2025
Journal article
Open Access
StepLogger and EvaalScore: the software suite of the IPIN onsite indoor localization competition
Girolami M., Baronti P., Potortì F., Crivello A., Palumbo F.
This paper illustrates the software suite developed for Track 1 of the IPIN competition, which evaluates smartphone apps for indoor localization. Competitors have one day before the trial day to survey the competition area. On the trial day, an independent “actor” carries the competing system on smartphone and walks a predefined path. Competing systems provide continuous location estimates, which are later compared to a ground truth. We describe the software suite used to gather and present the results: the StepLogger Android application for real-time logging of position estimates and the EvaalScore tool for performance evaluation. StepLogger collects location estimating data from competitors with a timestamp, while EvaalScore calculates the accuracy of the competing systems. The competition ranking is based on the third quartile of point localization error. The presented software suite ensures a standardized and fair assessment of competing systems, thus promoting reproducibility and transparency in indoor localization research.Source: SOFTWAREX, vol. 30
DOI: 10.1016/j.softx.2025.102115
Project(s): Age-IT
Metrics:
Girolami M., Baronti P., Potortì F., Crivello A., Palumbo F.
This paper illustrates the software suite developed for Track 1 of the IPIN competition, which evaluates smartphone apps for indoor localization. Competitors have one day before the trial day to survey the competition area. On the trial day, an independent “actor” carries the competing system on smartphone and walks a predefined path. Competing systems provide continuous location estimates, which are later compared to a ground truth. We describe the software suite used to gather and present the results: the StepLogger Android application for real-time logging of position estimates and the EvaalScore tool for performance evaluation. StepLogger collects location estimating data from competitors with a timestamp, while EvaalScore calculates the accuracy of the competing systems. The competition ranking is based on the third quartile of point localization error. The presented software suite ensures a standardized and fair assessment of competing systems, thus promoting reproducibility and transparency in indoor localization research.Source: SOFTWAREX, vol. 30
DOI: 10.1016/j.softx.2025.102115
Project(s): Age-IT
Metrics:
See at:
CNR IRIS 
| www.sciencedirect.com | CNR IRIS 
| CNR IRIS
2024
Journal article
Open Access
Distributed versus centralized computing of coverage in mobile crowdsensing
Girolami M., Kocian A., Chessa S.
The expected spatial coverage of a crowdsensing platform is an important parameter that derives from the mobility data of the crowdsensing platform users. We tackle the challenge of estimating the anticipated coverage while adhering to privacy constraints, where the platform is restricted from accessing detailed mobility data of individual users. Specifically, we model the coverage as the probability that a user detours to a point of interest if the user is present in a certain region around that point. Following this approach, we propose and evaluate a centralized as well as a distributed implementation model. We examine real-world mobility data employed for assessing the coverage performance of the two models, and we show that the two implementation models provide different privacy requirements but are equivalent in terms of their outputs.Source: JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING, vol. 15 (issue 6), pp. 2941-2951
DOI: 10.1007/s12652-024-04788-w
Metrics:
Girolami M., Kocian A., Chessa S.
The expected spatial coverage of a crowdsensing platform is an important parameter that derives from the mobility data of the crowdsensing platform users. We tackle the challenge of estimating the anticipated coverage while adhering to privacy constraints, where the platform is restricted from accessing detailed mobility data of individual users. Specifically, we model the coverage as the probability that a user detours to a point of interest if the user is present in a certain region around that point. Following this approach, we propose and evaluate a centralized as well as a distributed implementation model. We examine real-world mobility data employed for assessing the coverage performance of the two models, and we show that the two implementation models provide different privacy requirements but are equivalent in terms of their outputs.Source: JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING, vol. 15 (issue 6), pp. 2941-2951
DOI: 10.1007/s12652-024-04788-w
Metrics:
See at:
Journal of Ambient Intelligence and Humanized Computing | IRIS Cnr | IRIS Cnr | Archivio della Ricerca - Università di Pisa | Archivio della Ricerca - Università di Pisa | CNR IRIS | CNR IRIS
2024
Journal article
Open Access
An experimental dataset for search and rescue operations in avalanche scenarios based on LoRa technology
Girolami M., Mavilia F., Berton A., Marrocco G., Bianco G. M.
Wireless technologies suitable for Search and Rescue (SaR) operations are becoming crucial for the success of such missions. In avalanche scenarios, the snow depth and the snowpack profile significantly influence the wireless propagation of technologies used to locate victims, such as ARVA (in French: appareil de recherche de victimes d’avalanche) systems. In this work, we explore the potential of LoRa technology under challenging realistic conditions. For the first time, we collect radiopropagation data and the contextual snow profile when the transmitter is buried over a 50×50 m area resembling a typical human-triggered avalanche. Specifically, we detail the methodology adopted to collect data through three test types: cross, maximum distance, and drone flyover. The data are annotated with accurate ground truth which allows evaluating localization algorithms based on the RSSI (received signal strength indicator) and SNR (signal-to-noise ratio) of LoRa units. We conducted tests under various environmental conditions, ranging from dry to wet snowpacks. Our results demonstrate the high quality of the LoRa channel, even when the target is buried at a depth of 1 meter in snow with a high liquid water content. At the same time, we quantify the effects of two main degrading factors for the LoRa propagation: the amount of the snow and the liquid water content existing in the snowpack profiles.Source: IEEE ACCESS, vol. 12, pp. 171015-171035
DOI: 10.1109/access.2024.3497654
Metrics:
Girolami M., Mavilia F., Berton A., Marrocco G., Bianco G. M.
