We have developed Name-It, a system that associates faces and names in news videos. The system is given news videos, which include image sequences and transcripts obtained from audio tracks or closed caption texts. The system can then either infer possible name candidates for a given face, or locate a face in news videos by name. To accomplish this task, the system takes a multi-modal video ana...

A novel modal identification approach for the use of a wireless sensor network (WSN) for structural health monitoring is presented, in which the computational task is distributed among remote nodes to reduce the communication burden of the network and, as a result, optimize the time and energy consumption of the monitoring system. Considering the need for having an agile system to capture the e...

In this paper an attempt is made to develop speaker & gender identification system using continuous speech signal spoken in different languages as input. MFCCs and delta-MFCCs are used to build modal for classification . Radial basis function network is used for classification. Here resilient back propagation algorithm used to train Multilingual Speech signal . Two separate modules are used for...

In this research, the modal parameters of a beam in free-free condition are extracted by performing different experiments in laboratory. For this purpose, two different techniques are employed. The first methodology is considered as a time domain method in Operational Modal Analysis. While the other one is frequency domain impact hammer test which is categorized as an Experimental Modal Analysi...

This paper summarize the principles main methods for structural dynamic identification and presents the experiences in using operational modal analysis techniques in Civil Engineering field. Shown black-box modelling of system for describes the input-output relation of the system and given its application to 11 storey reinforced concrete building. The monitoring, experimental details and data-p...

It's important to understand the dynamic behavior of a structure under operating condition from the view point of vibration shapes of a structure on well excited frequency components and accurate identification of amplitude on each point of a structure. Operating Deflection Shapes (ODSs) can be defined for nonlinear and non stationary structural motion. ODSs provide very useful information for ...

In the wind tunnel test of a long-span bridge model, to ensure that dynamic characteristics model can satisfy design requirements, it is particularly important accurately identify modal parameters model. First, stochastic subspace identification algorithm was used analyze in test; then, Grubbs criterion introduced effectively eliminate outliers damping ratio matrix. Stochastic with improved acc...

Presenting structural damage detection problem as an inverse model-updating approach is one of the well-known methods which can reach to informative features of damages. This paper proposes a model-based method for fault prognosis in engineering structures. A new damage-sensitive cost function is suggested by employing the main concepts of the Modal Assurance Criterion (MAC) on the first severa...

The subject of structural health monitoring and damage identification of structures at the earliest possible stage has been a noteworthy topic for researchers in the last years. Modal strain energy (MSE) based index is one of the efficient methods which are commonly used for detecting damage in structures. It is also more effective and economical to employ some methods for reducing the degrees ...

We have developed Name-It, a system that associates faces and names in news videos. The system is given news videos, which include image sequences and transcripts obtained from audio tracks or closed caption texts. The system can then either infer possible name candidates for a given face, or locate a face in news videos by name. To accomplish this task, the system takes a multi-modal video ana...