“…However, from the view of global optimization, RAIN has several critical parameters manually set for efficient initialization, such as the number of *Correspondence to: Feng Qian, State-Key Laboratory of Chemical Engineering, East China University of Science and Technology, Shanghai 200237, China. E-mail: fqian@ecust.edu.cn B cells, the network affinity threshold, and mutation rate, [5] which usually directly influence the complexity and performance of the algorithm, while aiNet has more application dependent parameters to be processed overhead of each iteration than RAIN. [10,11] Another noticeable algorithm in AIS field is clonal selection algorithm (CLONALG), [12] which on the basis of clonal selection principle, has been widely used in machine learning, pattern recognition, multimodal optimization, etc.…”