2021 Research Projects
Projects are posted below; new projects will continue to be posted. To learn more about the type of research conducted by undergraduates, view the archived symposium booklets and search the past SURF projects.
This is a list of research projects that may have opportunities for undergraduate students. Please note that it is not a complete list of every SURF project. Undergraduates will discover other projects when talking directly to Purdue faculty.
You can browse all the projects on the list or view only projects in the following categories:
Big Data/Machine Learning (25)
4D Materials Science - X-ray Microtomography, Image Analysis, and Machine Learning
Description:
The student will be working on state-of-the-art characterization techniques, such as x-ray microtomography and correlative microscopy of high performance materials. The project will involve image analysis and machine learning algorithms for efficiently and accurately analyzing the x-ray tomography datasets.
Research categories:
Big Data/Machine Learning, Composite Materials and Alloys, Material Modeling and Simulation, Material Processing and Characterization
Preferred major(s):
Materials science and engineering, mechanical engineering, and/or computer engineering
Desired experience:
Microstructural Characterization
Computer programming/coding
Image analysis
Junior or Seniors are particularly encouraged to apply.
School/Dept.:
MSE
Professor:
Nik
Chawla
More information: https://engineering.purdue.edu/MSE/people/ptProfile?resource_id=239946
Accelerator Architecture Lab at Purdue (AALP): Optimizing Simulators for Advanced Processor Development
Description:
Modern processor design and research in both industry and academia rely on early-stage modeling and simulation. The ideas that make up every CPU, GPU, and accelerator you have ever used started their life in cycle-level C++ processor simulation. Today, much of the progress we see in the processor industry comes from specialization (i.e. Google’s TPU) and acceleration (i.e. GPGPU computing, such as NVIDIA’s CUDA). The Accelerator Architecture Lab at Purdue (AALP) develops a popular open-source GPU simulator called Accel-Sim that models modern NVIDIA GPUs executing compute workloads, like those commonly used in machine learning. Intimate details of the actions taken on each cycle of a real processor are modeled in Accel-Sim’s C++ code, such that new architectural ideas can be explored and empirically evaluated on real workloads. Simulating such an advanced, scaled system consumes a significant amount of CPU-time and memory (for some workloads - on the order of a TB!). This summer project involves understanding the high-level design of GPUs, the basic operation of CUDA, and optimizing the simulator infrastructure to consume orders of magnitude less memory at runtime, enabling larger and more complex workloads to be simulated. The successful completion of the project will see the student contribute to a highly-visible piece of open-source software and develop foundational skills to work at hardware design companies like Intel, AMD, NVIDIA, Qualcomm, Microsoft, and many others.
More information: https://accel-sim.github.io
Group Website: https://engineering.purdue.edu/tgrogers/group/aalp.html
More information: https://accel-sim.github.io
Group Website: https://engineering.purdue.edu/tgrogers/group/aalp.html
Research categories:
Big Data/Machine Learning, Deep Learning, Other
Preferred major(s):
Computer Engineering, Computer Science
Desired experience:
C/C++ and Python experience
Knowledge of computer architecture a plus
School/Dept.:
ECE
Professor:
Timothy
Rogers
More information: https://engineering.purdue.edu/tgrogers/
Accelerator Architecture Lab at Purdue (AALP): Modeling Diverse GPU Architectures in C++ Simulation
Description:
Modern processor design and research in both industry and academia rely on early-stage modeling and simulation. The ideas that make up every CPU, GPU, and accelerator you have ever used started their life in cycle-level C++ processor simulation. Today, much of the progress we see in the processor industry comes from specialization (i.e. Google’s TPU) and acceleration (i.e. GPGPU computing, such as NVIDIA’s CUDA). The Accelerator Architecture Lab at Purdue (AALP) develops a popular open-source GPU simulator called Accel-Sim that models modern NVIDIA GPUs executing compute workloads, like those commonly used in machine learning. Intimate details of the actions taken on each cycle of a real processor are modeled in Accel-Sim’s C++ code, such that new architectural ideas can be explored and empirically evaluated on real workloads. Although the basic design of GPUs share many similarities across generations and vendors, each part and company have subtle differences that can greatly affect their performance on critical applications, such as those found in machine learning. This summer project involves understanding the high-level design of GPUs, the basic operation of CUDA, and modeling the performance of bleeding-edge GPU parts from both NVIDIA (an Ampere A100) and AMD. The successful completion of the project will see the student contribute to a highly-visible piece of open-source software and develop foundational skills to work at hardware design companies like Intel, AMD, NVIDIA, Qualcomm, Microsoft, and many others.
More information: https://accel-sim.github.io
Group Website: https://engineering.purdue.edu/tgrogers/group/aalp.html
More information: https://accel-sim.github.io
Group Website: https://engineering.purdue.edu/tgrogers/group/aalp.html
Research categories:
Big Data/Machine Learning, Deep Learning, Other
Preferred major(s):
Computer Engineering, Computer Science
Desired experience:
C/C++.
Computer Architecture and Digital Design Background.
