Search: onr:"swepub:oai:DiVA.org:hv-20675" >
Deep learning-based...
Deep learning-based robust analysis of laser bio-speckle data for detection of fungal-infected soybean seeds
-
- Kaler, Nikhil (author)
- Signals and Software Group, Discipline of Electrical Engineering & Centre for Advance Electronics, Indian Institute of Technology Indore (IIT Indore) (IND)
-
- Bhatia, Vimal (author)
- Signals and Software Group, Discipline of Electrical Engineering & Centre for Advance Electronics, Indian Institute of Technology Indore (IIT Indore) (IND); Faculty of Informatics and Management, University of Hradec Kralove, 50003 Hradec Kralove (CZE); School of Electronic and Information Engineering, Soochow University, Suzhou (CHN)
-
- Kumar Mishra, Amit (author)
- Högskolan Väst,Avdelningen för Matematik, Data- och Lantmäteriteknik,Department of Electrical Engineering, University of Cape Town, Cape Town (ZAF)
-
(creator_code:org_t)
- IEEE, 2023
- 2023
- English.
-
In: IEEE Access. - : IEEE. - 2169-3536. ; 11, s. 89331-89348
- Related links:
-
https://doi.org/10.1...
-
show more...
-
https://hv.diva-port... (primary) (Raw object)
-
https://urn.kb.se/re...
-
https://doi.org/10.1...
-
show less...
Abstract
Subject headings
Close
- T Seed-borne diseases play a crucial role in affecting the overall quality of seeds, efficient disease management, and crop productivity in agriculture. Detection of seed-borne diseases using machine learning (ML) and deep learning (DL) can automate the process at large-scale industrial applications for providinghealthy and high-quality seeds. ML-based methods are accurate for detecting and classifying fungal infectionin seeds; however, their performance degrades in the presence of noise. In this work, we propose a laser biospeckle based DL framework for detection and classification of disease in seeds under varying experimental parameters and noises. We develop a DL-based spatio-temporal analysis technique for bio-speckle data using DL networks, including neural networks (NN), convolutional neural networks (CNN) with long-short-termmemory (LSTM), three-dimensional convolutional neural networks (3D CNN), and convolutional LSTM (ConvLSTM). The robustness of the DL models to noise is a key aspect of this spatio-temporal analysis.In this study, we find that the ConvLSTM model has an accuracy of 97.72% on the test data and is robust to different types of noises with an accuracy of 97.72%, 94.31%, 98.86%, and 96.59% . Furthermore, the robust model (ConvLSTM) is evaluated for variations in experimental data parameters such as frame rate, frame size, and number of frames used. This model is also sensitive towards detecting bio-speckle activity of different order, and it shows average test accuracy of 99% for detecting four different classes.
Subject headings
- LANTBRUKSVETENSKAPER -- Bioteknologi med applikationer på växter och djur -- Genetik och förädling inom lantbruksvetenskap (hsv//swe)
- AGRICULTURAL SCIENCES -- Agricultural Biotechnology -- Genetics and Breeding in Agricultural Sciences (hsv//eng)
Keyword
- Agriculture
- Bio-speckle
- Convolutional neural network
- Deep learning
- Long-short term memory
- Neural network
- Noise
- Photonics
- Seed-borne fungi
Publication and Content Type
- ref (subject category)
- art (subject category)
Find in a library
To the university's database