. The findings revealed that, in collaborative learning, positive interdependence and individual responsibility, no significant differences were identified (p <0.05). In addition, significant differences were found in interaction and social skills, with respect to virtual environments (p>0.05). It is concluded that virtual environments positively influence collaborative learning in university students.