Students should be comfortable reading assembly language (ECE 362 equivalent)
School/Dept.:
ECE
Professor:
Tim
Rogers
More information: https://engineering.purdue.edu/tgrogers/
Advanced Vehicle Automation and Human-Subject Experimentation
Description:
Vehicle automation is developing at a rapid rate worldwide. While fully autonomous vehicles will be pervasive on the roadway for the next several years, many research initiatives are currently underway to understand and design approaches that will make this technology a future reality. This work ranges from the development of sensors and controls algorithms, to schemes for networks and connectivity, to the creation of in-vehicle driver interfaces. Here, one component that is key to the effective design of next-generation autonomous driving systems is the human driver and, thus studying human-vehicle interactions and defining driver’s roles/tasks will be important.
The goal of this project is to describe and measure the ways in which a person interacts with advanced vehicle automation. Students will assist with multiple activities and will learn a combination of the following: how to a) develop/code advanced driving simulation scenarios, b) collect driving performance data, c) analyze driver and performance data (using methods via software packages), and d) write technical reports and/or publications. Students may also gain experience collecting and analyzing complementary physiological measures, such as eye movement data, brain activity, skin conductance, and heart rate. The students will work closely with graduate student mentors to enhance learning.
The goal of this project is to describe and measure the ways in which a person interacts with advanced vehicle automation. Students will assist with multiple activities and will learn a combination of the following: how to a) develop/code advanced driving simulation scenarios, b) collect driving performance data, c) analyze driver and performance data (using methods via software packages), and d) write technical reports and/or publications. Students may also gain experience collecting and analyzing complementary physiological measures, such as eye movement data, brain activity, skin conductance, and heart rate. The students will work closely with graduate student mentors to enhance learning.
Research categories:
Big Data/Machine Learning, Learning and Evaluation, Other
Preferred major(s):
Industrial Engineering, Mechanical Engineering, and/or Computer Science Engineering
Desired experience:
Human Factors, Matlab, transportation, some experience in statistics, some computer programming and machine learning experience (in any language)
School/Dept.:
Industrial Engineering
Professor:
Brandon
Pitts
More information: https://engineering.purdue.edu/NHanCE
Advancing Pharmaceutical Manufacturing through Process Modeling and Novel Sensor Development
Description:
The limitations of batch processes to manufacture pharmaceutical products such as tablets, coupled with advances in process analytical technology (PAT) tools have led to a shift towards continuous manufacturing (CM), which represents the future of the pharmaceutical industry.
The flexibility of continuous processes can reduce wasted materials and facilitate scale-up more easily with active plant-wide control strategies. Ultimately, this results in cheaper and safer drugs, as well as a more reliable drug supply chain.
To fully realize the benefits of continuous manufacturing, it is important to capture the dynamics of the particulate process, which can be more complex than common liquid-based or gas-based chemical processes. In addition, effective fault detection and diagnostic systems need to be in place, so intervention strategies can be implemented in case the system goes awry.
All of these require the development of process models that leverages knowledge of the process and big data. Students in this part of the research would have a chance to gain experience in industry-leading software for process modeling (e.g. Simulink, gProms, OSI PI) and machine learning (e.g. Matlab, Python, .NET).
Most importantly, they would be able to test the models in Purdue's Newly Installed Tablet Manufacturing Pilot Plant at the FLEX Lab in Discovery Park.
Another important aspect of the research are sensors. In this project, we will be investigating the feasibility of two novel sensors: a capacitance-based sensor to measure mass flow, and a particle imaging sensor that directly captures images of the powder particles to give you a particle size distribution. We will be testing these sensors together with NIR and Raman sensors, and use data analytics to determine their feasibility of application in a drug product manufacturing process.
The flexibility of continuous processes can reduce wasted materials and facilitate scale-up more easily with active plant-wide control strategies. Ultimately, this results in cheaper and safer drugs, as well as a more reliable drug supply chain.
To fully realize the benefits of continuous manufacturing, it is important to capture the dynamics of the particulate process, which can be more complex than common liquid-based or gas-based chemical processes. In addition, effective fault detection and diagnostic systems need to be in place, so intervention strategies can be implemented in case the system goes awry.
All of these require the development of process models that leverages knowledge of the process and big data. Students in this part of the research would have a chance to gain experience in industry-leading software for process modeling (e.g. Simulink, gProms, OSI PI) and machine learning (e.g. Matlab, Python, .NET).
Most importantly, they would be able to test the models in Purdue's Newly Installed Tablet Manufacturing Pilot Plant at the FLEX Lab in Discovery Park.
Another important aspect of the research are sensors. In this project, we will be investigating the feasibility of two novel sensors: a capacitance-based sensor to measure mass flow, and a particle imaging sensor that directly captures images of the powder particles to give you a particle size distribution. We will be testing these sensors together with NIR and Raman sensors, and use data analytics to determine their feasibility of application in a drug product manufacturing process.
Research categories:
Big Data/Machine Learning, Chemical Unit Operations, Material Processing and Characterization
Preferred major(s):
Chemical Engineering (but other majors are also welcome)
Desired experience:
Basic skills for MATLAB and powder characterization would be a plus, but they are not necessary. The student should be safety conscious, self-motivated, and can work with minimal supervision. Aptitude for mastering the use of gadgets is desired, as well as the ability to understand research papers, documents, and manuals.
Any student who prefers a combination of simulation/modeling and hands-on pilot plant work is welcome. Moreover, this project is ideal for a student who is interested in a career in pharma or in powder manufacturing.
