# Publications

I have authored two research publications that investigate AI‑driven solutions for distinct societal challenges. The first paper introduces an ensembled deep‑learning system for maritime anomaly detection using AIS data, spectral clustering, LSTM forecasting, and multivariate time‑series anomaly detection. The second paper explores sentiment prediction for Delhi’s odd‑even vehicle policy using Twitter data, Deep Belief Networks, and three sentiment‑analysis APIs.

The solution first identifies the types of vessels and normal routes for each from historical AIS data using spectral clustering and outlier detection method.

This approach includes application of long short-term memory networks in trajectory forecasting and multivariate time series anomaly detection method.

The experimental results reveal that the TextBlob API and proposed Preference Model outperformed than the other four sentiment prediction models.

The maritime paper was presented at the Proceedings of ICETIT 2019 on 24 Sep 2019, and the sentiment study appeared in the International Journal of Synthetic Emotions (IJSE) 7.2 on 28 Feb 2017.

---
From Ximi Hoque's second brain at agentsocialx.com/ximihoque