In recent years, the development of neuroscience and psychology fields has been a major breakthrough. Music can effectively improve attention, memory, relaxation and relieve stress effect through listening. In addition, some Brain–Computer Interface (BCI) researches have been confirmed the different musical elements will change the brainwaves, then further affect learning and memory. These studies often use multi-channel brainwave measurement instruments. However, the mobility and wearable styles are limited by multi-channel brainwave measurement instruments. In this thesis, a mobile BCI music recommender system (MBCI-MRS) is proposed and the music recommender algorithm is designed with this system. This system is combined with the mobile device and a single-channel brainwave measurement headset extracting brainwave signals. When users are listening to white noise music, their brainwave signals will be transmitted to the mobile device through Bluetooth connectivity. Based on collected brainwave signals, the music recommender algorithm will select appropriate white noise music for the user listening during memorizing English words. The MBCI-MRS software are designed in Android system. In order to evaluate the usability of the system, we use System Usability Scale (SUS) questionnaire and Think-Aloud Protocol to assist the enhancement of usability. Furthermore, the experimental results show that the music recommender algorithm has effectively recommended white noise music for the users.