VISHAL SRIVASTAVA

@bennett.edu.in

ASSISTANT PROFESSOR
BENNETT UNIVERSITY



              

https://researchid.co/vishalismdhanbad

RESEARCH INTERESTS

Computational Intelligence, Soft Computing, Computer Vision, Image Processing, Graph Mining, Community Detection

23

Scopus Publications

131

Scholar Citations

5

Scholar h-index

3

Scholar i10-index

Scopus Publications

  • Permutation driven evolutionary ordering with dependency filtering for multi-label classification
    Ankush Jain, Daksh Gupta, Sarthak Shukla, and Vishal Srivastava
    Springer Science and Business Media LLC

  • Early-Exit Deep Neural Network - A Comprehensive Survey
    Haseena Rahmath P, Vishal Srivastava, Kuldeep Chaurasia, Roberto G. Pacheco, and Rodrigo S. Couto
    Association for Computing Machinery (ACM)
    Deep neural networks (DNNs) typically have a single exit point that makes predictions by running the entire stack of neural layers. Since not all inputs require the same amount of computation to reach a confident prediction, recent research has focused on incorporating multiple “exits” into the conventional DNN architecture. Early-exit DNNs are multi-exit neural networks that attach many side branches to the conventional DNN, enabling inference to stop early at intermediate points. This approach offers several advantages, including speeding up the inference process, mitigating the vanishing gradients problems, reducing overfitting and overthinking tendencies. It also supports DNN partitioning across devices and is ideal for multi-tier computation platforms such as edge computing. This article decomposes the early-exit DNN architecture and reviews the recent advances in the field. The study explores its benefits, designs, training strategies, and adaptive inference mechanisms. Various design challenges, application scenarios, and future directions are also extensively discussed.

  • BT-LPD: B <sup>+</sup> Tree-Inspired Community-Based Link Prediction in Dynamic Social Networks
    Shashank Sheshar Singh, Samya Muhuri, and Vishal Srivastava
    Springer Science and Business Media LLC

  • A meta-heuristics based framework of cluster label optimization in MR images using stable random walk
    Vishal Srivastava and Shashank Sheshar Singh
    Springer Science and Business Media LLC

  • HyperGCN–a multi-layer multi-exit graph neural network to enhance hyperspectral image classification
    Haseena Rahmath P, Kuldeep Chaurasia, Anika Gupta, and Vishal Srivastava
    Informa UK Limited

  • Partition Clustering in Complex Weighted Networks Using K-Cut Ranking and Krill-Herd Optimization
    Vishal Srivastava, Shashank Sheshar Singh, and Ankush Jain
    Institute of Electrical and Electronics Engineers (IEEE)
    Network partitioning has been studied extensively on undirected and weighted networks that need to partition the graph into small clusters. Graph-cutting is a widely known approach that removes the inter-cluster edges to find the local network clusters. Cutting a network into small clusters is pivotal in a mixed integer optimization problem. Proper selection of cut sequences discards the possibility of trivial partitions and reduces the computation load to improve cluster quality. Proper cut-sequence selection relies on multiple heuristics that restrict this problem from being generalized. Cut-sequence selection is an NP-hard problem that turns out to be challenging for weighted networks. This paper presents a swarm-heuristics-based framework to solve the cut-sequence selection problem in weighted networks. First, we generate an affinity network from a given data set. A cost-based objective function is formalized that takes cut sequences as input and returns the weighted intra-cluster connected components. Subsequently, heuristics-based cut sequences are initialized, and krill-herd optimization is used to solve the objective function. The framework is empirically tested on simulated and real-world networks. Network-based indices are used to measure the quality of partitions. The comparative analysis, computation time, and convergence analysis are performed with state-of-the-art methods to report the competitive behavior of the framework. The framework is highly effective and has paved new ways for future research to solve the cut-sequence selection problem without prior knowledge.


