Master’s Student Research Opportunities

Several Faculty members in the Department of Electrical and Computer Engineering offer short-term or ongoing research projects in which Master’s students may participate for academic credit or for pay.

Descriptions of available projects are listed below, with application deadlines and links for applying.

DetailS

How to Apply

If you are interested in an opportunity, complete the corresponding application. Your application will be forwarded to the project supervisor. The project supervisor will contact you directly if interested in interviewing you.

Updates

Projects are updated at the beginning of each semester and as new projects become available.

Important: Hours Limit

Please remember that all graduate students may earn pay up to 19.9 hours per week only. Additional work authorization is not required for international students for on-campus employment.

Current Research Opportunities

3D Printed Mold Creation for Epoxy Deep Ocean Electronic Devices
Faculty Advisor: Dr. Martin Brooke

We have been experimenting with ways to quickly create arbitrarily shaped epoxy housings for electronic components such as raspberry pi based sensors.  3D printed molds tend to melt, and leak, and the epoxy remains bonded to the 3D printed plastics, even when using mold release.  We have had some promising results with using 3D Printing for Two-Part Silicone Molds. 

Deadline: Open until filled

Compensation Options: MS Project Exam, Independent Study

Expected Duration: One semester with potential to extend

Application link

3D Printing Biomolecules in the Protein Database
Faculty Advisor: Dr. Martin Brooke

We would like to be able to routinely print biomolecules such as ATP Synthase and ligand gated ion channels from their protein data base files.  This will involve developing a software pathway from the pdb or cif file to stl file for 3D printing. Issues such as how to support the molecules when printing, what style of print to use (e.g., space filling atomic style) will need to be dealt with.

Required Skills: Programming / 3D printing

Deadline: Open until filled

Compensation Options: MS Project Exam, Independent Study

Expected Duration: Two semesters

Application link

Deep Neural Network Game Player: Learning By Example
Faculty Advisor: Dr. Martin Brooke

We will use AI techniques such as Deep Neural Networks to attempt to train software to play online games.  The approach is to create a large database of game play that can be used to train progressively better software players, leading to software reinforcement learning, where the software creates its own training sets to improve itself.

Required Skills: MATLAB, cloud computing

Deadline: Open until filled

Compensation Options: MS Thesis Exam, MS Project Exam, Independent Study

Expected Duration: Two semesters

Application link

Neural Network Prediction of Ocean pH from Metal Potentials
Faculty Advisor: Dr. Martin Brooke

We will use a Neural Network or other learning software to predict ocean pH from the measured electrical potential of metals in seawater.  There is an opportunity to visit the Duke Marine Lab for testing of the sensors.

Required Skills: Arduino Code, MATLAB

Deadline: Open until filled

Compensation Options: MS Thesis Exam, MS Project Exam, Independent Study

Expected Duration: Two semesters

Application link

Predicting Strength of 3D Printed Parts for Lightweight Drone Frames
Faculty Advisor: Dr. Martin Brooke

We will use COMSOL / SOLIDWORKS or other software to try to predict the strength of 3D printed parts for use in drone airframes and other carbon fiber frames.  The directional (anisotropic) properties of 3D printed materials printed on low cost printers are of particular interest.

Deadline: Open until filled

Compensation Options: MS Thesis Exam, MS Project Exam, Independent Study

Expected Duration: Two semesters

Application link

Virtual Reality Interface for MATLAB Visualization
Faculty Advisor: Dr. Martin Brooke

We would like to have a way to visualize surfaces and other 3D objects in MATLAB using a virtual reality headset such as the oculus rift, HTC Vive, or Fove.

Deadline: Open until filled

Compensation Options: MS Thesis Exam, MS Project Exam, Independent Study

Expected Duration: Two semesters

Application link

 

Time-Series Data Analytics for Predictive Healthcare
Faculty Advisor: Dr. Krishnendu Chakrabarty

This is a joint project with Prof. Jeff Glass in ECE and other partners in the Duke Medical School. It will involve the generation of streaming data (details to be provided later) from an array of sensors, labeling of this data using knowledge of health disorders, training of machine learning models using carefully selected features, and then using real-life data to predict health disorders. Specifics include the detection of anomalies and changepoints, and studying the tradeoffs between false alarms (false positives) and false negatives. Please contact Prof. Chakrabarty (krish@duke.edu) for more details. 

Required/Preferred Coursework: Machine learning at graduate level

Required/Preferred Skills: C++, ML tools such as Weka 

Deadline: August 31, 2018

Compensation Options: MS Project Exam

Expected Duration: One semester with potential to extend

Application link

Advanced Machine Learning Techniques with Application to Landmine Detection 

Faculty Advisor: Dr. Leslie Collins

Our lab is looking for highly motivated masters students to participate in independent study projects during the semester (with potential for a longer engagements including summers). The students will conduct research applying machine learning and computer vision algorithms for real-world applications, and in particular to the detection of landmines. All candidates must be US citizens. Ideal candidates will have completed at least one machine learning course, and one probability theory course, however everyone is encouraged to apply!  

Preferred Coursework: Random Signals and Noise,  Signal Detection and Extraction Theory, Pattern Classification and Recognition Technology

Preferred Skills: Matlab, Python

Deadline: Open until filled

Compensation Options: Independent Study, MS Project Exam

Expected Duration: One semester with potential to extend

Application link 

Optimizing Stimulus Presentations Schedules in the P300-based Brain-computer Interface 
Faculty Advisor: Dr. Leslie Collins

The P300 speller is a stimulus-driven brain-computer interface (BCI) that relies on eliciting and detecting event-related potentials embedded in noisy electroencephalography (EEG) data. However, current P300 spellers operate with relatively slow communication rates, which limit their wide-scale adoption as alternative means of communication for individuals with severe neuro-muscular limitations. Dr. Collins’ lab is currently investigating information-based approaches to design stimulus presentation schedules for the P300 speller to improve BCI communication rates. We are looking for an MS student to investigate a data-driven algorithm to optimize stimulus presentation schedules for the P300 speller. Optimal candidates for this position would have a background in signal processing, detection and estimation, and optimization, and would have programming experience in Matlab and C++. 

Required Coursework: Random Signals and Noise (required), Pattern Classification and Recognition Technology (required)

Deadline: Open until filled

Compensation Options: Independent Study

Expected Duration: One semester with potential to extend

Application link 

Optimizing Cochlear Implant Sound Processor Configurations via Neural Response Properties to Improve Speech Comprehension
Faculty Advisor: Dr. Leslie Collins

Speech understanding by cochlear implant (CI) users is partially governed by the CI processor parameters, and these are typically adjusted by an audiologist in the clinic.  However, the sheer size of the processor parameter space makes it impossible to test every combination of parameter values manually in the clinic to optimize speech understanding. Dr. Collins’ lab in collaboration with Dr. Tobias Overath (DIBS), Dr. Mike Murias (DCABD), and Dr. Josh Stohl (MedEl) have recently received a DIBS Incubator Award for a project that investigates whether EEG data recorded while a CI subject is listening to speech might be used to automatically optimize CI processor parameters. We are looking for an MS student to help us develop estimation and optimization algorithms to investigate our hypothesis that CIs can be automatically tuned using EEG data.  Optimal candidates for this position would have a background in signal processing, detection and estimation, and optimization, and would have programming experience in Matlab or Python.

Required Coursework: Random Signals and Noise (required), Signal Detection and Extraction Theory (preferred)

Required Skills: Signal Processing, Machine Learning, Matlab, Python

Deadline: Open until filled

Compensation Options: MS Project Exam, Independent Study

Expected Duration: One semester with potential to extend

Application link 

Modeling and Testing Autonomous Forms of Transportation
Faculty Advisor: Dr. Missy Cummings

Interested in autonomous forms of transportation like driverless trains, planes and cars? The Duke Humans and Autonomy Laboratory (HAL) is looking for researchers interesting in developing simulation models of dispatch centers for all types of autonomous vehicles.

Required Skills: Java/C/C++

Deadline: Open until filled

Compensation Options: MS Thesis Exam, MS Project Exam, Independent Study, Paid ($19/hr)

Expected Duration: Can be scoped as needed

Application link

Validating Drone Operator Mod
Faculty Advisor: Dr. Missy Cummings

This project includes running a human-in-the-loop indoor drone experiment and then constructing hidden Markov models from the experimental data.

