Fruit Classification Model Based on Residual Filtering Network for Smart Community Robot

Chen, Yulin; Sun, Hailing; Zhou, Guofu; Bao, Peng

doi:10.1155/2021/5541665

Cited by 6 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the design of the sorting car, high stability and reliability were required. During the movement of the main ring, it was necessary to keep the car running smoothly when it was not sorting, and the movement was timely and smooth when it was sorting [21,22]. Sorting car was mainly composed of base, support, platform plate, door plate, spring rod, bevel gear, and so on.…”

Section: Design Of Camera Bracketmentioning

confidence: 99%

Intelligent Optimization Design of Automatic Sorting Robot Process

Liu

Wang

2022

Journal of Sensors

View full text Add to dashboard Cite

In order to further improve the efficiency of sorting robots, an algorithm based on artificial intelligence design is evaluated. On the basis of determining the design requirements of belt conveyor and motor selection, the reverse device and return device and camera bracket sorting car are redesigned, and the sorting car is further analyzed by finite element method. All programs are written based on PLC. The results show that the recognition and sorting rate of 100 express surface orders with the same specifications reaches 100% and the sorting rate reaches 94% by analyzing the data recorded in the database, and the average time consumed in each recognition process is 0.0493097 s and 0.047133 s, respectively, in basic and simulated recognition. The difference did not exceed 0.01 s, and the time was basically the same. Therefore, the scheme verifies the rationality of mechanical structure design, visual scheme design, and control system design.

show abstract

Section: Design Of Camera Bracketmentioning

confidence: 99%

Intelligent Optimization Design of Automatic Sorting Robot Process

Liu

Wang

2022

Journal of Sensors

View full text Add to dashboard Cite

show abstract

“…In practical applications, a simplified Shadowing model is often used, as shown in the following equation [12]:…”

Section: Indoor Positioning Methodmentioning

confidence: 99%

“…Except for the variable x in (12), they are all constants or can be obtained directly by the microcontroller. is equation is the general form of a quadratic equation in one variable, which can be expressed as follows [19]:…”

Section: Indoor Positioning Methodmentioning

confidence: 99%

Indoor Positioning Technology and Control of Mobile Home Service Robot

Wang

Wen

Zhou

2022

Scientific Programming

View full text Add to dashboard Cite

With the rapid development of the market economy, location information services have shifted from outdoor to indoor, requiring higher system accuracy. Indoor positioning and control is an indispensable technical support for mobile home service robots to perform system tasks, and this technology is also an important parameter that marks the level of intelligence of a home service robot. However, in indoor places, how to obtain the target node location information timely and accurately and how to control and path planning should be the first issues to be considered in the design of home robots at this stage. This article gave a brief overview of the current indoor positioning technology and control, analyzed the more widely and frequently used indoor positioning methods, and deeply studied the ultrasonic positioning technology. On this basis, a mobile home service robot system was designed, and simulation experiments were carried out, respectively, to test the receiving time and arrival time of the node signal, the node positioning accuracy, the optimal degree of route planning, and the absolute and relative errors of navigation and path estimation. The experimental results showed that the accuracy of the robot system positioning proposed in this article reached more than 80%, and the relative error was only 4.21%, which verified its feasibility and effectiveness in practical applications. Popularizing it in the market can effectively improve the system performance and intelligence of home service robots.

show abstract

“…The study compared five models, the hybrid model between VGGNet with SVM achieved a higher accuracy of 92.1% than others. The study in [19] performed similar work to [18] by adding the residual filter network for feature enhancement into the hybrid network (CNN-SVM), with the proposed model attaining an overall accuracy of 99% against others.…”

Section: Related Workmentioning

confidence: 99%

Tomato Quality Classification Based on Transfer Learning Feature Extraction and Machine Learning Algorithm Classifiers

Mputu,

Abdel-Mawgood,

Shimada

et al. 2024

IEEE Access

View full text Add to dashboard Cite

The demand for high-quality tomatoes to meet consumer and market standards, combined with large-scale production, has necessitated the development of an inline quality grading. Since manual grading is time-consuming, costly, and requires a substantial amount of labor. This study introduces a novel approach for tomato quality sorting and grading, focusing specifically on the color feature of tomato images. The method leverages pre-trained convolutional neural networks (CNNs) for feature extraction and traditional machine-learning algorithms for classification (hybrid model). The single-board computer NVIDIA Jetson TX1 was used to create a tomato image dataset. Image preprocessing and fine-tuning techniques were applied to enable deep layers to learn and concentrate on complex and significant features. The extracted features were then classified using traditional machine learning algorithms namely: support vector machines (SVM), random forest (RF), and k-nearest neighbors (KNN) classifiers. Among the proposed hybrid models, the CNN-SVM method has outperformed other hybrid approaches, attaining an accuracy of 97.50% in the binary classification of tomatoes as healthy or rejected and 96.67% in the multiclass classification of them as ripe, unripe, or rejected when Inceptionv3 was used as feature extractor. Once another dataset (public dataset) was used, the proposed hybrid model CNN-SVM achieved an accuracy of 97.54% in categorizing tomatoes as ripe, unripe, old, or damaged outperforming other hybrid models when Inceptionv3 was used as a feature extractor. The performance metrics accuracy, recall, precision, specificity, and F1-score of the best-performing proposed hybrid model were evaluated.INDEX TERMS Grading, feature extraction, machine learning algorithms, tomato, and image preprocessing.

show abstract

Fruit Classification Model Based on Residual Filtering Network for Smart Community Robot

Cited by 6 publications

References 24 publications

Intelligent Optimization Design of Automatic Sorting Robot Process

Intelligent Optimization Design of Automatic Sorting Robot Process

Indoor Positioning Technology and Control of Mobile Home Service Robot

Tomato Quality Classification Based on Transfer Learning Feature Extraction and Machine Learning Algorithm Classifiers

Contact Info

Product

Resources

About