SSLnDO-Based Deep Residual Network and RV-Coefficient Integrated Deep Fuzzy Clustering for Cotton Crop Classification

Sheela J, Karthika N () and Janet B ()
Additional contact information
Sheela J: Department of SCOPE, School of Computer Science and Engineering, VIT-AP University, Amaravati, India
Karthika N: Department of SCOPE, School of Computer Science and Engineering, VIT-AP University, Amaravati, India
Janet B: ��Department of Computer Applications, National Institute of Technology, Tiruchirappalli, India

International Journal of Information Technology & Decision Making (IJITDM), 2024, vol. 23, issue 01, 381-412

Abstract: The excellent classification accuracy of remote sensory images has led to a major expansion of their use in agricultural field surveillance in recent years. The accurate classification of crop is very significant for agricultural management and food security. There are diverse varieties of crops are available. Among them, each possesses same spectral curves. Due to increasing number of remote sensing information, a major limitation arises in the domain of crop classification is how to determine significant data from huge volume of information to maintain categorization accuracy and implementation time. Consequently, one of the main obstacles in the agricultural industry is the precise classification of crops. Deep Residual Network (ResNet)-based Social Sea Lion Driver Optimization (SSLnDO)-based Deep Fuzzy Clustering (DFC), where the distance is calculated using RV coefficient, are used to develop an effective method for classifying cotton crops. Finally, classification of the cotton crop is successfully accomplished using Deep ResNet, and the network classifier is trained by inserting produced SSLnDO. The vegetation index is generated for each color band independently. Combining the Social Ski Driver (SSD) optimization and the Sea Lion Optimization (SLnO) method yields the newly developed SSLnDO. A maximum testing accuracy of 0.940, a sensitivity of 0.931, and a specificity of 0.926 have been achieved by the designed model. When comparing the accuracy value produced by the proposed method for image-2 to the existing approaches, namely WLI-Fuzzy + BS-Lion NN, OSVM-OCNN, GAN, Hybrid CNN-RF, Deep learning, and Deep ResNet, they are 15.21%, 11.06%, 15.21%, 9.04%, 4.36%, and 2.3% higher.

Keywords: Vegetation index (VI); deep residual network (Deep ResNet); sea lion optimization (SLnO); social ski-driver optimization (SSDO); remote sensing image (search for similar items in EconPapers)
Date: 2024
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.worldscientific.com/doi/abs/10.1142/S0219622023500086
Access to full text is restricted to subscribers

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:wsi:ijitdm:v:23:y:2024:i:01:n:s0219622023500086

Ordering information: This journal article can be ordered from

DOI: 10.1142/S0219622023500086

Access Statistics for this article

International Journal of Information Technology & Decision Making (IJITDM) is currently edited by Yong Shi

More articles in International Journal of Information Technology & Decision Making (IJITDM) from World Scientific Publishing Co. Pte. Ltd.
Bibliographic data for series maintained by Tai Tone Lim ().