Required Coursework: None

Required Skills: some experience with java

Deadline: September 15, 2018

Compensation Options: MS Thesis Exam, MS Project Exam, Independent Study, Paid ($15-$19/hr, dependent on skill level)

Expected Duration: One semester with potential to extend

Application link

Deep Learning Based Retinal Image Analysis
Faculty Advisor: Dr. Sina Farsiu

Students interested in automated medical image analysis of ophthalmic images using deep learning are invited to participate in this multidisciplinary project.  Students should have a basic knowledge of image processing.  Examples of previous similar projects in PI's lab can be found here: http://people.duke.edu/~sf59/

Required Coursework: Digital Image Processing

Required Skills: Matlab (Required), Python programming skills (Preferred)

Deadline: Open until filled

Compensation Options: MS Thesis Exam, MS Project Exam, Independent Study, Paid ($15/hr)

Expected Duration: One semester with potential to extend

Application link 

Development of a Handheld Characterization System for Nanoscale Devices 

Faculty Advisor: Dr. Aaron Franklin 

In our lab, we fabricate electronic devices from nanomaterials, including carbon nanotubes, graphene and other two-dimensional crystals. Electrical characterization of these devices requires bulky and costly equipment, making it difficult to study a large number of devices over extended periods of time. We recently showed that a custom electronics board, developed from low-cost components, can be used to characterize the devices. In this project, design and implementation of this handheld board will be pursued. There is already a circuit to begin working from, allowing the student to have a reasonable place to start. From there, the circuit/hardware should be optimized, along with printed circuit board design, and ultimately packaged (with 3D printed casing) for robust use. Software should then be designed to allow interfacing with this handheld characterization system. The resultant system would have significant impact on the throughput of research in this field. Required Skills: Knowldege in fundamental and experimental analytical chemistry; strong laboratory skills 

Deadline: September 15, 2018

Compensation Options: MS Thesis Exam, MS Project, Independent Study

Expected Duration: One semester with potential to extend

Application link

Impact of Liquid Environments on Carbon Nanotube Transistors 
Faculty Advisor: Dr. Aaron Franklin

Because carbon nanotubes (CNTs) expose their entire crystal lattice, they can provide extreme sensitivity to biosensors. These sensors are often operated in liquids, with various buffer solution requirements. What impact does the buffer solution have on the device characteristics of the nanotube? It could be that some buffer solutions enable higher performance, or that others cause damage to the exposed carbon nanotube. The goal of this project is to find the answer by measuring existing CNT transistors in several buffer solutions. The results may indicate that taking measurements over time is necessary in order to observe slow changes in the device. The student would be provided with CNT transistors and trained on how to characterize them. They would be responsible for characterization, data analysis, and follow-up experiments to understand the observed behaviors. Some background (such as coursework) in solid-state devices is preferred. 

Deadline: September 15, 2018

Compensation Options: MS Project Exam, Independent Study

Expected Duration: One semester

Application link

Understanding Bias Stress Response in Thin-film Carbon Nanotube Transistors
Faculty Advisor: Dr. Aaron Franklin

Point-of-care medical tests are extremely valuable in developing countries where access to hospital laboratories and trained medical technicians is limited. In these circumstances, the test is also required to be inexpensive. To meet this need, low-cost printed biosensors able to perform a range of immunoassays are being developed in our lab using a carbon nanotube (CNT) thin film as the sensing element. Promising results showing high sensitivities have been obtained. Device reliability, however, has been problematic in that some of the sensors fail too quickly. Discovering the reason for these early failures is an important next step and will be the focus of this project. To gain more information about what could be causing these devices to fail, this project will consist of monitoring many thin-film CNT transistor devices over time. Average failure rates will be measured. Tests will be performed with the devices exposed to various media, such as ambient air, water, buffer, serum, and whole blood. Any interest in learning more about biosensors, printed electronics, microcontrollers, or applied programming could be valuable for this project. 

Deadline: September 15, 2018

Compensation Options: MS Thesis Exam, MS Project Exam, Independent Study

Expected Duration: One semester with potential to extend

Application link

Designing an Electrical Biosensing Platform
Faculty Advisor: Dr. Aaron Franklin

In our lab, we print electronic biosensors from nanomaterials. One sensing system we are currently working on is for monitoring prothrombin time (i.e., blood clot time) to help patients that require long-term use of blood thinning agents. In this project, a handheld electrical system will be designed for operating the biosensors. This includes the needed hardware (for which an example/starting platform will be provided), integration of components, design and 3D printing of enclosure, and software for controlling the unit, including the graphic user display. The student should have interest in learning about basic electronics hardware design, programming for a custom application, and biomedical technology. If successful, the handheld system may be tested on patient samples in the Duke clinic.  

Deadline: September 15, 2018

Compensation Options: MS Thesis Exam, MS Project Exam, Independent Study

Expected Duration: Two semesters

Application link

Investigation of Broadband X-ray Phase Imaging
Faculty Advisor: Dr. Michael Gehm

Phase-imaging methods are of interest in the x-ray domain because, unlike in conventional absorption imaging, the contrast mechanism is the interference between neighboring ray-paths. Use of this mechanism increases sensitivity to low-absorption materials and expands the application areas in which x-ray-based methods have utility. Major existing approaches to x-ray phase imaging either utilize monochromatic energy sources and spatial filtering to yield a coherent illumination source, or require a complicated set of diffraction gratings to induce the required coherence. In this project, we propose to investigate to what extent the use of energy-resolving detection can allow for broadband x-ray phase imaging without the need for additional complicated elements.
   
The project will be a mix of numerical (simulation) and experimental effort to explore this concept. Coursework in optics and/or electromagnetics will be helpful but is not required. More important is the motivation and self-direction to learn the underlying theory and to develop and drive forward the simulations and experimental exploration.   

Deadline: August 31, 2018

Compensation Options: MS Thesis Exam, MS Project Exam

Expected Duration: One semester with potential to extend

Application link

Circuit and Control of Novel Reconfigurable Battery

Faculty Advisor: Dr. Stefan Goetz

Conventional batteries are hard-wired packs made of individual cells. In all aspects, such as ageing, capacitance, heating, and peak power, the performance of the battery is limited by the weakest cell. If one cell is damaged, the entire battery has to be recycled. Furthermore, a number of dedicated electronic units are required to convert the battery voltage that substantially changes throughout a cycle to match the requirements, to balance cells that drift apart, and monitor thermal hotspots as well as ageing. We developed a novel circuit technology that can dynamically reconfigure a battery to perform all the tasks that are done by separate systems, increase the performance as well as efficiency, and generate almost any output voltage and current by reconfiguring the series-parallel circuit configuration of the battery cells rapidly. By changing the circuit configuration, energy can be transferred between cells, load can be shifted or balanced, the internal resistance can be varied, and the output voltage and current rating can be adjusted rapidly.

We are looking for a candidate who wants to contribute to this novel circuit technology and/or control of the many degrees of freedom and help to innovate the way we will store energy in the future.

Deadline: December 31, 2018

Compensation Options: MS Thesis Exam, MS Project Exam, Independent Study

Expected Duration: One semester with potential to extend

Additional Application Documents: Undergraduate transcript (can be unofficial)

Application link

Design and Implementation of Electric Vehicle Drive Train with Novel Dynamically Reconfigurable Battery
Faculty Advisor: Dr. Stefan Goetz

Conventional electric vehicles use a hard-wired battery and many dedicated electronic systems to convert power for the motor as well as many other systems and monitor the battery. We are developing a technology that revolutionizes the way how electric drive trains are set up and implement it into a prototype vehicle. We would like to welcome you in our team to participate in this tectonic shift and the study the new questions such a system entails.

Dependent on the aspect you want to concentrate on, you should have experience in at least one of the following topics: circuit design and layout, microcontroller/fpga programming, control, electric motors, sensors, drive-train control.

Deadline: December 31, 2018

Compensation Options: MS Thesis Exam, MS Project Exam, Independent Study

Expected Duration: One semester with potential to extend

Additional Application Documents: Undergraduate transcript (can be unofficial)

Application link

Design of Renewable-Energy Grid-Storage System Using Novel Highly Flexible Circuit Topology
Faculty Advisor: Dr. Stefan Goetz

At present, our electric energy supply is changing rapidly. Former centralized power generation from fossil and nuclear sources is amended and partly replaced by renewable energy sources with large power share but high volatility, such as wind and solar energy. Energy storage systems are a solution to average out the fluctuations and make the supply meet the demand. While electric vehicles have stimulated impressive developments in battery technology, typical electronics concepts for such systems use rather old technology with many limitations.

We will design and implement a novel circuit technology discovered at Duke that breaks with limiting conventions to form a highly flexible reconfigurable battery system that can run each sub-battery of system at its optimum point, substantially increase the performance of the system, perform many tasks conventionally done by separate units with the same electronics now, and generate any kind of DC and AC output with high quality.

Ideally, you have experience in some of the following topics: electronics, circuit design, microcontroller programming, high-performance electronics.

Deadline: December 31, 2018

Compensation Options: MS Thesis Exam, MS Project Exam, Independent Study

Expected Duration: One semester with potential to extend

Additional Application Documents: Undergraduate transcript (can be unofficial)

Application link

Novel High-Frequency High-Power Circuitry for Noninvasive Inductive Neurostimulation
Faculty Advisor: Dr. Stefan Goetz

Noninvasive neurostimulation systems such as TMS are high-performance electronic systems that can actuate neurons in the body to trigger their response and introduce artificial signals into neural processing circuits. As the activation dynamics of neurons is type-specific and strongly nonlinear (chaotic in the mathematical sense), variation of the dynamics of the excitation pulse allows preferable activation of some neuron types and an analysis of the dynamics of the activated neurons, similar to a filter circuit analysis with Fourier sweeps in analog electronics.