Wireless technologies suitable for Search and Rescue (SaR) operations are becoming crucial for the success of such missions. In avalanche scenarios, the snow depth and the snowpack profile significantly influence the wireless propagation of technologies used to locate victims, such as ARVA (in French: appareil de recherche de victimes d’avalanche) systems. In this work, we explore the potential of LoRa technology under challenging realistic conditions. For the first time, we collect radiopropagation data and the contextual snow profile when the transmitter is buried over a 50×50 m area resembling a typical human-triggered avalanche. Specifically, we detail the methodology adopted to collect data through three test types: cross, maximum distance, and drone flyover. The data are annotated with accurate ground truth which allows evaluating localization algorithms based on the RSSI (received signal strength indicator) and SNR (signal-to-noise ratio) of LoRa units. We conducted tests under various environmental conditions, ranging from dry to wet snowpacks. Our results demonstrate the high quality of the LoRa channel, even when the target is buried at a depth of 1 meter in snow with a high liquid water content. At the same time, we quantify the effects of two main degrading factors for the LoRa propagation: the amount of the snow and the liquid water content existing in the snowpack profiles.Source: IEEE ACCESS, vol. 12, pp. 171015-171035
DOI: 10.1109/access.2024.3497654
Metrics:
See at:
IEEE Access | IEEE Access | CNR IRIS | ieeexplore.ieee.org | CNR IRIS
2024
Journal article
Open Access
Integrating indoor localization systems through a handoff protocol
Furfari F., Girolami M., Barsocchi P.
The increasing adoption of location-based services drives the pervasive adoption of localization systems available anywhere. Environments equipped with multiple indoor localization systems (ILSs) require managing the transition from one ILS to another in order to continue localizing the user's device even when moving indoor or outdoor. In this article, we focus on the handoff procedure, whose goal is to enable a device to trigger the transition between ILSs when specific conditions are verified. We distinguish between the triggering and managing operations, each requiring specific actions. We describe the activation of the handoff procedure by considering three types of ILSs design, each with increasing complexity. Moreover, we define five handoff algorithms-based RSSI signal analysis and we test them in a realistic environment with two nearby ILSs. We establish a set of evaluation metrics to measure the performance of the handoff procedure.Source: IEEE JOURNAL OF INDOOR AND SEAMLESS POSITIONING AND NAVIGATION, vol. 2, pp. 130-142
DOI: 10.1109/jispin.2024.3377146
Project(s): Investment Partenariato Esteso PE8 “Conseguenze e sfide dell'invecchiamento”
Metrics:
Furfari F., Girolami M., Barsocchi P.
The increasing adoption of location-based services drives the pervasive adoption of localization systems available anywhere. Environments equipped with multiple indoor localization systems (ILSs) require managing the transition from one ILS to another in order to continue localizing the user's device even when moving indoor or outdoor. In this article, we focus on the handoff procedure, whose goal is to enable a device to trigger the transition between ILSs when specific conditions are verified. We distinguish between the triggering and managing operations, each requiring specific actions. We describe the activation of the handoff procedure by considering three types of ILSs design, each with increasing complexity. Moreover, we define five handoff algorithms-based RSSI signal analysis and we test them in a realistic environment with two nearby ILSs. We establish a set of evaluation metrics to measure the performance of the handoff procedure.Source: IEEE JOURNAL OF INDOOR AND SEAMLESS POSITIONING AND NAVIGATION, vol. 2, pp. 130-142
DOI: 10.1109/jispin.2024.3377146
Project(s): Investment Partenariato Esteso PE8 “Conseguenze e sfide dell'invecchiamento”
Metrics:
2024
Conference article
Open Access
Design of postural analysis and indoor localization services in AAL scenarios
Barsocchi P., Girolami M., Palumbo F.
Advancements in Ambient Assisted Living (AAL) technology have enabled innovative solutions to enhance the quality of life for older adults. The AA@THE project focuses on personalized coaching and monitoring systems to prevent risky conditions and promote healthy ageing. Two crucial domains, sedentariness and stability, are addressed through advanced technologies such as proximity detection and postural analysis services. By analyzing these specific health and behavioural aspects, personalized feedback is provided to improve overall well-being.Source: LECTURE NOTES IN BIOENGINEERING, pp. 157-160. Bari, Italy, 14-16/06/2023
DOI: 10.1007/978-3-031-63913-5_14
Project(s): Tuscany Health Ecosystem
Metrics:
Barsocchi P., Girolami M., Palumbo F.
