202 result(s)
Page Size: 10, 20, 50
Export: bibtex, xml, json, csv
Order by:

CNR Author operator: and / or
more
Typology operator: and / or
more
Language operator: and / or
Date operator: and / or
more
Rights operator: and / or
2021 Report Restricted

A deployment strategy for UAV based on a probabilistic data coverage model in mobile crowd-sensing
Girolami M., Cipullo E., Colella T., Chessa S.
Mobile CrowdSensing (MCS) is a computational paradigm designed to gather sensing data by using the personal devices of the MCS platform users. However, being the mobility of the devices tightly correlated with mobility of their owners, the covered area might be limited to specific sub-regions. We extend the coverage capability of a MCS platform by exploiting unmanned aerial vehicles (UAV) as mobile sensors gathering data from low covered locations. We present a probabilistic model designed to measure the coverage of a location by analysing the user's trajectories and the detouring capability of MCS users towards a location of interest. Our model provides a coverage used revealing low-covered locations. These are used as targets for StationPositioning, our proposed algorithm optimizing the deployment of k UAV stations. We analyze the performance of StationPositioning by comparing the ratio of the covered locations against Random, DBSCAN and KMeasn algorithm. We explore the performance by varying the time period, the deployment regions and the existence of areas where it is not possible to deploy any station. Our experimental results show that StationPositioning is able to optimize the selected target location for a number of UAV stations with a maximum covered ratio up to 60%Source: ISTI-TR-2021/010, pp.1–14, 2021
DOI: 10.32079/isti-tr-2021/010

See at: CNR ExploRA Restricted


2021 Journal article Open Access OPEN

How mobility and sociality reshape the context: a decade of experience in mobile crowdsensing
Girolami M., Belli D., Chessa S., Foschini L.
The possibility of understanding the dynamics of human mobility and sociality creates the opportunity to re-design the way data are collected by exploiting the crowd. We survey the last decade of experimentation and research in the field of mobile CrowdSensing, a paradigm centred on users' devices as the primary source for collecting data from urban areas. To this purpose, we report the methodologies aimed at building information about users' mobility and sociality in the form of ties among users and communities of users. We present two methodologies to identify communities: spatial and co-location-based. We also discuss some perspectives about the future of mobile CrowdSensing and its impact on four investigation areas: contact tracing, edge-based MCS architectures, digitalization in Industry 5.0 and community detection algorithms.Source: Sensors (Basel) 21 (2021). doi:10.3390/s21196397
DOI: 10.3390/s21196397

See at: ISTI Repository Open Access | CNR ExploRA Open Access | www.mdpi.com Open Access


2020 Journal article Restricted

A Probabilistic Model for the Deployment of Human-enabled Edge Computing in Massive Sensing Scenarios
Belli D., Chessa S., Foschini L., Girolami M.
Human-enabled Edge Computing (HEC) is a recent smart city technology designed to combine the advantages of massive Mobile CrowdSensing (MCS) techniques with the potential of Multi-access Edge Computing (MEC). In this context, the architectural hierarchy of the network shifts the management of sensing information close to terminal nodes through the use of intermediate entities (edges) bridging the direct Cloud-Device communication channel. Recent proposals suggest the implementation of those edges, not only employing fixed MEC nodes, but also opportunistically using as edge nodes mobile devices selected among the terminal ones. However, inappropriate selection techniques may lead to an overestimation or an underestimation of the number of nodes to be used in such a layer. In this work, we propose a probabilistic model for the estimation of the number of mobile nodes to be selected as substitutes of fixed ones. The effectiveness of our model is verified with tests performed on real-world mobility traces.Source: IEEE Internet of Things Journal 7 (2020): 2421–2431. doi:10.1109/JIOT.2019.2957835
DOI: 10.1109/jiot.2019.2957835

See at: academic.microsoft.com Restricted | dblp.uni-trier.de Restricted | Archivio istituzionale della ricerca - Alma Mater Studiorum Università di Bologna Restricted | ieeexplore.ieee.org Restricted | ieeexplore.ieee.org Restricted | CNR ExploRA Restricted | xplorestaging.ieee.org Restricted


