The development of IOT (Internet of Things) technology has led to the emergence of numerous applications that use the Internet as a means of communication. The paper presents an application of this kind that represents a smart home. The main feature of this application is due to the presence of artificial intelligence. Thus, a neural network is used to predict the occurrence of adverse events. This aim is a fingerprint of the signals generated by the sensors for different regimes of the smart house. When changing the fingerprint, the neural network decides whether the modification constitutes a dangerous situation and causes the measures to be taken accordingly.