School/Dept.:
Davidson School of Chemical Engineering
Professor:
Gintaras
Reklaitis
Analyzing educational teamwork dataset using quantitative and NLP techniques
Description:
Teamwork is an essential competency highly valued by both academia and industry, especially for engineers who usually work in a small group. With tens of years' development, our research group, the Comprehensive Assessment of Team Member Effectiveness (CATME), had collected millions of survey data, including peer comments. The selected SURF student will join our research group to assist with data cleaning, preparation, and analysis for educational or technical research related to teamwork, and perhaps NLP (NLP is not necessary but a plus).
Research categories:
Big Data/Machine Learning, Deep Learning, Learning and Evaluation, Other
Preferred major(s):
ECE, CS, IE, education, social science, management, linguistics, and others
Desired experience:
data analysis experience with R, Python, and etc.; familiar with NLP and software programming would be a plus.
School/Dept.:
Engineering Education
Professor:
Matthew
Ohland
More information: https://info.catme.org/
Automatically Detecting and Fixing Software Bugs and Vulnerabilities
Description:
In this project, we will develop cool machine learning approaches to automatically learn bug/vulnerability patterns and fix patterns from historical data to detect and fix software bugs and security vulnerabilities. This project is partially funded by a Facebook Research Award (https://research.fb.com/programs/research-awards/proposals/probability-and-programming-request-for-proposals/).
Earlier work can be found here: https://www.cs.purdue.edu/homes/lintan/publications/deeplearn-tse18.pdf
Earlier work can be found here: https://www.cs.purdue.edu/homes/lintan/publications/deeplearn-tse18.pdf
Research categories:
Big Data/Machine Learning, Cybersecurity, Deep Learning, Other
Preferred major(s):
Compuer Science; Computer Engineering
Desired experience:
Good programming skills and strong motivation in research are required. Background in security or machine learning is a plus.
School/Dept.:
Computer Science
Professor:
Lin
Tan
More information: https://www.cs.purdue.edu/homes/lintan/
Describing the collective motion of dislocations in metals
Description:
The collective behavior of dislocations (line defects) in crystals is not well understood. This is somewhat strange considering that this collective behavior is the physical origin of deformation in many crystalline materials. The only tool that we currently have to study this involves simulating how individual dislocations move in a crystal. However, we are creating a theory that treats these dislocations like a fluid, as a density field.
We have two projects available, please apply for this position if you are interested in either one.
• One project will involve simulating dislocations in face centered cubic metals to extract statistical information about how they form junctions. This junctions are the physical basis of work-hardening, and this statistical information will allow us to incorporate junctions into the density-based, fluid-like model.
• Another project will involve simulating x-ray diffraction patterns in face-centered cubic metals containing dislocations in order to identify signals relevant to the fluid-like properties of the dislocations. Basic machine learning techniques will be used to identify these signals. No experience with x-ray diffraction or machine learning is needed. These results will allow experimentalists at our national labs to measure the fluid-like properties of dislocations in a lab rather than through simulations.
We have two projects available, please apply for this position if you are interested in either one.
• One project will involve simulating dislocations in face centered cubic metals to extract statistical information about how they form junctions. This junctions are the physical basis of work-hardening, and this statistical information will allow us to incorporate junctions into the density-based, fluid-like model.
• Another project will involve simulating x-ray diffraction patterns in face-centered cubic metals containing dislocations in order to identify signals relevant to the fluid-like properties of the dislocations. Basic machine learning techniques will be used to identify these signals. No experience with x-ray diffraction or machine learning is needed. These results will allow experimentalists at our national labs to measure the fluid-like properties of dislocations in a lab rather than through simulations.
Research categories:
Big Data/Machine Learning, Material Modeling and Simulation, Material Processing and Characterization, Nanotechnology
Preferred major(s):
Physics, Mathematics, Materials Science
Desired experience:
Calculus 3 (vector calculus), familiarity with basic statistical concepts
School/Dept.:
Materials Engineering
Professor:
Anter
EL-AZAB
More information: Not yet
Developing Computational Methods to Classify Unlabeled Reactions Using Large Data Sets
Description:
The ability to understand how chemical structure and conditions (i.e., chemical reaction class) affect reactions is fundamental to generalizing chemical transformations to new conditions and substrates. This ability opens up new ways to simulate and predict chemical behavior. Although reaction classes have historically been based on hypothetical mechanisms or the presence of specific combinations of reactive groups, there is a pressing need to develop empirical methods for extracting reaction classes from reaction data generated by automated experimentation and computations. In this research project, students will learn how to use data science techniques to develop computational methods to automatically extract reaction classes from chemical data in a manner that can be used to predict reactivity in other contexts. Several approaches are possible and encouraged for reaching this goal, including unsupervised learning algorithms, supervised predictive models, or heuristic models that use a mixture of chemical expertise and automation to classify reactions. Participation in this project will provide exposure to research in machine learning and data science including training in programming, model training, and utilization of large data sets. Participants do not need to have prior experience in data science.