2020 Journal article Restricted

Optimization strategies for the selection of mobile edges in hybrid crowdsensing architectures
Belli D., Chessa S., Corradi A., Foschini L., Girolami M.
Communication infrastructures are rapidly evolving to support 5G enabling lower latency, high reliability, and scalability of the network and of the service provisioning. An important element of the 5G vision is Multi- access Edge Computing (MEC), that leverages the availability of powerful and low-cost middle boxes, i.e., MEC nodes, statically deployed at suitable edges of the network to extend the centralized cloud backbone. At the same time, after almost a decade of research, Mobile CrowdSensing (MCS) has established the technology able to collect sensing data on the environment by using personal devices, usually smartphones, as powerful sensing-and-communication platforms. Even though, mutual benefits due to the integration of MEC and Mobile CrowdSensing (MCS) are still largely unexplored. In this paper, we address and analyze the potential of the synergic use of MCS and MEC by thoroughly assessing various strategies for the selection of both traditional Fixed MEC (FMEC) edges as well as human-enabled Mobile MEC (M2EC) edges to support the collection of mobile CrowdSensing data. Collected results quantitatively show the effectiveness of the proposed optimization strategies in elastically scaling the load at edge nodes according to runtime provisioning needs.Source: Computer communications 157 (2020): 132–142. doi:10.1016/j.comcom.2020.04.006
DOI: 10.1016/j.comcom.2020.04.006

See at: Computer Communications Restricted | Computer Communications Restricted | Computer Communications Restricted | Computer Communications Restricted | CNR ExploRA Restricted | Computer Communications Restricted


2020 Master thesis Restricted

A survey on the use of 802.11 Channel State Information in device-free applications: indoor localization and human activity and gesture recognition
Uccheddu M. C.
It presents a survey on device-free applications using 802.11n Channel State Information (CSI). The survey analyzed device-free indoor localization works, human activity recognition works and gesture recognition works. For each work are described the system setting, the experimental environments and finally the evaluation. There is also the description of my personal implementation of a device-free indoor signal-based system setting, that was deployed at Consiglio Nazionale delle Ricerche (CNR) in Pisa.

See at: etd.adm.unipi.it Restricted | CNR ExploRA Restricted


2020 Conference article Restricted

Impact of evolutionary community detection algorithms for edge selection strategies
Barsocchi P., Belli D., Chessa S., Foschini L., Girolami M.
The combination of the edge computing paradigm with Mobile CrowdSensing (MCS) is a promising approach. However, the selection of the proper edge nodes is a crucial aspect that greatly affects the performance of the extended architecture. This work studies the performance of an edge-based MCS architecture with ParticipAct, a real-word experimental dataset. We present a community-based edge selection strategy and we measure two key metrics, namely latency and the number of requests satisfied. We show how they vary by adopting three evolutionary community detection algorithms, TILES, Infomap and iLCD configured by changing several configuration settings. We also study the two metrics, by varying the number of edge nodes selected so that to show its benefit.Source: GLOBECOM 2020 - IEEE Global Communications Conference, Taipei, Taiwan, December 07-11, 2020
DOI: 10.1109/globecom42002.2020.9348085

See at: Archivio istituzionale della ricerca - Alma Mater Studiorum Università di Bologna Restricted | ieeexplore.ieee.org Restricted | CNR ExploRA Restricted | xplorestaging.ieee.org Restricted


