scholarly journals Spatial Classification with Limited Observations Based on Physics-Aware Structural Constraint

2020 ◽  
Vol 34 (01) ◽  
pp. 898-905
Author(s):  
Arpan Man Sainju ◽  
Wenchong He ◽  
Zhe Jiang ◽  
Da Yan
Keyword(s):  
Hidden Variables ◽  
Large Data ◽  
Small Subset ◽  
Structural Constraints ◽  
Structural Constraint ◽  
Computationally Efficient ◽  
Spatial Classification ◽  
Contextual Feature ◽  
Feature Values ◽  
Missing Feature

Spatial classification with limited feature observations has been a challenging problem in machine learning. The problem exists in applications where only a subset of sensors are deployed at certain regions or partial responses are collected in field surveys. Existing research mostly focuses on addressing incomplete or missing data, e.g., data cleaning and imputation, classification models that allow for missing feature values, or modeling missing features as hidden variables and applying the EM algorithm. These methods, however, assume that incomplete feature observations only happen on a small subset of samples, and thus cannot solve problems where the vast majority of samples have missing feature observations. To address this issue, we propose a new approach that incorporates physics-aware structural constraints into the model representation. Our approach assumes that a spatial contextual feature is observed for all sample locations and establishes spatial structural constraint from the spatial contextual feature map. We design efficient algorithms for model parameter learning and class inference. Evaluations on real-world hydrological applications show that our approach significantly outperforms several baseline methods in classification accuracy, and the proposed solution is computationally efficient on a large data volume.

scholarly journals Flood Inundation Mapping with Limited Observations Based on Physics-Aware Topography Constraint

2021 ◽  
Vol 4 ◽  
Author(s):  
Arpan Man Sainju ◽  
Wenchong He ◽  
Zhe Jiang ◽  
Da Yan ◽  
Haiquan Chen
Keyword(s):  
Missing Values ◽  
Hidden Variables ◽  
Flood Inundation ◽  
Computationally Efficient ◽  
Recent Approach ◽  
Inference Algorithms ◽  
Inundation Mapping ◽  
Flood Inundation Mapping ◽  
Feature Values ◽  
Efficient Learning

Spatial classification with limited observations is important in geographical applications where only a subset of sensors are deployed at certain spots or partial responses are collected in field surveys. For example, in observation-based flood inundation mapping, there is a need to map the full flood extent on geographic terrains based on earth imagery that partially covers a region. Existing research mostly focuses on addressing incomplete or missing data through data cleaning and imputation or modeling missing values as hidden variables in the EM algorithm. These methods, however, assume that missing feature observations are rare and thus are ineffective in problems whereby the vast majority of feature observations are missing. To address this issue, we recently proposed a new approach that incorporates physics-aware structural constraint into the model representation. We design efficient learning and inference algorithms. This paper extends our recent approach by allowing feature values of samples in each class to follow a multi-modal distribution. Evaluations on real-world flood mapping applications show that our approach significantly outperforms baseline methods in classification accuracy, and the multi-modal extension is more robust than our early single-modal version. Computational experiments show that the proposed solution is computationally efficient on large datasets.

scholarly journals Stochastic Dynamical Modeling of Turbulent Flows

2020 ◽  
Vol 3 (1) ◽  
pp. 195-219 ◽  
Author(s):  
A. Zare ◽  
T.T. Georgiou ◽  
M.R. Jovanović
Keyword(s):  
Turbulent Flows ◽  
High Performance ◽  
Degrees Of Freedom ◽  
Stokes Equations ◽  
Measurement Techniques ◽  
Large Data ◽  
Low Rank ◽  
Structural Constraints ◽  
Mean Velocity ◽  
Linearized Model

Advanced measurement techniques and high-performance computing have made large data sets available for a range of turbulent flows in engineering applications. Drawing on this abundance of data, dynamical models that reproduce structural and statistical features of turbulent flows enable effective model-based flow control strategies. This review describes a framework for completing second-order statistics of turbulent flows using models based on the Navier–Stokes equations linearized around the turbulent mean velocity. Dynamical couplings between states of the linearized model dictate structural constraints on the statistics of flow fluctuations. Colored-in-time stochastic forcing that drives the linearized model is then sought to account for and reconcile dynamics with available data (that is, partially known statistics). The number of dynamical degrees of freedom that are directly affected by stochastic excitation is minimized as a measure of model parsimony. The spectral content of the resulting colored-in-time stochastic contribution can alternatively arise from a low-rank structural perturbation of the linearized dynamical generator, pointing to suitable dynamical corrections that may account for the absence of the nonlinear interactions in the linearized model.

