Devesh Kumar Srivastava
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Devesh Kumar Srivastava has a total of 44 co-authors. Here are the top co-authors by number of shared publications:
- Roheet Bhatnagar
Manipal University Jaipur
6 shared publications - Ashok Kumar Saini
Manipal University Jaipur
4 shared publications Ayush Singh
Manipal University Jaipur
3 shared publications- Mayank Srivastava
Department of Electronics and Communication Engineering, NIT Jamshedpur, Jamshedpur, India
3 shared publications - Pradeep Kumar Tiwari
Gurukula Kangri (Deemed To Be University)
3 shared publications - Ajay Kumar
Department of Electronics and Communication Engineering, National Institute of Technology, Jamshedpur, India
2 shared publications
Latest Publications
- 14 August 2026
- Published by Taru Publications in Journal of Discrete Mathematical Sciences and Cryptography
- Vol. 29 (8) , 3027-3036
Trust-aware ad hoc network security using random bit operations and RC4 stream cipher framework
In dynamic and decentralized environments such as ad hoc networks, ensuring secure communication and mutual trust among nodes presents a significant challenge d...
- 14 August 2026
- Published by Taru Publications in Journal of Discrete Mathematical Sciences and Cryptography
- Vol. 29 (8) , 3027-3036
Trust-aware ad hoc network security using random bit operations and RC4 stream cipher framework
In dynamic and decentralized environments such as ad hoc networks, ensuring secure communication and mutual trust among nodes presents a significant challenge d...
- 14 August 2026
- Published by Taru Publications in Journal of Discrete Mathematical Sciences and Cryptography
- Vol. 29 (8) , 3001-3009
P4-assisted context-aware encryption framework for secure packet transmission in active SDN networks
The rapid evolution of Software-Defined Networking (SDN) has transformed modern communication systems by enabling centralized and adaptive control of data flows...
- 14 August 2026
- Published by Taru Publications in Journal of Discrete Mathematical Sciences and Cryptography
- Vol. 29 (8) , 3001-3009
P4-assisted context-aware encryption framework for secure packet transmission in active SDN networks
The rapid evolution of Software-Defined Networking (SDN) has transformed modern communication systems by enabling centralized and adaptive control of data flows...
- 8 February 2026
- Published by Springer Nature
- p. 485-498
Deep Learning Fusion Model for Accurate Event and Timestamp Prediction in Process Monitoring
- 8 February 2026
- Published by Springer Nature
- p. 485-498
Deep Learning Fusion Model for Accurate Event and Timestamp Prediction in Process Monitoring
- 7 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 311-316
Mineral Mapping and Classification Using Advance Machine Learning Techniques
The mining of valuable minerals is aided by remote sensing technology. Launched in November 2000, NASA's Earth Observing I (EOI) satellite is crucial to spectrum research for a variety of applications, including mineral mapping and agriculture. Study of hyperspectral image spectra to identify mineralization zone and mineral spectral behavior. Spectral Angle Mapper classification helps in the detection and mapping of End-members such as Hematite, Montmorillonite and Pyrrhotite. It is clear from this study that Hyperion EO-1 Data can be successfully used for fast mineral identification. For identification and abundance mapping for the mineral in 2-plot (Spectral plot), the wavelength range is between $2.0-2.5 \mu ~\mathrm{m}$. The goal of mineral mapping is to map and detect differences. Techniques are used for remote sensing of minerals in a specific area. The study requires the gathering of satellite imagery data and the use of advanced image processing algorithms that identify and classify minerals based on their unique spectral signatures. The study also involves the use of Ground truth data to validate the accuracy of the remote sensing techniques. The results of this study contribute to mineral exploration, environmental monitoring, and resource management. Overall, Mineral Mapping research provides a complete measure for mineral identification and Mapping can be useful in a number of ways for various industries and applications. First, for mapping, the classification of the minerals is important, and here a CNN model is used for classification. It classifies minerals into seven classes and provides them with their labels using a machine learning-based framework.- 7 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 311-316
Mineral Mapping and Classification Using Advance Machine Learning Techniques
The mining of valuable minerals is aided by remote sensing technology. Launched in November 2000, NASA's Earth Observing I (EOI) satellite is crucial to spectrum research for a variety of applications, including mineral mapping and agriculture. Study of hyperspectral image spectra to identify mineralization zone and mineral spectral behavior. Spectral Angle Mapper classification helps in the detection and mapping of End-members such as Hematite, Montmorillonite and Pyrrhotite. It is clear from this study that Hyperion EO-1 Data can be successfully used for fast mineral identification. For identification and abundance mapping for the mineral in 2-plot (Spectral plot), the wavelength range is between $2.0-2.5 \mu ~\mathrm{m}$. The goal of mineral mapping is to map and detect differences. Techniques are used for remote sensing of minerals in a specific area. The study requires the gathering of satellite imagery data and the use of advanced image processing algorithms that identify and classify minerals based on their unique spectral signatures. The study also involves the use of Ground truth data to validate the accuracy of the remote sensing techniques. The results of this study contribute to mineral exploration, environmental monitoring, and resource management. Overall, Mineral Mapping research provides a complete measure for mineral identification and Mapping can be useful in a number of ways for various industries and applications. First, for mapping, the classification of the minerals is important, and here a CNN model is used for classification. It classifies minerals into seven classes and provides them with their labels using a machine learning-based framework.- 7 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 973-978