2020 Conference article Open Access OPEN

Understanding Human Mobility for CrowdSensing Strategies with the ParticipAct Data Set
Chessa S., Foschini L., Girolami M.
The Mobile CrowdSensing (MCS) paradigm has been increasingly adopted in the last years. Its adoption has been proved as beneficial for different scenarios, such as environmental monitoring and mobility analysis. However, one of the major barriers of the MCS initiatives, is the difficulty in recruiting users for the purpose of collecting data. We focus in this work to such limitation, and we analyze the mobility traces collected with a real-world MCS experiment, namely ParticipAct. Our goal is to discuss how to exploit the mobility features of the recruited users, as grounding information to plan and optimize a MCS data collection campaign. In detail, we analyze the quality of the data set, its accuracy and several features of human mobility such as radius of gyration and the real entropy of the locations visited. We discuss the impact of such metrics on the task scheduling, allocation and how to obtain a certain Tcoverage of data from visited locations.Source: GLOBECOM 2020 - 2020 IEEE Global Communications Conference, pp. 1–6, Taipei, Taiwan, Taiwan, 07/12/2020, 11/12/2020
DOI: 10.1109/globecom42002.2020.9322541

See at: ISTI Repository Open Access | academic.microsoft.com Restricted | dblp.uni-trier.de Restricted | Archivio istituzionale della ricerca - Alma Mater Studiorum Università di Bologna Restricted | ieeexplore.ieee.org Restricted | CNR ExploRA Restricted | xplorestaging.ieee.org Restricted


2019 Report Closed Access

Rapporto tecnico contenente i risultati ottenuti in merito allo studio di tecniche di crowd sourcing combinate con l'uso di droni
Cimino M. G. C. A, Gotta A., Chessa S., Del Vigna F., Dini G., Girolami M., La Manna M., Mavilia F., Perazzo P., Russo D., Saracino A., Varano D.
Descrizione del simulatore HUMSim utilizzato per la generazione di tracce sintetiche di mobilità pedestre Descrizione dell'analisi dei dati generati con HUMSim per l'utilizzo di droni al fine di raccogliere informazioni sensoriali in contesto urbanoSource: Project report, SCIADRO, 2019

See at: CNR ExploRA Restricted


2019 Journal article Restricted

Collaborative service discovery in mobile social networks
Girolami M., Belli D., Chessa S.
Mobile social networking is a recent paradigm arisen from the wide spread of mobile and wearable devices. Based on the short-range communication interfaces of these devices it is possible to establish opportunistic communications among them and build networks independent to the global one. Challenges introduced by this new type of networks are related to the sharing of resources and services and to the exploitation of the communication opportunities among devices. Limit of existing algorithms, that have sought to fill these shortages, is the lack of attention on the main actor of this service-oriented chain, the user. To this purpose, we introduce the COllaborative seRvice DIscovery ALgorithm (CORDIAL) that leverages both mobility and sociality of the users. We evaluate the performance of CORDIAL combined with different routing protocols for opportunistic networks, and we compare it with a benchmark algorithm (S-Flood) based on flooding and another service discovery algorithm designed to leverage mobile social network features, namely, ServIce DiscovEry in Mobile sociAl Networks (SIDEMAN). Our results show that the performance of CORDIAL remains stable with the different routing algorithms and that, in function of the query forwarding strategy triggered, CORDIAL matches the performance of S-Flood in terms of Query Response Time, achieving a better proactivity score with respect S-Flood and SIDEMAN as well.Source: Journal of network and systems management (Dordr., Online) 27 (2019): 233–268. doi:10.1007/s10922-018-9465-0
DOI: 10.1007/s10922-018-9465-0

See at: Journal of Network and Systems Management Restricted | Journal of Network and Systems Management Restricted | Journal of Network and Systems Management Restricted | link.springer.com Restricted | Journal of Network and Systems Management Restricted | Journal of Network and Systems Management Restricted | CNR ExploRA Restricted


2019 Conference article Restricted

Remote detection of indoor human proximity using bluetooth low energy beacons
Mavilia F., Palumbo F., Barsocchi P., Chessa S., Girolami M.
The way people interact in daily life is a challenging phenomenon to capture and to study without altering the natural rhythm of interactions. Our work investigates the possibility of automatically detecting proximity among people, the first mandatory condition before a dyad starts interacting. We present Remote Detection of Human Proximity (ReD-HuP), an algorithm based on the analysis of Bluetooth Low Energy beacons emitted by commercial wearable tags. We validate ReD-HuP with real-world indoor settings and we compare its performance with respect to detailed ground truth data collected from a number of volunteers. Experimental results show an accuracy and F-Score metric up to 95%.Source: IE 2019 - 15th International Conference on Intelligent Environments, pp. 16–21, Rabat, Morocco, June 24-27, 2109
DOI: 10.1109/ie.2019.000-1
Project(s): NESTORE via OpenAIRE

