Jiying Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Jiying Li has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Jianping Hu
Michigan State University-Department of Energy Plant Research Laboratory, Michigan State University , 612 Wilson Road, East Lansing, MI 48824
2 shared publications Alyssa L. Preiser
Michigan State University-Department of Energy Plant Research Laboratory, Michigan State University, East Lansing, Michigan 48824
1 shared publication- Anne C. Rea
MSU-DOE Plant Research LaboratoryMichigan State UniversityEast Lansing, Michigan
1 shared publication David M. Kramer
Michigan State University-Department of Energy Plant Research Laboratory, Michigan State University, East Lansing, Michigan 48824
1 shared publicationDeserah D. Strand
Michigan State University-Department of Energy Plant Research Laboratory, Michigan State University, East Lansing, Michigan 48824
1 shared publication- Ding Yongjun
School of Electronic Automation, Jiangxi University of Science and Technology, Ganzhou, China
1 shared publication
Latest Publications
- Open Access
- 14 May 2021
- Published by Oxford University Press (OUP) in Plant Physiology
- Vol. 186 (4) , 1786-1799
DeepLearnMOR: a deep-learning framework for fluorescence image-based classification of organelle morphology
The proper biogenesis, morphogenesis, and dynamics of subcellular organelles are essential to their metabolic functions. Conventional techniques for identifying, classifying, and quantifying abnormalities in organelle morphology are largely manual and time-consuming, and require specific expertise. Deep learning has the potential to revolutionize image-based screens by greatly improving their scope, speed, and efficiency. Here, we used transfer learning and a convolutional neural network (CNN) to analyze over 47,000 confocal microscopy images from Arabidopsis wild-type and mutant plants with abnormal division of one of three essential energy organelles: chloroplasts, mitochondria, or peroxisomes. We have built a deep-learning framework, DeepLearnMOR (Deep Learning of the Morphology of Organelles), which can rapidly classify image categories and identify abnormalities in organelle morphology with over 97% accuracy. Feature visualization analysis identified important features used by the CNN to predict morphological abnormalities, and visual clues helped to better understand the decision-making process, thereby validating the reliability and interpretability of the neural network. This framework establishes a foundation for future larger-scale research with broader scopes and greater data set diversity and heterogeneity.
- 14 May 2021
- Published by Oxford University Press (OUP) in Plant Physiology
- Vol. 186 (4) , 1786-1799
Open AccessDeepLearnMOR: a deep-learning framework for fluorescence image-based classification of organelle morphology
The proper biogenesis, morphogenesis, and dynamics of subcellular organelles are essential to their metabolic functions. Conventional techniques for identifying, classifying, and quantifying abnormalities in organelle morphology are largely manual and time-consuming, and require specific expertise. Deep learning has the potential to revolutionize image-based screens by greatly improving their scope, speed, and efficiency. Here, we used transfer learning and a convolutional neural network (CNN) to analyze over 47,000 confocal microscopy images from Arabidopsis wild-type and mutant plants with abnormal division of one of three essential energy organelles: chloroplasts, mitochondria, or peroxisomes. We have built a deep-learning framework, DeepLearnMOR (Deep Learning of the Morphology of Organelles), which can rapidly classify image categories and identify abnormalities in organelle morphology with over 97% accuracy. Feature visualization analysis identified important features used by the CNN to predict morphological abnormalities, and visual clues helped to better understand the decision-making process, thereby validating the reliability and interpretability of the neural network. This framework establishes a foundation for future larger-scale research with broader scopes and greater data set diversity and heterogeneity.
- 18 March 2019
- Published by Oxford University Press (OUP) in Plant Physiology
- Vol. 180 (2) , 783-792
A Cytosolic Bypass and G6P Shunt in Plants Lacking Peroxisomal Hydroxypyruvate Reductase
The oxygenation of ribulose 1,5-bisphosphate by Rubisco is the first step in photorespiration and reduces the efficiency of photosynthesis in C3 plants. Our recent data indicate that mutants in photorespiration have increased rates of photosynthetic cyclic electron flow around photosystem I. We investigated mutant lines lacking peroxisomal hydroxypyruvate reductase to determine if there are connections between 2-phosphoglycolate accumulation and cyclic electron flow in Arabidopsis (Arabidopsis thaliana). We found that 2-phosphoglycolate is a competitive inhibitor of triose phosphate isomerase, an enzyme in the Calvin-Benson cycle that converts glyceraldehyde 3-phosphate to dihydroxyacetone phosphate. This block in metabolism could be overcome if glyceraldehyde 3-phosphate is exported to the cytosol, where cytosolic triose phosphate isomerase could convert it to dihydroxyacetone phosphate. We found evidence that carbon is reimported as glucose-6-phosphate, forming a cytosolic bypass around the block of stromal triose phosphate isomerase. However, this also stimulates a glucose-6-phosphate shunt, which consumes ATP, which can be compensated by higher rates of cyclic electron flow.
