In recent years, the application of artificial intelligence (AI) in the automotive industry has led to the development of intelligent systems focused on road safety, aiming to improve protection for drivers and pedestrians worldwide to reduce the number of accidents yearly. One of the most critical functions of these systems is pedestrian detection, as it is crucial for the safety of everyone involved in road traffic. However, pedestrian detection goes beyond the front of the vehicle; it is also essential to consider the vehicle’s rear since pedestrian collisions occur when the car is in reverse drive. To contribute to the solution of this problem, this research proposes a model based on convolutional neural networks (CNN) using a proposed one-dimensional architecture and the Inception V3 architecture to fuse the information from the backup camera and the distance measured by the ultrasonic sensors, to detect pedestrians when the vehicle is reversing. In addition, specific data collection was performed to build a database for the research. The proposed model showed outstanding results with 99.85% accuracy and 99.86% correct classification performance, demonstrating that it is possible to achieve the goal of pedestrian detection using CNN by fusing two types of data.

Cybersecurity is an essential component for preserving the integrity of healthcare systems, particularly in the face of the increasing adoption of interconnected medical devices, which significantly expands cyber risk exposure. A critical issue in this context is the fragmentation of knowledge regarding the security of these devices. The absence of a unified framework hampers the systematic identification of vulnerabilities and the effective implementation of protective measures. This study highlights such fragmentation by requiring the integration of seven ISO standards, nine NIST controls, one HIPAA regulation, one ENISA directive, one GDPR regulation, and one HITRUST framework, along with the review of 47 scientific articles and analysis of 27 documented vulnerabilities (CVEs). The need to consult this broad range of sources reflects both the complexity of the regulatory landscape and the lack of standardization in medical device security. Based on this review, key pillars were defined to support an integral and adaptable security model. This model provides a practical tool to strengthen digital healthcare infrastructures, facilitate continuous audits, and mitigate emerging threats, all while aligning with international standards. Furthermore, it promotes the consolidation of fragmented knowledge, helping to close security gaps and enhance the resilience of healthcare systems in a globalized environment.

La inteligencia artificial se ha convertido en la principal protagonista del desarrollo tecnológico de los últimos años, experimentando avances vertiginosos que le han permitido integrarse en diversos aspectos de la vida humana. La capacidad de una IA para entregar al usuario exactamente lo que necesita es un factor fundamental para que soluciones que emplean estas tecnologías puedan masificarse y formar parte del día a día humano. No obstante, el contenido generado por una IA puede incorporar alteraciones que produzcan resultados imprecisos o incluso falsos. Este fenómeno conocido como alucinaciones de la IA representa importantes desafíos para el desarrollo de estas tecnologías y genera impactos políticos, económicos, reputacionales y personales, entre otros.