Elevating nanomaterial optical sensor arrays through the integration of advanced machine learning techniques for enhancing visual inspection of food quality and safety.

Food quality and safety problems caused by inefficient control in the food chain have significant implications for human health, social stability, and economic progress and optical sensor arrays (OSAs) can effectively address these challenges. This review aims to summarize the recent applications of nanomaterials-based OSA for food quality and safety visual monitoring, including colourimetric sensor array (CSA) and fluorescent sensor array (FSA). First, the fundamental properties of various advanced nanomaterials, mainly including metal nanoparticles (MNPs) and nanoclusters (MNCs), quantum dots (QDs), upconversion nanoparticles (UCNPs), and others, were described. Besides, the diverse machine learning (ML) and deep learning (DL) methods of high-dimensional data obtained from the responses between different sensing elements and analytes were presented. Moreover, the recent and representative applications in pesticide residues, heavy metal ions, bacterial contamination, antioxidants, flavor matters, and food freshness detection were comprehensively summarized. Finally, the challenges and future perspectives for nanomaterials-based OSAs are discussed. It is believed that with the advancements in artificial intelligence (AI) techniques and integrated technology, nanomaterials-based OSAs are expected to be an intelligent, effective, and rapid tool for food quality assessment and safety control.

Self-assembly of CuAuTA nanozymes for intelligent detection of ginkgolic acids.

Toxic ginkgolic acids (GAs) are a challenge for Ginkgo biloba-related food. Although a detection method for GAs is available, bulky instruments limit the field testing of GAs. Herein, by assembling gold nanoclusters with copper tannic acid (CuTA), CuAuTA nanocomposites were designed as peroxidase mimics for the colorimetric determination of GAs. Compared with single CuTA, the obtained CuAuTA nanocomposites possessed enhanced peroxidase-like properties. Based on the inhibitory effect of GAs for the catalytic activity of CuAuTA nanozymes, CuAuTA could be utilized for the colorimetric sensing of GAs with a low limit of quantitation of 0.17 µg mL-1. Using a smartphone and the ImageJ software in conjunction, a nanozyme-based intelligent detection platform was developed with a detection limit of 0.86 µg mL-1. This sensing system exhibited good selectivity against other potential interferents. Experimental data demonstrated that GAs might bind to the surface of CuAuTA, blocking the catalytically active sites and resulting in decreased catalytic activity. Our CuAuTA nanozyme-based system could also be applied to detect real ginkgo nut and ginkgo powder samples with recoveries of 93.12-111.6% and relative standard deviations less than 0.3%. Our work may offer a feasible strategy for the determination of GAs and expand the application of nanozymes in food safety detection.

Manganese-arginine nanozymes as oxidase mimics for smartphone-based intelligent detection of 4'-O-methylpyridoxine.

By self-assembly of MnCl2 and arginine under alkaline conditions, ultra-small MnArg nanoparticles were successfully constructed as oxidase (OXD) mimics for intelligent detection of the Ginkgo toxin 4'-O-methylpyridoxal (MPN). The obtained MnArg nanozymes possessed excellent OXD-like activity and thermal stability. Based on the inhibitory effect of MPN for the catalytic activity of MnArg, this system was utilized for the colorimetric sensing of MPN with a low limit of detection (LOD) of 2.16 µg mL-1. The detection  system exhibited good selectivity against other potential interferents. FTIR data showed that the presence of MPN binds with MnArg and shields the active sites, thereby interfering with the oxidase-like activity. Combined with a smartphone and the ColorMax software, this nanozyme-based intelligent detection platform could effectively detect MPN with a LOD of 2.1 µg mL-1. Our MnArg nanozyme-based system was applied to detect real ginkgo nut samples with recoveries of 92.4-108.7%, and the relative standard deviations were less than 0.7%. This work may promote the development of novel nanozymes and expand their applications in the field of food safety detection.

Research on Detection Method of Chaotian Pepper in Complex Field Environments Based on YOLOv8.

