Pattern vectors from algebraic graph theory

Locality Preserving Projections (LPP) is a linear projective map that optimally preserves the neighborhood structure of the data set. Though LPP has been applied in many fields, it has limits to solve recognition problem. Thus, a new palmprint recognition method is proposed based on Kernel Locality Preserving Projections (KLPP). Different from LPP method, KLPP not only describes the nonlinear correlations between pixels, but also preserves the local structure of the palmprint image space. In this way, the unwanted variations resulting from in lighting may be eliminated or reduced. We compare our proposed approach with Principal Component Analysis (PCA), LPP and Kernel Principal Component Analysis (KPCA) methods on PolyU palmprint database. Experiment results demonstrate that KLPP achieves better recognition rate as the dimension of the palmprint subspace changes.

In the present work, appearance-based face recognition method called the Laplacianface approach is used. The face images are mapped into a face subspace for analysis by using Locality Preserving Projections(LPP). The technique is different from Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) which effectively see only the Euclidean structure of face space. The main goal of LPP is to preserve neighbourhood structure of the data set optimally and hence obtain a face subspace that best detects the essential face manifold structure. The Laplacianfaces are the optimal linear approximations to the Eigen functions of the Laplace Beltrami operator on the face manifold. Hence, by using this approach undesired variations because of facial expression, changes in lighting conditions, and pose may be eliminated or reduced. Performance analysis of face recognition is carried out on standard databases using both LPP technique and PCA technique. For comparison purpose, PCA with ANN classifier based on Back Propagation Feed Forward Neural Network is also developed and being used for training the input face images and then testing. LPP approach outperforms PCA with ANN, and provides better face representation and also achieves lower error rate.

This paper proposes a new pattern classification scheme, combining global and local features. The proposed method uses principal component analysis (PCA) for global property and locality preserving projections (LPP) for local property of the pattern. PCA is known for preserving the most descriptive ones after projection while LPP is known for preserving the neighborhood structure of the data set. Our combing method integrates global and local descriptive information and finds a richer set of alternatives beyond PCA and LPP in a 2-D parametric space. In order to find the hybrid features adaptively and find optimal parameters, we employ the genetic algorithm (GA). Experiments are performed with UCI machine learning repository to show the performance of the proposed algorithm.

A novel dimensionality reduction algorithm named “global–local preserving projections” (GLPP) is proposed. Different from locality preserving projections (LPP) and principal component analysis (PCA), GLPP aims at preserving both global and local structures of the data set by solving a dual-objective optimization function. A weighted coefficient is introduced to adjust the trade-off between global and local structures, and an efficient selection strategy of this parameter is proposed. Compared with PCA and LPP, GLPP is more general and flexible in practical applications. Both LPP and PCA can be interpreted under the GLPP framework. A GLPP-based online process monitoring approach is then developed. Two monitoring statistics, i.e., D and Q statistics, are constructed for fault detection and diagnosis. The case study on the Tennessee Eastman process illustrates the effectiveness and advantages of the GLPP-based monitoring method.

Face recognition technology has evolved as an enchanting solution to address the contemporary needs in order to perform identification and verification of identity claims. By advancing the feature extraction methods and dimensionality reduction techniques in the application of pattern recognition, a number of face recognition systems has been developed with distinct degrees of success. Locality preserving projection (LPP) is a recently proposed method for unsupervised linear dimensionality reduction. LPP preserve the local structure of face image space which is usually more significant than the global structure preserved by principal component analysis (PCA) and linear discriminant analysis (LDA). This paper focuses on a systematic analysis of locality-preserving projections and the application of LPP in combination with an existing technique This combined approach of LPP through MPCA can preserve the global and the local structure of the face image which is proved very effective. Proposed approach is tested using the AT & T face database. Experimental results show the significant improvements in the face recognition performance in comparison with some previous methods.

In this paper, a multimode process monitoring strategy based on improved just‐in‐time‐learning associated with locality preserving projections (IJITL‐LPP) is proposed. First, raw data are projected into the feature space using locality preserving projections (LPP). Second, IJITL searches for similar samples of the query sample in the feature space by introducing a variational inference Gaussian mixture model (VIGMM). Finally, the new statistic named average distance is created to complete process monitoring. In the IJITL, the introduced VI can automatically determine the number of modes, thereby accelerating the efficiency of selecting similar samples. In the process monitoring phase, the average distance can reduce the impact of different mode dispersion on fault detection. In addition, LPP can render the model less sensitive to outliers. Compared with principal component analysis (PCA), LPP, K nearest neighbour rules, Gaussian mixture model (GMM), K‐means based‐PCA, and just‐in‐time‐learning (JITL)‐based LPP, the proposed method has better performance in a numerical case, the Tennessee Eastman process, and the semiconductor etching process.

