This paper presents a novel real-time smart system performing fall detection, location, and notification based on floor vibration data produced by fall downs. Only using floor vibration as the recognition source, the system incorporates a person identification through vibration produced by footsteps to inform who is the fallen person. Our approach operates in a real-time style, which means the system recognizes a fall immediately and can identify a person with only one or two footsteps. A collaborative in-network location method is used in which sensors collaborate with each other to recognize the person walking, and more importantly, detect if the person falls down at any moment. We also introduce a voting system among sensor nodes to improve person identification accuracy. Our system is robust to identify fall downs from other possible similar events, like jumps, door close, objects fall down, etc. Such a smart system can also be connected to smart commercial devices (Google Home or Amazon Alexa) for emergency notifications. Our approach represents an advance in smart technology for elder people who live alone. Evaluation of the system shows it is able to detect fall downs with an acceptance rate of 95.14% (distinguishing from other possible events), and it identifies people with one or two steps in a 97.22% (higher accuracy than other methods that use more footsteps). The fall down location error is smaller than 0.27 meters, which it is acceptable compared to the height of a person.

Instead of using traditional intrusive surveillance technologies such as cameras or body sensors, we propose a smart home system sensing the footstep induced vibrations to feature the same functions which can be used for the assisted living purpose. Based on distributed sensing and processing units, we adopt a distributed computing approach to preprocess the time-series data, recognize footstep signals, and extract vibration features locally. Through communications over the sensor networks, our system is capable to estimate the occupancy via counting the number of occupants. Besides, based on the multicomponent seismometer sensing system, we propose a novel indoor footstep localization method called angle constrained time difference of arrivals relying on both angle and arrival information of the recorded waveforms. According to separated pedestrian locations, different trajectories of multiple people can be tracked. From the location tracking history, the resident’s daily activities and social interactions can be inferred. In our experiments, the proposed system obtains promising results. Specifically, the location error is 0.14 m with a 0.11 m standard deviation. And the multipeople identification accuracy is above 87.83%.

In this paper, a bed-mounted vibration sensor-based system is proposed to monitor vital parameters during sleep, including heartbeat rate (HR) and respiratory rate (RR), body movements and sleep postures. Our system enables smart healthcare that monitors daily sleep in a ubiquitous and non-invasive manner. Besides, the system is contact-free, as no external wearable devices and physical contacts are required. Furthermore, the vibration-based approach also avoids the privacy violation caused by the usage of surveillance cameras. To effectively monitor sleep status, a robust stable signal mode decomposition based HR and RR estimation method is developed for the complicated and noisy vibration signals. Besides, algorithms for body movement and sleep posture identification are also proposed based on vibration signal features. A prototype system is demonstrated with system details, showing great potentials in monitoring sleep status in a real-time user-friendly manner. Experimental results of short term and long term experiments with different participants and beds show that our system achieves satisfying accuracy compared with dedicated commercial devices.

Understanding earthquakes and volcano eruptions phenomena require the analysis of large amounts of subsurface data. Currently, data collected from these events need post-processing in an off-line mode due to hardware limitations and strong bandwidth constraints. Furthermore, analytics may take days, even weeks, in being processed after collection. In some cases, underground structures require previous studies and subsurface knowledge from experts to establish certain input parameters. By leveraging current IoT technologies, we introduce an autonomous seismic imaging system (ASIS), a real-time system for monitoring and generating analytics of seismic data based on a sensor network. ASIS processes real-time analytics near where the events are generated (fog computing) to mitigate bandwidth limitations. Calculations for earthquake detection, location, and magnitude are processed in situ. ASIS allows monitoring sensor status, visualizing the data of each sensor, and generating two dimensional/three dimensional (2-D/3-D) subsurface structures. The system is able to learn the underground structure by taking advantage of ambient noise data analysis, which significantly reduces the need of initial parameters. We incorporated a renewable energy source to extend sensor functionality, and we made the system self-healing and fault-tolerant. Indoor and outdoor evaluation of the system showed the error of earthquake detection is 13.7 ms and the spatial location accuracy is 5.1 ft.

A wireless seismic network can be effectively used as a tool for subsurface monitoring and imaging. By recording and analyzing ambient noise, a seismic network can image underground infrastructures and provide velocity variation information of the subsurface that can help to detect anomalies. By studying the variation in the noise cross-correlation function of the noise, it is possible to determine the subsurface seismic velocity and image underground infrastructures. Ambient noise imaging can be done in a decentralized fashion using Distributed Spatial Auto-Correlation (dSPAC). In dSPAC over sensor networks, the cross-correlation is the most intensive communication process since nodes need to communicate their data with neighbor nodes. In this paper, a new communication-reduced method for cross-correlation is presented to meet bandwidth and cost of communication constraints in networks while ambient noise imaging is performed using dSPAC method. By applying the proposed communication-reduced method, we show that energy and computational cost of the nodes is also preserved.