Advancements in Ambient Assisted Living (AAL) technology have enabled innovative solutions to enhance the quality of life for older adults. The AA@THE project focuses on personalized coaching and monitoring systems to prevent risky conditions and promote healthy ageing. Two crucial domains, sedentariness and stability, are addressed through advanced technologies such as proximity detection and postural analysis services. By analyzing these specific health and behavioural aspects, personalized feedback is provided to improve overall well-being.Source: LECTURE NOTES IN BIOENGINEERING, pp. 157-160. Bari, Italy, 14-16/06/2023
DOI: 10.1007/978-3-031-63913-5_14
Project(s): Tuscany Health Ecosystem
Metrics:
See at:
CNR IRIS | link.springer.com | doi.org | CNR IRIS | CNR IRIS
2024
Conference article
Open Access
Evaluating the impact of injected mobility data on measuring data coverage in crowdsensing scenarios
Kocian A., Girolami M., Capoccia S., Foschini L., Chessa S.
A major weakness of Mobile CrowdSensing Platforms (MCS) is the willingness of users to participate, as this implies disclosing their private data (for example, concerning mobility) to the MCS platform. In the effort to enforce data privacy in the creation of mobility coverage maps using an MCS platform, recent work proposes the use of a spatially distributed approach that, however, is vulnerable to data injection attacks. In this contribution, we define and implement a progressive attacker model following a statistical approach. We propose a novel mitigation strategy based on unsupervised anomaly detection. Accessing the coverage performance with real-world mobility data indicates that the mean value of the attacker's profile determines the probability of being revealed. In particular, we are able to identify the attacker and filter out the data injected by the attackers with high precision.Source: ... IEEE GLOBAL COMMUNICATIONS CONFERENCE, pp. 4672-4677. Cape Town, South Africa, 2024
DOI: 10.1109/globecom52923.2024.10901097
Metrics:
Kocian A., Girolami M., Capoccia S., Foschini L., Chessa S.
A major weakness of Mobile CrowdSensing Platforms (MCS) is the willingness of users to participate, as this implies disclosing their private data (for example, concerning mobility) to the MCS platform. In the effort to enforce data privacy in the creation of mobility coverage maps using an MCS platform, recent work proposes the use of a spatially distributed approach that, however, is vulnerable to data injection attacks. In this contribution, we define and implement a progressive attacker model following a statistical approach. We propose a novel mitigation strategy based on unsupervised anomaly detection. Accessing the coverage performance with real-world mobility data indicates that the mean value of the attacker's profile determines the probability of being revealed. In particular, we are able to identify the attacker and filter out the data injected by the attackers with high precision.Source: ... IEEE GLOBAL COMMUNICATIONS CONFERENCE, pp. 4672-4677. Cape Town, South Africa, 2024
DOI: 10.1109/globecom52923.2024.10901097
Metrics:
See at:
CNR IRIS | ieeexplore.ieee.org | CNR IRIS | CNR IRIS
2024
Journal article
Open Access
Indoor localization algorithms based on Angle of Arrival with a benchmark comparison
Furfari F., Girolami M., Mavilia F., Barsocchi P.
Indoor localization is crucial for developing intelligent environments capable of understanding user contexts and adapting to environmental changes. Bluetooth 5.1 Direction Finding is a recent specification that leverages the angle of departure (AoD) and angle of arrival (AoA) of radio signals to locate objects or people indoors. This paper presents a set of algorithms that estimate user positions using AoA values and the concept of the Confidence Region (CR), which defines the expected position uncertainty and helps to remove outlier measurements, thereby improving performance compared to traditional triangulation algorithms. We validate the algorithms with a publicly available dataset, and analyze the impact of body orientation relative to receiving units. The experimental results highlight the limitations and potential of the proposed solutions. From our experiments, we observe that the Conditional All-in algorithm presented in this work, achieves the best performance across all configuration settings in both line-of-sight and non-line-of-sight conditions.Source: AD HOC NETWORKS, vol. 166
DOI: 10.1016/j.adhoc.2024.103691
DOI: 10.2139/ssrn.4876021
Project(s): Age-IT, ChAALenge
Metrics:
Furfari F., Girolami M., Mavilia F., Barsocchi P.
Indoor localization is crucial for developing intelligent environments capable of understanding user contexts and adapting to environmental changes. Bluetooth 5.1 Direction Finding is a recent specification that leverages the angle of departure (AoD) and angle of arrival (AoA) of radio signals to locate objects or people indoors. This paper presents a set of algorithms that estimate user positions using AoA values and the concept of the Confidence Region (CR), which defines the expected position uncertainty and helps to remove outlier measurements, thereby improving performance compared to traditional triangulation algorithms. We validate the algorithms with a publicly available dataset, and analyze the impact of body orientation relative to receiving units. The experimental results highlight the limitations and potential of the proposed solutions. From our experiments, we observe that the Conditional All-in algorithm presented in this work, achieves the best performance across all configuration settings in both line-of-sight and non-line-of-sight conditions.Source: AD HOC NETWORKS, vol. 166
DOI: 10.1016/j.adhoc.2024.103691
DOI: 10.2139/ssrn.4876021
Project(s): Age-IT, ChAALenge
Metrics:
See at:
Ad Hoc Networks | IRIS Cnr | IRIS Cnr | doi.org | CNR IRIS
2024
Journal article
Open Access
PRORL: Proactive Resource Orchestrator for Open RANs Using Deep Reinforcement Learning
Staffolani A., Darvariu V., Foschini L., Girolami M., Bellavista P., Musolesi M.
