8 peer-reviewed papers and 1 preprint on deep learning, forecasting, control and AI retrieval. Each has its own page with the abstract and a link to the paper. Also on Google Scholar and ORCID.
A new way to index documents for AI retrieval, in which each level of a hierarchy stores only what it adds to the level above. It matches standard retrieval quality with 30% fewer context tokens and scales far better with collection size; the paper also reports plainly that its top-down search step does not help.
arXiv, 2026
Forecasts that step forward one small interval at a time build up error over long horizons. RefreshNet stacks models that work at different time scales and lets the slower ones periodically correct the faster ones.
Nonlinear Dynamics, 2024
Using deep learning to tune a control system's settings automatically instead of by hand.
ICETCI 2021, IEEE, 2021 · Best Paper Award
Semantic Compression Trees: Multi-resolution knowledge retrieval via hierarchical semantic residuals
Junaid Farooq
arXiv Preprint
RefreshNet: Learning multiscale dynamics through hierarchical refreshing
Junaid Farooq, Danish Rafiq, Pantelis R. Vlachas, Mohammad Abid Bazaz
Nonlinear Dynamics, 112(16), 14479–14496 Peer-reviewed
Hybrid deep neural network for data-driven missile guidance with maneuvering target
Junaid Farooq, Mohammad Abid Bazaz
Defence Science Journal, 73(5), 602–611 Peer-reviewed
Multiscale autoencoder-RNN architecture for mitigating error accumulation in long-term forecasting
Junaid Farooq, Mohammad Abid Bazaz, Danish Rafiq
ICETCI 2023, IEEE Peer-reviewed · Best Presentation Award
Manzoor A. Wani, Junaid Farooq, Danish Mushtaq Wani
Environmental Science and Pollution Research, 29(12), 18271–18281 Peer-reviewed
Danish Rafiq, Junaid Farooq, Mohammad Abid Bazaz
International Journal of Electrical Power & Energy Systems, 138, 107908 Peer-reviewed
Junaid Farooq, Mohammad Abid Bazaz
Alexandria Engineering Journal, 60(1), 587–596 Peer-reviewed
Deep learning for self-tuning of control systems
Junaid Farooq, Mohammad Abid Bazaz
ICETCI 2021, IEEE, 6–11 Peer-reviewed · Best Paper Award
A novel adaptive deep learning model of COVID-19 with focus on mortality reduction strategies
Junaid Farooq, Mohammad Abid Bazaz
Chaos, Solitons & Fractals, 138, 110148 Peer-reviewed
