An improved moth flame optimization algorithm based on rough sets for tomato diseases detection

Abstract

Plant diseases is one of the major bottlenecks in agricultural production that have bad eects on the economic of any country. Automatic detection of such disease could minimize these eects. Features selection is a usual pre-processing step used for automatic disease detection systems. It is an important process for detecting and eliminating noisy, irrelevant, and redundant data. Thus, it could lead to improve the detection performance. In this paper, an improved moth-ame approach to automatically detect tomato diseases was proposed.

An Improved Harris Hawks Optimization Algorithm With Simulated Annealing for Feature Selection in the Medical Field

“…Nowadays, FS is an essential step to preprocess high-dimensional datasets. It must be pointed that there are representative computational intelligence algorithms that have been applied to improve the FS in different studies such as [7], [9], [33], [34], [27], [46], and [47]. The optimization methods aim to obtain the optimal solution for FS (i.e., significant feature subset) within an appropriate time and cost.…”

Review of image processing approaches for detecting plant diseases

“…The fungi affects various plants as well, causing several forms of diseases, Table 4 summarises span of work over the years concentrating on detection of diseases caused by fungus. Various diseases which occur due to fungus are corynespora [15], bird's eye spot [15], powdery mildew [30, 47–50], downy mildew [20, 30, 51–53], scab [29],black spot [54], red spot [55], rust [20], anthracnose [56, 57], melanose [58], frogeye [59], curvularia leaf spot [60], wheat stripe rust [61], septoria leaf spot [62]. Dataset varies from 40 to 1500 images, with small dataset of 40 images Youwen et al [30] achieved 100% accuracy in detecting powdery mildew, and with 1478 images Meunkaewjinda et al [29] achieved an accuracy of 82.5 and 83.5% for detecting scab and rust diseases in grape.…”

Recent Meta-Heuristics Improved by Self-Adaptation Applied to Nonlinear Model-Based Predictive Control

“…For instance, to GWO were applied a cauchy operator [27], [28], chaotic mapping [29]- [31], fuzzy logic [32] and refraction learning [33]. Improved MFO versions were utilized in parameter tuning problems [34]- [36], feature selection [37], photo-voltaic models [38], standard benchmark functions [39], [40], power flow problem [41], among others. Self-adaptation was applied in GWO to solve a transmit antenna selection problem [42] and a 2-dimensional logistic chaotic mapping [43].…”