Dr Harish kumar Shakya

Scopus Publications

A hybrid multi-stream deep learning model for cognitive feature-based schizophrenia detection
Muhilarasi Arumugam, Malarvizhi Nandagopal, Harish Kumar Shakya
Discover Computing, 2026
Schizophrenia is a complicated neural condition that has serious effects on thinking, behavioral and perception; thus, early and proper diagnosis is highly necessary to provide early intervention and effective treatment of the disease. Nevertheless, the current detection methods especially the classical deep learning and transfer learning paradigms have several challenges which include, overfitting on large dimensional fMRI data, poor generalizations between datasets and weaknesses in the distributions of subtle neural patterns. Such shortcomings prevent clinical dependability and relevance of automated diagnostic means on actual environments. To address these issues, this work proposes a new framework of integrating Twisted Cascade Mind Network (TwiscaMind-Net) with the Hyper-Intelligent DRaco-Hippo Algorithm (HIDRA) to be robust in schizophrenia classification. TwiscaMind-Net is a new attention-based and multi-stream convolutional neural network based on the idea of twisted processing of the brain to learn complex spatie temporal patterns in the fMRI data. The HIDRA hyper-intelligent, hippocampal neuro-like modeled and Draco-lizard survival based optimization, is an intelligence optimizer that can adjust network settings and select the most discriminating features with a bio-inspired evolutionary algorithm. The offered methodology presupposes fMRI data preprocessing on three classic datasets, including Kaggle Schizophrenia, COBRE, and FBIRN, and then deep extraction of features by using TwiscaMind-Net and optimal adjustment of parameters on the basis of HIDRA. The last clustering is done by a neural final classification layer which is fully connected. The accuracy, sensitivity, and specificity of the model on the COBRE dataset reach the remarkable value of 98.9%, 98.85%, and 98.89, respectively, with a low error rate of only 5.4 and training time of 75 s. Similar results are also on the Kaggle and the FBIRN dataset. On the whole, the TwiscaMind-Net and HIDRA framework can serve as the viable example of an effective and innovative method of schizophrenia detection that would achieve higher diagnostic accuracy, decreased computational expenses, and increased generalizability, which positions the method as an effective tool of clinical decision support in the context of mental health diagnostics.
Wavelet-Pix2pix Framework for CT Denoising and Super Resolution
Chaitanya Vishwakarma, Shubham Jha, Govind Bansal, Harish Kumar Shakya, Durgesh Kumar Jha
Lecture Notes in Networks and Systems, 2026
BFRN-IoV: Blockchain and Fog-Enabled Route Navigation for Digital Twin-Based Internet of Vehicles
Amrendra Singh Yadav, Mihir Bhatt, Sameer Yadav, Sanjeev Kumar Dwivedi, Harish Kumar Shakya
IEEE Open Journal of Vehicular Technology, 2026
The rapid evolution of the Internet of Vehicles (IoV) necessitates secure, scalable, and low-latency route navigation mechanisms that can operate in highly dynamic vehicular environments. Emerging paradigms such as Vehicular Digital Twins (VDTs) further enhance IoV ecosystems by enabling real-time virtual representations of physical vehicles, facilitating predictive analytics, intelligent decision-making, and context-aware routing. However, conventional VANET-based approaches suffer from centralized trust dependencies, high computational overhead, and limited adaptability to real-time traffic conditions. This paper proposes BFRN-IoV, a blockchain- and fog-enabled route navigation framework that integrates lightweight ECC-HMAC-based mutual authentication, RSU-assisted fog routing, and global route validation via a Geo-Location Provider (GLP), while leveraging VDTs for enhanced situational awareness and dynamic route optimization. The framework ensures key security properties-including confidentiality, integrity, pseudonymity, unlinkability, and non-repudiation-using ECDH-derived session keys, HKDF-based key expansion, and HMAC verification, while preserving privacy through pseudonym-based identity management. A permissioned blockchain provides immutable and auditable logging of routing interactions without exposing vehicle identities. Simulation results using SUMO and implementation via Web3 demonstrate significant improvements in routing accuracy, along with reduced communication and computational overhead compared to existing approaches. Formal verification using the Scyther tool confirms robustness against replay, impersonation, and man-in-the-middle attacks. The proposed framework delivers a unified, secure, and efficient solution for real-time IoV route navigation, further strengthened by the integration of VDTs in next-generation intelligent transportation systems.
