بهينه سازي درخت تصميم گيري فازي با استفاده از الگوريتم ژنتيك به منظور تشخيص مزاج در طب سنتي ايران

Fuzzy decision tree optimization by genetic algorithm for Mizaj (Temperament) detection in Traditional Persian Medicine

ﺳﺎﺑﻘﻪ ﻭ ﻫﺪﻑ: ﻳﻜﻲ ﺍﺯ ﻣﺒﺎﺣﺚ ﻣﻬﻢ ﻭ ﺍﺳﺎﺳﻲ ﺩﺭ ﻃﺐ ﺍﻳﺮﺍﻧﻲ، ﺩﺍﻧﺶ ﺷﻨﺎﺧﺖ ﻣﺰﺍﺝ ﺍﺳﺖ ﻭ ﺑﺴﻴﺎﺭﻱ ﺍﺯ ﺩﺳﺘﻮﺭﺍﺕ ﺣﻔﻆ ﺳﻼﻣﺘﻲ، ﺗﺸﺨﻴﺺ ﻭ ﺩﺭﻣﺎﻥ ﺑﻴﻤﺎﺭﻱ ﻫﺎ ﺑﺮ ﻣﺒﻨﺎﻱ ﻣﺰﺍﺝ ﺗﻌﻴﻴﻦ ﺷﺪﺓ ﻫﺮ ﻓﺮﺩ ﺑﺎ ﺩﻳﮕﺮﺍﻥ ﻣﺘﻔﺎﻭﺕ ﺍﺳﺖ. ﻛﺸﻒ ﻭ ﺷﻨﺎﺧﺖ ﺷﻴﻮﻩ ﻫﺎﻱ ﺍﺳﺘﺎﻧﺪﺍﺭﺩ ﺗﻌﻴﻴﻦ ﻣﺰﺍﺝ ﺍﺯ ﻣﻬﻢ ﺗﺮﻳﻦ ﺍﻭﻟﻮﻳﺖ ﻫﺎﻱ ﭘﮋﻭﻫﺸﻲ ﺩﺭ ﻃﺐ ﺍﻳﺮﺍﻧﻲ ﺍﺳﺖ. ﺩﺭ ﺍﻳﻦ ﭘﮋﻭﻫﺶ ﺍﺯ ﺩﺭﺧﺖ ﺗﺼﻤﻴﻢ ﻓﺎﺯﻱ ﺑﺮﺍﻱ ﻃﺒﻘﻪ ﺑﻨﺪﻱ ﺩﺍﺩﻩ ﻫﺎ ﻭ ﺍﻟﮕﻮﺭﻳﺘﻢ ژﻧﺘﻴﻚ ﺑﺮﺍﻱ ﺑﻬﻴﻨﻪ ﺳﺎﺯﻱ ﻭﻳﮋﮔﻲ ﻫﺎﻱ ﻻﺯﻡ ﺑﺮﺍﻱ ﺗﺸﺨﻴﺺ ﻣﺰﺍﺝ ﺍﺳﺘﻔﺎﺩﻩ ﻣﻲ ﺷﻮﺩ. ﻣﻮﺍﺩ ﻭ ﺭﻭﺵ ﻫﺎ: ﺩﺭ ﻣﻄﺎﻟﻌﺔ ﺣﺎﺿﺮ ﺍﺯ ﺩﻭ ﻣﺠﻤﻮﻋﻪ ﺩﺍﺩﻩ ﺑﺎ 52 ﻧﻤﻮﻧﻪ ﻭ221 ﻧﻤﻮﻧﻪ ﺍﺳﺘﻔﺎﺩﻩ ﻣﻲ ﺷﻮﺩ. ﺑﺮﺍﻱ ﻫﺮ ﺩﻭ ﻣﺠﻤﻮﻋﺔ ﺩﺍﺩﻩ، ﺷﻨﺎﺧﺖ ﺩﺍﺩﻩ ﻭ ﻣﺪﻝ ﺳﺎﺯﻱ ﺗﺸﺨﻴﺺ ﻣﺰﺍﺝ ﺑﺮ ﻣﺒﻨﺎﻱ ﺩﺭﺧﺖ ﺗﺼﻤﻴﻢ ﮔﻴﺮﻱ ﻓﺎﺯﻱ ﺑﺎ ﺍﻟﮕﻮﺭﻳﺘﻢ ژﻧﺘﻴﻚ ﺍﻧﺠﺎﻡ ﻣﻲ ﺷﻮﺩ. ﺑﺮﺍﻱ ﺍﻳﻦ ﻛﺎﺭ ﺍﺑﺘﺪﺍ ﺯﻳﺮﻣﺠﻤﻮﻋﻪ ﺍﻱ ﺍﺯ ﻭﻳﮋﮔﻲ ﻫﺎ ﺑﺎ ﺍﺳﺘﻔﺎﺩﻩ ﺍﺯ ﺍﻟﮕﻮﺭﻳﺘﻢ ژﻧﺘﻴﻚ ﺍﻧﺘﺨﺎﺏ ﻭ ﺳﭙﺲ ﺩﺭﺧﺖ ﺗﺼﻤﻴﻢ ﮔﻴﺮﻱ ﻓﺎﺯﻱ ﺑﻪ ﻣﻨﻈﻮﺭ ﺳﺎﺧﺖ ﻗﻮﺍﻧﻴﻦ ﺍﺳﺘﻔﺎﺩﻩ ﻣﻲ ﺷﻮﺩ. ﻳﺎﻓﺘﻪ ﻫﺎ: ﺑﺮﺍﻱ ﻫﺮ ﻣﺠﻤﻮﻋﺔ ﺩﺍﺩﻩ ﺩﻭ ﺩﺭﺧﺖ ﺗﺼﻤﻴﻢ ﮔﻴﺮﻱ ﺑﺮﺍﻱ ﮔﺮﻣﻲ/ﺳﺮﺩﻱ ﻭ ﺗﺮﻱ/ﺧﺸﻜﻲ ﺳﺎﺧﺘﻪ ﻭ ﻗﻮﺍﻋﺪ ﺗﻮﻟﻴﺪ ﺷﺪﻩ ﺗﻮﺳﻂ ﭘﺰﺷﻚ ﻣﺘﺨﺼﺺ ﻃﺐ ﺍﻳﺮﺍﻧﻲ ﺍﺭﺯﻳﺎﺑﻲ ﺷﺪ. ﻧﺘﺎﻳﺞ ﻧﺸﺎﻥ ﺩﺍﺩ ﻗﻮﺍﻧﻴﻦ ﺻﺤﻴﺢ ﺗﻮﻟﻴﺪ ﺷﺪﻩ ﺩﺭ ﻣﺠﻤﻮﻋﺔ ﺩﺍﺩﻩ ﺩﻭﻡ ﺑﺮﺍﻱ ﻣﺰﺍﺝ ﮔﺮﻡ/ﺳﺮﺩ ﺑﺮﺍﺑﺮ ﺑﺎ 44 ﺩﺭﺻﺪ ﻭ ﻣﺰﺍﺝ ﺗﺮ/ﺧﺸﻚ ﺑﺮﺍﺑﺮ ﺑﺎ 33 ﺩﺭﺻﺪ ﺍﺳﺖ. ﺩﺭ ﻣﺠﻤﻮﻋﺔ ﺩﺍﺩﺓ ﺍﻭﻝ ﻗﻮﺍﻧﻴﻦ ﺻﺤﻴﺢ ﺗﻮﻟﻴﺪ ﺷﺪﻩ ﺗﻮﺳﻂ ﺩﺭﺧﺖ ﺗﺼﻤﻴﻢ ﻓﺎﺯﻱ ﺑﺎ ﺍﻟﮕﻮﺭﻳﺘﻢ ژﻧﺘﻴﻚ ﺑﺮﺍﻱ ﻣﺰﺍﺝ ﺗﺮ/ﺧﺸﻚ ﺑﺮﺍﺑﺮ ﺑﺎ9/5 ﺩﺭﺻﺪ ﺍﺳﺖ. ﻧﺘﻴﺠﻪ ﮔﻴﺮﻱ: ﻣﻘﺎﻳﺴﺔ ﻧﺘﺎﻳﺞ ﺑﺎ ﭘﮋﻭﻫﺶ ﺍﻧﺠﺎﻡ ﺷﺪﺓ ﻗﺒﻠﻲ، ﻧﺸﺎﻥ ﻣﻲ ﺩﻫﺪ ﻛﻪ ﺍﺳﺘﻔﺎﺩﻩ ﺍﺯ ﺍﻟﮕﻮﺭﻳﺘﻢ ژﻧﺘﻴﻚ ﻭ ﺍﻧﺘﺨﺎﺏ ﺯﻳﺮﻣﺠﻤﻮﻋﻪ ﺍﻱ ﺍﺯ ﻭﻳﮋﮔﻲ ﻫﺎ، ﺣﺠﻢ ﻣﺤﺎﺳﺒﺎﺗﻲ ﻭ ﺍﻧﺪﺍﺯﺓ ﺩﺭﺧﺖ ﺭﺍ ﻛﺎﻫﺶ ﻣﻲ ﺩﻫﺪ ﻭ ﻧﺘﺎﻳﺞ ﺑﻬﻴﻨﻪ ﺗﺮﻱ ﺣﺎﺻﻞ ﻣﻲ ﺷﻮﺩ ﻭ ﺩﺭﺻﺪ ﺧﻄﺎﻫﺎﻱ ﺭﺥ ﺩﺍﺩﻩ ﻫﻢ ﻛﺎﻫﺶ ﻣﻲ ﻳﺎﺑﺪ. ﻫﺮ ﭼﻨﺪ ﺑﻪ ﻧﻈﺮ ﻣﻲ ﺭﺳﺪ، ﺩﺭ ﺣﺎﻝ ﺣﺎﺿﺮ ﻧﺘﺎﻳﺞ ﺣﺎﺻﻞ ﺍﺯ ﺍﻳﻦ ﭘﮋﻭﻫﺶ ﻛﺎﺭﺑﺮﺩﻱ ﻧﻴﺴﺖ ﻭﻟﻲ ﻣﻲ ﺗﻮﺍﻧﺪ ﺷﺮﻭﻋﻲ ﺑﺮﺍﻱ ﭘﮋﻭﻫﺶ ﻫﺎﻱ ﺑﻌﺪﻱ ﺩﺭ ﺯﻣﻴﻨﺔ ﺑﻬﻴﻨﻪ ﺳﺎﺯﻱ ﺍﻟﮕﻮﺭﻳﺘﻢ ﻫﺎﻱ ﻫﻮﺷﻤﻨﺪ ﺑﺮﺍﻱ ﺗﺸﺨﻴﺺ ﻣﺰﺍﺝ ﺑﺎﺷﺪ

Background and Purpose: One of the most important topics in Persian Medicine is the knowledge of temperament identification and many of the instructions for preserving health, diagnosis and treatment of diseases are different based on the individualchr('39')s temperament. Discovering and recognizing standard methods of temperament determination, is one of the most important research priorities in Persian Medicine. In this research, fuzzy decision tree for data classification and Genetic Algorithm (GA) to optimize the features necessary for the diagnosis of temperament is used. Materials and Methods: In this study, two datasets with 52 and 221 samples were used. For datasets, data recognition and modeling Mizaj (Temperament) diagnosis based on fuzzy decision tree with GA was performed. To do this, first, a subset of features was selected using GA and then a fuzzy decision tree was used to make the rules. Results: For each dataset, two decision trees were generated for warmth/cold and wet/dry and the produced rules by the Persian Medicine specialist were evaluated. The results showed that the produced correct rules in the second dataset are 44% for warm/cold Mizaj and 33% for wet/dry Mizaj. In the first dataset, the generated correct rules by the fuzzy decision tree with the GA for wet/dry Mizaj was 9.5%. Conclusion: Comparison of the results with the previous research shows that the use of GA and subset selection of features, reduces the computational volume, size of the tree and error percentage so that better results can be achieved. Although, according to Persian Medicine experts’ opinion, the results of this research are not currently applicable, they can be a starting point for further researches in the optimization of intelligent swarm algorithms for the diagnosis of Mizaj.