针对最小二乘孪生支持向量机(least squares twin support vector machine,LSTSVM)对噪声或是异常数据敏感和忽略数据内在结构信息的问题,提出了一种直觉模糊的结构化最小二乘孪生支持向量机(intuition fuzzy and structural least squa...针对最小二乘孪生支持向量机(least squares twin support vector machine,LSTSVM)对噪声或是异常数据敏感和忽略数据内在结构信息的问题,提出了一种直觉模糊的结构化最小二乘孪生支持向量机(intuition fuzzy and structural least squares twin support vector machine,IF-SLSTSVM)。首先采用孤立森林对输入样本点进行预处理;然后通过直觉模糊数的概念,赋予输入样本点不同的权重以减少噪声或是异常数据对分类超平面产生的影响;最后采用K-Means算法,以协方差的形式获取输入样本点之间的结构信息。IFSLSTSVM在LS-TSVM的基础上,考虑了输入样本点在特征空间中的分布信息及输入样本点之间的关系,提高了模型的鲁棒性。实验采取UCI数据集,在0%、5%、10%以及20%的不同比例噪声环境对IF-SLSTSVM算法的有效性进行验证。结果显示相较于6种对比算法,IF-SLSTSVM算法有更好的鲁棒性。展开更多
本文基于UCI机器学习库中的一家银行机构营销活动的数据,以客户是否认购定期存款为响应变量,以9个描述客户信息以及社会经济状况的离散和连续指标作为解释变量建立预测模型。提出了一种改进的弹球损失模糊支持向量机(Pin-FSVM)预测模型...本文基于UCI机器学习库中的一家银行机构营销活动的数据,以客户是否认购定期存款为响应变量,以9个描述客户信息以及社会经济状况的离散和连续指标作为解释变量建立预测模型。提出了一种改进的弹球损失模糊支持向量机(Pin-FSVM)预测模型,旨在提高金融服务行业中银行识别潜在客户认购定期存款的准确性和效率。Pin-FSVM模型通过融合弹球损失函数和模糊隶属度的概念,优化了传统模糊支持向量机的性能。该模型在含噪声数据环境下维持了预测准确率,并有效处理了数据中的不确定性。在应用于银行客户认购存款的预测实践中,Pin-FSVM成功识别出更可能选择定期存款的客户,显著提升了预测效果,为银行精准识别和服务客户群体提供了有力工具。This paper is based on data from the UCI machine learning repository on the marketing activities of a banking institution, with whether a customer subscribes to a time deposit as the response variable, and nine discrete and continuous indicators describing the customer’s information as well as his socio-economic status as the explanatory variables. In this paper, an improved Pinball Loss Fuzzy Support Vector Machine (Pin-FSVM) prediction model is proposed with the aim of improving the accuracy and efficiency of banks in the financial services industry in identifying potential customers to subscribe to time deposits. The Pin-FSVM model optimises the performance of the traditional fuzzy support vector machine by incorporating the concepts of the Pinball Loss Function and the Fuzzy Affiliation Degree. The model maintains prediction accuracy in noisy data environments and effectively handles the uncertainty in the data. In the application to the practice of predicting bank customers’ subscription deposits, Pin-FSVM successfully identifies customers who are more likely to choose time deposits, which significantly improves the prediction effect and provides a powerful tool for banks to accurately identify and serve their customer groups.展开更多
先进的故障诊断方法对保证工业机器人高效稳定运行具有重要作用。针对传统机器学习故障诊断的不足,利用模糊理论提高处理不确定信息的能力,构建一种协同模糊支持向量机(Synergetic Fuzzy Support Vector Machine,SFSVM)工业机器人故障...先进的故障诊断方法对保证工业机器人高效稳定运行具有重要作用。针对传统机器学习故障诊断的不足,利用模糊理论提高处理不确定信息的能力,构建一种协同模糊支持向量机(Synergetic Fuzzy Support Vector Machine,SFSVM)工业机器人故障诊断模型,并对其进行机制优化。在多论域空间结构下,综合处理工业机器人的不确定性信息运行状态监测数据和专家先验知识,提高了工业机器人故障诊断的适用性和鲁棒性。展开更多
文摘针对最小二乘孪生支持向量机(least squares twin support vector machine,LSTSVM)对噪声或是异常数据敏感和忽略数据内在结构信息的问题,提出了一种直觉模糊的结构化最小二乘孪生支持向量机(intuition fuzzy and structural least squares twin support vector machine,IF-SLSTSVM)。首先采用孤立森林对输入样本点进行预处理;然后通过直觉模糊数的概念,赋予输入样本点不同的权重以减少噪声或是异常数据对分类超平面产生的影响;最后采用K-Means算法,以协方差的形式获取输入样本点之间的结构信息。IFSLSTSVM在LS-TSVM的基础上,考虑了输入样本点在特征空间中的分布信息及输入样本点之间的关系,提高了模型的鲁棒性。实验采取UCI数据集,在0%、5%、10%以及20%的不同比例噪声环境对IF-SLSTSVM算法的有效性进行验证。结果显示相较于6种对比算法,IF-SLSTSVM算法有更好的鲁棒性。
文摘本文基于UCI机器学习库中的一家银行机构营销活动的数据,以客户是否认购定期存款为响应变量,以9个描述客户信息以及社会经济状况的离散和连续指标作为解释变量建立预测模型。提出了一种改进的弹球损失模糊支持向量机(Pin-FSVM)预测模型,旨在提高金融服务行业中银行识别潜在客户认购定期存款的准确性和效率。Pin-FSVM模型通过融合弹球损失函数和模糊隶属度的概念,优化了传统模糊支持向量机的性能。该模型在含噪声数据环境下维持了预测准确率,并有效处理了数据中的不确定性。在应用于银行客户认购存款的预测实践中,Pin-FSVM成功识别出更可能选择定期存款的客户,显著提升了预测效果,为银行精准识别和服务客户群体提供了有力工具。This paper is based on data from the UCI machine learning repository on the marketing activities of a banking institution, with whether a customer subscribes to a time deposit as the response variable, and nine discrete and continuous indicators describing the customer’s information as well as his socio-economic status as the explanatory variables. In this paper, an improved Pinball Loss Fuzzy Support Vector Machine (Pin-FSVM) prediction model is proposed with the aim of improving the accuracy and efficiency of banks in the financial services industry in identifying potential customers to subscribe to time deposits. The Pin-FSVM model optimises the performance of the traditional fuzzy support vector machine by incorporating the concepts of the Pinball Loss Function and the Fuzzy Affiliation Degree. The model maintains prediction accuracy in noisy data environments and effectively handles the uncertainty in the data. In the application to the practice of predicting bank customers’ subscription deposits, Pin-FSVM successfully identifies customers who are more likely to choose time deposits, which significantly improves the prediction effect and provides a powerful tool for banks to accurately identify and serve their customer groups.
文摘先进的故障诊断方法对保证工业机器人高效稳定运行具有重要作用。针对传统机器学习故障诊断的不足,利用模糊理论提高处理不确定信息的能力,构建一种协同模糊支持向量机(Synergetic Fuzzy Support Vector Machine,SFSVM)工业机器人故障诊断模型,并对其进行机制优化。在多论域空间结构下,综合处理工业机器人的不确定性信息运行状态监测数据和专家先验知识,提高了工业机器人故障诊断的适用性和鲁棒性。
