Coding odor modality in piriform cortex efficiently with low-dimensional subspaces: a shared covariance decoding approach.

Fisher linear discriminant analysis (LDA) involves within-class and between-class covariance matrices. For 2-D data such as images, regularized LDA (RLDA) can improve LDA due to the regularized eigenvalues of the estimated within-class matrix. However, it fails to consider the eigenvectors and the estimated between-class matrix. To improve these two matrices simultaneously, we propose in this paper a new two-stage method for 2-D data, namely a bidirectional LDA (BLDA) in the first stage and the RLDA in the second stage, where both BLDA and RLDA are based on the Fisher criterion that tackles correlation. BLDA performs the LDA under special separable covariance constraints that incorporate the row and column correlations inherent in 2-D data. The main novelty is that we propose a simple but effective statistical test to determine the subspace dimensionality in the first stage. As a result, the first stage reduces the dimensionality substantially while keeping the significant discriminant information in the data. This enables the second stage to perform RLDA in a much lower dimensional subspace, and thus improves the two estimated matrices simultaneously. Experiments on a number of 2-D synthetic and real-world data sets show that BLDA+RLDA outperforms several closely related competitors.

Assessment of direct knowledge of the human olfactory system

Computational analyses of in-vivo cerebral activity show that gamma oscillations in the olfactory cortex originate from local feedback inhibition following each sniff and serve to segregate competing odor representations through a winner-take-all process, providing an optimal window to decode odor.

Hyperspectral image based automatic target recognition (ATR) systems often project the high dimensional hyperspectral reflectance signatures onto a lower dimensional subspace using techniques such as principal components analysis (PCA), Fisher's linear discriminant analysis (LDA) and stepwise LDA. In a general classification framework, these projections are sub-optimal, and in the absence of sufficient training data, are likely to be ill conditioned. In recent work, the authors proposed a divide and conquer approach that partitions the hyperspectral space into contiguous subspaces followed by multi-classifiers and decision fusion. Although this technique alleviated the small sample size problem and provided a good recognition performance in light and moderate pixel mixing, the performance significantly decreased under severe mixing conditions, as does with conventional ATR techniques. In this work, the authors propose a kernel discriminant analysis based projection in each subspace of the partition, followed by the multi-classifier, decision fusion framework to ensure robust recognition even in severe pixel mixing conditions. The performance of the proposed system (as measured by overall target recognition accuracies) is greatly superior to conventional dimensionality reduction techniques, as well as the more recently proposed divide-and-conquer technique.

A hunger for odour: Leptin modulation of olfaction.

Hyperspectral-based automatic target recognition (ATR) and classification systems often project the high-dimensional hyperspectral reflectance signatures onto a lower dimensional subspace using techniques such as principal component analysis, Fisher's linear discriminant analysis (LDA), and stepwise LDA. In a general classification framework, these projections are suboptimal and, in the absence of sufficient training data, are likely to be ill conditioned. In recent work, the authors proposed a divide-and-conquer approach that partitions the hyperspectral space into contiguous subspaces followed by a multiclassifier and decision-fusion (MCDF) framework. Although this technique alleviated the small-sample-size problem and provided a good recognition performance in light and moderate pixel mixing, the performance significantly decreased under severe mixing conditions, as it does with conventional ATR techniques. In this letter, the authors propose a kernel discriminant analysis-based projection in each subspace of the partition, followed by the MCDF framework to ensure robust recognition even in severe pixel-mixing conditions. The performance of the proposed system (as measured by overall recognition accuracies) is greatly superior to conventional dimensionality-reduction techniques as well as the more recently proposed LDA-based MCDF technique.

A computer vision system for automatic recognition and classification of five varieties of plant leaves under controlled laboratory imaging conditions, comprising: 1–Cydonia oblonga (quince), 2–Eucalyptus camaldulensis dehn (river red gum), 3–Malus pumila (apple), 4–Pistacia atlantica (mt. Atlas mastic tree) and 5–Prunus armeniaca (apricot), is proposed. 516 tree leaves images were taken and 285 features computed from each object including shape features, color features, texture features based on the gray level co-occurrence matrix, texture descriptors based on histogram and moment invariants. Seven discriminant features were selected and input for classification purposes using three classifiers: hybrid artificial neural network–ant bee colony (ANN–ABC), hybrid artificial neural network–biogeography based optimization (ANN–BBO) and Fisher linear discriminant analysis (LDA). Mean correct classification rates (CCR), resulted in 94.04%, 89.23%, and 93.99%, for hybrid ANN–ABC; hybrid ANN–BBO; and LDA classifiers, respectively. Best classifier mean area under curve (AUC), mean sensitivity, and mean specificity, were computed for the five tree varieties under study, resulting in: 1–Cydonia oblonga (quince) 0.991 (ANN–ABC), 95.89% (ANN–ABC), 95.91% (ANN–ABC); 2–Eucalyptus camaldulensis dehn (river red gum) 1.00 (LDA), 100% (LDA), 100% (LDA); 3–Malus pumila (apple) 0.996 (LDA), 96.63% (LDA), 94.99% (LDA); 4–Pistacia atlantica (mt. Atlas mastic tree) 0.979 (LDA), 91.71% (LDA), 82.57% (LDA); and 5–Prunus armeniaca (apricot) 0.994 (LDA), 88.67% (LDA), 94.65% (LDA), respectively.

