ML-Based Aging Monitoring and Lifetime Prediction of IoT Devices With Cost-Effective Embedded Tags for Edge and Cloud Operability

Shamshiri, Ahmad Reza; Ghaznavi‐Ghoushchi, M. B.; Kariman, A. R.

doi:10.1109/jiot.2021.3116065

Cited by 6 publications

(2 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It also eases the mitigation of unwanted effects such as drifting over time, if proper periodic recalibration policies are adopted. ML-based calibrations can be operated directly on the deployed sensors (edge scenario) [32], [33] or on the time series stored in a database (cloud scenario) [34][35][36].…”

Section: Introductionmentioning

confidence: 99%

Minimized Training of Machine Learning-Based Calibration Methods for Low-Cost O₃ Sensors

Tondini,

Scilla,

Casari

2024

IEEE Sensors J.

View full text Add to dashboard Cite

Low-cost sensors (LCSs) show a huge potential towards enabling the pervasive and continuous monitoring of crucial environmental parameters, supporting environment preservation and informing citizens' well-being through ubiquitous air quality data. The main drawback of LCSs is that their data is usually biased, even if LCSs are calibrated by their manufacturer at production time. More accurate in-field calibration methods based on machine learning (ML) and neural networks (NNs) are being considered in some recent studies. They typically imply LCSs co-location with reference measurement stations certified by environmental agencies. Due to seasonality effects, however, the correlation between LCSs and their reference may rapidly degrade once the LCSs are moved from the calibration site, making even really accurate calibrations useless. In this work, we specifically target this problem by optimizing the training settings of the most popular ML and NN calibration models for LCSs when a sequential split schema is adopted to separate training-and test-set. Then, we assess the degradation of the calibration over time based on the R 2 score, when the splitting of the dataset between training-and test-set is different from the classical 80% -20% ratio. This method is applied to real data gathered from an O3 sensor deployed in co-location with a certified reference station for a period of 6 months. Eventually, we show that, in the case of Long-Short Term Memory NNs, using 20% of the dataset for the training is a trade-off condition that minimizes the calibration effort and still yields a robust and long-lasting calibration.

show abstract

Section: Introductionmentioning

confidence: 99%

Minimized Training of Machine Learning-Based Calibration Methods for Low-Cost O₃ Sensors

Tondini,

Scilla,

Casari

2024

IEEE Sensors J.

View full text Add to dashboard Cite

show abstract

“…Some scholars research and design big data analysis platform based on cloud computing, hoping to provide reference for the construction of big data analysis platform [3][4]. Some scholars believe that machine learning platform can flexibly use existing computing resources to improve data processing efficiency [5][6]. Therefore, it is of great significance to use machine learning to simulate and analyze cloud monitoring data.…”

Section: Introductionmentioning

confidence: 99%

Cloud Monitoring Data Analysis and Simulation Based on Machine Learning

2022

View full text Add to dashboard Cite

With the rapid development of Internet technology, cloud computing has gradually been widely used in people's lives. However, due to the huge and complex data volume, limited storage space and maintenance difficulties, there are still some problems in cloud monitoring data analysis. This paper intends to use the combination of machine learning to study the analysis and experimental simulation of cloud monitoring data, in order to improve the data processing ability of the monitoring system. This paper mainly uses the experimental analysis method and information entropy to study the cloud monitoring system and its data processing and analysis capabilities. The experimental data show that the error of computer tools is less than 6%, which shows that the method is feasible and worthy of application.

show abstract

Design of an improved graph-based model for real-time anomaly detection in healthcare using hybrid CNN-LSTM and federated learning

Nagamani,

Kumar

2024

Heliyon

View full text Add to dashboard Cite

ML-Based Aging Monitoring and Lifetime Prediction of IoT Devices With Cost-Effective Embedded Tags for Edge and Cloud Operability

Cited by 6 publications

References 48 publications

Minimized Training of Machine Learning-Based Calibration Methods for Low-Cost O₃ Sensors

Minimized Training of Machine Learning-Based Calibration Methods for Low-Cost O₃ Sensors

Cloud Monitoring Data Analysis and Simulation Based on Machine Learning

Design of an improved graph-based model for real-time anomaly detection in healthcare using hybrid CNN-LSTM and federated learning

Contact Info

Product

Resources

About

ML-Based Aging Monitoring and Lifetime Prediction of IoT Devices With Cost-Effective Embedded Tags for Edge and Cloud Operability

Cited by 6 publications

References 48 publications

Minimized Training of Machine Learning-Based Calibration Methods for Low-Cost O3 Sensors

Minimized Training of Machine Learning-Based Calibration Methods for Low-Cost O3 Sensors

Cloud Monitoring Data Analysis and Simulation Based on Machine Learning

Design of an improved graph-based model for real-time anomaly detection in healthcare using hybrid CNN-LSTM and federated learning

Contact Info

Product

Resources

About

Minimized Training of Machine Learning-Based Calibration Methods for Low-Cost O₃ Sensors

Minimized Training of Machine Learning-Based Calibration Methods for Low-Cost O₃ Sensors