Shashank Dhananjaya

@nie.ac.in

Associate Professor in Department of Information Science and Engineering
The National Institute of Engineering

Shashank Dhananjaya


               Download Compact PDF  
https://researchid.co/shashankmysore

EDUCATION

B.E. in Computer Science and Engineering
M.Tech in Software Engineering
Ph.D. from VTU

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Science, Software
17

Scopus Publications

40

Scholar Citations

4

Scholar h-index

1

Scholar i10-index

Scopus Publications

  • DeepCog: Classification of Mild Cognitive Impairment Using Structural MRI
    Lavanya M S
    Journal of Applied Data Sciences, 2026
    Early identification of Mild Cognitive Impairment (MCI) is essential for preventing or delaying the progression of severe neurodegenerative disorders. The primary objective of this study is to develop an automated and computationally efficient framework for detecting MCI using structural brain imaging. The proposed research focuses on improving early diagnostic capability through a deep learning–based classification system that analyzes structural changes in brain images. The major contribution of this work lies in combining region-focused morphometric analysis with lightweight convolutional neural network architecture to achieve accurate classification while maintaining computational efficiency suitable for clinical environments. The methodology involves extracting anatomically meaningful features from structural brain scans using a region-of-interest based morphometric approach. Brain images undergo several preprocessing procedures including skull stripping, normalization, spatial alignment and data augmentation to ensure consistency and robustness of the dataset. After preprocessing, the images are used to train a lightweight deep learning model that performs binary classification between cognitively normal subjects and individuals with MCI. The study employs a publicly available neuroimaging dataset consisting of structural brain scans and associated clinical information. Experimental results demonstrate that the proposed framework achieves strong classification performance while maintaining low computational complexity. The model achieves 88.2% subject-wise test accuracy and 0.90 cross-validation accuracy, outperforming commonly used architectures such as VGG16 (78.1%) and ResNet50 (53.7%). These findings indicate that lightweight neural networks combined with region-based anatomical analysis can effectively support automated screening of MCI. The proposed approach has potential implications for scalable clinical decision support systems and may assist neurologists in early diagnosis, timely intervention, and improved cognitive healthcare management. Future research may explore multimodal data integration and longitudinal clinical validation to further enhance diagnostic reliability.
  • Optimized Cross-Modal Data Fusion Framework for Robust Emotion Recognition Multimodal using Hybrid Deep Learning Techniques
    International Journal of Intelligent Engineering and Systems, 2026
    Emotion recognition has become a critical component in modern affective computing systems, influencing applications in healthcare, human-computer interaction (HCI), and intelligent tutoring systems.In this paper, we present an Optimized Fusion for Cross-Modal Adaptive Emotion Recognition (OF-CMAER).It is a novel framework to perform cross-modal emotion recognition using modality-specific encoders, cross-modal attention alignment, adaptive weight optimization, and contrastive fusion with classification.Proposed OF-CMAER model evaluated on four benchmark datasets like MELD, IEMOCAP, K-EmoCon, RAVDESS and a mixed dataset combining all modalities.In our experiments, OF-CMAER significantly outperforms state-of-the-art models like TFN, LMF, and MGAT across all datasets achieving an average accuracy of 95.9%, with a weighted F1 of 95.3% and a macro F1 of 94.6% over all datasets.The proposed approach exhibits strong generalization across unseen data, establishing a promising direction toward lightweight, interpretable, and robust emotion recognition systems.
