To make machines emotionally more intelligent, it is necessary to choose the right measuring devices that are able to collect physiological biosignals, which can be used to recognize the emotional state of the user. These devices should not restrict the users in their everyday life, therefore commercial, non-invasive Internet of Things (IoT) devices must be used. Thanks to the interoperability of IoT devices, it is possible to send the obtained data to a server, where it can be used in the predict method of a trained machine learning algorithm. Based on the recognized emotion, it is possible to create different instructions for smart home elements.