Completed

In recent years, unmanned aerial vehicles(UAVs) have been used for numerous applications such as defence industry, urban planning, agriculture, emergency response and disaster management. Like most of the other widely used machines, increasing UAVs autonomy and independent decision making is literally a must in order to improve eciency, safety and accuracy of the devices. A UAVs autonomy directly a ected by its ability to model the outer world which is now more successful with the improvements of the computer vision.

Most NER datasets do not contain many lexically ambiguous words, as a result it becomes hard for a NER model trained with such a dataset to distinguish between different meanings of a lexically ambiguous word. For example, in the sentence "Paris Hilton owns a Hilton Hotel in Paris.", Both Paris and Hilton are used with two different meanings and their entity types are different too.

This project aims to prevent burglaries by imitating the household activities when nobody is home. We realize that any such device cannot deter burglars completely, but our goal is to provide a cheap and user friendly option, which can work well in the general case.

After design of Ethereum blockchain completed, smart contracts, which are execution of programs on EVM, has risen up. Smart contracts have shown to be applicable in many domains including financial industry, public sector and cross-industry. Smart contracts can handle large numbers of virtual coins, in our case called Ethereum(ETH), worth of thousand of dollars. This huge money network easily making financial incentives high enough to attract adversaries.

My mobile test automation web framework project is a web application where mobile developers can test their mobile applications and detect crashes. They can get detailed reports about those crashes, run generated and custom tests and interact with the device their application is being tested on in real time. I am using technologies like React, NodeJS MongoDB and Heroku to create this project.