Despite a world-wide desire to have a noninvasive magnetic stimulation device that can freely synthesize almost any pulse shape, there has not been an appropriate circuit technology for this challenge. We recently developed a novel circuit technology that can generate almost any output signal with high frequency content at high power as required here. We would like to welcome you in our team for participating in a development at the forefront of electronics in neuroscience and medicine.

Ideally, you have experience in at least two of the following to design an appropriate subproject according to your needs and interest: circuit design as well as layout, high-performance electronics, control systems, microcontroller and/or FPGA programming.

Deadline: December 31, 2018

Compensation Options: MS Thesis Exam, MS Project Exam, Independent Study

Expected Duration: One semester with potential to extend

Additional Application Documents: Undergraduate transcript (can be unofficial)

Application link

Signal Processing and Feature Extraction from Neurosignals
Faculty Advisor: Dr. Stefan Goetz

Neurons communicate electrically. These subtle signals can be detected to analyze and understand the electrical behavior of neural circuits. We use latest signal-processing, estimation, and machine-learning methods to detect patterns, find signals far below the noise level, and reconstruct ongoing neural computation in a living human. The project aims at developing novel methods to extract and quantify such information. Ideally, the findings are implemented in a neuroamplifier that can become a commercial product.

You ideally have experience in advanced signal processing, matlab, and first contact to machine learning and estimation.

Deadline: December 31, 2018

Compensation Options: MS Thesis Exam, MS Project Exam, Independent Study

Expected Duration: One semester with potential to extend

Additional Application Documents: Undergraduate transcript (can be unofficial)

Application link

Novel High-Fidelity High-Power Audio Amplifier Technology
Faculty Advisor: Dr. Stefan Goetz

The project aims to design and implement the concept of a novel high-fidelity audio amplifier technology for public places such as stadiums and concert halls.
   
Currently, high-fidelity audio amplifiers are dominated by linear amplification circuits (e.g., class A/B/AB), which require trmendous amounts of energy and have weak driving capability. On the other hand, switched-mode power supplies (e.g., class D) have unlimited output power but limited sound quality. In this project, we will develop a novel electronics technology to achieve quality and power at the same time.

Phase 1: Start with circuit simulations to identify critical parts in the system design.
Phase 2: Design and fabricate the circuits.
Phase 3: System assembly and trouble-shooting.

We can provide hands-on training on simulation (spice, Matlab/Simulink), analysis, circuit design (Altium Designer), and assembly. The pre-requisites are secondary if you genuinely love building things and are willing to acquire practical engineering mindset.

Required/Preferred Courses Taken: analog circuits, circuit theory

Required/Preferred Skills: spice simulation, Matlab/Simulink, Altium Designer

Deadline: September 30, 2018

Compensation Options: MS Thesis Exam, MS Project Exam, Independent Study

Expected Duration: Two semesters

Application link

Pattern Recognition to Isolate Few- or Single-Unit Responses in Motor Responses Evoked through Brain Stimulation for the First Time
Faculty Advisor: Dr. Stefan Goetz

Motor signals in electromyography evoked through brain stimulation are a key instrument in diagnosis of neural lesions and the study of neurophysiology. Conventionally, only signals of a large number of units can be detected and lots of information is not used. We are looking for a student who is familiar with statistics and machine learning tools to improve methods for information extraction and pattern recognition to detect the responses of few or even a single unit for the first time. We aim at developing an easy-to-use but informative method for research and furtheron also clinical use. This project can be based on preliminary work done in our lab.

Required/Preferred Courses Taken: signal processing

Required/Preferred Skills: data analysis, pattern recognition, statistics or machine learning 

Deadline: October 30, 2018

Compensation Options: MS Thesis Exam, MS Project Exam, Independent Study

Expected Duration: One semester with potential to extend

Application link

Optical Fluorescence Imaging of the Live Brain
Faculty Advisor: Dr. Yiyang Gong

The Gong lab is looking for a researcher to investigate neural activity using fluorescence imaging. Our goal is to image the activity of thousands of neurons simultaneously in the brain of live zebrafish and live mice. This large scale imaging will allow us to better understand the brain.

The lab has expertise in creating protein sensors that respond to neural activity (see lab homepage: http://neurotoolbox.pratt.duke.edu). We are looking for a researcher to acquire the fluorescence movies from live animal samples and then process the resulting data. The research should be experienced with labview control software and/or fluorescence image processing. Projects will be geared toward the experience level of the student. Long-term effort on the project should lead to significant research products that count toward thesis work and/or publications.

Required Skills: Labview; Matlab; Fourier transforms; Signals and systems

Deadline: Open until filled

Compensation Options: MS Thesis Exam, MS Project Exam, Independent Study, Paid ($15/hr)

Expected Duration: One semester with potential to extend

Additional Application Documents: Most recent transcripts

Application link

Towards Practical Multi-User Augmented Reality (AR): Understanding and Overcoming Limitations of AR Systems

Faculty Advisor: Dr. Maria Gorlatova

Augmented reality (AR) is a rapidly developing technology area with potential for transforming many daily human experiences. While promising, current AR systems are somewhat limited in their capabilities, in particular in multi-user experiences, high energy consumption, and general lack of robustness and adaptability.

The goal of this project is to obtain in-depth experimental understanding of the limitations of current augmented reality experiences, and to establish how these limitations can be addressed.

Students involved in this work will experiment with develop and experiment with different augmented reality applications, experiences, and platforms, in order to understand the systems and network loads of different operations, key drivers of immersive user experiences, and the potential of edge and cloud computing platforms to address the discovered limitations. The project involves both the development of Unity-based holographic experiences, and real-world holographic deployments with mobile phones and HoloLens sets.

The project is best suited for students who have an experimental mindset and who enjoy obtaining in-depth understanding of system performance, physical phenomena, and human behavior.

Coursework in communications and/or networking and programming ability are important for quickly getting up to speed on this project. Mobile systems experience is preferable but not required.

More information about project supervisor's research interests: https://maria.gorlatova.com/current-research/

Deadline: September 7, 2018

Compensation Options: MS Project Exam, MS Thesis, Independent Study

Expected Duration: One semester with potential to extend

Additional Application Documents: Transcripts

Application link

Dynamic Reservation Mechanisms for Ensuring Co-Existence of Different Traffic Types in 5G 
Faculty Advisor: Dr. Maria Gorlatova

Current networks struggle to achieve quality of service for the combinations of latency-oriented and bandwidth-hungry traffic. The solutions to this problem that have been recently proposed, such as Time-Sensitive Networking and Dynamic Network Slicing, operate on the principle of reserving network resources for different traffic classes. While the solutions have been proposed, much remains to be specified about them, including the "triggers" for activating different types of reservations, theoretical performance guarantees achievable with and without reservation mechanisms, and the practically achievable levels of responsiveness in the adaptations.
   
The goal of this project is to further define and elucidate the performance of these dynamic reservations, in particularly in context of the needs of ultra-low-latency traffic, such as traffic associated with augmented and virtual reality applications. The project involves analytical, simulation-based, and, potentially, hands-on experimental explorations of dynamic reservations, and the development of algorithms with performance guarantees.

Required: communications/networking. Preferred: optimization, algorithms, stochastic modeling

Deadline for Application: Open until filled

Project Compensation Options: MS Thesis Exam , MS Project Exam, Independent Study

Expected Duration of Project: Two semesters

Additional Application Documents: Transcripts 

Application link

Distributed Restructured Machine Learning for the Internet of Things  
Faculty Advisor: Dr. Maria Gorlatova

The current state of the art in machine learning requires transmitting all data to a centralized repository. This approach has privacy challenges, and involves potentially unnecessary transfers of large amounts of data. Correspondingly, decentralized techniques are nowadays starting to appear, that allow part of the training process to be completed on local devices, without transmitting the devices' data to the cloud -- Google's "federated learning" being one example. 
    
The goal of this project is to develop such restructured learning techniques, and to evaluate their performance with realistic data and in real-world settings. Project requires background in machine learning. Experience working with real-world data is preferred but not required.

Deadline for Application: Open until filled 

Project Compensation Options: MS Thesis Exam , MS Project Exam, Independent Study 

Expected Duration of Project: One semester with potential to extend

Additional Application Documents: Transcripts 

Application link

Making Augmented Reality More Intelligent with Advanced Machine Learning
Faculty Advisor: Dr. Maria Gorlatova

Machine learning has the potential to take the performance of Augmented Reality experiences to the next level. Unity Machine Learning Agents Toolkit provides an excellent starting point for experimenting with such approaches; in our ongoing work, we have already developed a simulator that works on top of Unity, and have preliminary demonstrated the potential of both reinforcement learning and behavioral cloning for Augmented Reality of the future. 
    
