This work presents a framework to recognise signer independent mouthings in continuous sign language, with no manual annotations needed. Mouthings represent lip-movements that correspond to pronunciations of words or parts of them during signing. Research on sign language recognition has focused extensively on the hands as features. But sign language is multi-modal and a full understanding part...

The present study carries out output-only modal analysis using two blind source separation (BSS) techniques, namely independent component analysis and second-order blind identification. The concept of virtual source is exploited and renders the application of these BSS techniques possible. The proposed modal analysis method is illustrated using numerical and experimental examples. r 2007 Elsevi...

Decades ago, a major concern of structural engineers was the development and application of new and powerful numerical methods for the static and dynamic analysis of large civil engineering structures. The rapid development of finite-element techniques accompanied by tremendous technological progress in the field of personal computers allowed structural designers to use software packages for ac...

Speech perception involves multiple input modalities. Research has indicated that perceivers establish cross-modal associations between auditory and visuospatial events to aid perception. Such intermodal relations can be particularly beneficial for speech development and learning, where infants and non-native perceivers need additional resources to acquire and process new sounds. This study exa...

Civil engineering structures are often subjected to multidirectional actions such as earthquake ground motion, which lead to complex structural responses. The contributions from the latter multidirectional actions to the response are highly coupled, leading to a MIMO system identification problem. Compared with single-input, multiple-output (SIMO) system identification, MIMO problems are more c...

Many activities in modal analysis research and applications are classified under the general area of the inverse problem. Examples are modal parameter identification, parameter identification, finite element model updating and damage detection, among others. These type of problems usually result in a system of linear equations that are characterized by one or both of the following: (a) Ill cond...

Random Decrement Technique (RDT) based decentralized computing approaches implemented in wireless sensor networks (WSNs) have shown advantages for modal parameters and data aggregation identification. However, previous studies of RDT-based approaches from ambient vibration data have usually assumed that the input excitation is a broad-band stochastic process modeled by stationary white or filte...

The success of vibration-based damage identification procedures depends significantly on the accuracy and completeness of the available identified modal parameters. This paper investigates the level of confidence in the damage identification results as a function of uncertainty in the identified modal parameters through a probabilistic damage identification strategy, i.e., Bayesian finite eleme...