scholarly journals Neural-network fusion processing and inverse mapping to combine multi-sensor satellite data and to analyze significant features

2021 ◽  
Author(s):  
Gunjan Joshi ◽  
Ryo Natsuaki ◽  
Akira Hirose
Keyword(s):  
Neural Network ◽  
Satellite Data ◽  
Optical Sensors ◽  
Remote Sensing Data ◽  
Activation Function ◽  
Significant Feature ◽  
Unknown Parameters ◽  
Inverse Mapping ◽  
Observation Area ◽  
Synthetic Aperture Radars

<div>In the last decade, the increase in the number of active and passive earth observation satellites has provided us with more remote sensing data. This fact has led to increased interests in the field of fusion of the different satellite data since some of the satellites have properties complementary to one another. Fusion techniques can improve the estimation in areas of interest (AOIs) by using complementary information and inferring unknown parameters. However, when the observation area is large, extensive human labor and domain expertise are required for processing and analysis. Thus, we propose a neural network which combines and analyzes the data obtained from synthetic aperture radars (SAR) and optical sensors. The neural network employs a modified logarithmic activation function, unlike conventional networks, to realize inverse mapping for significant feature analysis based on dynamics consistent with its forward processing. In this paper, we focus on earthquake damage detection by dealing with the data of the 2018 Sulawesi earthquake in Indonesia. The fusion-based results show increased classification accuracy compared to the results of independent sensors. We further attempt to understand which input features are the significant contributors for which classification outputs by inverse-mapping in the data fusion neural network. We observe that inverse mapping shows reasonable explanations in a consistent manner. It also indicates contributions of features different from straightforward counterparts, namely pre- and post-seismic features, in the detection of particular classes.</div>

scholarly journals Neural-network fusion processing and inverse mapping to combine multi-sensor satellite data and to analyze significant features

2021 ◽  
Author(s):  
Gunjan Joshi ◽  
Ryo Natsuaki ◽  
Akira Hirose
Keyword(s):  
Neural Network ◽  
Satellite Data ◽  
Optical Sensors ◽  
Remote Sensing Data ◽  
Activation Function ◽  
Significant Feature ◽  
Unknown Parameters ◽  
Inverse Mapping ◽  
Observation Area ◽  
Synthetic Aperture Radars

<div>In the last decade, the increase in the number of active and passive earth observation satellites has provided us with more remote sensing data. This fact has led to increased interests in the field of fusion of the different satellite data since some of the satellites have properties complementary to one another. Fusion techniques can improve the estimation in areas of interest (AOIs) by using complementary information and inferring unknown parameters. However, when the observation area is large, extensive human labor and domain expertise are required for processing and analysis. Thus, we propose a neural network which combines and analyzes the data obtained from synthetic aperture radars (SAR) and optical sensors. The neural network employs a modified logarithmic activation function, unlike conventional networks, to realize inverse mapping for significant feature analysis based on dynamics consistent with its forward processing. In this paper, we focus on earthquake damage detection by dealing with the data of the 2018 Sulawesi earthquake in Indonesia. The fusion-based results show increased classification accuracy compared to the results of independent sensors. We further attempt to understand which input features are the significant contributors for which classification outputs by inverse-mapping in the data fusion neural network. We observe that inverse mapping shows reasonable explanations in a consistent manner. It also indicates contributions of features different from straightforward counterparts, namely pre- and post-seismic features, in the detection of particular classes.</div>

scholarly journals NN-Based Prediction of Sentinel-1 SAR Image Filtering Efficiency

Geosciences ◽  
2019 ◽  
Vol 9 (7) ◽  
pp. 290 ◽  
Author(s):  
Rubel ◽  
Lukin ◽  
Rubel ◽  
Egiazarian
Keyword(s):  
Neural Network ◽  
Image Quality ◽  
Real Life ◽  
Remote Sensing Data ◽  
Radar Data ◽  
Quality Metrics ◽  
Radar Images ◽  
Filtering Efficiency ◽  
Trained Neural Network ◽  
Synthetic Aperture Radars

Images acquired by synthetic aperture radars are degraded by speckle that prevents efficient extraction of useful information from radar remote sensing data. Filtering or despeckling is a tool often used to improve image quality. However, depending upon image and noise properties, the quality of improvement can vary. Besides, a quality can be characterized by different criteria or metrics, where visual quality metrics can be of value. For the case study of discrete cosine transform (DCT)based filtering, we show that improvement of radar image quality due to denoising can be predicted in a simple and fast way, especially if one deals with particular type of radar data such as images acquired by Sentinel-1. Our approach is based on application of a trained neural network that, in general, might have a different number of inputs (features). We propose a set of features describing image and noise statistics from different viewpoints. From this set, that contains 28 features, we analyze different subsets and show that a subset of the 13 most important and informative features leads to a very accurate prediction. Test image generation and network training peculiarities are discussed. The trained neural network is then tested using different verification strategies. The results of the network application to test and real-life radar images are presented, demonstrating good performance for a wide set of quality metrics.