See at: academic.microsoft.com Restricted | dblp.uni-trier.de Restricted | ieeexplore.ieee.org Restricted | CNR ExploRA Restricted | xplorestaging.ieee.org Restricted


2019 Conference article Restricted

Selection of mobile edges for a hybrid crowdsensing architecture
Belli D., Chessa S., Corradi, Di Paolo G., Foschini L., Girolami M.
Mobile crowdsensing aims at the collection of sensor data on the environment by leveraging personal devices, usually smartphones. Its popularity is due to the ability of reaching capillary even the most remote areas (provided humans live there), with no infrastructure costs. This is possible because it leverages on existing 4G/5G communication infrastructures that are now rapidly evolving towards edge computing models. In this work we address the synergy between mobile crowdsensing and multi-access edge computing by analysing and assessing strategies for the selection of fixed and mobile edges to support the collection of mobile crowdsensing data.Source: ISCC 2019 - IEEE Symposium on Computers and Communications, Barcelona, Spain, 29 June - 3 July, 2019
DOI: 10.1109/iscc47284.2019.8969597

See at: academic.microsoft.com Restricted | dblp.uni-trier.de Restricted | Archivio istituzionale della ricerca - Alma Mater Studiorum Università di Bologna Restricted | ieeexplore.ieee.org Restricted | CNR ExploRA Restricted | xplorestaging.ieee.org Restricted


2019 Journal article Restricted

Personalized real-time anomaly detection and health feedback for older adults
Parvin P., Chessa S., Kaptein M., Paterno F.
Rapid population aging and the availability of sensors and intelligent objects motivate the development of healthcare systems; these systems, in turn, meet the needs of older adults by supporting them to accomplish their day-to-day activities. Collecting information regarding older adults daily activity potentially helps to detect abnormal behavior. Anomaly detection can subsequently be combined with real-time, continuous and personalized interventions to help older adults actively enjoy a healthy lifestyle. This paper introduces a system that uses a novel approach to generate personalized health feedback. The proposed system models user's daily behavior in order to detect anomalous behaviors and strategically generates interventions to encourage behaviors conducive to a healthier lifestyle. The system uses a Mamdani-type fuzzy rule-based component to predict the level of intervention needed for each detected anomaly and a sequential decision-making algorithm, Contextual Multi-armed Bandit, to generate suggestions to minimize anomalous behavior. We describe the system's architecture in detail and we provide example implementations for the anomaly detection and corresponding health feedback.Source: Journal of ambient intelligence and smart environments (Print) 11 (2019): 453–469. doi:10.3233/AIS-190536
DOI: 10.3233/ais-190536

See at: Journal of Ambient Intelligence and Smart Environments Restricted | Journal of Ambient Intelligence and Smart Environments Restricted | Journal of Ambient Intelligence and Smart Environments Restricted | Journal of Ambient Intelligence and Smart Environments Restricted | CNR ExploRA Restricted | Journal of Ambient Intelligence and Smart Environments Restricted | Journal of Ambient Intelligence and Smart Environments Restricted


2018 Conference article Open Access OPEN

UAVs and UAV swarms for civilian applications: communications and image processing in the SCIADRO project
Bacco M., Chessa S., Di Benedetto M., Fabbri D., Girolami M., Gotta A., Moroni D., Pascali M. A., Pellegrini V.
The use of Unmanned Aerial Vehicles (UAVs), or drones, is increasingly common in both research and industrial fields. Nowadays, the use of single UAVs is quite established and several products are already available to consumers, while UAV swarms are still subject of research and development. This position paper describes the objectives of a research project, namely SCIADRO2, which deals with innovative applications and network architectures based on the use of UAVs and UAV swarms in several civilian fields.Source: WiSATS 2017 - International Conference on Wireless and Satellite Systems, pp. 115–124, Oxford, UK, 14-15 September 2017
DOI: 10.1007/978-3-319-76571-6_12

