Purpose: Localization-based technologies promise to keep older adults with dementia safe and support them and their caregivers during getting lost events. This paper summarizes mainly technological contributions to support the target group in these events. Moreover, important aspects of the getting lost phenomenon such as its concept and ethical issues are also briefly addressed. Methods: Papers were selected from scientific databases and gray literature. Since the topic is still in its infancy, other terms were used to find contributions associated with getting lost e.g. wandering. Results: Trends of applying localization systems were identified as personal locators, perimeter systems and assistance systems. The first system barely considered the older adult’s opinion, while assistance systems may involve context awareness to improve the support for both the elderly and the caregiver. Since few studies report multidisciplinary work with a special focus on getting lost, there is not a strong evidence of the real efficiency of localization systems or guidelines to design systems for the target group. Conclusions: Further research about getting lost is required to obtain insights for developing customizable systems. Moreover, considering conditions of the older adult might increase the impact of developments that combine localization technologies and artificial intelligence techniques.
In this paper, a comparison of IMU-based step length and heading estimation methods for indoor environments is presented. We compared two step detection methods: detecting the stance phase in each stride and detecting negative peaks in the horizontal acceleration filtered signal. Likewise, three step length estimation methods were compared: Zero Velocity Update (ZUPT), step frequency-based and step length parameter-based. Finally, the comparison of two heading estimation methods is presented: Heuristic Heading Reduction (HHR) and Zero Angular Rate update (ZARU). The yaw obtained from the sensor was corrected and compared with both heading estimation methods. All methods were tested at high, normal and low walking frequencies. Both step detections methods showed a good performance at normal and high step frequencies. The step length estimation method that depend of a linear parameter presented an error of 0.3m in a route of 96m and was the one with lowest error. The yaw corrected presents the lowest error of 3° in turns of 90°.
Monitoring people during their daily activities has become a topic of great interest among the scientific community, largely due to the great advances in microelectronics, wearable devices, ubiquitous computing, or artificial intelligence. Among these advances, smartphones have arisen as a key technology to monitor people, thanks to their onboard sensors and their increasing computational capabilities. Most accessible smartphones are equipped with accelerometers, which has opened avenues to explore aspects based on human mobility. For example, linear accelerations present patterns during human walking cycle allowing for analyzing the gait. Despite identifying those patterns with smartphones is feasible, some restrictions must be considered, for example, the device position in the human body or battery consumption.In this paper, we compare the performance of time domain algorithms for step detection considering: (1) varying sampling frequency of the data; (2) different positions of the device while users walk (i.e., hand, pocket and lower back); and (3) different paces during walking (i.e., low, normal and quick). The compared algorithms include vertical acceleration (VA), magnitude, energy and vertical acceleration using the inclination angle of the device (VAIA). Our results did not indicate considerable influence of the device position and user's pace in the performance of the algorithms based on magnitude, energy and VAIA. On the contrary, the lower performance was presented by the VA algorithm.