Detection of Anomalies in Daily Activities Using Data from Smart Meters.

The massive deployment of smart meters in most Western countries in recent decades has allowed the creation and development of a significant variety of applications, mainly related to efficient energy management. The information provided about energy consumption has also been dedicated to the areas of social work and health. In this context, smart meters are considered single-point non-intrusive sensors that might be used to monitor the behaviour and activity patterns of people living in a household. This work describes the design of a short-term behavioural alarm generator based on the processing of energy consumption data coming from a commercial smart meter. The device captured data from a household for a period of six months, thus providing the consumption disaggregated per appliance at an interval of one hour. These data were used to train different intelligent systems, capable of estimating the predicted consumption for the next one-hour interval. Four different approaches have been considered and compared when designing the prediction system: a recurrent neural network, a convolutional neural network, a random forest, and a decision tree. By statistically analysing these predictions and the actual final energy consumption measurements, anomalies can be detected in the undertaking of three different daily activities: sleeping, breakfast, and lunch. The recurrent neural network achieves an F1-score of 0.8 in the detection of these anomalies for the household under analysis, outperforming other approaches. The proposal might be applied to the generation of a short-term alarm, which can be involved in future deployments and developments in the field of ambient assisted living.

Simulation Tool and Online Demonstrator for CDMA-Based Ultrasonic Indoor Localization Systems.

This work presents the CODEUS platform, which includes a simulation tool together with an online experimental demonstrator to offer analysis and testing flexibility for researchers and developers in Ultrasonic Indoor Positioning Systems (UIPSs). The simulation platform allows most common encoding techniques and sequences to be tested in a configurable UIPS. It models the signal modulation and processing, the ultrasonic transducers' response, the beacon distribution, the channel propagation effects, the synchronism, and the application of different positioning algorithms. CODEUS provides results and performance analysis for different metrics and at different stages of the signal processing. The UIPS simulation tool is specified by means of the MATLAB© App-Designer environment, which enables the definition of a user-friendly interface. It has also been linked to an online demonstrator that can be managed remotely by means of a website, thus avoiding any hardware requirement or equipment on behalf of researchers. This demonstrator allows the selected transmission schemes, modulation or encoding techniques to be validated in a real UIPS, therefore enabling a fast and easy way of carrying out experimental tests in a laboratory environment, while avoiding the time-consuming tasks related to electronic design and prototyping in the UIPS field. Both simulator and online demonstrator are freely available for researchers and students through the corresponding website.

LOCATE-US: Indoor Positioning for Mobile Devices Using Encoded Ultrasonic Signals, Inertial Sensors and Graph-Matching.

Indoor positioning remains a challenge and, despite much research and development carried out in the last decade, there is still no standard as with the Global Navigation Satellite Systems (GNSS) outdoors. This paper presents an indoor positioning system called LOCATE-US with adjustable granularity for use with commercial mobile devices, such as smartphones or tablets. LOCATE-US is privacy-oriented and allows every device to compute its own position by fusing ultrasonic, inertial sensor measurements and map information. Ultrasonic Local Positioning Systems (U-LPS) based on encoded signals are placed in critical zones that require an accuracy below a few decimeters to correct the accumulated drift errors of the inertial measurements. These systems are well suited to work at room level as walls confine acoustic waves inside. To avoid audible artifacts, the U-LPS emission is set at 41.67 kHz, and an ultrasonic acquisition module with reduced dimensions is attached to the mobile device through the USB port to capture signals. Processing in the mobile device involves an improved Time Differences of Arrival (TDOA) estimation that is fused with the measurements from an external inertial sensor to obtain real-time location and trajectory display at a 10 Hz rate. Graph-matching has also been included, considering available prior knowledge about the navigation scenario. This kind of device is an adequate platform for Location-Based Services (LBS), enabling applications such as augmented reality, guiding applications, or people monitoring and assistance. The system architecture can easily incorporate new sensors in the future, such as UWB, RFiD or others.