Shape vs. volume: Invariant shape descriptors for 3D region of interest characterization in MRI

We propose a new approach for quantifying regions of interest (ROIs) in medical image data. Rotationally invariant shape descriptors (ISDs) were applied to 3D brain regions extracted from MRI scans of 5 Parkinson's patients and 10 control subjects. We concentrated on the thalamus and the caudate nucleus since prior studies have suggested they are affected in Parkinson's disease (PD). In the caudate, both the ISD and volumetric analyses found significant differences between control and PD subjects. The ISD analysis however revealed additional differences between the left and right caudate nuclei in both control and PD subjects. In the thalamus, the volumetric analysis showed significant differences between PD and control subjects, while ISD analysis found significant differences between the left and right thalami in control subjects but not in PD patients, implying disease-induced shape changes. These results suggest that employing ISDs for ROI characterization both complements and extends traditional volumetric analyses. © 2006 IEEE.

A neurophysiologically plausible population code model for feature integration explains visual crowding.

An object in the peripheral visual field is more difficult to recognize when surrounded by other objects. This phenomenon is called "crowding". Crowding places a fundamental constraint on human vision that limits performance on numerous tasks. It has been suggested that crowding results from spatial feature integration necessary for object recognition. However, in the absence of convincing models, this theory has remained controversial. Here, we present a quantitative and physiologically plausible model for spatial integration of orientation signals, based on the principles of population coding. Using simulations, we demonstrate that this model coherently accounts for fundamental properties of crowding, including critical spacing, "compulsory averaging", and a foveal-peripheral anisotropy. Moreover, we show that the model predicts increased responses to correlated visual stimuli. Altogether, these results suggest that crowding has little immediate bearing on object recognition but is a by-product of a general, elementary integration mechanism in early vision aimed at improving signal quality.

A Maximum-Likelihood Interpretation for Slow Feature Analysis

The brain extracts useful features from a maelstrom of sensory information, and a fundamental goal of theoretical neuroscience is to work out how it does so. One proposed feature extraction strategy is motivated by the observation that the meaning of sensory data, such as the identity of a moving visual object, is often more persistent than the activation of any single sensory receptor. This notion is embodied in the slow feature analysis (SFA) algorithm, which uses “slowness” as an heuristic by which to extract semantic information from multi-dimensional time-series. Here, we develop a probabilistic interpretation of this algorithm showing that inference and learning in the limiting case of a suitable probabilistic model yield exactly the results of SFA. Similar equivalences have proved useful in interpreting and extending comparable algorithms such as independent component analysis. For SFA, we use the equivalent probabilistic model as a conceptual spring-board, with which to motivate several novel extensions to the algorithm.

On the relation of slow feature analysis and Laplacian eigenmaps

The past decade has seen a rise of interest in Laplacian eigenmaps (LEMs) for nonlinear dimensionality reduction. LEMs have been used in spectral clustering, in semisupervised learning, and for providing efficient state representations for reinforcement learning. Here, we show that LEMs are closely related to slow feature analysis (SFA), a biologically inspired, unsupervised learning algorithm originally designed for learning invariant visual representations. We show that SFA can be interpreted as a function approximation of LEMs, where the topological neighborhoods required for LEMs are implicitly defined by the temporal structure of the data. Based on this relation, we propose a generalization of SFA to arbitrary neighborhood relations and demonstrate its applicability for spectral clustering. Finally, we review previous work with the goal of providing a unifying view on SFA and LEMs. © 2011 Massachusetts Institute of Technology.

A theory of slow feature analysis for transformation-based input signals with an application to complex cells

We develop a group-theoretical analysis of slow feature analysis for the case where the input data are generated by applying a set of continuous transformations to static templates. As an application of the theory, we analytically derive nonlinear visual receptive fields and show that their optimal stimuli, as well as the orientation and frequency tuning, are in good agreement with previous simulations of complex cells in primary visual cortex (Berkes and Wiskott, 2005). The theory suggests that side and end stopping can be interpreted as a weak breaking of translation invariance. Direction selectivity is also discussed. © 2011 Massachusetts Institute of Technology.

The Supervised IBP: Neighbourhood Preserving Infinite Latent Feature Models

We propose a probabilistic model to infer supervised latent variables in the Hamming space from observed data. Our model allows simultaneous inference of the number of binary latent variables, and their values. The latent variables preserve neighbourhood structure of the data in a sense that objects in the same semantic concept have similar latent values, and objects in different concepts have dissimilar latent values. We formulate the supervised infinite latent variable problem based on an intuitive principle of pulling objects together if they are of the same type, and pushing them apart if they are not. We then combine this principle with a flexible Indian Buffet Process prior on the latent variables. We show that the inferred supervised latent variables can be directly used to perform a nearest neighbour search for the purpose of retrieval. We introduce a new application of dynamically extending hash codes, and show how to effectively couple the structure of the hash codes with continuously growing structure of the neighbourhood preserving infinite latent feature space.

