Swin-MLP: a strawberry appearance quality identification method by Swin Transformer and multi-layer perceptron

Zheng, Hao; Wang, Guo Hui; Li, Xuchen

doi:10.1007/s11694-022-01396-0

Cited by 46 publications

(26 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In general, during storage, softening and waterlogging of the tissue in a small area on the surface of strawberries will initially occur, giving the appearance of a bruise (Choi et al, 2021); the area will then be susceptible to mold invasion and further spoilage (Cristiana et al, 2014). The methods of categorization proposed by Li et al (2022) and Zheng et al (2022) were used with modifications. The tissue on the surface was recorded as soft and wet when softened and waterlogged over a diameter of 0.5 cm; mold growth observed over an area more than 0.5 cm in diameter was recorded as decayed.…”

Section: Methodsmentioning

confidence: 99%

“…Well‐known as a popular fruit, strawberries are a high‐value and health‐promoting agricultural product. Their high nutritional value is due to their biologically active compounds and essential nutrients associated with health benefits (Amoriello et al, 2022; Yan et al, 2021; Zheng et al, 2022). At the same time, their unique taste makes them a fruit that has gained widespread popularity among consumers from around the globe (Bhat et al, 2015; Yan et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A new strategy to design novel modified atmosphere packaging formulation maintains the qualities of postharvest strawberries (Fragaria ananassa) during low‐temperature storage

Cheng,

Huang,

Chan

et al. 2023

Journal of Food Safety

View full text Add to dashboard Cite

For fresh foods, the purpose and benefits of modified atmosphere packaging (MAP) generally include the preservation of antioxidants, the extension of shelf life, deferral of microbial spoilage, and retention of product color. Commercial MAP products frequently involve a mixture of nitrogen, oxygen, and carbon dioxide, affecting consumer acceptability, cost‐effectiveness, and hygienic food safety issues. This study investigated a novel active MAP formulation for strawberries in retail packaging which ensures changes in quality‐related physicochemical characteristics [including hardness, moisture, vitamin C, total soluble solids (TSS), titratable acid, and appearance] during low‐temperature storage, whereas samples of different storage times were assessed for shelf life by sensory evaluation. The innovative active MAP formulation of 0.8 g of sodium ascorbate, 2.6 g of sodium carbonate, and 1.6 g of ferrous sulfate achieved atmosphere equilibrium in packaged strawberries in <48 h, compared to 5–6 days in the control group. Strawberries treated with active MAP maintained their moisture, firmness, vitamin C, TSS, and titratable acid contents better than the control group (p < 0.05). The strawberries showed softening and waterlogging of tissue and 50% moldiness by the 14th day, while the control group lost commercial value by the 8th. New applications of similar commodities in food are unavailable based on current knowledge. Therefore, the scope of fresh food applications covered in this study and the refinement of other functions will be helpful directions for future research.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A new strategy to design novel modified atmosphere packaging formulation maintains the qualities of postharvest strawberries (Fragaria ananassa) during low‐temperature storage

Cheng,

Huang,

Chan

et al. 2023

Journal of Food Safety

View full text Add to dashboard Cite

show abstract

“…MLP is a feedforward artificial neural network-based supervised learning model [ 34 ]. The artificial neural network uses many representation layers to process the data.…”

Section: Study Methodologymentioning

confidence: 99%

Predicting microbe organisms using data of living micro forms of life and hybrid microbes classifier

et al. 2023

View full text Add to dashboard Cite

Microbe organisms make up approximately 60% of the earth’s living matter and the human body is home to millions of microbe organisms. Microbes are microbial threats to health and may lead to several diseases in humans like toxoplasmosis and malaria. The microbiological toxoplasmosis disease in humans is widespread, with a seroprevalence of 3.6-84% in sub-Saharan Africa. This necessitates an automated approach for microbe organisms detection. The primary objective of this study is to predict microbe organisms in the human body. A novel hybrid microbes classifier (HMC) is proposed in this study which is based on a decision tree classifier and extra tree classifier using voting criteria. Experiments involve different machine learning and deep learning models for detecting ten different living microforms of life. Results suggest that the proposed HMC approach achieves a 98% accuracy score, 98% geometric mean score, 97% precision score, and 97% Cohen Kappa score. The proposed model outperforms employed models, as well as, existing state-of-the-art models. Moreover, the k-fold cross-validation corroborates the results as well. The research helps microbiologists identify the type of microbe organisms with high accuracy and prevents many diseases through early detection.

show abstract

“…Wang et al (2022) enabled the identification and counting of typical apple pests based on the improved Faster R‐CNN. Zheng et al (2022) proposed a strawberry appearance quality recognition method based on Swin Transformer and multilayer perceptron.…”

Section: Introductionmentioning

confidence: 99%

Tomato leaf disease recognition based on improved convolutional neural network with attention mechanism

Zhou

Zhao

et al. 2023

Plant Pathology

View full text Add to dashboard Cite

Plant diseases are common factors restricting crop yield and quality. For individuals without training, it is still difficult to identify various diseases accurately because many leaf diseases are similar in colour, shape and other aspects. Requiring an expert diagnosis can cause delays and lead to increasing costs. Therefore, this paper proposes an improved convolutional neural network for recognition of tomato leaf diseases. The experimental dataset was from the publicly available dataset PlantVillage. Based on the original ResNet18 model, a new convolutional neural network, TomatoNet, was constructed by adding a squeeze‐and‐excitation module and modifying the classifier structure. The results show that the average recognition accuracy of the TomatoNet network is 99.63%, which is 0.53% higher than the ResNet18 network. In addition, the recognition accuracy improved from 88.97% to 98.35% after the improvement of the AlexNet network. Finally, the superiority of TomatoNet was verified by comparison with other advanced models. This experiment verifies the feasibility of a deep learning algorithm for plant leaf disease recognition, which can provide a more efficient and convenient solution for detecting plant leaf disease.

show abstract

Swin-MLP: a strawberry appearance quality identification method by Swin Transformer and multi-layer perceptron

Cited by 46 publications

References 49 publications

A new strategy to design novel modified atmosphere packaging formulation maintains the qualities of postharvest strawberries (Fragaria ananassa) during low‐temperature storage

A new strategy to design novel modified atmosphere packaging formulation maintains the qualities of postharvest strawberries (Fragaria ananassa) during low‐temperature storage

Predicting microbe organisms using data of living micro forms of life and hybrid microbes classifier

Tomato leaf disease recognition based on improved convolutional neural network with attention mechanism

Contact Info

Product

Resources

About