One of the most common attacks is man‐in‐the‐middle (MitM) which, due to its complex behaviour, is difficult to detect by traditional cyber‐attack detection systems. MitM attacks on internet of things systems take advantage of special features of the protocols and cause system disruptions, making them invisible to legitimate elements. In this work, an intrusion detection system (IDS), where intelligent models can be deployed, is the approach to detect this type of attack considering network alterations. Therefore, this paper presents a novel method to develop the intelligent model used by the IDS, being this method based on a hybrid process. The first stage of the process implements a feature extraction method, while the second one applies different supervised classification techniques, both over a message queuing telemetry transport (MQTT) dataset compiled by authors in previous works. The contribution shows excellent performance for any compared classification methods. Likewise, the best results are obtained using the method with the highest computational cost. Thanks to this, a functional IDS will be able to prevent MQTT attacks.

The hotel industry is an important energy consumer that needs efficient energy management methods to guarantee its performance and sustainability. The new role of hotels as prosumers increases the difficulty in the design of these methods. Also, the scenery is more complex as renewable energy systems are present in the hotel energy mix. The performance of energy management systems greatly depends on the use of reliable predictions for energy load. This paper presents a new methodology to predict energy load in a hotel based on intelligent techniques. The model proposed is based on a hybrid intelligent topology implemented with a combination of clustering techniques and intelligent regression methods (Artificial Neural Network and Support Vector Regression). The model includes its own energy demand information, occupancy rate, and temperature as inputs. The validation was done using real hotel data and compared with time-series models. Forecasts obtained were satisfactory, showing a promising potential for its use in energy management systems in hotel resorts.

Los avances tecnológicos en general, y en el ámbito de la industria en particular, conllevan el desarrollo y optimización de las actividades que en ella tienen lugar. Para alcanzar este objetivo, resulta de vital importancia detectar cualquier tipo de anomalía en su fase más incipiente, contribuyendo, entre otros, al ahorro energético y económico, y a una reducción del impacto ambiental. En un contexto en el que se fomenta la reducción de emisión de gases contaminantes, las energías alternativas, especialmente la energía eólica, juegan un papel crucial. En la fabricación de las palas de aerogenerador se recurre comúnmente a materiales de tipo bicomponente, obtenidos a través del mezclado de dos substancias primarias. En la presente investigación se evalúan distintas técnicas inteligentes de clasificación one-class para detectar anomalías en un sistema de mezclado para la obtención de materiales bicomponente empleados en la elaboración de palas de aerogenerador. Para lograr los modelos inteligentes que permitan la detección de anomalías, se han usado datos reales extraídos de una planta de mezclado en operación durante su correcto funcionamiento. Los clasificadores obtenidos para cada técnica son validados a través de anomalías generadas de manera artificial, obteniéndose resultados altamente satisfactorios.