Research categories:
Big Data/Machine Learning, Chemical Unit Operations
Preferred major(s):
Chemical Engineering, Chemistry
School/Dept.:
Chemical Engineering
Professor:
Allison
Godwin
More information: https://cistar.us/
Developing IoT sensors for real-time concrete strength monitoring
Description:
EMI technique is a nondestructive testing (NDT) method that makes use of the piezoelectric nature of lead zirconate titanate (PZT) sensor that vibrates and interacts with the host structure, thereby tuning the electrical characteristics of PZT through mechanical interaction. Inversion algorithm is then used to extract mechanical properties of host structure from using electrical characteristics of PZT sensor. EMI technique has been evolving for decades and demonstrated to be a good in-situ method to determine bulk concrete properties, e.g. Young’s modulus, in lieu of tedious molding and compression test. However, current EMI studies in modulus measurement are mostly established on the statistical relationship between EMI spectrum and conventional compression test, and the variation of sensors can lead to a bad repeatability.
In this work, a novel EMI method for concrete modulus measurement will be reported. This novel NDT method can extract the dynamic modulus of concrete cylinder using only one PZT sensor. The specific activities include: (a) embedding PZT sensor in cylinder mold; (b) casting concrete in mold; (c) measuring the electrical impedance spectrum of sensor; (d) reading the resonance frequencies of the spectrum in low frequency band and (e) calculating the modulus using resonance frequencies. The orientation of sensor, the sensing range and the repeatability between different sensors will be discussed in this project. The investigation of the nature of EMI sensor-structure interaction has a broad interest to NDT and piezoelectric material community.
In this work, a novel EMI method for concrete modulus measurement will be reported. This novel NDT method can extract the dynamic modulus of concrete cylinder using only one PZT sensor. The specific activities include: (a) embedding PZT sensor in cylinder mold; (b) casting concrete in mold; (c) measuring the electrical impedance spectrum of sensor; (d) reading the resonance frequencies of the spectrum in low frequency band and (e) calculating the modulus using resonance frequencies. The orientation of sensor, the sensing range and the repeatability between different sensors will be discussed in this project. The investigation of the nature of EMI sensor-structure interaction has a broad interest to NDT and piezoelectric material community.
Research categories:
Big Data/Machine Learning, Engineering the Built Environment, Internet of Things, Mobile Computing
Preferred major(s):
civil engineering, electrical engineering
Desired experience:
MATLAB, IC circuit design
School/Dept.:
Civil Engineering
Professor:
Luna
Lu
More information: https://engineering.purdue.edu/SMARTLab
Efficient and renewable water treatment
Description:
Water and energy are tightly linked resources that must both become renewable for a successful future. However, today, water and energy resources are often in conflict with one another, especially related to impacts on electric grids. Further, advances in material science and artificial intelligence allow for new avenues to improve the widespread implementation of desalination and water purification technology. This project aims to explore nanofabricated membranes, artificial intelligence control algorithms, and thermodynamically optimized system designs. The student will be responsible for fabricating membranes, building hydraulic systems, modeling thermal fluid phenomenon, analyzing data, or implementing control strategies in novel system configurations.
Research categories:
Big Data/Machine Learning, Ecology and Sustainability, Energy and Environment, Internet of Things, Material Modeling and Simulation, Material Processing and Characterization, Medical Science and Technology, Nanotechnology, Thermal Technology
Preferred major(s):
Mechanical, Civil, Electrical, Materials, Chemical, or Environmental Engineering
Desired experience:
Applicants should have an interest in thermodynamics, water treatment, and sustainability. Applicants with experience in some (not all) of the following are preferred: experimental design and prototyping, manufacturing, Python, LabView, EES, MATLAB, 3D CAD Software, & Adobe Illustrator. 2nd semester Sophomores, Juniors, and 1st semester Seniors are preferred.
School/Dept.:
Mechanical Engineering
Professor:
David
Warsinger
More information: www.warsinger.com
Enhancing Human-Robot Interaction Using Wearable Technologies
Description:
While intelligent systems promise to extend human capabilities within occupational settings, workers must increasingly collaborate with artificial intelligence (AI) to achieve desired outcomes. This research aims at enhancing bi-directional interaction between workers and robots at the construction jobsites by obtaining continuous neurophysiological and psychophysiological data from workers. The developed personalized AI will measure, adapt, and enhance the skill performance of the next generation of the workforce to work safely and communicate effectively in the future automated jobsites.
Research categories:
Big Data/Machine Learning, Deep Learning, Engineering the Built Environment
Preferred major(s):
All Engineering Fields or Neuroscience
Desired experience:
Programming (Python, Matlab, C++), Data Analytics (Machine learning, Deep-learning)
Seeking applicants who are creative and passionate to explore new areas
School/Dept.:
School of Civil engineering and CEM
Professor:
Sogand
Hasanzadeh
Epidemic Analysis Via Social Networks
Description:
Social media has significantly increased the rate at which news spreads through the population, enabling shifts in people’s beliefs towards the news. One such example is the disagreement on the severity of the disease over different communities during the COVID-19 pandemic. The contention over COVID-19 affects people’s attitudes and behaviors towards the policies and suggestions from the government and scientific institutions, respectively. Our question is if it is possible to mitigate the spreading of the epidemic by impacting the opinions over the social networks. Our proposed solution is to capture the opinions of the COVID-19 pandemic through dynamical social networks with both cooperative and antagonistic interactions. We will validate the network model with social network data. Through the data-based model, we will explore the role of opinion dissemination on epidemic spreading in reality. The undergraduate researchers will learn to model signed social networks via the opinions on COVID-19. The students will gain fundamental knowledge in systems and control, social network modeling and analysis, and hands-on experience in data collection, analysis, and model validation.
