A. Ravi Raja
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
A. Ravi Raja has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Polasi Phani Kumar
SRM Institute of Science and Technology
2 shared publications A Jitendra
Computer Science and Engineering V R Siddhartha Engineering College, Kanuru, Vijayawada, India
1 shared publication- Abhaya Pal Singh
Department of Mechanical Engineering and Technology Management, Faculty of Science and Technology, Norwegian University of Life Sciences (NMBU), 1430 Ås, Norway
1 shared publication Arul Raj M.
Computer Science and Engineering, Indian Space Research Organization, Electronics and Communication Engineering, VR Siddhartha Engineering College, National Remote Sensing Centre, VR Siddhartha Engineering College, Vijayawada, Andhra Pradesh, India, Hyderabad, India, Vijayawada, Andhra Pradesh, India
1 shared publicationArvind Kumar
K.I.T.E, Jaipur, India-302022
1 shared publicationDinesh Sharma
Chandigarh College of Engineering & Technology (CCET), Chandigarh,-160019 India
1 shared publication
Latest Publications
- 15 March 2024
- Published by World Scientific Pub Co Pte Ltd in Journal of Mechanics in Medicine and Biology
- Vol. 24 (10)
ENHANCED CHAMELEON SWARM OPTIMIZATION-BASED ENSEMBLE LEARNING APPROACH FOR SLEEP STAGE CLASSIFICATION FRAMEWORK
In today’s world, every individual faces the maladies of sleep malfunction, which is diagnosed by analyzing the PolySomnoGraphy (PSG) records. The primary remedy is systematically identifying the sleep stages. But practically, the sleep stage analysis depends on the visual examination of the 30[ ]s time duration of PSG record signals. Such expertise has developed an enormous model to rectify the issues. Albeit, it exhibits effective performance, it becomes cumbersome to handle the large-scale dimension of data. Thus, the model becomes fragile when it is implemented in some sleep clinics. Even if it contains a better compatible of PSG; it subsists with limitations such as obtaining less efficiency and mitigates the robustness of the system. To alleviate this problem, a novel scheme is proposed by an Ensemble Learning Approach (ELA) for sleep stage classification using ElectroEncephaloGram (EEG) signals. Initially, the required EEG signals for the proposed model are gathered from the standard data sources. Further, the garnered EEG signals are utilized in the sleep signal extraction phase, in which the band pass filter is employed for extracting the sleep signals. The extracted sleep signal is used under the signal decomposition phase, which is accomplished by 5-level Discrete Wavelet Transform (DWT) for decomposing the sleep signals. Subsequently, the decomposed signals are given into the feature extraction phase, where the spectral features and Principal Component Analysis (PCA) are used for extracting the EEG signal features. Further, the extracted features are fed as input into ELA using Deep Temporal Convolutional Networks (DTCNs), Long Short-Term Memory (LSTM), and Deep Neural Networks (DNNs) for classifying the sleep stages. Here, the hyper-parameter tuning is engaged for enhancing the classification performance using the Modified Position Updated Chameleon Search Algorithm (MPU-CSA). The experimental analysis is conducted by distinct validating metrics for revealing the efficacy of the developed sleep stage classification model over the conventional models.
