改良約略集決策機制以提昇雷射醫學美容診斷品質之研究

Modify Decision Algorithm of Rough Set Theory to Upgrade the Diagnosis Quality of Laser Medical Cosmetology

10.30001/JIES.201006.0008

胡維萍；黃素慧；陳雅玲

雷射醫學美容 ； 約略集理論 ； 不可辨識關係表 ； 可辨識分類函數 ； 範數 ； Laser Medical cosmetology ； Rough set theory ； Indiscernibility relation table ； Discernibility classification function ； Norm

美容科技學刊

7卷2期（2010 / 06 / 01）

141 - 161

繁體中文

「雷射醫學美容」的主要原理：是利用高能量雷射光束，將皮膚中色素顆粒「燒毀」，並由皮膚自行代謝吸收，以達到除斑的效果；而本研究改良「約略集」理論的決策機制，來輔助並提昇初期診斷的品質，用以强化雷射醫學美容的效果。 本研究歸納雷射醫學美容中較常使用的療程種類，及其所專精處理的膚質狀況，區分出「雷射療程」－「膚質」兩構面，以對應「約略集」(Rough set)理論中的「宇集合」(Universe)與「屬性集合」(Attribute)，透過收集各個醫學美容中心與網站資料分析，建構出「不可辨識關係表」(Indiscernibility relation table)，進一步簡化出「可辨識分類函數」(Discernibility classification function)，根據約略分類(Rough classification)的精確度分析，將「核心」(Core)與「可簡化」(Reduct)膚質屬性分離，用以確定雷射療程所主要與次要處理的多重膚質屬性狀況為何！ 再則，依據約略分類所建構出的「膚質資料庫」，將實驗客戶所期望處理的膚質狀況，設計為新決策需求，對應原有雷射療程元素問的決策規則，本研究改良原約略集的決策機制，使用「二階範數」(Znd Norm)的平均值，作為判斷療程與客戶膚質間的分類「距離」(Distance)，取最小的數值作為最適雷射療程，整體推導過程與相關文獻探討將被探討！

The basic concept of Laser medical cosmetology is to utilize high-energy laser beam to penetrate the skin surface, and ”burning” the pigment particle inside. The skin itself would absorb and metabolize the pigment, and achieve the effect of removing specks. In this paper, the modified decision algorithm of the rough set theory would be applied to upgrade the diagnosis quality of Laser medical cosmetology. In this research, laser treatment programs and related skin conditions would be collected and used to build up the universe and the attribute of the rough set. By means of surveying Medical cosmetic centers and investigating websites information, the indiscernibility relation table could be facilitated, and discernibility classification functions would be simplified by applying Boolean algebra. Simplified discernibility functions would be deduced from the discernibility classification matrix. According to the rough classification, the core and the reduct attributes would be separated, and the skin condition database would be defined. Therefore, the optimal treatment program could be located for the specific skin condition.. Based on the skin condition attribute database, the requirement of the designated customer could be transformed as the new decision of the rough set, and the average 2nd norm would be introduced to find out the distance between the treatment program and the customer’s need. The smallest distance would be the most appropriate treatment program for the designated customer. An experimental case would be discussed, and the feasibility and precision of this method would be examined. The overall analysis procedure would be discussed, and the new perspective of upgrading the diagnosis quality of the laser medical cosmetology would be provided in this paper.

1. 胡維萍、黃素慧、謝逸蓁(2008)。應用約略集理論建構醫學美容先期診斷療程之探討。美容科技學刊，5(1)，79-102。
   連結：
2. 胡維萍、黃素慧、謝逸蓁(2008)。應用約略集理論建構醫學美容先期診斷療程之探討。美容科技學刊，5(1)，79-102。
   連結：
3. 網站資訊：http://www.iplonline.net/index.php?op=item2（2009年3月取得）
4. 網站資訊：http://www.taiwanlaser.com/laser/introduction.htm（2009年6月取得）
5. Attoh-Okine, N.O.(1997).Rough set application to data mining principles in pavament management database.Journal of Computing in Civil Engineering,11(4),231-7.
6. Bell, D.,Guan, J.(1998).Computational methods for rough classification and discovery.Journal of the American Society for Information Science,49(5),403-414.
7. Czyzewski, A.,Skarzynski, H.,Kostek, B.,Krolikowski, R.(1999).Rough set analysis of electro stimulation test database for the prediction of post-operative profits in cochlear implanted patients.Lecture Notes in Artificial Intelligence,1711,109-117.
8. Hu, Q.,Yu, D.,Xie, Z.,Liu, J.(2006).Fuzzy probabilistic approximation spaces and their information measures.Transaction on Fuzzy Systems,14,191-201.
9. Kusiak, A.,Kern, J.,Kernstine, K.,Tseng, B.(2000).Autonomous decision-making: a data mining approach.IEEE Transactions on Information Technology in Biomedicine,4(4),274-284.
10. Liu, J.,Hu, Q.,Yu, D.(2008).A weighted rough set based method developed for class imbalance learning.Information Science,4,1235-1256.
11. Mitra, P.,Mitra, S.,Pal, S.(2001).Evolutionary modular MLP with rough sets and ID3 algorithm for staging of cervical cancer.Neural Computing and Applications,10(1),67-76.
12. Pawlak, Z.,Rough, Sets(1991).Theoretical Aspects of Reasoning about Data.Dordrecht, Netherland:Kluwer Academic Publishers.
13. Polkowski, L.(Ed.),Skowron, A.(Ed.)(1998).Rough Sets in Knowledge Discovery 1: Methodology and Applications, Physica-Verlag.Heidelberg:
14. Slowinski, R.(1992).Intelligent Decision Support. Handbook of Applications and Advances of the Rough Sets Theory.Dordrecht, Netherland:Kluwer Academic Publishers.
15. Stefanowski, J.,Slowinski, K.(1997).Rough set theory and rule induction techniques for discovery of attribute dependencies in medical information systems.Lecture Notes in Artificial Intelligence,1263,36-46.
16. Walczak, B.,Massart, D. L.(1999).Rough sets theory.Chemometrics and intelligent laboratory systems,47,1-16.
17. Yahia, M.,Mahmod, R.,Sulaiman, N.,Ahmad, F.(2000).Rough neural expert systems.Expert Systems with Applications,18(2),87-99.
18. Yang, Hsu-Uao,Wu, Chang-Lun(2009).Rough sets to help medical diagnosis-Evidence from a Taiwan' s clinic.Expert Systems with Applications: An International Journal,36(5)
19. 胡維萍、黃素慧(2008)。探討約略集理論建構的順逆向醫學美容療程之診斷程序。2008台灣長榮企業管理暨經營決策學術研討會
20. 胡維萍、黃素慧、謝逸蓁(2007)。約略集導入醫學美容療程藉以建構出膚質資料庫之探討。科技與管理學術研討會
21. 廖苑利(2002)。斑長不見了。大康出版社。
22. 蔡仁雨(2002)。皮膚美容外科學。武陵出版社。