Recently clustering techniques have been used to automatically discover typical user profiles. In general, it is a challenging problem to design effective similarity measure between the session vectors which are usual...Recently clustering techniques have been used to automatically discover typical user profiles. In general, it is a challenging problem to design effective similarity measure between the session vectors which are usually high-dimensional and sparse. Two approaches for mining typical user profiles, based on matrix dimensionality reduction, are presented. In these approaches, non-negative matrix factorization is applied to reduce dimensionality of the session-URL matrix, and the projecting vectors of the user-session vectors are clustered into typical user-session profiles using the spherical k -means algorithm. The results show that two algorithms are successful in mining many typical user profiles in the user sessions.展开更多
On one hand, when the bridge stays in a windy environment, the aerodynamic power would reduce it to act as a non-classic system. Consequently, the transposition of the system’s right eigenmatrix will not equal its le...On one hand, when the bridge stays in a windy environment, the aerodynamic power would reduce it to act as a non-classic system. Consequently, the transposition of the system’s right eigenmatrix will not equal its left eigenmatrix any longer. On the other hand, eigenmatrix plays an important role in model identification, which is the basis of the identification of aerodynamic derivatives. In this study, we follow Scanlan’s simple bridge model and utilize the information provided by the left and right eigenmatrixes to structure a self-contained eigenvector algorithm in the frequency domain. For the purpose of fitting more accurate transfer function, the study adopts the combined sine-wave stimulation method in the numerical simulation. And from the simulation results, we can conclude that the derivatives identified by the self-contained eigenvector algorithm are more dependable.展开更多
文摘Recently clustering techniques have been used to automatically discover typical user profiles. In general, it is a challenging problem to design effective similarity measure between the session vectors which are usually high-dimensional and sparse. Two approaches for mining typical user profiles, based on matrix dimensionality reduction, are presented. In these approaches, non-negative matrix factorization is applied to reduce dimensionality of the session-URL matrix, and the projecting vectors of the user-session vectors are clustered into typical user-session profiles using the spherical k -means algorithm. The results show that two algorithms are successful in mining many typical user profiles in the user sessions.
基金supported by the State Key Program of National Natural Science Foundation of China (Grant No. 11032009)the National Natural Science Foundation of China (Grant No. 10772048)
文摘On one hand, when the bridge stays in a windy environment, the aerodynamic power would reduce it to act as a non-classic system. Consequently, the transposition of the system’s right eigenmatrix will not equal its left eigenmatrix any longer. On the other hand, eigenmatrix plays an important role in model identification, which is the basis of the identification of aerodynamic derivatives. In this study, we follow Scanlan’s simple bridge model and utilize the information provided by the left and right eigenmatrixes to structure a self-contained eigenvector algorithm in the frequency domain. For the purpose of fitting more accurate transfer function, the study adopts the combined sine-wave stimulation method in the numerical simulation. And from the simulation results, we can conclude that the derivatives identified by the self-contained eigenvector algorithm are more dependable.