The goal of this project is to explore in depth the potential of various machine learning techniques to benefit Augmented Reality. Knowledge of modern machine learning techniques is essential for this project. The project involves development of a simulator, ideally to the level of making it available to others. Experience developing production-quality or open-source code is preferable but not required.

Deadline for Application: Open until filled 

Project Compensation Options: MS Thesis Exam , MS Project Exam, Independent Study 

Expected Duration of Project: One semester with potential to extend

Additional Application Documents: Transcripts 

Application link

Characterizing Latency, Reliability, and Stability in Fog Computing Systems
Faculty Advisor: Dr. Maria Gorlatova

Edge/Fog computing, where traditionally centralized computing capability is placed on different points between the cloud and the end user, has been attracting considerable attention lately, in part because of its potential to provide low-latency services for end-point devices. While it is understood that edge/fog achieves lower latency than the cloud, definitive experimental characterizations of the latency associated with various available execution points are currently lacking.
   
The goal of this project is to obtain quantitative data-driven understanding of key performance parameters of edge/fog systems, such as the stability of nodes' latency characteristics, and the variability of results across geographies and deployment specifics. We have collected a dataset that supports this analysis, and have used it to obtain a collection of preliminary insights. While we have the starting points for the analysis, we are looking for students with solid background in stochastic processes or statistics, and the desire to work with large-scale datasets, to turn our preliminary hunches into definitive data-driven insights and conclusions.
   
This project is ideally suited for students who are looking to turn their MS Thesis/Project/Independent Study into a publication, as we plan to submit this work to a top-tier conference or a top-tier journal before the end of the semester.

Required: communications/networking, stochastic processes, statistics. 

Deadline for Application: Open until filled 

Project Compensation Options: MS Thesis Exam , MS Project Exam, Independent Study 

Expected Duration of Project: One semester with potential to extend

Additional Application Documents: Transcripts 

Application link

Deploying -- and Breaking -- Edge Computing Platforms
Faculty Advisor: Dr. Maria Gorlatova

Over the last two years, several cross-application software platforms that bridge Internet of Things (IoT) devices and the cloud have become available -- they include, for example, EdgeX and AWS Greengrass. Such platforms hold the promise of enabling true scaling of the IoT by making IoT nodes easy to set up and manage, and by mitigating some of the disadvantages of the cloud in cloud-node interactions. We seek to understand the core principles, the performance, and the limitations of these promising novel systems.
   
This project involves implementing, examining, and contrasting edge computing platforms, using real-world hardware and a range of IoT nodes.
   
This project is ideally suited to students who like to architect and examine complex computer systems, reverse-engineer existing system designs, and look for design shortcomings and vulnerabilities.
   
Solid software development skills are important for the success of this project. Experience with/ interest in open-source software development would be advantageous in some elements of this project, but is not required.

Required: communications/networking, software development. Preferred: distributed systems, mobile systems.

Deadline for Application: Open until filled 

Project Compensation Options: MS Thesis Exam , MS Project Exam, Independent Study 

Expected Duration of Project: One semester with potential to extend

Additional Application Documents: Transcripts 

Application link

The Data and Physics of X-ray Diffraction 
Faculty Advisor: Dr. Joel Greenberg

X-ray diffraction is a well-established technique for determining the molecular structure of a material. It’s ability to tell explosives from non-threat materials in luggage or malignant from cancerous tissue in tumors is driving its development as a diagnostic, imaging technique. In this project, the student will acquire experimental data and apply data mining and data processing techniques to understand how the statistical properties of the diffracted x-rays the statistical properties of the scattering material. Understanding this relationship will improve the performance of X-ray diffraction based systems, as well as potentially provide insight into visible-optics systems such as a holographic imaging and imaging through thick scattering media.
   
Coursework in the areas of optics/electromagnetism and/or signal processing is preferred. The student should be proficient in using Matlab or similar data manipulation tools.

Deadline for Application: September 1, 2018

Project Compensation Options: MS Thesis Exam , MS Project Exam

Expected Duration of Project: Two semesters

Application link

Spotting Bombs in Bags
Faculty Advisor: Dr. Joel Greenberg

Aviation security is constantly pushing X-ray imaging and detection technology forward to combat ever-evolving threats.  In parallel, X-ray-based medical imaging is pushing toward earlier and more sensitive disease diagnosis. To this end, I am studying a novel X-ray imaging technique that combines the most recent advances in computational imaging with X-ray physics.  I am seeking an interested and motivated student to a) make experimental measurements on an already-built system b) develop and perform numerical simulations, and c) use statistical/machine learning approaches to analyze data.   The results of the work are directly relevant to ongoing research at several major security and medical technology vendors and will be published in peer-reviewed journals.  In addition, through working on the project, the involved student will be a part of the ALERT program (http://www.northeastern.edu/alert/education-programs/). 

Coursework in the area signal processing is preferred. The student should be proficient in using Matlab or similar data manipulation tools.

Deadline for Application: September 1, 2018

Project Compensation Options: MS Thesis Exam , MS Project Exam

Expected Duration of Project: Two semesters

Application link

Data-Driven MPC for High Speed Quadcopter Navigation
Faculty Advisor: Dr. Kris Hauser

Model predictive control has the potential to yield high performance controllers for dynamic, nonlinear systems, but requires a significant amount of computation. This project will learn control policies from trajectory optimization data generated offline. The technique shall be demonstrated on quadcopters performing high speed dynamic navigation and obstacle avoidance tasks. Using sensor feedback the system will estimate unknown inertial and disturbance parameters and adjust its control accordingly.

Required Skills: C++ programming, experience with ROS, motion capture, multivariable calculus 

Deadline: February 1, 2018

Compensation Options: MS Thesis Exam, MS Project Exam

Expected Duration: Two semesters

Application link

Deep Learning Robotic Multifingered Grasps
Faculty Advisor: Dr. Kris Hauser

The goal of this project is to learn complex robot manipulation strategies using deep learning and massive amounts of simulation data. The student will program scripts to generate simulated grasps of objects both isolated and in clutter. Using the generated datasets, convolutional neural network architectures will be trained and evaluated to predict grasping poses and grasp pose success from RGB-D images of the object. If successful, the student will continue to evaluate the model applied to a real robot.

Required Coursework: Machine learning

Preferred Skills: Tensorflow and Python experience preferred

Deadline: December 31, 2018

Compensation Options: MS Project Exam, Independent Study (Must enroll by September 7, 2018)

Expected Duration: One semester with potential to extend

Additional Application Documents: 

Application link

Benchmarking Datasets for Volumetric and Semantic Segmentation of Indoor Scenes
Faculty Advisor: Dr. Kris Hauser

Existing 3D object segmentation and recognition algorithms only identify the structure of visible surfaces, but for many applications in robotic manipulation and augmented reality, it is important to also understand what is behind or beneath the surface. To help develop and benchmark new volumetric object segmentation algorithms, this project aims to produce a dataset of 3D indoor scenes with labelled volumetric information. The student will develop camera rigs and 3D scene capture methodologies, and then post-process and deploy the datasets on a public website.

Required Coursework: Signal processing, Computer architecture

Required Skills: C++ experience (Required), CUDA experience (Preferred)

Deadline: December 31, 2018

Compensation Options: MS Project Exam, Independent Study (Must enroll by September 7, 2018)

Expected Duration: One semester with potential to extend

Application link

Software-Related Student-Proposed Project
Faculty Advisor: Dr. Drew Hilton

Open to a wide variety of student-generated software-related projects. Please uploead a project proposal with your application. 

Recommended Coursework and/or Skills: Generally will need skills from some combination of ECE 650, ECE 651, ECE 553, ECE 590: Engineering Robust Server Software, or a similar level and depth of experience. 

Deadline: January 1, 2018

Compensation Options: MS Project Exam

Expected Duration: As appropriate for proposed project

Application link

Measuring the State of Health of the Body Using Microwaves
Faculty Advisor: Dr. Bill Joines

Using less than 0.02 W of power at 915 MHz (comparable to cell phone output) we can measure the composite electrical properties of the path across the body between antennas using a vector network analyzer.  Comparing these results with those obtained with human volunteers, and those obtained with static models composed of water and muscle and fat tissues, we want to be able to establish measurable guidelines for the state of health of the body in terms of the proper balance between the percentage of water, muscle and fat.  The results to date are promising, but more measurements and calculations are needed.

