A Novel Radius Adaptive Based on Center-Optimized Hybrid Detector Generation Algorithm

Negative selection algorithm(NSA)is one of the classic artificial immune algorithm widely used in anomaly detection.However,there are still unsolved shortcomings of NSA that limit its further applications.For example,the nonselfdetector generation efficiency is low;a large number of nonselfdetector is needed for precise detection;low detection rate with various application data sets.Aiming at those problems,a novel radius adaptive based on center-optimized hybrid detector generation algorithm(RACO-HDG)is put forward.To our best knowledge,radius adaptive based on center optimization is first time analyzed and proposed as an efficient mechanism to improve both detector generation and detection rate without significant computation complexity.RACO-HDG works efficiently in three phases.At first,a small number of self-detectors are generated,different from typical NSAs with a large number of self-sample are generated.Nonself-detectors will be generated from those initial small number of self-detectors to make hybrid detection of self-detectors and nonself-detectors possible.Secondly,without any prior knowledge of the data sets or manual setting,the nonself-detector radius threshold is self-adaptive by optimizing the nonself-detector center and the generation mechanism.In this way,the number of abnormal detectors is decreased sharply,while the coverage area of the nonself-detector is increased otherwise,leading to higher detection performances of RACOHDG.Finally,hybrid detection algorithm is proposed with both self-detectors and nonself-detectors work together to increase detection rate as expected.Abundant simulations and application results show that the proposed RACO-HDG has higher detection rate,lower false alarm rate and higher detection efficiency compared with other excellent algorithms.

A New Restarting Adaptive Trust-Region Method for Unconstrained Optimization

In this paper,we present a new adaptive trust-region method for solving nonlinear unconstrained optimization problems.More precisely,a trust-region radius based on a nonmonotone technique uses an approximation of Hessian which is adaptively chosen.We produce a suitable trust-region radius;preserve the global convergence under classical assumptions to the first-order critical points;improve the practical performance of the new algorithm compared to other exiting variants.Moreover,the quadratic convergence rate is established under suitable conditions.Computational results on the CUTEst test collection of unconstrained problems are presented to show the effectiveness of the proposed algorithm compared with some exiting methods.

A randomized nonmonotone adaptive trust region method based on the simulated annealing strategy for unconstrained optimization

Purpose–The purpose of this paper is to employ stochastic techniques to increase efficiency of the classical algorithms for solving nonlinear optimization problems.Design/methodology/approach–The well-known simulated annealing strategy is employed to search successive neighborhoods of the classical trust region(TR)algorithm.Findings–An adaptive formula for computing the TR radius is suggested based on an eigenvalue analysis conducted on the memoryless Broyden-Fletcher-Goldfarb-Shanno updating formula.Also,a(heuristic)randomized adaptive TR algorithm is developed for solving unconstrained optimization problems.Results of computational experiments on a set of CUTEr test problems show that the proposed randomization scheme can enhance efficiency of the TR methods.Practical implications–The algorithm can be effectively used for solving the optimization problems which appear in engineering,economics,management,industry and other areas.Originality/value–The proposed randomization scheme improves computational costs of the classical TR algorithm.Especially,the suggested algorithm avoids resolving the TR subproblems for many times.