The intelligent detection of chili peppers is crucial for achieving automated operations. In complex field environments, challenges such as overlapping plants, branch occlusions, and uneven lighting make detection difficult. This study conducted comparative experiments to select the optimal detection model based on YOLOv8 and further enhanced it. The model was optimized by incorporating BiFPN, LSKNet, and FasterNet modules, followed by the addition of attention and lightweight modules such as EMBC, EMSCP, DAttention, MSBlock, and Faster. Adjustments to CIoU, Inner CIoU, Inner GIoU, and inner_mpdiou loss functions and scaling factors further improved overall performance. After optimization, the YOLOv8 model achieved precision, recall, and mAP scores of 79.0%, 75.3%, and 83.2%, respectively, representing increases of 1.1, 4.3, and 1.6 percentage points over the base model. Additionally, GFLOPs were reduced by 13.6%, the model size decreased to 66.7% of the base model, and the FPS reached 301.4. This resulted in accurate and rapid detection of chili peppers in complex field environments, providing data support and experimental references for the development of intelligent picking equipment.

Consumer-oriented smart dynamic detection of fresh food quality: recent advances and future prospects.

Since fresh foods include a significant amount of water, fat, and protein, it is more likely to become infected by microorganisms causing a major loss of quality. Traditional detection techniques are less able to meet customer expectations owing to the limitations of high cost, slow response time, and inability to permit dynamic monitoring. Intelligent non-destructive detection technologies have emerged in recent years, which offer the advantages of small size and fast response at low cost. However, dynamic monitoring of fresh food quality based on intelligent detection technologies on the consumer side has not been rigorously evaluated yet. This paper discussed the application of intelligent detection technologies based on the consumer side in the dynamic monitoring of fresh food freshness, microorganisms, food additives, and pesticide residues. Furthermore, the application of intelligent detection technologies combined with smartphones for quality monitoring and detection of fresh foods is evaluated. Moreover, the challenges and development trends of intelligent fresh food quality detection technologies are also discussed. Intelligent detection technologies based on the consumer side are designed to detect in real-time the quality of fresh food through visual color changes in combination with smartphones. This paper provides ideas and recommendations for the application of intelligent detection technologies based on the consumer side in food quality detection/monitoring and future research trends.

A spectral learning path for simultaneous multi-parameter detection of water quality.

Water quality parameters (WQP) are the most intuitive indicators of the environmental quality of water body. Due to the complexity and variability of the chemical environment of water body, simple and rapid detection of multiple parameters of water quality becomes a difficult task. In this paper, spectral images (named SPIs) and deep learning (DL) techniques were combined to construct an intelligent method for WQP detection. A novel spectroscopic instrument was used to obtain SPIs, which were converted into feature images of water chemistry and then combined with deep convolutional neural networks (CNNs) to train models and predict WQP. The results showed that the method of combining SPIs and DL has high accuracy and stability, and good prediction results with average relative error of each parameter (anions and cations, TOC, TP, TN, NO3--N, NH3-N) at 1.3%, coefficient of determination (R2) of 0.996, root mean square error (RMSE) of 0.1, residual prediction deviation (RPD) of 16.2, and mean absolute error (MAE) of 0.067. The method can achieve rapid and accurate detection of high-dimensional water quality multi-parameters, and has the advantages of simple pre-processing and low cost. It can be applied not only to the intelligent detection of environmental waters, but also has the potential to be applied in chemical, biological and medical fields.

Sensing Method for Wet Spraying Process of Tunnel Wall Based on the Laser LiDAR in Complex Environment.

In tunnel lining construction, the traditional manual wet spraying operation is labor-intensive and can be challenging to ensure consistent quality. To address this, this study proposes a LiDAR-based method for sensing the thickness of tunnel wet spray, which aims to improve efficiency and quality. The proposed method utilizes an adaptive point cloud standardization processing algorithm to address differing point cloud postures and missing data, and the segmented Lamé curve is employed to fit the tunnel design axis using the Gauss-Newton iteration method. This establishes a mathematical model of the tunnel section and enables the analysis and perception of the thickness of the tunnel to be wet sprayed through comparison with the actual inner contour line and the design line of the tunnel. Experimental results show that the proposed method is effective in sensing the thickness of tunnel wet spray, with important implications for promoting intelligent wet spraying operations, improving wet spraying quality, and reducing labor costs in tunnel lining construction.

An Intelligent Online Drunk Driving Detection System Based on Multi-Sensor Fusion Technology.