SCORING MODELING BASED ON NEURAL NETWORKS FOR DETERMINING A BANK BORROWER'S RATING

2020 ◽  
Vol 2020 (10) ◽  
pp. 54-62
Author(s):  
Oleksii VASYLIEV ◽  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Architecture ◽  
Statistical Data ◽  
Activation Function ◽  
Decision Making Process ◽  
Neural Network Architecture ◽  
Acceptable Accuracy ◽  
The Neural Network ◽  
Sigmoid Activation Function

The problem of applying neural networks to calculate ratings used in banking in the decision-making process on granting or not granting loans to borrowers is considered. The task is to determine the rating function of the borrower based on a set of statistical data on the effectiveness of loans provided by the bank. When constructing a regression model to calculate the rating function, it is necessary to know its general form. If so, the task is to calculate the parameters that are included in the expression for the rating function. In contrast to this approach, in the case of using neural networks, there is no need to specify the general form for the rating function. Instead, certain neural network architecture is chosen and parameters are calculated for it on the basis of statistical data. Importantly, the same neural network architecture can be used to process different sets of statistical data. The disadvantages of using neural networks include the need to calculate a large number of parameters. There is also no universal algorithm that would determine the optimal neural network architecture. As an example of the use of neural networks to determine the borrower's rating, a model system is considered, in which the borrower's rating is determined by a known non-analytical rating function. A neural network with two inner layers, which contain, respectively, three and two neurons and have a sigmoid activation function, is used for modeling. It is shown that the use of the neural network allows restoring the borrower's rating function with quite acceptable accuracy.

Evaluation of Capacity of Salandi Reservoir Using Remote Sensing Data Along With Qgis Software

2018 ◽  
Vol 6 (8) ◽  
pp. 339
Author(s):  
Rupali Dhal ◽  
D. P. Satapathy
Keyword(s):  
Remote Sensing ◽  
Satellite Data ◽  
Remote Sensing Data ◽  
Project Work ◽  
Space Technology ◽  
Reservoir Water ◽  
Sediment Distribution ◽  
Sensing Data ◽  
Spread Area ◽  
Water Spread

The dynamic aspects of the reservoir which are water spread, suspended sediment distribution and concentration requires regular and periodical mapping and monitoring. Sedimentation in a reservoir affects the capacity of the reservoir by affecting both life and dead storages. The life of a reservoir depends on the rate of siltation. The various aspects and behavior of the reservoir sedimentation, like the process of sedimentation in the reservoir, sources of sediments, measures to check the sediment and limitations of space technology have been discussed in this report. Multi satellite remote sensing data provide information on elevation contours in the form of water spread area. Any reduction in reservoir water spread area at a specified elevation corresponding to the date of satellite data is an indication of sediment deposition. Thus the quality of sediment load that is settled down over a period of time can be determined by evaluating the change in the aerial spread of the reservoir at various elevations. Salandi reservoir project work was completed in 1982 and the same is taken as the year of first impounding. The original gross and live storages capacities were 565 MCM& 556.50 MCM respectively. In SRS CWC (2009), they found that live storage capacity of the Salandi reservoir is 518.61 MCM witnessing a loss of 37.89 MCM (i.e. 6.81%) in a period of 27 years.The data obtained through satellite enables us to study the aspects on various scales and at different stages. This report comprises of the use of satellite to obtain data for the years 2009-2013 through remote sensing in the sedimentation study of Salandi reservoir. After analysis of the satellite data in the present study(2017), it is found that live capacity of the reservoir of the Salandi reservoir in 2017 is 524.19MCM witnessing a loss of 32.31 MCM (i.e. 5.80%)in a period of 35 years. This accounts for live capacity loss of 0.16 % per annum since 1982. The trap efficiencies of this reservoir evaluated by using Brown’s, Brune’s and Gill’s methods are 94.03%, 98.01and 99.94% respectively. Thus, the average trap efficiency of the Salandi Reservoir is obtained as 97.32%.

Application of geoinformation technologies for arranging a satellite monitoring system

2019 ◽  
Vol 943 (1) ◽  
pp. 110-118
Author(s):  
A.A. Kadochnikov
Keyword(s):  
Remote Sensing ◽  
Satellite Data ◽  
Remote Sensing Data ◽  
Web Gis ◽  
Nature Management ◽  
Satellite Monitoring ◽  
Technological Support ◽  
Sensing Data ◽  
Territorial Planning ◽  
Operational Information

Today, remote sensing data are an important source of operational information about the environment for thematic GIS, this data can be used for the development of water, forestry and agriculture management, in the ecology and nature management, with territorial planning, etc. To solve the problem of ensuring the effective use of the space activities’results in the Krasnoyarsk Territory a United Regional Remote Sensing Center was created. On the basis of the Center, a new satellite receiving complex of FRC KSC SB RAS was put into operation. It is currently receiving satellite data from TERRA, AQUA, Suomi NPP and FENG-YUN satellites. Within the framework in cooperation with the Siberian Regional Center for Remote Sensing the Earth, an archive of satellite data from domestic Resource-P and Meteor-M2 satellites was created. The work considers some features of softwaredevelopment and technological support tools for loading, processing and publishing remote sensing data. The product is created in the service-oriented paradigm based on geoportal technologies and interactive web-cartography. The focus in this article is paid to the peculiarities of implementing the software components of the web GIS, the efficient processing and presentation of geospatial data.

