DEVELOPMENT OF AN INTERNET OF THINGS BASED AIR QUALITY MONITORING SYSTEM USING MACHINE LEARNING DOI Open Access

Abdulrasheed O. Abdulganiyu,

Jonathan Gana Kolo,

Abraham U. Usman

et al.

International Journal of Advanced Natural Sciences and Engineering Researches, Journal Year: 2023, Volume and Issue: 7(6), P. 276 - 282

Published: July 25, 2023

Air pollution and its negative impacts on human health have become serious concerns in many places throughout the world. The traditional methods of monitoring air quality, such as manual sampling laboratory analysis, are time-consuming, expensive, may not provide real-time information. In this study, an IoT-based Quality Monitoring System that uses Machine Learning to accurate timely analysis quality data is presented. system collects from a network sensors measuring various parameters, processes using ML algorithms identify patterns predict future conditions, provides insights into current state environment. findings showed emissions had inversely proportional impact study region achieved accuracy 0.978. This has potential regulate real-time.

Language: Английский

AI-Assisted Detection of Biomarkers by Sensors and Biosensors for Early Diagnosis and Monitoring DOI Creative Commons
Tomasz Wasilewski, Wojciech Kamysz, Jacek Gębicki

et al.

Biosensors, Journal Year: 2024, Volume and Issue: 14(7), P. 356 - 356

Published: July 22, 2024

The steady progress in consumer electronics, together with improvement microflow techniques, nanotechnology, and data processing, has led to implementation of cost-effective, user-friendly portable devices, which play the role not only gadgets but also diagnostic tools. Moreover, numerous smart devices monitor patients' health, some them are applied point-of-care (PoC) tests as a reliable source evaluation patient's condition. Current practices still based on laboratory tests, preceded by collection biological samples, then tested clinical conditions trained personnel specialistic equipment. In practice, collecting passive/active physiological behavioral from patients real time feeding artificial intelligence (AI) models can significantly improve decision process regarding diagnosis treatment procedures via omission conventional sampling while excluding pathologists. A combination novel methods digital traditional biomarker detection portable, autonomous, miniaturized revolutionize medical diagnostics coming years. This article focuses comparison modern techniques AI machine learning (ML). presented technologies will bypass laboratories start being commercialized, should lead or substitution current Their application PoC settings technology accessible every patient appears be possibility. Research this field is expected intensify Technological advancements sensors biosensors anticipated enable continuous real-time analysis various omics fields, fostering early disease intervention strategies. integration health platforms would predictive personalized healthcare, emphasizing importance interdisciplinary collaboration related scientific fields.

Language: Английский

Citations

31
A comprehensive review on advancements in sensors for air pollution applications DOI

Thara Seesaard,

Kamonrat Kamjornkittikoon,

Chatchawal Wongchoosuk

et al.

The Science of The Total Environment, Journal Year: 2024, Volume and Issue: 951, P. 175696 - 175696

Published: Aug. 26, 2024

Language: Английский

Citations

23
Real-time IoT-powered AI system for monitoring and forecasting of air pollution in industrial environment DOI Creative Commons
Montaser N.A. Ramadan, Mohammed A. H. Ali,

Shin Yee Khoo

et al.

Ecotoxicology and Environmental Safety, Journal Year: 2024, Volume and Issue: 283, P. 116856 - 116856

Published: Aug. 15, 2024

Air pollution in industrial environments, particularly the chrome plating process, poses significant health risks to workers due high concentrations of hazardous pollutants. Exposure substances like hexavalent chromium, volatile organic compounds (VOCs), and particulate matter can lead severe issues, including respiratory problems lung cancer. Continuous monitoring timely intervention are crucial mitigate these risks. Traditional air quality methods often lack real-time data analysis predictive capabilities, limiting their effectiveness addressing hazards proactively. This paper introduces a forecasting system specifically designed for industry. The system, supported by Internet Things (IoT) sensors AI approaches, detects wide range pollutants, NH

Language: Английский

Citations

22
A Survey of Deep Anomaly Detection in Multivariate Time Series: Taxonomy, Applications, and Directions DOI Creative Commons
Fengling Wang, Yiyue Jiang, Rongjie Zhang

et al.

Sensors, Journal Year: 2025, Volume and Issue: 25(1), P. 190 - 190

Published: Jan. 1, 2025

Multivariate time series anomaly detection (MTSAD) can effectively identify and analyze anomalous behavior in complex systems, which is particularly important fields such as financial monitoring, industrial equipment fault detection, cybersecurity. MTSAD requires simultaneously temporal dependencies inter-variable relationships have prompted researchers to develop specialized deep learning models detect patterns. In this paper, we conducted a structured comprehensive overview of the latest techniques for multivariate methods. Firstly, proposed taxonomy strategies from perspectives paradigms models, then provide systematic review that emphasizes their advantages drawbacks. We also organized public datasets along with respective application domains. Finally, open issues future research on were identified.

Language: Английский

Citations

1
Towards Federated Learning and Multi-Access Edge Computing for Air Quality Monitoring: Literature Review and Assessment DOI Open Access

Satheesh Abimannan,

El-Sayed M. El-Alfy, Shahid Hussain

et al.

