Lightweight Evolution Strategies for Nanoswimmers-oriented in Vivo Computation

Shi, Shaolong1,2; Chen, Yifan3,4; Yao, Xin2; Zhang, Mengjie5

10.1109/CEC.2019.8790356

2019

978-1-7281-2154-3

2019 IEEE Congress on Evolutionary Computation, CEC 2019

866-872

10-13 June 2019

Wellington, New zealand

345 E 47TH ST, NEW YORK, NY 10017 USA

Institute of Electrical and Electronics Engineers Inc.

We propose two novel evolution strategies of swarm intelligence for nanoswimmer-oriented in vivo computation, which corresponds to the computing model of the direct targeting strategy (DTS) where externally manipulable magnetic nanoswimmers are employed for cancer detection. In the DTS, the nanoswimmers move in the high-risk tissue region guided by an external magnetic field to search for the early cancer that cannot be visualized using traditional imaging modalities due to their limited resolution. Subject to the constraint of the state-of-the-art controlling technology which can only generate a uniform magnetic field to steer all the nanoswimmers simultaneously, we revisit the conventional gravitational search algorithm (GSA) and propose the orthokinetic gravitational search algorithm (OGSA) to carry out the DTS. Furthermore, we propose the general evolution strategy (G-ES) and the weak priority evolution strategy (WP-ES) and apply them to the OGSA for the path planning of magnetic nanoswimmers. To prove the superiority of the OGSA in the DTS, we present some simulation examples and make comparison with the "brute-force" search, which corresponds to the traditional systemic targeting strategy. Furthermore, we compare the performance of WP-ES and G-ES in the OGSA. It is found that the WP-ES can improve the performance of swarm intelligence algorithms (e.g., GSA) in the DTS.
© 2019 IEEE.

cancer detection nanoswimmers swarm intelligence uniform magnetic field gravitational search algorithm

其他

英语

EI ; CPCI-S

Program for University Key Laboratory of Guangdong Province[2017KSYS008]

Engineering ; Mathematical & Computational Biology

Engineering, Electrical & Electronic ; Mathematical & Computational Biology

WOS:000502087100115

20193507373674

Diseases ; Learning algorithms ; Magnetic fields ; Motion planning ; Swarm intelligence

Magnetism: Basic Concepts and Phenomena:701.2

EV Compendex

1.Harbin Institute of Technology, Harbin, China
2.Shenzhen Key Laboratory of Computational Intelligence, Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China
3.University of Electronic Science and Technology of China, Chengdu, China
4.University of Waikato, Hamilton, New Zealand
5.Victoria University of Wellington, Wellington, New Zealand

Shi, Shaolong,Chen, Yifan,Yao, Xin,et al. Lightweight Evolution Strategies for Nanoswimmers-oriented in Vivo Computation[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:Institute of Electrical and Electronics Engineers Inc.,2019:866-872.