Open Radio Access Network (O-RAN) is an emerging paradigm proposed for enhancing the 5G network infrastructure. O-RAN promotes open vendor-neutral interfaces and virtualized network functions that enable the decoupling of network components and their optimization through intelligent controllers. The decomposition of base station functions enables better resource usage, but also opens new technical challenges concerning their efficient orchestration and allocation. In this paper, we propose Proactive Resource Orchestrator based on Reinforcement Learning (PRORL), a novel solution for the efficient and dynamic allocation of resources in O-RAN infrastructures. We frame the problem as a Markov Decision Process and solve it using Deep Reinforcement Learning; one relevant feature of PRORL is that it learns demand patterns from experience for proactive resource allocation. We extensively evaluate our proposal by using both synthetic and real-world data, showing that we can significantly outperform the existing algorithms, which are typically based on the analysis of static demands. More specifically, we achieve an improvement of 90% over greedy baselines and deal with complex trade-offs in terms of competing objectives such as demand satisfaction, resource utilization, and the inherent cost associated with allocating resources.Source: IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT
DOI: 10.1109/tnsm.2024.3373606
Project(s): The Alan Turing Institute
Metrics:
Staffolani A., Darvariu V., Foschini L., Girolami M., Bellavista P., Musolesi M.
Open Radio Access Network (O-RAN) is an emerging paradigm proposed for enhancing the 5G network infrastructure. O-RAN promotes open vendor-neutral interfaces and virtualized network functions that enable the decoupling of network components and their optimization through intelligent controllers. The decomposition of base station functions enables better resource usage, but also opens new technical challenges concerning their efficient orchestration and allocation. In this paper, we propose Proactive Resource Orchestrator based on Reinforcement Learning (PRORL), a novel solution for the efficient and dynamic allocation of resources in O-RAN infrastructures. We frame the problem as a Markov Decision Process and solve it using Deep Reinforcement Learning; one relevant feature of PRORL is that it learns demand patterns from experience for proactive resource allocation. We extensively evaluate our proposal by using both synthetic and real-world data, showing that we can significantly outperform the existing algorithms, which are typically based on the analysis of static demands. More specifically, we achieve an improvement of 90% over greedy baselines and deal with complex trade-offs in terms of competing objectives such as demand satisfaction, resource utilization, and the inherent cost associated with allocating resources.Source: IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT
DOI: 10.1109/tnsm.2024.3373606
Project(s): The Alan Turing Institute
Metrics:
See at:
UCL Discovery | doi.org | Archivio istituzionale della ricerca - Alma Mater Studiorum Università di Bologna | IRIS Cnr | Archivio istituzionale della ricerca - Alma Mater Studiorum Università di Bologna | GitHub | CNR IRIS
2024
Journal article
Open Access
A UAV deployment strategy based on a probabilistic data coverage model for mobile CrowdSensing applications
Girolami M., Cipullo E., Colella T., Chessa S.
Mobile CrowdSensing (MCS) is a computational paradigm designed to gather sensing data by using personal devices of MCS platform users. However, being the mobility of devices tightly correlated with mobility of their owners, the locations from which data are collected might be limited to specific sub-regions. We extend the data coverage capability of a traditional 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. The model analyses the user’s trajectories and the detouring capability of users towards locations of interest. Our model provides a coverage probability for each of the target locations, so that to identify low-covered locations. In turn, these locations are used as targets for the StationPositioning algorithms which optimizes the deployment of k UAV stations. We analyze the performance of StationPositioning by comparing the ratio of the covered locations against Random, DBSCAN and KMeans deployment 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: JOURNAL OF AMBIENT INTELLIGENCE AND SMART ENVIRONMENTS, vol. 16 (issue 2), pp. 241-268
DOI: 10.3233/ais-220601
Metrics:
Girolami M., Cipullo E., Colella T., Chessa S.
Mobile CrowdSensing (MCS) is a computational paradigm designed to gather sensing data by using personal devices of MCS platform users. However, being the mobility of devices tightly correlated with mobility of their owners, the locations from which data are collected might be limited to specific sub-regions. We extend the data coverage capability of a traditional 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. The model analyses the user’s trajectories and the detouring capability of users towards locations of interest. Our model provides a coverage probability for each of the target locations, so that to identify low-covered locations. In turn, these locations are used as targets for the StationPositioning algorithms which optimizes the deployment of k UAV stations. We analyze the performance of StationPositioning by comparing the ratio of the covered locations against Random, DBSCAN and KMeans deployment 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: JOURNAL OF AMBIENT INTELLIGENCE AND SMART ENVIRONMENTS, vol. 16 (issue 2), pp. 241-268
DOI: 10.3233/ais-220601
Metrics:
See at:
IRIS Cnr | IRIS Cnr | IRIS Cnr | Archivio della Ricerca - Università di Pisa | Journal of Ambient Intelligence and Smart Environments | Archivio della Ricerca - Università di Pisa | Archivio della Ricerca - Università di Pisa | CNR IRIS | CNR IRIS
2024
Journal article
Open Access
Bluetooth dataset for proximity detection in indoor environments collected with smartphones
Girolami M., La Rosa D., Barsocchi P.
