Acute Lymphoblastic Leukemia Classification with Blood Smear Microscopic Images Using Taylor-MBO based SVM

Acute lymphoblastic leukemia (ALL) is a serious hematological neoplasis that is characterized by the development of immature and abnormal growth of lymphoblasts. However, microscopic examination of bone marrow is the only way to achieve leukemia detection. Hence, an effective leukemia detection approach is designed using the proposed Taylor-Monarch Butterfly Optimization based Support Vector Machine (Taylor-MBO based SVM). However, the proposed Taylor-MBO is designed by the integration of Taylor series and Monarch Butterfly Optimization (MBO), respectively. The sparking process is designed to perform automatic segmentation of blood smear image by estimating optimal threshold values. By extracting the features, such as texture features, statistical and grid-based features from the segmented smear image, the performance of classification is increased with less training time However, the proposed Taylor-MBO based SVM obtained better performance using the metrics, such as accuracy, sensitivity, and specificity with the values of 94.5751%, 95.526%, and 94.570%, respectively.

Robust approach for optimized path selection in Monarch Butterfly Optimization

Nature Inspired Computing or (NIC) strives to develop new computing technologies by observing how nature can inspired to solve complex problems under various environmental conditions. This has produced unconventional research in new fields such as neural networks, swarm intelligence, evolutionary computing, and artificial immune systems. NIC technology is used in almost every branch of physics, biology, engineering, economics and even management. In this paper, one of the nature-inspired approach namely Monarch Butterfly Optimization (MBO)is used for modifying the chromosome parameter in it. The new conditional path selection criteria are developed for the movement of individual subpopulation along with the amplitude parameter. Ackley function is implemented by using conditional path selection mathematical model and the effect of amplitude parameter with adjusting ratio has been identified. The results show better performance among the conditional path selection criteria in terms of route optimization selection.

TAYLOR–MONARCH BUTTERFLY OPTIMIZATION-BASED SUPPORT VECTOR MACHINE FOR ACUTE LYMPHOBLASTIC LEUKEMIA CLASSIFICATION WITH BLOOD SMEAR MICROSCOPIC IMAGES

Acute lymphoblastic leukemia (ALL) is a serious hematological neoplasis that is characterized by the development of immature and abnormal growth of lymphoblasts. However, microscopic examination of bone marrow is the only way to achieve leukemia detection. Various methods are developed for automatic leukemia detection, but these methods are costly and time-consuming. Hence, an effective leukemia detection approach is designed using the proposed Taylor–monarch butterfly optimization-based support vector machine (Taylor–MBO-based SVM). However, the proposed Taylor–MBO is designed by integrating the Taylor series and MBO, respectively. The sparking process is designed to perform the automatic segmentation of blood smear images by estimating optimal threshold values. By extracting the features, such as texture features, statistical, and grid-based features from the segmented smear image, the performance of classification is increased with less training time. The kernel function of SVM is enabled to perform the leukemia classification such that the proposed Taylor–MBO algorithm accomplishes the training process of SVM. However, the proposed Taylor–MBO-based SVM obtained better performance using the metrics, such as accuracy, sensitivity, and specificity, with 94.5751, 95.526, and 94.570%, respectively.