SURP 2023 Project Abstracts
Summer Undergraduate Research Program
Faculty: Javier Gonzalez Sanchez
Department: CSSE
Email: javiergs@calpoly.edu
Funded by The Noyce School of Applied Computing.
Number of Students: 1
Description: An Intelligent Tutoring System (ITS) is a computer system that provides immediate and customized instruction or feedback to learners without requiring intervention from a human teacher. An ITS emulates the qualities of skillful human teachers (including having empathy and creating an engaging presence). Doing that involves real-time awareness of students’ cognitive challenges and affective states (emotions and mood). Two technologies that can support providing an understanding of cognitive challenges and affective states to software systems are eye tracking for gaze behavior analysis and brain-computer interfaces for brain activity monitoring. Imagine having continuous real-time access to what a student is looking at and their brain’s activity while reading a page, solving a problem, or answering a quiz. How can we leverage such information (gaze and brain activity) to improve the depth and accuracy of machine learning modeling for the student and use such a model to drive an ITS’s behavior? In particular, we aim to leverage such capabilities into an ITS that supports students in learning Software Design topics. In that context, this summer’s undergraduate research project focused on: (1) exploring lowcost open-source eye-tracking technology and its application in triggering tutoring behaviors, primarily examining the relationship between eye gaze and software models (diagrams), focusing on detecting the differences between skilled and unskilled students, and (2) using low-cost brain-computer interface (Emotiv Headset) to examine cognitive and emotional reactions to software structural models. Particularly, examine whether modular design affects levels of cognitive load or affect.
Faculty: Long Wang
Department: CE
Email: lwang38@calpoly.edu
Number of Students: 2
Funded By: Sprague
Description: As it is well known that when most of the materials are stretched in one direction, they would shrink in another direction. This is an example of Poisson’s effect, and most of the conventional materials possess positive Poisson’s ratios. However, certain “auxetic” materials exhibit negative Poisson’s ratios, which indicate that they could expand transversally while being stretched longitudinally. Due to their unique mechanical behavior, auxetic materials have significant potentials in various application fields, including aerospace structures, energy absorption, and biomaterial engineering, to name a few. There has been extensive research on computationally designing structures of controlled auxetic performance. However, limited work has been conducted on integrating the theoretical designs with practical additive manufacturing process and actual structural material properties. To bridge this gap, this research project aims to establish a framework for rationally designing, manufacturing, and characterizing auxetic structures. Specific research tasks include:
1) optimizing stereolithography (SLA) 3D printing process to manufacture designed auxetic structures using different UV-curable elastic resin;
2) conducting mechanical tests on 3D printed structures;
3) quantifying the achieved Poisson’s ratios and analyzing the stress distribution in the structures using the digital image correlation (DIC) technique.
It should be noted that this is a multidisciplinary collaborative project. The students will have opportunity to work with both Dr. Wang’s research group and computational mechanics experts from other institutes. In addition, the students will have the opportunity to participate in outreach activities to promote 3D printing techniques to high school students from diverse backgrounds.
Faculty: Franz Kurfess
Department: CSSE
Email: fkurfess@calpoly.edu
Co-PI: Lynne Slivovsky, CPE
Funded by Gary Bloom
Number of Students: 4
Description: Building on the work done initially as a SURP 2021 project and continued through 2021-23, the focus for this summer project will be on the use of computer technology for locating a missing person. Over the last year, we developed the digital equivalents of about 30 paper-based S&R forms and the infrastructure to collect the respective information. In their current use, these paper forms are filled out by search teams, collected in a command post, and reviewed by search coordinators. This process is time-consuming, prone to errors and loss of information, and relies heavily on the experience, skills, and mental acuity of the search coordinators. At the core of this process is the Lost Person Questionnaire, a lengthy and complex form that collects relevant information about the subject of the S&R mission. For this SURP effort, we will explore the use of Artificial Intelligence and Machine Learning to combine information about the ongoing search effort, past missions with similar profiles, and general knowledge such as terrain and travel routes to identify areas of high priority for the search.