  • Social Network Analysis: A Survey on Measure, Structure, Language Information Analysis, Privacy, and Applications
    Shashank Sheshar Singh, Vishal Srivastava, Ajay Kumar, Shailendra Tiwari, Dilbag Singh, and Heung-No Lee
    Association for Computing Machinery (ACM)
    The rapid growth in popularity of online social networks provides new opportunities in computer science, sociology, math, information studies, biology, business, and more. Social network analysis (SNA) is a paramount technique supporting understanding social relationships and networks. Accordingly, certain studies and reviews have been presented focusing on information dissemination, influence analysis, link prediction, and more. However, the ultimate aim is for social network background knowledge and analysis to solve real-world social network problems. SNA still has several research challenges in this context, including users’ privacy in online social networks. Inspired by these facts, we have presented a survey on social network analysis techniques, visualization, structure, privacy, and applications. This detailed study has started with the basics of network representation, structure, and measures. Our primary focus is on SNA applications with state-of-the-art techniques. We further provide a comparative analysis of recent developments on SNA problems in the sequel. The privacy preservation with SNA is also surveyed. In the end, research challenges and future directions are discussed to suggest to researchers a starting point for their research.


  • A Strategy to Accelerate the Inference of a Complex Deep Neural Network
    P. Haseena Rahmath, Vishal Srivastava, and Kuldeep Chaurasia
    Springer Nature Singapore

  • Manifold Preserving Features and Regression for Semantic Labelling in High Dimensional Images
    Vishal Srivastava, Shashank Sheshar Singh, and Bhaskar Biswas
    Springer Science and Business Media LLC

  • FLP-ID: Fuzzy-based link prediction in multiplex social networks using information diffusion perspective
    Shashank Sheshar Singh, Divya Srivastva, Ajay Kumar, and Vishal Srivastava
    Elsevier BV

  • LM-MFP: large-scale morphology and multi-criteria-based feature pooling for image parsing
    Vishal Srivastava and Bhaskar Biswas
    Springer Science and Business Media LLC

  • CNN-EFF: CNN Based Edge Feature Fusion in Semantic Image Labelling and Parsing
    Vishal Srivastava and Bhaskar Biswas
    Springer Science and Business Media LLC

  • Graph Similarity Using Tree Edit Distance
    Shri Prakash Dwivedi, Vishal Srivastava, and Umesh Gupta
    Springer International Publishing

  • NN-LP-CF: Neural Network Based Link Prediction on Social Networks Using Centrality-Based Features
    Shashank Sheshar Singh, Divya Srivastva, Ajay Kumar, and Vishal Srivastava
    Springer International Publishing

  • Manifold Preserving CNN for Pixel-Based Object Labelling in Images for High Dimensional Feature spaces
    Vishal Srivastava and Bhaskar Biswas
    Springer Science and Business Media LLC
    Deep CNN’s have achieved an excellent performance in computer vision and image processing methods, designating them as a state-of-art in this domain. CNN based applications have achieved tremendous advancement towards vision computing with high dimensional object labelling in images. The complex nature of High Dimensional (HD) images limits the performance of CNN’s. In high dimensional feature space, the pixel-based image labelling is a complex problem for the parsing of objects in an image. To overcome this issue, we have studied a two-stage end-to-end framework that uses manifold embedding based patch-wise CNN architecture to extract the features and classify the image for labelled classes. We have investigated the deep-features with an information fusion technique for low dimensional feature space compression by using pre-trained CNNs and spatiality preserving manifold embedding in the first stage. The cost of pixel-based labelling in HD feature space is very high, so researchers have tried to encapsulate maximum information within the minimum image size. Therefore, in this stage, we have first increased the valuable information by concatenating the deep spatial features and then embedding the massive dataset by using manifold preservation. In stage-2, the image patches are extracted and passed into three layers of convolution-pooling pair and two layers of fully connected pair using parameter tuning. The training dataset is prepared in the form of pixel-label pairs. Subsequently, the proposed method has been evaluated on publicly available images and compared with the previously proposed schemes. The proposed method has outperformed the previous techniques in accuracy and computation time with a significant margin.

