A novel air-suction classifier for fresh sphere fruits in pneumatic bulk grading

Cao, Miaolong; Zhang, Jinli; Sun, Yingjuan; Zhu, Jiayi; Hu, Yong

doi:10.1007/s11694-023-01878-9

Cited by 3 publications

(2 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditional methods frequently fail to capture the intricate patterns and variations present in fruit images, resulting in suboptimal classification and grading outcomes. In addition, these methods are incapable of learning and adapting to their surroundings, which hinders their overall performance levels like in the case of Convolutional Neural Networks (CNNs) [4,5,6]. This paper presents a novel approach that combines the power of Deep Q Learning (DQL) for classification and Logistic Regression (LR) with Deep Forests for fruit grading in order to address these challenges.…”

Section: Introductionmentioning

confidence: 99%

DQLRFMG: Design of an Augmented Fusion of Deep Q Learning with Logistic Regression and Deep Forests for Multivariate Classification and Grading of Fruits

Said,

Joshi

2023

IJRITCC

View full text Add to dashboard Cite

Accurate categorization and grading of fruits are essential in numerous fields, including agriculture, food processing, and distribution. This paper addresses the need for an advanced model capable of classifying and grading fruits more effectively than existing methods. Traditional approaches are limited by their lower precision, accuracy, recall, area under the curve (AUC), and delay. In order to overcome these obstacles, the proposed model combines the capabilities of Deep Q Learning (DQL) for classification and Logistic Regression (LR) with Deep Forests for fruit grading process. Three distinct datasets were used to evaluate the model: the Kaggle - Fruits 360 Dataset, the FRont Experimental System for High throughput plant phenotyping Datasets, and ImageNet samples. In multiple respects, comparative analysis demonstrates that the proposed model outperforms existing methods. Specifically, it achieves a remarkable 4.9% improvement in precision, 5.5% improvement in accuracy, 4.5% improvement in recall, 3.9% improvement in AUC, and an 8.5% reduction in delay levels. Utilizing the strengths of both DQL and LR with Deep Forests, the proposed model achieves its superior performance. DQL, a technique for reinforcement learning, provides the ability to learn and make decisions based on the feedback from the environment. By combining DQL and LR, the classification accuracy is improved, allowing for the precise identification of fruit varieties including Mango, Apple. Papaya, etc. In addition, Deep Forests, a novel framework for ensemble learning, is utilized for fruit grading. Deep Forests utilizes decision trees to effectively capture complex patterns in the data, allowing for dependable and robust fruit grading. Experimental findings indicate that the combination of DQL and LR with Deep Forests yields remarkable performance improvements in fruit classification and grading tasks. Improved precision, accuracy, recall, AUC, and delay indicate the model's superiority over existing methods. This research contributes to the field of fruit classification and grading by developing a sophisticated model that can support a variety of applications in the agriculture, food processing, and distribution industries.

show abstract

Section: Introductionmentioning

confidence: 99%

DQLRFMG: Design of an Augmented Fusion of Deep Q Learning with Logistic Regression and Deep Forests for Multivariate Classification and Grading of Fruits

Said,

Joshi

2023

IJRITCC

View full text Add to dashboard Cite

show abstract

“…It is also helpful for the prevention of pests and mechanical damage. Typical studies include Cao et al (2023), who developed a suction ball fruit grader that achieves grading by pneumatic movement according to the size and quality of the fruit, but it may cause different degrees of damage to the skin of the fruits. Kumari et al (2022) developed an intelligent automated grading system for mango, which can classify fruits into precise grades, but the grading process is long and is not suitable for industrial production.…”

mentioning

confidence: 99%

A grader for fresh jujube with electromagnetic synchronous actuator assembly

Zhang,

Yu,

Kang

et al. 2024

J Food Process Engineering

View full text Add to dashboard Cite

In recent years, the post‐harvest commercialization of fresh jujube sorting technology is backward, the efficiency of manual grading is low, and the application of machine vision technology in fruit grading has been a research hotspot. To improve the grading accuracy and speed of the fresh jujube machine vision grading machine, this study designs a method of fresh jujube machine vision grading using an electromagnetic synchronous actuator. The grading machine consists of an automatic distribution and arrangement system, an image acquisition and processing system, and a synchronous actuator assembly, which uses a sensitive electromagnet to adsorb a silicon steel switching buckling plate to execute the action. The image processing process includes an image color component, Sobel operator filtering, Otsu method binarization, and ellipse fitting to extract the color and size eigenvalues. The experimental results show that the date images can be acquired quickly and processed accurately with a processing speed of 50 ms per frame. In addition, the proposed actuator can be sensitively triggered with a response time of 40 ms. The grader successfully classified jujube into five size classes and one color class. The grading accuracy and non‐destructive rate reached 93.7% and 100%, respectively. The grading efficiency is 20 jujubes per second, with a maximum production rate of 1400 kilograms per hour. This grading machine realizes the requirements of high accuracy, high speed, and non‐destructive grading of fresh jujube and provides an important technical and theoretical basis for the development of machine vision jujube rapid grading technology.Practical applicationsIn recent years, sorting technology in the post‐harvest commercialization of fruits has been outdated, and manual grading has been inefficient. The application of machine vision technology in fruit grading has been a research hotspot in recent years. This study designs a machine vision grading of fresh dates with an electromagnetic synchronous actuator. The grader was composed of a roller conveyor, synchronous actuator assembly, image main processor, and actuator controlling co‐processor. Experimental results indicated that jujube images could be acquired rapidly and processed accurately, with a processing speed of 50 ms per frame. In addition, the proposed actuator could be sensitively triggered with a response time of 40 ms. Finally, the grader successfully sorted jujubes into five size classes and one color class. The grading accuracy rate and non‐destructive rate reached 93.7% and 100%, respectively. The grading efficiency was 20 jujubes per second, and the maximum productivity was 1400 kg/h.

show abstract

Empirical investigation of parameter impacts on the three-dimensional coefficient of restitution of jujube at the time of harvest

Yao,

An,

Bai

et al. 2024

Postharvest Biology and Technology

View full text Add to dashboard Cite

A novel air-suction classifier for fresh sphere fruits in pneumatic bulk grading

Cited by 3 publications

References 29 publications

DQLRFMG: Design of an Augmented Fusion of Deep Q Learning with Logistic Regression and Deep Forests for Multivariate Classification and Grading of Fruits

DQLRFMG: Design of an Augmented Fusion of Deep Q Learning with Logistic Regression and Deep Forests for Multivariate Classification and Grading of Fruits

A grader for fresh jujube with electromagnetic synchronous actuator assembly

Empirical investigation of parameter impacts on the three-dimensional coefficient of restitution of jujube at the time of harvest

Contact Info

Product

Resources

About