scholarly journals Urban Matanuska Flood Prediction using Deep Learning with Sentinel-2 Images

2021 ◽  
Author(s):  
Ramasamy Sankar Ram Chellapa ◽  
Santhana Krishnan Rajan ◽  
Golden Julie Eanoch ◽  
Harold Robinson Yesudhas ◽  
Lakshminarayanan Kumaragurubaran ◽  
...  
Keyword(s):  
Graphics Processing Unit ◽  
Classification Model ◽  
Gradient Boosting ◽  
Processing Unit ◽  
Classification Result ◽  
Data Set ◽  
Flood Prediction ◽  
Spectral Bands ◽  
Graphics Processing ◽  
Sentinel 2

Abstract In this paper, we produce a novel raster dataset depending upon the Sentinel-2 satellite. They envelop over thirteen spectral bands. Our novel data set consists of ten classes within a total of 27000 Geo-referenced and labelled images. Gradient Boosting Model (GBM) used to explore this novel dataset in which the overall prediction and accuracy of 97% is obtained from the support of Graphics Processing Unit (GPU) afforded from Google Colaboratory (Colab). The obtained classification result can provide a gateway for numerous earth observation applications. Here, in this paper, we also elaborate on how this classification model might be applied for a conspicuous change in land cover and how it plays an important role in improving the graphical maps.

An Interval Type 2 Fuzzy Logic Framework for Faster Evolutionary Design

2019 ◽  
Vol 16 (12) ◽  
pp. 5140-5148
Author(s):  
Sarabjeet Singh ◽  
Satvir Singh ◽  
Vijay Kumar Banga
Keyword(s):  
Fuzzy Logic ◽  
Graphics Processing Unit ◽  
Noisy Data ◽  
Parallel Execution ◽  
Rule Base ◽  
Processing Unit ◽  
Data Set ◽  
Interval Type ◽  
Graphics Processing

In this paper, a fast processing and efficient framework has been proposed to get an optimum output from a noisy data set of a system by using interval type-2 fuzzy logic system. Further, the concept of GPGPU (General Purpose Computing on Graphics Processing Unit) is used for fast execution of the fuzzy rule base on Graphics Processing Unit (GPU). Application of Whale Optimization Algorithm (WOA) is used to ascertain optimum output from noisy data set. Which is further integrated with Interval Type-2 (IT2) fuzzy logic system and executed on Graphics Processing Unit for faster execution. The proposed framework is also designed for parallel execution using GPU and the results are compared with the serial program execution. Further, it is clearly observed that the parallel execution rule base evolved provide better accuracy in less time. The proposed framework (IT2FLS) has been validated with classical bench mark problem of Mackey Glass Time Series. For non-stationary time-series data with additive gaussian noise has been implemented with proposed framework and with T1 FLS. Further, it is observed that IT2 FLS provides better rule base for noisy data set.

scholarly journals Genus-Physiognomy-Ecosystem Map with 88 Legends Produced at 10m-resolution First-time in a Country Scale through Machine Learning of Multi-temporal Satellite Images

2022 ◽  
Author(s):  
Ram C. Sharma ◽  
Keitarou Hara
Keyword(s):  
Machine Learning ◽  
Satellite Images ◽  
Graphics Processing Unit ◽  
Ground Truth ◽  
Training Data ◽  
Gradient Boosting ◽  
Processing Unit ◽  
Spectral Bands ◽  
Multi Temporal ◽  
First Time

This research introduces Genus-Physiognomy-Ecosystem (GPE) mapping at a prefecture level through machine learning of multi-spectral and multi-temporal satellite images at 10m spatial resolution, and later integration of prefecture wise maps into country scale for dealing with 88 GPE types to be classified from a large size of training data involved in the research effectively. This research was made possible by harnessing entire archives of Level-2A product, Bottom of Atmosphere reflectance images collected by MultiSpectral Instruments onboard a constellation of two polar-orbiting Sentinel-2 mission satellites. The satellite images were pre-processed for cloud masking and monthly median composite images consisting of 10 multi-spectral bands and 7 spectral indexes were generated. The ground truth labels were extracted from extant vegetation survey maps by implementing systematic stratified sampling approach and noisy labels were dropped out for preparing a reliable ground truth database. Graphics Processing Unit (GPU) implementation of Gradient Boosting Decision Trees (GBDT) classifier was employed for classification of 88 GPE types from 204 satellite features. The classification accuracy computed with 25% test data varied from 65-81% in terms of F1-score across 48 prefectural regions. This research produced seamless maps of 88 GPE types first time at a country scale with an average 72% F1-score.

scholarly journals Visualisation of Large-Scale Call-Centre Data

2020 ◽  
Author(s):  
◽  
Dylan G Rees
Keyword(s):  
Large Scale ◽  
Graphics Processing Unit ◽  
Large Data ◽  
Mean Value ◽  
Data Sets ◽  
Call Centre ◽  
Processing Unit ◽  
Data Set ◽  
Domain Experts ◽  
Graphics Processing

