To manage the voiding dysfunction, getting the exact data about patient’s voiding pattern is very important, though it is very cumbersome.  We invented a wearable device which can measure the voiding time and number by checking a habitual series of characteristic motion of men. This study was performed by collecting and analyzing the urination time and interval data sensed through smart bands worn to resolve the clinical issues caused by using voiding charts. By developing a smart band-based algorithm for recognizing urination time and interval, this study aimed to explore the feasibility of urination management systems.

We designed a device that could recognize urination time and interval based on patient’s specific posture and consistent changes in posture. These motion data were obtained by smart band on the wrist. An algorithm that recognizes the 3 stages of urination (forward movement, urination, backward movement) was devised based on the movement and tilt angle data collected from 3-axis accelerometer. The sequential body movement on voiding is temporal but consistent characteristics, so we analyze HMM (Hidden Markov Model)-based sequential data and provide a way to recognize urination time. Real-time data were acquired from the smart band, and for data corresponding to a certain duration, the value of the signals was calculated and then compared with the set analysis model to calculate the time of urination. Comparison study between real voiding and device detected voiding for assessing the performance of the recognition technology proposed was performed

An experiment was carried out to assess the performance of the recognition technology proposed in this study. The final accuracy of the algorithm was calculated based on clinical guidelines for urologists. The experiment showed a high average accuracy of 92.5%, proving the robustness of the proposed algorithm.

This results shows that this device could be adopted as a possible method to help making the voiding diary with ease

The urination behavior recognition technology shows high accuracy and might be applied in clinical field for finding out patient’s voiding pattern. As wearable devices are developed and generalized, the algorithm detecting consistent sequential body movement pattern reflecting specific physiologic behavior might be a new methodology in studying human physiologic behavior.