Required Skills: Some knowledge of electromagnetics and vector network analyzers

Deadline: Open until filled

Compensation Options: MS Thesis Exam, MS Project Exam

Expected Duration: One semester with potential to extend

Application link

Controlling Microwave Reflections from Conductive Surfaces
Faculty Advisor: Dr. Bill Joines

We have extended some work that was started more than 70 years ago; namely, the Jaumann shield and the Salisbury screen. These involve placing thin films, of precise conductivity, at quarter wavelength intervals in front of and parallel with a highly conductive surface to prevent or minimize reflections from that surface. We have developed the design theory that yields a maximally-flat response for any number of film layers, where the frequency bandwidth for negligible reflections increases with the number of layers. But beyond that, by adjusting the conductivity and spacing of the film layers, we can achieve better than 10 dB return loss (10\% reflected power) over the entire frequency range from 1 to 100 GHz (or 0.3 m to 3 mm wavelength). We believe that these results could be extended to even higher frequencies if needed. We also believe that materials can be found or developed that would allow us to create flexible layered materials that could be used to render military vehicles and installations (or anything else) undetectable by radar. This would include the equipment of soldiers on the battlefield or the soldiers themselves. Zero reflection would not generally be required since that state could be detectable by radar, but just enough reflection to blend into the surrounding background. Our plans for this work are to optimize the bandwidth for a desired level of return loss; for example, at 10 dB, 15 dB and 20 dB of return loss, or anywhere between 10\% and 1\% reflected power as needed for the particular application.

Required Coursework: Electromagnetics, Microwaves

Deadline: Open until filled

Compensation Options: MS Thesis Exam, MS Project Exam

Expected Duration: One semester with potential to extend

Application link

Lowering the Operating Frequency of Patch Antennas
Faculty Advisor: Dr. Bill Joines

A microstrip patch antenna usually consists of a rectangular or square sheet of copper on a dielectric substrate on top of a ground plane.  An input coaxial line protruding through from ground plane to patch is usually connected  at 45 electrical degrees from one end of the patch and 135 degrees from the other.  Thus, the length of the patch is 180 degrees or one half-wavelength at the chosen operating frequency.  The coaxial connection is placed at tlhe center of the patch in the width direction.  To loweer the operating frequency the patch must be made physically longer, so that the half wavelength distance is longer.  By experiment and analysis there are otther interesting ways to create the electrical delays (45 degrees and 135 degrees).that lower the frequency without increasing the patch size.  We will be exploring these ways.

Required Coursework: Electromagnetic transmission circuits

Required Skills: Some knowledge of vector network analyzers and spectrum analyzers

Deadline: Open until filled

Compensation Options: MS Thesis Exam, MS Project Exam

Expected Duration: One semester with potential to extend

Application link

Managing Datacenters with Game Theory
Faculty Advisor: Dr. Ben Lee

Performance-centric management policies are insufficient for privately shared computer systems. Conventional wisdom assumes that users must share and policies need only mitigate performance losses. Such performance goals are suitable for public systems that deliver hardware for which users have paid. In contrast, private systems consist of users who voluntarily combine their resources and subscribe to a common management policy. However, these users also reserve the right to withdraw from the system if resources are managed poorly.

We use algorithmic game theory to manage large, complex computer systems. Game theory is a framework for reasoning about selfish users and modeling the competition for resources. Privately shared systems must manage resources fairly to encourage participation and guard against strategic behavior. Real-word users are selfish and rational, an observation that has motivated numerous game-theoretic perspectives on systems management. Neglecting users' preferences or fairness induces strategic behavior. Users may circumvent policies or break away from shared clusters, redeploying hardware to form smaller, separate systems. Fairness addresses these challenges, ensuring system integrity and stability.

We seek research assistants with expertise in either computer systems or microeconomics / game theory, and a willingness to learn about the other discipline. Research assistants should have some experience in programming (e.g., C, C++, Java) as well as comfort with algorithms and mathematics.

Deadline: Open until filled

Compensation Options: MS Thesis Exam, MS Project Exam

Expected Duration: One semester with potential to extend

Application link

Managing Datacenters with Machine Learning
Faculty Advisor: Dr. Ben Lee

Performance anomalies threaten performance from datacenter-scale computation. Datacenters split a job into many tasks, execute them in parallel across many machines, and aggregate results when the last task completes. Stragglers are exceptionally slow tasks within a job that significantly delay its completion. Unfortunately, stragglers' effects increase with the number of tasks and scale of the system. In a Google datacenter, we find that stragglers degrade performance in 20% of jobs by more than 1.5x. We apply statistical methods in machine learning to understand system performance. These methods infer stragglers' root causes by (i) modeling performance as a function of system predictors and (ii) discovering recurring and interpretable causes of poor performance across jobs and machines.

We seek research assistants with expertise in either computer systems or machine learning, and a willingness to learn about the other discipline. Research assistants should have some experience in programming (e.g., C, C++, Java) or statistical computing (e.g., R).

Deadline: Open until filled

Compensation Options: MS Thesis Exam, MS Project Exam

Expected Duration: One semester with potential to extend

Application link

Customizing Hardware for Datacenters
Faculty Advisor: Dr. Ben Lee

Custom hardware can improve energy efficiency by 100x. General-purpose hardware is inefficient because of overheads from data movement (e.g., through the cache hierarchy) and instruction control (e.g., dynamic scheduling). Specialized accelerators eliminate these inefficiencies by tailoring the hardware to the exact needs of the software.

However, customizing hardware is expensive. Design is difficult and costs are high. Recent advances in high-level synthesis permit users to express computation in user-friendly languages, which resemble C, and automatically generate hardware descriptions with Verilog or VHDL. High-level synthesis allows the user to explore a large number of different designs for the same computation. The exploration can optimize key objectives such as performance, power, and area. We are studying new methods for (i) optimizing performance and power during design and (ii) allocating and scheduling resources in custom or reconfigurable hardware.

We seek research assistants with expertise in computer architecture and digital design. Research assistants should have some experience in Verilog or VHDL, some experience with FPGAs, as well as some comfort with programming (e.g., C, C++).

Deadline: Open until filled

Compensation Options: MS Thesis Exam, MS Project Exam

Expected Duration: One semester with potential to extend

Application link

AI Design of Wireless Devices
Faculty Advisor: Dr. Qing Liu

This project will apply artificial intelligence (AI) techniques for the design optimization of wireless devices, such as antennas and filters.  The student should be familiar with Matlab programming, and C++ or Java programming will be also helpful but not required.

Required Skills/Coursework: 

Deadline: Open until filled

Compensation Options: MS Project Exam

Expected Duration: Two semesters

Application link

GPU Computing for Electromagnetic Imaging 
Faculty Advisor: Dr. Qing Liu

Students interested in GPU computing are invited to participate in this for electromagnetic imaging project. The goal is to use GPU to greatly accelerate the computation in imaging. Interested students should have prior experience with C programming and are willing to learn and excel in CUDA implementation. 

Required Skills/Coursework: C Programming

Deadline: Open until filled

Compensation Options: MS Thesis Exam, MS Project Exam, Independent Study

Expected Duration: One semester with potential to extend 

Application link

Deep Learning for Object Identification and Mapping in Satellite Imagery
Faculty Advisor: Dr. Jordan Malof

Students will utilize existing deep learning approaches, as well as develop new approaches, for the problem of automatically identifying and mapping objects (e.g., buildings, roads, vehicles) in aerial imagery (e.g., satellite imagery). This is an exciting and rapidly developing field of study with many new problems that we wish to investigate. Students will have access to graphics processing units to evaluate their algorithms, as well as guidance from graduate students with substantial experience in deep learning algorithms and software (e.g., tensorflow with python).

Students are expected to perform research in the lab for (at least) two semesters via independent study. This can conclude in a masters project or thesis defense, and often results in one (or more) publications for the student, depending upon their commitment and motivation. Students are expected to commit ~15 hours per week to research, and to report their progress regularly. Successful students will gain substantial knowledge and experience with deep learning.  

Deadline: Open until filled

Compensation Options: MS Thesis Exam, MS Project Exam, Independent Study

Expected Duration: At least two semesters

Application link

Acousto-electromagnetic Metasurface
Faculty Advisor: Dr. Willie Padilla

Terahertz technology have attracted increasing attention for a large variety of applications, including biomedical spectroscopy, agriculture, security, astronomy, materials science and communications. However, much progress is hindered by the development of devices for dynamically tailoring terahertz radiation, such as amplitude, phase, polarization and direction. In order to achieve efficient terahertz modulation, the SMIE lab proposes to develop an acoustic wave controlled terahertz modulator utilizing an extremely high-Q resonance, termed bound-states-in-the-continuum. As sound is coupled to the discrete vibration modes of the free-standing metasurface, the deformation of the structure enables significant modulation of the scattering from the metasurface, leading to coded terahertz radiation.

We are looking for a candidate who has relevant knowledge and experience in at least two of the following aspects: optics, electromagnetics, microfabrication, spectrum analyzers and matlab.

Deadline: Open until filled

Compensation Options: MS Thesis Exam

Expected Duration: Two semesters

Application link

Metamaterial Coherent Perfect Absorber Detector
Faculty Advisor: Dr. Willie Padilla

Using new a novel metamaterial design and theory, a metasurface known as a Coherent Perfect Absorber (CPA) can be created that absorbs incoming radiation based on the phase and amplitude of a control beam. We are developing a detector and instrumentation based on this concept.
   
This project involves the experimental design, construction, and test of a benchtop terahertz metasurface-based detector system that operates with much lower size, weight, power, and cost than existing microwave systems. This can provide needed instruments for use in future millimeter-wave communication systems, terahertz imagers, and IR LIDAR systems.