  • CNN-based salient features in HSI image semantic target prediction
    Vishal Srivastava and Bhaskar Biswas
    Informa UK Limited
    ABSTRACT Deep networks have escalated the computational performance in the sensor-based high dimensional imaging such as hyperspectral images (HSI), due to their informative feature extraction competency. Therefore in this work, we have extracted the informative features from different CNN models for the benchmark HSI datasets. The deep features have concatenated with spectral features to increase the informative knowledge in the image datacube. The feature concatenation has massively increased the size of datacube. Therefore, we have applied an unsupervised maximum object identification-based salient feature selection to identify the most informative features of datacube and discard the less informative features to reduce the computational time without compromising the accuracy. It is an unsupervised feature selection approach that transforms the data into scale space and achieved robust and strong features. In the previous CNN-based methods, raw features have directly fed to the MLP (multilayer perception) layers for target prediction whereas we have provided our salient features into a multi-core SVM-based set-up and have achieved high accuracy with low computational time as compared to the previous state-of-art techniques.

  • Deep CNN feature fusion with manifold learning and regression for pixel classification in HSI images
    Vishal Srivastava and Bhaskar Biswas
    Informa UK Limited
    ABSTRACT Supervised classification and target recognition of Hyperspectral images (HSI) is a challenging task due to high dimensionality and spectral mixing. Straightforward cognitive computation and target classification lead to high computation cost and low recognition accuracy. Limited availability of training samples makes the recognition process very slow and inaccurate. The main purpose of this work is to improve the classification accuracy for high-dimensional images by the fusion of posterior probability obtained from the two-stage probabilistic framework. The first stage addresses the issue of high dimensionality and the second stage addresses the spectral mixing problem. Both stages provide the prediction probability of pixels in a particular class. In stage-1, we have addressed the imbalance between dimensionality and training samples problem for which we have integrated the deep CNN based spatial and spectral features in combined data-cube form, using ‘off-the-shelf’ CNN models. Subsequently, a graph-based non-linear manifold embedding has performed to extract and fuse the region-wise external information. A probability of prediction has obtained by using LDA classifier. These probabilistic values have denoted as a global probability, as an outcome of stage-1. In the stage-2, the spectral mixing issue was addressed by computing the regional probabilities of class mixing for each pixel. The regional probabilities have calculated by using a regional subspace regression approach. Subsequently, the probabilistic output, obtained from stage-1 and stage-2, has been combined with a linear decision fusion method using regularizers. The experiments have conducted on three real Hyperspectral images, i.e. Indian pines (IP), Pavia University (PU), Salinas Valley (SV) datasets. The probabilistic fusion of stage-1 and stage-2 yields to the maximum overall accuracy of 97.38%, 95.10%, and 99.88% for IP, PU and SV datasets. The over-all accuracies have compared with past methods, and it has found that the proposed framework is providing higher prediction accuracies than previous state-of-art methods.

  • A subspace regression and two phase label optimization for High Dimensional Image classification
    Vishal Srivastava and Bhaskar Biswas
    Springer Science and Business Media LLC
    This paper introduces a two-step algorithm which deals with spectral mixing issue as well as performs the empirical study of continuous labelling in HSI images for over segmentation within class labels. In step-1, we have applied a subspace regression followed by an alpha expansion method to obtain the classified HSI image. This method better classifies the HSI image by removing the spectral mixing problem, which is a well-known problem in HSI domain. The classified image of step-1 is directly used in step-2 to improve the classification result by label update optimization using the energy of clusters. The optimization process in step-2 has performed in two phases. In the first phase of step-2, we have updated the cluster centers by the minimization of cluster energy. This energy minimization has stopped until some stopping criteria have met. The energy minimization has resulted in improved cluster centers. In the second phase of step-2, the RBF kernel based image function has updated using improved cluster centres, obtained from the phase-1. Classification probabilistic result from step-1 and updated image function from step-2 has transformed into a spectral data-cost. Subsequently, the data-cost of step-1 and step-2 have fused with the linear decision fusion method. Finally, The graph-cut method has applied to the fused spectral data-cost(Dc) and a spatial smoothness cost(Sc). Fusion of data-costs has resulted in a significant improvement in accuracy.