See at: ISTI Repository Open Access | academic.microsoft.com Restricted | link.springer.com Restricted | link.springer.com Restricted | CNR ExploRA Restricted | rd.springer.com Restricted


2018 Journal article Open Access OPEN

Real-time anomaly detection in elderly behavior with the support of task models
Parvin P., Chessa S., Manca M., Paternò F.
With today's technology, elderly can be supported in living independently in their own homes for a prolonged period of time. Monitoring and analyzing their behavior in order to find possible unusual situation helps to provide the elderly with health warnings at the proper time. Current studies are focusing on the elderly daily activity and the detection of anomalous behaviors aiming to provide the older people with remote support. To this aim, we propose a real-time solution which models the user daily routine using a task model specification and detects relevant contextual events occurred in their life through a context manager. In addition, by a systematic validation through a system that automatically generates wrong sequences of tasks, we show that our algorithm is able to find behavioral deviations from the expected behavior at different times by considering the extended classification of the possible deviations with good accuracy.Source: Proceedings of the ACM on human-computer interaction 2 (2018). doi:10.1145/3229097
DOI: 10.1145/3229097

See at: ISTI Repository Open Access | Proceedings of the ACM on Human-Computer Interaction Restricted | Proceedings of the ACM on Human-Computer Interaction Restricted | dl.acm.org Restricted | Proceedings of the ACM on Human-Computer Interaction Restricted | Proceedings of the ACM on Human-Computer Interaction Restricted | Proceedings of the ACM on Human-Computer Interaction Restricted | Proceedings of the ACM on Human-Computer Interaction Restricted | CNR ExploRA Restricted


2018 Journal article Open Access OPEN

Indoor bluetooth low energy dataset for localization, tracking, occupancy, and social interaction
Baronti P., Barsocchi P., Chessa S., Mavilia F., Palumbo F.
Indoor localization has become a mature research area, but further scientific developments are limited due to the lack of open datasets and corresponding frameworks suitable to compare and evaluate specialized localization solutions. Although several competitions provide datasets and environments for comparing different solutions, they hardly consider novel technologies such as Bluetooth Low Energy (BLE), which is gaining more and more importance in indoor localization due to its wide availability in personal and environmental devices and to its low costs and flexibility. This paper contributes to cover this gap by: (i) presenting a new indoor BLE dataset; (ii) reviewing several, meaningful use cases in different application scenarios; and (iii) discussing alternative uses of the dataset in the evaluation of different positioning and navigation applications, namely localization, tracking, occupancy and social interaction.Source: Sensors (Basel) 18 (2018). doi:10.3390/s18124462
DOI: 10.3390/s18124462
Project(s): NESTORE via OpenAIRE

See at: Sensors Open Access | Sensors Open Access | Sensors Open Access | Sensors Open Access | Europe PubMed Central Open Access | ISTI Repository Open Access | CNR ExploRA Open Access | Sensors Open Access | Sensors Open Access | Sensors Open Access | Sensors Open Access


2018 Conference article Open Access OPEN

A Social-Based Approach to Mobile Edge Computing
Belli D., Chessa S., Foschini L., Girolami M.
Mobile Edge Computing (MEC) opens to the opportunity of moving high-volumes of data from the cloud to locations where the information is actually accessed. In turn, the combination of MEC with the Mobile Crowdsensing approach, using a restricted number of devices with respect the number of base stations, matches the performance of the conventional MEC middleware layer ensuring the same spatial coverage. In this work, we envision a MEC architecture composed by mobile and fixed edges. Their goal is to optimize the share of contents among users by exploiting their mobility and sociality. We first present an algorithm to identify a suitable set of mobile edges and we show how such selection increases the performance of a content-sharing scenario. Our experiments are based on the ParticipAct dataset, which captures the mobility of about 170 users for 10 months. The experiments show that the number of requests that can be served mobile edges is similar to that of requests served by fixed edges, and then that mobile edges can be considered a viable (and lowcost) alternative to fixed edges.Source: IEEE Symposium on Computers and Communications (ISCC), pp. 00292–00297, 25/06/2018, 28/06/2016
DOI: 10.1109/iscc.2018.8538763

