Linear discriminant analysis (LDA) is a simple but widely used algorithm in pattern recognition. However it has some shortcomings in that it is sensitive to outliers and limited to linearly separable cases. To solve this problem a new version of nonlinear discriminant algorithm is proposed. This new version, SC-LLE, uses LDA combined with LLE method to take into account non-linearly separable c...

Impurity profiling of methamphetamine (MA) using thermal desorption (TD) and gas chromatography-mass spectrometry (GC-MS) was examined. Using TD/GC-MS, impurities were extracted and separated under various conditions. Optimal chromatograms were obtained when a 20 mg MA sample was extracted at 120 degrees C for 3 min using a TD instrument, followed by separation of the extracts using a non-polar...

Manifold learning addresses the problem of finding low–dimensional structure within collections of high–dimensional data. Recent interest in this problem was motivated by the development of a pair of algorithms, locally linear embedding (LLE) [6] and isometric feature mapping (IsoMap) [8]. Both methods use local, linear relationships to derive global, nonlinear structure, although their specifi...

Background: Several physiologically beneficial effects of consuming a whey protein hydrolysate (WPH) have been attributed to the greater availability of bioactive peptides. Aims: The aim was to investigate the effect of four branched-chain amino acid- (BCAA-)containing dipeptides, present in WPH, on immune modulation, stimulation of HSP expression, muscle protein synthesis, glycogen content, sa...

Locally linear embedding (LLE) is a recently proposed method for unsupervised nonlinear dimensionality reduction. It has a number of attractive features: it does not require an iterative algorithm, and just a few parameters need to be set. Two extensions of LLE to supervised feature extraction were independently proposed by the authors of this paper. Here, both methods are unified in a common f...

Current practice in Quantitative Structure Activity Relationship (QSAR) methods usually involves generating a great number of chemical descriptors and then cutting them back with variable selection techniques. Variable selection is an effective method to reduce the dimensionality but may discard some valuable information. This paper introduces Locally Linear Embedding (LLE), a local non-linear ...

In this report, the student presents her study on a multivariate visualization task. Specifically, the student would like to learn the use of Locally Linear Embedding (LLE) for visualization. While the experiment is using Wisconsin Breast Cancer dataset, the method is more generally applicable to other high-dimensional data as well. Three experiments were run to visualize the dataset. The three...

The capabilities of learning and memory in parents are presumably transmitted to their offsprings, in which genetic codes and epigenetic regulations are thought as molecular bases. As neural plasticity occurs during memory formation as cellular mechanism, we aim to examine the correlation of activity strengths at cortical glutamatergic and GABAergic neurons to the transgenerational inheritance ...

Liquid-liquid equilibrium (LLE) data correlation of multicomponent mixtures is frequently carried out without using any procedure to ensure that the model parameters obtained for totally miscible binary are consistent with such behavior (i.e. they do not lead two liquid phases in equilibrium). In other words, beyond LLE region fitted (experimental tie-lines) usually considered correlations. It ...

Locally Linear Embedding (LLE) is a nonlinear dimensionality reduction method proposed recently. It can reveal the intrinsic manifold of data, which can’t be provided by classical linear dimensionality reduction methods. The application of LLE, however, is limited because of its lack of a mapping between the observation and the low-dimensional output. In this paper, we propose a method to estab...