AutoDetect: A Novel Real-Time Intelligent Sensor Failure Detection for Connected Vehicles

Matthew Robinson; Pedram Asef; Mohammad Shojafar; Zahra Pooranian; Harry Lees; Mark Longden

doi:10.1109/GlobConET56651.2023.10150095

AutoDetect: A Novel Real-Time Intelligent Sensor Failure Detection for Connected Vehicles

Matthew Robinson, Pedram Asef, Mohammad Shojafar, Zahra Pooranian, Harry Lees, Mark Longden

Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding

3 Citations (SciVal)

36 Downloads (Pure)

Abstract

This study addresses the need for developing new frameworks to monitor and detect sensor failures in connected commercial vehicles (CCV)s. The CCV’s sensor health is more important when performance predictions and other communication-related errors (e.g. cyber-physical attacks) can manipulate the sensory network’s resiliency. We developed a novel machine learning (ML)-based framework, AutoDetect, to equip the cloud-tied operators with tools for understanding the abnormal sensor data streaming from the vehicle on the cloud level which explains the sensor data errors due to sensor failures only. We developed an innovative autoencoder (AE) neural network algorithm coupled with K-means clustering to create patterns. To learn the relationship between operating samples and features, when streaming sensor data over high-dimensional datasets is collected in the United Kingdom (UK). Different profiles of sensor data are collected under various driving conditions to monitor the ground truth of the sensor’s confidence levels in CCVs. The new AutoDetect tracked real-time sensor failures with a minimum accuracy of 90%.

Original language	English
Title of host publication	2023 IEEE IAS Global Conference on Emerging Technologies, GlobConET 2023
Publisher	IEEE
Number of pages	6
ISBN (Electronic)	9798350331790
DOIs	https://doi.org/10.1109/GlobConET56651.2023.10150095
Publication status	Published - 16 Jun 2023
Event	2023 IEEE IAS Global Conference on Emerging Technologies: IEEE IAS GLOBCONET 2023 - Loughborough University, London, UK United Kingdom Duration: 19 May 2023 → 23 May 2023 https://www.globconet.org/

Publication series

Name	2023 IEEE IAS Global Conference on Emerging Technologies, GlobConET 2023

Conference

Conference	2023 IEEE IAS Global Conference on Emerging Technologies
Country/Territory	UK United Kingdom
City	London
Period	19/05/23 → 23/05/23
Internet address	https://www.globconet.org/

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

Connected vehicles
failure detection
intelligent transportation
internet of things
machine learning
sensors

ASJC Scopus subject areas

Information Systems and Management
Artificial Intelligence
Control and Optimization
Safety, Risk, Reliability and Quality
Energy Engineering and Power Technology
Electrical and Electronic Engineering
Computer Vision and Pattern Recognition
Renewable Energy, Sustainability and the Environment

Access to Document

10.1109/GlobConET56651.2023.10150095

Novel_Failure_Detection_CameraReady
© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript, 842 KB

Cite this

Robinson, M., Asef, P., Shojafar, M., Pooranian, Z., Lees, H., & Longden, M. (2023). AutoDetect: A Novel Real-Time Intelligent Sensor Failure Detection for Connected Vehicles. In 2023 IEEE IAS Global Conference on Emerging Technologies, GlobConET 2023 (2023 IEEE IAS Global Conference on Emerging Technologies, GlobConET 2023). IEEE. https://doi.org/10.1109/GlobConET56651.2023.10150095

AutoDetect: A Novel Real-Time Intelligent Sensor Failure Detection for Connected Vehicles. / Robinson, Matthew; Asef, Pedram; Shojafar, Mohammad et al.
2023 IEEE IAS Global Conference on Emerging Technologies, GlobConET 2023. IEEE, 2023. (2023 IEEE IAS Global Conference on Emerging Technologies, GlobConET 2023).

Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding

Robinson, M, Asef, P, Shojafar, M, Pooranian, Z, Lees, H & Longden, M 2023, AutoDetect: A Novel Real-Time Intelligent Sensor Failure Detection for Connected Vehicles. in 2023 IEEE IAS Global Conference on Emerging Technologies, GlobConET 2023. 2023 IEEE IAS Global Conference on Emerging Technologies, GlobConET 2023, IEEE, 2023 IEEE IAS Global Conference on Emerging Technologies, London, UK United Kingdom, 19/05/23. https://doi.org/10.1109/GlobConET56651.2023.10150095