The contact centre industry employs 4% of the entire United King-dom and United States’ working population and generates gigabytes of operational data that require analysis, to provide insight and to improve efficiency. This thesis is the result of a collaboration with QPC Limited who provide data collection and analysis products for call centres. They provided a large data-set featuring almost 5 million calls to be analysed. This thesis utilises novel visualisation techniques to create tools for the exploration of the large, complex call centre data-set and to facilitate unique observations into the data.A survey of information visualisation books is presented, provid-ing a thorough background of the field. Following this, a feature-rich application that visualises large call centre data sets using scatterplots that support millions of points is presented. The application utilises both the CPU and GPU acceleration for processing and filtering and is exhibited with millions of call events.This is expanded upon with the use of glyphs to depict agent behaviour in a call centre. A technique is developed to cluster over-lapping glyphs into a single parent glyph dependant on zoom level and a customizable distance metric. This hierarchical glyph repre-sents the mean value of all child agent glyphs, removing overlap and reducing visual clutter. A novel technique for visualising individually tailored glyphs using a Graphics Processing Unit is also presented, and demonstrated rendering over 100,000 glyphs at interactive frame rates. An open-source code example is provided for reproducibility.Finally, a novel interaction and layout method is introduced for improving the scalability of chord diagrams to visualise call transfers. An exploration of sketch-based methods for showing multiple links and direction is made, and a sketch-based brushing technique for filtering is proposed. Feedback from domain experts in the call centre industry is reported for all applications developed.

scholarly journals Accelerating the XGBoost algorithm using GPU computing

2017 ◽  
Vol 3 ◽  
pp. e127 ◽  
Author(s):  
Rory Mitchell ◽  
Eibe Frank
Keyword(s):  
High Performance ◽  
Gpu Computing ◽  
Graphics Processing Unit ◽  
Gradient Boosting ◽  
Processing Unit ◽  
Radix Sort ◽  
Construction Algorithm ◽  
Tree Construction ◽  
Ranking Tasks ◽  
Graphics Processing

We present a CUDA-based implementation of a decision tree construction algorithm within the gradient boosting library XGBoost. The tree construction algorithm is executed entirely on the graphics processing unit (GPU) and shows high performance with a variety of datasets and settings, including sparse input matrices. Individual boosting iterations are parallelised, combining two approaches. An interleaved approach is used for shallow trees, switching to a more conventional radix sort-based approach for larger depths. We show speedups of between 3× and 6× using a Titan X compared to a 4 core i7 CPU, and 1.2× using a Titan X compared to 2× Xeon CPUs (24 cores). We show that it is possible to process the Higgs dataset (10 million instances, 28 features) entirely within GPU memory. The algorithm is made available as a plug-in within the XGBoost library and fully supports all XGBoost features including classification, regression and ranking tasks.

Implementing wide baseline matching algorithms on a graphics processing unit.

2007 ◽  
Author(s):  
Fredrick H. Rothganger ◽  
Kurt W. Larson ◽  
Antonio Ignacio Gonzales ◽  
Daniel S. Myers
Keyword(s):  
Graphics Processing Unit ◽  
Processing Unit ◽  
Wide Baseline Matching ◽  
Graphics Processing

scholarly journals Two Decades of 4D-QSAR: A Dying Art or Staging a Comeback?

2021 ◽  
Vol 22 (10) ◽  
pp. 5212
Author(s):  
Andrzej Bak
Keyword(s):  
Molecular Conformation ◽  
Graphics Processing Unit ◽  
Processing Unit ◽  
Diverse Range ◽  
Current State ◽  
Gpu Clusters ◽  
Pharmacophore Hypothesis ◽  
Rising Power ◽  
Graphics Processing ◽  
Ligand Conformation

A key question confronting computational chemists concerns the preferable ligand geometry that fits complementarily into the receptor pocket. Typically, the postulated ‘bioactive’ 3D ligand conformation is constructed as a ‘sophisticated guess’ (unnecessarily geometry-optimized) mirroring the pharmacophore hypothesis—sometimes based on an erroneous prerequisite. Hence, 4D-QSAR scheme and its ‘dialects’ have been practically implemented as higher level of model abstraction that allows the examination of the multiple molecular conformation, orientation and protonation representation, respectively. Nearly a quarter of a century has passed since the eminent work of Hopfinger appeared on the stage; therefore the natural question occurs whether 4D-QSAR approach is still appealing to the scientific community? With no intention to be comprehensive, a review of the current state of art in the field of receptor-independent (RI) and receptor-dependent (RD) 4D-QSAR methodology is provided with a brief examination of the ‘mainstream’ algorithms. In fact, a myriad of 4D-QSAR methods have been implemented and applied practically for a diverse range of molecules. It seems that, 4D-QSAR approach has been experiencing a promising renaissance of interests that might be fuelled by the rising power of the graphics processing unit (GPU) clusters applied to full-atom MD-based simulations of the protein-ligand complexes.

Sign in / Sign up

Export Citation Format

Share Document