Required/Preferred Courses Taken: Electromagnetics or optics

Required/Preferred Skills: Programming for data acquisition and instrument control. Experience with microwave instrumentation, and optical/quasi-optic systems is desired.

Deadline: Open until filled

Compensation Options: MS Thesis Exam

Expected Duration: Two semesters

Application link

Learning-Based Patient Scheduling in ER
Faculty Advisor: Dr. Miroslav Pajic

In collaboration with physicians from Duke ER, the goal of the project is to develop a learning-based recommendation system for scheduling patients in emergency rooms after initial triage is performed.

Deadline: N/A

Compensation Options: MS Thesis Exam, MS Project Exam, Independent Study

Expected Duration: Two semesters

Application link

Design of Robotic Assistant for Combat Casualty Care
Faculty Advisor: Dr. Miroslav Pajic

The goal of this project is to develop a prototype of a robot to facilitate combat casualty care. Specifically this robot will work in conjunction with a forward medic to both diagnose and treat major causes of battlefield death. The robot will utilize ultrasound to diagnose and treat causes of truncal hemorrhage. The initial phase of the project will focus on having the robot identify (using real-time ultrasound analysis) and compress the subclavian artery between its exit from the chest and the distal arm where a tourniquet can be placed. In addition, the robot should be capable of identifying pneumothorax and perform the initial steps of thoracic pigtail catheter placement.

The project will be done in tight collaboration with surgeons from Duke University Medical Center.

Required Skills/Coursework: C/C++ programming, experience with ROS

Deadline: N/A

Compensation Options: MS Thesis Exam, MS Project Exam, Independent Study, Paid ($15-$19/hr, dependent on skill level)

Expected Duration: Two semesters

Application link

Automatization of Retinal Image Analysis
Faculty Advisor: Dr. Miroslav Pajic

The retina is a constituent of the posterior eye segment. It is the inner most, light sensitive multi-layered tissue. The layers of neurosensory retina can be seen in cross-sectional histologic preparations. There are ten distinct layers, consisting mostly of neurons interconnected by synapses. The retinal pigment epithelium (RPE) is outer retinal monolayer of very metabolically active pigmented cells with multiple roles.

The goal of this project is to design image processing techniques and tools for automatic detection of normal and abnormal (e.g., with Age-related macular degeneration) RPE morphology in retinal images. The student will work directly with physicians at Duke Eye Center, with an opportunity for continued collaboration in this exciting field even after the project is completed.

Required/Preferred Courses Taken: image/signal processing 

Required Skills/Coursework: Matlab (required), python

Deadline: N/A

Compensation Options: MS Thesis Exam, MS Project Exam, Independent Study, Paid ($15-$19/hr, dependent on skill level)

Expected Duration: Two semesters

Application link

Ensuring Medication Compliance and Reconciliation in Rural Population
Faculty Advisor: Dr. Miroslav Pajic

In medicine, compliance (or adherence, capacitance) describes the degree to which a patient correctly follows medical advice. Although the term applies to other situations (e.g., medical device use, self-care), most commonly it refers to medication or drug compliance. Non-compliance is a major obstacle to the effective delivery of health care. Efforts to improve compliance have been aimed at simplifying medication packaging, providing effective medication reminders, improving patient education, and limiting the number of medications prescribed simultaneously.

One of the major problems we face in rural healthcare is medication adherence, especially with patients having multiple medications at home prescribed by multiple providers. These patients do not have a method to accurately report to the physician what medications they are taking. Due to HIPAA, the primary care provider computer, other service providers’ computers and the pharmacy computer cannot talk. Patients would greatly benefit if a method can be established tracking all of their prescriptions, reminding them to take the right medicine at the right time, understand which medicines are for what conditions, and which medicines should never be taken at the same time - despite the fact that they have been prescribed to them (by non-communicating providers). In addition, they need a way to know if they have already taken their medication. This is especially challenging in rural areas, where cell service and internet are not always available. These patients would benefit from a mobile repository of all their prescribed medications available to all healthcare providers involved in their care. The benefit would be even greater if drug interactions and warnings could be generated by the system, as well as reminders and possible confirmation of taking prescribed doses in prescribed intervals.

The goal of this project is to evaluate HIPAA and safety requirements for the aforementioned system and to develop and test an initial prototype in collaboration with West Virginia School of Osteopathic Medicine, Lewisburg, WV. Specific challenges that needs to be addressed include: a) How to provide privacy and security guarantees? b) How can we ensure fault tolerant operation in the presence of limited communication infrastructure, with intermitted network access (using various communication standards)? c) How can we ensure that the developed technology takes into account limited technical understanding of some of the users?

Required Skills/Coursework: Any relevant or prior experience 

Deadline: Open until filled

Compensation Options: MS Thesis Exam

Expected Duration: Two semesters

Application link

Tracking and Coordinating Pediatric Care for Neonatal Abstinence Syndrome Infants
Faculty Advisor: Dr. Miroslav Pajic

Due to an ongoing opioid epidemic, the number of babies suffering from neonatal abstinence syndrome is increasing. Fetal and neonatal addiction and withdrawal are a result of the mother's dependence on drugs during pregnancy. Neonatal abstinence syndrome patients require continued multidisciplinary care. At a minimum, professionals involved in this care include obstetricians, neonatologists, pediatricians, nurses, nutritionists, mental health professionals, social workers, substance abuse counselors, and child development specialists.

Due to geographic and economic disadvantages, multidisciplinary treatment centers are not readily available to rural patients. Keeping track of all the required services, compliance and follow-ups would be in the best interest of these children. Furthermore, keeping track of all the services and appointments required for these patients is a challenge under normal circumstances and with a supportive family. However, more often than not, these infants are being transferred between multiple state system foster care providers and the biological parents for prolonged periods of time. The primary care providers, as well as other services, tend to change with each geographical and/or legal guardian change. This adds an unnecessary level of burden to providing care for these children and may contribute to developmental delays. It would be extremely beneficial to have a personalized central repository of all the relevant health records, ongoing and required medical services, as well as progress notes that would follow the child regardless of their geographical location or foster (parent) and medical provider status. Without such a repository, there is currently no way to keep the continuum of care for this child by a newly established primary care provider or a social worker.

The goal of this project is to evaluate HIPAA and safety requirements for the aforementioned system and to develop and test an initial prototype in collaboration with West Virginia School of Osteopathic Medicine, Lewisburg, WV. Specific challenges that needs to be addressed include: a) How to provide privacy and security guarantees? b) How can we ensure fault tolerant operation in the presence of limited communication infrastructure, with intermitted network access (using various communication standards)? c) How can we ensure that the developed technology takes into account limited technical understanding of some of the users?

Required Skills/Coursework: Any relevant or prior experience 

Deadline: Open until filled

Compensation Options: MS Thesis Exam

Expected Duration: Two semesters

Application link

Securing Autonomous Systems in Contested Environments
Faculty Advisor: Dr. Miroslav Pajic

Most of existing control and autonomous systems have not been built with security in mind. Even with the proliferation of different networking technologies and the use of more open control architectures, until recently their security has usually been an afterthought. Yet, with the advance of cyber-physical systems (CPS), the tight interaction between information technology and the physical world have made control components of CPS vulnerable to attack vectors well beyond the standard cyber attacks. In the last few years, several incidents have clearly illustrated susceptibility of CPS to attacks, raising attention to serious security challenges. These include the StuxNet virus attack on an industrial SCADA system, as well as attacks on modern cars and RQ-170 Sentinel US drone that was captured in Iran.

Relying exclusively on cyber-security techniques for securing CPS is insufficient. For example, GPS spoofing attacks to misguide a yacht or unmanned aerial vehicle (UAV) of their routes have been demonstrated in recent years. Consequently, the goal of this project is to show how combination of security-aware control policies can be used to increase security guarantees in autonomous systems operating in contested environments. The scope of this project will be to secure the video-based navigation of an UAV, by exploiting recently developed control techniques such as attack-resilient state estimation and active attack detection.

Required Skills: C, C++, knowledge of ROS is a plus 

Deadline: Open until filled

Compensation Options: MS Thesis Exam

Expected Duration: Two semesters

Application link

Ensuring Timeliness in Safety-Critical IoT Systems
Faculty Advisor: Dr. Miroslav Pajic

To manage complexity of modern Internet-of-Things (IoT) systems, employed platforms require the use of efficient operating systems (OS) that provide timing, performance and security guarantees, as well as support for key IoT networking and communication technologies. One example is the latest mbed OS 5.1, which incorporates a Real-Time Operating System (RTOS) in order to provide native real-time thread support to the applications running on top of the RTOS.

The RTOS core is based on the widely used open-source CMSIS-RTOS RTX - an established kernel that can support threads and other RTOS services on very resource constrained devices. However, the underlying scheduling is based on thve well known round-robin policy, effectively preventing the use of this OS in development on safety critical IoT applications where timeliness is the first class citizen. In these systems (e.g., in industrial, medical, automotive, avionics and many other application domains), the ability to prioritize a critical task at any given moment in time, and guarantee availability of resources required to complete that task is essential.

