TERRA-CD: A Benchmark Dataset for Semantic Change Detection
Published:
Created a benchmark dataset of 5,221 paired Sentinel-2 images and trained Siamese networks for change detection.
Posts by Collection
portfolio
Mini-AutoDiff: Reverse-Mode Automatic Differentiation
Published:
Built a lightweight Deep Learning framework from scratch using NumPy, featuring a dynamic computational graph engine and reverse-mode differentiation.
Narrative Sense Disambiguation with LLMs
Published:
Engineered a graded word-sense plausibility pipeline using DeBERTa, RoBERTa, and GPT-4 to quantify semantic ambiguity.
Scalable Sequence Modeling: Mamba vs. Transformers
Published:
Benchmarked Mamba (Selective SSM) and Transformer architectures to investigate trade-offs in computational complexity and memory scaling.
AI Interview Companion (Second Brain)
Published:
Engineered a full-stack RAG agent on Cloudflare Workers that acts as a personalized mock interviewer. Features an automated Python evaluation pipeline achieving 90% retrieval accuracy.
InsightFlow: Serverless AI Analytics Agent
Published:
Engineered a serverless AI agent on Cloudflare Workers that converts natural language to SQL and performs real-time sales forecasting.
DreamShaper Interactive Workbench
Published:
Developed a real-time generative prototyping tool mirroring Adobe Firefly, optimizing Stable Diffusion to <1.2s latency using Latent Consistency Models.
publications
A Novel Transfer Learning based CNN Model for Wildfire Susceptibility Prediction
Published in 2024 5th IEEE International Conference for Emerging Technology (INCET), 2024
A transfer learning approach using a three-layered pyramid structure on satellite imagery, achieving 96.5% accuracy in wildfire risk assessment.
Recommended citation: O. Oak, R. Nazre, S. Naigaonkar, S. Sawant, A. Joshi. (2024). "A Novel Transfer Learning based CNN Model for Wildfire Susceptibility Prediction." IEEE INCET 2024.
Download Paper
A Comparative Analysis of CNN-based Deep Learning Models for Landslide Detection
Published in 2024 Asian Conference on Intelligent Technologies (ACOIT), 2024
Benchmarking four semantic segmentation models (U-Net, LinkNet, PSPNet, FPN) for landslide detection; LinkNet achieved the best performance with 97.49% accuracy.
Recommended citation: O. Oak, R. Nazre, S. Naigaonkar, S. Sawant, H. Vaidya. (2024). "A Comparative Analysis of CNN-based Deep Learning Models for Landslide Detection." IEEE ACOIT 2024.
Download Paper
A Novel Multivariate Bi-LSTM Model for Short-Term Equity Price Forecasting
Published in 2024 5th IEEE Global Conference for Advancement in Technology (GCAT), 2024
A Bidirectional Multivariate LSTM model for short-term stock prediction, achieving an R2 score of 99.47% by integrating technical indicators like Bollinger Bands and EMA.
Recommended citation: O. Oak, R. Nazre, R. Budke, Y. Mahatekar. (2024). "A Novel Multivariate Bi-LSTM Model for Short-Term Equity Price Forecasting." IEEE GCAT 2024.
Download Paper
A Temporal Convolutional Network-based Approach for Network Intrusion Detection
Published in 2024 International Conference on Integrated Intelligence and Communication Systems (ICIICS), 2024
A TCN model with residual blocks and dilated convolutions for network traffic analysis, achieving 96.72% accuracy on the Edge-IIoTset dataset.
Recommended citation: R. Nazre, R. Budke, O. Oak, S. Sawant, A. Joshi. (2024). "A Temporal Convolutional Network-based Approach for Network Intrusion Detection." IEEE ICIICS 2024.
Download Paper
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown file that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
Teaching experience 1
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.