Research categories:
Big Data/Machine Learning, Learning and Evaluation, Other
Desired experience:
Preferred: Mathematical background, programming skills, data processing experience
School/Dept.:
ECE
Professor:
Philip
Paré
More information: https://sites.google.com/view/philpare/home
Epidemic Modeling and Prediction with COVID-19 Dataset
Description:
COVID-19 has been a major challenge in the year 2020 and the epidemic modeling community has yet to come up with an accurate and reliable method for epidemic spread prediction. Some difficulties of the epidemic spread prediction problem include testing delays, testing inaccuracy and feedback effects from local health authorities’ disease mitigation policies. These complexities in the dataset will lead to inaccurate prediction and poor disease mitigation strategies if not resolved properly.
There are abundant well-organized Covid-19 datasets available online, including the COVID-19 Data Repository by the Center for Systems Science and Engineering (CSSE) at Johns Hopkins University. By leveraging these datasets, we plan to design a project-based learning experience that participants will model and predict epidemic spread over a nine-week schedule. The project includes five major stages: 1) data collection, 2) model selection, 3) parameters optimization, 4) model verification, and 5) prediction. The participants will learn to model and analyze epidemic processes with compartmental models, and they will get the first-hand experience using a programming language of their choice to implement the modeling, optimization, and prediction pipeline.
There are abundant well-organized Covid-19 datasets available online, including the COVID-19 Data Repository by the Center for Systems Science and Engineering (CSSE) at Johns Hopkins University. By leveraging these datasets, we plan to design a project-based learning experience that participants will model and predict epidemic spread over a nine-week schedule. The project includes five major stages: 1) data collection, 2) model selection, 3) parameters optimization, 4) model verification, and 5) prediction. The participants will learn to model and analyze epidemic processes with compartmental models, and they will get the first-hand experience using a programming language of their choice to implement the modeling, optimization, and prediction pipeline.
Research categories:
Big Data/Machine Learning, Learning and Evaluation, Other
Desired experience:
Preferred: Mathematical background, programming skills, data processing experience
School/Dept.:
ECE
Professor:
Philip
Paré
More information: https://sites.google.com/view/philpare/home
Human Factors: Enhancing Performance of Nurses and Surgeons
Description:
High physical and cognitive workload among surgeons and nurses are becoming more common. The purpose of this project is to examine the contributors to these and develop technology to understand and enhance their performance.
The SURF student will participate in data collection in the operating room at Indiana University School of Medicine, data analysis and interpretation, and write his/her results for a journal publication. The student will regularly communicate his/her progress and results with faculty, graduate mentors, and surgeon collaborators.
The SURF student will participate in data collection in the operating room at Indiana University School of Medicine, data analysis and interpretation, and write his/her results for a journal publication. The student will regularly communicate his/her progress and results with faculty, graduate mentors, and surgeon collaborators.
Research categories:
Big Data/Machine Learning, Learning and Evaluation, Medical Science and Technology, Other
Preferred major(s):
Industrial Engineering, Computer Science, Biomedical Engineering
Desired experience:
Human Factors, Machine Learning, Sensors, Programming
School/Dept.:
Industrial Engineering
Professor:
Denny
Yu
More information: https://engineering.purdue.edu/YuGroup
IoT4Ag P3: Biophysical modeling and integration with in-situ and remotely sensed data
Description:
By 2050, the US population is estimated to grow to 400 million and the world population to 9.7 billion. Current agricultural practices account for 70% of global water use, energy accounts for one of the largest costs on a farm, and inefficient use of agrochemicals is altering Earth’s ecosystems. With finite arable land, water, and energy resources, ensuring food, energy, and water security will require new technologies to improve the efficiency of food production, create sustainable approaches to supply energy, and prevent water scarcity.
A new Engineering Research Center on the Internet of Things for Precision Agriculture (IoT4Ag) has recently been established to ensure food, energy, and water security by advancing technology to increase crop production, while minimizing the use of energy and water resources and the impact of agricultural practices on the environment. The center will create novel, integrated systems that capture the microclimate and spatially, temporally, and compositionally map heterogeneous stresses for early detection and intervention to better outcomes in agricultural crop production. The Center will create internet of things (IoT) technologies to optimize practices for every plant; from sensors, robotics, and energy and communication devices to data-driven models constrained by plant physiology, soil, weather, management practices, and socio-economics. We are looking to hire a cohort of SURF students to work on different activities in the center.
IoT4Ag P3: Biophysical modeling and integration with in-situ and remotely sensed data
# of students: 3, US Citizens or permanent residents only
This interdisciplinary project will focus on acquisition and processing of remotely sensed data acquired by sensors on UAVs and wheel-based vehicles, developing empirical models, and working collaboratively with teams in the College of Agriculture to integrate empirical machine learning models with biophysical modeling to detect plant stress and predict yield. The project will provide opportunities for students to learn about sensors via field-based data acquisition from remote sensing platforms, expand their understanding of techniques for processing data, use data products for applications related to cropping systems (plant breeding, production management, in-season treatments) and engage in development of hybrid models that include both data analytics and biophysically based approaches. Use of existing models may require use of APIs for data acquisition, familiarity with file types, and aptitude for functions and systems thinking.
