Manoj T

Dr. Manoj T


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 December 2022 in Computers and Electronics in Agriculture
Verified
Journal Article
Closed access
MTManoj T
Manoj T
KMKrishnamoorthi Makkithaya
Krishnamoorthi Makkithaya
NGNarendra V G
Narendra V G

24 February 2025 in SN Computer Science
Verified
Journal Article
Open access
PDF file
MTManoj T
Manoj T
KMKrishnamoorthi Makkithaya
Krishnamoorthi Makkithaya
NGNarendra V G
Narendra V G
Smart agriculture promises to alleviate the burden of climate risks on crop production by leveraging machine learning tasks. These tasks act as a decision support instrument for making well-informed choices by stakeholders in the agricultural value chain. Currently, predictive models in smart agriculture demand a centralized collection of diverse data, fragmented across multiple information systems leading to a single point of failure. The application of the Federated Learning (FL) technique restricts the movement of raw data and trains the model at the data source. However, the FL approach does not ensure trust factors like privacy, authentication, data provenance, transparency and traceability. To address this, a decentralized federated learning framework built on blockchain can be a potential solution. In this study, we introduce a blockchain-based framework called AgriFLChain for trusted federated learning in the context of smart agriculture. We focus on crop yield prediction as an illustrative use case, initially discussing centralized deep learning models (ResNet-16, ResNet-28, CNN-DNN, and CNN-LSTM). We then detail the authentication and data provenance mechanisms for federated learning participants, utilizing blockchain-based Decentralized Identifiers (DIDs) and Verifiable Credentials (VCs). We implement these models using vanilla federated learning and Differential Privacy (DP) federated learning approaches, achieving transparency and traceability through smart contracts by recording metadata of model updates into the blockchain. Finally, detailed evaluation demonstrates that AgriFLChain achieves comparable efficiency to centralized models while maintaining scalability in blockchain transactions for higher data volumes.

8 March 2022 in Cogent Engineering
Verified
Journal Article
Open access
MTManoj T
Manoj T
KMKrishnamoorthi Makkithaya
Krishnamoorthi Makkithaya
NGNarendra V G
Narendra V G
Over the past two decades, the fast pace of digitization in the healthcare ecosystem led to a phenomenal rise in the creation, storage and sharing of Electronic Health Records (EHRs) across the globe. However, the mechanism of authentication used for proving the identity of entities in EHRs is based on the identifiers issued by centralized identity providers (IDPs). It may lead to a single point of failure, loss of privacy and lack of interoperability. A new wave of decentralized identifiers (DIDs) and verifiable credentials(VCs) data modelled by blockchain has made it possible to achieve entity authentication in a decentralized manner. In this study, a blockchain-based framework with decentralized identifiers for patient authentication and consent management for EHR access using verifiable credentials is proposed. It describes the process of DID generation and authentication credential setup along with workflows for issuing and verifying credentials in the EHR ecosystem. The framework is implemented using Hyperledger Indy blockchain and Aries library. The study evaluates the performance of proposed workflows in terms of scalability, efficiency, resource utilization and conducts security analysis. Specifically, the outcome of this study can be used to realize the decentralized identity management and authentication in EHR systems.

1 September 2025 in Smart Agricultural Technology
Verified
Journal Article
Open access
OPOmkar Prabhu
Omkar Prabhu
MTManoj T
Manoj T
SSSUCHARITHA SHETTY
SUCHARITHA SHETTY

7 October 2025 in ACM Computing Surveys
Verified
Journal Article
Open access
NCNamrata Marium Chacko
Namrata Marium Chacko
NGNarendra V G
Narendra V G
MAMATHA BALACHANDRAMAMATHA BALACHANDRA
MAMATHA BALACHANDRA
MTManoj T
Manoj T
Blockchain technology has seen a rapid pace of development and expanded application domains swiftly due to the rising demand for decentralized trust, transparency, and integrity. The consensus algorithm plays a critical role in ensuring trust, immutability and governance of the decentralized network. However, traditional consensus face challenges such as high energy consumption, low scalability, security, and fault tolerance. Researchers have been investigating Lightweight Consensus to overcome these challenges. Lightweight Consensus is a mechanism that enables a more efficient and scalable blockchain system while ensuring security and immutability. This work uses the Systematic Literature Review method to comprehend Lightweight Consensus. 127 studies were grouped based on application specific network, and an in-depth analysis was done on the characteristics of the consensus. A novel taxonomy of Lightweight Consensus based on the agreement method and round propagation is proposed. Various parameters that needed consideration for a Lightweight Consensus are also analyzed. Finally, the study makes recommendations for future research on Lightweight Consensus in blockchain, emphasizing the importance of more empirical investigations and real-world implementations. This study offers a comprehensive overview of the current research landscape on lightweight consensus in blockchain, shedding light on its potential impact on the evolution of blockchain technology. It also serves as a valuable guide for researchers, helping them identify the most suitable consensus features for specific application domains with unique requirements.

9 December 2025 in Soft Computing
Verified
Journal Article
Open access
PDF file
VDViraj C. Desai
Viraj C. Desai
SSSUCHARITHA SHETTY
SUCHARITHA SHETTY
STSujithra Thandapani
Sujithra Thandapani
MTManoj T
Manoj T
Alzheimer’s disease (AD), a leading cause of dementia, presents persistent challenges in accurate staging and diagnosis from neuroimaging data. This study investigates advanced deep learning approaches for classifying AD from brain MRI, focusing on both predictive performance and resource efficiency. We evaluate a suite of convolutional neural network (CNN) architectures—including VGG16, ResNet50V2, MobileNetV2, EfficientNetB0, a custom lightweight CNN — under diverse configurations of activation functions (Mish, GELU, Swish, PReLU) and optimizers (AdamW, AdaBelief, NovoGrad, Lion, and SGD with cosine decay). Lightweight Vision Transformers (ViTs), such as MobileViT, are also benchmarked for comparison. Ensemble strategies are explored through both soft-voting and trainable attention mechanisms. The attention-based ensemble achieved the highest classification performance with an F1-score of 0.9492, while an efficient CNN-VGG ensemble reduced model size and memory usage by over threefold with only a minor performance trade-off. The best lightweight transformer model, MobileViT-Small, achieved an F1-score of 0.927 with exceptionally low inference latency, making it suitable for edge deployment. These findings highlight the effectiveness of combining model optimization with ensembling to produce accurate, interpretable, and resource-conscious models for Alzheimer’s diagnosis from MRI, advancing the state of neuroimaging-based decision support systems.