See at: ISTI Repository Open Access | academic.microsoft.com Restricted | dblp.uni-trier.de Restricted | doi.org Restricted | Archivio istituzionale della ricerca - Alma Mater Studiorum Università di Bologna Restricted | ieeexplore.ieee.org Restricted | CNR ExploRA Restricted | xplorestaging.ieee.org Restricted


2018 Conference article Restricted

Enhancing mobile edge computing architecture with human-driven edge computing model
Belli D., Chessa S., Foschini L., Girolami M.
In an increasingly interconnected world, mobile and wearable devices, through short range communication interfaces and sensors, become needful tools for collecting and disseminating information in high population density environments. In this context Mobile Crowdsensing (MCS), leveraging people's roaming and their devices' resources, raised the citizen from mere walk-on parts to active participant in the knowledge building and data dissemination process. At the same time, Mobile Edge Computing (MEC) architecture has recently enhanced the two-layer cloud-device architectural model easing the exchange of information and shifting most computational cost from devices towards middle-layer proxies, namely, network edges. We introduce Human-driven Edge Computing, a new model which melts together the power of MEC platform and the large-scale sensing of MCS to realize a better data spreading and environmental coverage in smart cities. In addition, it will be briefly discussed the main sociological aspects related to human behavior and how they can influence the exchange of data in large-scale sensor networks.Source: 14th International Conference on Intelligent Environments (IE), pp. 95–98, Rome, Italy, 25-28 June, 2018
DOI: 10.1109/ie.2018.00023

See at: academic.microsoft.com Restricted | cris.unibo.it Restricted | dblp.uni-trier.de Restricted | Archivio istituzionale della ricerca - Alma Mater Studiorum Università di Bologna Restricted | ieeexplore.ieee.org Restricted | CNR ExploRA Restricted | xplorestaging.ieee.org Restricted


2018 Conference article Restricted

Anomaly detection in the elderly daily behavior
Parvin P., Paternò F., Chessa S.
The increasing availability of sensors and intelligent objects enables new functionalities and services. In the Ambient Assisted Living (AAL) domain, such technologies can be used for monitoring and reasoning about the older people behavior to detect possible anomalous situations, which could be a sign of the next onset of chronic illness or initial physical and cognitive decline. We propose an approach to detecting abnormal behavior by developing a profiling strategy (in which task models specify the normal behavior), which can also work in case of rare anomaly data. Events corresponding to the user behavior is detecting by a middleware software(Context Manager). Afterward, our algorithm compares the planned and actual behavior to identify if any deviation occurred and also defines to which category the anomaly belongs. The resulting environment should be able to generate multi-modal actions (i.e alarms, reminders) based on detected anomalous behavior, aiming to provide useful support to improve older people well-being.Source: 14TH INTERNATIONAL CONFERENCE ON INTELLIGENT ENVIRONMENTS, pp. 103–106, Rome, 25-28 June, 2018
DOI: 10.1109/ie.2018.00025

See at: academic.microsoft.com Restricted | dblp.uni-trier.de Restricted | ieeexplore.ieee.org Restricted | ieeexplore.ieee.org Restricted | CNR ExploRA Restricted | xplorestaging.ieee.org Restricted


