An Integrated Food Freshness Sensor Array System Augmented by a Metal-Organic Framework Mixed-Matrix Membrane and Deep Learning

Fast real-time monitoring of meat freshness based on fluorescent sensing array and deep learning: From development to deployment

A fluorescent sensor array (FSA) combined with deep learning (DL) techniques was developed for meat freshness real-time monitoring from development to deployment. The array was made up of copper metal nanoclusters (CuNCs) and fluorescent dyes, having a good ability in the quantitative and qualitative detection of ammonia, dimethylamine, and trimethylamine gases with a low limit of detection (as low as 131.56 ppb) in range of 5 ∼ 1000 ppm and visually monitoring the freshness of various meats stored at 4 °C. Moreover, SqueezeNet was applied to automatically identify the fresh level of meat based on FSA images with high accuracy (98.17 %) and further deployed in various production environments such as personal computers, mobile devices, and websites by using open neural network exchange (ONNX) technique. The entire meat freshness recognition process only takes 5 ∼ 7 s. Furthermore, gradient-weighted class activation mapping (Grad-CAM) and uniform manifold approximation and projection (UMAP) explanatory algorithms were used to improve the interpretability and transparency of SqueezeNet. Thus, this study shows a new idea for FSA assisted with DL in meat freshness intelligent monitoring from development to deployment.

Deep learning-assisted flavonoid-based fluorescent sensor array for the nondestructive detection of meat freshness

Gas sensors containing indicators have been widely used in meat freshness testing. However, concerns about the toxicity of indicators have prevented their commercialization. Here, we prepared three fluorescent sensors by complexing each flavonoid (fisetin, puerarin, daidzein) with a flexible film, forming a fluorescent sensor array. The fluorescent sensor array was used as a freshness indication label for packaged meat. Then, the images of the indication labels on the packaged meat under different freshness levels were collected by smartphones. A deep convolutional neural network (DCNN) model was built using the collected indicator label images and freshness labels as the dataset. Finally, the model was used to detect the freshness of meat samples, and the overall accuracy of the prediction model was as high as 97.1%. Unlike the TVB-N measurement, this method provides a nondestructive, real-time measurement of meat freshness.

Visible detection of chilled beef freshness using a paper-based colourimetric sensor array combining with deep learning algorithms

This study developed an innovative approach that combines a colourimetric sensor array (CSA) composed of twelve pH-response dyes with advanced algorithms, aiming to detect amine gases and assess the freshness of chilled beef. With the assistance of multivariate statistical analysis, the sensor array can effectively distinguish five amine gases and enable rapid quantification of trimethylamine vapour with a limit of detection (LOD) of 8.02 ppb and visually monitor the fresh levels of chilled beef. Moreover, the utilization of deep learning models (ResNet34, VGG16, and GoogleNet) for chilled beef freshness evaluation achieved an overall accuracy of 98.0 %. Furthermore, t-distributed stochastic neighbour embedding (t-SNE) visualized the feature extraction process and provided explanations to understand the classification process of deep learning. The results demonstrated that applying deep learning techniques in the process of pattern recognition of CSA can help in realizing the rapid, robust, and accurate assessment of chilled beef freshness.

Integration of lanthanide MOFs/methylcellulose-based fluorescent sensor arrays and deep learning for fish freshness monitoring

Preserving fish meat poses a significant challenge due to its high protein and low fat content. This study introduces a novel approach that utilizes a common type of lanthanide metal-organic frameworks (Ln-MOFs), EuMOFs, in combination with 5-fluorescein isothiocyanate (FITC) and methylcellulose (MC) to develop fluorescent sensor arrays for real-time monitoring the freshness of fish meat. The EuMOF-FITC/MC fluorescence films were characterized with excellent fluorescence response, ideal morphology, good mechanical properties, and improved hydrophobicity. The efficacy of the fluorescence sensor array was evaluated by testing various concentrations of spoilage gases (such as ammonia, dimethylamine, and trimethylamine) within a 20-min timeframe using a smartphone-based camera obscura device. This sensor array enables the real-time monitoring of fish freshness, with the ability to preliminarily identify the freshness status of mackerel meat with the naked eye. Furthermore, the study employed four convolutional neural network (CNN) models to enhance the performance of freshness assessment, all of which achieved accuracy levels exceeding 93 %. Notably, the ResNext-101 model demonstrated a particularly high accuracy of 98.97 %. These results highlight the potential of the EuMOF-based fluorescence sensor array, in conjunction with the CNN model, as a reliable and accurate method for real-time monitoring the freshness of fish meat.

