Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

1. Introduction and Overview. 2. Detecting Influential Observations and Outliers. 3. Detecting and Assessing Collinearity. 4. Applications and Remedies. 5. Research Issues and Directions for Extensions. Bibliography. Author Index. Subject Index.

Regression Diagnostics: Identifying Influential Data and Sources of Collinearity

Wavelet filter-based weak signature detection method and its application on rolling element bearing prognostics

Digital Coding of Waveforms

This article reviews various procedures used in the analysis of circadian rhythms at the populational, organismal, cellular and molecular levels. The procedures range from visual inspection of time plots and actograms to several mathematical methods of time series analysis. Computational steps are described in some detail, and additional bibliographic resources and computer programs are listed.

/pdf/procedures-for-numerical-analysis-of-circadian-rhythms-2s10ln0129.pdf

Procedures for numerical analysis of circadian rhythms.

A language family is a group of languages which have descended from a common mother language. Since the ancestor is common, these languages are expected to be similar in some respect and manifest the similarity in scientific experiments. In language identification, language-specific features are extracted from speech and a model is created which represents the language. This work extends the language identification framework to capture features common to language families and create models which can efficiently represent the language families. Mel frequency cepstral coefficient (MFCC) and speech signal-based frequency cepstral coefficient (SFCC) are used as primary feature extraction tools. A combination of these along with shifted delta coefficient (SDC) gives the final set of features. The work uses Gaussian mixture model (GMM) and support vector machines (SVM) as modelling tools. Different combinations of these feature extraction and modelling techniques are used to get four different systems: MFCC + SDC + GMM, SFCC + SDC + GMM, MFCC + SDC + SVM and SFCC + SDC + SVM. Experiments with these systems show that the language families can be identified with reasonable accuracy. Further, the work tests the influence of one language family on the other and finds that in most cases, the languages which are spoken in areas lying on the boundary of two families are more influenced by the other family. A deviation from it can relate to geopolitical isolation of two neighbouring regions and thus can give new insights or corroborate investigations of historians.

Identification of the Major Language Families of India and Evaluation of their Mutual Influence

https://doi.org/10.1016/j.specom.2022.11.005

Modulation spectral features for speech emotion recognition using deep neural networks

The perception of an external stimulus is not just stimulus-dependent but is also influenced by the ongoing brain activity prior to the presentation of stimulus. In this work, we directly tested whether spontaneous electroencephalogram (EEG) signal in prestimulus period could predict perceptual outcome in face pareidolia (visualizing face in noise images) on a trial-by-trial basis using machine learning framework. Participants were presented with only noise images but with the prior information that some faces would be hidden in these images while their electrical brain activities were recorded; participants reported their perceptual decision, face or no-face, on each trial. Using features based on the Regularized Common Spatial Patterns (RCSP) in a machine learning classifier, we demonstrated that prestimulus brain activities could discriminate face and no-face perception with an accuracy of 73.15%. The channels corresponding to the maximal coefficients of spatial pattern vectors may be the channels most correlated with the task-specific sources, i.e., frontal and parieto-occipital regions activate for ‘face’ and ‘no-face’ imagery class, respectively. These findings suggest a mechanism of how prior expectations in the prestimulus period may affect post-stimulus decision-making.

Investigating the Influence of Prior Expectation in Face Pareidolia using Spatial Pattern

Macroinvertebrates as engineers for bioturbation in freshwater ecosystem

Abstract Background Wetlands provide diverse ecological services to sustain rich biodiversity, but they are recklessly exploited around the globe. East Kolkata Wetlands (EKW; Ramsar site No. 1208, ~ 125 km 2 ) was once very rich in faunal diversity that declined over the years due to various anthropogenic pressures. In such scenarios, effective management plans need to contemplate local and landscape level initiatives and prioritize areas for conservation. Studying the foraging guild structure and spatial patterns of relationship between bird and its environment provides important insight of ecological processes of avifauna. Thus, we carried out extensive surveys in 142 point count stations to explore the diversity and foraging guild structure of birds in EKW. We addressed two important questions that how bird diversity varied from the outer periphery of the city towards the wetlands and how bird diversity is influenced by land cover features at local and landscape level in wetland complex. The goal of this study was to prepare a spatial map of avian diversity and to find the conservation priority areas for birds in this internationally recognized wetland complex. Results We recorded 94 species of birds and the Shannon diversity index values ranged between 1.249 and 3.189. We found that the avian diversity increased with increasing distance from city periphery. Omnivores and insectivores were the dominant foraging guilds, followed by carnivores, granivores, frugivores and piscivores. Generalized Linear Models revealed that bird communities were positively influenced by areas of wetlands, dikes and banks, agricultural field and emergent vegetation, and negatively influenced by built-up area. In the projected spatial map of species diversity, 74.15 km 2 area has high diversity. Finally, we identified 12.82 km 2 of top 10% conservation priority areas. Conclusions Low bird diversity near city periphery is related to habitat degradation due to anthropogenic pressure. Dominance of omnivores and insectivores indicates a possible impact of urbanization in EKW. We suggest that a mix of agricultural field, wetland areas and emergent vegetation helps to sustain a greater avian community. Besides, protection of conservation priority areas, restoration of the degraded habitats and reduction of threats (particularly in the north-eastern parts of EKW near the city periphery) will ensure the conservation of avifauna, and also the overall biodiversity of EKW. 

/pdf/influence-of-land-cover-features-on-avian-community-and-2ufsxsm2.pdf

Goutam Saha

Papers

Identification of the Major Language Families of India and Evaluation of their Mutual Influence

Modulation spectral features for speech emotion recognition using deep neural networks

Investigating the Influence of Prior Expectation in Face Pareidolia using Spatial Pattern

Macroinvertebrates as engineers for bioturbation in freshwater ecosystem

Influence of land cover features on avian community and potential conservation priority areas for biodiversity at a Ramsar site in India