英文摘要
To efficiently and accurately detect minuscule foreign objects in the processing of Pu-erh sun-dried green tea, ensuring food quality and consumer safety, this study innovatively proposes an enhanced YOLOv8 neural network based on deep learning. In light of the shortcomings of the traditional YOLOv8 network, to further enhance the model’s ability to identify foreign object targets, improve the depth and breadth of feature extraction, and to better understand the contextual connections between different parts of the image, this study employs a Shape-IoU optimized loss function. It replaces parts of the network structure with Receptive-Field Attention Convolution technology and embeds Double Attention Networks to optimize the network. Experimental results show that the enhanced YOLOv8 neural network model achieves a precision rate of 98.35% for the detection of foreign objects in Pu-erh sun-dried green tea, which is a 3.93% increase compared to the original YOLOv8 network. Compared to mainstream detection models such as YOLOv7, YOLOv5, Faster-RCNN, CornerNet, and SSD, the mean Average Precision values of the enhanced YOLOv8 network model have significantly increased by 4.48%, 6.66%, 13.63%, 13.20%, and 9.84% respectively. This enhanced YOLOv8 network provides a viable research method and significant reference for the detection of small foreign objects in Pu-erh sun-dried green tea, holding substantial importance for tea-producing enterprises and food safety regulatory authorities. Furthermore, this study offers a more comprehensive and efficient solution for foreign object detection in Pu-erh tea and the broader food industry, laying the groundwork for the modernization and intelligentization of food safety and quality control.
中文摘要
为高效、准确地检测普洱晒青茶加工过程中混入的微小异物，保障食品质量与消费者安全，本研究创新性地提出了一种基于深度学习的增强型YOLOv8神经网络模型。针对传统YOLOv8网络存在的不足，为进一步提升模型对异物目标的识别能力、增强特征提取的深度与广度，并更好地捕捉图像不同区域之间的上下文关联，本研究采用了Shape-IoU优化的损失函数，将网络部分结构替换为感受野注意力卷积（Receptive-Field Attention Convolution）技术，并嵌入双重注意力网络（Double Attention Networks）以优化整体架构。实验结果表明，所提出的增强型YOLOv8神经网络模型在普洱晒青茶异物检测任务中达到了98.35%的精确率，较原始YOLOv8模型提升了3.93%。与YOLOv7、YOLOv5、Faster R-CNN、CornerNet和SSD等主流检测模型相比，该增强模型的平均精度均值（mAP）分别显著提高了4.48%、6.66%、13.63%、13.20%和9.84%。该增强型YOLOv8网络为普洱晒青茶中微小异物的检测提供了一种切实可行的研究方法和重要参考，对茶叶生产企业及食品安全监管部门具有显著应用价值。此外，本研究还为普洱茶乃至更广泛的食品工业中的异物检测提供了更加全面、高效的解决方案，为食品安全与质量控制的现代化和智能化奠定了坚实基础。
打标依据

英文摘要
Portable and fast genetically modified organisms (GMOs) detection can achieve accurate labeling and precise regulation. Here, we build a universal and intelligent Multi-RPA-CRISPR/Cas12a-G4 detection chip platform for simultaneous CaMV35S and NOS detection. The use of multiple primer pairs for RPA enables one-tube amplification of dual targets. Independent cleavage of Cas12a for dual targets was controlled by flow amplification products into the respective detection chambers containing CaMV35S crRNA and NOS crRNA. The detection results are obtained based that uncut G4 in solution can produce peroxidase activity to catalyze ABTS2- making the negative result approaching dark green. The multi-RPA-CRISRP/Cas12a-G4 colorimetric platform achieves a 1 aM LOD for CaMV35S and NOS in 55 min. The Yolov5 deep learning algorithm and the analysis of gray values was trained and developed for colorimetric detection that is more sensitive than the naked eye. These algorithms are integrated into a smartphone app to automate the reading of test results. The 100% accuracy of colorimetry detection and the 93.3% accuracy of portable chip detection for rice and soy sauce samples demonstrate our method can rapidly and inexpensively detect samples of GMOs across species. Overall, our efficient, low-cost portable Multi-RPA-CRISPR/Cas12a-G4 detection platform coupled with deep learning algorithms enables portable GMOs detection with automated signal readout.