PPWCS: A Strategy for Enhancing Caching Performance in Content-Centric Networking Enabled Consumer IoT Systems
Sumit Kumar, Rajeev Tiwari, Shashank Sheshar Singh, Harish Shakya, Gyanendra Kumar, Ali Kashif Bashir
IEEE Transactions on Consumer Electronics, 2026
The exponential increase in smart consumer devices and bandwidth-intensive applications is accelerating the integration of 5G and 6G technologies in Internet-of-Things (IoT) ecosystems. Content-Centric Networking (CCN) has gained prominence as a future-oriented Internet architecture for the growing needs of consumer device applications with its in-network caching capability. It offers a scalable solution for efficient content retrieval. However, consumer-grade router nodes have substantially smaller caching capacity, which presents challenges in maintaining Quality-of-Service (QoS). In this direction, this paper proposes a Partitioning and Dynamic Popularity Window-based Caching Strategy (PPWCS) that combines partition-aware collaboration with an adaptive popularity window to optimize content placement in consumer IoT systems. In contrast to prior approaches, PPWCS divides the network nodes into non-overlapping partitions based on the proposed heuristic and takes collaborative caching decisions by identifying frequently requested contents. Comprehensive evaluations on Abilene-based and US-26-based network topologies demonstrate that PPWCS consistently outperforms existing strategies. It achieves up to 10% higher cache hit ratio, 23% lower hop count, 17% lower delay, 20% less traffic, and 17% lower energy consumption in Abilene. Similarly, in US-26 topology, the proposed scheme achieves up to 9% higher cache hit ratio, 21% lower hop count, 20% lower delay, and 18% lower energy consumption. These improvements validate PPWCS as a technically innovative and practically viable solution for consumer IoT networks operating over next-generation network infrastructure.
Leveraging similarity and community-based features for link prediction in temporal social networks using attention-enabled LSTM
Rohit Ahuja, Simranjit Kaur, Harish Kumar Shakya, Shashank Sheshar Singh
Scientific Reports, 2025
Link prediction refers to predicting future or missing links within the social network. Static social networks, with their fixed topology, require less data analysis, making predicting future or missing links relatively easier than in dynamic social networks. Dynamic social networks change over time, which makes link prediction challenging. Modern similarity-based features look at the topological structure of the network but only use a single snapshot to calculate, so they miss important patterns and changes in the network over time. Community features, which divide the whole network into communities, help to improve the prediction by focusing on links between the intra-communities. Our proposed framework, SimCom-AN-LSTM, shows that combining structural and community features can leverage the strengths of both approaches. The sequence-based Long Short-Term Memory (LSTM) model processes the snapshot sequences to capture the network's temporal dependencies. These features help the model learn temporal patterns and predict future links by capturing local interaction between the nodes, the overall network topology, and community structure. The attention mechanism enhances the performance of the LSTM model by giving more weight to the feature that yields the best results. Results indicate that the proposed framework surpasses the individual state-of-the-art algorithms.
Hybrid Convolution-Recurrent Deep Learning Framework for High-Precision Lung and Colon Disease Detection
Anirudh Singh, Satyam Kumar, Jayesh Gangrade, Shweta Gangrade, Harish Kumar Shakya
SN Computer Science, 2025
Plant disease detection using a hybrid dilated CNN with attention mechanisms and optimized mask RCNN segmentation
Kalicharan Sahu, Shivam Tiwari, Manoj Kumar Singh, Jankisharan Pahareeya, Harish Kumar Shakya, Gyanendra Kumar, Shitharth Selvarajan
Scientific Reports, 2025
In accordance with human life, agriculture has main role in it, and in addition to that most people are involved in some kind of agricultural activity either in a direct or indirect manner. Moreover, the agricultural sectors acquired a major role in supplying better quality food and thus made the greatest attribution to the growth of populations and economics. But, the disease over the crop has influenced the growth of the corresponding species and thus requires an earlier diagnosis of plant disease by utilizing the most adequate and automatic detection approach for improving the quality of the production of food as well as to reduce the loss in economic. But, there are no techniques in the conventional system for identifying the disease in diverse crops in the agricultural environment. In modern times, deep learning approaches have acquired tremendous enhancement in the identification of image categorization as well as the object detection system. For precise detection of plant disease, an improved classification model is developed. Initially, from the standard publicly available database, the images of the plants are aggregated. The gathered images are segmented using Dilated, Adaptive, and Attention-based Mask Recurrent Convolutional Neural Networks (DAA-MRCNN). Then, it is fed into a hybrid classification phase, where the new model namely Dilated, Adaptive, and Attention-based Multiscale DenseNet termed as (DAA-MDeNet) for classification. The classifier performance is improved by optimizing the parameter in Mask RCNN and Multiscale DenseNet using the hybrid optimization algorithm named African Vulture and Lemur Optimizer (AVLO). When compared with the other model, a superior performance is shown in the proposed model.
