Research Article
Artificial Intelligence Based Image Processing Model for Early Pest Detection in Sorghum Crop Plantations: In Case of Southern Tigrai
Asfaw Kiros Desalegn*
,
Kahsay Niguse Gebrekidan
Issue:
Volume 1, Issue 2, December 2026
Pages:
69-79
Received:
15 July 2026
Accepted:
15 September 2026
Published:
15 October 2026
Abstract: Agriculture not only provides food for the human existence, it is also a big source for the economy of any country. Pests damage the crops and, thus, are very dangerous for the overall growth of the crop. In this proposed system sorghum leaf image was given as an input and for noise removal median filtering algorithm is used then the background subtraction takes place using Otsu thresholding algorithm. Then, at the end of image processing step extract and calculate three types of feature color, texture and morphological features for the segmented foreground leaf image. After feature selection algorithm is implemented, six color, five texture and ten morphological features are extracted from each sorghum plant leaf image and combined to get dataset which is used to develop the model, though model attempts with separate features were conducted in experiment. Finally, these extracted features are feed in to the classifier for the classification, K-Nearest Neighbor, Support Vector Machine and Artificial Neural Network implemented for classification purposes. In general the overall experimental result shows that the developed Artificial Neural Network model with a combination of three features namely color, texture and morphological features achieved a better result with an accuracy of 90%.
Abstract: Agriculture not only provides food for the human existence, it is also a big source for the economy of any country. Pests damage the crops and, thus, are very dangerous for the overall growth of the crop. In this proposed system sorghum leaf image was given as an input and for noise removal median filtering algorithm is used then the background sub...
Show More
Research Article
A Fractional-Order Tumor-Immune-Healthy Tissue Interaction Model: Mathematical Analysis and Numerical Investigation Using the Atangana-Baleanu Derivative
Gizachew Tirite Gellow*
Issue:
Volume 1, Issue 2, December 2026
Pages:
80-91
Received:
11 July 2026
Accepted:
22 August 2026
Published:
3 November 2026
DOI:
10.11648/j.sdcomput.20260102.12
Downloads:
Views:
Abstract: Tumor progression is governed by nonlinear interactions among malignant cells, immune effector cells, and the surrounding healthy tissue. Such interactions are influenced by previous biological states, including accumulated immune stimulation, tissue damage, and cellular adaptation. Conventional integer-order models describe the instantaneous rate of change but do not explicitly represent this history dependence. In this work, a fractional-order tumor–immune–healthy tissue model is formulated using the Atangana–Baleanu Caputo (ABC) fractional derivative, whose nonsingular Mittag–Leffler kernel provides a nonlocal representation of biological memory. The model consists of three interacting populations: tumor cells, immune effector cells, and healthy tissue. Tumor proliferation is represented by logistic growth, immune-mediated tumor elimination and immune suppression are incorporated through nonlinear interaction terms, and healthy tissue regeneration is balanced against tumor-induced damage. The model is first analyzed mathematically. Under explicit regularity and parameter assumptions, local existence and uniqueness of solutions are established by a fixed-point argument. Positivity is obtained from the vector field on the boundary of the nonnegative orthant, and boundedness follows from comparison estimates. The fractional formulation is then converted into its equivalent Volterra integral equation and a history-weighted product-integration discretization with an implicit correction is implemented for numerical computation. Numerical illustrations are used to examine the effect of fractional order on tumor, immune, and healthy-tissue trajectories. The results indicate that decreasing the fractional order changes the transient response and introduces a stronger dependence on previous states, whereas the integer-order case is recovered at α=1. The study therefore provides a mathematically consistent framework for examining memory-dependent tumor dynamics and identifies directions for subsequent calibration with clinical or experimental data.
Abstract: Tumor progression is governed by nonlinear interactions among malignant cells, immune effector cells, and the surrounding healthy tissue. Such interactions are influenced by previous biological states, including accumulated immune stimulation, tissue damage, and cellular adaptation. Conventional integer-order models describe the instantaneous rate ...
Show More