Faculty: Mohsen Kivy
Department: MATE
Email: mbeyrama@calpoly.edu
Number of Students: 2
Funded By: Jim Beaver
Description: Study of multi-component alloys has historically relied heavily on extensive experimental investigations. However, these experimental studies can be complex, costly and time-consuming. To overcome these obstacles, engineers and researchers use various computational tools such as simulations and machine learning.This project is designed to combine a meso-scale computational simulation technique (CALPHAD) and Machine Learning to predict the phase diagrams of multi-component systems. CALPHAD method will be used to calculate the phase diagrams of binary and ternary systems. The obtained data will then be fed into a Machine Learning algorithm to predict the phase diagrams of alloys with higher number of elements (four or more). The predicted results will be compared to calculated phase diagrams using the commercial databases to validate/evaluate the accuracy of the used algorithm. Due to the nature of this project, students across the college (especially from MATE, CPE, CSC, and/or GENE) can apply.
Faculty: Dianne DeTurris
Department: AERO
Email: ddeturri@calpoly.edu
Number of Students: 2
Funded By: NNSS
Description: This research focuses on system visualization and attribute testing techniques for managing complexity in the development of modern aerospace systems. A collection of qualitative and quantitative methods has been compiled that enable system characteristics and vulnerabilities due to complexity to be described (Flumerfelt, Meadows, Snowden, Bonabeau, Tamaskar, Eppinger). The proposed research will be geared toward implementation of a combination of visualization tools and attribute testing to be used during system development to best allocate resources for managing complexity. The systems competencies developed using these tools will be synthesized for application to aerospace.
Faculty: Joydeep Mukherjee
Department: CSSE
Email: jmukherj@calpoly.edu
Funded by The Noyce School of Applied Computing.
Number of Students: 2
Description: Industrial Internet-of-Things (IoT) is an emerging paradigm where millions of sensors are used to stream, aggregate, and analyze data to monitor physical, environmental, and human systems in real time. IoT applications in domains such as smart healthcare and smart buildings typically have data flows with high frequency and low latency requirement from sensors to gateways and to datacenters. These applications introduce new challenges and opportunities for researchers to explore diverse IoT-related areas such as performance, Big Data, anomaly detection, security and AI-enabled recommendation systems. This project aims to build an Industrial IoT benchmark which imitates a real IoT platform that monitors, ingests, processes, and analyzes data streams from numerous heterogeneous IoT sensor devices. This project will use a small number of IoT sensors as a starting point to create an IoT framework and will build on top of this framework to create a benchmark that can potentially scale to a large number of virtual IoT sensors. The IoT framework will be designed using state-of-the-art tools such as Apache Kafka, Apache Spark and a Cassandra cloud storage. The end goal of this project is to build a scalable IoT benchmark that is representative of a real Industrial IoT platform and can be configured to simulate different practical scenarios that capture the functioning of such platforms. The proposed IoT benchmark created in this project will enable faculty members and students conduct interdisciplinary research and generate large datasets using cutting-edge infrastructure technologies relevant to modern IoT platforms and applications.
Faculty: Behnam Ghalamchi
Department: ME
Email: bghalamc@calpoly.edu
Number of Students: 1
Funded By: Bonderson
Note: The student working on this project will work closely with the student on the below project of the same name.
Description: The proposed research project aims to develop a simple and affordable vibration measurement setup that can be used for predictive maintenance and monitoring in various industrial applications. Vibration analysis is a crucial technique used to detect and diagnose faults in mechanical systems, and it is a fundamental step towards developing a digital twin, a virtual replica of a physical system. However, most of the available vibration measurement setups are either too expensive or too complex for small and medium-sized enterprises (SMEs) to adopt. This project will leverage recent advances in sensor technologies and machine learning algorithms to develop a low-cost and user-friendly vibration measurement setup that can be used by SMEs to improve their maintenance practices. The outcomes of this project will advance knowledge and understanding in the field of vibration analysis and will pave the way for the adoption of digital twin technologies in SMEs.
Faculty: Behnam Ghalamchi
Department: ME
Email: bghalamc@calpoly.edu
Number of Students: 1
Funded By: College of Engineering DEI Initiative
Note: The student working on this project will work closely with the student on the above project of the same name.
