The high installation and operational costs of reference-grade air quality monitoring systems have accelerated the widespread adoption of low-cost sensors (LCS). However, their susceptibility to environmental influences, temporal drift, and measurement uncertainty necessitates robust calibration approaches to ensure reliable measurements. Although machine learning (ML)-based calibration methods have been widely investigated, most existing implementations rely on static analytical workflows and require programming expertise, which limits their accessibility for many domain specialists. To simplify and standardize the calibration process for low-cost air quality sensors, this study presents Air Quality Multi-Model Calibration (AQ-MultiCal), an interactive, no-code platform. The platform provides a unified environment for evaluating 14 regression models, performing automated hyperparameter optimization, and conducting comparative performance analysis through an intuitive graphical interface supported by interactive visualization tools. The platform is validated using CO₂ measurements collected from January and February 2025. Experimental results indicate that the optimized k-nearest neighbors (kNN) model achieved the best performance, with a coefficient of determination of R² = 0.990 with low prediction error. These results demonstrate that AQ-MultiCal enables accurate sensor calibration and systematic comparison of ML models while improving the accessibility of ML-based calibration through an open-source platform designed for domain experts without programming expertise.

Low-cost sensors (LCSs) are increasingly used in air quality monitoring because of their affordability and scalability; however, their limited accuracy necessitates reliable calibration approaches. Although machine learning (ML)-based calibration methods have shown promising results, direct comparisons of hyperparameter optimization (HPO) strategies remain challenging due to differences in datasets, search spaces, and optimization budgets. In this study, ML models and HPO methods were evaluated within a standardized experimental framework developed on the AQ-MultiCal platform. Grid Search (GS), Random Search (RS), and Bayesian Optimization (BO) were implemented using identical hyperparameter search spaces and equal iteration budgets across both short-term and long-term real-world CO₂ datasets obtained from five low-cost NDIR-based sensors. The results showed that tree-based models achieved strong baseline performance, whereas the k-nearest neighbors (kNN) model demonstrated the greatest improvement after optimization. The optimized kNN model reduced the average RMSE from 77.4 ppm to 54.4 ppm for the short-term dataset and from 37.3 ppm to 26.2 ppm for the long-term dataset. Although the HPO methods achieved comparable predictive accuracy, substantial differences were observed in computational cost. The proposed framework enables fair and reproducible comparison of HPO strategies while balancing predictive performance and computational efficiency in real-world sensor calibration applications.

Optically stimulated luminescence (OSL) is widely used in radiation dosimetry and luminescence research, creating a continuing need for flexible measurement systems capable of supporting diverse experimental protocols. In this study, LuminaOSL was designed and developed as a modular, automated, computer-controlled research platform for implementing different OSL measurement protocols. The platform integrates programmable LED-based optical stimulation, photomultiplier tube (PMT)-based photon counting, an automated eight-position sample mechanism, microcontroller-based control, and a Python-based user interface within a unified architecture. System performance was evaluated through repeated measurements using beryllium oxide (BeO), low-signal control tests, and CW-OSL and LM-OSL experiments. A cycle-to-cycle coefficient of variation of 0.41% was obtained over successive measurement cycles, with no missing data observed during data acquisition and transfer. BeO measurements yielded monotonically decreasing CW-OSL responses under constant optical stimulation and peak-shaped LM-OSL responses under linearly increasing optical stimulation. These findings indicate that LuminaOSL can support stable and reproducible measurements through the integration of programmable optical stimulation, automated sample handling, and time-controlled photon counting, with potential applicability to radiation dosimetry and smart healthcare engineering research.