This paper describes a data collection experiment and the resulting dataset based on Bluetooth beacon messages collected in an indoor museum. The goal of this dataset is to study algorithms and techniques for proximity detection between people and points of interest (POI). To this purpose, we release the data we collected during 32 museum's visits, in which we vary the adopted smartphones and the visiting paths. The smartphone is used to collect Bluetooth beacons emitted by Bluetooth tags positioned nearby each POI. The visiting layout defines the order of visit of 10 artworks. The combination of different smartphones, the visiting paths and features of the indoor museum allow experiencing with realistic environmental conditions. The dataset comprises RSS (Received Signal Strength) values, timestamp and artwork identifiers, as long as a detailed ground truth, reporting the starting and ending time of each artwork's visit. The dataset is addressed to researchers and industrial players interested in further investigating how to automatically detect the location or the proximity between people and specific points of interest, by exploiting commercial technologies available with smartphone. The dataset is designed to speed up the prototyping process, by releasing an accurate ground truth annotation and details concerning the adopted hardware.Source: DATA IN BRIEF, vol. 53
DOI: 10.1016/j.dib.2024.110215
Project(s): Project Tuscany Health Ecosystem, Recupero di Sistemi Informativi STOrico-artistici per una rinnovata comunicazione del patrimonio
Metrics:
Girolami M., La Rosa D., Barsocchi P.
This paper describes a data collection experiment and the resulting dataset based on Bluetooth beacon messages collected in an indoor museum. The goal of this dataset is to study algorithms and techniques for proximity detection between people and points of interest (POI). To this purpose, we release the data we collected during 32 museum's visits, in which we vary the adopted smartphones and the visiting paths. The smartphone is used to collect Bluetooth beacons emitted by Bluetooth tags positioned nearby each POI. The visiting layout defines the order of visit of 10 artworks. The combination of different smartphones, the visiting paths and features of the indoor museum allow experiencing with realistic environmental conditions. The dataset comprises RSS (Received Signal Strength) values, timestamp and artwork identifiers, as long as a detailed ground truth, reporting the starting and ending time of each artwork's visit. The dataset is addressed to researchers and industrial players interested in further investigating how to automatically detect the location or the proximity between people and specific points of interest, by exploiting commercial technologies available with smartphone. The dataset is designed to speed up the prototyping process, by releasing an accurate ground truth annotation and details concerning the adopted hardware.Source: DATA IN BRIEF, vol. 53
DOI: 10.1016/j.dib.2024.110215
Project(s): Project Tuscany Health Ecosystem, Recupero di Sistemi Informativi STOrico-artistici per una rinnovata comunicazione del patrimonio
Metrics:
See at:
Data in Brief | Data in Brief | IRIS Cnr | IRIS Cnr | CNR IRIS
2024
Contribution to book
Open Access
HCCS 2024: 4th Workshop on Human-Centered Computational Sensing - Welcome and Committees
Delmastro F., Girolami M., Theoleyre F.
We are pleased to present the proceedings of the Fourth edition of the International IEEE Workshop on Human-Centered Computational Sensing (HCCS'24) held in conjunction with IEEE PerCom 2024. The HCCS workshop aims to advance and promote research about how unobtrusive observation of human cognitive, behavioral, physiological, and contextual data increasingly enables new computing experiences and effective intervention opportunities. The workshop also seeks to stimulate dialogue about the implications of human-centered computational sensing for societyDOI: 10.1109/percomworkshops59983.2024.10503049
Metrics:
Delmastro F., Girolami M., Theoleyre F.
We are pleased to present the proceedings of the Fourth edition of the International IEEE Workshop on Human-Centered Computational Sensing (HCCS'24) held in conjunction with IEEE PerCom 2024. The HCCS workshop aims to advance and promote research about how unobtrusive observation of human cognitive, behavioral, physiological, and contextual data increasingly enables new computing experiences and effective intervention opportunities. The workshop also seeks to stimulate dialogue about the implications of human-centered computational sensing for societyDOI: 10.1109/percomworkshops59983.2024.10503049
Metrics:
See at:
CNR IRIS | ieeexplore.ieee.org | doi.org | CNR IRIS | CNR IRIS
2023
Conference article
Open Access
Evaluating the impact of anchors deployment for an AoA-based indoor localization system
Mavilia F, Barsocchi P, Furfari F, Girolami M
Indoor localization techniques are rapidly moving toward the combination of multiple source of information. Among these, RSS, Time of Flight (ToF), Angle of Arrival (AoA) and of Departure (AoD) represent effective solutions for indoor environments. In this work, we propose an on-going activity investigating the performance of an indoor localization system based on the AoA-Bluetooth 5.1 specification, namely Direction Finding. We evaluate the effect of two anchor deployments and we test our localization algorithm by varying the orientation of the target according to four postures: North, West, South and East. From our study, we observe that anchor nodes deployed on the ceiling provide the best performance in terms of localization error. We conclude this work with a discussion of two further lines of investigation potentially increasing the performance of AoA-based indoor localization systems.DOI: 10.23919/wons57325.2023.10061949
Metrics:
Mavilia F, Barsocchi P, Furfari F, Girolami M
Indoor localization techniques are rapidly moving toward the combination of multiple source of information. Among these, RSS, Time of Flight (ToF), Angle of Arrival (AoA) and of Departure (AoD) represent effective solutions for indoor environments. In this work, we propose an on-going activity investigating the performance of an indoor localization system based on the AoA-Bluetooth 5.1 specification, namely Direction Finding. We evaluate the effect of two anchor deployments and we test our localization algorithm by varying the orientation of the target according to four postures: North, West, South and East. From our study, we observe that anchor nodes deployed on the ceiling provide the best performance in terms of localization error. We conclude this work with a discussion of two further lines of investigation potentially increasing the performance of AoA-based indoor localization systems.DOI: 10.23919/wons57325.2023.10061949
Metrics:
See at:
CNR IRIS | ieeexplore.ieee.org | ISTI Repository | CNR IRIS | CNR IRIS
2023
Other
Restricted
THE D.3.2.1 - AA@THE User needs, technical requirements and specifications
Pratali L, Campana M G, Delmastro F, Di Martino F, Pescosolido L, Barsocchi P, Broccia G, Ciancia V, Gennaro C, Girolami M, Lagani G, La Rosa D, Latella D, Magrini M, Manca M, Massink M, Mattioli A, Moroni D, Palumbo F, Paradisi P, Paternò F, Santoro C, Sebastiani L, Vairo C
Deliverable D3.2.1 del progetto PNRR Ecosistemi ed innovazione - THE
Pratali L, Campana M G, Delmastro F, Di Martino F, Pescosolido L, Barsocchi P, Broccia G, Ciancia V, Gennaro C, Girolami M, Lagani G, La Rosa D, Latella D, Magrini M, Manca M, Massink M, Mattioli A, Moroni D, Palumbo F, Paradisi P, Paternò F, Santoro C, Sebastiani L, Vairo C
Deliverable D3.2.1 del progetto PNRR Ecosistemi ed innovazione - THE
2023
Conference article
Open Access
A TinyML-approach to detect the proximity of people based on bluetooth low energy beacons
Girolami M, Fattori F, Chessa S
Proximity detection is the process of estimating the closeness between a target and a point of interest, and it can be estimated with different technologies and techniques. In this paper we focus on how detecting proximity between people with a TinyML-based approach. We analyze RSS values (Received Signal Strength) estimated by a micro-controller and propagated by Bluetooth's tags. To this purpose, we collect a dataset of Bluetooth RSS signals by considering different postures of the involved people. The dataset is adopted to train and test two neural networks: a fully-connected and an LSTM model that we compress to be executed directly on-board of the micro-controller. Experimental results conducted over the dataset show an average precision and recall metrics of 0.8 with both of the models, and with an inference time less than 1 ms.DOI: 10.1109/ie57519.2023.10179090
Metrics:
Girolami M, Fattori F, Chessa S
Proximity detection is the process of estimating the closeness between a target and a point of interest, and it can be estimated with different technologies and techniques. In this paper we focus on how detecting proximity between people with a TinyML-based approach. We analyze RSS values (Received Signal Strength) estimated by a micro-controller and propagated by Bluetooth's tags. To this purpose, we collect a dataset of Bluetooth RSS signals by considering different postures of the involved people. The dataset is adopted to train and test two neural networks: a fully-connected and an LSTM model that we compress to be executed directly on-board of the micro-controller. Experimental results conducted over the dataset show an average precision and recall metrics of 0.8 with both of the models, and with an inference time less than 1 ms.DOI: 10.1109/ie57519.2023.10179090
Metrics:
See at:
CNR IRIS | ieeexplore.ieee.org | ISTI Repository | CNR IRIS | CNR IRIS
2023
Journal article
Open Access
A Bluetooth 5.1 dataset based on angle of arrival and RSS for indoor localization
Girolami M, Furfari F, Barsocchi P, Mavilia F
Several Radio-Frequency technologies have been explored to evaluate the efficacy of localization algorithms in indoor environments, including Received Signal Strength (RSS), Time of Flight (ToF), and Angle of Arrival (AoA). Among these, AoA technique has been gaining interest when adopted with the Bluetooth protocol. In this work, we describe a data collection measurement campaign of AoA and RSS values collected from Bluetooth 5.1 compliant tags and a set of anchor nodes deployed in the environment. We detail the adopted methodology to collect the dataset and we report all the technical details to reproduce the data collection process. The resulting dataset and the adopted software is publicly available to the community. To collect the dataset, we deploy four anchor nodes and four Bluetooth tags and we reproduce some representative scenarios for indoor localization: calibration, static, mobility, and proximity. Each scenario is annotated with an accurate ground truth (GT). We also assess the quality of the collected data. Specifically, we compute the Mean Absolute Error (MAE) between the AoA estimated by the anchors and the corresponding GT. Additionally, we investigate the packet loss metric which measures the percentage of Bluetooth beacons lost by the anchors.Source: IEEE ACCESS, vol. 11, pp. 81763-81776
DOI: 10.1109/access.2023.3301126
Metrics:
Girolami M, Furfari F, Barsocchi P, Mavilia F
