LEARNING FOR PATTERN CLASSIFICATION USING MULTI-OBJECTIVE PROGRAMMING AND ITS APPLICATON TO DIAGNOSIS SUPPORT SYSTEM OF DIABETIC ANGIOATHY

多目标规划学习模式分类及其在糖尿病血管病诊断支持系统中的应用

• 批准号: 06680414
• 负责人: NAKAYAMA Hirotaka
• 金额: $ 1.41万
• 依托单位: KONAN UNIVERSITY
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for General Scientific Research (C)
• 财政年份: 1994
• 资助国家: 日本
• 起止时间: 1994 至 1995
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-06680414/
• 关键词: pattern classification; neural networks; committee machine; multi-objective programming; diagnosis support system; diabetic macroangiopathy; diabetic microangiopathy; risk factors; 多目的決定; 線形計画法; 機械学習; 糖尿病; 大血管障害; 細小血管障害; 統計解析

In order to construct a diagnosis support system of diabetic angiopathy, we examined characteristic features of risk factors for macroangiopathy in 899 Japanese NIDDM with and without macroangiopathy. They were registered from 40 facilities by Multiclinical Study for Diabetic Macroangiopathy group. Three hundred eighty six subjects were identified as having macroangiopathy (MA (+) total) ; these includes 217 with ischemic heart disease (IHD), 169 with cerebrovascular disease (CVD), and 77 with peripheral vascular disease (PVD). Univariate and multivariate analyzes revealed the following factors for MA (+) total, IHD,CVD and PVD : age, fast blood sugar, hypertension, systolic blood pressure, diastolic blood pressure, duration of diabetes, diabetic microangiopathy, high-density lipoprotein cholesterol (HDL-C), low-density lipoprotein cholesterol (LDL-C), LDL-C : HDL-C ratio, brinkman index (smoking) and body mass index. In conclusion, in NIDDM patients, age, hypertension, systolic blood pressure, diastolic blood pressure and duration of diabetes were found to be risk factors for macroangiopathy.Technologies of machine learning is applied for supporting diagnosis. We developed two kinds of methods for pattern classification. One of them is a method for getting a piecewise linear discrimination function using fuzzy and/or multi-objective linear programming. The other is a committee machine which is a complex neural network consisting of several submodular neural networks. It has been observed that both methods can be effectively applied to our diagnosis problem.

为了构建糖尿病血管病变的诊断支持系统，我们对899例伴有和不伴有大血管病变的日本NIDDM患者的大血管病变危险因素特征进行了分析。他们来自40家医院，由糖尿病大血管病变多临床研究小组登记。386名受试者被确定为患有大血管病变（MA (+) total）；其中包括缺血性心脏病（IHD）患者217人，脑血管疾病（CVD）患者169人，周围血管疾病（PVD）患者77人。单因素和多因素分析显示：年龄、空腹血糖、高血压、收缩压、舒张压、糖尿病病程、糖尿病微血管病变、高密度脂蛋白胆固醇（HDL-C）、低密度脂蛋白胆固醇（LDL-C）、LDL-C: HDL-C比值、brinkman指数（吸烟）和体重指数是影响MA (+) total、IHD、CVD和PVD的因素。综上所述，在NIDDM患者中，年龄、高血压、收缩压、舒张压和糖尿病病程是大血管病变的危险因素。应用机器学习技术辅助诊断。我们开发了两种模式分类方法。其中之一是利用模糊和/或多目标线性规划求分段线性判别函数的方法。另一种是委员会机，它是由多个子模块神经网络组成的复杂神经网络。结果表明，这两种方法都能有效地应用于我们的诊断问题。

项目成果

Y.Hattori: "Adjacency Matrix Representations of Elementary Subordinations" Transactions of the Institute of Systems, Control and Information Engineers. Vol.7, No.12. 531-532 (1994)

Y.Hattori：“基本从属关系的邻接矩阵表示”系统、控制和信息工程师研究所的交易。

Y.Hattori: "Properties of Subordinate Relations Represented by Adjacency Matrices with Plural Connected Components" Transactions of the Institute of Systems, Control and Information Engineers. Vol.8, No.11. 665-666 (1995)

Y.Hattori：“由具有多个连通分量的邻接矩阵表示的从属关系的属性”系统、控制和信息工程师学会的交易。

Hirotaka Nakayama: "Engineering Applications of Multi-objective Programming : Recent Results" Multiple Criteria Decision Making,ed. by G. H. Tzeng,H. F. Wang,Springer. 369-378 (1994)

Hirotaka Nakayama：“多目标规划的工程应用：最新结果”多标准决策，编辑。

Hirotaka Nakayama: "Aspiration level approach to interactive multi-objective programming and its applications" Advances in Multicriteria Analysis ed. by P. M. Pardalos,Y. Siskos and C. Zopounidis.Kluwer. 147-174 (1995)

Hirotaka Nakayama：“交互式多目标编程的愿望水平方法及其应用”多标准分析进展编辑。

服部雄一: "基本従属の隣接行列の性質" システム制御情報学会論文誌. 8. 183-184 (1995)

Yuichi Hattori：“基本依赖的邻接矩阵的性质”，系统、控制和信息工程师学会汇刊，8. 183-184 (1995)。