A two-step machine learning approach for predictive maintenance and anomaly detection in environmental sensor systems

Environmental sensor systems are essential for monitoring infrastructure and environmental quality but are prone to unreliability caused by sensor faults and environmental anomalies. Using Environmental Sensor Telemetry Data, this study introduces a novel methodology that combines unsupervised and s...

Full description

Saved in:
Bibliographic Details
Main Authors: Saiprasad Potharaju, Ravi Kumar Tirandasu, Swapnali N. Tambe, Devyani Bhamare Jadhav, Dudla Anil Kumar, Shanmuk Srinivas Amiripalli
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:MethodsX
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2215016125000299
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832557501296410624
author Saiprasad Potharaju
Ravi Kumar Tirandasu
Swapnali N. Tambe
Devyani Bhamare Jadhav
Dudla Anil Kumar
Shanmuk Srinivas Amiripalli
author_facet Saiprasad Potharaju
Ravi Kumar Tirandasu
Swapnali N. Tambe
Devyani Bhamare Jadhav
Dudla Anil Kumar
Shanmuk Srinivas Amiripalli
author_sort Saiprasad Potharaju
collection DOAJ
description Environmental sensor systems are essential for monitoring infrastructure and environmental quality but are prone to unreliability caused by sensor faults and environmental anomalies. Using Environmental Sensor Telemetry Data, this study introduces a novel methodology that combines unsupervised and supervised machine learning approaches to detect anomalies and predict sensor failures. The dataset consisted of sensor readings such as temperature, humidity, CO, LPG, and smoke, with no class labels available. This research is novel in seamlessly blending unsupervised anomaly detection using Isolation Forest to create labels for data points that were previously unlabeled. Finally, these generated labels were used to train the supervised learning models such as Random Forest, Neural Network (MLP Classifier), and AdaBoost to predict anomalies in new sensor data as soon as it gets recorded. The models confirmed the proposed framework's accuracy, whereas Random Forest 99.93 %, Neural Network 99.05 %, and AdaBoost 98.04 % validated the effectiveness of the suggested framework. Such an approach addresses a critical gap, transforming raw, unlabeled IoT sensor data into actionable insights for predictive maintenance. This methodology provides a scalable and robust real-time anomaly detection and sensor fault prediction methodology that greatly enhances the reliability of the environmental monitoring systems and advances the intelligent infrastructure management. • Combines Isolation Forest for anomaly labeling and supervised models for anomaly prediction. • Scalable and adaptable for diverse IoT applications for environmental monitoring. • Provides actionable insights through anomaly visualization, revealing patterns in sensor performance.
format Article
id doaj-art-34bd57d9f1f14249ab985af5433be8fd
institution Kabale University
issn 2215-0161
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series MethodsX
spelling doaj-art-34bd57d9f1f14249ab985af5433be8fd2025-02-03T04:16:44ZengElsevierMethodsX2215-01612025-06-0114103181A two-step machine learning approach for predictive maintenance and anomaly detection in environmental sensor systemsSaiprasad Potharaju0Ravi Kumar Tirandasu1Swapnali N. Tambe2Devyani Bhamare Jadhav3Dudla Anil Kumar4Shanmuk Srinivas Amiripalli5Department of CSE, Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune, India; Corresponding author.Department of CSE, Koneru Lakshmaiah Education Foundation, Vaddeswaram, Andhra Pradesh, IndiaDepartment of Information Technology, K. K.Wagh Institute of Engineering Education & Research, Nashik, Maharashtra, IndiaAIML Department, Sanjivani University, Kopargaon, Maharashtra, IndiaDepartment of CSE, Lakireddy Bali Reddy College of Engineering, NTR District, Andhra Pradesh, IndiaDepartment of CSE, GST, GITAM University, Visakhapatnam, Andhra Pradesh, IndiaEnvironmental sensor systems are essential for monitoring infrastructure and environmental quality but are prone to unreliability caused by sensor faults and environmental anomalies. Using Environmental Sensor Telemetry Data, this study introduces a novel methodology that combines unsupervised and