The project will involve both field-based and computer laboratory focused research. Courses /experience in python programming, data analytics and image processing, and particularly related to remote sensing technologies, are desirable. Interest in interdisciplinary research is essential.
A new Engineering Research Center on the Internet of Things for Precision Agriculture (IoT4Ag) has recently been established to ensure food, energy, and water security by advancing technology to increase crop production, while minimizing the use of energy and water resources and the impact of agricultural practices on the environment. The center will create novel, integrated systems that capture the microclimate and spatially, temporally, and compositionally map heterogeneous stresses for early detection and intervention to better outcomes in agricultural crop production. The Center will create internet of things (IoT) technologies to optimize practices for every plant; from sensors, robotics, and energy and communication devices to data-driven models constrained by plant physiology, soil, weather, management practices, and socio-economics. We are looking to hire a cohort of SURF students to work on different activities in the center.
IoT4Ag P3: Biophysical modeling and integration with in-situ and remotely sensed data
# of students: 3, US Citizens or permanent residents only
This interdisciplinary project will focus on acquisition and processing of remotely sensed data acquired by sensors on UAVs and wheel-based vehicles, developing empirical models, and working collaboratively with teams in the College of Agriculture to integrate empirical machine learning models with biophysical modeling to detect plant stress and predict yield. The project will provide opportunities for students to learn about sensors via field-based data acquisition from remote sensing platforms, expand their understanding of techniques for processing data, use data products for applications related to cropping systems (plant breeding, production management, in-season treatments) and engage in development of hybrid models that include both data analytics and biophysically based approaches. Use of existing models may require use of APIs for data acquisition, familiarity with file types, and aptitude for functions and systems thinking.
The project will involve both field-based and computer laboratory focused research. Courses /experience in python programming, data analytics and image processing, and particularly related to remote sensing technologies, are desirable. Interest in interdisciplinary research is essential.
Research categories:
Big Data/Machine Learning, IoT for Precision Agriculture, Other
Preferred major(s):
ABE, CE, ECE, IE
Desired experience:
Courses /experience in python programming, data analytics and image processing, and particularly related to remote sensing technologies, are desirable.
Strong computer and math skills, preferably experience with data wrangling and visualization (Python preferred)
Interest in interdisciplinary research is essential.
School/Dept.:
CE, ECE, Agronomy
Professor:
Melba
Crawford
More information: iot4ag.us
Lithium-ion Battery Analytics
Description:
Lithium-ion (Li-ion) batteries are ubiquitous. Thermo-electrochemical characteristics and porous electrode structures of these systems are critical toward safer and high-performance batteries for electric vehicles. As part of this research, physics-based modeling and experimental data-driven analytics will be performed over a wide range a normal and anomalous operating conditions of Li-ion cells.
Research categories:
Big Data/Machine Learning, Energy and Environment, Material Modeling and Simulation
Preferred major(s):
Mechanical, Chemical, Materials Engineering
Desired experience:
The student will work closely with a senior graduate student researcher on the modeling and experimental data analysis in the form of weekly reports. The final deliverable will be one end-of-summer research report (based on the weekly progress) and a presentation at the research group meeting. Experience with modeling and analysis tools and methods is desirable.
School/Dept.:
Mechanical Engineering
Professor:
Partha
Mukherjee
More information: https://engineering.purdue.edu/ETSL/
Measuring wetland greenhouse gas emissions with environmental Internet of Things sensors.
Description:
Wetlands in agricultural landscapes are important sites for maintaining water quality in streams, rivers, and reservoirs that are downstream of farmland. Despite these benefits, such wetlands can be a large source of potent greenhouse gasses—primarily methane (CH4) and nitrous oxide (N2O). Yet, data on the amount of greenhouse gasses produced by agricultural wetlands and the environmental factors that cause these differences are not widely available. For this project, we will leverage environmental internet of things (IoT) technology to deploy networks of gas sensors in agricultural wetlands. We will use these gas sensors to determine what local environmental factors (e.g., water inundation length, elevation, soil organic matter content) cause CH4 and N2O emissions to increase and decrease from wetland soils.
The student working on this project would be responsible for deploying gas sensors, which will involve fieldwork at wetlands located near Purdue. This student will also have the opportunity to analyze the data collected from these sensors with the assistance of faculty and graduate student mentors.
The student working on this project would be responsible for deploying gas sensors, which will involve fieldwork at wetlands located near Purdue. This student will also have the opportunity to analyze the data collected from these sensors with the assistance of faculty and graduate student mentors.
Research categories:
Big Data/Machine Learning, Ecology and Sustainability, Environmental Characterization, Internet of Things
Preferred major(s):
Biology, Natural Resources, Computer Science, and Environmental Engineering majors (interpreted broadly).
Desired experience:
Students with an interest in working with IoT technology, including sensors powered by Arduino processors, are encouraged to apply. Experience with environmental sensors and/or wetland field work is beneficial, but not required.
School/Dept.:
Forestry & Natural Resources
Professor:
Jacob
Hosen
More information: http://www.ecosystemscience.io
Mobile Air Quality Sensors and the Internet of Things
Description:
The project goal is to design and develop a hardware, software and cloud computing system for the acquisition of air quality data from mobile platforms such as taxis, backpacks, and drones. The sensors will be deployed around Purdue and eventually in the city of Arequipa, Peru. Data will be used to assess the spatial and temporal changes in air pollutions in Peru's 2nd largest city. The research is a collaboration between Purdue and the University of San Augustin (UNSA) as part of the NEXUS project.