Methods for Reducing a Large Number of Current Profiles to a Small Subset for Riser VIV Analysis

2005 ◽  
Author(s):  
Kostas F. Lambrakos ◽  
Djoni E. Sidarta ◽  
Hugh M. Thompson ◽  
Atle Steen ◽  
Roger W. Burke
Keyword(s):  
Fatigue Damage ◽  
Average Power ◽  
Small Subset ◽  
Large Set ◽  
Computationally Efficient ◽  
Excitation Mode ◽  
Average Value ◽  
Vortex Induced Vibrations ◽  
Simplified Procedure

The paper presents two different approaches to construct subsets of current profiles from a large set of long term current profiles for the purpose of performing calculations for riser fatigue damage from vortex induced vibrations (VIV). The subsets are intended to reproduce the fatigue damage from the full set of current profiles. In the first approach, the full set of profiles is first sorted into bins based on current magnitude, direction and shear in the profile. The profiles within each bin are then reduced to a single constructed profile through one of many possible current averaging schemes. The present study includes two types of constructed profiles; one profile is generated by the average value of the currents for each bin and the other by the average value plus one standard deviation. The second approach is based on first performing a simplified and computationally efficient VIV analysis of the full set of profiles. The profiles are then sorted into bins by the dominant excitation mode, and then a single profile is chosen to represent all the profiles that excite the mode of interest. The chosen profile for the mode of interest has VIV power-in which is close to the average power-in for all the profiles that excite the mode. The number of profiles in the subset is equal to the number of modes that are excited by the full set of profiles. The VIV power-in in this paper is estimated through a simplified procedure that is consistent with the SHEAR7 methodology. Other available codes can also be used for the simplified VIV calculations.

scholarly journals Designing allostery-inspired response in mechanical networks

2017 ◽  
Vol 114 (10) ◽  
pp. 2520-2525 ◽  
Author(s):  
Jason W. Rocks ◽  
Nidhi Pashine ◽  
Irmgard Bischofberger ◽  
Carl P. Goodrich ◽  
Andrea J. Liu ◽  
...  
Keyword(s):  
Long Range ◽  
Conformational Changes ◽  
Biological Molecules ◽  
Small Subset ◽  
Individual Response ◽  
Computationally Efficient ◽  
Mechanical Responses ◽  
Mechanical Networks ◽  
Disordered Networks ◽  
2D And 3D

Recent advances in designing metamaterials have demonstrated that global mechanical properties of disordered spring networks can be tuned by selectively modifying only a small subset of bonds. Here, using a computationally efficient approach, we extend this idea to tune more general properties of networks. With nearly complete success, we are able to produce a strain between any two target nodes in a network in response to an applied source strain on any other pair of nodes by removing only ∼1% of the bonds. We are also able to control multiple pairs of target nodes, each with a different individual response, from a single source, and to tune multiple independent source/target responses simultaneously into a network. We have fabricated physical networks in macroscopic 2D and 3D systems that exhibit these responses. This work is inspired by the long-range coupled conformational changes that constitute allosteric function in proteins. The fact that allostery is a common means for regulation in biological molecules suggests that it is a relatively easy property to develop through evolution. In analogy, our results show that long-range coupled mechanical responses are similarly easy to achieve in disordered networks.

Breast Tissue Classification Using Diagnostic Ultrasound and Pattern Recognition Techniques: II. Experimental Results

1983 ◽  
Vol 5 (1) ◽  
pp. 71-86 ◽  
Author(s):  
Steven Finette ◽  
Alan R. Bleier ◽  
William Swindell ◽  
Kai Haber
Keyword(s):  
Pattern Recognition ◽  
Malignant Disease ◽  
Imaging System ◽  
Statistical Tests ◽  
Large Data ◽  
Benign Disease ◽  
Small Subset ◽  
Large Set ◽  
Tissue Classification

The methods of statistical pattern recognition have been applied to the problem of in vivo ultrasonic characterization of breast disease in humans. Backscattered A-mode signals obtained from a commercial pulse imaging system were used to generate a large set of potentially useful features. Using statistical tests, a small subset of discriminatory features was selected to design a Bayes decision rule for each of two tissue classification schemes: malignant disease vs. benign disease, and malignant disease vs. (benign disease + normal tissue). Classification results obtained by the rotation method included sensitivities of 88 percent and 76 percent for the two schemes, based on data obtained from 32 women. These results are encouraging, though a definitive statement concerning the extrapolation of these numbers to the general population should only be made after obtaining results with a large data base.

scholarly journals A review of forecasting techniques for large datasets

2008 ◽  
Vol 203 ◽  
pp. 109-115 ◽  
Author(s):  
Jana Eklund ◽  
George Kapetanios
Keyword(s):  
State Of The Art ◽  
Large Data ◽  
Large Datasets ◽  
Large Data Sets ◽  
Multiple Models ◽  
Small Subset ◽  
Data Sets ◽  
Single Model ◽  
Data Set ◽  
Forecasting Techniques

This paper aims to provide a brief and relatively non-technical overview of state-of-the-art forecasting with large data sets. We classify existing methods into four groups depending on whether data sets are used wholly or partly, whether a single model or multiple models are used and whether a small subset or the whole data set is being forecast. In particular, we provide brief descriptions of the methods and short recommendations where appropriate, without going into detailed discussions of their merits or demerits.

scholarly journals DESCRIBING AND IDENTIFYING VARIOUS CONSTRAINTS OF PARTICIPATING IN OUTDOOR RECREATION ACTIVITIES AMONG FEMALE STUDENTS

