Deep learning enabled smart mats as a scalable floor monitoring system

Abstract

Toward smart building and smart home, floor as one of our most frequently interactive interfaces can be implemented with embedded sensors to extract abundant sensory information without the video-taken concerns. Yet the previously developed floor sensors are normally of small scale, high implementation cost, large power consumption, and complicated device configuration. Here we show a smart floor monitoring system through the integration of self-powered triboelectric floor mats and deep learning-based data analytics. The floor mats are fabricated with unique “identity” electrode patterns using a low-cost and highly scalable screen printing technique, enabling a parallel connection to reduce the system complexity and the deep-learning computational cost. The stepping position, activity status, and identity information can be determined according to the instant sensory data analytics. This developed smart floor technology can establish the foundation using floor as the functional interface for diverse applications in smart building/home, e.g., intelligent automation, healthcare, and security.

Progress inTENGtechnology—A journey from energy harvesting to nanoenergy and nanosystem

“…To achieve multi-functionalities, with the aid of triboelectric materials and structural designs, advanced electrode designs can also be incorporated into conventional TENGs, resulting in applicationoriented TENG configurations, that is, operating independently in the form of real-time and situ sensing. 105,226,243,[374][375][376][377][378][379][380][381][382][383][384][385][386][387][388][389][390][391][392] Toward NENS, blue energy is one of the most important application directions, which is mainly in forms of wave energy, tidal energy, and osmotic energy harvesting. To the aspect of the wearable electronics and HMI, TENG shows the potential abilities in realizing the advanced manipulation with the digital world.…”

Flourishing energy harvesters for future body sensor network: from single to multiple energy sources

“…Owing to the versatile choices of materials, diversified working modes, and cost-effective fabrication process, a growing number of large-area TENGs for wider application scenarios such as smart home or athletic big data analysis have been reported. For instance, Shi et al recently developed a smart floor monitoring system by integrating triboelectric floor mats with deep learning data analytics (Shi et al, 2020b). As shown in Figure 2F, the floor mats are characterized with unique ''identity'' electrode patterns fabricated with the highly scalable and low-cost screen printing technique, which enable the parallel connections between each mat to reduce the systematic complexity.…”

“… (F) A triboelectric-based smart mat with unique electrode patterns as a scalable floor monitoring system enabled by advanced deep learning analytics. Reprinted from ref ( Shi et al., 2020b ) with permission, Copyright©2019 Springer Nature. (G) A 3D-printed haptic-feedback smart glove as a creative HMI for diversified VR/AR applications.…”

“…For instance, Shi et al. recently developed a smart floor monitoring system by integrating triboelectric floor mats with deep learning data analytics ( Shi et al., 2020b ). As shown in Figure 2 F, the floor mats are characterized with unique “identity” electrode patterns fabricated with the highly scalable and low-cost screen printing technique, which enable the parallel connections between each mat to reduce the systematic complexity.…”

“…Wearable electronics that would well merge with our bodies are set to extend the way we perceive and interact with the world ( Chu et al., 2017 ; Shi et al., 2020a , 2020b ; Wen et al., 2020a ). The rapid advancement in materials, sensors, circuits, and wireless transmission technologies will give way to the body sensor network (bodyNET) ( Niu et al., 2019 ; Tian et al., 2019 ), which enables human physiological signal detection not only on the skin but also inside the body as shown in Figure 1 A ( Lee et al., 2019a ; Zheng et al., 2020 ).…”