A5070868618- Model Reduction and Neural Networks
- Soil Moisture and Remote Sensing
- Remote Sensing in Agriculture
- Precipitation Measurement and Analysis
- Power System Optimization and Stability
- Remote Sensing and Land Use
- Synthetic Aperture Radar (SAR) Applications and Techniques
- Real-time simulation and control systems
- Hydraulic and Pneumatic Systems
- Frequency Control in Power Systems
- Probabilistic and Robust Engineering Design
- Control Systems and Identification
- Remote-Sensing Image Classification
- Numerical methods for differential equations
- Urban Heat Island Mitigation
- Spectroscopy and Chemometric Analyses
- Smart Agriculture and AI
- Land Use and Ecosystem Services
- Optimal Power Flow Distribution
- Leaf Properties and Growth Measurement
- Cryospheric studies and observations
- Power Systems Fault Detection
- Soil Geostatistics and Mapping
- Microgrid Control and Optimization
- Fuzzy Logic and Control Systems
Tata Motors (India)
2024
Banaras Hindu University
2015-2024
Indian Institute of Technology BHU
2015-2024
Indian Institute of Technology Roorkee
2014-2023
National Institute Of Technology Silchar
2018
IIT Research Institute
2014
Sikkim Manipal University
2011
Indian Institute of Technology Indore
2007
Energy and Resources Institute
1992
Astronomical Institute of the Slovak Academy of Sciences
1972
The Resourcesat-2 is a highly suitable satellite for crop classification studies with its improved features and capabilities. Data from one of sensors, the linear imaging self-scanning (LISS IV), which has spatial resolution 5.8 m, was used to compare relative accuracies achieved by support vector machine (SVM), artificial neural network (ANN), spectral angle mapper (SAM) algorithms various crops non-crop covering part Varanasi district, Uttar Pradesh, India. separability analysis performed...
A mixed method is proposed for finding stable reduced order models of single-input- single-output large-scale systems using Pade approximation and the clustering technique. The denominator polynomial model determined by forming clusters poles original system, coefficients numerator are obtained This guarantees stability when high system stable. methodology illustrated with help examples from literature.
A new method of model order reduction is introduced by combining the merits big bang crunch (BBBC) optimization technique and stability equation (SE) method. linear-continuous single-input single-output system higher considered reduced to a lower system. The denominator polynomial obtained SE method, whereas numerator terms are generated using BBBC optimization. Furthermore, step frequency responses original plotted. superiority proposed justified solving numerical examples from available...
In this paper, a new technique for order reduction of linear time-invariant systems is presented. This intended both single-input single-output (SISO) and multi-input multi-output (MIMO) systems. Motivated by other techniques, the proposed based on modified pole clustering factor division algorithm with objective obtaining stable reduced-order system preserving all essential properties original system. The illustrated three numerical examples which are considered from literature. To evaluate...
In the present study, Sentinel-1A Synthetic Aperture Radar analysis of time series data at C-band was carried out to estimate winter wheat crop growth parameters. Five different date images were acquired during January 2015–April 2015 stages from tillering ripening in Varanasi district, India. The parameters, i.e. leaf area index, vegetation water content (VWC), fresh biomass (FB), dry (DB) and plant height (PH) estimated using random forest regression (RFR), support vector (SVR), artificial...
The aim of this paper is to construct a new model order reduction method for linear dynamic systems. In technique, the denominator polynomial reduced (ROM) obtained by balanced truncation and numerator calculated factor division technique. This proposed overcoming existing problems such as mismatch steady-state values original model. guarantees preservation stability value system in ROM; hence, it preserves advantages methods A special advantage technique that first few time moments ROM....
A new mixed method for reducing the order of large-scale linear dynamic multi-input-multi-output (MIMO) systems has been presented. In this method, common denominator polynomial reduced-order transfer function matrix is synthesized by using modified pole clustering while coefficients numerator elements are computed minimizing integral square error between time responses original and reduced system element Genetic Algorithm. The generates more dominant cluster centres than obtained technique...
In the present study, random forest regression (RFR), support vector (SVR) and artificial neural network (ANNR) models were evaluated for retrieval of soil moisture covered by winter wheat, barley corn crops. SVR with radial basis function kernel was provided highest adj. R2 (0.95) value wheat crop at VV polarization. However, RFR (0.94) polarization using Sentinel-1A satellite data. The values found RFR, linear kernels. least performance reported ANNR model almost all crops under...