Several Radio-Frequency technologies have been explored to evaluate the efficacy of localization algorithms in indoor environments, including Received Signal Strength (RSS), Time of Flight (ToF), and Angle of Arrival (AoA). Among these, AoA technique has been gaining interest when adopted with the Bluetooth protocol. In this work, we describe a data collection measurement campaign of AoA and RSS values collected from Bluetooth 5.1 compliant tags and a set of anchor nodes deployed in the environment. We detail the adopted methodology to collect the dataset and we report all the technical details to reproduce the data collection process. The resulting dataset and the adopted software is publicly available to the community. To collect the dataset, we deploy four anchor nodes and four Bluetooth tags and we reproduce some representative scenarios for indoor localization: calibration, static, mobility, and proximity. Each scenario is annotated with an accurate ground truth (GT). We also assess the quality of the collected data. Specifically, we compute the Mean Absolute Error (MAE) between the AoA estimated by the anchors and the corresponding GT. Additionally, we investigate the packet loss metric which measures the percentage of Bluetooth beacons lost by the anchors.Source: IEEE ACCESS, vol. 11, pp. 81763-81776
DOI: 10.1109/access.2023.3301126
Metrics:
See at:
CNR IRIS | ieeexplore.ieee.org | ISTI Repository | CNR IRIS | CNR IRIS
2023
Conference article
Open Access
Modelling the localization error of an AoA-based localization system
Furfari F, Barsocchi P, Girolami M, Mavilia F
Indoor localization provides important context information to develop Intelligent Environments able to understand user situations, to react and adapt to changes in the surrounding environment. Bluetooth 5.1 Direction Finding (DF) is a recent specification based on angle of departure (AoD) and arrival (AoA) of radio signals and it is addressed to localize objects or people in indoor scenarios. In this work, we study the error propagation of an indoor localization system based on AoA technique and on multiple anchor receivers.DOI: 10.1109/ie57519.2023.10179094
Metrics:
Furfari F, Barsocchi P, Girolami M, Mavilia F
Indoor localization provides important context information to develop Intelligent Environments able to understand user situations, to react and adapt to changes in the surrounding environment. Bluetooth 5.1 Direction Finding (DF) is a recent specification based on angle of departure (AoD) and arrival (AoA) of radio signals and it is addressed to localize objects or people in indoor scenarios. In this work, we study the error propagation of an indoor localization system based on AoA technique and on multiple anchor receivers.DOI: 10.1109/ie57519.2023.10179094
Metrics:
See at:
CNR IRIS | ieeexplore.ieee.org | ISTI Repository | CNR IRIS | CNR IRIS
2023
Contribution to book
Open Access
Welcome from the demo chairs
Girolami M, Yasumoto K
This year we had 33 demo proposals submitted and 23 of them have been accepted by the committee. These papers address important problems in several application domains ranging from IoT, wearable and mobile devices, security/privacy, and real-life applications in pervasive computing. During PerCom, one of the selected demos receives the "Best Demo Award" based on its research value, originality, and presentation. We thank all the authors who submitted their innovative demo papers to PerCom this year, and the committee members for volunteering their time and hard to benefit the PerCom community by providing high-quality reviews.DOI: 10.1109/percomworkshops56833.2023.10150290
Metrics:
Girolami M, Yasumoto K
This year we had 33 demo proposals submitted and 23 of them have been accepted by the committee. These papers address important problems in several application domains ranging from IoT, wearable and mobile devices, security/privacy, and real-life applications in pervasive computing. During PerCom, one of the selected demos receives the "Best Demo Award" based on its research value, originality, and presentation. We thank all the authors who submitted their innovative demo papers to PerCom this year, and the committee members for volunteering their time and hard to benefit the PerCom community by providing high-quality reviews.DOI: 10.1109/percomworkshops56833.2023.10150290
Metrics:
See at:
CNR IRIS | ieeexplore.ieee.org | ISTI Repository | CNR IRIS
2023
Conference article
Open Access
A VNF-chaining approach for enhancing ground network with UAVs in a crowd-based environment
Bozzone Montagno D, Chessa S, Girolami M, Paganelli F
In the context of a 5G and beyond network operating in a smart city, in which the fixed network infrastructure is supported by a flock of unmanned aerial vehicles (UAV) operating as carriers of Virtual Network Functions (VNF), we propose a Mixed Integer Linear Programming (MILP) model to place chains of VNFs on a hybrid UAV-terrestrial infrastructure so to maximize the UAV lifetime while considering resource constraints and by taking into account the network traffic originated by crowds of people assembling in the city at given hotpoints. We formalize the UAV deployment problem and we test our solution with a practical scenario based on DoS detection system. The experimental results assess the deployment in a practical scenario of a DoS detection system and show that the proposed solution can effectively enhance the capability of the system to process the input flows under a DoS attack.Source: PROCEEDINGS - IEEE SYMPOSIUM ON COMPUTERS AND COMMUNICATIONS. Gammarth, Tunisia, 9-12/07/2023
DOI: 10.1109/iscc58397.2023.10217879
Metrics:
Bozzone Montagno D, Chessa S, Girolami M, Paganelli F
In the context of a 5G and beyond network operating in a smart city, in which the fixed network infrastructure is supported by a flock of unmanned aerial vehicles (UAV) operating as carriers of Virtual Network Functions (VNF), we propose a Mixed Integer Linear Programming (MILP) model to place chains of VNFs on a hybrid UAV-terrestrial infrastructure so to maximize the UAV lifetime while considering resource constraints and by taking into account the network traffic originated by crowds of people assembling in the city at given hotpoints. We formalize the UAV deployment problem and we test our solution with a practical scenario based on DoS detection system. The experimental results assess the deployment in a practical scenario of a DoS detection system and show that the proposed solution can effectively enhance the capability of the system to process the input flows under a DoS attack.Source: PROCEEDINGS - IEEE SYMPOSIUM ON COMPUTERS AND COMMUNICATIONS. Gammarth, Tunisia, 9-12/07/2023
