Darshan Joshi — Research Publications

Research & Publications
R —

Publications

Peer-reviewed research spanning enterprise cybersecurity, computer vision AI, seismic deep learning, and NLP-driven document intelligence.

3
Total Publications
2
Published
1
In Pipeline
4
Domains
Google Scholar Profile
View all citations and publications

Abstract

A comprehensive study on enterprise cybersecurity architectures covering risk mitigation, layered defense strategies, and scalable infrastructure design. The paper synthesizes best practices across firewalls, IDS/IPS, SIEM systems, and endpoint protection frameworks.

Key Contributions

  • ›Authored a comprehensive research study on enterprise cybersecurity architectures, focusing on risk mitigation, layered defense strategies, and scalable infrastructure design.
  • ›Conducted systematic literature review of security framework components (firewalls, IDS/IPS, SIEM, endpoint protection) to derive actionable recommendations.
  • ›Synthesized complex technical findings into a formal research manuscript, demonstrating disciplined documentation and analytical reasoning.
  • ›Managed end-to-end research workflow including conceptualization, data collection, critical evaluation, and formal publication.
  • ›Analyzed real-world enterprise network topologies and proposed a layered defense-in-depth model for large organizations.

Keywords

CybersecurityEnterprise ArchitectureIDS/IPSSIEMFirewallRisk MitigationEndpoint Protection
View PaperGoogle Scholar
Journal / Venue
IJARESM
International Journal of Advanced Research in Engineering, Science and Management
Focus Area
Enterprise Cybersecurity
Framework
Defense-in-Depth
Key Topic
IDS/IPS · SIEM · Firewall
Status
Published
APA Citation

Joshi, D. (2023). Design and Analysis of Cyber Security Infrastructure in Large Enterprises and Organisations. International Journal of Advanced Research in Engineering, Science and Management.

Abstract

This paper presents a production-grade classroom behavior detection framework trained on the SCB-05 dataset using YOLOv8x on Google Colab Pro (A100 GPU). The system achieves 74.85% mAP@0.5 overall across 11+ behavioral classes, with a standout 93.5% detection accuracy on sleeping behavior. A tiled inference pipeline enables real-time deployment on CCTV/RTSP feeds. Grad-CAM explainability layers validate that the model attends to posture and body position rather than facial features, supporting responsible AI deployment in educational settings.

Key Contributions

  • ›Trained YOLOv8x on the SCB-05 dataset using Google Colab Pro (A100 GPU), achieving 74.85% mAP@0.5 across 11+ behavioral classes.
  • ›Achieved 93.5% detection accuracy on sleeping behavior — the highest per-class precision in the model.
  • ›Built tiled inference pipeline for real-time CCTV/RTSP feed processing for live classroom monitoring.
  • ›Curated and annotated the SCB-05 multi-class dataset via Roboflow with rigorous quality control.
  • ›Integrated Grad-CAM heatmap visualization confirming model attends to posture over facial features.
  • ›Proposed RTSP-based deployment architecture for resource-constrained campus hardware.

Keywords

YOLOv8Computer VisionBehavior DetectionGrad-CAMExplainable AIPyTorchObject DetectionEducation AI
In PreparationGoogle Scholar
Journal / Venue
IJSRST
International Journal of Scientific Research in Science and Technology
Model
YOLOv8x · A100 GPU
mAP@0.5
74.85% Overall
Top Class
93.5% Sleeping AP
Status
Under Review
APA Citation

Joshi, D. (2025). Classroom Behavior Detection Using YOLOv8 and Explainable AI. International Journal of Scientific Research in Science and Technology.

Abstract

This paper presents a hybrid CNN-LSTM deep learning architecture for earthquake prediction and the generation of synthetic seismograms. The model leverages convolutional layers for spatial feature extraction from seismic waveform data and LSTM layers for temporal sequence modeling, enabling accurate magnitude prediction and realistic synthetic seismogram synthesis for data augmentation and simulation purposes.

Key Contributions

  • ›Designed a hybrid CNN-LSTM architecture that combines convolutional spatial features with LSTM temporal sequence modeling for seismic data analysis.
  • ›Developed a pipeline for processing real seismic waveform datasets and training multi-target prediction models for magnitude and location estimation.
  • ›Implemented synthetic seismogram generation capabilities to augment training datasets for improved model generalization.
  • ›Evaluated model performance against baseline deep learning models on established seismic datasets.
  • ›Demonstrated that CNN-LSTM hybrid models outperform standalone CNN or LSTM architectures on temporal seismic prediction tasks.
  • ›Published findings in the American Journal of Civil Engineering, October 30, 2025.

Keywords

CNNLSTMEarthquake PredictionSeismogramDeep LearningHybrid ModelSeismologyTime Series
View PaperDOIGoogle Scholar
Journal / Venue
American Journal of Civil Engineering
American Journal of Civil Engineering
Architecture
CNN + LSTM Hybrid
Application
Seismic Prediction
Published
Oct 30, 2025
Status
Published
APA Citation

Joshi, D. (2025). Earthquake Prediction and Synthetic Seismogram Generation Using Hybrid CNN-LSTM Model. American Journal of Civil Engineering. https://doi.org/10.11648/j.ajce.20251305.14

Research Interests

◈
Computer Vision
Real-time object detection, behavior recognition, and Grad-CAM explainability.
◉
NLP & Document AI
Job description parsing, skills extraction, automated career document generation.
◎
Seismic AI
CNN-LSTM hybrid models for earthquake prediction and synthetic seismogram generation.
◆
Cybersecurity
Enterprise infrastructure design, buffer overflow analysis, responsible disclosure.
⬡
MLOps & Pipelines
Reproducible YAML training workflows, hyperparameter tuning, deployment strategies.
◐
Explainable AI
Grad-CAM visualization, model interpretability, responsible AI practices.