  • An efficient feature fusion in HSI image classification
    Vishal Srivastava and Bhaskar Biswas
    Springer Science and Business Media LLC
    In recent times, the fusion of spatial relaxation with spectral data has achieved remarkable success in target classification methods. Spatial relaxation is a scheme which exploits the neighbourhood relationship between the pixels of an image to minimize the spatio-spectral distortion. Application of spatial relaxation with spectral data can lead to reduce the noise effect and increase the class characterization. Such methods can also be applied to estimate the posteriors of the probabilistic classifier, to increase the classifier’s final accuracy. In this paper, we have introduced an edge based feature fusion method which helps in characterizing the class labels of hyperspectral image (HSI) in a better sense. It is an iterative method which exploits the spatial information from an image in such a manner that it assumes the feature preservation in vertical and horizontal directions for each pixel. With combining subspace regression based probabilistic method, the proposed method gives better accuracy for benchmark HSI datasets. Before this, we have implemented a fast Bayesian subspace regression method to achieve the posterior probabilities, for our edge feature relaxation method. Finally, we have compared the results with some recently proposed methods, and $$\\alpha $$ α expansion graph cut optimization method, which is an efficient technique to fuse the contextual knowledge in posterior probabilities.

  • An efficient approach for dimension selection and classification in HSI images
    Vishal Srivastava and Bhaskar Biswas
    Informa UK Limited
    ABSTRACT In this paper, we have proposed a divide and select approach for dimension selection (DSCS) and classification of hyperspectral images (HSI). The DSCS algorithm has been offered using a two-stage framework. In stage-1, we have generated the intermediate channels for every pair of spectral dimensions that are weakly correlated and highly significant. These channels have derived by splitting the adjacent dimensions without any loss of physical meaning. Intermediated channels are concatenated with original HSI in a better sense to transform the image into a more informative datacube. However, this leads to an increase in the dimensionality of the image. In stage-2, a trace and determinant based local feature response approach has applied to select the most informative dimensions of transformed HSI. We have exploited the local feature and scale selection methods to obtain significant channels. Finally, classification experiments have conducted for selected bands with SVM (Support Vector Machine) and LDA (Linear Discriminant Analysis). An expansion graph cut optimization has applied to improve the classification accuracy. This method has demonstrated as state-of-art for target detection in hyperspectral scenes.

  • Mining on the Basis of Similarity in Graph and Image Data
    Vishal Srivastava and Bhaskar Biswas
    Springer Singapore
    Data sets emanating from number of engineering and physical world realm can be depicted as the mutual or one way interaction within a graph like connected structure, in a quite common, robust and relevant way. This is precisely a real context in social graphs, notably the accustomed current advances in navigation in map based technologies, vision on biometrics and various web based application advances towards a disparate range of emerging social graphs and other networks. Careful scrutiny of such networks precisely results in diagnosis of potentially useful and interesting pattern in networks as well as their relative and combined growth. Some social structures of graphs and networks displays the robust commutable behaviour for any community,represented as graph. That is why an precise research plan is exits to describe and analyse the communities within the graph in the domain of community detection. Vast majority of graph based application also resilient in image and vision based application and mining in the field of geoinformation engineering and neural computation. In this paper we studied the graph based approaches for classification and clustering in graph based datasets subsequently we applied the approach in coloured images and identified the clustering trends in both types of data. Our study is completely uncovering the complex nature of graph based trend detection.

