Toward a User-Accessible Spectroscopic Sensing Platform for Beverage Recognition Through K-Nearest Neighbors Algorithm

Abstract

Proper nutrition is a fundamental aspect to maintaining overall health and well-being, influencing both physical and social aspects of human life; an unbalanced or inadequate diet can lead to various nutritional deficiencies and chronic health conditions. In today's fast-paced world, monitoring nutritional intake has become increasingly important, particularly for those with specific dietary needs. While smartphone-based applications using image recognition have simplified food tracking, they still rely heavily on user interaction and raise concerns about practicality and privacy. To address these limitations, this paper proposes a novel, compact spectroscopic sensing platform for automatic beverage recognition. The system utilizes the AS7265x commercial sensor to capture the spectral signature of beverages, combined with a K-Nearest Neighbors (KNN) machine learning algorithm for classification. The approach is designed for integration into everyday objects, such as smart glasses or cups, offering a noninvasive and user-friendly alternative to manual tracking. Through optimization of both the sensor configuration and KNN parameters, we identified a reduced set of four wavelengths that achieves over 96% classification accuracy across a diverse range of common beverages. This demonstrates the potential for embedding accurate, low-power, and cost-efficient sensors into Internet of Things (IoT) devices for real-time nutritional monitoring, reducing the need for user input while enhancing accessibility and usability.

Keywords: IoT devices; KNN; beverage recognition; diet monitoring; machine learning; public health; sensing platform; smart cutlery.

Figure 1

(a) Distribution of peak absorption for the AS7265x kit sensor [26] and (b) normalized emission spectra of the LED as measured with Photonic Multi-channel Analyzer PMA-12.

Figure 2

(a) 3D renders and (b) photo of the system setup.

Figure 3

Two-dimensional example of KNN (K = 3) classification algorithm: (a) training dataset with two classes (labeled green and orange dots). (b) A new unclassified data is added to the graph (white dot) and compared with the 3 nearest neighbors. (c) The new data is then assigned to the category whose number of first neighbors is highest (green).

Figure 4

Normalized beverage light absorption as a function of the wavelength.

Figure 5

Accuracy of the KNN model as a function of the K nearest neighbors as average (red dots) respect to the several K-fold tests performed.

Figure 6

Confusion matrix of the KNN model (K = 1), showing the classification performance across the different beverages.

Figure 7

Accuracy of the KNN model as a function of the wavelengths combination.

Figure 8

Confusion matrix of the KNN model (K = 1), illustrating beverage classification performance using the optimized wavelengths (460, 535, 610, and 810 nm).