Satellite Remote Sensing and the Management of Natural Resources

2019 ◽  
Author(s):  
Nathalie Pettorelli
Keyword(s):  
Remote Sensing ◽  
Resource Management ◽  
Natural Resource Management ◽  
Natural Resource ◽  
Satellite Data ◽  
Satellite Remote Sensing ◽  
Habitat Restoration ◽  
Remote Sensing Data ◽  
Ecological Knowledge ◽  
Postgraduate Students

This book intends to familiarise prospective users in the environmental community with satellite remote sensing technology and its applications, introducing terminology and principles behind satellite remote sensing data and analyses. It provides a detailed overview of the possible applications of satellite data in natural resource management, demonstrating how ecological knowledge and satellite-based information can be effectively combined to address a wide array of current natural resource management needs. Topics considered include the use of satellite data to monitor the various dimensions of biodiversity; the use of this technology to track pressures on biodiversity such as invasive species, pollution, and illegal fishing; the utility of satellite remote sensing to inform the management of protected areas, translocation, and habitat restoration; and the contribution of satellite remote sensing towards the monitoring of ecosystem services and wellbeing. The intended audience is ecologists and environmental scientists; the book is targeted as a handbook and is therefore also suitable for advanced undergraduate and postgraduate students in the biological and ecological sciences, as well as policy makers and specialists in the fields of conservation biology, biodiversity monitoring, and natural resource management. The book assumes no prior technical knowledge of satellite remote sensing systems and products. It is written so as to generate interest in the ecological, environmental management, and remote sensing communities, highlighting issues associated with the emergence of truly synergistic approaches between these disciplines.

scholarly journals Prediction of Stress in Power Transformer Winding Conductors Using Artificial Neural Networks: Hyperparameter Analysis

Energies ◽  
2021 ◽  
Vol 14 (14) ◽  
pp. 4242
Author(s):  
Fausto Valencia ◽  
Hugo Arcos ◽  
Franklin Quilumba
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Finite Element ◽  
Power Transformer ◽  
Network Models ◽  
Activation Function ◽  
Neural Network Models ◽  
Transformer Winding ◽  
Artificial Neural ◽  
Femm Software

The purpose of this research is the evaluation of artificial neural network models in the prediction of stresses in a 400 MVA power transformer winding conductor caused by the circulation of fault currents. The models were compared considering the training, validation, and test data errors’ behavior. Different combinations of hyperparameters were analyzed based on the variation of architectures, optimizers, and activation functions. The data for the process was created from finite element simulations performed in the FEMM software. The design of the Artificial Neural Network was performed using the Keras framework. As a result, a model with one hidden layer was the best suited architecture for the problem at hand, with the optimizer Adam and the activation function ReLU. The final Artificial Neural Network model predictions were compared with the Finite Element Method results, showing good agreement but with a much shorter solution time.

Breast cancer diagnosis using multiple activation deep neural network

2021 ◽  
pp. 1063293X2110251
Author(s):  
K Vijayakumar ◽  
Vinod J Kadam ◽  
Sudhir Kumar Sharma
Keyword(s):  
Breast Cancer ◽  
Neural Network ◽  
Deep Neural Network ◽  
Breast Cancer Diagnosis ◽  
Activation Function ◽  
Linear Functions ◽  
Cancer Data ◽  
Final Layer ◽  
Improved Performance ◽  
Hidden Layer

Deep Neural Network (DNN) stands for multilayered Neural Network (NN) that is capable of progressively learn the more abstract and composite representations of the raw features of the input data received, with no need for any feature engineering. They are advanced NNs having repetitious hidden layers between the initial input and the final layer. The working principle of such a standard deep classifier is based on a hierarchy formed by the composition of linear functions and a defined nonlinear Activation Function (AF). It remains uncertain (not clear) how the DNN classifier can function so well. But it is clear from many studies that within DNN, the AF choice has a notable impact on the kinetics of training and the success of tasks. In the past few years, different AFs have been formulated. The choice of AF is still an area of active study. Hence, in this study, a novel deep Feed forward NN model with four AFs has been proposed for breast cancer classification: hidden layer 1: Swish, hidden layer, 2:-LeakyReLU, hidden layer 3: ReLU, and final output layer: naturally Sigmoidal. The purpose of the study is twofold. Firstly, this study is a step toward a more profound understanding of DNN with layer-wise different AFs. Secondly, research is also aimed to explore better DNN-based systems to build predictive models for breast cancer data with improved accuracy. Therefore, the benchmark UCI dataset WDBC was used for the validation of the framework and evaluated using a ten-fold CV method and various performance indicators. Multiple simulations and outcomes of the experimentations have shown that the proposed solution performs in a better way than the Sigmoid, ReLU, and LeakyReLU and Swish activation DNN in terms of different parameters. This analysis contributes to producing an expert and precise clinical dataset classification method for breast cancer. Furthermore, the model also achieved improved performance compared to many established state-of-the-art algorithms/models.

Sign in / Sign up

Export Citation Format

Share Document