Python, C++, C, Java, MySQL, Julia, HTML, CSS, JavaScript
GNU Radio, Scilab, MATLAB, Keil µVision, Quartus, Proteus, Postman, ns-3, Wireshark, Burpsuite, EAGLE, SDR console, Unity, Saturn PCB toolkit, Solidworks
Node.js, Tensorflow
In the commercial aviation domain, there are a large number of documents, like accident reports of NTSB and ASRS, and regulatory directives ADs. There is a need for a system to efficiently access these diverse repositories to serve the demands of the aviation industry, such as maintenance, compliance, and safety. In this paper, we propose a Knowledge Graph (KG) guided Deep Learning (DL) based Question Answering (QA) system to cater to these requirements. We construct a KG from aircraft accident reports and contribute this resource to the community of researchers. The efficacy of this resource is tested and proved by the proposed QA system. Questions in Natural Language are converted into SPARQL (the interface language of the RDF graph database) queries and are answered from the KG. On the DL side, we examine two different QA models, BERT-QA and GPT3-QA, covering the two paradigms of answer formulation in QA. We evaluate our system on a set of handcrafted queries curated from the accident reports. Our hybrid KG + DL QA system, KGQA + BERT-QA, achieves 7% and 40.3% increase in accuracy over KGQA and BERT-QA systems respectively. Similarly, the other combined system, KGQA + GPT3-QA, achieves 29.3% and 9.3% increase in accuracy over KGQA and GPT3-QA systems respectively. Thus, we infer that the combination of KG and DL is better than either KG or DL individually for QA, at least in our chosen domain.
In this paper, prospects of the utilization of the 4th stage of ISRO’s PSLV, after the completion of the launch mission, as an orbital platform, to host scientific payloads have been discussed. Payloads from 4 domains-Technological Demonstration, Earth Observation, Microgravity, Biology Experiments and the associated mission concepts have been surveyed, and comments have been made on their suitability to be launched onboard the orbital platform. Technological challenges in achieving these have been highlighted. Based on this analysis, two technology demonstration missions have been proposed by the team.
An Antenna Deployment System has become an essential component of any pico-or nano-satellite design due to space constraints during launch. The Sanket mission is a technology demonstration designed to be flown on the Indian Space Research Organization's PSLV Stage-4 Orbital Platform (PS4-OP). It aims to qualify the team's Antenna Deployment System (ADS) in Ultra High Frequency (UHF) band to a Technology Readiness Level (TRL)-7 in Low Earth Orbit (LEO). Sanket comprises of an ADS and an Auxiliary system. The purpose of the auxiliary system is to test the ADS on PS4-OP simulating a 1U CubeSat mission life cycle and conditions. Sanket will be mounted on PS4-OP which remains in LEO for around six months. Our Antenna Deployment System is developed as an independent module that is compatible with standard CubeSat sizes 1U, 2U, and 3U.
Rank 164 out of 6061 teams in Intelligent Picking
See the submission here
"I mentored Shreya for an Internship Project. She was very quick to ramp up with Tech Stack and was productive in a week. The dedication and ownership shown was amazing. She came up with production quality code in a short span of time and when above and beyond to make the project successful. I highly recommend Shreya and would love to work with her again. I wish her all the best in her career."
[ZLevelApps]
"Shreya is a meticulous student and a lovely person. She worked as a Research Intern at Praxis Business School in the summer of 2020 under my guidance. She worked on a project in the areas of NLP and Machine Learning. The problem focussed on mining the opinions of different customers on different product features of a product. She is a quick learner. Although she had no prior knowledge of NLP, she took almost no time to learn what was needed and jumped right into the problem. She is also very open to suggestions and new ideas. During the project, she came up with some noteworthy thoughts based on the outcomes of her experiments. I enjoyed working with her. We did several experimental studies to figure out various advantages and the limitations of the algorithm we were using. I am sure Shreya will do very well wherever she goes."
[Praxis Business School]