- 15 March 2024
- Published by World Scientific Pub Co Pte Ltd in Journal of Mechanics in Medicine and Biology
- Vol. 24 (10)
ENHANCED CHAMELEON SWARM OPTIMIZATION-BASED ENSEMBLE LEARNING APPROACH FOR SLEEP STAGE CLASSIFICATION FRAMEWORK
In today’s world, every individual faces the maladies of sleep malfunction, which is diagnosed by analyzing the PolySomnoGraphy (PSG) records. The primary remedy is systematically identifying the sleep stages. But practically, the sleep stage analysis depends on the visual examination of the 30[ ]s time duration of PSG record signals. Such expertise has developed an enormous model to rectify the issues. Albeit, it exhibits effective performance, it becomes cumbersome to handle the large-scale dimension of data. Thus, the model becomes fragile when it is implemented in some sleep clinics. Even if it contains a better compatible of PSG; it subsists with limitations such as obtaining less efficiency and mitigates the robustness of the system. To alleviate this problem, a novel scheme is proposed by an Ensemble Learning Approach (ELA) for sleep stage classification using ElectroEncephaloGram (EEG) signals. Initially, the required EEG signals for the proposed model are gathered from the standard data sources. Further, the garnered EEG signals are utilized in the sleep signal extraction phase, in which the band pass filter is employed for extracting the sleep signals. The extracted sleep signal is used under the signal decomposition phase, which is accomplished by 5-level Discrete Wavelet Transform (DWT) for decomposing the sleep signals. Subsequently, the decomposed signals are given into the feature extraction phase, where the spectral features and Principal Component Analysis (PCA) are used for extracting the EEG signal features. Further, the extracted features are fed as input into ELA using Deep Temporal Convolutional Networks (DTCNs), Long Short-Term Memory (LSTM), and Deep Neural Networks (DNNs) for classifying the sleep stages. Here, the hyper-parameter tuning is engaged for enhancing the classification performance using the Modified Position Updated Chameleon Search Algorithm (MPU-CSA). The experimental analysis is conducted by distinct validating metrics for revealing the efficacy of the developed sleep stage classification model over the conventional models.
- 27 October 2023
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 18 (2) , 1131-1142
A new automatic sleep stage classification model using swarm intelligence-based hybrid transfer learning architecture
- 27 October 2023
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 18 (2) , 1131-1142
A new automatic sleep stage classification model using swarm intelligence-based hybrid transfer learning architecture
- Open Access
- 8 February 2020
- Published by Association for Computing Machinery (ACM)
- p. 7-11
Detection and Extraction of Roads using Cartosat-2 High Resolution Satellite Imagery
The extraction of roads from panchromatic images has many insightful applications in the fields of urban planning, setting up of transportation, disaster management and cartography in geographical information systems (GIS). The process of extracting roads from high-resolution images is composite, due to the presence of different noises (i.e., buildings, shadows, clouds etc.). Various image processing techniques and various quality measures are applied on the high-resolution remote sensing satellite images to improve the quality of the image and interactively extract the information of roads. Cartosat-2 images available in Bhuvan website of ISRO are taken for testing the validity of proposed method. The proposed method enhances the images using Contrast Limited Adaptive Histogram Equalization (CLAHE) and Line Detector for detecting road segments. Connected component analysis (CCA) is performed on segmented image for connection of disconnected objects in the segmented image. Morphological operations fill the holes caused by the presence of shadows, buildings and trees on the road surface.
- 8 February 2020
- Published by Association for Computing Machinery (ACM)
- p. 7-11
Open AccessDetection and Extraction of Roads using Cartosat-2 High Resolution Satellite Imagery
The extraction of roads from panchromatic images has many insightful applications in the fields of urban planning, setting up of transportation, disaster management and cartography in geographical information systems (GIS). The process of extracting roads from high-resolution images is composite, due to the presence of different noises (i.e., buildings, shadows, clouds etc.). Various image processing techniques and various quality measures are applied on the high-resolution remote sensing satellite images to improve the quality of the image and interactively extract the information of roads. Cartosat-2 images available in Bhuvan website of ISRO are taken for testing the validity of proposed method. The proposed method enhances the images using Contrast Limited Adaptive Histogram Equalization (CLAHE) and Line Detector for detecting road segments. Connected component analysis (CCA) is performed on segmented image for connection of disconnected objects in the segmented image. Morphological operations fill the holes caused by the presence of shadows, buildings and trees on the road surface.
- Open Access
- 8 February 2020
- Published by Association for Computing Machinery (ACM)
- p. 153-157
Object based Classification of Multispectral Remote Sensing Images for Forestry Applications
Multispectral Image classification is one of the Important and complex tasks in remote sensing image analysis. Many approaches have been studied to improve classification performance. Most of these methods use pixel based Classification. Unlike, this paper proposed object based Classification which uses Vector data by make use of geometrical shapes like lines and polygons. Series of steps are designed and implemented for remote sensing satellite images like Deimos-2 and Cartosat-1. The Overall Accuracy (OA) and Kappa coefficient values have shown the effectiveness of the proposed method. These values are 93.6% and 87% respectively for Deimos-2 Data. But for Cartosat-1 Data accuracy values are less and observed as 87.33% and 81%. Besides, the proposed method can be useful in tree parameters estimation along with supported elevation data.
