The complexity inherent in the End Degree Projects (EDP) within engineering programs frequently results in substantial challenges for students regarding project preparation and execution. This also contributes to a heavy workload for the faculty involved in tutoring these works. The presented educational innovation project seeks to address these issues based on developing audiovisual resources intended to support students in EDP preparation and reduce the tutoring burden on teaching staff. This approach aims toward more efficient and sustainable learning outcomes.The primary motivation behind the study described here was to conduct a thorough needs assessment from the perspective of the teaching staff. The goal was to precisely identify the aspects of the EDP process that pose the most recurrent difficulties for students. The information gathered serves the critical purpose of determining what specific types of support or additional resources would be most beneficial, enabling the team to adequately identify and prioritize learning needs to focus the content of the audiovisual resources to be developed. The comprehensive needs assessment derived from the faculty survey establishes the necessary empirical foundation for developing targeted and effective educational support. The identified priorities will directly guide the content, format, and pedagogical design of the upcoming audiovisual resources. By aligning resource development with the empirically verified needs of the teaching staff, the project maximizes the potential for these videos to efficiently support student learning in the EDP process and successfully reduce the faculty’s tutoring load, thereby enhancing the overall quality and sustainability of the educational practice.

This paper proposes a methodology for implementing Artificial Intelligence (AI) in a dairy barn system at CAETEC (Experimental Agricultural Field from Tecnologico de Monterrey) to optimize dairy production, enhance milk nutritional value, and promote environmental sustainability. The project focuses on integrating data science, predictive models, and AI to select the best dairy cows. The core challenge lies in synthesizing vast amounts of data—including cow genetics, feeding behavior, rumination, milking results from a robotic system, and animal welfare—to inform decision-making. The methodology outlines four steps for implementing AI, including sensor identification, system interconnection, continuous training, and data analysis.

Various monitoring systems and data sources are utilized to feed the databases for the AI algorithms, including the Sense Hub system for rumination and health, the DeLaval VMS CLASSIC robotic milking system, the DeLaval activity meter system for behavior and heat detection, and the GREENFEED system for measuring methane emissions. The crucial, non-digital knowledge of the expert (veterinarian) is also digitized and integrated.

The selection of breeding sires, a crucial step in genetic improvement, is presented as a complex decision-making problem that is ripe for AI intervention. The analysis highlights the combinatorial complexity in selecting a stallion, even when considering only four specific genetic types (A2A2, High HHP$, Mastitis resistant PRO, and Polled Genetics) with multiple variables and sire options. The total number of possible ways to select sires, considering badges and characteristics, exceeds 172,000, which necessitates the use of AI to identify the optimal matches.

The paper proposes that a 'cow-match' tool can be developed using data science and algorithms to identify the optimal cow-sire match. This tool is designed to support decision-making in an academic context, offering a practical application for students. The significant number of variables and possibilities demonstrates the immediate need for an AI-powered prompt and decision theory to assist students from different backgrounds, like agronomy (with prior knowledge) and industrial engineering (without previous knowledge), in selecting the best sires based on multiple, often conflicting, objectives (e.g., milk production, cost, reproductive issues, and pollution). The goal is to minimize errors and measure the probability of success in the selection process.

This paper presents a learner-centered pedagogical framework for teaching the Information System Factory (ISF) concept using a flipped classroom and project-based learning approach. Originating in the 1980s, the ISF vision anticipated industrialized, component-oriented information system development, but could not be fully realized due to technological limitations at the time. Advances in cloud infrastructure, AI-assisted development, and low-cost computing now make this vision practically accessible within educational contexts.

The proposed framework integrates flipped classroom pedagogy with hands-on system development activities across the full System Development Life Cycle (SDLC), with particular emphasis on the construction and integration phase. Conceptual content is introduced through pre-class materials, while synchronous sessions focus on coached, collaborative system assembly using open-source tools and single-board computers such as Raspberry Pi. AI-assisted coding sup- ports component selection and exploratory learning, while small-group coaching enables individualized feedback and reflection.

The framework employs Mediathread as a collaborative platform for multimedia annotation and reflection, enabling students to connect theoretical concepts with practical implementation. The ISF concept has been applied in multidisciplinary contexts including Business Administration, Cultural Heritage, and the In-ternet of Things, demonstrating flexibility and adaptability across domains.

Rather than presenting a controlled evaluation study, the paper contributes a design-oriented instructional model informed by teaching practice and formative observations. By integrating flipped classroom principles, project-based learning, and an ISF-inspired development workflow, the framework offers a transferable approach for educators seeking to bridge conceptual understanding and authentic information system development in contemporary higher education.

The digitalization of vocational education requires scientifically grounded approaches to assess learning outcomes resulting from the integration of artificial intelligence, simulation tools, and Learning Management Systems (LMS). In response to the rapid evolution of digital technologies and the need for efficient resource utilization, this study proposes a mathematical model for evaluating the effectiveness of digital tools in training future professionals. The model is based on a system of weighted performance indicators: knowledge quality (Kq), learning time (Kt), student engagement (Ka), and resource expenditure (C). These indicators are synthesized into a composite efficacy index (E), enabling comparative analysis between digital and traditional instructional approaches. The research methodology involved analyzing data from LMS platforms such as Moodle and Google Classroom, as well as AI-based interactive environments. Student engagement was measured through analytical surveys, while instructional scenarios and cognitive load were modeled to assess learning dynamics. Generative AI tools were used to analyze student responses, identify semantic patterns, and refine indicator structures. Data normalization, statistical filtering, and expert-based weighting ensured the model’s validity. The model integrates quantitative metrics (e.g., scores, time, cost) with qualitative indicators (e.g., engagement, cognitive interaction), offering a comprehensive framework for evaluating educational outcomes. Validation was conducted through a comparative study involving two cohorts: one using digital technologies and another following traditional methods. Results demonstrated improved knowledge acquisition, a 22% increase in student activity, reduced learning time, and lower resource consumption in the digital cohort. The composite efficacy index (E) showed a 19% increase compared to the traditional model. This model provides a robust foundation for strategic decision-making in the digitalization of vocational education. Its application supports enhanced training quality, efficient resource allocation, and the development of adaptive, data-driven educational systems.

Digital Twin (DT) technology has been used as a transformative approach for data monitoring and industrial process optimization, especially in older machinery contexts where retrofitting sensor networks is more difficult. This systematic review analyzed 803 publications from 2015 to 2025. The main focus was on sensor placement methodologies for DT applications in industrial machinery. The comprehensive database searches were done using Scopus and Google Scholar databases. We identified and categorized sensor placement approaches into six primary methodologies, including optimization-based methods, machine learning approaches, model-based techniques, information theory methods, rule-based/heuristic approaches, and hybrid methods. Our analysis shows a significant trend in the direction of data-driven and AI-enhanced approaches. For old machinery applications, we found that hybrid approaches combining physics-based models with machine learning show superior performance in scenarios with limited historical data. This work provides practitioners with a comprehensive taxonomy of sensor placement strategies. It highlights a trade-offs between implementation complexity, data requirements, and performance for old industrial systems.