Abstract-A novel non-linear dimensionality reduction method, called Temporal Laplacian Eigenmaps, is introduced to process efficiently time series data. In this embedded-based approach, temporal information is intrinsic to the objective function, which produces description of low dimensional spaces with time coherence between data points. Since the proposed scheme also includes bidirectional mapping between data and embedded spaces and automatic tuning of key parameters, it offers the same benefits as mapping-based approaches. Experiments on a couple of computer vision applications demonstrate the superiority of the new approach to other dimensionality reduction method in term of accuracy. Moreover, its lower computational cost and generalisation abilities suggest it is scalable to larger datasets.

No abstract

Abstract. We introduce a novel approach to automatically learn intuitive and compact descriptors of human body motions for activity recognition. Each action descriptor is produced, first, by applying Temporal Laplacian Eigenmaps to view-dependent videos in order to produce a stylistic invariant embedded manifold for each view separately. Then, all view-dependent manifolds are automatically combined to discover a unified representation which model in a single three dimensional space an action independently from style and viewpoint. In addition, a bidirectional nonlinear mapping function is incorporated to allow projecting actions between original and embedded spaces. The proposed framework is evaluated on a real and challenging dataset (IXMAS), which is composed of a variety of actions seen from arbitrary viewpoints. Experimental results demonstrate robustness against style and view variation and match the most accurate action recognition method.

A novel embedding-based dimensionality reduction approach, called structural Laplacian Eigenmaps, is proposed to learn models representing any concept that can be defined by a set of multivariate sequences. This approach relies on the expression of the intrinsic structure of the multivariate sequences in the form of structural constraints, which are imposed on dimensionality reduction process to generate a compact and data-driven manifold in a low dimensional space. This manifold is a mathematical representation of the intrinsic nature of the concept of interest regardless of the stylistic variability found in its instances. In addition, this approach is extended to model jointly several related concepts within a unified representation creating a continuous space between concept manifolds. Since a generated manifold encodes the unique characteristic of the concept of interest, it can be employed for classification of unknown instances of concepts. Exhaustive experimental evaluation on different datasets confirms the superiority of the proposed methodology to other state-of-the-art dimensionality reduction methods. Finally, the practical value of this novel dimensionality reduction method is demonstrated in three challenging computer vision applications, i.e., view-dependent and view-independent action recognition as well as human-human interaction classification.

Purpose -A highly accurate method of current spectrum estimation of a nonlinear load is presented in this paper. Using the method makes it possible to evaluate the current injection frequency domain model of a nonlinear load from previously recorded time domain voltage and current waveforms. The paper aims to discuss these issues. Design/methodology/approach -The method incorporates the idea of coherent resampling (resampling synchronously with the base frequency of the signal) followed by the discrete Fourier transform (DFT) to obtain the frequency spectrum. When DFT is applied to a synchronously resampled signal, the spectrum is free of negative DFT effects (the spectrum leakage, for example). However, to resample the signal correctly it is necessary to know its base frequency with high accuracy. To estimate the base frequency, the first-order Prony's frequency estimator was used. Findings -It has been shown that the presented method may lead to superior results in comparison with window interpolated Fourier transform and time-domain quasi-synchronous sampling algorithms.Research limitations/implications -The method was designed for steady-state analysis in the frequency domain. The voltage and current waveforms across load terminals should be recorded simultaneously to allow correct voltage/current phase shift estimation. Practical implications -The proposed method can be used in case when the frequency domain model of a nonlinear load is desired and the voltage and current waveforms recorded across load terminals are available. The method leads to correct results even when the voltage/current sampling frequency has not been synchronized with the base frequency of the signal. It can be used for off-line frequency model estimation as well as in real-time DSP systems to restore coherent sampling of the analysed signals. Originality/value -The method proposed in the paper allows to estimate a nonlinear load frequency domain model from current and voltage waveforms with higher accuracy than other competitive methods, while at the same time its simplicity and computational efficiency is retained.