RECENT SCHOLAR PUBLICATIONS

  • Permutation driven evolutionary ordering with dependency filtering for multi-label classification
    A Jain, D Gupta, S Shukla, V Srivastava
    International Journal of Machine Learning and Cybernetics, 1-36 2025

  • Early-exit deep neural network-a comprehensive survey
    H Rahmath P, V Srivastava, K Chaurasia, RG Pacheco, RS Couto
    ACM Computing Surveys 57 (3), 1-37 2024

  • HyperGCN–a multi-layer multi-exit graph neural network to enhance hyperspectral image classification
    H Rahmath P, K Chaurasia, A Gupta, V Srivastava
    International Journal of Remote Sensing 45 (14), 4848-4882 2024

  • Partition Clustering in Complex Weighted Networks Using K-Cut Ranking and Krill-herd Optimization
    V Srivastava, SS Singh, A Jain
    IEEE Transactions on Network Science and Engineering 2024

  • BT-LPD: B Tree-Inspired Community-Based Link Prediction in Dynamic Social Networks
    SS Singh, S Muhuri, V Srivastava
    Arabian Journal for Science and Engineering 49 (3), 4039-4060 2024

  • A meta-heuristics based framework of cluster label optimization in MR images using stable random walk
    V Srivastava, SS Singh
    Multimedia Tools and Applications 83 (7), 21397-21434 2024

  • An optimization based framework for region wise optimal clusters in MR images using hybrid objective
    V Srivastava, B Biswas
    Neurocomputing 541, 126286 2023

  • Social network analysis: A survey on measure, structure, language information analysis, privacy, and applications
    SS Singh, V Srivastava, A Kumar, S Tiwari, D Singh, HN Lee
    ACM Transactions on Asian and Low-Resource Language Information Processing 2023

  • An optimization for adaptive multi-filter estimation in medical images and EEG based signal denoising
    V Srivastava
    Biomedical Signal Processing and Control 82, 104513 2023

  • A strategy to accelerate the inference of a complex deep neural network
    P Haseena Rahmath, V Srivastava, K Chaurasia
    Proceedings of Data Analytics and Management: ICDAM 2022, 57-68 2023

  • Manifold Preserving Features and Regression for Semantic Labelling in High Dimensional Images
    V Srivastava, SS Singh, B Biswas
    Wireless Personal Communications 126 (4), 3119-3146 2022

  • NN-LP-CF: Neural Network Based Link Prediction on Social Networks Using Centrality-Based Features
    SS Singh, D Srivastva, A Kumar, V Srivastava
    Deep Learning for Social Media Data Analytics, 27-42 2022

  • Graph similarity using tree edit distance
    SP Dwivedi, V Srivastava, U Gupta
    Joint IAPR International Workshops on Statistical Techniques in Pattern 2022

  • FLP-ID: Fuzzy-based link prediction in multiplex social networks using information diffusion perspective
    SS Singh, D Srivastva, A Kumar, V Srivastava
    Knowledge-Based Systems 248, 108821 2022

  • LM-MFP: large-scale morphology and multi-criteria-based feature pooling for image parsing
    V Srivastava, B Biswas
    Soft Computing 26 (13), 6201-6218 2022

  • CNN-EFF: CNN based edge feature fusion in semantic image labelling and parsing
    V Srivastava, B Biswas
    Neural Processing Letters 54 (3), 1753-1781 2022

  • Manifold preserving CNN for pixel-based object labelling in images for high dimensional feature spaces
    V Srivastava, B Biswas
    Neural Processing Letters 53 (1), 607-635 2021

  • Application of Clustering for Edge and Node Based Community Detection in Networks
    VS Navin Upadhyay, Shashank Sheshar Singh, Ajay Kuamr
    ICDS-2021: International E-Conference on Computing & Data Science 6 (3), 25-30 2021

  • CNN-based salient features in HSI image semantic target prediction
    V Srivastava, B Biswas
    Connection Science 32 (2), 113-131 2020

  • Deep cnn feature fusion with manifold learning and regression for pixel classification in hsi images
    V Srivastava, B Biswas
    Journal of Experimental & Theoretical Artificial Intelligence 32 (2), 339-358 2020

MOST CITED SCHOLAR PUBLICATIONS

  • CNN-based salient features in HSI image semantic target prediction
    V Srivastava, B Biswas
    Connection Science 32 (2), 113-131 2020
    Citations: 39

