Gaurav Vishnu Londhe

Dr. Gaurav Vishnu Londhe

Jain University, Bengaluru, India
orcid
Associated with Symbiosis International (Deemed) University ...

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
1 January 2021
Verified
Book Chapter
Closed access
SBSatish Rupraoji Billewar
Satish Rupraoji Billewar
GLGaurav Vishnu Londhe
Gaurav Vishnu Londhe
SGSunil Bahiru Ghane
Sunil Bahiru Ghane
History repeats itself. Quantum cryptography has started a revolution of quantum computing and has repeated the days of Einstein's research paper on “Theory of Relativity,” which changed the world's perceptions of physics completely written based on Newton's laws. Quantum cryptography is going to change the definition of computers right from scratch. The last century was witness of a space race between US and USSR. This century would be witness of quantum computing race between US and China. It has changed the dimensions of operating systems, software, hardware, databases, and applications. Quantum computers are in a phase to replace the conventional computers and they are reaching to the level called quantum supremacy. The chapter covers the details of the basic principles and work methodology of quantum cryptography, the contribution of various pioneers, advantages over classical cryptography, its applications, future scope, and limitations simultaneously. The chapter covers the contribution of leading countries and organizations in quantum revolution.

20 March 2026 in Discover Applied Sciences
Verified
Journal Article
Open access
PDF file
AJAditi Jha
Aditi Jha
RPRavi Shankar Pandey
Ravi Shankar Pandey
GTGyanendra Tiwary
Gyanendra Tiwary
GLGaurav Vishnu Londhe
Gaurav Vishnu Londhe
The increase in vehicle ownership and urban population puts a strain on roads and increases traffic congestion within developed and developing nations. Congestion affects an individual’s time and increases an individual’s fuel consumption and pollution output, undercutting efforts towards smart/ sustainable cities. Outdated statistical congestion predicting methods do not account for the non-linear, dynamic nature of congestion with regards to external factors such as, weather, road incidents, and infrastructure. The adoption of machine and deep learning develops the framework towards adaptable and data-driven congestion predicting methods. This study develops a framework that combines the fundamentals of machine learning algorithms, Queuing Theory, Decision Trees, Random Forests, and Deep Belief Networks (DBN) for robust and interprefig traffic congestion forecasting. The traffic flow micro-dynamics integration with Queuing Theory and the use of historical/ real-time multimodal data such as sensor feeds, GPS trajectories, and incident reports as a basis for forecasting helps in robust congestion prediction. Polynomials of moving and rest queues with defined traffic characteristics fuel flow mechanisms. The designed framework uses the DBN and Queuing Theory for robust traffic forecasting.

31 October 2025 in Research Square
Verified
Preprint
Open access
PDF file
AJAditi Jha
Aditi Jha
RPR. S. Pandey
R. S. Pandey
GTGyannedra Tiwary
Gyannedra Tiwary
GLGaurav Vishnu Londhe
Gaurav Vishnu Londhe
The exponential growth of urban populations and vehicular owner- ship has escalated the challenge of road traffic congestion in both developed and developing countries. Congestion not only increases travel delays but also aggravates fuel consumption and environmental pollution, impeding the vision of smart, sustainable cities. Traditional statistical and rule-based traffic predic- tion models often fail to capture the dynamic and nonlinear evolution of con- gestion, especially under the influence of exogenous factors such as weather, road incidents, and infrastructural changes. Recent advancements in machine learning and deep learning have offered new paradigms for data-driven, adap- tive traffic prediction. In this research, we propose a comprehensive framework that synergistically combines queuing theory with machine learning algo- rithms—specifically Decision Tree, Random Forest, and Deep Belief Network (DBN)—to provide both interpretable and robust predictions of traffic conges- tion. The model integrates historical and real-time multimodal data, including GPS trajectories, sensor feeds, and incident reports, while leveraging queuing theory to model the fundamental dynamics of vehicular flow at the micro-level. Decision Trees facilitate rule-based feature dominance and initial classification, Random Forests enhance robustness and feature selection, and DBNs perform deep spatiotemporal feature learning. Experimental validation on real-world datasets demonstrates that the proposed hybrid model outperforms conven- tional approaches on key accuracy metrics such as precision and recall. This research contributes a scalable and generalizable traffic congestion prediction solution aligned with the evolving needs of intelligent transportation systems and urban mobility management.

4 November 2026 in Scientific Reports
Verified
Journal Article
Open access
PDF file
TLT. Thomas Leonid
T. Thomas Leonid
GLGaurav Vishnu Londhe
Gaurav Vishnu Londhe
JTJ. Robert Theivadas
J. Robert Theivadas
SPSuresh Ponnan
Suresh Ponnan
Driver drowsiness detectors must be judged on minority-class sensitivity, calibration and alarm behaviour, not accuracy alone. DrowsyFormer-Gen combines physiological, vehicle and behavioural transformer streams with cross-modal fusion, an adaptive classification head and class-conditional diffusion augmentation. We re-implemented and evaluated it on shared causal windows and subject-disjoint folds against five classical baselines, using DMPS (225,000 samples; 15 drivers) and SC-DD (87,430 segments; 20 participants); DMPS drivers are a subset of SC-DD participants. Baselines received nested hyperparameter optimisation; thresholds were fixed on training data. Tuned logistic regression reached 99.747 ± 0.031% accuracy, 0.953 drowsy-class recall and expected calibration error 0.0008, ahead of every neural configuration. Each proposed component failed a controlled test: removing diffusion augmentation improved every metric, and class weighting alone reached 0.989 recall; zeroing the adaptive head’s reference halved calibration error while its refresh interval was inert; and the fusion ablation, over 25 runs, ranged from 0.000 to 1.000 recall at a fixed threshold despite stable ranking. A single sample reached 0.915 recall against 0.956 for the 32-sample window. We report a negative result, conditional on the supplied records being what the source publications describe.

1 February 2026 in Bulletin of Electrical Engineering and Informatics
Verified
Journal Article
Open access
PDParul Dubey
Parul Dubey
GLGaurav Vishnu Londhe
Gaurav Vishnu Londhe
VKVinay Keswani
Vinay Keswani
ACAkshita Chanchlani
Akshita Chanchlani
MMMurtuza Murtuza
Murtuza Murtuza
PDPushkar Dubey
Pushkar Dubey
Wildfire forecasting is a critical challenge in environmental signal processing and disaster response planning. The ability to interpret multimodal spatiotemporal signals is essential for early warning systems and resource deployment. This study addresses these limitations by proposing a unified prediction-to-action framework. We utilized four open-access datasets—wildland fire emissions database (WFED), fire information for resource management system (FIRMS), Sentinel Hub, and a custom moderate resolution imaging spectroradiometer+shuttle radar topography mission (ERA5+MODIS+SRTM) fusion—covering fire occurrences, vegetation indices, meteorological parameters, and topographic features. These heterogeneous signals were preprocessed, aligned, and transformed into structured tensors for model training and evaluation. We use a transformer-based system to understand long-term patterns in space and time, enhanced by a belief–desire–intention (BDI) reasoning module that connects our predictions to flexible wildfire response plans. The novelty lies in the integration of signal-aware attention mechanisms with symbolic decision modeling. Model performance was evaluated using F1-score, intersection over union (IoU), mean absolute error (MAE), and directional accuracy. The suggested framework did better than the basic convolutional neural network (CNN) models, reaching an F1-score of 0.74, a directional accuracy of 84.3%, and lowering the MAE to 7.6 km², while also providing clear and relevant action suggestions.