DOI: 10.1109/iscc58397.2023.10217879
Metrics:
See at:
CNR IRIS | ieeexplore.ieee.org | ISTI Repository | CNR IRIS | CNR IRIS
2023
Conference article
Open Access
On the analysis of body orientation for indoor positioning with BLE 5.1 direction finding
Mavilia F, Barsocchi P, Furfari F, La Rosa D, Girolami M
The last decade showed a clear technological trend toward the adoption of heterogeneous source of information, combined with data-fusion strategies to increase the performance of indoor localization systems. In this respect, the adoption of short-range network protocols such as WiFi and Bluetooth represent a common approach. We investigate, in this work, the use of Bluetooth 5.1 Direction Finding specification to test an indoor localization system solely based on the estimated Angle of Arrival (AoA) between an anchor and a receiver. We first detail our experimental data collection campaign and the adopted hardware. Then, we study not only the accuracy of the estimated angles on two reference planes but also the localization error introduced with the proposed algorithm by varying the body orientation of the target user, namely North, South, West, Est. Experimental results in a real-world indoor environment show an average localization error of 2.08m with only 1 anchor node and 5° of AoA' error for all 28 monitored locations. We also identify regions in which the AoA estimation rapidly decreases, giving rise to the possibility of identifying the boundaries of the adopted technology.DOI: 10.1109/icc45041.2023.10279029
Metrics:
Mavilia F, Barsocchi P, Furfari F, La Rosa D, Girolami M
The last decade showed a clear technological trend toward the adoption of heterogeneous source of information, combined with data-fusion strategies to increase the performance of indoor localization systems. In this respect, the adoption of short-range network protocols such as WiFi and Bluetooth represent a common approach. We investigate, in this work, the use of Bluetooth 5.1 Direction Finding specification to test an indoor localization system solely based on the estimated Angle of Arrival (AoA) between an anchor and a receiver. We first detail our experimental data collection campaign and the adopted hardware. Then, we study not only the accuracy of the estimated angles on two reference planes but also the localization error introduced with the proposed algorithm by varying the body orientation of the target user, namely North, South, West, Est. Experimental results in a real-world indoor environment show an average localization error of 2.08m with only 1 anchor node and 5° of AoA' error for all 28 monitored locations. We also identify regions in which the AoA estimation rapidly decreases, giving rise to the possibility of identifying the boundaries of the adopted technology.DOI: 10.1109/icc45041.2023.10279029
Metrics:
See at:
CNR IRIS | ieeexplore.ieee.org | ISTI Repository | CNR IRIS | CNR IRIS
2023
Journal article
Open Access
A CrowdSensing-based approach for proximity detection in indoor museums with bluetooth tags
Girolami M, La Rosa D, Barsocchi P
In this work, we investigate the performance of a proximity detection system for visitors in an indoor museum exploiting data collected from the crowd. More specifically, we propose a CrowdSensing-based technique for proximity detection. Users' smartphones can collect and upload RSS (Received Signal Strength) values of nearby Bluetooth tags to a backend server, together with some context-information. In turn, the collected data are elaborated with the goal of calibrating two proximity detection algorithms: a range-based and a learning-based algorithm. We embed the algorithms with R-app, a visiting museum application tested in the Monumental Cemetery's museum located in Piazza dei Miracoli, Pisa (IT). We detail in this work an experimental campaign to measure the performance improvements of the CrowdSensing approach with respect to state-of-the-art algorithms widely adopted in the field of proximity detection. Experimental results show a clear improvement of the performance when data from the crowd are exploited with the proposed architecture.Source: AD HOC NETWORKS, vol. 154
DOI: 10.1016/j.adhoc.2023.103367
Metrics:
Girolami M, La Rosa D, Barsocchi P
In this work, we investigate the performance of a proximity detection system for visitors in an indoor museum exploiting data collected from the crowd. More specifically, we propose a CrowdSensing-based technique for proximity detection. Users' smartphones can collect and upload RSS (Received Signal Strength) values of nearby Bluetooth tags to a backend server, together with some context-information. In turn, the collected data are elaborated with the goal of calibrating two proximity detection algorithms: a range-based and a learning-based algorithm. We embed the algorithms with R-app, a visiting museum application tested in the Monumental Cemetery's museum located in Piazza dei Miracoli, Pisa (IT). We detail in this work an experimental campaign to measure the performance improvements of the CrowdSensing approach with respect to state-of-the-art algorithms widely adopted in the field of proximity detection. Experimental results show a clear improvement of the performance when data from the crowd are exploited with the proposed architecture.Source: AD HOC NETWORKS, vol. 154
DOI: 10.1016/j.adhoc.2023.103367
Metrics:
See at:
Ad Hoc Networks | CNR IRIS | ISTI Repository | ISTI Repository | www.sciencedirect.com | CNR IRIS | CNR IRIS