Volatile organic compounds (VOCs) in exhaled human breath serve as pivotal biomarkers for disease identification and medical diagnostics. In the context of diabetes mellitus, the noninvasive detection of acetone, a primary biomarker using electronic noses (e-noses), has gained significant attention. However, employing e-noses requires pre-trained algorithms for precise diabetes detection, often requiring a computer with a programming environment to classify newly acquired data. This study focuses on the development of an embedded system integrating Tiny Machine Learning (TinyML) and an e-nose equipped with Metal Oxide Semiconductor (MOS) sensors for real-time diabetes detection. The study encompassed 44 individuals, comprising 22 healthy individuals and 22 diagnosed with various types of diabetes mellitus. Test results highlight the XGBoost Machine Learning algorithm’s achievement of 95% detection accuracy. Additionally, the integration of deep learning algorithms, particularly deep neural networks (DNNs) and one-dimensional convolutional neural network (1D-CNN), yielded a detection efficacy of 94.44%. These outcomes underscore the potency of combining e-noses with TinyML in embedded systems, offering a noninvasive approach for diabetes mellitus detection.
Diabetes mellitus, a chronic condition affecting millions worldwide, necessitates continuous monitoring of blood glucose level (BGL). The increasing prevalence of diabetes has driven the development of non-invasive methods, such as electronic noses (e-noses), for analyzing exhaled breath and detecting biomarkers in volatile organic compounds (VOCs). Effective machine learning models require extensive patient data to ensure accurate BGL predictions, but previous studies have been limited by small sample sizes. This study addresses this limitation by employing conditional generative adversarial networks (CTGAN) to generate synthetic data from real-world tests involving 29 healthy and 29 diabetic participants, resulting in over 14,000 new synthetic samples. These data were used to validate machine learning models for diabetes detection and BGL prediction, integrated into a Tiny Machine Learning (TinyML) e-nose system for real-time analysis. The proposed models achieved an 86% accuracy in BGL identification using LightGBM (Light Gradient Boosting Machine) and a 94.14% accuracy in diabetes detection using Random Forest. These results demonstrate the efficacy of enhancing machine learning models with both real and synthetic data, particularly in non-invasive systems integrating e-noses with TinyML. This study signifies a major advancement in non-invasive diabetes monitoring, underscoring the transformative potential of TinyML-powered e-nose systems in healthcare applications.
Background/Objectives: The increasing prevalence of diabetes underscores the urgent need for non-invasive, rapid, and cost-effective diagnostic alternatives. This study presents a breath-based multiclass diabetes classification system leveraging only three gas sensors (CO, alcohol, and acetone) to analyze exhaled breath composition. Methods: Breath samples were collected from 58 participants (22 healthy, 7 prediabetic, and 29 diabetic), with blood glucose levels serving as the reference metric. To enhance classification performance, we introduced a novel biomarker, the alcohol-to-acetone ratio, through a feature engineering approach. Class imbalance was addressed using the Synthetic Minority Over-Sampling Technique (SMOTE), ensuring a balanced dataset for model training. A nested cross-validation framework with 3 outer and 3 inner folds was implemented. Multiple machine learning classifiers were evaluated, with Random Forest and Gradient Boosting emerging as the top-performing models. Results: An ensemble combining both yielded the highest overall performance, achieving an average accuracy of 98.86%, precision of 99.07%, recall of 98.81% and F1 score of 98.87%. These findings highlight the potential of gas sensor-based breath analysis as a highly accurate, scalable, and non-invasive method for diabetes screening. Conclusions: The proposed system offers a promising alternative to blood-based diagnostic approaches, paving the way for real-world applications in point-of-care diagnostics and continuous health monitoring.
In this work, a photodetector fabricated in standard CMOS 0.5 μm technology useful to detect UV radiation in the 250 nm to 296 nm range is presented. The photodetector consists of an NMOS floating-gate transistor (poly1 to poly2) with a 12 μm/0.6 μm aspect ratio and an input capacitor of 186 fF. Such floating-gate is made of n+ polysilicon surrounded by silicon oxide whose interface presents a barrier of 4.19 eV. Therefore, photoelectrons produced by the incidence of UV radiation (λ ≤296 nm) can cross the interface bandgap and be stored at the floating-gate producing a detectable potential change. The characterization of the transistor I-V curves allows the charge quantification at the floating-gate due to UV exposure; such characterization was done using monochromatic and non-monochromatic sources. The developed mathematical models agree with experimental data. An average responsivity of 4.5 μA/W was obtained, which can be easily improved by using extra circuitry as current amplifiers, op-amps or other analog stages also available in standard CMOS technology.
Foundation time-series models have recently shown potential for forecasting complex temporal signals, but their behavior in patient-specific continuous glucose monitoring (CGM) forecasting remains insufficiently understood, particularly when only glucose history is available. This study provides a patient-level benchmark of foundation models for 30 min ahead glucose prediction in adults with type 1 diabetes mellitus (T1DM) under a strictly univariate CGM-only setting. Using the HUPA–UCM dataset from 25 individuals, we evaluated TimeGPT, Chronos, and Sundial against representative statistical, machine learning, and deep learning forecasters, including ARIMA, ETS, gradient-boosting models, recurrent networks, and neural forecasting architectures. Models were assessed using a local walk-forward validation strategy over the final 24 h of CGM data for each patient. Foundation models achieved the strongest global performance, with Sundial obtaining the lowest overall MAE (), while TimeGPT and Chronos remained among the most competitive approaches. However, patient-level analyses showed that this advantage was not uniform: ARIMA remained highly competitive in selected individuals, and no single model consistently dominated across the cohort. These findings suggest that foundation time-series models are promising tools for short-horizon CGM forecasting, but their use should be framed within patient-specific model selection rather than as universal replacements for classical forecasting methods.
Automated medication management devices are mechatronic systems that have attracted interest from the embedded systems and open design communities because they integrate mechanical actuation, electronic control and temporal programming into compact, reproducible platforms. However, many commercial solutions are proprietary and provide limited access to their internal architectures, while several low-cost research prototypes lack comprehensive documentation and systematic technical characterisation. This paper presents the design and development of an automated pill dispenser conceived as a fully documented, reproducible technical platform with publicly available design files. The device implements a simple mechatronic architecture comprising a continuous-rotation servomotor, permanent magnets and reed-type magnetic sensors. This enables repeatable compartment positioning to be achieved without the need for absolute angular sensors or complex control algorithms. The system was evaluated from an engineering perspective through validation and quantitative characterisation, including tests of mechanical repeatability, power consumption, and operational stability. The results demonstrate consistent and reproducible behaviour, supporting the use of the proposed device as a practical platform for education, prototyping and experimental applications in low-cost mechatronics and embedded systems.