Projects:

BAM
Lifetime prognosis using time series. We designed and implemented a Long Short-Term Memory(LSTM) model to analyze time series data. We used Python, scikit-learn, TensorFlow, and Keras in this project.
This project was in collaboration with NEC Labs. 
ADE - Adverse Drug Events discovery
The aim of this study is to develop a big data analytics strategy which mines the content of scientific articles and health-related Web-based social media to detect and identify ADEs. We analyze two data sources: Biomedical articles and Health-related social media blog posts. We develop an intelligent and scalable text mining solution on big data infrastructures, composed of Apache Spark, natural language processing(NLP), and Deep Learning.
This is combined with an Elasticsearch No-SQL distributed database to explore and visualize ADEs. The accuracy, precision, recall and area under ROC(receiver operating characteristic) of the system will be calculated and compared with traditional approaches in the literature.
AIUM - Artificial Intelligence Usability Measurement
We designed and implemented experimental test-beds to study on impact of network conditions on performance of AI. This project supported by Networks Lab,
Department of Computer Science, Montana State University. This project was in collaboration with Citrix Systems Inc. We used C++, C#, and Python to develop this project.
Results of the project published in couple of journal and conference papers.
This work has been supported through grant NSF CSR-1527097.
CODEC - Network Coding TestBed
Applying Random Linear Network Coding in designing and implementing a real-time streaming system which remains accurate under difficult network traffic conditions.
We designed and implemented a real-time streaming application using network coding over UDP and compared the performance of this system with two popular streaming applications -
Apple Siri, and Google Speech Recognition - under difficult network conditions. We used Python, C#, and C++ in this project.
This work has been supported through grant NSF CSR-1527097.
ALICE - Adaptive Learning for Interdisciplinary Collaborative Environments
ALICE generates individualized development plans, according to previous experiences and current challenges. Instruction is delivered through an information system powered by the
Literatronica artificial intelligence engine. We use Visual Studio .NET, MATLAB, SQL, and JavaScript in this project.
ALICE is supported through NSF award 1649226, 2016-2018