  • FLP-ID: Fuzzy-based link prediction in multiplex social networks using information diffusion perspective
    SS Singh, D Srivastva, A Kumar, V Srivastava
    Knowledge-Based Systems 248, 108821 2022
    Citations: 20

  • Social network analysis: A survey on measure, structure, language information analysis, privacy, and applications
    SS Singh, V Srivastava, A Kumar, S Tiwari, D Singh, HN Lee
    ACM Transactions on Asian and Low-Resource Language Information Processing 2023
    Citations: 17

  • CNN-EFF: CNN based edge feature fusion in semantic image labelling and parsing
    V Srivastava, B Biswas
    Neural Processing Letters 54 (3), 1753-1781 2022
    Citations: 8

  • An optimization for adaptive multi-filter estimation in medical images and EEG based signal denoising
    V Srivastava
    Biomedical Signal Processing and Control 82, 104513 2023
    Citations: 7

  • An optimization based framework for region wise optimal clusters in MR images using hybrid objective
    V Srivastava, B Biswas
    Neurocomputing 541, 126286 2023
    Citations: 4

  • A strategy to accelerate the inference of a complex deep neural network
    P Haseena Rahmath, V Srivastava, K Chaurasia
    Proceedings of Data Analytics and Management: ICDAM 2022, 57-68 2023
    Citations: 4

  • Graph similarity using tree edit distance
    SP Dwivedi, V Srivastava, U Gupta
    Joint IAPR International Workshops on Statistical Techniques in Pattern 2022
    Citations: 4

  • An efficient feature fusion in HSI image classification
    V Srivastava, B Biswas
    Multidimensional Systems and Signal Processing 31 (1), 221-247 2020
    Citations: 4

  • LM-MFP: large-scale morphology and multi-criteria-based feature pooling for image parsing
    V Srivastava, B Biswas
    Soft Computing 26 (13), 6201-6218 2022
    Citations: 3

  • Manifold preserving CNN for pixel-based object labelling in images for high dimensional feature spaces
    V Srivastava, B Biswas
    Neural Processing Letters 53 (1), 607-635 2021
    Citations: 3

  • Deep cnn feature fusion with manifold learning and regression for pixel classification in hsi images
    V Srivastava, B Biswas
    Journal of Experimental & Theoretical Artificial Intelligence 32 (2), 339-358 2020
    Citations: 3

  • A subspace regression and two phase label optimization for high dimensional image classification
    V Srivastava, B Biswas
    Multimedia Tools and Applications 79 (9), 5897-5918 2020
    Citations: 3

  • Mining on the basis of similarity in graph and image data
    V Srivastava, B Biswas
    Advanced Informatics for Computing Research: Second International Conference 2019
    Citations: 3

  • Early-exit deep neural network-a comprehensive survey
    H Rahmath P, V Srivastava, K Chaurasia, RG Pacheco, RS Couto
    ACM Computing Surveys 57 (3), 1-37 2024
    Citations: 2

  • HyperGCN–a multi-layer multi-exit graph neural network to enhance hyperspectral image classification
    H Rahmath P, K Chaurasia, A Gupta, V Srivastava
    International Journal of Remote Sensing 45 (14), 4848-4882 2024
    Citations: 2

  • BT-LPD: B Tree-Inspired Community-Based Link Prediction in Dynamic Social Networks
    SS Singh, S Muhuri, V Srivastava
    Arabian Journal for Science and Engineering 49 (3), 4039-4060 2024
    Citations: 2

  • An efficient approach for dimension selection and classification in HSI images
    V Srivastava, B Biswas
    Remote Sensing Letters 10 (9), 844-853 2019
    Citations: 2

  • NN-LP-CF: Neural Network Based Link Prediction on Social Networks Using Centrality-Based Features
    SS Singh, D Srivastva, A Kumar, V Srivastava
    Deep Learning for Social Media Data Analytics, 27-42 2022
    Citations: 1