- 18 March 2019
- Published by Oxford University Press (OUP) in Plant Physiology
- Vol. 180 (2) , 783-792
A Cytosolic Bypass and G6P Shunt in Plants Lacking Peroxisomal Hydroxypyruvate Reductase
The oxygenation of ribulose 1,5-bisphosphate by Rubisco is the first step in photorespiration and reduces the efficiency of photosynthesis in C3 plants. Our recent data indicate that mutants in photorespiration have increased rates of photosynthetic cyclic electron flow around photosystem I. We investigated mutant lines lacking peroxisomal hydroxypyruvate reductase to determine if there are connections between 2-phosphoglycolate accumulation and cyclic electron flow in Arabidopsis (Arabidopsis thaliana). We found that 2-phosphoglycolate is a competitive inhibitor of triose phosphate isomerase, an enzyme in the Calvin-Benson cycle that converts glyceraldehyde 3-phosphate to dihydroxyacetone phosphate. This block in metabolism could be overcome if glyceraldehyde 3-phosphate is exported to the cytosol, where cytosolic triose phosphate isomerase could convert it to dihydroxyacetone phosphate. We found evidence that carbon is reimported as glucose-6-phosphate, forming a cytosolic bypass around the block of stromal triose phosphate isomerase. However, this also stimulates a glucose-6-phosphate shunt, which consumes ATP, which can be compensated by higher rates of cyclic electron flow.
- 1 September 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
A new robust CKF for jammer tracking
The jammer may influence our wartime communication, as well as the result of the war widely. Thus, in order to improve the accuracy of jammer tracking when influenced by outliers, the M-estimated based robust Backward-Smoothing Cubature Kalman filter (MR-BSCKF) is proposed, which the M-Estimation theory and Backward-Smoothing function is introduced into CKF filter frame. Firstly, the Mahalanobis distance is used for the P-Huber equivalent weight function, and then the traditional CKF is improved its performance based on the Backward-Smoothing function. Finally, by combining the secondary filtering with backward-smoothing and the forward, the misjudgement reduced and the filtering accuracy and the robust improved at the same time. MRBSCKF was tested in three different interference situations and the simulation results show the MR-BSCKF's high peerformance compared with the traditional filter.
- 1 September 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
A new robust CKF for jammer tracking
The jammer may influence our wartime communication, as well as the result of the war widely. Thus, in order to improve the accuracy of jammer tracking when influenced by outliers, the M-estimated based robust Backward-Smoothing Cubature Kalman filter (MR-BSCKF) is proposed, which the M-Estimation theory and Backward-Smoothing function is introduced into CKF filter frame. Firstly, the Mahalanobis distance is used for the P-Huber equivalent weight function, and then the traditional CKF is improved its performance based on the Backward-Smoothing function. Finally, by combining the secondary filtering with backward-smoothing and the forward, the misjudgement reduced and the filtering accuracy and the robust improved at the same time. MRBSCKF was tested in three different interference situations and the simulation results show the MR-BSCKF's high peerformance compared with the traditional filter.
- 1 June 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 341-345
The application of Quantum-inspired ant colony algorithm in automatic segmentation of tomato image
The premise realizing intelligent picking tomato is to segment tomato from complex background accurately, the quality of segmentation tomato affects the picking accuracy of the manipulator. Based on this, the paper puts forward a new type of quantum ant colony algorithm, and the traditional quantization bionic intelligent algorithm, using quantum bit probability amplitude of the individual's current location information, increase the search space. Quantum NOT gate is used to realize mutation and depend on the different fitness of individuals with different chaotic disturbance to overcome the single rotation direction of quantum door and the defects of fixed size and avoid falling into local precocious. Compared with the traditional ant colony algorithm, the quantization of ant colony algorithm has a better diversity of population and overcomes the premature stagnation phenomenon effectively in the optimization process. We use the segmentation experiment of 100 tomato images to show this method can not only segment tomato image effectively on condition of natural light but also has been improved greatly on the segmentation speed and precision.
- 1 June 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 341-345
The application of Quantum-inspired ant colony algorithm in automatic segmentation of tomato image
The premise realizing intelligent picking tomato is to segment tomato from complex background accurately, the quality of segmentation tomato affects the picking accuracy of the manipulator. Based on this, the paper puts forward a new type of quantum ant colony algorithm, and the traditional quantization bionic intelligent algorithm, using quantum bit probability amplitude of the individual's current location information, increase the search space. Quantum NOT gate is used to realize mutation and depend on the different fitness of individuals with different chaotic disturbance to overcome the single rotation direction of quantum door and the defects of fixed size and avoid falling into local precocious. Compared with the traditional ant colony algorithm, the quantization of ant colony algorithm has a better diversity of population and overcomes the premature stagnation phenomenon effectively in the optimization process. We use the segmentation experiment of 100 tomato images to show this method can not only segment tomato image effectively on condition of natural light but also has been improved greatly on the segmentation speed and precision.