Bioinformatics-Driven Identification of Ferroptosis-Related Gene Signatures Distinguishing Active and Latent Tuberculosis
Rakesh Arya, Hemlata Shakya, Viplov Kumar Biswas, Gyanendra Kumar, Sumendra Yogarayan, Harish Kumar Shakya, Jong-Joo Kim
Genes, 2025
Background: Tuberculosis (TB) remains a major global public health challenge, and diagnosing it can be difficult due to issues such as distinguishing active TB from latent TB infection (LTBI), as well as the sample collection process, which is often time-consuming and lacks sensitivity and specificity. Ferroptosis is emerging as an important factor in TB pathogenesis; however, its underlying molecular mechanisms are not fully understood. Thus, there is a critical need to establish ferroptosis-related diagnostic biomarkers for tuberculosis (TB). Methods: This study aimed to identify and validate potential ferroptosis-related genes in TB infection while enhancing clinical diagnostic accuracy through bioinformatics-driven gene identification. The microarray expression profile dataset GSE28623 from the Gene Expression Omnibus (GEO) database was used to identify ferroptosis-related differentially expressed genes (FR-DEGs) associated with TB. Subsequently, these genes were used for immune cell infiltration, Gene Set Enrichment Analysis (GSEA), functional enrichment and correlation analyses. Hub genes were identified using Weighted Gene Co-expression Network Analysis (WGCNA) and validated in independent datasets GSE37250, GSE39940, GSE19437, and GSE31348. Results: A total of 21 FR-DEGs were identified. Among them, four hub genes (ACSL1, PARP9, TLR4, and ATG3) were identified as diagnostic biomarkers. These biomarkers were enriched in immune-response related pathways and were validated. Immune cell infiltration, GSEA, functional enrichment and correlation analyses revealed that multiple immune cell types could be activated by FR-DEGs. Throughout anti-TB therapy, the expression of the four hub gene signatures significantly decreased in patients cured of TB. Conclusions: In conclusion, ferroptosis plays a key role in TB pathogenesis. These four hub gene signatures are linked with TB treatment effectiveness and show promise as biomarkers for differentiating TB from LTBI.
Recommendation System for Movies Using Improved Version of SOM with Hybrid Filtering Methods
Saurabh Sharma, Harish Shakya
Communications in Computer and Information Science, 2025
Fixing Poorly Written Questions and Classifying Their Difficulty with DistilBERT, ALBERT, CNN, and Explainable AI
Aradhana Saxena, A. Santhanavijayan, Harish Kumar Shakya
Procedia Computer Science, 2025
Classifying question difficulty levels is critical in educational data mining, impacting adaptive learning systems and assessments. However, questions are sometimes poorly written, which can lead to misunderstandings. This study focuses on ensuring questions are clear and comprehensible before classification. By utilizing DistilBERT (Distilled Bidirectional Encoder Representations from Transformers) to clarify ambiguously written questions and ALBERT (A Lite BERT) integrated along with a convolutional neural network (CNN) to classify them, the proposed method enhances both the clarity and accuracy of the classification process. The methodology uses Random Over Sampling (ROS) for dataset balancing and Explainable AI (XAI) techniques, particularly SHAP; to understand model decisions. The models are evaluated on a labelled dataset of questions, with ALBERT achieves a validation accuracy of 94.76% and DistilBERT reaching 91.83%, demonstrating improved handling of class imbalance. Comparisons between ALBERT and RoBERTa (Robustly Optimized BERT Approach) indicate that ALBERT achieves higher accuracy, higher AUC, and lower loss, making it the preferred choice for classification. DistilBERT is used for efficient and effective text correction. This research underscores the importance of question clarification, robust evaluation strategies, and model interpretability in natural language processing tasks, offering valuable insights for the development of intelligent educational systems.