Potentiation of late components in olfactory bulb and piriform cortex requires activation of cortical association fibers

Face recognition using direct, weighted linear discriminant analysis and modular subspaces

Olfactory dysfunction often emerges before cognitive symptoms and may signal early vulnerability to neurodegenerative processes. This study examined whether genetic risk, specifically the presence of the epsilon 4 allele in apolipoprotein E, is associated with altered functional connectivity between the hippocampus and olfactory-related brain regions. Resting-state functional imaging data from 126 participants (mean age = 71.8 years, SD = 6.9; 67 females) across a range of clinical stages were analyzed. Functional connectivity was computed between the hippocampus and four olfactory-related regions: anterior piriform cortex, posterior piriform cortex, olfactory bulb, and olfactory tract. Multiple regression models assessed whether genetic risk, age, sex, and clinical diagnosis predicted connectivity strength. Genetic risk was significantly associated with increased connectivity between the hippocampus and both the olfactory bulb and olfactory tract, while no significant effects were observed in the piriform cortex regions. Clinical diagnosis was not a significant predictor of connectivity in any region. These results suggest that genetic risk is linked to early functional reorganization in specific olfactory-hippocampal pathways, particularly the olfactory tract, independent of clinical disease stage. The olfactory-hippocampal network may serve as a sensitive target for detecting early brain changes associated with neurodegenerative risk.

Is there an association between microRNAs (miRNAs) and impaired sense of smell? This is an interesting and relevant topic related to how genes affect brain circuits and behaviour in health and disease. In the present volume of Acta Physiologica, Wu et al1 addressed this question using a multi-technique approach. miRNAs are small single-stranded nucleotides involved in RNA silencing and the post-transcriptional regulation of gene expression2; miRNA deficiency in VIP+ GABAergic interneurons (VIP+ INs) leads to cortical circuit dysfunction3; and VIP+ INs in the olfactory bulb (OB), the first relay station in the olfactory system, are known to play a role in circadian rhythm regulation of olfactory function.4 Wu et al ask whether miRNA expression in VIP+ neurons in the OB plays a role in olfaction. Wu et al1 ablated Dicer, an RNase III protein that cleaves double-stranded RNAs into miRNAs, to disrupt miRNA expression in postmitotic VIP+ INs and performed a sequence of experiments to assess the behavioural and circuit consequences of this cell-specific miRNA ablation. Both odour detection in a food-seeking task and odorant discrimination in a go-no-go associative learning task were disrupted by miRNA ablation. In vivo single unit and local field potential (LFP) recordings in the OB in head-fixed awake mice found a marked decrease in firing rate of mitral/tufted cells (M/Ts)—the projection neurons of the OB—and the power of beta oscillations in the OB and in the downstream target of MCs—the piriform cortex (PCx). Beta oscillations have been proposed to play a key role in transfer of information from the OB to PCx.5 Moreover, tetrode single unit recordings from the M/T layer after Dicer ablation in VIP+ INs in awake head-fixed mice demonstrated decreased odour-evoked firing in M/Ts. Finally, Wu et al1 showed that Dicer ablation restricted to the OB produced similar results. In conclusion, VIP miRNA ablation affects olfactory function and olfactory neural activity. Since miRNA function in processes such as circadian rhythm and olfaction is evolutionary conserved,6 those conclusions potentially could apply to other species as well. Further studies are required to investigate the changes in gene expression in the VIP+ Dicer-ablated mice, how these changes in gene expression alter function of VIP+ INs and the specific role of VIP+ INs in the neural circuit of the OB. The authors have declared no conflict of interest.

In this paper, we investigate the application of Fisher’s linear discriminant analysis (FLDA) to hyperspectral remote sensing image classification. The basic idea of FLDA is to design an optimal transform so that the classes can be well separated in the low-dimensional space. The practical difficulty of applying FLDA to hyperspectral images includes the unavailability of enough training samples and unknown information for all the classes present. So the original FLDA is modified to avoid the requirements of complete class knowledge, such as the number of actual classes present. We also investigate the performance of the class of principal component analysis (PCA) techniques prior to FLDA and find that the interference and noise adjusted PCA (INAPCA) can provide the improvement in the final classification.KeywordsFisher’s Linear Discriminant AnalysisDimensionality ReductionClassificationHyperspectral Imagery

Characterization and anatomical distribution of selective long-term potentiation in the olfactory forebrain

Olfactory system modulation of hippocampal cell death.

In this paper a novel non-linear subspace method for face verification is proposed. The problem of face verification is considered as a two-class problem (genuine versus impostor class). The typical Fisher's linear discriminant analysis (FLDA) gives only one or two projections in a two-class problem. This is a very strict limitation to the search of discriminant dimensions. As for the FLDA for N class problems (N is greater than two) the transformation is not person specific. In order to remedy these limitations of FLDA, exploit the individuality of human faces and take into consideration the fact that the distribution of facial images, under different viewpoints, illumination variations and facial expression is highly complex and non-linear, novel kernel discriminant algorithms are proposed. The new methods are tested in the face verification problem using the XM2VTS database where it is verified that they outperform other commonly used kernel approaches.