supervised machine learning approaches to detect anomalies and predict sensor failures. The dataset consisted of sensor readings such as temperature, humidity, CO, LPG, and smoke, with no class labels available. This research is novel in seamlessly blending unsupervised anomaly detection using Isolation Forest to create labels for data points that were previously unlabeled. Finally, these generated labels were used to train the supervised learning models such as Random Forest, Neural Network (MLP Classifier), and AdaBoost to predict anomalies in new sensor data as soon as it gets recorded. The models confirmed the proposed framework's accuracy, whereas Random Forest 99.93 %, Neural Network 99.05 %, and AdaBoost 98.04 % validated the effectiveness of the suggested framework. Such an approach addresses a critical gap, transforming raw, unlabeled IoT sensor data into actionable insights for predictive maintenance. This methodology provides a scalable and robust real-time anomaly detection and sensor fault prediction methodology that greatly enhances the reliability of the environmental monitoring systems and advances the intelligent infrastructure management. • Combines Isolation Forest for anomaly labeling and supervised models for anomaly prediction. • Scalable and adaptable for diverse IoT applications for environmental monitoring. • Provides actionable insights through anomaly visualization, revealing patterns in sensor performance.http://www.sciencedirect.com/science/article/pii/S2215016125000299Integration of Unsupervised and Supervised learning
spellingShingle Saiprasad Potharaju
Ravi Kumar Tirandasu
Swapnali N. Tambe
Devyani Bhamare Jadhav
Dudla Anil Kumar
Shanmuk Srinivas Amiripalli
A two-step machine learning approach for predictive maintenance and anomaly detection in environmental sensor systems
MethodsX
Integration of Unsupervised and Supervised learning
title A two-step machine learning approach for predictive maintenance and anomaly detection in environmental sensor systems
title_full A two-step machine learning approach for predictive maintenance and anomaly detection in environmental sensor systems
title_fullStr A two-step machine learning approach for predictive maintenance and anomaly detection in environmental sensor systems
title_full_unstemmed A two-step machine learning approach for predictive maintenance and anomaly detection in environmental sensor systems
title_short A two-step machine learning approach for predictive maintenance and anomaly detection in environmental sensor systems
title_sort two step machine learning approach for predictive maintenance and anomaly detection in environmental sensor systems
topic Integration of Unsupervised and Supervised learning
url http://www.sciencedirect.com/science/article/pii/S2215016125000299
work_keys_str_mv AT saiprasadpotharaju atwostepmachinelearningapproachforpredictivemaintenanceandanomalydetectioninenvironmentalsensorsystems
AT ravikumartirandasu atwostepmachinelearningapproachforpredictivemaintenanceandanomalydetectioninenvironmentalsensorsystems
AT swapnalintambe atwostepmachinelearningapproachforpredictivemaintenanceandanomalydetectioninenvironmentalsensorsystems
AT devyanibhamarejadhav atwostepmachinelearningapproachforpredictivemaintenanceandanomalydetectioninenvironmentalsensorsystems
AT dudlaanilkumar atwostepmachinelearningapproachforpredictivemaintenanceandanomalydetectioninenvironmentalsensorsystems
AT shanmuksrinivasamiripalli atwostepmachinelearningapproachforpredictivemaintenanceandanomalydetectioninenvironmentalsensorsystems
AT saiprasadpotharaju twostepmachinelearningapproachforpredictivemaintenanceandanomalydetectioninenvironmentalsensorsystems
AT ravikumartirandasu twostepmachinelearningapproachforpredictivemaintenanceandanomalydetectioninenvironmentalsensorsystems
AT swapnalintambe twostepmachinelearningapproachforpredictivemaintenanceandanomalydetectioninenvironmentalsensorsystems
AT devyanibhamarejadhav twostepmachinelearningapproachforpredictivemaintenanceandanomalydetectioninenvironmentalsensorsystems
AT dudlaanilkumar twostepmachinelearningapproachforpredictivemaintenanceandanomalydetectioninenvironmentalsensorsystems
AT shanmuksrinivasamiripalli twostepmachinelearningapproachforpredictivemaintenanceandanomalydetectioninenvironmentalsensorsystems