中文摘要
便携、快速的转基因生物（GMOs）检测有助于实现准确标识和精准监管。本文构建了一种通用且智能化的多重RPA-CRISPR/Cas12a-G4检测芯片平台，可同时检测CaMV35S和NOS两种常见转基因元件。该平台利用多对引物进行重组酶聚合酶扩增（RPA），实现双目标在单管内的同步扩增。随后，扩增产物通过流动分别进入含有CaMV35S crRNA和NOS crRNA的独立检测腔室，由Cas12a对两个靶标进行特异性切割。检测结果基于以下原理：溶液中未被切割的G-四链体（G4）具有类过氧化物酶活性，可催化ABTS²⁻显色，使阴性结果呈现深绿色。该多重RPA-CRISPR/Cas12a-G4比色检测平台在55分钟内即可实现对CaMV35S和NOS低至1 aM（阿摩尔）的检测限。为进一步提升灵敏度（超越肉眼判读能力），我们训练并开发了基于YOLOv5深度学习算法和灰度值分析的图像识别模型，并将其集成到智能手机应用程序中，以自动读取检测结果。在实际样本测试中，该方法对大米和酱油样品的比色检测准确率达100%，便携式芯片检测准确率达93.3%，表明本方法能够跨物种快速、低成本地检测各类GMO样品。总体而言，我们开发的这一高效、低成本、便携式的多重RPA-CRISPR/Cas12a-G4检测平台，结合深度学习算法，实现了GMO检测的自动化信号读取与现场快速筛查。
打标依据

英文摘要
Accurate estimation of saffron purity is essential for ensuring product integrity, particularly in the presence of common chemical adulterants such as tartrazine, sunset yellow, and quinoline yellow. This study introduces the alternating conditional expectations (ACE) algorithm, coupled with diffuse reflectance infrared Fourier transform spectroscopy (DRIFTS), as an innovative chemometric approach to address this challenge. The ACE algorithm utilizes optimal transformations for both independent and dependent variables, revealing nonlinear relationships and maximizing linear effects between transformed variables. To prepare the spectral data for ACE modeling, we will perform moving average smoothing and Standard Normal Variate (SNV) transformation for preprocessing. Subsequently, we will employ the duplex algorithm to select both calibration and prediction sets from the preprocessed data matrix. The effectiveness of the ACE model was evaluated using several metrics, including the coefficient of determination (R2), adjusted Rsquared (R2adj), sum of squared errors (SSE), Regression Sum of Squares (SSR) and mean squared error (MSE). ACE model exhibited excellent performance in determining saffron content even in the presence of adulterants like tartrazine, sunset yellow, and quinoline yellow, on both calibration and prediction sets. Our model achieved excellent performance on both datasets. On the calibration set, a high R2 value (0.9951) indicates a strong correlation between predicted and observed saffron content in the model. The R2adj (0.9950) further strengthens this conclusion by accounting for model complexity, suggesting the model avoids overfitting. These findings are complemented by robustness measures. The statistical parameters of the ACE model, such as total sum of squares (SST) (1.103104), SSR (1.098104), SSE (54.414), and MSE (0.878), were calculated to compare the performance of the developed methods for determining Saffron's concentration in each mixed sample.