Integrated Fruit Ripeness Assessment System Based on an Artificial Olfactory Sensor and Deep Learning

Artificial scent screening systems, inspired by the mammalian olfactory system, hold promise for fruit ripeness detection, but their commercialization is limited by low sensitivity or pattern recognition inaccuracy. This study presents a portable fruit ripeness prediction system based on colorimetric sensing combinatorics and deep convolutional neural networks (DCNN) to accurately identify fruit ripeness. Using the gas chromatography-mass spectrometry (GC-MS) method, the study discerned the distinctive gases emitted by mango, peach, and banana across various ripening stages. The colorimetric sensing combinatorics utilized 25 dyes sensitive to fruit volatile gases, generating a distinct scent fingerprint through cross-reactivity to diverse concentrations and varieties of gases. The unique scent fingerprints can be identified using DCNN. After capturing colorimetric sensor image data, the densely connected convolutional network (DenseNet) was employed, achieving an impressive accuracy rate of 97.39% on the validation set and 82.20% on the test set in assessing fruit ripeness. This fruit ripeness prediction system, coupled with a DCNN, successfully addresses the issues of complex pattern recognition and low identification accuracy. Overall, this innovative tool exhibits high accuracy, non-destructiveness, practical applicability, convenience, and low cost, making it worth considering and developing for fruit ripeness detection.

Machine Learning-Assisted Janus Colorimetric Face Mask for Breath Ammonia Analysis

Artificial olfactory systems have been widely used in medical fields such as in the analysis of volatile organic compounds (VOCs) in human exhaled breath. However, there is still an urgent demand for a portable, accurate breath VOC analysis system for the healthcare industry. In this work, we proposed a Janus colorimetric face mask (JCFM) for the comfortable evaluation of breath ammonia levels by combining the machine learning K-nearest neighbor (K-NN) algorithm. Such a Janus fabric is designed for the unidirectional penetration of exhaled moisture, which can reduce stickiness and ensure facial dryness and comfort. Four different pH indicators on the colorimetric array serve as recognition elements that cross-react with ammonia, capturing the optical fingerprint information on breath ammonia by mimicking the sophisticated olfactory structure of mammals. The Euclidean distance (ED) is used to quantitatively describe the ammonia concentration between 1 ppm and 10 ppm, indicating that there is a linear relationship between the ammonia concentration and the ED response (R2 = 0.988). The K-NN algorithm based on RGB response features aids in the analysis of the target ammonia level and achieves a prediction accuracy of 96%. This study integrates colorimetry, Janus design, and machine learning to present a wearable and portable sensing system for breath ammonia analysis.

Metal-Organic Framework/Polyvinyl Alcohol Composite Films for Multiple Applications Prepared by Different Methods

The incorporation of different functional fillers has been widely used to improve the properties of polymeric materials. The polyhydroxy structure of PVA with excellent film-forming ability can be easily combined with organic/inorganic multifunctional compounds, and such an interesting combining phenomenon can create a variety of functional materials in the field of materials science. The composite membrane material obtained by combining MOF material with high porosity, specific surface area, and adjustable structure with PVA, a non-toxic and low-cost polymer material with good solubility and biodegradability, can combine the processability of PVA with the excellent performance of porous filler MOFs, solving the problem that the poor machinability of MOFs and the difficulty of recycling limit the practical application of powdered MOFs and improving the physicochemical properties of PVA, maximizing the advantages of the material to develop a wider range of applications. Firstly, we systematically summarize the preparation of MOF/PVA composite membrane materials using solution casting, electrostatic spinning, and other different methods for such excellent properties, in addition to discussing in detail the various applications of MOF/PVA composite membranes in water treatment, sensing, air purification, separation, antibacterials, and so on. Finally, we conclude with a discussion of the difficulties that need to be overcome during the film formation process to affect the performance of the composite film and offer encouraging solutions.

Facile Synthesis of Ag NP Films via Evaporation-Induced Self-Assembly and the BA-Sensing Properties

Herein, we design and prepare large-area silver nanoparticle (Ag NP) films based on evaporation-induced self-assembly, which offers the visual and real-time detection of chilled broiler meat freshness. The color change is based on the fact that an increase in the biogenic amine (BA) concentration causes a change in the absorption wavelength of Ag NPs caused by aggregation and etch of the Ag NPs, resulting in a yellow to brown color change, thus enabling a naked-eye readout of the BA exposure. The Ag NP films exhibit a rapid, sensitive, and linear response to BAs in a wide detection range of 2 µM to 100 µM. The Ag NP films are successfully applied as a quick-response, online, high-contrasting colorimetric sensor for visual detection of the freshness of chilled broiler meat.

Metal-organic frameworks for food contaminant adsorption and detection

Metal-organic framework materials (MOFs) have been widely used in food contamination adsorption and detection due to their large specific surface area, specific pore structure and flexible post-modification. MOFs with specific pore size can be targeted for selective adsorption of some contaminants and can be used as pretreatment and pre-concentration steps to purify samples and enrich target analytes for food contamination detection to improve the detection efficiency. In addition, MOFs, as a new functional material, play an important role in developing new rapid detection methods that are simple, portable, inexpensive and with high sensitivity and accuracy. The aim of this paper is to summarize the latest and insightful research results on MOFs for the adsorption and detection of food contaminants. By summarizing Zn-based, Cu-based and Zr-based MOFs with low cost, easily available raw materials and convenient synthesis conditions, we describe their principles and discuss their applications in chemical and biological contaminant adsorption and sensing detection in terms of stability, adsorption capacity and sensitivity. Finally, we present the limitations and challenges of MOFs in food detection, hoping to provide some ideas for future development.