  • Robust Emotion Recognition Multimodal Using an Optimized Cross-Modal Data Fusion Framework
    Monika Sharma D, Sonika Sharma D, Mohanish B M, Shashank Dhananjaya, Reshma J, Dhruva M S, Chaithra C P
    Journal Europeen Des Systemes Automatises, 2026
  • A Conversational Healthcare Companion in Kannada
    Jayalakshmi Raju, K. Rohitaksha, K. S. Rekha, Bhat Geetalaxmi Jairam, M. Narender, Shashank Dhananjaya, G. S. Ananth
    Engineering Technology and Applied Science Research, 2026
    This study presents an AI-powered bilingual healthcare chatbot to enhance accessibility to primary medical assistance by enabling seamless interactions in both Kannada and English—addressing a critical gap in digital healthcare solutions for multilingual populations. Integrating machine learning–based symptom prediction, voice-enabled communication, secure SQLite-driven appointment scheduling, and Gemini AI for natural conversational responses, the system offers a unified and intelligent healthcare support framework. A multi-class classification model covering 41 disease categories was developed using symptom-level inputs derived from a large-scale clinical dataset comprising approximately 4,900 patient records. To ensure robust and unbiased evaluation, 5-fold stratified cross-validation was employed. Experimental results show that the Random Forest–based model achieved an average classification accuracy of 91%, with consistently balanced precision, recall, and F1-scores across disease classes. Additional noise-injection experiments further confirm the model's robustness under realistic symptom uncertainties. These findings highlight the system's effectiveness as a first-level clinical decision support tool. The key novelty of this work lies in the seamless integration of bilingual conversational AI, predictive analytics, and automated appointment management, offering an end-to-end, accessible, and context-aware healthcare assistance platform. This contribution is particularly significant for resource-constrained and linguistically diverse regions, where timely and reliable medical guidance remains a critical challenge.
  • Early Detection and Severity Classification of Diabetic Retinopathy Using Convolutional Neural Networks
    S. A. Karthik, M. N. Geetha, K. Prabhavathi, Dhananjaya Shashank, K. P. Suhaas, M. Narender
    SN Computer Science, 2025
    Diabetic retinopathy (DR) has become a leading cause of blindness, and detection of the condition at an early stage is important for successful treatment. Nonetheless, it is quite difficult to detect DR in its initial stages in areas with a lack of medical care. This research seeks to develop a neural network that will have the ability to (1) detecting the presence or absence of DR, (2) early, detection (3) classification of severity of DR. We used the APTOS DR dataset that contains 3681 fundus images with DR ratings from 0 (no DR) to 4 (severe proliferative DR). Three distinct models were trained: a binary classifier, an early detector, and a severity classifier that use a neural network with three convolutional layers, a global average pooling layer, and three fully connected layers. The models were cross-validated, with a fivefold used, tracking the training and validation accuracy. The binary classifier was able to have a validation accuracy of 96.2% and an AUC of 0.992, which is higher than existing models in the literature. Early detector managed to have 86% accuracy but had difficulty distinguishing between early and severe DR. The accuracy of the severity classifier was 79.4%, being very successful in detecting healthy subjects but failing to classify more severe cases, possibly because of the model’s inability to discriminate against slight differences between later DR degrees. Such results show the effectiveness of the NN usage in the diagnostics of DR and its classification, but still, more work is required for better severity prediction.
