Improved local tangent space alignment (ILTSA) is a recent nonlinear dimensionality reduction method which can efficiently recover the geometrical structure of sparse or non-uniformly distributed data manifold. In thi...Improved local tangent space alignment (ILTSA) is a recent nonlinear dimensionality reduction method which can efficiently recover the geometrical structure of sparse or non-uniformly distributed data manifold. In this paper, based on combination of modified maximum margin criterion and ILTSA, a novel feature extraction method named orthogonal discriminant improved local tangent space alignment (ODILTSA) is proposed. ODILTSA can preserve local geometry structure and maximize the margin between different classes simultaneously. Based on ODILTSA, a novel face recognition method which combines augmented complex wavelet features and original image features is developed. Experimental results on Yale, AR and PIE face databases demonstrate the effectiveness of ODILTSA and the feature fusion method.展开更多
针对局部切空间排列算法面临的无法利用样本标签信息和不能高效处理增量式维数约简问题,提出一种新的增量式监督局部切空间排列算法(Incremental Supervised Local Tangent Space Alignment,ISLTSA)。为充分利用训练样本标签信息,在LTS...针对局部切空间排列算法面临的无法利用样本标签信息和不能高效处理增量式维数约简问题,提出一种新的增量式监督局部切空间排列算法(Incremental Supervised Local Tangent Space Alignment,ISLTSA)。为充分利用训练样本标签信息,在LTSA算法的基础上加入散度矩阵,构造新的最小目标函数,使得高维样本的低维嵌入坐标同类聚集、异类分离。对于新增样本可能影响部分训练样本局部邻域,更新全局坐标矩阵,获取训练样本低维坐标和新增样本低维坐标,并作为初值进行特征值迭代实现所有样本全局坐标的更新。结合支持向量机分类算法,将ISLTSA算法应用于齿轮箱的故障状态识别,实验分析验证了该方法的监督学习能力,可提高故障状态识别率,并具备增量学习能力,可降低维数约简方法的复杂度。展开更多
局部切空间排列算法(Local Tangent Space Alignment)是一种具有严格数学推理的流形学习算法,能有效地学习出高维数据的低维嵌入坐标,但也存在一些不足,如对近邻点的选取依赖性较强、不适应处理高曲率分布、稀疏分布数据源。针对这些缺...局部切空间排列算法(Local Tangent Space Alignment)是一种具有严格数学推理的流形学习算法,能有效地学习出高维数据的低维嵌入坐标,但也存在一些不足,如对近邻点的选取依赖性较强、不适应处理高曲率分布、稀疏分布数据源。针对这些缺点,提出了一种基于几何距离摄动的局部切空间排列算法。利用几何摄动条件把样本空间划分为一组线性分块的组合,在每一个线性块上应用LTSA算法完成降维。实验结果表明了该算法的有效性。展开更多
基金the National Natural Science Foundation of China(No.61004088)the Key Basic Research Foundation of Shanghai Municipal Science and Technology Commission(No.09JC1408000)
文摘Improved local tangent space alignment (ILTSA) is a recent nonlinear dimensionality reduction method which can efficiently recover the geometrical structure of sparse or non-uniformly distributed data manifold. In this paper, based on combination of modified maximum margin criterion and ILTSA, a novel feature extraction method named orthogonal discriminant improved local tangent space alignment (ODILTSA) is proposed. ODILTSA can preserve local geometry structure and maximize the margin between different classes simultaneously. Based on ODILTSA, a novel face recognition method which combines augmented complex wavelet features and original image features is developed. Experimental results on Yale, AR and PIE face databases demonstrate the effectiveness of ODILTSA and the feature fusion method.
文摘针对局部切空间排列算法面临的无法利用样本标签信息和不能高效处理增量式维数约简问题,提出一种新的增量式监督局部切空间排列算法(Incremental Supervised Local Tangent Space Alignment,ISLTSA)。为充分利用训练样本标签信息,在LTSA算法的基础上加入散度矩阵,构造新的最小目标函数,使得高维样本的低维嵌入坐标同类聚集、异类分离。对于新增样本可能影响部分训练样本局部邻域,更新全局坐标矩阵,获取训练样本低维坐标和新增样本低维坐标,并作为初值进行特征值迭代实现所有样本全局坐标的更新。结合支持向量机分类算法,将ISLTSA算法应用于齿轮箱的故障状态识别,实验分析验证了该方法的监督学习能力,可提高故障状态识别率,并具备增量学习能力,可降低维数约简方法的复杂度。
基金国家自然科学基金(the National Natural Science Foundation of China under Grant No.61074018)
文摘局部切空间排列算法(Local Tangent Space Alignment)是一种具有严格数学推理的流形学习算法,能有效地学习出高维数据的低维嵌入坐标,但也存在一些不足,如对近邻点的选取依赖性较强、不适应处理高曲率分布、稀疏分布数据源。针对这些缺点,提出了一种基于几何距离摄动的局部切空间排列算法。利用几何摄动条件把样本空间划分为一组线性分块的组合,在每一个线性块上应用LTSA算法完成降维。实验结果表明了该算法的有效性。
