Deep learning-based robust analysis of laser bio-speckle data for detection of fungal-infected soybean seeds

↓ Direkt till sidans innehåll
↓ Direkt till sidans sekundära innehåll (sidomenyn)

Sökning: id:"swepub:oai:DiVA.org:hv-20675" > Deep learning-based...

1 av 1
Föregående post
Nästa post
Till träfflistan

Kaler, NikhilSignals and Software Group, Discipline of Electrical Engineering & Centre for Advance Electronics, Indian Institute of Technology Indore (IIT Indore) (IND) (författare)

Deep learning-based robust analysis of laser bio-speckle data for detection of fungal-infected soybean seeds

Artikel/kapitelEngelska2023

Förlag, utgivningsår, omfång ...

IEEE,2023
electronicrdacarrier

Nummerbeteckningar

LIBRIS-ID:oai:DiVA.org:hv-20675
https://urn.kb.se/resolve?urn=urn:nbn:se:hv:diva-20675URI
https://doi.org/10.1109/ACCESS.2023.3305273DOI

Kompletterande språkuppgifter

Språk:engelska
Sammanfattning på:engelska

Ingår i deldatabas

SwePubSwePub

Klassifikation

Ämneskategori:ref swepub-contenttype
Ämneskategori:art swepub-publicationtype

Anmärkningar

CC BY 4.0This work was supported by Government of India, being implemented by Digital India Corporation, and Science and Engineering ResearchBoard project grant (CRG/2021/001215 and CRG/2018/002697), and the staff and student mobility funded by Erasmus+ project betweenIIT Indore and University West.
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.

Ämnesord och genrebeteckningar

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
Agriculture
Bio-speckle
Convolutional neural network
Deep learning
Long-short term memory
Neural network
Noise
Photonics
Seed-borne fungi

Biuppslag (personer, institutioner, konferenser, titlar ...)

Bhatia, VimalSignals 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) (författare)
Kumar Mishra, AmitHögskolan Väst,Avdelningen för Matematik, Data- och Lantmäteriteknik,Department of Electrical Engineering, University of Cape Town, Cape Town (ZAF)(Swepub:hv)amimis (författare)
Signals and Software Group, Discipline of Electrical Engineering & Centre for Advance Electronics, Indian Institute of Technology Indore (IIT Indore) (IND)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) (creator_code:org_t)

Sammanhörande titlar

Ingår i:IEEE Access: IEEE11, s. 89331-893482169-3536

Internetlänk

Hitta via bibliotek

IEEE Access (Sök värdpublikationen i LIBRIS)

Till lärosätets databas

1 av 1
Föregående post
Nästa post
Till träfflistan

Hitta mer i SwePub

Av författaren/redakt...: Kaler, Nikhil; Bhatia, Vimal; Kumar Mishra, Am ...

Om ämnet

LANTBRUKSVETENSKAPER: LANTBRUKSVETENSK ...; och Bioteknologi med ...; och Genetik och förä ...

Artiklar i publikationen: IEEE Access

Av lärosätet: Högskolan Väst

Sök utanför SwePub

Sök vidare i:: Google; Google Book Search; Google Scholar

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

LIBRIS.kb.se