Identification and Categorization of Gemstones Through Deep Learning Approach
In this research work, machine learning and convolutional neural network (CNN) techniques are employed for object recognition and classification of gemstones. By using CNN, we can identify patterns in a gemstone to determine its proper classification. The images were cropped using bounding boxes to only retain the necessary areas. Furthermore, CANNY and VGG16 have been used for image recognition. Canny is used to find the coordinates in the image of the gemstone and create a virtual boundary around the image. VGG-16 is used for image classification and recognition. A dataset [2] from Kaggle was used for the completion of this study. Because ADAM method is so effective to handle complex problems with huge amount of data and many parameters, so it is chosen for Optimization. Since it is easy to optimize models that are close to linear, RELU (Rectified Linear Unit) function is chosen as the activation function for CNN's input layers. Canny and Hough line method are used for edge and border detection of the gems. SOFTMAX is utilized for the output layer. Its functions similarly to the sigmoid function and divides each output into equal halves such that the sum of all the outputs produces one. While processing this model, an accuracy of 87% is attained.
- 7 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 973-978
Identification and Categorization of Gemstones Through Deep Learning Approach
In this research work, machine learning and convolutional neural network (CNN) techniques are employed for object recognition and classification of gemstones. By using CNN, we can identify patterns in a gemstone to determine its proper classification. The images were cropped using bounding boxes to only retain the necessary areas. Furthermore, CANNY and VGG16 have been used for image recognition. Canny is used to find the coordinates in the image of the gemstone and create a virtual boundary around the image. VGG-16 is used for image classification and recognition. A dataset [2] from Kaggle was used for the completion of this study. Because ADAM method is so effective to handle complex problems with huge amount of data and many parameters, so it is chosen for Optimization. Since it is easy to optimize models that are close to linear, RELU (Rectified Linear Unit) function is chosen as the activation function for CNN's input layers. Canny and Hough line method are used for edge and border detection of the gems. SOFTMAX is utilized for the output layer. Its functions similarly to the sigmoid function and divides each output into equal halves such that the sum of all the outputs produces one. While processing this model, an accuracy of 87% is attained.
- Open Access
- 26 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 58407-58424
Multi-Modal Deep Embedded Clustering (MM-DEC): A Novel Framework for Mineral Detection Using Hyperspectral Imagery
Identification of minerals through remote sensing imagery plays an important role in mineral exploration, especially when ground truth data or field work is not accessible. Hyperspectral imaging, which collects information from hundreds of narrow spectral bands, is a powerful tool that provides intricate surface information, but presents challenges due to its high-dimensionality and the complex structure of the data. To this end, we propose Multi-Modal Deep Embedded Clustering (MM-DEC) approach, an innovative unsupervised learning framework that integrates Convolutional Autoencoders(CAEs), Variational Autoencoders (VAEs), and Gray Level Co-occurrence Matrix (GLCM) based texture extraction that is able to exploit the spatial, spectral, and texture features of mineral in consideration We demonstrate the MM-DEC potential to identify hematite prospects in the mineralized Kiriburu area of Jharkhand, India using EO-1 Hyperion hyperspectral data. Preprocessing pipeline includes denoising using Machine Learning(ML) and statistical techniques, followed by major land cover classification based on spectral indices including Normalized Difference Vegetation Index (NDVI); Normalized Difference Water Index (NDWI) and Normalized Difference Soil Index (NDSI). By using the widely applied Pixel Purity Index (PPI), pure spectral pixels are extracted for refining and providing a high-confidence target point of hematite detection. Evaluation metrics based on cluster quality such as Silhouette Score, and Davies-Bouldin Index(DBI), show that MM-DEC is a competent model, as it is able to produce relatively compact and well-defined clusters as compared to conventional clustering methods. We achieved a similarity score of 98.69% in reference to the hematite spectral signatures. With accurate cluster labels, geographical coordinates, and spectral similarity scores, our method establishes a precedent in mineral extraction and resource planning based on remote sensing advancements.