Since drunk driving poses a significant threat to road traffic safety, there is an increasing demand for the performance and dependability of online drunk driving detection devices for automobiles. However, the majority of current detection devices only contain a single sensor, resulting in a low degree of detection accuracy, erroneous judgments, and car locking. In order to solve the problem, this study firstly designed a sensor array based on the gas diffusion model and the characteristics of a car steering wheel. Secondly, the data fusion algorithm is proposed according to the data characteristics of the sensor array on the steering wheel. The support matrix is used to improve the data consistency of the single sensor data, and then the adaptive weighted fusion algorithm is used for multiple sensors. Finally, in order to verify the reliability of the system, an online intelligent detection device for drunk driving based on multi-sensor fusion was developed, and three people using different combinations of drunk driving simulation experiments were conducted. According to the test results, a drunk person in the passenger seat will not cause the system to make a drunk driving determination. When more than 50 mL of alcohol is consumed and the driver is seated in the driver's seat, the online intelligent detection of drunk driving can accurately identify drunk driving, and the car will lock itself as soon as a real-time online voice prompt is heard. This study enhances and complements theories relating to data fusion for online automobile drunk driving detection, allowing for the online identification of drivers who have been drinking and the locking of their vehicles to prevent drunk driving. It provides technical support for enhancing the accuracy of online systems that detect drunk driving in automobiles.

Facile Fabrication of 1-Methylimidazole/Cu Nanozyme with Enhanced Laccase Activity for Fast Degradation and Sensitive Detection of Phenol Compounds.

Facile construction of functional nanomaterials with laccase-like activity is important in sustainable chemistry since laccase is featured as an efficient and promising catalyst especially for phenolic degradation but still has the challenges of high cost, low activity, poor stability and unsatisfied recyclability. In this paper, we report a simple method to synthesize nanozymes with enhanced laccase-like activity by the self-assembly of copper ions with various imidazole derivatives. In the case of 1-methylimidazole as the ligand, the as-synthesized nanozyme (denoted as Cu-MIM) has the highest yield and best activity among the nanozymes prepared. Compared to laccase, the Km of Cu-MIM nanozyme to phenol is much lower, and the vmax is 6.8 times higher. In addition, Cu-MIM maintains excellent stability in a variety of harsh environments, such as high pH, high temperature, high salt concentration, organic solvents and long-term storage. Based on the Cu-MIM nanozyme, we established a method for quantitatively detecting phenol concentration through a smartphone, which is believed to have important applications in environmental protection, pollutant detection and other fields.

Intelligent detection for fresh-cut fruit and vegetable processing: Imaging technology.

Fresh-cut fruits and vegetables are healthy and convenient ready-to-eat foods, and the final quality is related to the raw materials and each step of the cutting unit. It is necessary to integrate suitable intelligent detection technologies into the production chain so as to inspect each operation to ensure high product quality. In this paper, several imaging technologies that can be applied online to the processing of fresh-cut products are reviewed, including: multispectral/hyperspectral imaging (M/HSI), fluorescence imaging (FI), X-ray imaging (XRI), ultrasonic imaging, thermal imaging (TI), magnetic resonance imaging (MRI), terahertz imaging, and microwave imaging (MWI). The principles, advantages, and limitations of these imaging technologies are critically summarized. The potential applications of these technologies in online quality control and detection during the fresh-cut processing are comprehensively discussed, including quality of raw materials, contamination of cutting equipment, foreign bodies mixed in the processing, browning and microorganisms of the cutting surface, quality/shelf-life evaluation, and so on. Finally, the challenges and future application prospects of imaging technology in industrialization are presented.

[Detection of white blood cells in microscopic leucorrhea images based on deep active learning].

The number of white blood cells in the leucorrhea microscopic image can indicate the severity of vaginal inflammation. At present, the detection of white blood cells in leucorrhea mainly relies on manual microscopy by medical experts, which is time-consuming, expensive and error-prone. In recent years, some studies have proposed to implement intelligent detection of leucorrhea white blood cells based on deep learning technology. However, such methods usually require manual labeling of a large number of samples as training sets, and the labeling cost is high. Therefore, this study proposes the use of deep active learning algorithms to achieve intelligent detection of white blood cells in leucorrhea microscopic images. In the active learning framework, a small number of labeled samples were firstly used as the basic training set, and a faster region convolutional neural network (Faster R-CNN) training detection model was performed. Then the most valuable samples were automatically selected for manual annotation, and the training set and the corresponding detection model were iteratively updated, which made the performance of the model continue to increase. The experimental results show that the deep active learning technology can obtain higher detection accuracy under less manual labeling samples, and the average precision of white blood cell detection could reach 90.6%, which meets the requirements of clinical routine examination.