MRI-to-CT Scan Conversion Using CycleGAN: A Deep Learning Approach
Shubham Jha, Chaitanya Vishwakarma, Vemula Ananya, Harish Kumar Shakya
2025 IEEE International Conference on Computer Electronics Electrical Engineering and their Applications Ic2e3 2025, 2025
Cache Invalidation-Based Optimization in Next Generation Wireless Network: Taxonomy, Review, and Future Directions
Rajeev Tiwari, Sumit Kumar, Shashank Sheshar Singh, Harish Kumar Shakya
IEEE Access, 2025
Improved SOM and Hybrid Filtering Techniques for Recommending Next-Generation Movies in the Entertainment Industry
Saurabh Sharma, Ghanshyam Prasad Dubey, Harish Kumar Shakya, Deepak Motwani
Lecture Notes in Electrical Engineering, 2025
Big Data Meets Social Networks: A Survey of Analytical Strategies and Research Challenges
Shashank Sheshar Singh, Shashank Singh, Kuldeep Singh, Vishal Srivastava, Harish Kumar Shakya
IEEE Access, 2025
Smart Agriculture: Harnessing Machine Learning for Plant Disease Detection
Shivali Amit Wagle, Neha Chankhore, Rajiv Iyer, Garima Shukla, Sunaina Sridhar, Harish Kumar Shakya
2025 IEEE 7th International Conference on Computing Communication and Automation Iccca 2025, 2025
Deep Learning Methods for Accurate Modulation Recognition in Radio Signals
Surendra Solanki, Banalaxmi Brahma, Puneet Mittal, Gaurav Kumawat, Harish Kumar Shakya, Yadvendra Pratap Singh
Smart Innovation Systems and Technologies, 2025
Facial Expression Recognition and Deep Learning: Revolutionizing Personalized Music Therapy
Shivali Amit Wagle, Om Mishra, Rajiv Iyer, Garima Shukla, Sunaina Sridhar, Harish Kumar Shakya
2025 IEEE 7th International Conference on Computing Communication and Automation Iccca 2025, 2025
E-Voting System over Conventional Voting System Using Blockchain Technology
Vishan Kumar Gupta, Neeraj Jain, Harish Shakya, Shaili Gupta, Paras Jain, Kanishka Bhatt
Proceedings of the International Conference on Electrical Electronics and Computer Science with Advance Power Technologies A Future Trends Ice2cpt 2025, 2025
Energy-Proficient Cluster Enrichment in Wireless Sensor Networks via Categorized Fuzzy Clustering and Multi-Hop Routing Optimization
Harish Kumar Shakya, Amit Kumar Chandanan, Chatti Subbalakshmi, Geetanjli Khambra, Mohd Shahnawaz Ansari, Ajay Kushwaha, Vandana Roy
SN Computer Science, 2025
Hybrid recommendation system for movies using artificial neural network
Saurabh Sharma, Harish Kumar Shakya
Expert Systems with Applications, 2024
Nested Sentiment Analysis for ESG Impact: Leveraging FinBERT to Predict Market Dynamics Based on Eco-Friendly and Non-Eco-Friendly Product Perceptions with Explainable AI
Aradhana Saxena, A. Santhanavijayan, Harish Kumar Shakya, Gyanendra Kumar, Balamurugan Balusamy, Francesco Benedetto
Mathematics, 2024
Social Network Analysis: A Survey on Process, Tools, and Application
S. Singh, S. Muhuri, S. Mishra, Divya Srivastava, H. K. Shakya, Neeraj Kumar
ACM Computing Surveys, 2024
Advanced security solutions for conversational AI
Ranjana Sikarwar, Harish Kumar Shakya, Ajay Kumar, Anjali Rawat
Conversational Artificial Intelligence, 2024
Optimizing User Satisfaction in Movie Recommendations Using Variable Learning Rates and Dynamic Neighborhood Functions in SOMs
Saurabh Sharma, Ghanshyam Prasad Dubey, Harish Kumar Shaky
International Journal of Experimental Research and Review, 2024
Reducing Cluster Overlap in Movie Recommendations with IKSOM and Silhouette Clustering
Saurabh Sharma, Ghanshyam Dubey, Harish Shakya
