Search

Your search keyword '"Feng Yanfang"' showing total 543 results
Start Over Author "Feng Yanfang"
543 results on '"Feng Yanfang"'

1. A trajectory planning method for DELTA sorting robot in tomato production line based on improved gate shaped trajectory

Author

FENG Yanfang, WU Birui, and ZHAO Qian

Subjects
delta robot, tomato sorting, processing production line, gate shaped trajectory, ant colony optimization algorithm, time optimal, Food processing and manufacture, TP368-456
Abstract

Objective: To solve the problems of low efficiency and poor motion stability of DELTA robots in the tomato sorting process of existing tomato processing production lines. Methods: Based on the analysis of the DELTA robot sorting system, the optimized gate shaped trajectory of the cyclotron was used for DELTA robot trajectory planning. By replacing the right angle part of the gate shaped trajectory with a convolutional line, an optimization model with the goal of time optimization was established. The optimized parameters of the gate shaped trajectory were solved using an improved ant colony optimization algorithm. Analyzed its performance through experiments. Results: The proposed method had better average sorting time and sorting success rate compared to the gate shaped trajectory and other methods, with an average sorting time reduction of 11.61% and 1.63%, respectively, and a sorting success rate increase of 2.05% and 0.56%. Conclusion: The proposed planning method effectively improves the sorting accuracy and efficiency of DELTA robots.

Published
2023
Full Text
View/download PDF

5. Segmentation Ability Map: Interpret deep features for medical image segmentation

Author

He, Sheng, Feng, Yanfang, Grant, P. Ellen, and Ou, Yangming

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition
Abstract

Deep convolutional neural networks (CNNs) have been widely used for medical image segmentation. In most studies, only the output layer is exploited to compute the final segmentation results and the hidden representations of the deep learned features have not been well understood. In this paper, we propose a prototype segmentation (ProtoSeg) method to compute a binary segmentation map based on deep features. We measure the segmentation abilities of the features by computing the Dice between the feature segmentation map and ground-truth, named as the segmentation ability score (SA score for short). The corresponding SA score can quantify the segmentation abilities of deep features in different layers and units to understand the deep neural networks for segmentation. In addition, our method can provide a mean SA score which can give a performance estimation of the output on the test images without ground-truth. Finally, we use the proposed ProtoSeg method to compute the segmentation map directly on input images to further understand the segmentation ability of each input image. Results are presented on segmenting tumors in brain MRI, lesions in skin images, COVID-related abnormality in CT images, prostate segmentation in abdominal MRI, and pancreatic mass segmentation in CT images. Our method can provide new insights for interpreting and explainable AI systems for medical image segmentation. Our code is available on: \url{https://github.com/shengfly/ProtoSeg}.

Published
2022

6. Deep Relation Learning for Regression and Its Application to Brain Age Estimation

Author

He, Sheng, Feng, Yanfang, Grant, P. Ellen, and Ou, Yangming

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Most deep learning models for temporal regression directly output the estimation based on single input images, ignoring the relationships between different images. In this paper, we propose deep relation learning for regression, aiming to learn different relations between a pair of input images. Four non-linear relations are considered: "cumulative relation", "relative relation", "maximal relation" and "minimal relation". These four relations are learned simultaneously from one deep neural network which has two parts: feature extraction and relation regression. We use an efficient convolutional neural network to extract deep features from the pair of input images and apply a Transformer for relation learning. The proposed method is evaluated on a merged dataset with 6,049 subjects with ages of 0-97 years using 5-fold cross-validation for the task of brain age estimation. The experimental results have shown that the proposed method achieved a mean absolute error (MAE) of 2.38 years, which is lower than the MAEs of 8 other state-of-the-art algorithms with statistical significance (p$<$0.05) in paired T-test (two-side).

Published
2022

Catalog

Books, media, physical & digital resources
See catalog results