Research

Call for book chapter proposals:

 

My research interests are related to artificial intelligence, trustable uses of AI, and cybersecurity with applications in many domains, including but not limited to

  • Explainable Artificial Intelligence
  • Knowledge Graph
  • Ontology
  • Cybersecurity
  • Semantic Web
  • Scalable Deep Learning

 

Recently, I have been trying to create a human-understandable explanation (XAI) from the excellent but opaque decision achieved by deep learning algorithms. This research needs to combine statistical methods with linear algebra and knowledge graph (ontology). Previously, I have worked to make ontology editing easier, and for that, I have developed two plugins (OWLAx and ROWL) for linked data analysis.

During my summer internships at Intel Corporation, I analyzed the performance bottleneck of the TensorFlow framework to improve the performance of Intel CPU and make the TensorFlow framework scalable.  As a research intern at Accenture Technology Lab for summer-2017, I analyzed various explainable artificial methods to produce a human-understandable explanation from deep learning algorithms.

 

Present and Past Projects:

  1. Knowledge Graph based Data Analysis: Analyze Data by connecting it with the context makes data more interpretable and valuable, rather than analyzing it as a discrete item. We can connect data with the knowledge graph to make more sense of it, and guide the data exploration to identify extra information. I am building methods and tools to make data analysis based on the knowledge graph.

  2. Human Centered Big Data: Deep learning algorithms are performing very well, and sometimes they outperform humans. But still, their decision-making process is opaque. This is important for safety-critical operations like medical diagnostics, emergency response etc. We are trying to explain the decision of the algorithm. Our results are being published at the AAAI conference, NeSy, and NIPS workshops.

  3. Ontology Axiomatization:

    • OWLAx: OWL Axiomatizer. Ontology Design Pattern Plugin for Desktop Protégé. Nominated as 1 of the 7 demos for the best Demo award at ISWC 2016.

    • ROWL: Rule to OWL Axiom Converter. Rule to OWL Axiom Conversion Plugin for Protégé.

  4. Deep Learning Performance Optimization for Intel Architecture: This work has been done during my internship at Intel from January 2019 to August 2019. Analyzed and optimized the scalability of key deep learning (DL) algorithms implemented using TensorFlow on Intel Xeon CPU. Created containerized solution for intel optimized TensorFlow using Docker and Singularity.

  5. Health Insurance Cost Prediction: Insurance companies, especially health insurance companies need to calculate the cost of a new customer. Currently, they take user information and calculate the cost manually. We tried to automate this process using deep learning algorithms.

  6. Samsung Android: Worked as part of the Android Connectivity team. Solved more than 100 issues related to Wi-Fi connectivity of 30+ Samsung Android Devices. Developed music listener and sync with Android devices for Samsung Gear. Developed a decryption method for I-Cloud contact being used in Smart Switch Migration. All code was reviewed, perfected, and pushed to production.