Evolution Pattern in Bruised Tissue of 'Red Delicious' Apple

The study of apple damage mechanisms is key to improving post-harvest apple treatment techniques, and the evolution pattern of damaged tissue is fundamental to the study of apple damage mechanisms. In the study, 'Red Delicious' apples were used to explore the relationship between damage and time. A cell death zone was found in the pulp of the damaged tissue after the apple had been bruised. The tissue damage was centered in the cell death zone and developed laterally, with the width of the damage increasing with injury time. The extent of tissue damage in the core and pericarpal directions varied. About 60% of the damaged tissue developed in the core direction and 40% in the pericarpal direction, and the damage ratios in both directions remained consistent throughout the injury. The depth of damage and the rate of damage were influenced by the impact force size and the difference in the size of the damaged part of the apple, but the damage development pattern was independent of the impact force size and the difference in the damaged part. The maximum damage rate was reached at about 30 min, and the depth of damage was stabilized at about 72 min. By studying the evolution pattern of the damaged tissue of the bruised 'Red Delicious' apple, it provides the research idea and theoretical basis for enhancing the prediction accuracy and robustness of early stage damage in apples.

Vegetable and fruit freshness detection based on deep features and principal component analysis

Vegetable and fruit freshness detecting can ensure that consumers get vegetables and fruits with good taste and rich nutrition, improve the health level of diet, and ensure that the agricultural and food industries provide high-quality products to meet consumer needs and increase sales and market share. At present, the freshness detection of vegetables and fruits mainly relies on manual observation and judgment, which has the problems of subjectivity and low accuracy, and it is difficult to meet the needs of large-scale, high-efficiency, and rapid detection. Although some studies have shown that large-scale detection of vegetable and fruit freshness can be carried out based on artificially extracted features, there is still the problem of poor adaptability of artificially extracted features, which leads to low efficiency of freshness detection. To solve this problem, this paper proposes a novel method for detecting the freshness of vegetables and fruits more objectively, accurately and efficiently using deep features extracted by pre-trained deep learning models of different architectures. First, resized images of vegetables and fruits are fed into a pre-trained deep learning model for deep feature extraction. Then, the deep features are fused and the fused deep features are dimensionally reduced to a representative low-dimensional feature space by principal component analysis. Finally, vegetable and fruit freshness are detected by three machine learning methods. The experimental results show that combining the deep features extracted by the three architecture pre-trained deep learning models GoogLeNet, DenseNet-201 and ResNeXt-101 combined with PCA dimensionality reduction processing has achieved the highest accuracy rate of 96.98% for vegetable and fruit freshness detection. This research concluded that the proposed method is promising to improve the efficiency of freshness detection of vegetables and fruits.

Prediction of Date Fruit Quality Attributes during Cold Storage Based on Their Electrical Properties Using Artificial Neural Networks Models

Evaluating and predicting date fruit quality during cold storage is critical for ensuring a steady supply of high-quality fruits to meet market demands. The traditional destructive methods take time in the laboratory, and the results are based on one specific parameter being tested. Modern modeling techniques, such as Machine Learning (ML) algorithms, offer unique benefits in nondestructive methods for food safety detection and predicting quality attributes. In addition, the electrical properties of agricultural products provide crucial information about the interior structures of biological tissues and their physicochemical status. Therefore, this study aimed to use an alternative approach to predict physicochemical properties, i.e., the pH, total soluble solids (TSS), water activity (a_w), and moisture content (MC) of date fruits (Tamar), during cold storage based on their electrical properties using Artificial Neural Networks (ANNs), which is the most popular ML technique. Ten date fruit cultivars were studied to collect data for the targeted parameters at different cold storage times (0, 2, 4, and 6 months) to train and test the ANNs models. The electrical properties of the date fruits were measured using a high-precision LCR (inductance, capacitance, and resistance) meter from 10 Hz to 100 kHz. The ANNs models were compared with a Multiple Linear Regression (MLR) at all testing frequencies of the electrical properties. The MLR models were less accurate than ANNs models in predicting fruit pH and had low performance and weak predictive ability for the TSS, a_w, and MC at all testing frequencies. The optimal ANNs prediction model consisted of the input layer with 14 neurons, one hidden layer with 15 neurons, and the output layer with 4 neurons, which was determined depending on the measurements of the electrical properties at a 10 kHz testing frequency. This optimal ANNs model was able to predict the pH with R² = 0.938 and RMSE = 0.121, TSS with R² = 0.954 and RMSE = 2.946, a_w with R² = 0.876 and RMSE = 0.020, and MC with R² = 0.855 and RMSE = 0.803 b by using the measured electrical properties. The developed ANNs model is a powerful tool for predicting fruit quality attributes after learning from the experimental measurement parameters. It can be suggested to efficiently predict the pH, total soluble solids, water activity, and moisture content of date fruits based on their electrical properties at 10 kHz.