Exploring dimensionality reduction of EEG features in motor imagery task classification

With the deployment of collaborative robotics in industrial and domestic applications, intelligent robots are anticipated to work with humans in dynamically challenging daily life environments. Robots must deal with several photometric and spatio-temporal complexity in the workspace to achieve successful human-robot collaboration. To overcome these issues, especially in the case of vision-sensor-based systems, several robustness and adaptability measures need to be incorporated. One of such could be the adaptation of a concise and distinctive feature extraction tool for information-rich, high-dimensional data such as locality preserving projections (LPP). The locality information of the original higher-dimensional data is encoded and preserved in that weight parameter unlike principal component analysis (PCA) and linear discriminant analysis (LDA). This can be very much useful in real-life vision-sensor-based systems where the intrinsic locality structure of the images carries significant information. This paper proposes an LPP-based solution for a real-life human-supervised robot navigation guidance system. The proposed approach outperforms contemporary feature extraction techniques like PCA.

This doctoral thesis presents a framework for machine based interpretation of Malaysian Sign Language (MSL). The goal is to explore and develop necessary core algorithms that are capable of recognizing hand signs, based on the monocular/2D visual input of a low-cost hardware (Digital Webcam), without the assistance of visual-markers on hands. Successful hand sign interpretation with the aforementioned constrained visual system is challenging. Economical hardware devices often provide noisy/cluttered raw data with limited useful information. Non-involvement of visual markers imposes the requirement of additional strategies to disambiguate occlusions and background complexities. Natural variations in hand posture/gesture performances further convolute the recognition task. Addressing these challenges require computationally heavy algorithms in image processing, machine learning and pattern recognition. Thus vision-based sign language translator frameworks have to be multifaceted and versatile, in order to address innumerable practical concerns. In this research, hand postures interpretation is achieved by statistical projection methods. Analysis of high dimensional hand shape data is a complex task. Thus reducing dimensions via known projection methods aids in alleviating some of these complexities. Locality Preserving Projection (LPP) has been employed to accomplish this goal, while Principal Component Analysis (PCA) has been used as the benchmark method. Both methods were extensively tested against a hand posture database of 24 alphabet signs from MSL. As for the hand gesture interpretation, parameter-less Gaussian process based machine learning methods are proposed, as an alternative to current status quo. A variation of the Gaussian latent variable model – Gaussian Process Dynamic Model (GPDM) – has been employed for hand gesture interpretation. This has been comparatively studied against the established Hidden Markov Model (HMM). These machine learning methods were thoroughly tested against a hand gesture database of 64 signs from MSL. Grammatical sentence construction offers both intelligible sentences, and a mean of identifying erroneous sign classifications. In this thesis, a proof-of-concept on: use of Context Free Grammar (CFG) in successful parsing of meaningful sentences based on recognised gesture words, and how it can be extended in identifying (and correcting) erroneous sign classifications, is demonstrated with 92 sentences and the output of GPDM gesture classification. The novelty and contribution of this research: this is the first undertaking of markerless vision-based translation for MSL. Both LPP and GPDM are introduced to the sign language research field as an outcome of this investigation. The preliminary study and demonstration of grammatical sentence construction for translated gesture signs, is the first of its kind to the best of author's knowledge.

Although graph structures have proved useful in high level vision for object recognition and matching, they can prove computationally cumbersome because of the need to establish reliable correspondences between nodes. Hence, standard pattern recognition techniques can not be easily applied to graphs since feature vectors and not easily contructed. To overcome this problem, in this paper we turn to the spectral matrix. We show how the elements of this matrix can be used to construct symmetric polynomials that are permutation invariants. The co-efficients of these polynomials can be used as graph-features which can be encoded in a vectorial manner. We demonstrate that these vectors can be embedded in a low dimensional space using locally linear embedding, and that the embedding results in well defined graph clusters.

