No abstract

Understanding fruit quality is an effective way to reduce fruit loss and waste by providing proper strategies for fruit processing and management. Various noninvasive technologies have been developed for assessing fruit quality. Among them, acoustic vibration technology has received considerable attention from academics. As the fruit ripens, the physical and biochemical diversities of fruit cell lead to changes in the vibration characteristics of the fruit, which verified the feasibility of assessing fruit firmness by acoustic vibration technology from the microscopic view. Besides, the acoustic and vibration theories also provided the theoretical basis for this technology. The measurement system was mainly consisted of excitation devices, detection sensors, and signal processing modules. By using different excitation methods and devices, the fruit could demonstrate a free or forced vibration. The response signals of fruit were influenced by detection methods and sensors. To meet the requirement of high‐throughput detection, noncontact excitation devices and detection sensors were more suitable for on‐line applications. In addition, the relative locations of excitation and detection points and the posture style of fruit also had an impact on the measurement results, which should be determined before the test. Moreover, the proper data analysis method was equally important to extract potential parameters to improve the performance of prediction models. This paper provided a comprehensive overview concerning the principle, system composition, data analysis, and on‐line applications of acoustic vibration technology, and discussed the perspectives of future trends to promote the intensive study and further extension of this technology.

No abstract

Blood spots are one of undesired inclusions in eggs, whose detection success is highly dependent on shell color. This research reports a method for detecting blood spots in light brown-shelled eggs on the basis of hyperspectral transmittance images. The normalized spectra of intact eggs and their shells were acquired. Five feature wavelengths of intact eggs selected by the successive projections algorithm and 3 absorption peak locations of eggshells were regarded as characteristic bands. The k-nearest neighbor (kNN) and support vector machine (SVM) algorithms were adopted to develop detection models. The latter achieved better performance. The overall classification accuracy increased to 100% by merging normalized spectra of intact eggs at 5 feature wavelengths with 3 absorption peaks of eggshells as input variables of SVM-based model. Moreover, a practical SVM-based model with 96.43% overall classification accuracy was established by replacing inputs with normalized spectra of intact eggs at characteristic bands.