Fish quality evaluation by sensor and machine learning: A mechanistic review

Overcoming the Limits of Cross-Sensitivity: Pattern Recognition Methods for Chemiresistive Gas Sensor Array

As information acquisition terminals for artificial olfaction, chemiresistive gas sensors are often troubled by their cross-sensitivity, and reducing their cross-response to ambient gases has always been a difficult and important point in the gas sensing area. Pattern recognition based on sensor array is the most conspicuous way to overcome the cross-sensitivity of gas sensors. It is crucial to choose an appropriate pattern recognition method for enhancing data analysis, reducing errors and improving system reliability, obtaining better classification or gas concentration prediction results. In this review, we analyze the sensing mechanism of cross-sensitivity for chemiresistive gas sensors. We further examine the types, working principles, characteristics, and applicable gas detection range of pattern recognition algorithms utilized in gas-sensing arrays. Additionally, we report, summarize, and evaluate the outstanding and novel advancements in pattern recognition methods for gas identification. At the same time, this work showcases the recent advancements in utilizing these methods for gas identification, particularly within three crucial domains: ensuring food safety, monitoring the environment, and aiding in medical diagnosis. In conclusion, this study anticipates future research prospects by considering the existing landscape and challenges. It is hoped that this work will make a positive contribution towards mitigating cross-sensitivity in gas-sensitive devices and offer valuable insights for algorithm selection in gas recognition applications.

Assessment of fish adulteration using SnO2 nanopetal-based gas sensor and machine learning

The work presents the identification of fish adulteration and quality assessment by incorporating a chemiresistive gas sensor and machine learning (ML) techniques. Highly sensitive SnO2 nanopetals were synthesized chemically and integrated with interdigitated electrodes to fabricate a sensor device. The sensor was calibrated with formaldehyde (37 %) with a theoretical detection limit of 75 ppb and further utilized to detect the vapors emitted from fresh and formalin-adulterated fish. An extensive sensing investigation was conducted with freshly caught Rohu fish samples. The sensing behavior was examined for all the samples at different time intervals to estimate the spoilage level. The classification between fresh and adulterated fish samples was obtained with 100 % accuracy by employing ML tools. Moreover, the storage duration and spoilage level of fish samples were quantified using regression models. This work emphasizes the potential of nanomaterials combined with machine learning for the accurate detection of adulteration in food systems.

The concentration of Potentially Toxic elements (PTEs) in the muscle of crabs: a global systematic review, meta-analysis, and health risk assessment

The concentration of PTEs in the muscle of crabs, was meta-analyzed using a random-effects model based on countries' subgroups. The non-carcinogenic and carcinogenic risks related to the ingestion of PTEs via the consumption of crab fish were estimated. The meta-analysis included one hundred and eight papers with 109 data reports. The rank order of PTEs based on pooled (mean) concentration in the muscle of crabs was Ni (4.490 mg/kg-ww) > Pb (1.891 mg/kg-ww) >As (1.601 mg/kg-ww) > Cd (1.101 mg/kg-ww). The results showed that adults and children consumers in many countries are at risk of non-carcinogenicity due to ingestion of Ni, Pb, As, and Cd and carcinogenicity risk due to As. Therefore, the bioaccumulation of PTEs in the muscle of crabs can be considered a global health risk. Hence, to decrease the health risk of PTEs in the muscle of crabs, continuous monitoring and reducing the emission of PTEs in aquatic environments are recommended.

Antimicrobial activity of probiotic bacteria-mediated cadmium oxide nanoparticles against fish pathogens

The current research was designed to investigate the antibacterial activity of probiotic bacteria mediated cadmium oxide nanoparticles (CdO NPs) on common fish pathogenic bacteria like Serratia marcescens, Aeromonas hydrophila, Vibrio harveyi, and V. parahaemolyticus. CdO NPs were synthesized using probiotic bacteria as follows: Lactobacillus species with different precursor of cadmium sulfate concentrations (5, 10, and 20 mM). The average crystalline sizes of the CdO NPs were determined based on the XRD patterns using the Debye-Scherrer equation for different precursor concentrations. Specifically, sizes of 40, 48, and 67 nm were found at concentrations of 5, 10, and 20 mM, respectively. The antibacterial efficacy of CdO NPs was estimated using a well diffusion assay, which demonstrated the best efficacy of 20 mM CdO NPs against all pathogens. AFM analysis of nanoparticle-treated and untreated biofilms was performed to further validate the antibacterial effect. Antibacterial activity of CdO nanoparticles synthesized at varying concentrations (5, 10, and 20 mM) against fish pathogens (S. marcescens, A. hydrophila, V. harveyi, and V. parahaemolyticus). The results indicated the highest inhibitory effect of 20 mM CdO NPs across all concentrations (30, 60, and 90 μg/mL), demonstrating significant inhibition against S. marcescens. These findings will contribute to the development of novel strategies for combating aquatic diseases and advancing aquaculture health management practices.

