Reliable Quality Evaluation Research Articles

Enhancing quality assessment of live Pacific oysters (Crassostrea gigas) using flexible sensors real‐time monitoring physiological signals

AbstractShell‐closing strength (SCS) is commonly used to assess oyster vigor and quality as an important physiological stress indicator of the oyster organism. In this study, a quality decision support system based on flexible wireless sensor network and web services was designed and developed to explore the application of SCS in the rapid assessment of vitality and quality. Based on physiological and environmental information collected by flexible wireless sensor networks, this study proposes a novel quantitative vitality assessment method to identify oyster life decline cycles and processes. Meanwhile, TVB‐N, TVC, and pH were selected as quality indicators, and a back‐propagation artificial neural network (BP‐ANN) was used to predict and evaluate oyster quality indicators. The results showed that the root mean square errors (RMSE) for TVB‐N, TVC, and pH were 0.4624, 0.8827, and 0.1941; the coefficients of determination (R2) were 0.8919, 0.8578, and 0.6249. Therefore, the rapid assessment of oyster vitality and quality based on a flexible wireless sensor network is a reliable and effective means.Practical applicationsThis study aims to explore the application of live oyster SCS for rapid quality evaluation. In this article, a quality decision support system based on a flexible wireless sensor network (WSN) and web services is developed to improve the quality and health of live oysters in the supply chain. The use of the multi‐sensor system enables the monitoring and collection of environmental and physiological signals of live oysters throughout the supply chain process. The evaluation of the quality of live oysters using physiological and environmental information collected by flexible wireless sensor networks is a reliable and efficient method. This will provide an effective and reliable quality evaluation and management for the oyster industry.

Content-Variant Reference Image Quality Assessment via Knowledge Distillation

Generally, humans are more skilled at perceiving differences between high-quality (HQ) and low-quality (LQ) images than directly judging the quality of a single LQ image. This situation also applies to image quality assessment (IQA). Although recent no-reference (NR-IQA) methods have made great progress to predict image quality free from the reference image, they still have the potential to achieve better performance since HQ image information is not fully exploited. In contrast, full-reference (FR-IQA) methods tend to provide more reliable quality evaluation, but its practicability is affected by the requirement for pixel-level aligned reference images. To address this, we firstly propose the content-variant reference method via knowledge distillation (CVRKD-IQA). Specifically, we use non-aligned reference (NAR) images to introduce various prior distributions of high-quality images. The comparisons of distribution differences between HQ and LQ images can help our model better assess the image quality. Further, the knowledge distillation transfers more HQ-LQ distribution difference information from the FR-teacher to the NAR-student and stabilizing CVRKD-IQA performance. Moreover, to fully mine the local-global combined information, while achieving faster inference speed, our model directly processes multiple image patches from the input with the MLP-mixer. Cross-dataset experiments verify that our model can outperform all NAR/NR-IQA SOTAs, even reach comparable performance than FR-IQA methods on some occasions. Since the content-variant and non-aligned reference HQ images are easy to obtain, our model can support more IQA applications with its robustness to content variations. Our code is available: https://github.com/guanghaoyin/CVRKD-IQA.

Flight maneuver intelligent recognition based on deep variational autoencoder network

The selection and training of aircraft pilots has high standards, long training cycles, high resource consumption, high risk, and high elimination rate. It is the particularly urgent and important requirement for the current talent training strategy of national and military to increase efficiency and speed up all aspects of pilot training, reduce the training cycle and reduce the elimination rate. To this end, this paper uses deep variational auto-encoder network and adaptive dynamic time warping algorithms as support to explore the establishment of an integrated evaluation system for flight maneuver recognition and quality evaluation, solve the industry difficulty faced by current flight training data mining applications, and achieve accurate recognition and reliable quality evaluation of flight regimes under the background of high mobility. It will fully explore the benefits of existing airborne flight data for military trainee pilots, support the personalized and accurate training of flight talents, and reduce the rate of talent elimination.

Ultrasonic Propagation Imaging for Wind Turbine Blade Quality Evaluation

Soundness of wind turbine blade plays paramount role in supplying cheap and reliable wind energy. To ensure that blades are sound and free from inherent manufacturing defects, easy and reliable quality evaluation before delivering blades for installation is crucial. We propose an ultrasonic amplitude imaging method based on Ultrasonic Propagation Imaging (UPI) system for this purpose. The system utilizes a scanning Q-switched continuous wave laser as ultrasonic wave generator. Various acousto-ultrasonic sensors, either contact or non-contact type, could be adopted as ultrasonic receiver. The system was tested on a blade section made of glass fiber reinforced plastic sandwiched with balsa wood. The leading edge of the specimen with a kissing disbond was inspected. A PZT-based sensor attached temporarily on the outer surface of a blade was used for ultrasonic reception to demonstrate that this imaging method is applicable even for the blades without integrated sensor. The amplitude map clearly showed the disbond defect with the kissing features. The location, shape, and size of the defect evaluated from the result agree excellently with the actual defect. The result proved that the proposed method works well for the quality evaluation of wind turbine blades. Inheriting the advantages of UPI technology, i.e. focusing-free characteristics, acceptance of large laser incident angle up to 60°, and rapid scanning without needing an expensive scan gantry, this system is suitable for automatic quality evaluation of blades with different geometry. On top of that, this system does not require any reference data, making it a flexible quality evaluation system suitable for different methods of blade production flow.