學習向量量化神經網路拓璞於網路醫療診斷問題之分析

Learning Vector Quantization Neural Networks to Internet Medical Diagnosis Problems Analysis

黃建裕(Chien-Yu Huang) ； 潘信利(Hsin-Li Pan) ； 董建郎(Jian-Lang Dong)

《2008資通技術管理與應用會議》 2008 (2008/12) Pp. 411-425

摘要

由於目前醫院管理已經逐漸資訊化，而且醫療資料庫的引用也相當的普及，資料量的累積可說是與日遽增，相較之下傳統的人工方式並不適用於處理如此大量的資料，另外在於傳統的醫學診斷的過程中，大多也只能依靠著醫師以往的經驗來作出醫療的診斷。但由於現今疾病因素的多元化，如果能配合類神經網路的預測分類技術則可以輔助醫生來提高醫療診斷的正確率。本研究將針對網路醫療相關資料庫進行分類問題之研究，未來可應用於診斷的問題上，並可從龐大的醫療資料庫中，運用學習向量量化網路來建立預測分類器，並且在前置作業中選擇有意義的屬性，再進一步以田口實驗設計的方式來調整學習向量量化網路的核心參數，以得到較佳的分類正確率和運算效率，因此可以利用學習向量量化網路來輔助醫師診斷，以達到及早發現及早治療的目的。然而以往傳統的方式在於選擇與設計參數組合時，常依靠有經驗的技術人員，或利用試誤法的方式來找出較佳的參數組合，但這通常需耗費大量的時間與成本，因此需反覆的測試來找出較佳的參數組合，可以想像於實驗階段中需耗費相當多的時間及成本。所以本研究提出以學習向量量化網路建立分類預測器，並應用田口實驗設計，來找出類神經應用於網路醫療型資料庫之最佳參數組合，實驗結果顯示在於多種疾病分類上正確率皆可逹到九成以上，也可得知分類的效果優於其它分類系統。本研究所提出的最佳參數組合，能客觀的應用於多種的疾病分類上有效逹到不同品質特性的要求，並且也能有效的減少實驗中，重複測試的次數，使得在應用上更有效率。

關鍵字

類神經網路 ； 學習向量量化網路 ； 田口方法

並列摘要

Hospital information management has been computerized gradually, and the medical databases are now quite popular in contrast with traditional storage methods. The accumulation of information through database can be considered to be significant and there are many known and unknown hidden information waiting for our application. The traditional manual method is not applicable for a large number of information processing. Moreover, medical diagnosis can only rely on past experience of physicians and there are many diversified factors of disease. In this research, the aim is to provide forecast and classification technology by using Artificial Neural Network in order to support the doctors to improve diagnosis with high accuracy. In accordance with this aim, the research method is to address data set of Medical network to classification issues by using Learning Vector Quantization (LVQ) to establish the prediction and classification parameters as well as pre-operating it to choose the meaningful attributes. Furthermore, Taguchi Experimental Design Method (TEDM) approach is also used to adjust the LVQ core parameters in order to obtain the better classification rate and efficient computing processes. This method applied for Internet medical database with Try and Error repeating process to find out the ideal parameter portfolio. The experimental results show that, a variety of disease classification, the accurate rate is more than 90 per cent. Moreover, the ideal parameters portfolio found by using TEDM can reduce the number of repeated testing experiment as well as efficiently applied to other disease classification.

並列關鍵字

Artificial Neural Network ； Learning Vector Quantization ； Taguchi method