Research categories:
Big Data/Machine Learning, Ecology and Sustainability, Energy and Environment
Preferred major(s):
Data science, computer science, electrical engineering, computer engineering, chemistry
Desired experience:
One or more of the following
Java, python, html, raspberriPI, aurdino, circuits, statistics, machine learning, internet of things, cloud computing
School/Dept.:
EAPS
Professor:
Greg
Michalski
More information: https://www.purdue.edu/discoverypark/arequipa-nexus/en/index.php
On-Line Programming Assessment
Description:
Computer programs are difficult to evaluate due to the large number of possibilities. Existing evaluation systems are restricted to simple programs or impose restrictions to limit possibilities. This project aims to build an online assessment system that can evaluate non-trivial programs and assist students learning computer programming.
Research categories:
Big Data/Machine Learning, Cybersecurity, Deep Learning, Learning and Evaluation
Preferred major(s):
computer engineering, computer science, electrical engineering
Desired experience:
at least two courses on computer programming
School/Dept.:
Electrical and Computer Engineering
Professor:
Yung-Hsiang
Lu
Real time analysis of viral particles for continuous processing approach
Description:
The increasing worldwide demand for vaccines along with the intensifying economic pressure on health care systems underlines the need for further improvement of vaccine manufacturing. In addition, regulatory authorities are encouraging investment in the continuous manufacturing processes to ensure robust production, avoid shortages, and ultimately lower the cost of medications for patients. The limitations of in-line process analytical tools are a serious drawback of the efforts taken in place. In line analysis of viral particles are very limited, due to the large time required for the current techniques for detection, qualitative and quantitative analysis. Therefore, there is a need for new alternatives for viral detection.
Research categories:
Big Data/Machine Learning, Biological Characterization and Imaging, Biological Simulation and Technology, Biotechnology Data Insights, Cellular Biology
Preferred major(s):
Chemical Eng, Biological Eng, Biomedical Eng, Physics, Mechanical Eng
Desired experience:
This project requires lab work and presence on campus, however, an online version can be offered to focus on coarse-grained modeling of proteins/cells.
School/Dept.:
Mechanical Engineering
Professor:
Arezoo
Ardekani
More information: https://engineering.purdue.edu/ComplexFlowLab/
Reliable Deep Learning Software
Description:
We will build cool and novel techniques to make deep learning code such as TensorFlow and PyTorch reliable and secure. We will build it on top of our award winning project (https://www.cs.purdue.edu/homes/lintan/publications/variance-ase20.pdf), which won an ACM SIGSOFT Distinguished Paper Award! There may be opportunities to collaborate with Microsoft. See below for more details.
Machine learning systems including deep learning (DL) systems demand reliability and security. DL systems consist of two key components: (1) models and algorithms that perform complex mathematical calculations, and (2) software that implements the algorithms and models. Here software includes DL infrastructure code (e.g., code that performs core neural network computations) and the application code (e.g., code that loads model weights). Thus, for the entire DL system to be reliable and secure, both the software implementation and models/algorithms must be reliable and secure. If software fails to faithfully implement a model (e.g., due to a bug in the software), the output from the software can be wrong even if the model is correct, and vice versa.
This project aims to use novel approaches including differential testing to detect and localize bugs in DL software (including code and data) to address the testing oracle challenge. Good programming skills and strong motivation in research are required. Background in deep learning and testing is a plus.
Machine learning systems including deep learning (DL) systems demand reliability and security. DL systems consist of two key components: (1) models and algorithms that perform complex mathematical calculations, and (2) software that implements the algorithms and models. Here software includes DL infrastructure code (e.g., code that performs core neural network computations) and the application code (e.g., code that loads model weights). Thus, for the entire DL system to be reliable and secure, both the software implementation and models/algorithms must be reliable and secure. If software fails to faithfully implement a model (e.g., due to a bug in the software), the output from the software can be wrong even if the model is correct, and vice versa.
This project aims to use novel approaches including differential testing to detect and localize bugs in DL software (including code and data) to address the testing oracle challenge. Good programming skills and strong motivation in research are required. Background in deep learning and testing is a plus.
Research categories:
Big Data/Machine Learning, Deep Learning, Other
Preferred major(s):
Computer Science; Computer Engineering; Data Science
School/Dept.:
Computer Science
Professor:
Lin
Tan
More information: https://www.cs.purdue.edu/homes/lintan/
Resilient Extraterrestrial Habitat Engineering
Description:
There is growing interest from Space agencies such as NASA and the European Space Agency in establishing permanent human settlements outside Earth. To advance knowledge in the field, the Resilient Extra-Terrestrial Habitat Institute (RETHi) is taking steps to develop technologies that will enable resilient habitats in deep space, that will adapt, absorb and rapidly recover from expected and unexpected disruptions without fundamental changes in function or sacrifices in safety. To study, demonstrate, and evaluate the technologies developed in pursuit of this mission, a multi-physics cyber-physical testbed is being founded at the Ray W. Herrick Laboratories at Purdue University with collaboration from partners at three universities and two industrial partners. It allows to examine emergent behaviors in habitat systems and the interactions among its virtual (computational) and physical components.
