IoT based smart agri system: deep classifiers for black gram disease classification with modified feature set

Neha Hajare () and Anand Singh Rajawat ()
Additional contact information
Neha Hajare: Sandip University
Anand Singh Rajawat: Sandip University

International Journal of System Assurance Engineering and Management, 2024, vol. 15, issue 7, No 39, 3368-3384

Abstract: Abstract Black gram, sometimes referred to as urdbean (Vigna mungo), is an important pulse crop that is produced extensively in Asian nations including Bangladesh, India, Pakistan, and Thailand. It is a crop with a brief growing season and is ideally suited to semiarid climates. Hence, it is most suitable for dry land cultivation. Black gram is packed with a high nutritional content of about 26% protein which is thrice times more than cereals. It makes it an excellent plant-based food source. Yet, the country’s domestic demand requirements are unable to be satisfied by the present level of production. Viral and fungi infections diminish the production of black gram production. As a countermeasure to this issue, this research work gives the introduction of an Internet of Things (IoT) based agri system on black gram disease classification. At first, the disease classification model is kicked off with data augmentation using image-augmenting techniques like shifting, rotation and shearing. Secondly, the pre-processing stage is handled by an Improved wiener process. Further, the segmentation process is done by an improved Density-Based Spatial Clustering of Applications with Noise (DBSCAN) model for enhanced image segmentation. Furthermore, features including modified Local Gabor Transitional Pattern (LGTP) feature, colour feature and hierarchy of skeleton-based shape feature are extracted from the segmented image. To classify images from healthy and diseased for pesticide recommendation, disease classification on images is performed by a hybrid classifier model with Long Short Term Memory (LSTM) and Bidirectional-Gated Recurrent Units(Bi-GRU) classifiers. After, the classification stage, the recommendation stage takes place to assist farmers with accurate results on the recommendation. In the end, by comparing performance metrics with precise categorization, the suggested model’s effectiveness compared to cutting-edge models was demonstrated. Following this, suggestions/recommendations are given to the farmers based on the classified outcome.

Keywords: Black gram; Improved Wiener process; Improved DBSCAN model; Modified LGTP feature; Hierarchy of skeleton (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s13198-024-02347-2 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

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:spr:ijsaem:v:15:y:2024:i:7:d:10.1007_s13198-024-02347-2

Ordering information: This journal article can be ordered from
http://www.springer.com/engineering/journal/13198

DOI: 10.1007/s13198-024-02347-2

Access Statistics for this article

International Journal of System Assurance Engineering and Management is currently edited by P.K. Kapur, A.K. Verma and U. Kumar

More articles in International Journal of System Assurance Engineering and Management from Springer, The Society for Reliability, Engineering Quality and Operations Management (SREQOM),India, and Division of Operation and Maintenance, Lulea University of Technology, Sweden
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().