We propose a new computing-inspired bio-detection framework called touchable computation (TouchComp). Under the rubric of TouchComp, the best solution in the parameter space is associated with the target to be detected. A population of externally steerable agents locate the optimal solution by moving through the parameter space, whose landscape (objective function) may be altered by these agents but the location of the best solution remains unchanged. Thus, one can infer the parameter space by observing the movement of agents. The term 'touchable' emphasizes the framework's similarity to controlling by touching the screen with a finger, where the external field for controlling and tracking acts as the finger. We apply the TouchComp model to cancer detection, where the target is the cancer, the parameter space is the tissue region at high risk of malignancy, and agents are nanorobots loaded with contrast medium molecules for tracking purpose. Given this analogy, we revisit the classical particle swarm optimization (PSO) algorithm and apply it to TouchComp in order to achieve effective cancer detection. The PSO is modified by taking into account realistic in vivo propagation, controlling, and tracking conditions of nanorobots. Finally, we present numerical examples to demonstrate the effectiveness of the proposed computing-inspired bio-detection strategy. © 2017 IEEE.
|Title of host publication
|IEEE Workshop on Signal Processing Advances in Wireless Communications, SPAWC
|Institute of Electrical and Electronics Engineers Inc.
|Number of pages
|Published - Jul 2017
Bibliographical noteThis work is supported by the Guangdong Natural Science Funds for Distinguished Young Scholar (S2013050014223), the Shenzhen Development and Reform Commission Funds (944, 1939), and the Shenzhen Science, Technology and Innovation Commission Funds (KQCX2015033110182368, JCYJ20160301113918121, JSGG20160427105120572)
- Computing-inspired bio-detection
- Contrast-enhanced medical imaging
- Touchable computation