- 26 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 58407-58424
Open AccessMulti-Modal Deep Embedded Clustering (MM-DEC): A Novel Framework for Mineral Detection Using Hyperspectral Imagery
Identification of minerals through remote sensing imagery plays an important role in mineral exploration, especially when ground truth data or field work is not accessible. Hyperspectral imaging, which collects information from hundreds of narrow spectral bands, is a powerful tool that provides intricate surface information, but presents challenges due to its high-dimensionality and the complex structure of the data. To this end, we propose Multi-Modal Deep Embedded Clustering (MM-DEC) approach, an innovative unsupervised learning framework that integrates Convolutional Autoencoders(CAEs), Variational Autoencoders (VAEs), and Gray Level Co-occurrence Matrix (GLCM) based texture extraction that is able to exploit the spatial, spectral, and texture features of mineral in consideration We demonstrate the MM-DEC potential to identify hematite prospects in the mineralized Kiriburu area of Jharkhand, India using EO-1 Hyperion hyperspectral data. Preprocessing pipeline includes denoising using Machine Learning(ML) and statistical techniques, followed by major land cover classification based on spectral indices including Normalized Difference Vegetation Index (NDVI); Normalized Difference Water Index (NDWI) and Normalized Difference Soil Index (NDSI). By using the widely applied Pixel Purity Index (PPI), pure spectral pixels are extracted for refining and providing a high-confidence target point of hematite detection. Evaluation metrics based on cluster quality such as Silhouette Score, and Davies-Bouldin Index(DBI), show that MM-DEC is a competent model, as it is able to produce relatively compact and well-defined clusters as compared to conventional clustering methods. We achieved a similarity score of 98.69% in reference to the hematite spectral signatures. With accurate cluster labels, geographical coordinates, and spectral similarity scores, our method establishes a precedent in mineral extraction and resource planning based on remote sensing advancements.
- 29 December 2024
- Published by Springer Nature
- p. 101-111
Classification and Prediction of Knee Osteoarthritis by Deep Learning Approach
- 29 December 2024
- Published by Springer Nature
- p. 101-111
Classification and Prediction of Knee Osteoarthritis by Deep Learning Approach
- Open Access
- 1 December 2024
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 14 (6) , 6913-6928
Noise reduction in Hyperion high dynamic range hyperspectral data using machine learning and statistical techniques
Numerous remote sensing applications rely heavily on hyperspectral imagery, but it is frequently plagued by noise, which degrades the data quality and hinders subsequent analysis. In this research paper, we present an in-depth analysis of noise removal techniques for hyperspectral imagery, specifically for data acquired from the Hyperion EO-1 sensor. Setting off with obtaining Hyperion data and the pre-processing stages, the paper discusses the acquisition and denoising of Hyperion data. The hyperspectral data considered is in the high dynamic range (HDR) format, which maintains the original imagery's complete dynamic range. The study explores various noise reduction methods, such as minimum noise fraction (MNF), principal component analysis (PCA), wavelet denoising, non-local means (NLM), and denoising autoencoders, aimed at enhancing the signal-to-noise ratio. The effectiveness of these techniques is evaluated through visual quality, mean square error (MSE), and peak signal-to-noise ratio (PSNR), alongside their impact on mineral exploration. Furthermore, the paper investigates the application of machine learning algorithms on denoised data for mineral identification, highlighting the potential of integrating denoising techniques with machine learning for improved mineral exploration. This comparative analysis aims to identify the most efficient noise removal methods for hyperspectral imagery, facilitating higher quality data for subsequent analysis.
