Tushar Shrivastav
I'm a Computer Science Major at Santa Clara University, where I work in the EPIC and Cloud Labs.
My research so far has led me to develop IoT solutions to automate agriculture, virtual reality software, and machine learning algorithms for malware detection.
Email /
CV /
Twitter /
Github
|
|
Research
I'm interested in Computer Graphics and Vision, specifically rendering, computational photography, geometry, and graphics hardware.
|
|
Swing Beats
Swing Beats is an augmented/virtual reality music visualization and mobile/IoT tactile feedback system for teaching/learning how to dance to music. The project is to identify the beat of live music using a cellphone app and translating that into tactile feedback on the phone, wearables, and small IoT devices which will enable the accurate movement initiation and footwork during dancing. The app also feeds AR and VR environments in order to produce visualizations of the music and eventually an avatar which can react to the music accurately and hence help teach dance moves to learners. I am mainly focused on the AR and VR side of this project, helping to bolster my experience in Computer Graphics.
|
|
Hydration Automation
IoT system for continuously monitoring the level of water in water tanks.
|
|
HiveSpy
IoT system for continuously monitoring the amount of honey in each individual frame in the beehive.
|
|
DOxy: Dissolved Oxygen Monitoring
DOxy is an IoT System which utilizes cost-effective, accessible, and sustainable Sensing Units (SUs) for measuring the dissolved oxygen levels present in bodies of water which send their readings to a web based cloud infrastructure for storage, analysis, and visualization. DOxy's SUs are equipped with a High-sensitivity Pulse Oximeter meant for measuring dissolved oxygen levels in human blood, not water. Hence a number of parallel readings of water samples were gathered by both the High-sensitivity Pulse Oximeter and a standard dissolved oxygen meter. Then two approaches were investigated. One, in which various machine learning models were trained and tested to produce a dynamic mapping of sensor readings to actual DO values. And another in which curve-fitting models were used to produce successful conversion formula usable in the DOxy SUs offline. Both proved successful in producing accurate results. Pending Publication "DOxy 2.0" in MDPI Sensor Networks Journal.
|
|
ÂB
An Energy Aware Communication Protocols (EACP) for use in IoT and other networks which is currently under testing in EPIC Lab's DOxy, HA, and HiveSpy IoT projects.
|
|
Ransomware Detection using Machine Learning
Using Machine Learning to detect ransomware with application on programmable networks. My current work can be viewed here: Ransomware Detection XG
|
|