  • A Blockchain-Enabled GNN Framework for Secure Routing in IoT Networks
    Rekha K S, Bhat Geetalaxmi Jairam, Jagruthi H, Shashank Dhananjaya, Sonika Sharma D, Suhaas K P, Rakhi Krishna C R, Sunitha R
    International Journal of Safety and Security Engineering, 2025
    The Internet of Things (IoT) has made secure and reliable data communication more difficult due to its dynamic topologies, energy constrictions, and intelligent and sophisticated adversaries.To address these difficulties in IoT networks, we propose G-TrustChain, an integrated hybrid framework based on Graph Neural Networks (GNNs) for intelligent and dynamic routing and a light Blockchain for distributed trust.G-TrustChain makes use of node-level parameters including latency, remaining energy, and behavioural trust scores derived from a Graph Attention Network (GAT) for routing paths.A lightweight Directed Acyclic Graph (DAG)-structure Blockchain maintains trust scores with a distributed, scalable, and tamper-proof ledger that minimizes dependency on a centralized authority.Experimentation is done for 10,000 rounds, G-TrustChain demonstrated superior routing performance to other protocols such as Trust-based Routing, BBTR, and ROUTENET.It is achieving 95.6% packet delivery ratio, 91.2% detection rate of attacks, and energy consumption as low as 0.0110 J/bit.Also achieving more accurate and reliable trust scores despite energy constraints and higher/extensive attacks.These outcomes demonstrated G-TrustChain provides energy-efficient, secure, and intelligent data communication for the next generation of IoT networks.
  • A Framework for the Video Surveillance Suspicious Activity Detection
    K. Rohitaksha, Annapurna L. Pujari, Shashank Dhananjaya, M. Narender
    Engineering Technology and Applied Science Research, 2025
    Video surveillance is globally considered to be of considerable importance. Recent advances have resulted in notable improvements in the incorporation of artificial intelligence, machine learning, and deep learning techniques into video surveillance devices. The utilization of combinations and distinct frameworks facilitates the differentiation of various questionable behaviors through real-time image analysis. Human behavior is inherently unpredictable, making it difficult to determine whether it is suspicious or typical. This study characterized human actions into two categories: normal and suspicious. Normal actions include sitting, strolling, running, waving hands, etc., while arrest, abuse, shoplifting, etc., are examples of suspicious actions. This study used a convolutional neural network, achieving 97.96% accuracy on the CIFAR-100 dataset, demonstrating its effectiveness in recognizing and categorizing various activities, and paving the way for improved surveillance and security applications. Future work will focus on further refining the model and expanding its capabilities to include real-time video analysis, allowing more dynamic responses to potential threats and enabling faster decision-making in critical situations. Additionally, the integration of advanced algorithms for behavior prediction could further enhance the model's performance in complex environments.
  • Deep Reinforcement Learning-Based Energy-Aware Intrusion Prevention in IoT Environment
    K. S. Rekha, Priyadarshini Jainapur, K. Manjushree, Shashank Dhananjaya, S. R. Nandini, G. Nandini, R. Sunitha