- 1 December 2024
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 14 (6) , 6913-6928
Open AccessNoise reduction in Hyperion high dynamic range hyperspectral data using machine learning and statistical techniques
Numerous remote sensing applications rely heavily on hyperspectral imagery, but it is frequently plagued by noise, which degrades the data quality and hinders subsequent analysis. In this research paper, we present an in-depth analysis of noise removal techniques for hyperspectral imagery, specifically for data acquired from the Hyperion EO-1 sensor. Setting off with obtaining Hyperion data and the pre-processing stages, the paper discusses the acquisition and denoising of Hyperion data. The hyperspectral data considered is in the high dynamic range (HDR) format, which maintains the original imagery's complete dynamic range. The study explores various noise reduction methods, such as minimum noise fraction (MNF), principal component analysis (PCA), wavelet denoising, non-local means (NLM), and denoising autoencoders, aimed at enhancing the signal-to-noise ratio. The effectiveness of these techniques is evaluated through visual quality, mean square error (MSE), and peak signal-to-noise ratio (PSNR), alongside their impact on mineral exploration. Furthermore, the paper investigates the application of machine learning algorithms on denoised data for mineral identification, highlighting the potential of integrating denoising techniques with machine learning for improved mineral exploration. This comparative analysis aims to identify the most efficient noise removal methods for hyperspectral imagery, facilitating higher quality data for subsequent analysis.
- Open Access
- 1 April 2024
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 14 (2) , 2191-2201
SADCNN-ORBM: a hybrid deep learning model based citrus disease detection and classification
Citrus disease has a significant influence on agricultural productivity these days, so technology based on artificial intelligence has been developed for creating computer vision (CV) models. By spotting disease in its early stages and enabling necessary productivity actions, CV in agriculture improves the production of agricultural goods. In this paper, we developed a CV-based citrus disease detection model called the self-attention dilated convolutional neural network optimized restricted Boltzmann machine (SADCNN-ORBM) model, which consists of two crucial parts: a SADCNN for disease segmentation and an ORBM optimized by the self-adaptive coati optimization (SACO) algorithm to improve the classification performance of diseases, which successfully divides the disease type into three groups: anthracnose, melanose, and brown spot. Numerous feature sets, such as texture features, three-channel red, green, blue (RGB) features, local binary pattern (LBP) features, and speeded-up robust features (SURF) features, are combined and given as input into the classification layer in the proposed model. We compare our proposed model's performance with existing methods by using several evaluation metrics. The findings demonstrate the SADCNN-ORBM model's superiority in precisely recognizing and classifying citrus illnesses, outperforming all available techniques.
- 1 April 2024
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 14 (2) , 2191-2201
Open AccessSADCNN-ORBM: a hybrid deep learning model based citrus disease detection and classification
Citrus disease has a significant influence on agricultural productivity these days, so technology based on artificial intelligence has been developed for creating computer vision (CV) models. By spotting disease in its early stages and enabling necessary productivity actions, CV in agriculture improves the production of agricultural goods. In this paper, we developed a CV-based citrus disease detection model called the self-attention dilated convolutional neural network optimized restricted Boltzmann machine (SADCNN-ORBM) model, which consists of two crucial parts: a SADCNN for disease segmentation and an ORBM optimized by the self-adaptive coati optimization (SACO) algorithm to improve the classification performance of diseases, which successfully divides the disease type into three groups: anthracnose, melanose, and brown spot. Numerous feature sets, such as texture features, three-channel red, green, blue (RGB) features, local binary pattern (LBP) features, and speeded-up robust features (SURF) features, are combined and given as input into the classification layer in the proposed model. We compare our proposed model's performance with existing methods by using several evaluation metrics. The findings demonstrate the SADCNN-ORBM model's superiority in precisely recognizing and classifying citrus illnesses, outperforming all available techniques.
- 29 February 2024
- Published by Springer Nature
- p. 9-20
Feature Extraction and Fusion Method for Detection and Classification of Gastrointestinal Diseases Using Deep Learning Algorithms
- 29 February 2024
- Published by Springer Nature
- p. 9-20
Feature Extraction and Fusion Method for Detection and Classification of Gastrointestinal Diseases Using Deep Learning Algorithms