@inproceedings{982925a0a2244d758f5d8ab0987f3d66,

title = "AutoDetect: A Novel Real-Time Intelligent Sensor Failure Detection for Connected Vehicles",

abstract = "This study addresses the need for developing new frameworks to monitor and detect sensor failures in connected commercial vehicles (CCV)s. The CCV{\textquoteright}s sensor health is more important when performance predictions and other communication-related errors (e.g. cyber-physical attacks) can manipulate the sensory network{\textquoteright}s resiliency. We developed a novel machine learning (ML)-based framework, AutoDetect, to equip the cloud-tied operators with tools for understanding the abnormal sensor data streaming from the vehicle on the cloud level which explains the sensor data errors due to sensor failures only. We developed an innovative autoencoder (AE) neural network algorithm coupled with K-means clustering to create patterns. To learn the relationship between operating samples and features, when streaming sensor data over high-dimensional datasets is collected in the United Kingdom (UK). Different profiles of sensor data are collected under various driving conditions to monitor the ground truth of the sensor{\textquoteright}s confidence levels in CCVs. The new AutoDetect tracked real-time sensor failures with a minimum accuracy of 90\%.",

keywords = "Connected vehicles, failure detection, intelligent transportation, internet of things, machine learning, sensors",

author = "Matthew Robinson and Pedram Asef and Mohammad Shojafar and Zahra Pooranian and Harry Lees and Mark Longden",

year = "2023",

month = jun,

day = "16",

doi = "10.1109/GlobConET56651.2023.10150095",

language = "English",

series = "2023 IEEE IAS Global Conference on Emerging Technologies, GlobConET 2023",

publisher = "IEEE",

booktitle = "2023 IEEE IAS Global Conference on Emerging Technologies, GlobConET 2023",

address = "USA United States",

note = "2023 IEEE IAS Global Conference on Emerging Technologies : IEEE IAS GLOBCONET 2023 ; Conference date: 19-05-2023 Through 23-05-2023",

url = "https://www.globconet.org/",

}

TY - GEN

T1 - AutoDetect

T2 - 2023 IEEE IAS Global Conference on Emerging Technologies

AU - Robinson, Matthew

AU - Asef, Pedram

AU - Shojafar, Mohammad

AU - Pooranian, Zahra

AU - Lees, Harry

AU - Longden, Mark

PY - 2023/6/16

Y1 - 2023/6/16

N2 - This study addresses the need for developing new frameworks to monitor and detect sensor failures in connected commercial vehicles (CCV)s. The CCV’s sensor health is more important when performance predictions and other communication-related errors (e.g. cyber-physical attacks) can manipulate the sensory network’s resiliency. We developed a novel machine learning (ML)-based framework, AutoDetect, to equip the cloud-tied operators with tools for understanding the abnormal sensor data streaming from the vehicle on the cloud level which explains the sensor data errors due to sensor failures only. We developed an innovative autoencoder (AE) neural network algorithm coupled with K-means clustering to create patterns. To learn the relationship between operating samples and features, when streaming sensor data over high-dimensional datasets is collected in the United Kingdom (UK). Different profiles of sensor data are collected under various driving conditions to monitor the ground truth of the sensor’s confidence levels in CCVs. The new AutoDetect tracked real-time sensor failures with a minimum accuracy of 90%.

AB - This study addresses the need for developing new frameworks to monitor and detect sensor failures in connected commercial vehicles (CCV)s. The CCV’s sensor health is more important when performance predictions and other communication-related errors (e.g. cyber-physical attacks) can manipulate the sensory network’s resiliency. We developed a novel machine learning (ML)-based framework, AutoDetect, to equip the cloud-tied operators with tools for understanding the abnormal sensor data streaming from the vehicle on the cloud level which explains the sensor data errors due to sensor failures only. We developed an innovative autoencoder (AE) neural network algorithm coupled with K-means clustering to create patterns. To learn the relationship between operating samples and features, when streaming sensor data over high-dimensional datasets is collected in the United Kingdom (UK). Different profiles of sensor data are collected under various driving conditions to monitor the ground truth of the sensor’s confidence levels in CCVs. The new AutoDetect tracked real-time sensor failures with a minimum accuracy of 90%.

KW - Connected vehicles

KW - failure detection

KW - intelligent transportation

KW - internet of things

KW - machine learning

KW - sensors

UR - https://www.scopus.com/pages/publications/85164251648

U2 - 10.1109/GlobConET56651.2023.10150095

DO - 10.1109/GlobConET56651.2023.10150095

M3 - Chapter in a published conference proceeding

T3 - 2023 IEEE IAS Global Conference on Emerging Technologies, GlobConET 2023

BT - 2023 IEEE IAS Global Conference on Emerging Technologies, GlobConET 2023

PB - IEEE

Y2 - 19 May 2023 through 23 May 2023

ER -

AutoDetect: A Novel Real-Time Intelligent Sensor Failure Detection for Connected Vehicles

Abstract

Publication series

Conference

UN SDGs

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this