Search

In the realm of commercial trade, the appearance quality of wheat is a crucial metric for assessing its value and grading. Traditionally, evaluating wheat appearance quality is a manual process conducted by inspectors, which is time-consuming, laborious, and error-prone. In this research, we developed an intelligent detection system for wheat appearance quality, leveraging state-of-the-art neural network technology for the efficient and standardized assessment of wheat appearance quality. Our system was meticulously crafted, integrating high-performance hardware components and sophisticated software solutions. Central to its functionality is a detection model built upon multi-grained convolutional neural networks. This innovative setup allows for the swift and precise evaluation and categorization of wheat quality. Remarkably, our system achieved an exceptional overall recognition accuracy rate of 99.45% for wheat grain categories, boasting a recognition efficiency that was approximately five times faster than manual recognition processes. This groundbreaking system serves as a valuable tool for assisting inspectors, offering technical support for customs quarantine, grain reserves, and food safety. [ABSTRACT FROM AUTHOR]

ConvNet-based object detection networks have achieved outstanding performance on clean images. However, many works have shown that these detectors perform poorly on corrupted images caused by noises, blurs, poor weather conditions and so on. With the development of security-sensitive applications, the detector's practicability has raised increasing concerns. Existing approaches improve detector robustness via extra operations (image restoration or training on extra labeled data) or by applying adversarial training at the expense of performance degradation on clean images. In this paper, we present Selective Adversarial Learning with Constraints (SALC) as a universal detector training approach to simultaneously improve the detector's precision and robustness. We first propose a unified formulation of adversarial samples for multitask adversarial learning, which significantly diversifies the obtained adversarial samples when integrated into the adversarial training of the detector. Next, we examine our findings on model bias against adversarial attacks of different strengths and differences in Batch Normalization (BN) statistics among clean images and different adversarial samples. On this basis, we propose a batch local comparison strategy with two BN branches to balance the detector's accuracy and robustness. Furthermore, to avoid performance degradation caused by overwhelming subtask losses, we leverage task-aware ratio thresholds to control the influence of learning in each subtask. The proposed approach can be applied to various detectors without any extra labeled data, inference time costs, or model parameters. Extensive experiments show that our SALC achieves state-of-the-art results on both clean benchmarks (Pascal VOC and MS-COCO) and corruption benchmarks (Pascal VOC-C and MS-COCO-C).

Comprehensive experiments course is a bridge for higher vocational students to integrate theoretical knowledge with production practice. The article introduces that our biological pharmacy department is committed to the principles of "promotion of teaching, learning and construction through skills competition so as to integrate education and training". By taking penicillin fermentation process as an example, reform has been made in several aspects including teaching objectives, teaching content and teaching methods. We integrate the practical operation of fermentation equipment with virtual simulation software to develop a two-way interactive course. By reducing the subjective dependence, the quantitative management and evaluation of fermentation process parameter control were put into place, which efficiently integrated the skills competition with practical teaching. Improved teaching performance has been achieved over recent years, which may facilitate the reform and practice of similar courses based on skills competition.

Objective: To determine the structures and contents of the volatile components of flowers of Fritillaria thunbergii, and investigate the effects of operation modes on its volatile components., Method: The volatile oils were first obtained by the hydrodistillation assay and then submitted to gas chromatography-time-of flight mass spectrometry (GC-TOF-MS) analysis., Result: More than 60 peaks were resolved, and 39 of which were identified quantitatively and qualitatively based on high-resolution spectra and compounds library screening. Among these identified components, the octadecatrienoic acid methyl esters were major components in the unprocessed flowers, while some aromatic aldehydes and ketones, such as benzeneacetaldehyde and 1-(2-hydroxy-5-methylphenyl)-ethanone, were prominent components in the flowers both dried in the fluidized bed and in shadow. In addition, the flowers dried in the fluidized bed were more fragrant than other flowers., Conclusion: The component and contents closely related to their processing mode, and the fluided bed drying may be a best choice to process the flowers of F. thunbergii.