Anjana Tiha

Volunteer Researcher

United Nations Volunteers•  July 2020 - September 2020

Economic Model Development for Covid-19 Pandemic with Machine Learning [Jul - Sep 2020] - Conducted analysis for detecting relationships among 24 economic features to develop map for economic crisis in COVID-19 and probable solution adopted by government. - Dataset consisted of 20 years of country-level economic data with 24 features. - Applied machine learning for deriving relationships among the features and developed visualization.

Graduate Research Assistant

University of Memphis•  September 2016 - December 2017

Distributed Machine Learning for Biomarkers Detection from Wearable Sensor Big Data[Python] [January 2017 - April 2017] - Developed Distributed Machine Learning (ML) module for training ML models on multiple clusters with Apache Spark for detecting bio-markers from multimodal wearable sensor data. - Developed Grid & Random Grid Search CV module for training time and parameter search optimization. - Detected bio-markers (psychological stress) from big stream data (accelerometer, ECG, respiration rate) from multi-modal wearable sensors with prediction accuracy (F-1 Score) of 87% with SVM radial kernel. Survey on Machine Learning based Physical Activity Recognition Methods from Sensor Data [December 2016 – February 2017] - Conducted research on machine learning based algorithms for physical activity recognition (e.g. walking, running, eating, and drinking) from multimodal wearable sensor data. Big Data Application for Large Scale US Stock Market Data Analysis [Java, Apache Spark] [May 2017 - July 2017] - Developed Big Data framework for processing and analysis of 7 years of historical US stock market data (50 TB) with nanosecond granularity from 13 US exchanges on multiple clusters with Apache Spark. - Added support for information extraction from binary files based on field spec for multiple years, file formats. - Conducted multi-market analysis (for market dominance detection), anomaly detection (for Flash crash day). Analysis of Pediatric Asthma Data in City of Memphis [Excel, Python] [September 2017 - December 2017] - Surveyed multiple pediatric asthma risk factors including environmental factors (air quality) & living conditions. - Conducted data analysis on survey data collected from parents in multiple schools in Shelby county, Memphis, Tennessee, USA over few months on around 23 factors.

University of Memphis

Computer Science, MS•  August 2016 - May 2018

Specialized in Machine Learning, Natural Language Processing, Computer Vision, Big Data Analytics, Distributed Computing, Artificial Intelligence. Masters Project Title: "Intelligent Chatbot Using Deep Neural Network" - A Generative Open Domain Chatbot Application with Deep Learning - Developed intelligent open domain conversational agent (Human vs AI) using Sequence-to-Sequence (Seq2Seq) architecture and attained validation perplexity 46.82 and Bleu 10.6. - Trained encoder-decoder based Seq2Seq model fully from scratch and further optimized the Recurrent Neural Network based model with Bidirectional LSTM cells, Neural Attention Mechanism and Beam Search. - Used Cornell Movie Subtitle Corpus following data preprocessing as data, PyQT for chat interface (GUI) development and untrained Google’s Neural Machine Translation (NMT) model for Seq2Seq module.

Bangladesh University of Engineering and Technology (BUET)

Computer Science & Engineering, BS•  February 2006 - July 2014

Undergraduate Thesis Title: "A Survey on Application of Cloud Computing for Sensor Network"