Supervised linear classification of Gaussian spatio-temporal data

In this article we focus on the problem of supervised classifying of the spatio-temporal Gaussian random field observation into one of two classes, specified by different mean parameters. The main distinctive feature of the proposed approach is allowing the class label to depend on spatial location as well as on time moment. It is assumed that the spatio-temporal covariance structure factors into a purely spatial component and a purely temporal component following AR(p) model. In numerical illustrations with simulated data, the influence of the values of spatial and temporal covariance parameters to the derived error rates for several prior probabilities models are studied.

Download Full-text

Classification of Gaussian spatio-temporal data with stationary separable covariances

Nonlinear Analysis Modelling and Control ◽

10.15388/namc.2021.26.22359 ◽

2021 ◽

Vol 26 (2) ◽

pp. 363-374

Author(s):

Marta Karaliutė ◽

Kęstutis Dučinskas

Keyword(s):

Gaussian Random Field ◽

Error Rates ◽

Small Error ◽

Classification Rule ◽

Temporal Data ◽

Spatial Covariance ◽

Covariance Functions ◽

Novel Approach ◽

Spatio Temporal

The novel approach to classification of spatio-temporal data based on Bayes discriminant functions is developed. We focus on the problem of supervised classifying of the spatiotemporal Gaussian random field (GRF) observation into one of two classes specified by different drift parameters, separable nonlinear covariance functions and nonstationary label field. The performance of proposed classification rule is validated by the values of local Bayes and empirical error rates realized by leave one out procedure. A simulation study for spatial covariance functions belonging to powered-exponential family and temporal covariance functions of AR(1) models is carried out. The influence of the values of spatial and temporal covariance parameters to error rates for several label field models are studied. The results showed that the proposed classification methodology can be applied successfully in practice with small error rates and can be a useful tool for discriminant analysis of spatio-temporal data.

Download Full-text

Error rates in spatial classification of Gaussian data with random labeling

Lietuvos matematikos rinkinys ◽

10.15388/lmr.2010.77 ◽

2010 ◽

Vol 51 ◽

Author(s):

Lijana Stabingienė ◽

Kęstutis Dučinskas

Keyword(s):

Random Field ◽

Error Rate ◽

Field Model ◽

Gaussian Random Field ◽

Parametric Uncertainty ◽

Error Rates ◽

Spatial Classification ◽

Random Labeling ◽

Gaussian Data

In spatial classification it is usually assumed that features observations given labels are independently distributed. We have retracted this assumption by proposing stationary Gaussian random field model for features observations. The label are assumed to follow Disrete Random Field (DRF) model. Formula for exact error rate based on Bayes discriminant function (BDF) is derived. In the case of partial parametric uncertainty (mean parameters and variance are unknown), the approximation of the expected error rate associated with plug-in BDF is also derived. The dependence of considered error rates on the values of range and clustering parameters is investigated numerically for training locations being second-order neighbors to location of observation to be classified.

Download Full-text

Effect of anisotropy coeficient on error rates of linear discriminant functions

Lietuvos matematikos rinkinys ◽

10.15388/lmr.2007.24228 ◽

2021 ◽

Vol 47 ◽

Author(s):

Kęstutis Dučinskas ◽

Lina Dreižienė

Keyword(s):

Spatial Data ◽

Supervised Classification ◽

Statistical Approach ◽

Gaussian Random Field ◽

Error Rates ◽

Discriminant Functions ◽

Linear Discriminant ◽

Recognition Error ◽

Two Populations

Paper deals with statistical classification of spatial data as a part of widely applicable statistical approach to pattern recognition. Error rates in supervised classification of Gaussian random field observation into one of two populations specified by different constant means and common stationary geometric anisotropic covariance are considered. Formula for the exact Bayesian error rate is derived. The influence of the ratio of anisotropy to the error rates is evaluated numerically for the case of complete parametric certainty.

Download Full-text

Cancellation of Towing Ship Interference in Passive SONAR in a Shallow Ocean Environment

Defence Science Journal ◽

10.14429/dsj.72.17370 ◽

2022 ◽

Vol 72 (1) ◽

pp. 122-132

Author(s):

Remadevi M. ◽

N. Sureshkumar ◽

R. Rajesh ◽

T. Santhanakrishnan

Keyword(s):

Long Range ◽

Simulated Data ◽

Interference Signal ◽

Spectral Leakage ◽

Low Snr ◽

Eigenvector Analysis ◽

Spatio Temporal ◽

Ocean Environment ◽

Space Time Adaptive Processing

Towed array sonars are preferred for detecting stealthy underwater targets that emit faint acoustic signals in the ocean, especially in shallow waters. However, the towing ship being near to the array behaves as a loud target, introducing additional interfering signals to the array, severely affecting the detection and classification of potential targets. Canceling this underlying interference signal is a challenging task and is investigated in this paper for a shallow ocean operational scenario where the problem is more critical due to the multipath phenomenon. A method exploiting the eigenvector analysis of spatio-temporal covariance matrix based on space time adaptive processing is proposed for suppressing tow ship interference and thus improving target detection. The developed algorithm learns the interference patterns in the presence of target signals to mitigate the interference across azimuth and to remove the spectral leakage of own-ship. The algorithm is statistically analyzed through a set of relevant metrics and is tested on simulated data that are equivalent to the data received by a towed linear array of acoustic sensors in a shallow ocean. The results indicate a reduction of 20-25dB in the tow ship interference power while the detection of long-range low SNR targets remain largely unaffected with minimal power-loss. In addition, it is demonstrated that the spectral leakage of tow ship, on multiple beams across the azimuth, due to multipath, is also alleviated leading to superior classification capabilities. The robustness of the proposed algorithm is validated by the open ocean experiment in the coastal shallow region of the Arabian Sea at Off-Kochi area of India, which produced results in close agreement with the simulations. A comparison of the simulation and experimental results with the existing PCI and ECA methods is also carried out, suggesting the proposed method is quite effective in suppressing the tow ship interference and is immensely beneficial for the detection and classification of long-range targets.

