Open Access

ARTICLE

Cat Swarm with Fuzzy Cognitive Maps for Automated Soil Classification

by Ashit Kumar Dutta^1,*, Yasser Albagory², Manal Al Faraj¹, Majed Alsanea³, Abdul Rahaman Wahab Sait⁴

1 Department of Computer Science and Information Systems, College of Applied Sciences, AlMaarefa University, Ad Diriyah, Riyadh, 13713, Kingdom of Saudi Arabia
2 Department of Computer Engineering, College of Computers and Information Technology, Taif University, Taif, 21944, Kingdom of Saudi Arabia
3 Department of Computing, Arabeast Colleges, Riyadh, 11583, Kingdom of Saudi Arabia
4 Department of Archives and Communication, King Faisal University, Al Ahsa, Hofuf, 31982, Kingdom of Saudi Arabia

* Corresponding Author: Ashit Kumar Dutta. Email:

Computer Systems Science and Engineering 2023, 44(2), 1419-1432. https://doi.org/10.32604/csse.2023.027377

Received 16 January 2022; Accepted 23 February 2022; Issue published 15 June 2022

Abstract

Accurate soil prediction is a vital parameter involved to decide appropriate crop, which is commonly carried out by the farmers. Designing an automated soil prediction tool helps to considerably improve the efficacy of the farmers. At the same time, fuzzy logic (FL) approaches can be used for the design of predictive models, particularly, Fuzzy Cognitive Maps (FCMs) have involved the concept of uncertainty representation and cognitive mapping. In other words, the FCM is an integration of the recurrent neural network (RNN) and FL involved in the knowledge engineering phase. In this aspect, this paper introduces effective fuzzy cognitive maps with cat swarm optimization for automated soil classification (FCMCSO-ASC) technique. The goal of the FCMCSO-ASC technique is to identify and categorize seven different types of soil. To accomplish this, the FCMCSO-ASC technique incorporates local diagonal extrema pattern (LDEP) as a feature extractor for producing a collection of feature vectors. In addition, the FCMCSO model is applied for soil classification and the weight values of the FCM model are optimally adjusted by the use of CSO algorithm. For examining the enhanced soil classification outcomes of the FCMCSO-ASC technique, a series of simulations were carried out on benchmark dataset and the experimental outcomes reported the enhanced performance of the FCMCSO-ASC technique over the recent techniques with maximum accuracy of 96.84%.

---

Keywords

---