Description: The proposed research project seeks to advance knowledge and understanding in engineering education through the exploration of digital twins (DT) as a means of promoting diversity and inclusion in hands-on laboratory environments. In addition to conducting a literature review in the field of DT, the student researcher will also examine related fields such as human-computer interaction and physical lab engagement to provide a comprehensive review of the topic. This process will not only provide students with a deeper understanding of the role that DT can play in engineering education, but it will also allow them to gain insight into interdisciplinary research areas that intersect with DT and diversity and inclusion.
By examining the potential of DT to promote diversity and inclusion in hands-on laboratory environments, this research project has the potential to make significant contributions to the field of engineering education. Moreover, the interdisciplinary nature of this research will enable insights into the potential of DT in other fields as well. Ultimately, the research project seeks to advance knowledge and understanding in engineering education and to promote a more inclusive and equitable learning environment for all students
Faculty: Jean Lee
Department: MATE
Email: jlee473@calpoly.edu
Number of Students: 2
Funded By: Jean Lee
Description: A growing number of utility-scale photovoltaic (PV) power plants in the U.S. are now being designed and constructed with bi-facial crystalline silicon PV modules, which can convert light into electricity from both the front and rear sides of the module. The energy incident upon the ground-facing side of the modules depends on several factors including solar irradiance and ground albedo (reflectance). This project seeks to improve the energy harvest of bi-facial PV modules via ground surface albedo treatments to increase the amount of solar energy reaching the ground-facing side of bi-facial PV modules, and results from this work are expected to contribute to improvements and best practices in the area of solar energy/renewable energy. A team of two students will identify and characterize 2 – 3 high albedo / high reflectance materials that can be used as ground treatments, taking into consideration factors including material cost, availability, ease of deployment, maintenance requirements, and estimated expected increase in energy harvest. A comparison of white versus silver high reflectance materials is of particular interest. Characterization of the test materials will include measuring their change in albedo and reflectance over time under outdoor exposure conditions, and measuring their physical degradation via mechanical testing under each of outdoor exposure and accelerated weathering conditions. Clearway Energy is supporting this project by loaning the use of an albedometer and a MET (meterological) station valued at $5,000.
Secondary Project: Development of Cost-Effective Methods for Rapid Detection of Common Water Pathogens
As the primary project may or may not have large amounts of down time, work on this secondary project will proceed as time permits. Current commonly-used detection methods for these pathogens are time consuming and might not be accessible in certain parts of the world due to cost or resource limitations. This project aims to develop a nanotechnology-based method that can rapidly give a qualitative indication of the presence of water pathogens through color change, and quantitatively determine the concentrations of pathogens in water samples using non-sophisticated equipment. This detection technique has previously been reported in the literature using gold nanoparticles as the nanosensors. In this technique, the addition of the negatively-charged enzyme ßgalactosidase (ß-Gal), the dye chlorophenol red-β-D-galactopyranoside (CPRG), and positively-charged gold nanoparticles to a water sample without microbes will result in the ß-Gal binding to the gold nanoparticles via Coulombic attraction, and the color of the water will not change. However, when the negatively-charged microbes are present in the water sample, competitive binding will take place and the microbes will bind to the gold nanoparticles, freeing up the ß-Gal to react with the CPRG and change color. The magnitude of color change is directly proportional to the microbe concentration in the water sample. Initial results have indicated that high isoelectric point (IEP) materials (i.e., materials that are positively charged with respect to neutral water) tested with non-pathogenic E. coli support the hypothesis that Coulombic effects between a high IEP nanosensor material and E. coli predominates over any chemical bonding effects between a high IEP nanosensor material and E. coli in the colorimetric sensing of E. coli in water. This project seeks to build upon these initial results by testing high IEP nanosensor materials with other common pathogens such as salmonella and/or listeria. This project will also investigate whether positively-charged nanosensor materials can be eliminated altogether from this technique by using an electrically insulating material to contain the water sample (such as a clear glass vial) and positively charging the container. In this case, it is hypothesized that any negatively-charged microbes in the water sample will be attracted to the walls of the container, and that the ß-Gal and the CPRG that has been added to the water sample should react to change the color of the water to indicate the presence of microbes. If successful, the technology from this project can be commercialized and used for the testing of water quality in resource-challenged locations to determine if their water is safe to drink and use. A team of two students are anticipated for this project.
