Showing papers by "Andrea Sciarrone published in 2017"

Enabling IoT for In-Home Rehabilitation: Accelerometer Signals Classification Methods for Activity and Movement Recognition

Abstract: Rehabilitation and elderly monitoring for active aging can benefit from Internet of Things (IoT) capabilities in particular for in-home treatments. In this paper, we consider two functions useful for such treatments: 1) activity recognition (AR) and 2) movement recognition (MR). The former is aimed at detecting if a patient is idle, still, walking, running, going up/down the stairs, or cycling; the latter individuates specific movements often required for physical rehabilitation, such as arm circles, arm presses, arm twist, curls, seaweed, and shoulder rolls. Smartphones are the reference platforms being equipped with an accelerometer sensor and elements of the IoT. The work surveys and compares accelerometer signals classification methods to enable IoT for the aforementioned functions. The considered methods are support vector machines (SVMs), decision trees, and dynamic time warping. A comparison of the methods has been proposed to highlight their performance: all the techniques have good recognition accuracies and, among them, the SVM-based approaches show an accuracy above 90% in the case of AR and above 99% in the case of MR.

Context‐awareness over transient cloud in D2D networks: energy performance analysis and evaluation

Abstract: The exponential increase in the number and types of mobile devices, along with their ever-growing sets of capabilities, have enabled the development of new architectures that aim to harness such heterogeneity. Transient clouds are examples of mobile clouds, which are created on-the-fly by the devices present in an environment to share their physical resources (e.g. CPU, memory and network) and would disappear as the nodes leave the network. They enable a device to go beyond its own physical limitations through utilising the capabilities offered by nearby devices over an ad hoc network. This idea exploits the device-to-device (D2D) communications paradigm, which allows two nearby devices to communicate with each other in the licenced cellular bandwidth without a base station involved. In this paper, we present a transient context-aware cloud (TCAC) paradigm based on the assumption that the nodes of the network care more about providing/learning higher level functionalities rather than lower level capabilities in D2D scenario. The proposed architecture, realised by using a WiFi Direct, can be portable through any paradigm, which exploits the D2D communications, so opening the doors to forthcoming 5G scenarios. We present a prototype implementation of our architecture over Android smartphones connected via WiFi Direct along with the performance metrics (power/energy consumption and accuracy) to show the benefits of TCAC. A theoretical and analytical model for the energy consumption related to a device within the TCAC is provided as well. Copyright © 2015 John Wiley & Sons, Ltd.

A Smart 2 Gaussian process approach for indoor localization with RSSI fingerprints

Abstract: Location Fingerprinting (LF) is a promising localization technique that enables many commercial and emergency Location-Based Services (LBS). The idea of this paper is two- folded. First, a Gaussian Process (GP) is used during the training (offline) phase of an indoor positioning algorithm to generate the fingerprint database, reducing the expensive labor of acquiring and maintaining the fingerprint database significantly. Furthermore, during the positioning (online) phase, a Smart algorithm (already proposed in [1]) is used for reducing the computation effort for positioning calculation. We call our idea Smart2 since it enhances the advantages of the base Smart approach. Specifically, Smart2 reduces the labor during the offline phase by trading it with a small positioning error and, at the same time, it limits the energy consumption in the online phase without incurring in any additional accuracy detriment.

Speaker Recognition Exploiting D2D Communications Paradigm: Performance Evaluation of Multiple Observations Approaches

Abstract: The diffusion of Device-to-Device (D2D) communications opens the door to exploit the contributions of multiple Mobile Devices (MDs) to accomplish collaborative tasks In this paper a speaker recognition algorithm for MDs based on a multiple-observations approach is presented We propose various fusion and clustering algorithms aimed at efficiently exploiting data coming from MDs Numerical results show that in many cases our multiple-observation approach is able to significantly improve the accuracy of the considered speaker recognition algorithm

Mobile Smart Helmet for Brain Stroke Early Detection through Neural Network-Based Signals Analysis

Abstract: The treatments for brain stroke are strongly time- dependent. The medical literature highlights the need of a quick diagnosis in order to guarantee the most effective therapy. An important target for strokes is trying to achieve a Door-to-Needle (DTN) time of less than 60 minutes, which is called Golden Hour [1]. This paper proposes a mobile Smart Helmet (SH) thought to be worn by a patient when the first aid medical team arrives and the aim is to efficiently recognize and detect a brain stroke, on site. While similar solutions in the literature employ the (usually computationally heavy) electromagnetic field inversion problem and image analysis, the proposal of this paper is an NN-based SH. It uses signal analysis to recognize the presence of a stroke with a limited computational burden. In the reported preliminary experiments, carried out via simulations, we have employed a MultiLayer Perceptron (MLP) model that implements a 4-layer NN. Numerical results show that proposed signal analysis, applied to a single brain model, is able to efficiently detect the stroke presence with an accuracy around 90%.

Performance analysis of smart audio pre-processing for noise-robust text-independent speaker recognition

Abstract: This paper presents a study on the performance of a speaker identification system in challenging environmental conditions, such as in the presence of noise and at a distance. We propose a robust speaker recognition algorithm, which includes a smart pre-processing method based on Voice Activity Detection (VAD), capable to boost the system accuracy. Results show that our solution is able to improve the correct classification rate of traditional speaker recognition systems, even in case of distant audio acquisition and noisy environments.

Brain stroke detection by means of complex dielectric permittivity reconstruction at microwaves

Abstract: Brain stroke detection is becoming an important topic for the microwave imaging research community. In this work, we propose a quantitative method for detecting hemorrhagic brain strokes through the reconstruction of the dielectric permittivity distribution inside head. The associated nonlinear inverse scattering problem is iteratively solved by means of an inexact-Newton method. Preliminary numerical results, produced by applying the proposed method without a previous knowledge of the internal structure of the head, are presented and briefly discussed.

Microwave data inversion in hemorrhagic brain stroke imaging: A Newton-conjugate-gradient based approach in L p Banach spaces (Invited paper)

Abstract: This paper concerns the problem of data inversion in microwave imaging for biomedical applications. In particular, the integral equations of the inverse scattering problem are solved — in a regularized sense — by a new iterative procedure based on a conjugate gradient method. The approach is developed in Lp Banach spaces. Transverse magnetic illumination conditions are assumed in a tomographic configuration. The detection of hemorrhagic brain strokes is considered in the reported numerical simulations.

A nonlinear iterative inverse scattering procedure in L p Banach spaces for microwave biomedical imaging

Abstract: This paper presents a tomographic inverse scattering algorithm based on an iterative regularization approach developed in Lp Banach spaces. The proposed technique has been applied to the microwave biomedical imaging of the human head, in order to detect and locate hemorrhagic brain strokes. Preliminary numerical results are provided in order to show the capabilities of the inversion method.