中文摘要
准确评估藏红花纯度对于保障产品真实性至关重要，尤其是在存在常见化学掺假物（如酒石黄、日落黄和喹啉黄）的情况下。本研究提出了一种创新的化学计量学方法——将交替条件期望（ACE）算法与漫反射傅里叶变换红外光谱（DRIFTS）相结合，以应对这一挑战。ACE算法通过对自变量和因变量进行最优变换，揭示变量间的非线性关系，并在变换后的变量之间最大化线性效应。为构建ACE模型，首先对光谱数据进行预处理，包括移动平均平滑和标准正态变量变换（SNV）。随后，采用Duplex算法从预处理后的数据矩阵中分别选取校正集和预测集。通过多个评价指标对ACE模型的性能进行评估，包括决定系数（R²）、调整后决定系数（R²adj）、残差平方和（SSE）、回归平方和（SSR）以及均方误差（MSE）。结果表明，ACE模型在校正集和预测集中均表现出优异的性能，即使在存在酒石黄、日落黄和喹啉黄等掺假物的情况下，也能准确测定藏红花含量。在校正集中，模型获得了很高的R²值（0.9951），表明预测值与实测藏红花含量之间具有极强的相关性；而调整后的R²（R²adj = 0.9950）进一步证实了该结论，说明模型在考虑复杂度后仍能有效避免过拟合。此外，模型的稳健性也得到了验证。通过计算ACE模型的各项统计参数——总平方和（SST = 1.103104）、回归平方和（SSR = 1.098104）、残差平方和（SSE = 54.414）以及均方误差（MSE = 0.878）——对所开发方法在各混合样品中测定藏红花浓度的性能进行了比较。这些结果共同表明，所提出的ACE-DRIFTS方法在藏红花纯度检测方面具有高准确性与可靠性。
打标依据

英文摘要
Fatty acid (FA) profiling in muscle and hepatopancreas of Litopenaeus vannamei was combined with k-nearest neighbor (KNN), and random forest (RF) to differentiate L. vannamei raised in freshwater and seawater areas. The FA profiles of the two tissues differed between L. vannamei cultured in freshwater and seawater. Moreover, six and seven variables in muscle and hepatopancreas, respectively, were selected by orthogonal partial least squares-discriminant analysis (OPLS-DA) to create models for distinguishing L. vannamei cultured in freshwater and seawater. The most selected variables in muscle and hepatopancreas were related to salinity. Furthermore, using FA profiles from the two tissues, both KNN and RF had initial and cross-validated classification rates > 93%, while the predictive classification rates of the models based on muscle FA profiles were higher than that of the models based on hepatopancreas FA profiles. Therefore, FA profiles in muscle were more effective than hepatopancreas FAs for identifying shrimps. FA profiling in muscle tissue represents a promising method for discriminating between L. vannamei cultured in freshwater and seawater.
中文摘要
本研究结合南美白对虾肌肉和肝胰腺的脂肪酸谱、K近邻算法和随机森林算法，以区分淡水和海水养殖的南美白对虾。两个组织的脂肪酸谱在淡水和海水养殖的对虾中存在差异。此外，分别通过正交偏最小二乘判别分析筛选出肌肉和肝胰腺中的6个和7个关键变量，用于建立区分养殖环境的模型。这些关键变量大多与盐度相关。基于两个组织的脂肪酸谱，K近邻和随机森林模型的初始分类准确率和交叉验证准确率均高于93%，且基于肌肉脂肪酸谱的模型预测准确率高于基于肝胰腺的模型。因此，肌肉的脂肪酸谱在鉴别虾的养殖环境方面比肝胰腺更有效。肌肉组织的脂肪酸谱分析是区分淡水和海水养殖南美白对虾的一种有前景的方法。
打标依据

英文摘要
The agri-food sector represents a boundless source for sustaining a growing global population, with food quality emerging as a paramount concern. However, the evolving landscape presents several challenges, necessitating a compelling need to harness the potential of recent advancements in computer-aided systems. Fortunately, advances in computer-aided digital transformation have ushered in the era of Industry 4.0, representing a dramatic leap forward. Within this framework, Quality 4.0 has emerged as a pivotal component, leveraging intelligent and innovative technologies to enhance quality monitoring systems. This review emphasizes within the broader context of digital transformation that defines today’s food industry, facilitating the utilization of artificial intelligence (AI), big data analytics, food printing techniques, digital twins, smart sensors, and blockchain technology to revolutionize quality management in different food sector.
中文摘要
农业食品领域是支撑全球人口增长的不可或缺的资源，食品质量已成为首要关注点。然而，不断变化的环境带来了诸多挑战，这就迫切需要充分利用计算机辅助系统的最新发展潜力。幸运的是，计算机辅助数字化转型的进步催生了工业 4.0 时代，实现了跨越式发展。在此框架下，质量 4.0 已成为核心组成部分，它借助智能创新技术提升质量监测系统。本综述聚焦于当今食品工业所处的数字化转型大背景，探讨如何运用人工智能（AI）、大数据分析、食品打印技术、数字孪生、智能传感器和区块链技术，为不同食品领域的质量管理带来革命性变革
打标依据