    International Journal of Safety and Security Engineering, 2025
  • A Hybrid CNN-BiLSTM Model for Minimizing Packet Loss in IoT-Enabled Wireless Sensor Networks
    G N Shwetha, Shashank Dhananjaya, H Jagruthi, K S Rekha, R Pankaja, Abhilasha P Kumar, R Mahesh
    Ingenierie Des Systemes D Information, 2025
    Sensors embedded in Wireless Sensor Networks (WSNs) form a foundation in the Internet of Things (IoT) architecture.Nonetheless, packet loss caused by unreliable communication, interference, and energy limitations continues to be a major issue.In this paper, we propose a Convolutional Neural Networks and Bidirectional Long Short Term Memory (CNN-BiLSTM) combined Deep Learning (DL) approach for packet loss minimization in IoT based WSNs.Our model uniquely integrates CNN to capture spatial features with a BiLSTM to capture temporal dependencies, allowing for more accurate inherent prediction of packet loss and intelligent routing in IoT-enabled WSNs.This hybrid design allows for the proposed model to outperform independent deep learning models and traditional routing protocols in both prediction accuracy and performance at the network level.Given the traditional models such as AODV and independent LSTM/CNN approaches.Proposed model has a packet loss reduction of 52%, an overall throughput improvement of 18.7%, and maintained low latency and energy consumption, contributing to the overall success of routing decisions in practical WSN scenarios.This makes the proposed hybrid model is highly suitable for the implementation in the real-time applications.
  • Privacy-Preserving IoT Framework with Federated Learning and Lightweight NLP Integration
    Kallinatha H D, Suhas G K, Chaithra M, Shashank Dhananjaya, Suhaas K P, Bhat Geetalaxmi Jairam, Sunitha R
    Journal Europeen Des Systemes Automatises, 2025
  • AI Infused Secure Biometric Authentication for Remote Patient Monitoring Systems
    Rajeshwari D, Shashank Dhananjaya, Manasa KB, Chaya P, Shruthi B. S
    2nd International Conference on Research Methodologies in Knowledge Management Artificial Intelligence and Telecommunication Engineering Rmkmate 2025, 2025
  • An Advanced AI Framework for Mental Health Diagnostics Using Bidirectional Encoder Representations from Transformers with Gated Recurrent Units and Convolutional Neural Networks
    G. Pushpa, M. Chaitra, Lakshmi P. Kolur, Shashank Dhananjaya, M. N. Kavyasri, R. Sunitha, Abhilasha P. Kumar
    Ingenierie Des Systemes D Information, 2025
  • Millets Industry Dynamics: Leveraging Sales Projection and Customer Segmentation
    K. P. Suhaas, B. G. Deepa, D. Shashank, M. Narender
    SN Computer Science, 2024
  • An Energy-Efficient and Secure WSN Routing Protocol Using Bayesian Networks and Elitist Genetic Algorithms
    Abhilasha P. Kumar, Sunitha R, Chaithra M, Shashank Dhananjaya, Kavyasri M N, Nandini G
    Journal Europeen Des Systemes Automatises, 2024
  • End to End Model to Reduce the Inference, Jamming, and to Increase the Trust from the Compromised Secondary Nodes in Cognitive Radio Networks
    Shashank Dhananjaya, Narender M, Sunitha R
    Proceedings of the 2nd International Conference on Intelligent and Innovative Technologies in Computing Electrical and Electronics Iciitcee 2024, 2024
  • Identification of Counterfeit Products Using Blockchain in E-Commerce
    H. C. Pavithra, J. Rajeshwari, R. Sunitha, Shashank Dhanajaya, Abhilasha P. Kumar, J. Chandrika
    Lecture Notes in Networks and Systems, 2024
  • A Novel Method in Matched Filter Spectrum Sensing to Minimize Interference from Compromised Secondary Users of Cognitive Radio Networks
    Shashank Dhananjaya, B N Yuvaraju
    3rd International Conference on Electrical Electronics Communication Computer Technologies and Optimization Techniques Iceeccot 2018, 2018

