Showing papers by "Andrea Sciarrone published in 2015"

Smartphone-centric ambient assisted living platform for patients suffering from co-morbidities monitoring

Abstract: Recently, patients suffering from a set of physical and mental limitations, called co-morbidities, are often treated at home. In this environment, modern communication systems represent a great support to implement Ambient Assisted Living platforms aimed at monitoring patients at home because they enable the seamless integration of heterogeneous sensing units, medical devices, and ubiquitous access to data. This article describes a specific smartphone-centric architecture where smartphones are employed not only as hubs of the health information but also as sensing, processing, and transmitting devices. Smartphones have both short-range (Bluetooth and WiFi employed for local information exchange) and long-range (GPRS, 3G/4G, and WiFi employed as Internet access) communication capabilities; information processing capabilities offered by modern platforms often equipped with different CPUs and with flexible and efficient software; and sensing capabilities implemented through sensors embedded into smartphones such as GPS receivers, accelerometers, microphones, and radio interfaces or through external sensors added to smartphones by cables or connected through local radio interfaces. The specific case of co-morbidities considered in this article implies the necessity to acquire a heterogeneous set of data from patients and from their environment. For this reason this article highlights the information processing capabilities of the introduced smartphone-centric platform. Audio, localization, and movement information processing have been evidenced as well as the specific implementations of these capabilities and their performance.

A smartphone-centric platform for remote health monitoring of heart failure

Abstract: Heart failure is a chronic disease that alternates intense and weak phases and requires repeated and frequent hospital treatments. The use of automatic instruments for a remote and ubiquitous monitoring of biological parameters relevant to heart failure pathophysiology offers new perspectives to improve the patients' quality of life and the efficacy of the treatment.

SPECTRA: A SPEech proCessing plaTform as smaRtphone Application

Abstract: In this paper, an Android SPEech proCessing plaTform as smaRtphone Application (SPECTRA) is presented. Such application, developed by the authors, has three main functions: i) Gender Recognition (GR), ii) Speaker Recognition (SR) and iii) Language Recognition (LR). All these recognition functions are performed simultaneously by using unsupervised Support Vector Machine (SVM) classifiers. An innovative point of this paper lies in the automatic re-training of the employed SVMs which are able to dynamically update themselves when a (new) audio from a (new) speaker is provided. This allow to build more robust classifiers, which results in better recognition performances. In terms of accuracy, the GR reaches about 98% of correct classifications, SR performs around 80% while LR shows an accuracy of about 74%.

Asset tracking architecture with Bluetooth Low Energy tags and ad hoc smartphone applications

Abstract: The paper describes an original architecture aimed at tracking assets within construction sites or similar contexts. The main components are: i) RFID tags, ii) Bluetooth Low Energy (BLE) tags and iii) smartphones. The core functions of the architecture are performed by two Android applications: the Asset Proximity Locator (APL) and the Wandering Objects Location Finder (WOLF). The key feature of the asset tracking function is the ability to maximize smartphone battery lifetime by switching on and off the GPS unit, thus guaranteeing that the smartphone can be used for an entire working shift. A detailed energy consumption analysis is carried out for each component of the architecture. The results achieved by simulations, concerning BLE tag detection probability, are presented and discussed.