Consequently, the goal of this project is to extend the open-source scheduler for the RTOS and provide support for a variety of commonly used real-time scheduling policies that take into account thread criticality and execution deadline constraints. The developed RTOS will then be deployed and evaluated in several case studies in automotive, industrial automation, and medical device domains, allowing the student to both learn foundations of the RTOS development as well as its use in design of real-world systems (e.g., electric vehicles, cloud-based reconfigurable industrial systems, networked implantable medical devices).

Required Skills: C, C++, knowledge of embedded systems 

Deadline: Open until filled

Compensation Options: MS Project Exam

Expected Duration: One semester with potential to extend

Application link

Software Design for Autonomous Formula F1/10 vehicles
Faculty Advisor: Dr. Miroslav Pajic

The F1/10 competition focuses on creating a meaningful and challenging design experience for students. The competition involves designing, building, and testing an autonomous 1/10th scale F1 race car (capable of speeds in excess of 40MPH) all while learning about perception, planning, and control for autonomous navigation. The students in Duke team would start from the initial vehicle design and ROS-based software that provides baseline autonomous vehicle operation. More information available at: http://f1tenth.org

Required Skills: C, C++, Knowledge of ROS is a plus 

Deadline: Open until filled

Compensation Options: MS Project Exam

Expected Duration: One semester with potential to extend

Application link

UPP2SF Tool development
Faculty Advisor: Dr. Miroslav Pajic

Model-Driven Design (MDD) of cyber-physical systems advocates for design procedures that start with formal modeling of the real-time system, followed by the model’s verification at an early stage. The verified model must then be translated to a more detailed model for simulation-based testing and finally translated into executable code in a physical implementation. As later stages build on the same core model, it is essential that models used earlier in the pipeline are valid approximations of the more detailed models developed downstream. The focus of this effort is on the design and development of a model translation tool, UPP2SF, and how it integrates system modeling, verification, model-based WCET analysis, simulation and code generation into an MDD-based framework. UPP2SF should facilitate automatic conversion of verified timed automata-based models (in UPPAAL) to models that may be simulated and tested (in Simulink/Stateflow). The existing tool revision should be based on the design rules to ensure the conversion is correct, efficient and applicable to a large class of models.

Required Skills: Matlab

Deadline: Open until filled

Compensation Options: MS Project Exam

Expected Duration: One semester with potential to extend

Application link

Artifact-Resistant Bioamplifier 
Faculty Advisor: Dr. Angel Peterchev

In research and clinical applications such as transcranial magnetic stimulation, brain machine interface, and closed-loop stimulation there is increasing need to record brain signals (electroencephalography, local field potentials, single neuron spiking) immediately after electric or magnetic stimulation of the brain. However, the electromagnetic artifact corrupts the neural recording after the stimulus pulses. The objective of this project is to develop a neural amplifier that recovers rapidly (< 1 ms) after a stimulus pulse, opening a window into the neural dynamics in the immediate aftermath of stimulation.
   
Tasks involve specification, circuit design, simulation (e.g. in PSPICE), PCB design, soldering, wiring, debugging, testing, and documentation of a rapid recovery bioamplifier.
   
The project provides an opportunity to interact with an interdisciplinary team of researchers.

Required Coursework: Microelectronic circuits/analog electronics

Required Skills: Hands on experience with electronic circuit design, simulation, construction, testing, and debugging

Deadline: Floating

Compensation Options: MS Thesis Exam, MS Project Exam, Independent Study, Paid ($15-$19/hr, dependent on skill level)

Expected Duration: One semester with potential to extend

Additional Application Documents: Undergraduate and graduate (if available) transcripts (can be unofficial)

Application link

Community Detection with Structured Stochastic Block Models
Faculty Advisor: Dr. Galen Reeves

The problem of community detection is to find important clusters in a network. Specific examples include finding like-minded people in a social network and discovering the hierarchical relationships in organizations from observed behavior. The state-of-the art algorithms for this problem are based on spectral clustering techniques. The goal of this project is to study improved algorithms based on a divide-and-conquer approach. The work will require the implementation of the new approach and comparison with existing methods on both synthetic and representative real-world datasets.

The project is appropriate for a student who has a strong background in linear algebra (ECE 590), probability (ECE 581), and machine learning (ECE 681 or STA 561). The work will require programming in MATLAB. The scope of the project is one to two semesters.

Deadline: March 1, 2018

Compensation Options: MS Thesis Exam, MS Project Exam, Independent Study

Expected Duration: One semester with potential to extend

Application link

Universal Ambulatory Monitoring System 
Faculty Advisor: Dr. Rabih Younes

Doctors sometimes need to track a patient's physiological readings and activities for a length of time while the patient is performing their normal daily routine outside of the clinic. This process is known as ambulatory Monitoring (AM). For this project, the student is expected to collect data from existing literature and through surveying medical personnel familiar with AM about what is needed in an ideal AM system (wearability requirements, activities needed to be recognized, physiological readings needed to be tracked, etc.). They should also check -- for research purposes -- whether existing publicly available datasets contain adequate information for all the needed activities to be recognized in an appropriate real-life environment. If time permits, it is preferred that the student builds a wearable prototype representing the ideal AM system (only the wearable parts; no need for activity recognition at this point), tests its wearability using a sample of users, and draws conclusions for future AM systems' design.

Deadline: Open until filled

Compensation Options: MS Thesis Exam, MS Project Exam, Independent Study

Expected Duration: One semester with potential to extend

Application link

Garment-Independent Wearable Motion Capture System
Faculty Advisor: Dr. Rabih Younes

After getting familiar with the literature and available similar products, the student is expected to design and build a working prototype of a wearable motion capture system that can be transferred between garments and can ideally be embedded unobtrusively into everyday clothing. The system should be able to capture the movement of the main body limb segments. Such systems could be used for activity recognition applications in a variety of domains.

Required/Preferred Skills: Experience in embedded systems

Deadline: Open until filled

Compensation Options: MS Thesis Exam, MS Project Exam, Independent Study

Expected Duration: One semester with potential to extend

Application link

Wearable Motion Capture System Using Stretch and Bend Sensors
Faculty Advisor: Dr. Rabih Younes

After getting familiar with the literature and available products, the student is expected to design and build a working prototype of a wearable motion capture system that uses stretch and bend sensors embedded in clothing to detect body joints' angles. Such systems could be used for unobtrusive activity recognition applications in a variety of domains.

Required/Preferred Skills: Experience in embedded systems

Deadline: Open until filled

Compensation Options: MS Thesis Exam, MS Project Exam, Independent Study

Expected Duration: One semester with potential to extend

Application link

Road Worker Car Alert System
Faculty Advisor: Dr. Rabih Younes

Many road workers get injured or killed by cars traveling on the road due to miscommunication between the oncoming car and the worker. After getting familiar with the literature, the student is expected to design and build a working prototype that detects an oncoming car in the worker's lane and alerts the worker. Detecting the car can be done using any effective method, including the use of a camera. Various effective methods of alerting the worker -- while considering their working conditions and environment, e.g., surrounding sounds, day/night time, etc. -- should be studied and tested.

Required/Preferred Skills: Experience in embedded systems

Deadline: Open until filled

Compensation Options: MS Thesis Exam, MS Project Exam, Independent Study

Expected Duration: One semester with potential to extend

Application link

Portable Bicycle Protective Gear
Faculty Advisor: Dr. Rabih Younes

Many people choose not to wear a helmet and other protective gear while riding their bicycles because it is bulky and inconvenient to carry around wherever they go after their ride. For this project, the student is expected to design and build a working prototype of a collapsible/portable bicycle helmet. If time permits, the student should design other portable bicycle protective gear items (other than the helmet) and include visible brake lights and turn signals on the gear.

Required/Preferred Skills: Experience in 3D printing

Deadline: Open until filled

Compensation Options: MS Thesis Exam, MS Project Exam, Independent Study

Expected Duration: One semester with potential to extend

Application link

A Wearable Benefiting People with Sensory Needs
Faculty Advisor: Dr. Rabih Younes

This is an open-ended project that involves designing and building a working prototype of a wearable system that can help mitigate some sensory problems that people might have, such as those diagnosed with Generalized Anxiety Disorder (GAD) and Autism Spectrum Disorder (ASD). One example of such systems could be a compression garment that gets automatically triggered when the person is anxious.

Required/Preferred Skills: Experience in embedded systems and preferably machine learning

Deadline: Open until filled

Compensation Options: MS Thesis Exam, MS Project Exam, Independent Study

Expected Duration: One semester with potential to extend

Application link

Automatic CAD Drawings Grading Software
Faculty Advisor: Dr. Rabih Younes

After getting familiar with available products and their weaknesses, the student is expected to design and implement a software that can automatically grade students' 2D CAD drawings. The student should study the types of mistakes that instructors usually look for when comparing a student's drawing to the correct one. The student can work on extracting information from the CAD files themselves or from exported images of the drawings.