RECENT SCHOLAR PUBLICATIONS

  • A Conversational Healthcare Companion in Kannada
    J Raju, K Rohitaksha, KS Rekha, BG Jairam, M Narender, S Dhananjaya, ...
    Engineering, Technology & Applied Science Research 16 (1), 32377-32383 , 2026
    2026
  • Robust Emotion Recognition Multimodal Using an Optimized Cross-Modal Data Fusion Framework.
    S Dhananjaya
    Journal Européen des Systèmes Automatisés 59 (1), 275 , 2026
    2026
  • A Blockchain-Enabled GNN Framework for Secure Routing in IoT Networks.
    BG Jairam, S Dhananjaya
    International Journal of Safety & Security Engineering 15 (9) , 2025
    2025
    Citations: 1
  • A Framework for the Video Surveillance Suspicious Activity Detection
    K Rohitaksha, AL Pujari, S Dhananjaya, M Narender
    Engineering, Technology & Applied Science Research 15 (4), 25402-25406 , 2025
    2025
    Citations: 1
  • Deep Reinforcement Learning-Based Energy-Aware Intrusion Prevention in IoT Environment.
    KS Rekha, P Jainapur, K Manjushree, S Dhananjaya, SR Nandini, ...
    International Journal of Safety & Security Engineering 15 (8) , 2025
    2025
  • Synchronized transform-aggregate model for big data analytics towards in distributed cloud ecosystem.
    R Dembala, K Ananthapadmanabha, S Dhananjaya
    International Journal of Electrical & Computer Engineering (2088-8708) 15 (4) , 2025
    2025
  • A hybrid CNN-BiLSTM model for minimizing packet loss in IoT-enabled wireless sensor networks
    GN Shwetha, S Dhananjaya, H Jagruthi, KS Rekha, R Pankaja, AP Kumar, ...
    Ingénierie Des Systèmes D'information 30 (6), 1483 , 2025
    2025
    Citations: 1
  • Privacy-Preserving IoT Framework with Federated Learning and Lightweight NLP Integration.
    S Dhananjaya, BG Jairam
    Journal Européen des Systèmes Automatisés 58 (5) , 2025
    2025
  • Privacy-Preserving IoT Framework with Federated Learning and Lightweight NLP Integration
    HD Kallinatha, GK Suhas, M Chaithra, S Dhananjaya, KP Suhaas, ...
    Journal Europeen des Systemes Automatises 58 (5), 953 , 2025
    2025
    Citations: 2
  • An advanced AI framework for mental health diagnostics using bidirectional encoder representations from transformers with gated recurrent units and convolutional neural networks
    G Pushpa, M Chaitra, LP Kolur, S Dhananjaya, MN Kavyasri, R Sunitha, ...
    Ingenierie des Systemes d'Information 30 (1), 213 , 2025
    2025
    Citations: 8
  • An Energy-Efficient and Secure WSN Routing Protocol Using Bayesian Networks and Elitist Genetic Algorithms
    AP Kumar, R Sunitha, M Chaithra, S Dhananjaya, MN Kavyasri, ...
    Journal Européen des Systèmes Automatisés 57 (6), 1547 , 2024
    2024
    Citations: 4
  • A Real Time Application for Crime Trends Prediction Using ML Algorithms
    S Chaithra, R Pushpalatha
    International Conference on Technology Advances for Green Solutions and … , 2024
    2024
  • Identification of Counterfeit Products Using Blockchain in E-Commerce
    J Pavithra, H.C., Rajeshwari, J., Sunitha, R., Dhanajaya, S., Kumar, A.P ...
    Innovative Computing and Communications - Springer LNNS 1021, 465–482 , 2024
    2024
    Citations: 2
  • Stable Diffusion Image Processing.
    A Prasad, A CB, S Dhananjaya
    Library of Progress-Library Science, Information Technology & Computer 44 (3) , 2024
    2024
    Citations: 4
  • End to End Model to Reduce the Inference, Jamming, and to Increase the Trust from the Compromised Secondary Nodes in Cognitive Radio Networks
    S Dhananjaya, M Narender, R Sunitha
    2024 International Conference on Intelligent and Innovative Technologies in … , 2024
    2024
  • Increasing the Trust Factor in Cognitive Radio Networks Driven by Software Defined Radio
    YBN Shashank Dhananjaya
    International Journal of Science and Research 11 (6), 672-675 , 2022
    2022
  • Survey of SDN traffic flow classification approaches
    U Deshpande, N Rajesh, S Dhananjaya
    INFOCOMP Journal of Computer Science 20 (1) , 2021
    2021
    Citations: 2
  • A novel method in matched filter spectrum sensing to minimize interference from compromised secondary users of cognitive radio networks
    S Dhananjaya, BN Yuvaraju
    2018 international conference on electrical, electronics, communication … , 2018
    2018
    Citations: 14
  • A Learning Method for Secondary Users to Minimize the Effect of Jamming in Cognitive Radio Wireless Sensor-Networks State of the art in CRWSN Security
    YBN Shashank Dhananjaya
    International Journal for Research in Applied Science & Engineering … , 2018
    2018
  • Source Code Reusability Metric for Enhanced Legacy Software
    S Dhananjaya, T Yogesha, S Misba
    IRNet Transactions on Computer Science and Engineering , 2013
    2013
    Citations: 1