Irregular hour and suffering from stress cause driver doze and falling asleep during important situations. Therefore, it is necessary to know the mechanism of the sleeping. In this study, we distinct the sleep conditions by the rhythmic component extraction (RCE). By using this method, a particular EEG component is extracted as the weighted sum of multi-channel signals. This component concentrates the energy in a certain frequency range. Furthermore, when the weight of a specific channel is high, this channel is thought to be significant for extracting a focused frequency range. Therefore, the sleep conditions are analyzed by the power and the weight of RCE. As for weight analysis, the principal component analysis (PCA) and the locality preserving projection (LPP) are used to reduce the dimension. In the experiment, we measure the EEG in two conditions (before and during the sleeping). Comparing these EEGs by the RCE, the power of the alpha wave component decreased during the sleeping and the theta power increased. The weight distributions under two conditions did not significantly differ. It is to be solved in the further study.

Enhanced locality preserving projections using robust path based similarity

Dimensionality Reduction (DR) which tries to discover low-dimensional feature representation embedded into the high-dimensional observations are significant for data visualization and data preprocessing. However, most DR models are designed for vector-valued data while only few of them are for functional data where samples are considered as continuous data such as curves or surfaces compared to discrete vector-valued data. Motivated by Functional Principal Component Analysis (FPCA), which generalizes the idea of Principal Component Analysis (PCA) to the Hilbert space of square-integrable functions, in this paper we propose Functional Locality Preserving Projection (FLPP), where classic Locality Preserving Projection (LPP) is extended for functional data analysis. Different from FPCA which only focuses on the global structure, FLPP could preserve local manifold structure embedded into the functional data, thus FLPP is capable of dealing with noise data. Experimental results on both synthetic data and real-world data verify that FLPP outperforms FPCA and typical LPP.

The human brain is a complex system able to continuously adapt. How and where brain activity is modulated by behavior can be studied with functional magnetic resonance imaging (fMRI), a non-invasive neuroimaging technique with excellent spatial resolution and whole-brain coverage. FMRI scans of healthy adults completing a variety of behavioral tasks have greatly contributed to our understanding of the functional role of individual brain regions. However, by statistically analyzing each region independently, these studies ignore that brain regions act in concert rather than in unison. Thus, many studies since have instead examined how brain regions interact. Surprisingly, structured interactions between distinct brain regions not only occur during behavioral tasks but also while a subject rests quietly in the MRI scanner. Multiple groups of regions interact very strongly with each other and not only do these groups bear a striking resemblance to the sets of regions co-activated in tasks, but many of these interactions are also progressively disrupted in neurological diseases. This suggests that spontaneous fluctuations in activity can provide novel insights into fundamental organizing principles of the human brain in health and disease. Many techniques to date have segregated regions into spatially distinct networks, which ignores that any brain region can take part in multiple networks across time. A more natural view is to estimate dynamic brain networks that allow flexible functional interactions (or connectivity) over time. The estimation and analysis of such dynamic functional interactions is the subject of this dissertation. We take the perspective that dynamic brain networks evolve in a low-dimensional space and can be described by a small number of characteristic spatiotemporal patterns. Our proposed approaches are based on well-established statistical methods, such as principal component analysis (PCA), sparse matrix decompositions, temporal clustering, as well as a multiscale analysis by novel graph wavelet designs. We adapt and extend these methods to the analysis of dynamic brain networks. We show that PCA and its higher-order equivalent can identify co-varying functional interactions, which reveal disturbed dynamic properties in multiple sclerosis and which are related to the timing of stimuli for task studies, respectively. Further we show that sparse matrix decompositions provide a valid alternative approach to PCA and improve interpretability of the identified patterns. Finally, assuming an even simpler low-dimensional space and the exclusive temporal expression of individual patterns, we show that specific transient interactions of the medial prefrontal cortex are disturbed in aging and relate to impaired memory.

The time series clustering is one of the important research contents in the time series data mining. Since the dimension of time series is common high, the performance of direct raw time series data clustering is not ideal. How to improve the clustering performance of time series is the main research point of this paper. Firstly, use Locality Preserving Projection (LPP) to time series samples for dimensionality reduction; secondly, carry out clustering ensemble to the lowdimension data; finally, compare the clustering performance with the existing methods such as Principal Component Analysis (PCA) and Piecewise Aggregate Approximation (PAA). Experiment results show that the proposed method is superior to the compared methods.