Intelligent Detection of a Planetary Gearbox Composite Fault Based on Adaptive Separation and Deep Learning.

Due to the existence of multiple rotating parts in the planetary gearbox-such as the sun gear, planet gears, planet carriers, and its unique planetary motion, etc.-the vibration signals generated under multiple fault conditions are time-varying and nonstable, thus making fault diagnosis difficult. In order to solve the problem of planetary gearbox composite fault diagnosis, an improved particle swarm optimization variational mode decomposition (IPVMD) and improved convolutional neural network (I-CNN) are proposed. The method takes as input the spectrum of the original vibration signal that contains rich information. First, the automatic feature extraction of signal spectrum is performed by I-CNN, while a classifier is used to diagnose the fault modes. Second, the composite fault signal is decomposed into multiple single fault signals by adaptive variational mode, and the signal is decomposed as a model input to diagnose the single fault component. Finally, a complete intelligent diagnosis of planetary gearboxes is conducted. Through experimental verification, the composite fault diagnosis method combining IPVMD and I-CNN will diagnose the composite fault and effectively diagnose the sub-fault included in the composite fault.

An intelligent detection method for high-field asymmetric waveform ion mobility spectrometry.

In conventional high-field asymmetric waveform ion mobility spectrometry signal acquisition, multi-cycle detection is time consuming and limits somewhat the technique's scope for rapid field detection. In this study, a novel intelligent detection approach has been developed in which a threshold was set on the relative error of α parameters, which can eliminate unnecessary time spent on detection. In this method, two full-spectrum scans were made in advance to obtain the estimated compensation voltage at different dispersion voltages, resulting in a narrowing down of the whole scan area to just the peak area(s) of interest. This intelligent detection method can reduce the detection time to 5-10% of that of the original full-spectrum scan in a single cycle.

Intelligent System/Equipment for Quality Deterioration Detection of Fresh Food: Recent Advances and Application.

The quality of fresh foods tends to deteriorate rapidly during harvesting, storage, and transportation. Intelligent detection equipment is designed to monitor and ensure product quality in the supply chain, measure appropriate food quality parameters in real time, and thus minimize quality degradation and potential financial losses. Through various available tracking devices, consumers can obtain actionable information about fresh food products. This paper reviews the recent progress in intelligent detection equipment for sensing the quality deterioration of fresh foods, including computer vision equipment, electronic nose, smart colorimetric films, hyperspectral imaging (HSI), near-infrared spectroscopy (NIR), nuclear magnetic resonance (NMR), ultrasonic non-destructive testing, and intelligent tracing equipment. These devices offer the advantages of high speed, non-destructive operation, precision, and high sensitivity.

Ratiometric fluorescence sensor based on deep learning for rapid and user-friendly detection of tetracycline antibiotics.

The detection of tetracycline antibiotics (TCs) in food holds great significance in minimizing their absorption within the human body. Hence, this study aims to develop a rapid, convenient, real-time, and accurate detection method for detecting antibiotics in an authentic market setting. A colorimetric fluorescence sensor was devised for tetracycline detection utilizing PVA aerogels as the substrate. Its operating principle is based on the IFE effect and antenna effect. A detection device is designed to capture fluorescence images while deep learning was employed to aid in the detection process. The sensor exhibits high responsiveness with a mere 60-s requirement for detection and demonstrates substantial color changes(blue to red), achieving 99% accuracy within the range of 10-100 µM with the assistance of deep learning (Resnet18). Real sample simulation tests yielded recovery rates between 95% and 130%. Overall, the proposed strategy proved to be a simple, portable, reliable, and responsive solution for rapid real-time TCs detection in food samples.

CoMnOx Nanoflower-Based Smartphone Sensing Platform and Virtual Reality Display for Colorimetric Detection of Ziram and Cu2.