Faculty: Stephen Beard
Department: CSSE/CPE
Email: srbeard@calpoly.edu
Number of Students: 2
Funded By: Larry Bergman and the College of Engineering
Description: Trusted systems require the faithful execution of secure software by secure hardware. Today’s systems have neither. Essentially all software contains bugs that attackers can find and exploit. The complexity of hardware, combined with the large attack surface presented in its development, manufacturing, and deployment processes make it nearly impossible to secure every component. Containment Architectures reject any output produced by a contained system that does not match the output that would have been produced by a secure and correct system. They do this without relying upon the existence of a secure and correct system to use as a reference. Instead, trust comes from a small, simple, efficient, and trusted hardware element, called the Sentry, that must be convinced that the computation is safe, secure, and correct before allowing output to leave the container. This holistic system-based approach has the potential to guarantee the correctness of communication from a system without major impacts to its performance. There are still many open areas that deserve further investigation in this area, including exploration of programs and systems that can most utilize Containment Architectures; implementation of simulators; implementation of hardware components in FPGAs; and proofs of correctness. A SURP project could explore a number of areas, depending upon student interest. Students with an interest in computer architecture, software toolchains, proof systems, or security would likely find this project most suited to them.
Faculty: Sumona Mukhopadhyay
Email: mukhopad@calpoly.edu
Department: CSSE
Number of Students: 1
Funded By: The Noyce School of Applied Computing
Description: This project focusses on developing a Machine Learning (ML) / Deep Learning (DL) system for monitoring of livestock using aerial images. Building on the work done initially as a SURP 2022 project, the focus for this project this year will be to improve and accelerate the detection of several different livestock in the images using ML/DL . During SURP 2022, a benchmark model was developed for livestock detection of a single animal type using aerial images. The detection was found to be slow and worked for a single livestock detection. This year we focus on improving the model by using semantic hashing technique which are unique codes for an image that could accelerate the detection. In order to speed up the monitoring task using semantically similar livestock images, which is a crucial requirement for real-time detection, we propose to represent the images as a binary code or the hash code. Hashing has been a widely-adopted technique for nearest neighbor search which is a machine learning approach for image recognition in large-scale image retrieval tasks. This increases the recognition rate and allows for herd or group recognition of livestock. The livestock are detected based on using the hash codes with the popular nearest neighbor detector. Moreover, semantic based hashing will allow to retrieve images determine the highest possible accuracy that could be achieved in the detection of animals, of livestock which are visually similar to other breeds. Moreover, we want the model to be scalable such that it detects multiple different categories of livestock in the images. Thus an end-to-end ML pipeline for realtime detection of different types of livestock are the ultimate goal of this project.
Faculty: Mohammad Hasan
Email: mhasan04@calpoly.edu
Department: ME
Funded by: College of Engineering DEI Funding
Number of Students: 2
Funded By: College of Engineering DEI Initiative
Description: Robotics and machine learning are technologies that continue to make noticeable effects on society and everyday life. These technologies are mainly studied and developed with minimal attention to diversity and inclusion. This makes these technologies un-inclusive and bias at best, and damaging to minorities and underrepresented groups at worse. This research aims to scout the recent literature to study new research developments and ideas about diversity, equity, and inclusion (DEI) and ethics in robotics and machine learning and develop a summative document that highlights best practices to implement when developing these technologies.
Faculty: Mohammad H Hasan
Department: ME
Email: mhasan04@calpoly.edu
Number of Students: 2
Funded By: Bonderson Project Fund
Description: This project aims to design, fabricate, and actuate a work-like origami robot. The origami worm structure will be constructed from 3D-printed materials, paper, and tethers. The worm will be actuated by a DC motor and a vacuum pump, for friction control. The goal of this project is to construct an origami worm with simple directional (forward/backward) and high movement speed compared to similar origami-style worm robots in the literature. Because of the size and compliance of the robot, this makes such a robot an excellent prototype for a biomedical robot or a search-and-rescue robot.
