2020 Research Projects
Summer Internship
2020 Research Projects
| Project | Pre-Requisites |
Acoustic measurements in agriculture: Use a vertical array of above and below ground microphones to assess the ‘soundscape’. Develop AI techniques to process the recordings and identify recognizable patterns (fauna, local background noises, weather noises, etc.). |
OS: Linux, Arduino Software: C++, Python |
Temperature and heat flux measurements in agriculture: Use a vertical array of at ground level and below ground temperature and heat flux sensors to assess the soil temperature and heat flux profile. Combine these measurements with typical weather station (T, RH, solar radiation, precipitation, snow depth) data to study soil heat flows. |
OS: Linux, Arduino Software: C++, Python |
Soil moisture measurements: Use an array of soil moisture sensors to assess the moisture content across the soil matrix. Combine these measurements with precipitation and crop irrigation data. |
OS: Software: |
Long-range acoustic communication for new mobile applications: This project will develop an acoustic communication system that can achieve longer communication range to support broad applications on mobile devices, such as indoor broadcasting and device pairing. Museums can use acoustic beacons to broadcast information about nearby art pieces. IoT devices could find an alternative channel for communication, reducing the growing load on BLE. |
OS: Software: |
Adversarial machine learning for voice controllable systems: Adversarial samples are intentionally designed to mislead trained machine learning models into making wrong predictions. This project will leverage adversarial machine learning techniques to attack voice controllable systems. |
OS: Software: |
Hidden voice commands to attack voice assistant systems: The emerging voice assistant systems suffer the risks of being attacked and causing privacy leakage. This project explores an attack mechanism named hidden voice commands that are unintelligible to the users but can be correctly interpreted by a voice assistant system. |
OS: Software: |
| Educational Virtual Reality Escape Rooms: A game based on a set of virtual rooms in which players will have to solve a STEM related problem before being able to move to the next one – similar to the popular “escape rooms” experience. | OS: Windows, Android Software:C#,C/C++, Java |
| Ambient sensing with mulit-modal sensor box:: implement open source air filter using 3D printer and program it with smart control algorithms that filter the air and improve indoor air quality, proactively. | OS: Linux Software:Python, HTML5 |
| Self-Driving Vehicular Project: Assemble and train miniature autonomous vehicles to run in the miniature smart city environment. Design and implement self-driving algorithms using machine learning libraries in python. Design behavior that will allow the vehicles to react realistically to other cars and props in the smart city environment, and work with the testbed infrastructure to use external data from the intersection to improve performance. | OS: Linux Software:Python, C/C++ |
| Investigating the Biological Impacts of Radio Spectrum Transmissions: This project will investigate how the recent explosion of Radio Frequency (RF) signals in the environment can have biological impacts. Recent work has shown bird navigation is impacted by megahertz frequencies, the the investigation of the impacts of possible RF pollution is a concern. Honeybees are one of the few species which have been shown to have electromagnetic detection mechanisms sensitive enough to navigate using the Earth’s magnetic field. This project has two parts: First, we will build basic AM and FM radios directly using simple coils. These will be deployed at Rutgers’ horticulture farm next to their beehives in specialized feeders connected to web-cameras, where the bees must pass through the RF fields to get the food. The second task of this project is to develop computer vision and machine learning software to analyze the resulting videos to characterize the bees’ behavioural responses to the RF fields in the feeders. | OS: Linux, Embedded programming Software: C/C++, Python |
| Smart City Traffic Simulator: Work on virtual reality smart city environment using Unity. Connect VR environment to traffic simulation software to generate realistic car behavior in the smart city. Work with physical smart city environment to use real car behavior as input to the simulator. | OS: Linux Software: C/C++, Python |
| Secure distributed algorithms for edge computing in mobile phones:The security fo edge devices is becoming a critical issue. This project aims to implement and deploy secure distributed algorithms on mobile phones to perform distributed computing without compromising data privacy. | OS: Software: |
| Deploying efficient deep learning algorithms on resource-constrained mobile devices:The computational complexity and storage cost prevent the deployment of advanced deep learning algorithms to resource-constrained devices, such as mobile phones or IoT devices. This project will study the deep learning model compression and acceleration techniques that can be deployed on resource-constrained devices without sacrificing accuracy. | OS: Software: |
| Recognition of Radio Devices using Machine Learning: This project seeks to use machine learning to recognize different wireless devices. The project will use software defined radios (SDR) to record various devices, such as iphones, bluetooth earbuds, and Wifi laptops. These recordings will become the training data to a set of neural networks. The second part of the project will quantify the accuracy of the neural networks in classifying various device types based on their RF signatures. | OS: Linux Software: C/C++, Python |