sensors-logo

Journal Browser

Journal Browser

Sensors, Networks and Applications for Intelligent Services: Territory monitoring, Driver’s support, and Emergency

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Sensor Networks".

Deadline for manuscript submissions: closed (31 January 2022) | Viewed by 5245

Special Issue Editors


E-Mail Website
Guest Editor
Department of Engineering Enterprise “Mario Lucertini”, University of Rome “Tor Vergata”, 00133 Rome, Italy
Interests: 4G, 5G and 6G wireless/wired networks; signal processing and data analysis
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Department of Engineering Science, Guglielmo Marconi University, 00193 Rome, Italy
Interests: 5G; 6G; Network 2030; mobile radio systems; wired networks; Internet of Things; localization systems
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Department of Electronic Engineering, University of Roma Tor Vergata, Rome, Italy
Interests: 5G; 6G; wireless communication; drones and UAV communications; drone-enabled applications
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

In the last years the deployment of networks of sensors for providing intelligent services, such as the monitoring of territory, support to vehicles drivers and emergency, have become an indispensable necessity for almost every country. An advanced system for providing intelligent and integrated services integrates data originated from the different networks of sensors and Internet of Things (IoT) devices spared over the territory. Usually, each sensor network is tailored for the observation of one or a specific subset of phenomena to be kept under control i.e., we have networks for monitoring landslides and/or floods from rivers, earthquakes, volcanoes activity, etc. In  general,  the collecting sites  including  dataloggers,  mediators, servers in the cloud have just one group of data. Future applications (for vehicle drivers, for supporting emergency, for monitoring large areas or infrastructures) may be enabled by the integration of more than group of data such as weather and traffic data or user position and swelling of rivers. In each site, the single datalogger uses wired and/or local radio technologies (e.g., Wi-Fi, Bluetooth LE, ZigBee, etc.), to communicate with sensors acquiring the environmental data. In turn, the datalogger connects to the (specific) communication infrastructure serving the connecting network for the transfer of environmental as well as further data to one or more territorial control centers (TCCs). Due to the relatively small amount of data to be collected on a periodical basis, existing monitoring networks are characterized by very low transmission bit rates towards the TCC (i.e., from bit/s to some kbit/s) and we can refer to them as “narrowband” monitoring networks. The possibility of providing the TCC with environmental audio, FHD/4K/8K videos and/or images (in the visible and/or infrared ranges) from the observation sites would require a design of new sensor devices as well as to re-think the communication infrastructure to be associated with the innovative “broadband” monitoring network. The availability of these “new” types of data allow to improve the performance of the analysis and prediction algorithms used to assess the status of the environment and to ease the detection of anomalous/critical/emergency situations. Furthermore, “multimedia” information on the occurrence of anomalous events, provided by people recording video/audio contents with their smartphones has now become customary and could be seen as a sort of “casual” additional source of information on the environment to be exploited in some way.  In particular, innovative Machine Learning and Artificial Intelligence algorithms should integrate information from “social networks” (when available) with those from the narrowband/broadband monitoring networks in order to further support the detection of anomalous situations in a specific area. In addition, when properly managed and checked, information from “socials” could provide authorities with a preliminary view on the status of a declared emergency area even before the arrival of first responders. In the case of emergency, communications from authorities and organizations to individuals, groups or the general public are based on the emergency warning systems including a multitude of technologies such as: mobile phones, location-based alerting using short message service, email, TV, radio etc. Integration of the TCCs with the emergency warning system for fast alerting the population is an important aspect involving many technical and organizational issues.

Potential topics in this special issue include, but are not limited to:

  • Innovative, collaborative and advanced “broadband” monitoring networks for territory including, water monitoring, glacier monitoring, landslide monitoring, atmosphere monitoring and so on.
  • Aerial monitoring solutions including unmanned aerial systems (UAS).
  • Solutions for communication networks for the transport of monitored data on a local, regional, national scale: public and private terrestrial networks, LEO/MEO/GEO satellites.
  • Reliability, planning and dimensioning of innovative monitoring networks.
  • Technologies for sensors, IoT devices and UAS for the acquisition of environmental data even including multimedia data formats and/or information from social networks and social media.
  • Services and technologies for improve the drivers’ and pedestrians’ safety. Quality assurance and quality control of measurements.
  • GNSS accurate localization techniques for geo-tagging and for timestamp of data.
  • Machine learning, Artificial Intelligence and Big Data algorithms for environmental data analysis and for reliable detection of anomalous and critical situations.
  • Expert systems and Decision Support Systems (DSS) for Emergency Warning.
  • Network reconfigurability for emergency support.
  • Cost analysis of innovative and advanced monitoring networks and applications. Innovative business models.
  • Security aspects of monitoring networks and their applications.