- 8 February 2020
- Published by Association for Computing Machinery (ACM)
- p. 153-157
Open AccessObject based Classification of Multispectral Remote Sensing Images for Forestry Applications
Multispectral Image classification is one of the Important and complex tasks in remote sensing image analysis. Many approaches have been studied to improve classification performance. Most of these methods use pixel based Classification. Unlike, this paper proposed object based Classification which uses Vector data by make use of geometrical shapes like lines and polygons. Series of steps are designed and implemented for remote sensing satellite images like Deimos-2 and Cartosat-1. The Overall Accuracy (OA) and Kappa coefficient values have shown the effectiveness of the proposed method. These values are 93.6% and 87% respectively for Deimos-2 Data. But for Cartosat-1 Data accuracy values are less and observed as 87.33% and 81%. Besides, the proposed method can be useful in tree parameters estimation along with supported elevation data.
- 1 September 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Detection and Enumeration of Trees using Cartosat2 High Resolution Satellite Imagery
Remote sensing plays a key role to monitor the earth resources. Remote sensing uses High Resolution Satellites to capture and observe the various conditions of the earth like Land cover and Land use which provides the information regarding how much of land is covered by forest, wetland, water body and how much of land is used by people for rural development, urbanization and agricultural in digital images. Digital Image Processing is useful in decrypt satellite data which helps to know change detection and land cover classification. In this research, satellite data are used to investigate trees and identifying trees on the earth surface, where it is very difficult task to identify trees from high resolution satellite imagery. Digital Image Processing consists of various techniques like image enhancement, segmentation, feature extraction and classifying the extracted features. In this research, Cartosat2 images are used for detection and enumeration of trees. With utilization of digital image processing, the information can be known that is available in the satellite image. Image processing helps to refines the available data in the satellite images without any loss. Image segmentation is used to analyze the image in a understandable form, where it cleaves the image in the form of pixels. Basically it is used to detect and classify the shapes or object boundaries and other relevant data in the digital images. Contrast Limited Adaptive Histogram Equalization(CLAHE) is one of the effective simple techniques for enhancing image quality. Active Contour Model with masking is best suit for image Segmentation and feature Detection and Tree Enumeration.
- 1 September 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Detection and Enumeration of Trees using Cartosat2 High Resolution Satellite Imagery
Remote sensing plays a key role to monitor the earth resources. Remote sensing uses High Resolution Satellites to capture and observe the various conditions of the earth like Land cover and Land use which provides the information regarding how much of land is covered by forest, wetland, water body and how much of land is used by people for rural development, urbanization and agricultural in digital images. Digital Image Processing is useful in decrypt satellite data which helps to know change detection and land cover classification. In this research, satellite data are used to investigate trees and identifying trees on the earth surface, where it is very difficult task to identify trees from high resolution satellite imagery. Digital Image Processing consists of various techniques like image enhancement, segmentation, feature extraction and classifying the extracted features. In this research, Cartosat2 images are used for detection and enumeration of trees. With utilization of digital image processing, the information can be known that is available in the satellite image. Image processing helps to refines the available data in the satellite images without any loss. Image segmentation is used to analyze the image in a understandable form, where it cleaves the image in the form of pixels. Basically it is used to detect and classify the shapes or object boundaries and other relevant data in the digital images. Contrast Limited Adaptive Histogram Equalization(CLAHE) is one of the effective simple techniques for enhancing image quality. Active Contour Model with masking is best suit for image Segmentation and feature Detection and Tree Enumeration.