Adsorption and sensor performance of transition metal-decorated zirconium-doped silicon carbide nanotubes for NO2 gas application: a computational insight

Owing to the fact that the detection limit of already existing sensor-devices is below 100% efficiency, the use of 3D nanomaterials as detectors and sensors for various pollutants has attracted interest from researchers in this field. Therefore, the sensing potentials of bare and the impact of Cu-group transition metal (Cu, Ag, Au)-functionalized silicon carbide nanotube (SiCNT) nanostructured surfaces were examined towards the efficient detection of NO2 gas in the atmosphere. All computational calculations were carried out using the density functional theory (DFT) electronic structure method at the B3LYP-D3(BJ)/def2svp level of theory. The mechanistic results showed that the Cu-functionalized silicon carbide nanotube surface possesses the greatest adsorption energies of -3.780 and -2.925 eV, corresponding to the adsorption at the o-site and n-site, respectively. Furthermore, the lowest energy gap of 2.095 eV for the Cu-functionalized surface indicates that adsorption at the o-site is the most stable. The stability of both adsorption sites on the Cu-functionalized surface was attributed to the small ellipticity (ε) values obtained. Sensor mechanisms confirmed that among the surfaces, the Cu-functionalized surface exhibited the best sensing properties, including sensitivity, conductivity, and enhanced adsorption capacity. Hence, the Cu-functionalized SiCNT can be considered a promising choice as a gas sensor material.

Applications of Gas Sensing in Food Quality Detection: A Review

Food products often face the risk of spoilage during processing, storage, and transportation, necessitating the use of rapid and effective technologies for quality assessment. In recent years, gas sensors have gained prominence for their ability to swiftly and sensitively detect gases, making them valuable tools for food quality evaluation. The various gas sensor types, such as metal oxide (MOX), metal oxide semiconductor (MOS) gas sensors, surface acoustic wave (SAW) sensors, colorimetric sensors, and electrochemical sensors, each offer distinct advantages. They hold significant potential for practical applications in food quality monitoring. This review comprehensively covers the progress in gas sensor technology for food quality assessment, outlining their advantages, features, and principles. It also summarizes their applications in detecting volatile gases during the deterioration of aquatic products, meat products, fruit, and vegetables over the past decade. Furthermore, the integration of data analytics and artificial intelligence into gas sensor arrays is discussed, enhancing their adaptability and reliability in diverse food environments and improving food quality assessment efficiency. In conclusion, this paper addresses the multifaceted challenges faced by rapid gas sensor-based food quality detection technologies and suggests potential interdisciplinary solutions and directions.

Wearable Bioimpedance-Based Deep Learning Techniques for Live Fish Health Assessment under Waterless and Low-Temperature Conditions

(1) Background: At present, physiological stress detection technology is a critical means for precisely evaluating the comprehensive health status of live fish. However, the commonly used biochemical tests are invasive and time-consuming and cannot simultaneously monitor and dynamically evaluate multiple stress levels in fish and accurately classify their health levels. The purpose of this study is to deploy wearable bioelectrical impedance analysis (WBIA) sensors on fish skin to construct a deep learning-based stress dynamic evaluation model for precisely estimating their accurate health status. (2) Methods: The correlation of fish (turbot) muscle nutrients and their stress indicators are calculated using grey relation analysis (GRA) for allocating the weight of the stress factors. Next, WBIA features are sieved using the maximum information coefficient (MIC) in stress trend evaluation modeling, which is closely related to the key stress factors. Afterward, a convolutional neural network (CNN) is utilized to obtain the features of the WBIA signals. Then, the long short-term memory (LSTM) method learns the stress trends with residual rectification using bidirectional gated recurrent units (BiGRUs). Furthermore, the Z-shaped fuzzy function can accurately classify the fish health status by the total evaluated stress values. (3) Results: The proposed CNN-LSTM-BiGRU-based stress evaluation model shows superior accuracy compared to the other machine learning models (CNN-LSTM, CNN-GRU, LSTM, GRU, SVR, and BP) based on the MAPE, MAE, and RMSE. Moreover, the fish health classification under waterless and low-temperature conditions is thoroughly verified. High accuracy is proven by the classification validation criterion (accuracy, F1 score, precision, and recall). (4) Conclusions: the proposed health evaluation technology can precisely monitor and track the health status of live fish and provides an effective technical reference for the field of live fish vital sign detection.

Investigating the microbial properties of sodium alginate/chitosan edible film containing red beetroot anthocyanin extract for smart packaging in chicken fillet as a pH indicator