MOST CITED SCHOLAR PUBLICATIONS

  • A novel method in matched filter spectrum sensing to minimize interference from compromised secondary users of cognitive radio networks
    S Dhananjaya, BN Yuvaraju
    2018 international conference on electrical, electronics, communication … , 2018
    2018
    Citations: 14
  • An advanced AI framework for mental health diagnostics using bidirectional encoder representations from transformers with gated recurrent units and convolutional neural networks
    G Pushpa, M Chaitra, LP Kolur, S Dhananjaya, MN Kavyasri, R Sunitha, ...
    Ingenierie des Systemes d'Information 30 (1), 213 , 2025
    2025
    Citations: 8
  • An Energy-Efficient and Secure WSN Routing Protocol Using Bayesian Networks and Elitist Genetic Algorithms
    AP Kumar, R Sunitha, M Chaithra, S Dhananjaya, MN Kavyasri, ...
    Journal Européen des Systèmes Automatisés 57 (6), 1547 , 2024
    2024
    Citations: 4
  • Stable Diffusion Image Processing.
    A Prasad, A CB, S Dhananjaya
    Library of Progress-Library Science, Information Technology & Computer 44 (3) , 2024
    2024
    Citations: 4
  • Privacy-Preserving IoT Framework with Federated Learning and Lightweight NLP Integration
    HD Kallinatha, GK Suhas, M Chaithra, S Dhananjaya, KP Suhaas, ...
    Journal Europeen des Systemes Automatises 58 (5), 953 , 2025
    2025
    Citations: 2
  • Identification of Counterfeit Products Using Blockchain in E-Commerce
    J Pavithra, H.C., Rajeshwari, J., Sunitha, R., Dhanajaya, S., Kumar, A.P ...
    Innovative Computing and Communications - Springer LNNS 1021, 465–482 , 2024
    2024
    Citations: 2
  • Survey of SDN traffic flow classification approaches
    U Deshpande, N Rajesh, S Dhananjaya
    INFOCOMP Journal of Computer Science 20 (1) , 2021
    2021
    Citations: 2
  • A Blockchain-Enabled GNN Framework for Secure Routing in IoT Networks.
    BG Jairam, S Dhananjaya
    International Journal of Safety & Security Engineering 15 (9) , 2025
    2025
    Citations: 1
  • A Framework for the Video Surveillance Suspicious Activity Detection
    K Rohitaksha, AL Pujari, S Dhananjaya, M Narender
    Engineering, Technology & Applied Science Research 15 (4), 25402-25406 , 2025
    2025
    Citations: 1
  • A hybrid CNN-BiLSTM model for minimizing packet loss in IoT-enabled wireless sensor networks
    GN Shwetha, S Dhananjaya, H Jagruthi, KS Rekha, R Pankaja, AP Kumar, ...
    Ingénierie Des Systèmes D'information 30 (6), 1483 , 2025
    2025
    Citations: 1
  • Source Code Reusability Metric for Enhanced Legacy Software
    S Dhananjaya, T Yogesha, S Misba
    IRNet Transactions on Computer Science and Engineering , 2013
    2013
    Citations: 1
  • A Conversational Healthcare Companion in Kannada
    J Raju, K Rohitaksha, KS Rekha, BG Jairam, M Narender, S Dhananjaya, ...
    Engineering, Technology & Applied Science Research 16 (1), 32377-32383 , 2026
    2026
  • Robust Emotion Recognition Multimodal Using an Optimized Cross-Modal Data Fusion Framework.
    S Dhananjaya
    Journal Européen des Systèmes Automatisés 59 (1), 275 , 2026
    2026
  • Deep Reinforcement Learning-Based Energy-Aware Intrusion Prevention in IoT Environment.
    KS Rekha, P Jainapur, K Manjushree, S Dhananjaya, SR Nandini, ...
    International Journal of Safety & Security Engineering 15 (8) , 2025
    2025
  • Synchronized transform-aggregate model for big data analytics towards in distributed cloud ecosystem.
    R Dembala, K Ananthapadmanabha, S Dhananjaya
    International Journal of Electrical & Computer Engineering (2088-8708) 15 (4) , 2025
    2025
  • Privacy-Preserving IoT Framework with Federated Learning and Lightweight NLP Integration.
    S Dhananjaya, BG Jairam
    Journal Européen des Systèmes Automatisés 58 (5) , 2025
    2025
  • A Real Time Application for Crime Trends Prediction Using ML Algorithms
    S Chaithra, R Pushpalatha
    International Conference on Technology Advances for Green Solutions and … , 2024
    2024
  • End to End Model to Reduce the Inference, Jamming, and to Increase the Trust from the Compromised Secondary Nodes in Cognitive Radio Networks
    S Dhananjaya, M Narender, R Sunitha
    2024 International Conference on Intelligent and Innovative Technologies in … , 2024
    2024
  • Increasing the Trust Factor in Cognitive Radio Networks Driven by Software Defined Radio
    YBN Shashank Dhananjaya
    International Journal of Science and Research 11 (6), 672-675 , 2022
    2022
  • A Learning Method for Secondary Users to Minimize the Effect of Jamming in Cognitive Radio Wireless Sensor-Networks State of the art in CRWSN Security
    YBN Shashank Dhananjaya
    International Journal for Research in Applied Science & Engineering … , 2018
    2018