Multilinear function factorisation for time series feature extraction

This work applies a variety of multilinear function factorisation techniques to extract appropriate features or attributes from high dimensional multivariate time series for classification. Recently, a great deal of work has centred around designing time series classifiers using more and more complex feature extraction and machine learning schemes. This paper argues that complex learners and domain specific feature extraction schemes of this type are not necessarily needed for time series classification, as excellent classification results can be obtained by simply applying a number of existing matrix factorisation or linear projection techniques, which are simple and computationally inexpensive. We highlight this using a geometric separability measure and classification accuracies obtained though experiments on four different high dimensional multivariate time series datasets. © 2013 IEEE.

Species identification of Chinese sturgeon using acoustic descriptors and ascertaining their spatial distribution in the spawning ground of Gezhouba Dam

This study has developed an improved subjective approach of classification in conjunction with Step wise DFA analysis to discriminate Chinese sturgeon signals from other targets. The results showed that all together 25 Chinese sturgeon echo-signals were detected in the spawning ground of Gezhouba Dam during the last 3 years, and the identification accuracy reached 90.9%. In Stepwise DFA, 24 out of 67 variables were applied in discrimination and identification. PCA combined with DFA was then used to ensure the significance of the 24 variables and detailed the identification pattern. The results indicated that we can discriminate Chinese sturgeon from other fish species and noise using certain descriptors such as the behaviour variables, echo characteristics and acoustic cross-section characteristics. However, identification of Chinese sturgeon from sediments is more difficult and needs a total of 24 variables. This is due to the limited knowledge about the acoustic-scattering properties of the substrate regions. Based on identified Chinese sturgeon individuals, 18 individuals were distributed in the region between the site of Gezhouba Dam and Miaozui reach, with a surface area of about 3.4 km(2). Seven individuals were distributed in the region between Miaozui and Yanshouba reach, with a surface area of about 13 km(2).

Tandem system adaptation using multiple linear feature transforms

Adaptation to speaker and environment changes is an essential part of current automatic speech recognition (ASR) systems. In recent years the use of multi-layer percpetrons (MLPs) has become increasingly common in ASR systems. A standard approach to handling speaker differences when using MLPs is to apply a global speaker-specific constrained MLLR (CMLLR) transform to the features prior to training or using the MLP. This paper considers the situation when there are both speaker and channel, communication link, differences in the data. A more powerful transform, front-end CMLLR (FE-CMLLR), is applied to the inputs to the MLP to represent the channel differences. Though global, these FE-CMLLR transforms vary from time-instance to time-instance. Experiments on a channel distorted dialect Arabic conversational speech recognition task indicates the usefulness of adapting MLP features using both CMLLR and FE-CMLLR transforms. © 2013 IEEE.

An extension of slow feature analysis for nonlinear blind source separation

We present and test an extension of slow feature analysis as a novel approach to nonlinear blind source separation. The algorithm relies on temporal correlations and iteratively reconstructs a set of statistically independent sources from arbitrary nonlinear instantaneous mixtures. Simulations show that it is able to invert a complicated nonlinear mixture of two audio signals with a high reliability. The algorithm is based on a mathematical analysis of slow feature analysis for the case of input data that are generated from statistically independent sources. © 2014 Henning Sprekeler, Tiziano Zito and Laurenz Wiskott.

Wavelet denoising and feature extraction of seismic signal for footstep detection

Seismic sensors are widely used to detect moving target in ground sensor networks. Footstep detection is very important for security surveillance and other applications. Because of non-stationary characteristic of seismic signal and complex environment conditions, footstep detection is a very challenging problem. A novel wavelet denoising method based on singular value decomposition is used to solve these problems. The signal-to-noise ratio (SNR) of raw footstep signal is greatly improved using this strategy. The feature extraction method is also discussed after denosing procedure. Comparing, with kurtosis statistic feature, the wavelet energy feature is more promising for seismic footstep detection, especially in a long distance surveillance.

Thermal induced facet destructive feature of quantum cascade lasers

We present a study on the facet damage profile of quantum cascade lasers (QCLs). Conspicuous cascade half-loop damage strips on front facet are observed when QCLs catastrophically failed. Due to the large difference on thermal conductivities between active region and the substrate, dominant heat is compulsively driven to the substrate. Abundant heat accumulation and dissipation on substrate build large temperature gradient and thermal lattice mismatch. Thermal-induced stress due to sequential mismatch leads to the occurrence of the multistep damages on front facet. Good agreement is achieved between the observed locations of damaged strips and the calculated results.