Prof. Franco Mazzenga
Prof. Romeo Giuliano
Dr. Alessandro Vizzarri
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • environmental sensors
  • Internet of Things
  • intelligent monitoring of territory
  • broadband communication networks
  • emergency warning systems

Published Papers (2 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

27 pages, 3385 KiB  
Article
Communication Network Architectures for Driver Assistance Systems
by Romeo Giuliano, Franco Mazzenga, Eros Innocenti, Francesca Fallucchi and Ibrahim Habib
Sensors 2021, 21(20), 6867; https://doi.org/10.3390/s21206867 - 16 Oct 2021
Cited by 2 | Viewed by 2205
Abstract
Autonomous Driver Assistance Systems (ADAS) are of increasing importance to warn vehicle drivers of potential dangerous situations. In this paper, we propose one system to warn drivers of the presence of pedestrians crossing the road. The considered ADAS adopts a CNN-based pedestrian detector [...] Read more.
Autonomous Driver Assistance Systems (ADAS) are of increasing importance to warn vehicle drivers of potential dangerous situations. In this paper, we propose one system to warn drivers of the presence of pedestrians crossing the road. The considered ADAS adopts a CNN-based pedestrian detector (PD) using the images captured from a local camera and to generate alarms. Warning messages are then forwarded to vehicle drivers approaching the crossroad by means of a communication infrastructure using public radio networks and/or local area wireless technologies. Three possible communication architectures for ADAS are presented and analyzed in this paper. One format for the alert message is also presented. Performance of the PDs are analyzed in terms of accuracy, precision, and recall. Results show that the accuracy of the PD varies from 70% to 100% depending on the resolution of the videos. The effectiveness of each of the considered communication solutions for ADAS is evaluated in terms of the time required to forward the alert message to drivers. The overall latency including the PD processing and the alert communication time is then used to define the vehicle braking curve, which is required to avoid collision with the pedestrian at the crossroad. Full article
Show Figures

Figure 1

29 pages, 4761 KiB  
Article
Artificial Neural Networks, Sequence-to-Sequence LSTMs, and Exogenous Variables as Analytical Tools for NO2 (Air Pollution) Forecasting: A Case Study in the Bay of Algeciras (Spain)
by Javier González-Enrique, Juan Jesús Ruiz-Aguilar, José Antonio Moscoso-López, Daniel Urda, Lipika Deka and Ignacio J. Turias
Sensors 2021, 21(5), 1770; https://doi.org/10.3390/s21051770 - 4 Mar 2021
Cited by 12 | Viewed by 2221
Abstract
This study aims to produce accurate predictions of the NO2 concentrations at a specific station of a monitoring network located in the Bay of Algeciras (Spain). Artificial neural networks (ANNs) and sequence-to-sequence long short-term memory networks (LSTMs) were used to create the [...] Read more.
This study aims to produce accurate predictions of the NO2 concentrations at a specific station of a monitoring network located in the Bay of Algeciras (Spain). Artificial neural networks (ANNs) and sequence-to-sequence long short-term memory networks (LSTMs) were used to create the forecasting models. Additionally, a new prediction method was proposed combining LSTMs using a rolling window scheme with a cross-validation procedure for time series (LSTM-CVT). Two different strategies were followed regarding the input variables: using NO2 from the station or employing NO2 and other pollutants data from any station of the network plus meteorological variables. The ANN and LSTM-CVT exogenous models used lagged datasets of different window sizes. Several feature ranking methods were used to select the top lagged variables and include them in the final exogenous datasets. Prediction horizons of t + 1, t + 4 and t + 8 were employed. The exogenous variables inclusion enhanced the model’s performance, especially for t + 4 (ρ ≈ 0.68 to ρ ≈ 0.74) and t + 8 (ρ ≈ 0.59 to ρ ≈ 0.66). The proposed LSTM-CVT method delivered promising results as the best performing models per prediction horizon employed this new methodology. Additionally, per each parameter combination, it obtained lower error values than ANNs in 85% of the cases. Full article
Show Figures

Figure 1

Back to TopTop