The testbed will consider a habitat system and will aim to emulate the extreme temperature fluctuations that happen in deep space. To achieve this goal, a thermal transfer system is being developed, consisting of a chiller, an array of glycol lines, in-line heaters, actuated valves, and a series of sensors. Operated under a tuned controller, the thermal transfer system can cool or heat a certain surface area of the structure of the habitat to maintain a given temperature. However, to fully control the thermal transfer system is not straightforward. One of the critical challenges is its deep uncertainty, which results from inaccurate or long-delay sensors, variant test setup, complex controller design, etc. Therefore, a systematic study is needed to quantify the uncertainties to facilitate the thermal transfer system development. Emulation of a particular scenario considering a meteoroid impact will be performed, with random variations in the location and size of the impact and resulting consequences.
We are looking for undergraduate students to play key roles in this project, under the guidance of a graduate student and faculty members. The students are also expected to prepare a poster presentation on the results, and author a research paper if the desired results are achieved. Participating undergraduate researchers would be tasked to focus on the following research projects:
• Stochastic model for analyzing and exploring the behavior variability of the thermal transfer system, functioning in different scenarios.
• Experimental study to calibrate the developed model, involving parametric identification of the transfer system and experimental validation of the stochastic model.
• Numerical and experimental studies to detect and localize meteoroid impact and damage to the structure and other subsystems of the habitat, and use that information to make decisions regarding emergency actions to take.
• Numerical investigations to understand the limitations of fault damage detection methods when incomplete or erroneous sensor data is available.
The testbed will consider a habitat system and will aim to emulate the extreme temperature fluctuations that happen in deep space. To achieve this goal, a thermal transfer system is being developed, consisting of a chiller, an array of glycol lines, in-line heaters, actuated valves, and a series of sensors. Operated under a tuned controller, the thermal transfer system can cool or heat a certain surface area of the structure of the habitat to maintain a given temperature. However, to fully control the thermal transfer system is not straightforward. One of the critical challenges is its deep uncertainty, which results from inaccurate or long-delay sensors, variant test setup, complex controller design, etc. Therefore, a systematic study is needed to quantify the uncertainties to facilitate the thermal transfer system development. Emulation of a particular scenario considering a meteoroid impact will be performed, with random variations in the location and size of the impact and resulting consequences.
We are looking for undergraduate students to play key roles in this project, under the guidance of a graduate student and faculty members. The students are also expected to prepare a poster presentation on the results, and author a research paper if the desired results are achieved. Participating undergraduate researchers would be tasked to focus on the following research projects:
• Stochastic model for analyzing and exploring the behavior variability of the thermal transfer system, functioning in different scenarios.
• Experimental study to calibrate the developed model, involving parametric identification of the transfer system and experimental validation of the stochastic model.
• Numerical and experimental studies to detect and localize meteoroid impact and damage to the structure and other subsystems of the habitat, and use that information to make decisions regarding emergency actions to take.
• Numerical investigations to understand the limitations of fault damage detection methods when incomplete or erroneous sensor data is available.
Research categories:
Big Data/Machine Learning, Engineering the Built Environment, Thermal Technology, Other
Preferred major(s):
ME, AAE, CE, CS
Desired experience:
Students interested in this project should be critical thinkers, and have good experimental skills, some programming skills, CAD skills, and experience in MATLAB/Simulink.
School/Dept.:
Mechanical, Civil, Aero Eng. Departments
Professor:
Shirley
Dyke
More information: https://www.purdue.edu/rethi/
Smart Water for Smart Cities
Description:
Water is centrally important to environmental sustainability: it supports human societal needs and the natural environment, and powers the growth of economic sectors, geographic regions, and cities. Data science should be harnessed to better understand how much and where water is consumed. The undergraduate researcher will be apply methods to quantify and model industrial water consumption at fine spatial and industry-sector resolution, visualize the results with geographic information systems, and interpret the impacts of water consumption on the urban environment.
Research categories:
Big Data/Machine Learning, Ecology and Sustainability, Energy and Environment, Engineering the Built Environment, Environmental Characterization, Other
Preferred major(s):
EEE, CE, or IE
Desired experience:
Minimum GPA: 3.0.
Preferred majors: Environmental and Ecological Engineering, Civil Engineering, or Industrial Engineering.
Preferred coursework: CE/EEE 350 or CE/EEE 355 or EEE 250
Preferred skills: Proficiency with programming in R or Python Python, experience with ArcGIS or similar programs.
School/Dept.:
CE and EEE
Professor:
Inez
Hua
Virtual Reality animations of blood flow in a vessel network
Description:
The recently developed Paraview Immersive toolkit provides a simple way to produce virtual reality animations compatible with the Oculus Rift application using data from 3D simulations. This is a unique opportunity to better analyze the data by literally walking around inside them. In this project, the undergraduate students will produce a virtual reality animation using our 3D simulations of blood flow in capillaries.
Research categories:
Big Data/Machine Learning, Biological Simulation and Technology
Desired experience:
Knowledge about computer graphics and programming would be a plus.
School/Dept.:
Mechanical Engineering
Professor:
Hector
Gomez
More information: https://engineering.purdue.edu/gomez/