Paolo Barsocchi

A Novel Approach to Indoor RSSI Localization by Automatic Calibration of the Wireless Propagation Model

We propose a novel localization algorithm of mobile sensors based on wireless sensor networks providing RSSI measurements between the mobile and the fixed sensors (anchors) in the network. The algorithm selects and weights the RSSI measurements according to their strength, and it uses a propagation model to transform RSSI measurements into distances, in order to estimate the position of the mobile. The algorithm also uses a virtual calibration method of the propagation model that does not require human intervention. By an experimental setup we show that the localization algorithm increases the performance with respect to the commonly used least mean square algorithm showing also how to achieve a wished accuracy increasing the anchor density.

An experimental characterization of reservoir computing in ambient assisted living applications

In this paper, we present an introduction and critical experimental evaluation of a reservoir computing (RC) approach for ambient assisted living (AAL) applications. Such an empirical analysis jointly addresses the issues of efficiency, by analyzing different system configurations toward the embedding into computationally constrained wireless sensor devices, and of efficacy, by analyzing the predictive performance on real-world applications. First, the approach is assessed on a validation scheme where training, validation and test data are sampled in homogeneous ambient conditions, i.e., from the same set of rooms. Then, it is introduced an external test set involving a new setting, i.e., a novel ambient, which was not available in the first phase of model training and validation. The specific test-bed considered in the paper allows us to investigate the capability of the RC approach to discriminate among user movement trajectories from received signal strength indicator sensor signals. This capability can be exploited in various AAL applications targeted at learning user indoor habits, such as in the proposed indoor movement forecasting task. Such a joint analysis of the efficiency/efficacy trade-off provides novel insight in the concrete successful exploitation of RC for AAL tasks and for their distributed implementation into wireless sensor networks.

Evaluating Ambient Assisted Living Solutions: The Localization Competition

Evaluation of ambient assisted living (AAL) systems is particularly challenging due to the complexity of such systems and the variety of solutions adopted and services offered. Yet analyzing and comparing AAL solutions is paramount for assessing research results in this area. Evaluating AAL Systems through Competitive Benchmarking (EvAAL) is a recently established international competition that aims to address this problem, letting benchmarking and comparison methodologies of AAL systems emerge from experience. Here, the authors describes the first EvAAL competition, which was devoted to localization and tracking. They also review the proposed evaluation criteria, benchmarks, and results. All evaluation data is freely available from the EvAAL website.

Virtual Calibration for RSSI-Based Indoor Localization with IEEE 802.15.4

Localization systems based on Received Signal Strength Indicator (RSSI) exploit fingerprinting (based on extensive signal strength measurements) to calibrate the system parameters. This procedure is very expensive in terms of time as it relies on human operators. In this paper we propose a virtual calibration procedure which only exploits the measurements of the RSSI between pairs of anchors. In particular, we propose two procedures for virtual calibration and we evaluate their performance with respect to an ad-hoc calibration campaign by performing measures in an indoor environment with an IEEE 802.15.4 sensor network.

A stigmergic approach to indoor localization using Bluetooth Low Energy beacons

Localization of people and devices is one of the main building blocks of context aware systems since the user position represents the core information for detecting users activities, devices activations, proximity to points of interest, etc. While for outdoor scenarios Global Positioning System (GPS) constitutes a reliable and easily available technology, for indoor scenarios GPS is largely unavailable. In this paper we present a range-based indoor localization system that exploits the Received Signal Strength (RSS) of Bluetooth Low Energy (BLE) beacon packets broadcast by anchor nodes and received by a BLE-enabled device. The method used to infer the users position is based on stigmergy. We exploit the stigmergic marking process to create an on-line probability map identifying the users position in the indoor environment.

Evaluation of localization and activity recognition systems for ambient assisted living: The experience of the 2012 EvAAL competition

EvAAL is an annual international competition that addresses the “grand” challenge of evaluation and comparison of Ambient Assisted Living AAL systems and platforms, with the final goal to assess the autonomy, independent living and quality of life that AAL systems may grant to their end users. The 2012 Edition was focused on two pillars of AAL: Indoor localization and activity recognition. Results from both competitions suggest that there is still space for other editions not only to improve accuracy of such systems, but also their user acceptance and interoperability. This paper describes the organization and results of the 2012 edition.

Automatic virtual calibration of range-based indoor localization systems

The localization methods based on received signal strength indicator (RSSI) link the RSSI values to the position of the mobile to be located. In the RSSI localization techniques based on propagation models, the accuracy depends on the tuning of the propagation models parameters. In indoor wireless networks, the propagation conditions are hardly predictable due to the dynamic nature of the RSSI, and consequently the parameters of the propagation model may change. In this paper, we present an automatic virtual calibration method of the propagation model that does not require human intervention; therefore, can be periodically performed, following the wireless channel conditions. We also propose a novel RSSI-based localization algorithm that selects the RSSI values according to their strength, and uses a calibrated propagation model to transform these values into distances, in order to estimate the position of the mobile. Copyright

Monitoring elderly behavior via indoor position-based stigmergy

In this paper we present a novel approach for monitoring elderly people living alone and independently in their own homes. The proposed system is able to detect behavioral deviations of the routine indoor activities on the basis of a generic indoor localization system and a swarm intelligence method. For this reason, an in-depth study on the error modeling of state-of-the-art indoor localization systems is presented in order to test the proposed system under different conditions in terms of localization error. More specifically, spatiotemporal tracks provided by the indoor localization system are augmented, via marker-based stigmergy, in order to enable their self-organization. This allows a marking structure appearing and staying spontaneously at runtime, when some local dynamism occurs. At a second level of processing, similarity evaluation is performed between stigmergic marks over different time periods in order to assess deviations. The purpose of this approach is to overcome an explicit modeling of users activities and behaviors that is very inefficient to be managed, as it works only if the user does not stray too far from the conditions under which these explicit representations were formulated. The effectiveness of the proposed system has been experimented on real-world scenarios. The paper includes the problem statement and its characterization in the literature, as well as the proposed solving approach and experimental settings.

Frame error model in rural Wi-Fi networks

Commonly used frame loss models for simulations over Wi-Fi channels assume a simple double regression model with threshold. This model is widely accepted, but few measurements are available in the literature that try to validate it. As far as we know, none of them is based on field trials at the frame level. We present a series of measurements for relating transmission distance and packet loss on a Wi-Fi network in rural areas and propose a model that relates distance with packet loss probability. We show that a simple double regression propagation model like the one used in the ns-2 simulator can miss important transmission impairments that are apparent even at short transmitter-receiver distances. Measurements also show that packet loss at the frame level is a Bernoullian process for time spans of few seconds. We relate the packet loss probability to the received signal level using standard models for additive white Gaussian noise channels. The resulting model is much more similar to the measured channels than the simple models where all packets are received when the distance is below a given threshold and all are lost when the threshold is exceeded.

Multisensor Data Fusion for Activity Recognition Based on Reservoir Computing

Ambient Assisted Living facilities provide assistance and care for the elderly, where it is useful to infer their daily activity for ensuring their safety and successful ageing. In this work, we present an Activity Recognition system that classifies a set of common daily activities exploiting both the data sampled by accelerometer sensors carried out by the user and the reciprocal Received Signal Strength (RSS) values coming from worn wireless sensor devices and from sensors deployed in the environment. To this end, we model the accelerometer and the RSS stream, obtained from a Wireless Sensor Network (WSN), using Recurrent Neural Networks implemented as efficient Echo State Networks (ESNs), within the Reservoir Computing paradigm. Our results show that, with an appropriate configuration of the ESN, the system reaches a good accuracy with a low deployment cost.