The progression of converting depiction of medical analysis and measures into widespread medical code numbers is known as medical classification. According to the conclusion of medical investigation or description of medical handling, the classification of difficulty is resolved by means of the medical specialist in medical region. Primarily preprocessing is employed to alter appropriate model from unprocessed medical datasets in obtainable medical data classification process. After that, orthogonal local preserving projection (OLPP) is exploited to diminish the great dimensions of attribute. At last, the combination of artificial bee colony algorithm with neural network is used for classification of disease. This progression is extra time overriding and encompass poor exactness because classification is carry out devoid of removing the significant attribute from the medical dataset. Therefore, the proposed method is employed to eliminate of these difficulty. At this point the preprocessing is carrying out the medical dataset. It aids to eliminate the unnecessary noises and deficiency take place in the unprocessed medical datasets. Afterward feature choice is carry out. In medical data classification, feature choice is as well recognized as variable choice, attributes choice or variable subset choice which is the progression of choosing a subset of related attribute (variables, predictors). The ant lion optimization (ALO) is utilized for this intention. After that, classification is carrying out for distinguishing the occurrence and nonappearance of diseases. The intention is bring about by means of Modified Neuro Fuzzy classifier. The regulations engender through this classifier which are optimized by means of fruit fly optimization algorithm (FFOA). Therefore the medical data can be categorized into normal or abnormal one. This process task is quicker and generates extra precise consequences than the obtainable process. The presentation of the proposed process is calculated in expressions of accuracy, specificity and sensitivity value. The proposed process is executed in MATLAB.

将医学分析和措施的描述转换为广泛的医学代码编号的过程称为医学分类。根据医学调查的结论或医学处理的描述，通过医学领域的医学专家来解决困难的分类。在获得的医学数据分类过程中，主要采用预处理来从未处理的医学数据集中更改适当的模型。之后，利用正交局部保留投影（OLPP）来减小属性的巨大维度。最后，将人工蜂群算法与神经网络相结合，对疾病进行分类。由于进行分类时没有从医学数据集中删除重要属性，因此这种进展是多余的时间覆盖并包含较差的准确性。因此，采用所提出的方法消除了这些困难。此时，预处理正在进行医疗数据集。它有助于消除未处理的医学数据集中不必要的噪声和缺陷。之后进行功能选择。在医学数据分类中，特征选择也被认为是变量选择，属性选择或变量子集选择，这是选择相关属性子集（变量，预测变量）的过程。蚂蚁优化（ALO）用于此目的。之后，正在进行分类以区分疾病的发生和不出现。目的是通过改进的神经模糊分类器实现的。通过该分类器产生的法规通过果蝇优化算法（FFOA）进行了优化。因此，可以将医学数据分类为正常数据或异常数据。与可获得的过程相比，此过程任务更快，并且会产生更精确的结果。拟议过程的表示形式是通过准确性，特异性和敏感性值的表达来计算的。建议的过程在MATLAB中执行。因此，可以将医学数据分类为正常数据或异常数据。与可获得的过程相比，此过程任务更快，并且会产生更精确的结果。拟议过程的表示形式是通过准确性，特异性和敏感性值的表达来计算的。建议的过程在MATLAB中执行。因此，可以将医学数据分类为正常数据或异常数据。与可获得的过程相比，此过程任务更快，并且会产生更精确的结果。拟议过程的表示形式是通过准确性，特异性和敏感性值的表达来计算的。建议的过程在MATLAB中执行。