Faculty: Eric Mehiel
Department: AERO
Email: emehiel@calpoly.edu
Number of Students: 1
Funded By: Lockheed Martin
Description: The Horizon Simulation Framework (HSF) is an open-source hybrid time/event driven Discrete Event Simulator (DES) that uses a Dynamic Programing, breadth-first approach to generate possible task-based schedules for dynamic systems written in C# and Python and hosted on GitHub. The viability of each task on the schedule is determined by a system state-transition model developed by the user and written in Python. In short, the user provides a list of tasks to perform, a model of the system to simulate, and HSF generates an optimal schedule based on a user “value” function. As part of our ongoing work, we propose building an HSF Integrate Development Environment (IDE) to grow our user community. The proposed SURP project is for a student to research, develop, and prototype several key elements of the HSF IDE, the details of which are listed below. The primary goals of the project are for the student to research software tools and architectures, select a coding platform and tools, develop the requirements for the HSF IDE, and prototype several of the key elements with an emphasis on system model design. The HSF project can be applied to many fields that require simulation; however our primary focus is on the modeling and simulation of space-based systems. Modeling and simulation tools and knowledge are in high demand within the Aerospace industry as a means to support Model Based System Engineering (MBSE) designs.
Faculty: Jenny Wang
Department: CSSE/CPE
Email: jwang96@calpoly.edu
Co-PI: Xuan Wang, IME
Funded by The Noyce School of Applied Computing.
Number of Students: 1
Description: This research project aims to develop an integrated system for the material selection and 3D printing of lifelike human body models, revolutionizing surgical training by providing medical professionals with a realistic hands-on experience. By leveraging a user-friendly application, the system processes 2D medical images to create accurate 3D representations of human body parts, intelligently selects suitable printing materials based on available data, and ensures the quality and accuracy of the final model through a verification process. This solution will enhance the training experience for medical professionals and contribute to higher success rates in actual surgeries.
Faculty: Nandeesh Hiremath
Department: AERO
Email: nhiremat@calpoly.edu
Number of Students: 1
Funded By: Sprague
Description: The project is aimed at developing a cost-effective multi-axes loadcell for characterizing aerodynamic loads on bodies of arbitrary shapes for wind tunnel testing. This load cell will primarily be used to advance the knowledge gaps in bluff-body aerodynamics requiring low levels of uncertainties. The currently available commercial ATI loadcells (within Cal Poly) do not meet the accuracy levels for measuring drag forces. Precision loadcells are expensive primarily due to their compact formfactor and come at a cost of frequent calibration. As compact formfactor is not an essential component for the desired wind tunnel experiments, there is some flexibility in fine tuning the accuracy levels about various axes. As bluff body aerodynamics is a vastly unexplored area, case-by-case tuning and signal conditioning is anticipated for various test objects. In addition, voltage dritis and temperature compensations can be accounted for with a custom design and off the shelf electronics. The development of a 4-DOF and/or full 6-DOF will be considered for low-speed wind tunnel applications rated for specific load ranges about each axis. The work emphasizes on tying in concepts from structural mechanics, basic electronics, data acquisition and reduction making it suitable for an undergraduate student to gain exposure to instrumentation and wind tunnel testing.