Download Full-text

Error rates in classification of multivariate Gaussian random field observation

Lithuanian Mathematical Journal ◽

10.1007/s10986-011-9142-4 ◽

2011 ◽

Vol 51 (4) ◽

pp. 477-485 ◽

Cited By ~ 2

Author(s):

Kęstutis Dučinskas

Keyword(s):

Random Field ◽

Field Observation ◽

Gaussian Random Field ◽

Error Rates ◽

Multivariate Gaussian

Download Full-text

Values in Action Inventory of Strengths (VIA-IS): Translation and Validation in Urdu Language

Pakistan Journal of Psychological Research ◽

10.33824/pjpr.2020.35.1.10 ◽

2020 ◽

Vol 35 (1) ◽

pp. 163-189

Author(s):

Afifa Anjum ◽

Naumana Amjad

Keyword(s):

Factor Structure ◽

Convergent Validity ◽

Character Strengths ◽

Future Studies ◽

Structure Factors ◽

Adult Participants ◽

Positive Correlations ◽

Cross Language ◽

Translation And Validation

Values in Action is a classification of 24 character strengths grouped under six virtue categories. This classification is claimed to be universal across cultures and religions (Peterson & Seligman, 2004) and its measure that is, Values in Action Inventory of Strengths (VIA-IS) has been translated and validated in many languages. The present study aimed at its Urdu translation and validation on Pakistani adults taken from different educational institutes and workplaces. Study comprised two parts. Part I dealt with the translation and cross-language validation while in Part II, Construct validation on a sample of 542 adults and convergent validity on a sample of 210 adult participants were determined. Findings revealed satisfactory alpha coefficients for Urdu version. Significant positive correlations with positive affect and life satisfaction and negative correlations with negative affect were indicators of its convergent validity. Age was negatively associated with five strengths whereas significant gender differences were found on seven strengths. Social desirability effects were nonsignificant. Strength-to-virtue level factor structure exploration resulted in a theoretically meaningful four factor structure. Factors were named as Interpersonal, Cognitive, Vitality, and Transcendence and were comparable to factor structures proposed in studies on VIA-IS from a few other cultures. The study offers a valid Urdu translation for use in future studies with adult Urdu speaking population.

Download Full-text

Extracting Spatio-temporal Feature for Classification of Event-related Potentials*

PROGRESS IN BIOCHEMISTRY AND BIOPHYSICS ◽

10.3724/sp.j.1206.2011.00123 ◽

2011 ◽

Vol 38 (9) ◽

pp. 866-871 ◽

Cited By ~ 1

Author(s):

Zhi-Hua HUANG ◽

Ming-Hong LI ◽

Yuan-Ye MA ◽

Chang-Le ZHOU

Keyword(s):

Event Related Potentials ◽

Related Potentials ◽

Spatio Temporal ◽

Temporal Feature

Download Full-text

Pyramidal Framework: Guidance for the Next Generation of GIS Spatial-Temporal Models

ISPRS International Journal of Geo-Information ◽

10.3390/ijgi10030188 ◽

2021 ◽

Vol 10 (3) ◽

pp. 188

Author(s):

Cyril Carré ◽

Younes Hamdani

Keyword(s):

Conceptual Models ◽

Future Generations ◽

Temporal Data ◽

Temporal Modeling ◽

Temporal Models ◽

Gis Data ◽

Spatio Temporal ◽

New Interpretation ◽

Conventional Literature

Over the last decade, innovative computer technologies and the multiplication of geospatial data acquisition solutions have transformed the geographic information systems (GIS) landscape and opened up new opportunities to close the gap between GIS and the dynamics of geographic phenomena. There is a demand to further develop spatio-temporal conceptual models to comprehensively represent the nature of the evolution of geographic objects. The latter involves a set of considerations like those related to managing changes and object identities, modeling possible causal relations, and integrating multiple interpretations. While conventional literature generally presents these concepts separately and rarely approaches them from a holistic perspective, they are in fact interrelated. Therefore, we believe that the semantics of modeling would be improved by considering these concepts jointly. In this work, we propose to represent these interrelationships in the form of a hierarchical pyramidal framework and to further explore this set of concepts. The objective of this framework is to provide a guideline to orient the design of future generations of GIS data models, enabling them to achieve a better representation of available spatio-temporal data. In addition, this framework aims at providing keys for a new interpretation and classification of spatio-temporal conceptual models. This work can be beneficial for researchers, students, and developers interested in advanced spatio-temporal modeling.

Download Full-text