4.6 Article

A Comprehensive Dependability Model for QoM-Aware Industrial WSN When Performing Visual Area Coverage in Occluded Scenarios

Journal

SENSORS
Volume 20, Issue 22, Pages -

Publisher

MDPI
DOI: 10.3390/s20226542

Keywords

dependability; mathematical modelling; availability; wireless sensor networks; visual sensing; coverage failures

Funding

  1. Norte Portugal Regional Operational Programme (NORTE 2020), under the PORTUGAL 2020 Partnership Agreement, through the European Social Fund (ESF) [NORTE-08-5369-FSE-000003]
  2. Brazilian CNPq (Conselho Nacional de Desenvolvimento Cientifico e Tecnologico) Agency [204691/2018-4]

Ask authors/readers for more resources

In critical industrial monitoring and control applications, dependability evaluation will be usually required. For wireless sensor networks deployed in industrial plants, dependability evaluation can provide valuable information, enabling proper preventive or contingency measures to assure their correct and safe operation. However, when employing sensor nodes equipped with cameras, visual coverage failures may have a deep impact on the perceived quality of industrial applications, besides the already expected impacts of hardware and connectivity failures. This article proposes a comprehensive mathematical model for dependability evaluation centered on the concept of Quality of Monitoring (QoM), processing availability, reliability and effective coverage parameters in a combined way. Practical evaluation issues are discussed and simulation results are presented to demonstrate how the proposed model can be applied in wireless industrial sensor networks when assessing and enhancing their dependability.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.6
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

Article Multidisciplinary Sciences

Symmetry in Scientific Collaboration Networks: A Study Using Temporal Graph Data Science and Scientometrics

Breno Santana Santos, Ivanovitch Silva, Daniel G. Costa

Summary: This article proposes a novel approach that integrates graph theory, machine learning, and graph embedding to comprehensively evaluate research groups. Traditional methods often fail to capture the complex relationships between evaluated elements, but our methodology transforms publication data into graph structures, visualizing and quantifying relationships between researchers, publications, and institutions. By incorporating symmetry properties, we offer a deeper evaluation of research group cohesiveness and structure over time. This temporal evaluation methodology bridges the gap between unstructured scientometric networks and the evaluation process, making it a valuable tool for decision-making procedures. A case study demonstrates the potential of the proposed approach to provide valuable insights into the dynamics and limitations of research groups, reinforcing its feasibility for supporting decision making in funding agencies and research institutions.

SYMMETRY-BASEL (2023)

Article Construction & Building Technology

On the positioning of emergencies detection units based on geospatial data of urban response centres

Joao Paulo Just Peixoto, Daniel G. Costa, Washington de J. S. da Franca Rocha, Paulo Portugal, Francisco Vasques

Summary: This article proposes a method for deploying emergency detection units based on geospatial data, which defines the concept of mitigation zones and uses available urban infrastructure to express the perceived level of urban resilience to emergencies. Four positioning algorithms are proposed to utilize the mitigation zones and available detection units. This approach is applicable to any city with geospatial data and can support various smart city systems, potentially producing significant results in this field.

SUSTAINABLE CITIES AND SOCIETY (2023)

Article Engineering, Chemical

Advancing Fault Prediction: A Comparative Study between LSTM and Spiking Neural Networks

Rute Souza de Abreu, Ivanovitch Silva, Yuri Thomas Nunes, Renan C. Moioli, Luiz Affonso Guedes

Summary: This research introduces a novel approach using spiking neural networks (SNNs) combined with the generalized stochastic Petri net (GSPN) model to predict faults in syntactical time series. Comparative evaluation with long short-term memory (LSTM) networks suggests that SNNs offer comparable robustness and performance.

PROCESSES (2023)

Article Computer Science, Software Engineering

CityZones: A geospatial multi-tier software tool to compute urban risk zones

Joao Paulo Just Peixoto, Daniel G. Costa, Washington de J. S. da Franca Rocha, Paulo Portugal, Francisco Vasques

Summary: CityZones is an online tool that evaluates the emergency response capability of an urban area and computes risk zones based on real data. It allows users to define Areas of Interest (AoI) on a map, which are categorized into low, medium, and high-risk levels. The tool calculates the risk zones within an AoI by considering the distances to hospitals, firefighters, policemen, and metro stations using the OpenStreetMap database. The computed risk zones can be exported and visualized for further analysis, and the tool also suggests ideal positions for emergency detection units within an AoI.