Transition metal doping is an ideal strategy to construct multifunctional and efficient nanozymes for biosensing. In this work, a metal-doped CoMnOx nanozyme was designed and synthesized by hydrothermal reaction and high-temperature calcination. Based on its oxidase activity, an "on-off-on" smartphone sensing platform was established to detect ziram and Cu2+. The obtained flower-shaped CoMnOx could exhibit oxidase-, catalase-, and laccase-like activities. The oxidase activity mechanism of CoMnOx was deeply explored. O2 molecules adsorbed on the surface of CoMnOx were activated to produce a large amount of O2·-, and then, O2·- could extract acidic hydrogen from TMB to produce blue oxTMB. Meanwhile, TMB was oxidized directly to the blue product oxTMB via the high redox ability of Co species. According to the excellent oxidase-like activity of CoMnOx, a versatile colorimetric detection platform for ziram and Cu2+ was successfully constructed. The linear detection ranges for ziram and Cu2+ were 5~280 µM and 80~360 µM, and the detection limits were 1.475 µM and 3.906 µM, respectively. In addition, a portable smartphone platform for ziram and Cu2+ sensing was established for instant analysis, showing great application promise in the detection of real samples including environmental soil and water.

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 âˆ¼ 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 âˆ¼ 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.

A sensitive fluorometric-colorimetric dual-mode intelligent sensing platform for the detection of formaldehyde.

Excess formaldehyde (FA) is a strong carcinogen, so the development of a rapid visualized and portable formaldehyde detection platform is of great research importance. A multi-color fluorescence sensing system constituted of model compound (NAHN) and red-emitting InP/ZnS QDs was constructed herein, which can simultaneously realize fluorometric-colorimetric dual-mode sensing when exposed to FA environment. Its preparation process was simplified, the detection process was green, and the limits of detection (LOD) were 0.623 µM and 0.791 µM, respectively. The high recoveries of FA in actual water samples indicated that the sensor had broad application prospects. The prepared fluorescent film can be utilized for rapid visual simulation analysis of FA on the surface of various fruits and vegetables. In addition, a serial logic gate was designed to quickly semi-quantitatively assess FA concentration, which promoted the realization of on-site intelligent evaluation of FA.

Intelligent visual detection of OTC enabled by a multicolor fluorescence nanoprobe: Europium complex functionalized carbon dots.

It is of great significance to realize ultra-sensitive and visual detection of oxytetracycline (OTC) residues, especially for public health and environmental safety. In this study, a multicolor fluorescence sensing platform (CDs-Cit-Eu) for OTC detection was constructed by using rare earth europium complex functionalized carbon dots (CDs). The blue-emitting CDs (λem = 450 nm) prepared by one-step hydrothermal method using nannochloropsis were not only the scaffold of Eu3+ ion coordination, but also the recognition unit of OTC. After adding OTC to the multicolor fluorescent sensor, the emission intensity of CDs decreased slowly, and the emission intensity of Eu3+ ions (λem = 617 nm) enhanced significantly, accompanying by a significant color change of the nanoprobe from blue to red. The detection limit of the probe for OTC was calculated to be 3.5 nM, manifesting ultra-high sensitivity towards OTC detection. In addition, OTC detection in real samples (honey, lake water, tap water) was successfully achieved. Moreover, a semi-hydrophobic luminescent film SA/PVA/CDs-Cit-Eu was also prepared for OTC detection. With the help of smartphone color recognition APP, real-time intelligent detection of OTC was realized.

Intelligent detection strategy and bioimaging application of dual-responsive Hg2+ and ONOO- using near-infrared probes.

Mercury is a highly toxic heavy metal pollutant. Mercury and its derivatives pose serious threats to the environment and the health of organisms. Numerous reports have indicated that Hg2+ exposure induces a burst of oxidative stress in organisms, causing severe damage to the health of the organism. A large number of reactive oxygen species (ROS) and reactive nitrogen species (RNS) are produced under conditions of oxidative stress, and superoxide anions (O2-) and NO radicals react rapidly with each other to produce peroxynitrite (ONOO-), an important downstream product. Therefore, developing an efficient and highly responsive screening method to monitor the fluctuations of Hg2+ and ONOO- levels is particularly important. In this work, we designed and synthesized a highly sensitive and highly specific near-infrared probe W-2a, which can effectively detect and distinguish Hg2+ and ONOO- through fluorescence imaging. In addition, we developed a WeChat mini-program called "Colorimetric acquisition" and built an intelligent detection platform to assess the environmental hazards of Hg2+ and ONOO-. The probe can detect Hg2+ and ONOO- in the body through dual signaling, as evidenced by cell imaging, and has successfully monitored fluctuations in the ONOO- levels in inflamed mice. In conclusion, the W-2a probe provides a highly efficient and reliable method for assessing oxidative stress-induced changes in the ONOO- levels in the body.