The Entry for 2017 Human-competitiveness

1. The complete title of one (or more) paper(s) published in the open literature describing the work that the author claims describes a human-competitive result:

	ZCSR for Targeting the Optimal Impedance in Digital Radio Frequency Matching Box

2. The name, complete physical mailing address, e-mail address, and phone number of EACH author of EACH paper(s):

	Liang-Yu Chen
	Institute of Computer Science and Engineering
	National Chiao Tung University
	Taiwan(R.O.C.)
	b60306@hotmail.com
	+886 3 571 2121 x59329

	Ya-Liang Yang
	Department of Computer Science
	National Chiao Tung University
	Taiwan(R.O.C.)
	alan.yaco@msa.hinet.net
	+886 3 571 2121 x59329

	Tzu-Chien Hsiao 
	Department of Computer Science, Institute of Biomedical Engineering
	National Chiao Tung University
	Taiwan(R.O.C.)
	labview@cs.nctu.eud.tw
	+886 3 571 2121 x59329


3. The name of the corresponding author (i.e., the author to whom notices will be sent concerning the competition):

	Liang-Yu Chen

4. The abstract of the paper(s):

	Digital radio frequency (RF) matching box used in the manufacturing process of semiconductor is a critical equipment for discharging plasma.
 	In this process, the impedance of the plasma chamber is always changed.
 	Inconsistent impedance between matching box and plasma chamber leads to uneven thickness of plasma coating on semiconductor.
 	In order to maintain consistent impedance, the impedance of RF matching box and the plasma chamber have to achieve a dynamic match.
 	Past researches used the approximation method to approach the optimal impedance step by step.
	However, when the impedance of the plasma chamber is changed, the approximation method loses the trend approaching the optimal impedance point.
	Zeroth-level Classifier System (ZCS) is a rule-based machine learning method which adapts to a changing environment for online learning. 
 	In this paper, the ZCS with continuous-valued inputs (ZCSR) is applied for targeting the optimal impedance in digital RF matching box.
 	The results indicate that ZCSR is capable of approaching the optimal impedance on average about 225 problem instances in the fixed impedance of the simulated chamber.
 	We have verified that ZCSR can find optimal impedance in fixed impedance chamber.
 	In the future, we will apply the ZCSR to the variable impedance chamber.

5. A list containing one or more of the eight letters (A, B, C, D, E, F, G, or H) that correspond to the criteria (see above) that the author claims that the work satisfies:

	G

6. A statement stating why the result satisfies the criteria that the contestant claims (see examples of statements of human-competitiveness as a guide to aid in constructing this part of the submission):

	In order to maintain the best power transmission to stabilize plasma chamber operating, the industry uses the matching box to dynamically adjust all the impedance on the system route to become the same.
	The change of the impedance in the plasma chamber is very complex and it is difficult to achieve dynamically matching impedance.
	Poor matching will have electromagnetic radiation, the electromagnetic radiation will interfere the electronic equipment.
	The equation contains eight variables, but the industry can only control the change by two variables to find the optimal impedance.
	Uneven impedance on the system route will lead to power reflection.
	The change of impedance from the high reflected power to the low reflected power is linear relation.
	Therefore, the industry used General Delta Rule (GDR) to find the trend of impedance change in the past.
	However, the impedance of plasma chamber is always changed, this means that the change of impedance is not linear in the low reflected power region.
	When the impedance changes, GDR will lose the trend and the industry must rely on employee's experience to manual adjust the matching box.
	The industry want to import machine learning methods to achieve dynamic matching impedance.
 	In this work, we successfully use learning classifier system to reached matching impedance and locked in the optimal impedance.
	Therefore, we claim that the following criteria is satisfied: (G) The result solves a problem of indisputable difficulty in its field.

7. A full citation of the paper (that is, author names; publication date; name of journal, conference, technical report, thesis, book, or book chapter; name of editors, if applicable, of the journal or edited book; publisher name; publisher city; page numbers, if applicable):

	Liang-Yu Chen, Ya-Liang Yang, and Tzu-Chien Hsiao (2017, Jul). ZCSR for targeting the optimal impedance in digital radio frequency matching box. GECCO¡¦17-Proceedings of the 16th International Conference on Genetic and Evolutionary Computation Conference. Berlin, German.(Accepted on Mar 21, 2017) 

8. A statement either that "any prize money, if any, is to be divided equally among the co-authors" OR a specific percentage breakdown as to how the prize money, if any, is to be divided among the co-authors:

	any prize money, if any, is to be divided equally among the co-authors"

9. A statement stating why the judges should consider the entry as "best" in comparison to other entries that may also be "human-competitive;"

	This is the first time to show out the Learning Classifier System(LCS) can solve such dynamic problem in matching box.
	This work can prevent a large number of the expensive wafer be scrapped due to the uneven coating.
	This is also a major step for LCS applying to the semiconductor field.
	
10. An indication of the general type of genetic or evolutionary computation used, such as GA (genetic algorithms), GP (genetic programming), ES (evolution strategies), EP (evolutionary programming), LCS (learning classifier systems), GE (grammatical evolution), GEP (gene expression programming), DE (differential evolution), etc.:
 
	LCS(learning classifier system)