XAI-Supported Electronic Tongue for Estimating Milk Composition and Adulteration Indicators

2026-07-06T12:03:41+00:00

In this study, a low-cost AS7265x-based multispectral electronic tongue system was developed for estimating milk composition and adulteration indicators and supported with an explainable artificial intelligence (XAI) framework. Experimental analyses were conducted on 190 augmented commercial milk samples, where fat, protein, solids-not-fat (SNF), density, freezing point, and added water ratio were treated as target variables. Sensor data were modeled as RAW, DERIVED, and FUSION feature sets, and regression performance was compared using Random Forest, Gradient Boosting, AdaBoost, KNN, and XGBoost. Model validation was carried out with both five-fold cross-validation and Leave-One-Out (LOO) strategies to assess field-level generalizability. Results showed that a narrow-band, low-cost optical sensor platform can estimate not only fat and protein but also SNF, density, and freezing point with high accuracy. Within the XAI framework, permutation-based importance analysis and SHAP were used to identify critical spectral bands for each target parameter, enabling data-driven recommendations for band-oriented sensor design optimization. The study presents a scalable methodology that integrates low-cost sensor design, multi-parameter quality estimation, and explainable modeling beyond traditional fat–protein-focused approaches. Across all six targets, the XAI analysis consistently identified the near-infrared channel at 860 nm (asIR_3) as the most informative band, reflecting the combined effect of water absorption and Mie scattering by fat globules; the visible channel at 680 nm (asVIS_4) emerged as a secondary band, reflecting dissolved-matter scattering. These bands are therefore the natural starting point for cost-reduced versions of the sensor. Among the compared feature sets (RAW, DERIVED, FUSION), the 18-band RAW configuration provided the most balanced performance across all six targets.

Biosensor-Integrated Microneedle Devices for Diagnosis and Treatment of Chronic and Infectious Diseases: Current Status, Trends and Challenges

2026-05-21T11:08:49+00:00

Despite advancements in clinical diagnostics, traditional biomarker detection methods (e.g., ELISA) remain limited due to their invasive nature, slow results, and inadequate use for continuous monitoring in low-resource settings. With the rise in chronic, infectious, and metabolic diseases, there is a pressing demand for real-time, minimally invasive diagnostic tools. Nanoengineered microneedle (MN) biosensors offer a promising solution. These painless devices can access interstitial fluid (ISF), a rich source of biomarkers, while utilizing advanced nanomaterials for high sensitivity and multiplexed detection. When combined with AI, IoT connectivity, and cloud-based analytics, MN biosensors enable personalized health data and continuous disease management. This review outlines recent advances in MN technology, including innovations in design and nanomaterial integration, as well as translational challenges like manufacturing scalability and regulatory approval. We explore how MN designs incorporating various sensing modalities can facilitate real-time monitoring of biomarkers such as glucose, lactate, and inflammatory proteins. Importantly, we discuss how these devices can improve healthcare access, reduce costs, and empower patients through everyday monitoring. This review integrates developments in MN engineering with biosensing and therapeutics, positioning biosensor-integrated MNs as pivotal in enabling continuous, minimally invasive disease monitoring and personalized therapy beyond traditional hospital environments.

Research Spectrum: Advances in Biosensors

XAI-Supported Electronic Tongue for Estimating Milk Composition and Adulteration Indicators

Biosensor-Integrated Microneedle Devices for Diagnosis and Treatment of Chronic and Infectious Diseases: Current Status, Trends and Challenges