International Journal of Experimental Research and Review, 2024
An Elitism-based Novel Approach for Community Detection in Social Networks
Ranjana Sikarwar, Shyam Sunder Gupta, Harish Kumar Shakya
International Journal of Experimental Research and Review, 2024
SOM and Hybrid Filtering: Pioneering Next-Gen Movie Recommendations in the Entertainment Industry
Aditi Aditi, , , , , Ghanshyam Prasad Dubey, Harish Kumar Shakya, Aditi Sharma
Fusion Practice and Applications, 2024
Hybrid Filtering Methods in Movie Recommendation: The Enhanced SOM Approach
Saurabh Sharma, Ghanshyam Prasad Dubey, Harish Kumar Shakya, Deepak Motwani
Lecture Notes in Networks and Systems, 2024
Emotion Recognition by Using Machine Learning for Enhancing Human-Computer Interaction
Kapil Ghai, Anupriya, Paras Jain, Vishan Kumar Gupta, Vidisha, Harish Shakya
Proceedings of the 2024 International Conference on Artificial Intelligence and Emerging Technology Global AI Summit 2024, 2024
Open flow packet in message monitoring to prevent flooding attacks in SDN environment
Karnani Suruchi, Harish Kumar Shakya
Aip Conference Proceedings, 2023
Entrust SDP Authentication to Software-Defined Campus Network (SDCN)
Suruchi Karnani, Harish Kumar Shakya
Lecture Notes in Networks and Systems, 2023
A Hybrid Recommendation System of Upcoming Movies Using Improved version of SOM with Hybrid Filtering Methods
Saurabh Sharma, Harish Kumar Shakya
2023 6th International Conference on Information Systems and Computer Networks Iscon 2023, 2023
Recommendation System for Movies Using Improved version of SOM with Hybrid Filtering Methods
Saurabh Sharma, Harish Kumar Shakya
2023 6th International Conference on Information Systems and Computer Networks Iscon 2023, 2023
Recommendation Systems for a Group of Users Which Recommend Recent Attention: Using Hybrid Recommendation Model
Saurabh Sharma, Harish Kumar Shakya
Communications in Computer and Information Science, 2023
Hybrid Real-Time Implicit Feedback SOM-Based Movie Recommendation Systems
Saurabh Sharma, Harish Kumar Shakya
Lecture Notes in Networks and Systems, 2023
Mitigation strategies for distributed denial of service (DDoS) in SDN: A survey and taxonomy
Suruchi Karnani, Harish Kumar Shakya
Information Security Journal, 2023
Advanced Privacy Preserving Model for Smart Healthcare Using Deep Learning
Pinkal Jain, Harish Kumar Shakya, Ajay Lala
Proceedings of International Conference on Contemporary Computing and Informatics Ic3i 2023, 2023
A Review on Community Detection Using Deep Neural Networks with Enhanced Learning
Ranjana Sikarwar, Shashank Sheshar Singh, Harish Kumar Shakya
Lecture Notes in Networks and Systems, 2023
Opposition-Based Genetic Algorithm for Community Detection in Social Networks
Harish Kumar Shakya, Kuldeep Singh, Yashvardhan Singh More, Bhaskar Biswas
Proceedings of the National Academy of Sciences India Section A Physical Sciences, 2022
Filter Design for Radar Signal Analysis Using Field Programmable Gate Array
Anil Kumar Sahu, Abhishek Singh, Harish Kumar Shakya
Lecture Notes in Mechanical Engineering, 2022
A Review on Community Detection Methods and Algorithms in Social Networks: Open Trends and Challenges
Ranjana Sikarwar, Shashank Sheshar Singh, Harish Kumar Shakya
Lecture Notes in Electrical Engineering, 2022
Internet of Things-Based Intelligent Ontology Model for Safety Purpose Using Wireless Networks
Harish Kumar Shakya, R. Sundar, Ajay Kushwaha, Rakhi Thakur, Anurag S. D. Rai, Praveen Kumar Reddy, M. Sivasubramanian, R. Jaikumar, V. Venkataramanan, S. Chandragandhi, Worku Abera