Required/Preferred Skills: Experience in computer vision

Deadline: Open until filled

Compensation Options: MS Thesis Exam, MS Project Exam, Independent Study

Expected Duration: One semester with potential to extend

Application link

Robot Motion Planning in Partially Known Environments under High-Level Temporal Tasks
Faculty Advisor: Dr. Michael Zavlanos

This project focuses on motion and task planning of a mobile robot in a partially-known and dynamic environment. Specifically, the environment is partitioned in regions of interest and the robot can move between those regions using different motion primitives (e.g., move forward, move backward, turn right, turn left), which are subject to uncertainty due to actuation and sensing noise. This means that, by performing a motion primitive at one region, the robot may end up in several other regions with different probabilities. Moreover, these regions are labeled by properties of interest for the robotic task. For instance, for an office servant robot, these properties might be "this is an office room", "there is an ongoing meeting in the meeting room", "this corridor is occupied by obstacles", "new mail is available in the mail room". These labels are also uncertain and can only be predicated probabilistically. For instance, the probability that "there is a meeting now in the meeting room" is 80%; or the probability that "this corridor is occupied by obstacles" is 40%. The high-level task assigned to the robot is specified as a Linear Temporal Logic (LTL) formula over these aforementioned properties. LTL is expressive enough to specify many control tasks of practical interest, including reachability, safety, and liveness. For example, office errands such as "the robot should always deliver the mail from the mail room to the office room" and "the robot should surveil all corridors and avoid obstacles" can be expressed easily using LTL. Since the environment is only considered to be partially-known, along with high-level task planning, the robot also needs to create a map of the environment and locate itself within this map. This process is called Simultaneous Localization and Mapping (SLAM) in the literature. It also needs to react to contingent changes in the environment, such as moving humans and closing/opening doors.
   
Interested students will get involved in the development of algorithms and/or their experimental validation. The robot platform available in our lab is the ClearPath Jackal robot equipped with Velodyne laser sensors, and the software platform is the Robot Operating System (ROS). Students will obtain experience in controls, robotics, and formal methods (LTL planning), as well as in the mathematical and computational techniques required for the study of such systems. Students with a background in Mechanical Engineering, Electrical Engineering, or Computer Engineering, are encouraged to apply. For more information, please contact Prof. Michael M. Zavlanos.

Deadline: Apply any time

Compensation Options: MS Thesis Exam, MS Project Exam

Expected Duration: Two semesters or more

Application link

Robot Motion Planning in Wirelessly Connected and Uncertain Environments
Faculty Advisor: Dr. Michael Zavlanos

The focus of this project is on motion planning of a mobile robot in a networked environment with the objective to reliably deliver information to an end user. Future "smart" buildings, cities and, generally, infrastructure, will comprise of many sensors and actuators that are interconnected via dedicated wireless networks to form a networked control system. For example, sensors can sense the presence of people in different rooms of a building and control the temperature in a floor to save energy and provide a pleasant environment, or robots can visit patients in a hospital, deliver medicines and physician instructions, and record their vital signs. In every case, sensors and/or robots will need to be connected with each other, a control center, and possibly a human user, so that the integrated system can collectively coordinate its actions. For example, robot-to-robot communication in a hospital is necessary to avoid collisions and schedule tasks (e.g., robot 1 should not deliver medicine to a patient before robot 2 has taken their vital signs), while robot-to-user communication is needed to enable physicians to monitor patients. This connectivity can be achieved through dedicated wireless networks that outfit the environments in which the robots, sensors, and users operate. The robots and relay nodes in the network have limited communication capabilities due to power constraints and environmental interference, so this information needs to be propagated back to the user in a multi-hop way. Optimal operating points of the network need to be determined, that satisfy a number of constraints that ensure consistency of the operating points, as well as external constraints like minimum guaranteed throughputs or maximum power consumptions. Variables of this optimization typically depend on the robot positions, which calls for frequent re-optimization due to mobility. Uncertainty in the environment (geometry and communications) introduces additional complexity that affects system performance. If a model of this uncertainty is unknown, then the robots need to learn their environment at the same time that they compute optimal motion plans in it. A possible solution to this problem is to use reinforcement learning techniques.
   
Interested students will get involved in the development of algorithms and/or their experimental validation. The robot platform available in our lab is the ClearPath Jackal robot equipped with Velodyne laser sensors, and the software platform is the Robot Operating System (ROS). We also have developed dedicated wireless networks consisting of TI Sensortag nodes controlled by Raspberry Pi's, that will serve in testing the proposed algorithms. Students will obtain experience in controls, robotics, and wireless networking, as well as in the mathematical and computational techniques required for the study of such systems. Students with a background in Mechanical Engineering, Electrical Engineering, or Computer Engineering, are encouraged to apply. For more information, please contact Prof. Michael M. Zavlanos. 

Deadline: Apply any time

Compensation Options: MS Thesis Exam, MS Project Exam

Expected Duration: Two semesters or more

Application link

Localizing Sound Sources in Complex Environments using Mobile Robot Sensors
Faculty Advisor: Dr. Michael Zavlanos

The focus of this project is on localizing sound sources in real-time using teams of mobile robots. While localization of sound sources in the open space can be efficiently done using standard triangulation techniques, this is certainly not the case in cluttered environments, such as cities or indoor environments. In this case, a mathematical model of the sound (wave) propagation can significantly help with localization. Specifically, we assume that there are one or more sound sources in a building, and we utilize the Acoustic Wave Equation (AWE) to model the propagation of the acoustic (pressure) waves. We discretize the AWE using the Finite Element method (FEM), applying appropriate boundary conditions. The resulting discrete wave model associates the phase and magnitude of the waves at the grid points of the FEM mesh with the possible locations and intensities of the sources. Assume now that the mobile robots, equipped with microphone sensors, can visit some of the locations in the FEM grid and measure the pressure. The question that we aim to answer is whether, based on these measurements, we can infer the location and intensity of the sources. The great challenge is that the number of measurements is typically limited due to a limited number of available sensors and the limited time that the sensors have in their possession to complete their task. This means that the problem is under-determined, and novel algorithms and techniques are needed to solve it. Additional challenges arise when the measurements are corrupted by sensor noise or the AWE does not perfectly model the physics of the problem, as is often the case in practice.
   
Interested students will get involved in the development of algorithms and/or their experimental validation. The robot platform available in our lab is the ClearPath Jackal robot equipped with Velodyne laser sensors, and the software platform is the Robot Operating System (ROS). Students will obtain experience in controls, robotics and sensing, as well as in the mathematical and computational techniques required for the study of such systems. Students with a background in Mechanical Engineering, Electrical Engineering, or Computer Engineering, are encouraged to apply. For more information, please contact Prof. Michael M. Zavlanos. 

Deadline: Apply any time

Compensation Options: MS Thesis Exam, MS Project Exam

Expected Duration: Two semesters or more

Application link

Controlling Robotic Camera Networks
Faculty Advisor: Dr. Michael Zavlanos

The goal of this project is to control robotic sensor networks so that they can autonomously and reliably explore and build maps of unknown and uncertain environments. Specifically, we consider a team of mobile robots with the objective to explore and reconstruct a complete 3D model of an unknown environment with a pre-specified tolerance on the accuracy of the reconstruction. By dense 3D reconstruction here we refer to the problem of estimating the 3D coordinates of all surfaces captured by the sensors mounted on the robots. Robots that can sense the surface coordinates using, e.g., their on-board cameras, make noisy measurements of their location. Then, these measurements need to be fused by, e.g., a Kalman filter to improve on the localization accuracy of the coordinates. In practice, the robots cannot sense the whole environment without moving, therefore, we are faced with an active sensing problem. To achieve this task, every robot requires a collection of tightly integrated sensing, communication, and control capabilities. The challenge is in enabling efficient coordination and decomposition of roles within the team, which can result in significant improvements in area coverage and utilization of resources. For this, new control architectures are needed that allow the robots to share their measurements of the environment, the parts of the environment that they are responsible for observing, and their particular roles within the team. Once the exploration and 3D reconstruction of the environment is complete, the robotic team can benefit from the generated models in tasks such as inspection, surveillance, search, and robot-guided evacuation.
   
Interested students will get involved in the development of algorithms and/or their experimental validation. The robot platform available in our lab is the ClearPath Jackal robot equipped with Velodyne laser sensors, and the software platform is the Robot Operating System (ROS). Experiments will also involve monocular or binocular camera systems. Students will obtain experience in controls, robotics and sensing, as well as in the mathematical and computational techniques required for the study of such systems. Students with a background in Mechanical Engineering, Electrical Engineering, or Computer Engineering, are encouraged to apply. For more information, please contact Prof. Michael M. Zavlanos. 

Deadline: Apply any time

Compensation Options: MS Thesis Exam, MS Project Exam

Expected Duration: Two semesters or more

Application link