Aerosol Science Research Project Register

Most Popular

Research organisation	Project name	Project scope	More information
University of California, Davis	Toxic-metal Aerosol Real Time Analyzer	We have developed an instrument which is low-power, low-cost, portable, and battery powered that measures the concentration of metals in air. With a 1-hour sampling time, the limit of detection is 1-20 ng/m3, depending on the element.	Date submitted: November 2025
National Poison Centre, Universiti Sains Malaysia (USM)	TinyML-Enhanced Validation and Calibration of Low-Cost Real-time Aerosol Samplers for Occupational Settings: A Collaborative ISCG-USM Initiative to Revolutionize Exposure Measurement Accuracy.	The scope of this project is to significantly advance the accuracy and reliability of affordable, real-time aerosol monitoring devices for occupational hygiene. We will focus on integrating Tiny Machine Learning (TinyML)	https://iot.usmtech.my/iscg1/ Date submitted: November 2025
National Poison Centre, Universiti Sains Malaysia (USM)	Real-time Predictive Worker Exposure Risk and Intelligent Intervention Guidance System: A Collaborative ISCG-USM Initiative for Proactive Occupational Health Management.	The scope of this project is to transform reactive occupational exposure management into a proactive, predictive system. We will develop and validate an integrated framework that utilizes real-time data from affordable IoT sensors (e.g., for particulates, VOCs, temperature, humidity) to predict worker exposure risk to aerosols. Our core focus is on building advanced machine learning (ML) models that can analyze continuous sensor data in conjunction with contextual information (e.g., work schedules, process parameters) to forecast potential Occupational Exposure Limit (OEL) exceedances before they occur. The project will also develop an intelligent alerting system that provides context-specific, actionable recommendations for immediate intervention (e.g., "Increase ventilation in Zone A," "Workers in Area B don respirators"). This will be rigorously validated through pilot deployments in diverse workplace settings, assessing both the predictive accuracy of the system and the effectiveness of the intervention guidance. The ultimate aim is to create a robust, scalable solution that enhances worker protection by enabling timely, data-driven preventive measures.	https://iot.usmtech.my/iscg2/ Date submitted: November 2025

Research organisation

Project name

Project scope

More information

University of California, Davis

Toxic-metal Aerosol Real Time Analyzer

We have developed an instrument which is low-power, low-cost, portable, and battery powered that measures the concentration of metals in air. With a 1-hour sampling time, the limit of detection is 1-20 ng/m3, depending on the element.

Date submitted: November 2025

National Poison Centre, Universiti Sains Malaysia (USM)

TinyML-Enhanced Validation and Calibration of Low-Cost Real-time Aerosol Samplers for Occupational Settings: A Collaborative ISCG-USM Initiative to Revolutionize Exposure Measurement Accuracy.

The scope of this project is to significantly advance the accuracy and reliability of affordable, real-time aerosol monitoring devices for occupational hygiene. We will focus on integrating Tiny Machine Learning (TinyML)

https://iot.usmtech.my/iscg1/

Date submitted: November 2025

National Poison Centre, Universiti Sains Malaysia (USM)

Real-time Predictive Worker Exposure Risk and Intelligent Intervention Guidance System: A Collaborative ISCG-USM Initiative for Proactive Occupational Health Management.

The scope of this project is to transform reactive occupational exposure management into a proactive, predictive system. We will develop and validate an integrated framework that utilizes real-time data from affordable IoT sensors (e.g., for particulates, VOCs, temperature, humidity) to predict worker exposure risk to aerosols. Our core focus is on building advanced machine learning (ML) models that can analyze continuous sensor data in conjunction with contextual information (e.g., work schedules, process parameters) to forecast potential Occupational Exposure Limit (OEL) exceedances before they occur. The project will also develop an intelligent alerting system that provides context-specific, actionable recommendations for immediate intervention (e.g., "Increase ventilation in Zone A," "Workers in Area B don respirators"). This will be rigorously validated through pilot deployments in diverse workplace settings, assessing both the predictive accuracy of the system and the effectiveness of the intervention guidance. The ultimate aim is to create a robust, scalable solution that enhances worker protection by enabling timely, data-driven preventive measures.

https://iot.usmtech.my/iscg2/

Date submitted: November 2025

International Sampler Comparison Group