Sustainability, Journal Year: 2023, Volume and Issue: 15(18), P. 13951 - 13951

Published: Sept. 20, 2023

Systems for monitoring air quality are essential reducing the negative consequences of pollution, but creating real-time systems encounters several challenges. The accuracy and effectiveness these can be greatly improved by integrating federated learning multi-access edge computing (MEC) technology. This paper critically reviews state-of-the-art methodologies MEC-enabled systems. It discusses immense benefits learning, including privacy-preserving model training, MEC, such as reduced latency response times, applications. Additionally, it highlights challenges requirements developing implementing systems, data quality, security, privacy, well need interpretable explainable AI-powered models. By leveraging advanced techniques technologies, overcome various deliver accurate, reliable, timely predictions. Moreover, this article provides an in-depth analysis assessment emphasizes further research to develop more practical affordable decentralized with performance security while ensuring ethical responsible use support informed decision making promote sustainability.

Language: Английский

Citations

21
A Brief Review on Flexible Electronics for IoT: Solutions for Sustainability and New Perspectives for Designers DOI Creative Commons
Graziella Scandurra,

Antonella Arena,

C. Ciofi

et al.

Sensors, Journal Year: 2023, Volume and Issue: 23(11), P. 5264 - 5264

Published: June 1, 2023

The Internet of Things (IoT) is gaining more and popularity it establishing itself in all areas, from industry to everyday life. Given its pervasiveness considering the problems that afflict today's world, must be carefully monitored addressed guarantee a future for new generations, sustainability technological solutions focal point activities researchers field. Many these are based on flexible, printed or wearable electronics. choice materials therefore becomes fundamental, just as crucial provide necessary power supply green way. In this paper we want analyze state art flexible electronics IoT, paying particular attention issue sustainability. Furthermore, considerations will made how skills required designers such circuits, features design tools characterization electronic circuits changing.

Language: Английский

Citations

15
Prediction of the Posture of High-Rise Building Machine Based on Multivariate Time Series Neural Network Models DOI Open Access
Pan Xi, Junguang Huang, Yiming Zhang

et al.

Published: Jan. 22, 2024

High-rise building machines (HBMs) play a critical role in the successful construction of super-high skyscrapers, providing essential support and ensuring safety. The HBM’s climbing system relies on jacking mechanism consisting several independent cylinders. A reliable control is imperative to maintain smooth posture steel platform (SP) under action mechanism. This research introduces three multivariate time series neural network models—namely, Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Temporal Convolutional Network (TCN)—to predict HBM. models take pressure stroke measurements from cylinders as inputs, their outputs determine levelness SP HBM at various stages. development training these networks are based historical on-site data, with predictions subjected thorough comparative analysis. All proposed exhibit capability dynamically during process, using data sensors. Notably, GRU model shows better predictive performance.

Language: Английский

Citations

5
Prisma-Based Review Of Mis Solutions For Enhanced Disaster Response And Resource Allocation DOI

Emdadul Haque,

Zayadul Hasan

SSRN Electronic Journal, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

Language: Английский

Citations

0
Machine Learning–Based Calibration and Performance Evaluation of Low-Cost Internet of Things Air Quality Sensors DOI Creative Commons
Mehmet Taştan

Sensors, Journal Year: 2025, Volume and Issue: 25(10), P. 3183 - 3183

Published: May 19, 2025

Low-cost air quality sensors (LCSs) are increasingly being used in environmental monitoring due to their affordability and portability. However, sensitivity factors can lead measurement inaccuracies, necessitating effective calibration methods enhance reliability. In this study, an Internet of Things (IoT)-based system was developed tested using the most commonly preferred sensor types for measurement: fine particulate matter (PM2.5), carbon dioxide (CO2), temperature, humidity sensors. To improve accuracy, eight different machine learning (ML) algorithms were applied: Decision Tree (DT), Linear Regression (LR), Random Forest (RF), k-Nearest Neighbors (kNN), AdaBoost (AB), Gradient Boosting (GB), Support Vector Machines (SVM), Stochastic Descent (SGD). Sensor performance evaluated by comparing measurements with a reference device, best-performing ML model determined each sensor. The results indicate that GB kNN achieved highest accuracy. For CO2 calibration, R2 = 0.970, RMSE 0.442, MAE 0.282, providing lowest error rates. PM2.5 sensor, delivered successful results, 2.123, 0.842. Additionally, temperature sensors, demonstrated accuracy values (R2 0.976, 2.284). These findings demonstrate that, identifying suitable methods, ML-based techniques significantly LCSs. Consequently, they offer viable cost-effective alternative traditional high-cost systems. Future studies should focus on long-term data collection, testing under diverse conditions, integrating additional further advance field.

Language: Английский

Citations

0
Data reliability and fault diagnostic for air quality monitoring station based on low cost sensors and active redundancy DOI Creative Commons
Sylvain Poupry, Kamal Medjaher,

Cédrick Béler

et al.

Measurement, Journal Year: 2023, Volume and Issue: 223, P. 113800 - 113800

Published: Nov. 3, 2023

Language: Английский

Citations

9