SOFTWAREX (2023)

Article Economics

A composite indicator of liveability based on sociodemographic and Uber quality service dimensions: A data-driven approach

Gisliany L. A. de Oliveira, Ivanovitch Silva, Luciana Lima, Daniel G. Costa

Summary: This study aims to create a liveability index by combining traditional demographic data and non-traditional data sources from Uber services, in order to support the pursuit of new understandings of a city. A comprehensive analysis was conducted in Natal, Brazil, a city known for its socioeconomic and transport service inequalities. Through the use of data-driven methods, over 4 million trips and Estimated Time of Arrival (ETA) data were processed to evaluate the relationship between ETA and sociodemographic features. The results allowed for the creation and validation of a Composite Indicator of Liveability (CIL) that accurately reflected the socioeconomic characteristics of different areas within the city.

TRANSPORT POLICY (2023)

Article Multidisciplinary Sciences

A geospatial dataset of urban infrastructure for emergency response in Portugal

Joao Paulo Just Peixoto, Daniel G. Costa, Paulo Portugal, Francisco Vasques

Summary: Emergency response plays a critical role in mitigating the impact of disasters and ensuring public safety. This study assesses the emergency response capability of cities in Portugal using a comprehensive geospatial dataset, considering various urban infrastructures and the number of metro/railway stations. The dataset has potential applications in urban planning, resource allocation, and disaster response strategy development.

DATA IN BRIEF (2023)

Proceedings Paper Computer Science, Information Systems

Urban emergency detection system using hierarchical, collaborative and configurable wireless sensor networks

Gustavo A. A. Coelho, Thiago C. Jesus, Daniel G. Costa

Summary: The rapid urbanization of cities has brought about numerous challenges in terms of essential services and emergency management. In response to these complexities, smart city solutions have emerged, utilizing advanced technologies to automate and improve service quality. This paper proposes a novel urban multiple emergency detection system based on wireless sensor networks and the Internet of Things, featuring hierarchical and collaborative characteristics to achieve accurate and energy-efficient urban emergency detection.

2023 XIII BRAZILIAN SYMPOSIUM ON COMPUTING SYSTEMS ENGINEERING, SBESC (2023)

Article Computer Science, Interdisciplinary Applications

Exploiting geospatial data of connectivity and urban infrastructure for efficient positioning of emergency detection units in smart cities

Joao Paulo Just Peixoto, Joao Carlos N. Bittencourt, Thiago C. Jesus, Daniel G. Costa, Paulo Portugal, Francisco Vasques

Summary: This article explores the use of multi-sensor Emergency Detection Units (EDUs) to improve urban emergency response. By leveraging data-driven approaches and geospatial data, the positioning of these units can be optimized. Additionally, the coverage area of existing networks is modeled, and the EDUs are fine-tuned based on connectivity requirements to enhance the effectiveness of emergency management systems.

COMPUTERS ENVIRONMENT AND URBAN SYSTEMS (2024)

Proceedings Paper Transportation Science & Technology

An Adaptive TinyML Unsupervised Online Learning Algorithm for Driver Behavior Analysis

Marianne Silva, Thais Medeiros, Mariana Azevedo, Morsinaldo Medeiros, Mikael Themoteo, Tatiane Gois, Ivanovitch Silva, Daniel G. Costa

Summary: The integration of IoT technologies in the automotive sector has impacted driver behavior research, and a new unsupervised online algorithm is proposed for detecting driver behavior patterns, suitable for low-power IoT devices.

2023 IEEE INTERNATIONAL WORKSHOP ON METROLOGY FOR AUTOMOTIVE, METROAUTOMOTIVE (2023)

Proceedings Paper Transportation Science & Technology

AUTOSAR in the Smart Cities Era: Current Developments and Research Trends

Goncalo M. d. Santos, Daniel G. Costa

Summary: As technology advances and complex systems are developed, the demand for systems to adhere to multiple requirements is increasing. This is particularly significant in safety-critical automotive systems, especially in highly interconnected smart cities. This paper surveys the state-of-the-art in the field of AUTOSAR, focusing on key concepts and their relevance to the most critical challenges of today. The key issues of smart mobility, including common implementation problems and security concerns in interconnected urban scenarios, are addressed.

2023 IEEE INTERNATIONAL WORKSHOP ON METROLOGY FOR AUTOMOTIVE, METROAUTOMOTIVE (2023)

Proceedings Paper Transportation Science & Technology

TinyML for Safe Driving: The Use of Embedded Machine Learning for Detecting Driver Distraction

Thommas Flores, Marianne Silva, Mariana Azevedo, Thais Medeiros, Morsinaldo Medeiros, Ivanovitch Silva, Max Mauro Dias Santos, Daniel G. Costa

Summary: This paper proposes a developed driver distraction detection system that achieves high accuracy and low latency, while requiring minimal computational resources. The system utilizes TinyML algorithms and is developed with the support of the Edge Impulse platform, deployed on an Arduino Portenta H7 board.

2023 IEEE INTERNATIONAL WORKSHOP ON METROLOGY FOR AUTOMOTIVE, METROAUTOMOTIVE (2023)

No Data Available