Sleepwalking is a type of sleep disorder which originates during deep sleep and results in a walking state with people performing a series of complex behaviors or actions while sleeping. In some cases, sleepwalking patients can injure themselves from their actions, such as by driving a car or by climbing out of a window. In addition, waking up the sleepwalkers can be difficult. The sudden waking up can cause them to be confused, and they may even attack the person who wakes them. Therefore, detecting sleepwalking incidents in an early state can help the caretaker or family members stop the patients before they harm themselves from any strange, inappropriate, or violent behaviors. In this research, we present a prototype sleepwalking detection algorithm and a notification system using smart device which work coordinating with a wearable device. There are two main groups of users: patients and caretakers. A User Activity Sensor (UAS) in the wearable device is utilized for detecting User Activity Data (UAD), unusual activities, of a sleepwalking patient. This data is collected using software provided by the Remote Sensor software development kit (SDK). The system returns the patient UAD states consisting of standing, walking, and running. The smart device accepts the UAD states from the wearable device, performs sleepwalking detection algorithms, then informs caretakers when the sleepwalking state has already evoked. The system has been implemented, built, tested, and deployed. Experimental measurements of physical user activities have been performed to validate our proposed sleepwalking detection algorithms. The system correctly detects the sleepwalking states and notifies the caretaker.