The current trend in the production of smart films involves the use of pH-responsive color indicators derived from natural sources. In line with this trend, the aim of this research is to produce edible films from sodium alginate (A) and chitosan (Ch) incorporating red beet anthocyanin (Ac) extract, and to assess the properties of these films and their use as coatings for chicken fillets. The study employed a factorial design to evaluate the effects of treatments C (control), A25%-ch75% (films consisting of 25% sodium alginate and 75% chitosan), and A25%-ch75%-Ac (films consisting of 25% sodium alginate, 75% chitosan, and red beet anthocyanin). The findings indicate that the inclusion of red beet anthocyanin extract did not result in any discernible differences in the FTIR spectra of the film samples. Analysis of the XRD results revealed that the addition of the extract led to a reduction in the crystal structure of the film. Moreover, SEM results demonstrated that the extract caused alterations in the polymer chains and an increase in the porosity of the film matrix. With regard to the chicken fillet samples coated with the film, over time, there was an increase in microbial analysis (total microorganism count and Staphylococcus aureus coagulase-positive) and chemical properties (pH, peroxide, thiobarbituric acid, and nitrogen compounds) for all samples. However, this trend was significantly lower in the samples coated with the Ac extract (P < 0.05). Texture analysis results revealed that the hardness parameter of all samples decreased over the storage period, while the samples containing the Ac extract demonstrated a significant increase in this parameter (P < 0.05). Additionally, the color changes of the pH sensor corresponded to the anthocyanin structure. Based on the results, the smart film composed of sodium alginate/chitosan incorporating red beet anthocyanin extract has the potential to enhance the quality, prolong the shelf life, and decrease the microbial load of chicken fillet when used as a coating. Furthermore, red beet anthocyanin can serve as a suitable indicator for spoilage changes in packaged food products.

Assessing Meat Freshness via Nanotechnology Biosensors: Is the World Prepared for Lightning-Fast Pace Methods?

In the rapidly evolving field of food science, nanotechnology-based biosensors are one of the most intriguing techniques for tracking meat freshness. Purine derivatives, especially hypoxanthine and xanthine, are important signs of food going bad, especially in meat and meat products. This article compares the analytical performance parameters of traditional biosensor techniques and nanotechnology-based biosensor techniques that can be used to find purine derivatives in meat samples. In the introduction, we discussed the significance of purine metabolisms as analytes in the field of food science. Traditional methods of analysis and biosensors based on nanotechnology were also briefly explained. A comprehensive section of conventional and nanotechnology-based biosensing techniques is covered in detail, along with their analytical performance parameters (selectivity, sensitivity, linearity, and detection limit) in meat samples. Furthermore, the comparison of the methods above was thoroughly explained. In the last part, the pros and cons of the methods and the future of the nanotechnology-based biosensors that have been created are discussed.

Facile Synthesis of Pure and Cr-Doped WO3 Thin Films for the Detection of Xylene at Room Temperature

This paper focused on the preparation of pure and Cr-doped tungsten trioxide (WO₃) thin films using the spray pyrolysis method. Different techniques were adopted to analyze these films' structural and morphological properties. The X-ray detection analysis showed that the average crystallite size of the WO₃-nanostructured thin films increased as the Cr doping concentration increased. The atomic force microscopy results showed that the root-mean-square roughness of the films increased with Cr doping concentration up to 3 wt % and then decreased. The increased roughness is favorable for gas-sensing applications. Surface morphology and elemental analysis of the films were studied by field emission scanning electron microscopy with energy-dispersive X-ray spectroscopy measurements. The 3 wt % Cr-WO₃ has a large nanoflake-like structure with high surface roughness and porous morphology. Gas-sensing characteristics of undoped and Cr-doped WO₃ thin films were investigated with various gases at room temperature. The results showed that 3 wt % Cr-doped WO₃ film performed the maximum response toward 50 ppm of xylene with excellent selectivity at room temperature. We believe that increased lattice defects, surface morphology, and roughness due to Cr doping in the WO₃ crystal matrix might be responsible for increased xylene sensitivity.

Application of Fourier Transform Infrared (FT-IR) Spectroscopy, Multispectral Imaging (MSI) and Electronic Nose (E-Nose) for the Rapid Evaluation of the Microbiological Quality of Gilthead Sea Bream Fillets

The potential of Fourier transform infrared (FT-IR) spectroscopy, multispectral imaging (MSI), and electronic nose (E-nose) was explored in order to determine the microbiological quality of gilthead sea bream (Sparus aurata) fillets. Fish fillets were maintained at four temperatures (0, 4, 8, and 12 °C) under aerobic conditions and modified atmosphere packaging (MAP) (33% CO₂, 19% O₂, 48% N₂) for up to 330 and 773 h, respectively, for the determination of the population of total viable counts (TVC). In parallel, spectral data were acquired by means of FT-IR and MSI techniques, whereas the volatile profile of the samples was monitored using an E-nose. Thereafter, the collected data were correlated to microbiological counts to estimate the TVC during fish fillet storage. The obtained results demonstrated that the partial least squares regression (PLS-R) models developed on FT-IR data provided satisfactory performance in the estimation of TVC for both aerobic and MAP conditions, with coefficients of determination (R²) for calibration of 0.98 and 0.94, and root mean squared error of calibration (RMSE_C) values of 0.43 and 0.87 log CFU/g, respectively. However, the performance of the PLS-R models developed on MSI data was less accurate with R² values of 0.79 and 0.77, and RMSE_C values of 0.78 and 0.72 for aerobic and MAP storage, respectively. Finally, the least satisfactory performance was observed for the E-nose with the lowest R² (0.34 and 0.17) and the highest RMSE_C (1.77 and 1.43 log CFU/g) values for aerobic and MAP conditions, respectively. The results of this work confirm the effectiveness of FT-IR spectroscopy for the rapid evaluation of the microbiological quality of gilthead sea bream fillets.