2017 Journal article Restricted

Mobile crowd sensing management with the ParticipAct living lab
Chessa S., Girolami M., Foschini L., Ianniello R., Bellavista P., Corradi A.
On the one hand, some recent research projects, inspired by the widespread availability of sensor-provided smartphones, have built harvesting experiments to collect large quantities of data in urban areas. These efforts produced new real-world datasets, typically focusing on different technological aspects (GPS and Bluetooth mobility traces, WiFi indicators, ...) and, more recently, also on user-related data, from low-level accelerometer samples to higher-level social networking data. On the other hand, Mobile Crowd Sensing (MCS) blossomed with a few very recent projects, with the goal to efficiently coordinate user participation not only to collect passive monitoring data but also to allow active collaboration in participatory tasks. This paper presents the large- scale experience of the ParticipAct Living Lab, an ongoing experiment at the University of Bologna initiated 15 months ago, which involves about 170 students in MCS campaigns. In particular, the paper has two original goals: first, the comparison of the ParticipAct dataset against some primary datasets in the literature, such as the Nokia Mobile Data Challenge one; second, the robust evaluation and assessment of the original aspects of ParticipAct in itself, such as task assignment heuristics and consequent user acceptance of assigned MCS tasks. The reported results lead to an in-depth lessons learned discussion about socio- technical management aspects of MCS, valuable for the MCS community to design new MCS campaigns and to refine the whole MCS process to the purpose of better efficiency and scalability.Source: Pervasive and mobile computing (Print) 38 (2017): 200–214. doi:10.1016/j.pmcj.2016.09.005
DOI: 10.1016/j.pmcj.2016.09.005

See at: Pervasive and Mobile Computing Restricted | Pervasive and Mobile Computing Restricted | Pervasive and Mobile Computing Restricted | Pervasive and Mobile Computing Restricted | Pervasive and Mobile Computing Restricted | Pervasive and Mobile Computing Restricted | CNR ExploRA Restricted | Pervasive and Mobile Computing Restricted


2017 Journal article Open Access OPEN

A learning system for automatic Berg Balance Scale score estimation
Bacciu D., Chessa S., Gallicchio C., Micheli A., Pedrelli L., Ferro E., Fortunati L., La Rosa D., Palumbo F., Vozzi F., Parodi O.
The objective of this work is the development of a learning system for the automatic assessment of balance abilities in elderly people. The system is based on estimating the Berg Balance Scale (BBS) score from the stream of sensor data gathered by a Wii Balance Board. The scientific challenge tackled by our investigation is to assess the feasibility of exploiting the richness of the temporal signals gathered by the balance board for inferring the complete BBS score based on data from a single BBS exercise. The relation between the data collected by the balance board and the BBS score is inferred by neural networks for temporal data, modeled in particular as Echo State Networks within the Reservoir Computing (RC) paradigm, as a result of a comprehensive comparison among different learning models. The proposed system results to be able to estimate the complete BBS score directly from temporal data on exercise #10 of the BBS test, with ?10 s of duration. Experimental results on real-world data show an absolute error below 4 BBS score points (i.e. below the 7% of the whole BBS range), resulting in a favorable trade-off between predictive performance and user's required time with respect to previous works in literature. Results achieved by RC models compare well also with respect to different related learning models. Overall, the proposed system puts forward as an effective tool for an accurate automated assessment of balance abilities in the elderly and it is characterized by being unobtrusive, easy to use and suitable for autonomous usage.Source: Engineering applications of artificial intelligence 66 (2017): 60–74. doi:10.1016/j.engappai.2017.08.018
DOI: 10.1016/j.engappai.2017.08.018
Project(s): DOREMI via OpenAIRE

See at: Engineering Applications of Artificial Intelligence Open Access | Archivio della Ricerca - Università di Pisa Open Access | ISTI Repository Open Access | Engineering Applications of Artificial Intelligence Restricted | Engineering Applications of Artificial Intelligence Restricted | Engineering Applications of Artificial Intelligence Restricted | Engineering Applications of Artificial Intelligence Restricted | Engineering Applications of Artificial Intelligence Restricted | Engineering Applications of Artificial Intelligence Restricted | Engineering Applications of Artificial Intelligence Restricted | Engineering Applications of Artificial Intelligence Restricted | CNR ExploRA Restricted | Engineering Applications of Artificial Intelligence Restricted