2021 ◽  
Vol 17 (1) ◽  
pp. 96
Author(s):  
Hellinda Marius ◽  
Mohd Khairulanwar Md Yusof ◽  
Chee Hian Tan
Keyword(s):  
Outdoor Recreation ◽  
Education Level ◽  
Female Students ◽  
Structural Constraints ◽  
Structural Constraint ◽  
Recreational Activities ◽  
Intrapersonal Factors ◽  
The Future ◽  
Recreation Activities

The purpose of this study was to describe and identify various constraints of participating in outdoor recreation activities among female students of Universiti Teknologi MARA, Perlis. This study examined on the structural and intrapersonal factors. 150 respondents selected convenience at UiTM Perlis. The respondents were based on their education level, 75 for diploma and 75 for bachelor. Result showed that the highest mean for structural constraint was economic (M = 2.67) where else the highest mean for intrapersonal constraint was physical (M = 2.17). This finding also showed that there was no significance differences for structural constraints based on education level but there were significance differences for intrapersonal constraints based on education level: ‘Motivation’ (t =-7.03, p < 0.05), ‘Psychological’ (t = -6.31, p < 0.05) and ‘Physical’ (t = -4.77, p < 0.05) respectively. In conclusion this study expected to enhance as guide to the related parties concerned for overcoming the structural and intrapersonal constraints that influenced participating of recreational activities among female students specifically in UiTM Perlis. Hence, this study provided valuable factors that contributed as constraints among females as scope of interest to University and Ministry Youth and Sport in the future recreational phenomena of constraints to females participating in outdoor recreation activities as a whole nationwide.

scholarly journals Zheng Classification with Missing Feature Values Using Local-Validity Approach

2013 ◽  
Vol 2013 ◽  
pp. 1-6
Author(s):  
Yan Wang ◽  
Lizhuang Ma
Keyword(s):  
Liver Cirrhosis ◽  
Clinical Practice ◽  
Chinese Medicine ◽  
Classification Accuracy ◽  
Classification Performance ◽  
New Approach ◽  
Feature Values ◽  
Public Datasets ◽  
The Given ◽  
Missing Feature

Zheng classification is a very important step in the diagnosis of traditional Chinese medicine (TCM). In clinical practice of TCM, feature values are often missing and incomplete cases. The performance of Zheng classification is strictly related to rates of missing feature values. Based on the pattern of the missing feature values, a new approach named local-validity is proposed to classify zheng classification with missing feature values. Firstly, the maximum submatrix for the given dataset is constructed and local-validity method finds subsets of cases for which all of the feature values are available. To reduce the computational scale and improve the classification accuracy, the method clusters subsets with similar patterns to form local-validity subsets. Finally, the proposed method trains a classifier for each local-validity subset and combines the outputs of individual classifiers to diagnose zheng classification. The proposed method is applied to the real liver cirrhosis dataset and three public datasets. Experimental results show that classification performance of local-validity method is superior to the widely used methods under missing feature values.

Wrapper Feature Selection based on Genetic Algorithm for Recognizing Objects from Satellite Imagery

2015 ◽  
Vol 8 (3) ◽  
pp. 1-20 ◽  
Author(s):  
Nabil M. Hewahi ◽  
Eyad A. Alashqar
Keyword(s):  
Feature Selection ◽  
Satellite Imagery ◽  
Nearest Neighbor ◽  
Large Data ◽  
Research Area ◽  
Small Subset ◽  
Data Sets ◽  
K Nearest Neighbor ◽  
Spatial Features ◽  
Maintenance Cycle

Object recognition is a research area that aims to associate objects to categories or classes. The recognition of object specific geospatial features, such as roads, buildings and rivers, from high-resolution satellite imagery is a time consuming and expensive problem in the maintenance cycle of a Geographic Information System (GIS). Feature selection is the task of selecting a small subset from original features that can achieve maximum classification accuracy and reduce data dimensionality. This subset of features has some very important benefits like, it reduces computational complexity of learning algorithms, saves time, improve accuracy and the selected features can be insightful for the people involved in problem domain. This makes feature selection as an indispensable task in classification task. In this work, the authors propose a new approach that combines Genetic Algorithms (GA) with Correlation Ranking Filter (CRF) wrapper to eliminate unimportant features and obtain better features set that can show better results with various classifiers such as Neural Networks (NN), K-nearest neighbor (KNN), and Decision trees. The approach is based on GA as an optimization algorithm to search the space of all possible subsets related to object geospatial features set for the purpose of recognition. GA is wrapped with three different classifier algorithms namely neural network, k-nearest neighbor and decision tree J48 as subset evaluating mechanism. The GA-ANN, GA-KNN and GA-J48 methods are implemented using the WEKA software on dataset that contains 38 extracted features from satellite images using ENVI software. The proposed wrapper approach incorporated the Correlation Ranking Filter (CRF) for spatial features to remove unimportant features. Results suggest that GA based neural classifiers and using CRF for spatial features are robust and effective in finding optimal subsets of features from large data sets.

Sign in / Sign up

Export Citation Format

Share Document