A New Tiger Beetle Algorithm for Cybersecurity, Medical Image Segmentation and Other Global Problems Optimization

Abstract

The tiger beetle is a fierce and cunning predator insect that uses deception to hunt its prey. The tiger beetle traps and hunts them by digging holes along the path of other insects. This study used a tiger beetle hunting strategy to create a tiger beetle optimization (TBO) algorithm. In this algorithm, each solution represents the position of a tiger beetle, with the optimal position being the prey's location. Using this method, the tiger beetles gradually converge to the optimal solution, creating holes around them and searching for them. We evaluate the TBO algorithm's search capability using a series of well-known mathematical test functions. Moreover, among the sophisticated forms of malware are polymorphic viruses, which are adept at changing their behaviour while maintaining the same essential functions. Thus, a machine learning-based malware analysis system utilizing the power of the proposed TBO is introduced in this article. TBO handles the escalating issues of efficiently catching and mitigating cybersecurity threats in an era where conventional methods suffer from the complexity and volume of modern malware. Compared to other optimization methods, the proposed algorithm has shown less error in finding the optimal solution when implemented and evaluated on different functions. The tiger beetle optimization algorithm has proven helpful in various applications, including image clustering and reservoir well placement, where it can identify damaged areas or tissues with greater accuracy. When diagnosing lung cancer, the proposed method has shown a sensitivity, validity, and accuracy of 88.63%, 87.58%, and 89.86%, respectively, when using the EBT, WKNN, ESKNM, and QSVM methods.