Wireless Communications and Mobile Computing, 2022
Leveraging SDN for Load Balancing on Campus Network (CN)
Suruchi Karnani, Harish Kumar Shakya
Proceedings 2021 IEEE 13th International Conference on Computational Intelligence and Communication Networks Cicn 2021, 2021
A Review on Social Network Analysis Methods and Algorithms
Ranjana Sikarwar, Harish Kumar Shakya, Shashank Sheshar Singh
Proceedings 2021 IEEE 13th International Conference on Computational Intelligence and Communication Networks Cicn 2021, 2021
Medical Data Classification in Cloud Computing Using Soft Computing With Voting Classifier: A Review
Saurabh Sharma, Harish K. Shakya, Ashish Mishra
Internet of Medical Things Iomt Healthcare Transformation, 2021
Medical Data Security Using Blockchain With Soft Computing Techniques: A Review
Saurabh Sharma, Harish K. Shakya, Ashish Mishra
Internet of Medical Things Iomt Healthcare Transformation, 2021
A location based novel recommender framework of user interest through data categorization
Saurabh Sharma, Harish Kumar Shakya, Venkatadri Marriboyina
Materials Today Proceedings, 2020
Community Structure Identification in Social Networks Inspired by Parliamentary Political Competitions
Harish Kumar Shakya, Nazeer Shaik, Kuldeep Singh, G. R. Sinha, Bhaskar Biswas
Advances in Intelligent Systems and Computing, 2020
EHNL: An efficient algorithm for mining high utility itemsets with negative utility value and length constraints
Kuldeep Singh, Ajay Kumar, Shashank Sheshar Singh, Harish Kumar Shakya, Bhaskar Biswas
Information Sciences, 2019
A study of link prediction using deep learning
Anant Dadu, Ajay Kumar, Harish Kumar Shakya, Siddhartha Kumar Arjaria, Bhaskar Biswas
Communications in Computer and Information Science, 2019
An Implementation of Malware Detection System Using Hybrid C4.5 Decision Tree Algorithm
Ajay Kumar, Shashank Sheshar Singh, Kuldeep Singh, Harish Kumar Shakya, Bhaskar Biswas
Communications in Computer and Information Science, 2019
Mining of high-utility itemsets with negative utility
Kuldeep Singh, Harish Kumar Shakya, Abhimanyu Singh, Bhaskar Biswas
Expert Systems, 2018
An efficient genetic algorithm for fuzzy community detection in social network
Harish Kumar Shakya, Kuldeep Singh, Bhaskar Biswas
Communications in Computer and Information Science, 2017
Happiness index in social network
Kuldeep Singh, Harish Kumar Shakya, Bhaskar Biswas
Communications in Computer and Information Science, 2017
Discovery of Multi-frequent Patterns Using Directed Graph
Kuldeep Singh, Harish Kumar Shakya, Bhaskar Biswas
Emerging Research in Computing Information Communication and Applications Ercica 2015 Volume 2, 2016
Frequent patterns mining from data cube using aggregation and directed graph
Kuldeep Singh, Harish Kumar Shakya, Bhaskar Biswas
Advances in Intelligent Systems and Computing, 2016
An efficient approach to discovering frequent patterns from data cube using aggregation and directed graph
Kuldeep Singh, Harish Kumar Shakya, Bhaskar Biswas
ACM International Conference Proceeding Series, 2015
Improvisation of differential evolution for community detection
Anuranjan Kumar, Vaibhav Gupta, Gaurav Kumar Singh, Harish Kumar Shakya, Bhaskar Biswas
2014 IEEE International Conference on Computational Intelligence and Computing Research IEEE Iccic 2014, 2014

Dr Harish kumar Shakya

EDUCATION

RESEARCH, TEACHING, or OTHER INTERESTS

Scopus Publications

RECENT SCHOLAR PUBLICATIONS

MOST CITED SCHOLAR PUBLICATIONS