- 14 June 2018
- Published by Science Publishing Corporation in International Journal of Engineering & Technology
- Vol. 7 (3) , 1063-1066
Design of compact wideband unequal wilkinson power divider with improved isolation
In this article, a compact unequal, planar Wilkinson power divider with ultra-wideband operation is proposed. The composed power divider having the size of 11.6 mm × 18.5 mm. It consists of one input and two output branches with individual resistive values. Two isolation resistors are used to provide better isolation between the two output ports. The impedance values of each transmission branch and isolation resistors is varied based on the output power division ratio i.e. (P2/P3). The ADS package simulated results of the designed unequal WPD satisfy the operating range (S11 ≤ -10 dB) from 2.5 GHz to 18 GHz and isolation are obtained over the entire frequency of operation.
- 14 June 2018
- Published by Science Publishing Corporation in International Journal of Engineering & Technology
- Vol. 7 (3) , 1063-1066
Design of compact wideband unequal wilkinson power divider with improved isolation
In this article, a compact unequal, planar Wilkinson power divider with ultra-wideband operation is proposed. The composed power divider having the size of 11.6 mm × 18.5 mm. It consists of one input and two output branches with individual resistive values. Two isolation resistors are used to provide better isolation between the two output ports. The impedance values of each transmission branch and isolation resistors is varied based on the output power division ratio i.e. (P2/P3). The ADS package simulated results of the designed unequal WPD satisfy the operating range (S11 ≤ -10 dB) from 2.5 GHz to 18 GHz and isolation are obtained over the entire frequency of operation.
- Open Access
- 30 December 2016
- Published by Indian Society for Education and Environment in Indian Journal of Science and Technology
- Vol. 9 (S1)
Tree Crown Delineation from High Resolution Satellite Images
Tree Crown Delineation from High Resolution Satellite Images
- 30 December 2016
- Published by Indian Society for Education and Environment in Indian Journal of Science and Technology
- Vol. 9 (S1)
Open AccessTree Crown Delineation from High Resolution Satellite Images
Tree Crown Delineation from High Resolution Satellite Images
- Open Access
- 30 December 2016
- Published by Indian Society for Education and Environment in Indian Journal of Science and Technology
- Vol. 9 (S1)
Principal Component Analysis based Assessment of Trees Outside Forests in Satellite Images
This Paper Presents, an automated Matrix Laboratory (MATLAB) based procedure for assessing the number of tree crowns in a High Resolution Satellite Image based on Principal Component Analysis (PCA) algorithm. This automated method comes into picture to reduce the manual power, time and money. PCA involves in a mathematical approach in usage of orthogonal transforms for converting a given set of correlated observed values into a set of modified grey levels of linearly uncorrelated variables and these newly generated values are called principal components. Then a bounded set of thresholding values are used to identify the trees, Laplacian of Gaussian (LOG) operator is used to find and mark the boundaries of trees to extract the tree crowns available in the test site. Finally, count the number of tree crowns by using available morphological open and close operations with the help of connectivity methods. The results obtained are matched with manual approximated count and the accuracy of algorithm is done by testing on 20 different sets of test areas the accuracy achieved is 86.6 and it is better than NDVI and Watershed segmentations. Further improvement is possible when this method is combined with NDVI.
- 30 December 2016
- Published by Indian Society for Education and Environment in Indian Journal of Science and Technology
- Vol. 9 (S1)
Open AccessPrincipal Component Analysis based Assessment of Trees Outside Forests in Satellite Images
This Paper Presents, an automated Matrix Laboratory (MATLAB) based procedure for assessing the number of tree crowns in a High Resolution Satellite Image based on Principal Component Analysis (PCA) algorithm. This automated method comes into picture to reduce the manual power, time and money. PCA involves in a mathematical approach in usage of orthogonal transforms for converting a given set of correlated observed values into a set of modified grey levels of linearly uncorrelated variables and these newly generated values are called principal components. Then a bounded set of thresholding values are used to identify the trees, Laplacian of Gaussian (LOG) operator is used to find and mark the boundaries of trees to extract the tree crowns available in the test site. Finally, count the number of tree crowns by using available morphological open and close operations with the help of connectivity methods. The results obtained are matched with manual approximated count and the accuracy of algorithm is done by testing on 20 different sets of test areas the accuracy achieved is 86.6 and it is better than NDVI and Watershed segmentations. Further improvement is possible when this method is combined with NDVI.