TinyML-enabled fuzzy logic for enhanced road anomaly detection in remote sensing

Abstract Advanced techniques for detecting and classifying road anomalies are crucial due to road networks’ rapid expansion and increasing complexity. This study introduces a novel integration of Tiny Machine Learning (TinyML), remote sensing, and fuzzy logic through a fully connected U-Net architec...

Full description

Saved in:
Bibliographic Details
Main Authors: Amna Khatoon, Weixing Wang, Mengfei Wang, Limin Li, Asad Ullah
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-01981-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849769336197087232
author Amna Khatoon
Weixing Wang
Mengfei Wang
Limin Li
Asad Ullah
author_facet Amna Khatoon
Weixing Wang
Mengfei Wang
Limin Li
Asad Ullah
author_sort Amna Khatoon
collection DOAJ
description Abstract Advanced techniques for detecting and classifying road anomalies are crucial due to road networks’ rapid expansion and increasing complexity. This study introduces a novel integration of Tiny Machine Learning (TinyML), remote sensing, and fuzzy logic through a fully connected U-Net architecture, TinyML-U-Net-FL, tailored for anomaly detection in resource-constrained environments. Our framework addresses critical gaps in existing methodologies, such as high computational demands and limited real-time processing capabilities, by leveraging model compression, quantization, and pruning techniques. These enhancements facilitate efficient real-time analysis directly on edge devices. In rigorous evaluations using the DeepGlobe and Dubai aerial imagery datasets, our framework achieved a notable recall of 92.4%, precision of 78.2%, and an F1-Score of 84.7%, demonstrating superior performance compared to contemporary methods, including DCS-TransUperNet, GOALF, GCBNet, DiResNet, and ScRoadExtractor. Incorporating fuzzy logic significantly improves the robustness of anomaly detection, enabling more precise and reliable classification. This research contributes substantially to intelligent transportation systems by facilitating precise, energy-efficient, timely detection and classification of road network irregularities, enhancing infrastructure management road safety, and supporting autonomous navigation applications.
format Article
id doaj-art-afb63c6b99724ec387cdc0a5622a3dba
institution DOAJ
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-afb63c6b99724ec387cdc0a5622a3dba2025-08-20T03:03:27ZengNature PortfolioScientific Reports2045-23222025-07-0115112010.1038/s41598-025-01981-5TinyML-enabled fuzzy logic for enhanced road anomaly detection in remote sensingAmna Khatoon0Weixing Wang1Mengfei Wang2Limin Li3Asad Ullah4School of Information Engineering, Chang’an UniversitySchool of Information Engineering, Chang’an UniversityCollege of Electrical and Electronic Engineering, Wenzhou UniversityCollege of Electrical and Electronic Engineering, Wenzhou UniversitySchool of Information Engineering, Eurasia UniversityAbstract Advanced techniques for detecting and classifying road anomalies are crucial due to road networks’ rapid expansion and increasing complexity. This study introduces a novel integration of Tiny Machine Learning (TinyML), remote sensing, and fuzzy logic through a fully connected U-Net architecture, TinyML-U-Net-FL, tailored for anomaly detection in resource-constrained environments. Our framework addresses critical gaps in existing methodologies, such as high computational demands and limited real-time processing capabilities, by leveraging model compression, quantization, and pruning techniques. These enhancements facilitate efficient real-time analysis directly on edge devices. In rigorous evaluations using the DeepGlobe and Dubai aerial imagery datasets, our framework achieved a notable recall of 92.4%, precision of 78.2%, and an F1-Score of 84.7%, demonstrating superior performance compared to contemporary methods, including DCS-TransUperNet, GOALF, GCBNet, DiResNet, and ScRoadExtractor. Incorporating fuzzy logic significantly improves the robustness of anomaly detection, enabling more precise and reliable classification. This research contributes substantially to intelligent transportation systems by facilitating precise, energy-efficient, timely detection and classification of road network irregularities, enhancing infrastructure management road safety, and supporting autonomous navigation applications.https://doi.org/10.1038/s41598-025-01981-5TinyMLRoad anomalyFuzzy inference systemRemotely sensed road imageEdge computingRoad network extraction
spellingShingle Amna Khatoon
Weixing Wang
Mengfei Wang
Limin Li
Asad Ullah
TinyML-enabled fuzzy logic for enhanced road anomaly detection in remote sensing
Scientific Reports
TinyML
Road anomaly
Fuzzy inference system
Remotely sensed road image
Edge computing
Road network extraction
title TinyML-enabled fuzzy logic for enhanced road anomaly detection in remote sensing
title_full TinyML-enabled fuzzy logic for enhanced road anomaly detection in remote sensing
title_fullStr TinyML-enabled fuzzy logic for enhanced road anomaly detection in remote sensing
title_full_unstemmed TinyML-enabled fuzzy logic for enhanced road anomaly detection in remote sensing
title_short TinyML-enabled fuzzy logic for enhanced road anomaly detection in remote sensing
title_sort tinyml enabled fuzzy logic for enhanced road anomaly detection in remote sensing
topic TinyML
Road anomaly
Fuzzy inference system
Remotely sensed road image
Edge computing
Road network extraction
url https://doi.org/10.1038/s41598-025-01981-5
work_keys_str_mv AT amnakhatoon tinymlenabledfuzzylogicforenhancedroadanomalydetectioninremotesensing
AT weixingwang tinymlenabledfuzzylogicforenhancedroadanomalydetectioninremotesensing
AT mengfeiwang tinymlenabledfuzzylogicforenhancedroadanomalydetectioninremotesensing
AT liminli tinymlenabledfuzzylogicforenhancedroadanomalydetectioninremotesensing
AT asadullah tinymlenabledfuzzylogicforenhancedroadanomalydetectioninremotesensing