Faculty: Eric Mehiel
Department: AERO
Email: emehiel@calpoly.edu
Number of Students: 1
Funded By: Lockheed Martin
Description: The Horizon Simulation Framework (HSF) is an open-source hybrid time/event driven Discrete Event Simulator (DES) that uses a Dynamic Programing, breadth-first approach to generate possible task-based schedules for dynamic systems written in C# and Python, and hosted on GitHub. The viability of each task on the schedule is determined by a system state-transition model developed by the user and written in Python. In short, the user provides a list of tasks to perform, a model of the system to simulate, and HSF generates an optimal schedule based on a user “value” function. As part of our ongoing work, we propose building a “test harness” that can be used by the person designing the Python system model. The proposed SURP project is for a student to develop, implement and test an HSF subsystem model test harness in Python. The test harness would take a user defined model, a set of initial conditions, and allow the user to develop and debug the subsystem model (through unit testing) before the model is consumed by HSF for full system simulation. Since the system model acts as a statetransition function, the student will also develop a formal Discrete Event Simulation Specification (DESS) for said HSF models and test harness. The formal DESS will advance the body of knowledge of DESS descriptions, as well as the goals and usability of the HSF project. The HSF project can be applied to many fields that require simulation, however our primary focus is on the modeling and simulation of space-based systems. Modeling and simulation tools and knowledge are in high demand within the Aerospace industry as a means to support Model Based System Engineering (MBSE) designs.
Faculty: Joel Galos
Department: MATE
Email: jgalos@calpoly.edu
Number of Students: 2
Funded By: Jim Beaver
Description: Computational tools in conjunction with artificial intelligence (AI) and machine learning have the potential to play significant roles in engineering and engineering education. In addition, the trends of AI and machine learning coincide with pedagogical trends of active learning. This project will explore classroom applications of a new “no-code” software platform (developed by Citrine Informatics) that uses AI and machine learning to solve real world materials engineering problems. This software platform enables engineering students to learn about AI and machine learning concepts and their engineering applications without prior knowledge of computer programming (e.g., Matlab or Python) or algorithm development. Moreover, it is expected that the Citrine Informatics software platform can help facilitate an interactive classroom that enables brainstorming among engineering students, improving their experience in the introductory materials engineering class that is taken by most engineering majors. The aim of this project is to explore how the Citrine Informatics software platform for machine learning could be best used in an engineering classroom setting.
Faculty: Dev Sisodia
Department: CSSE
Email: dsisodia@calpoly.edu
Co-Advisor: Javier Gonzalez Sanchez
Number of Students: 3
Funded By: College of Engineering DEI Initiative
Application Link Coming Soon
Description:
Faculty: Benjamin Lutz
Department: ME
Email: blutz@calpoly.edu
Number of Students: 2
Funded By: College of Engineering
Description: This work will use qualitative methods to explore and better define inclusive teaching in engineering, with a long-term goal of enhancing student evaluation of teaching regarding inclusivity. Calls for inclusive teaching are growing in engineering education, but research remains limited regarding how engineering faculty enact inclusive practices and how students experience them. We will accomplish the beginning of this work during the summer of 2023 which will occur in three overarching phases, each lasting between 2-3 weeks. First, we will learn about human subjects research design and obtaining IRB approval for data collection. This will include developing semi-structured interview protocols for students and faculty that explore beliefs, experiences, and practices related to inclusive teaching. Second, we will pilot these methods with faculty and students. We will recruit students in Dr. Lutz’s research group as well as colleagues in different JEDI committees. Finally, we will conduct preliminary qualitative analysis and revise our interview protocols for subsequent data collection. This project is firmly situated within the scholarship of teaching and learning and is designed to enhance teaching in ways that benefit both engineering students and faculty. By focusing on aspects of inclusivity in engineering, this research has the potential to improve teaching and learning in Engineering at Cal Poly and can also influence the way educators think about what it means to be an effective engineering educator more broadly.
Faculty: Sumona Mukhopadhyay
Department: CSSE
Email: mukhopad@calpoly.edu
Co-Advisor: Zoe Wood
Number of Students: 2
Funded By: College of Engineering DEI Initiative
Description: Engineering programs are known to be academically difficult (rigorous), and research points to engineering culture’s impact for some students from historically underserved populations related to sense of belonging in engineering. Graduation and retention gaps for various demographic groups in engineering programs are an ongoing area of work for any engineering programs focused on inclusive excellence, such as here at Cal Poly. This unique summer project unites college of engineering faculty and the engineering student services to explore the use of Machine Learning (ML) applied to text data to identify themes and factors that may impact student success.
The project will use dataset collected from students that incorporates text information regarding academic progress. We will apply state-of-the art machine learning (ML) tools to extract hidden patterns and trends by processing the natural language text. The objective of this project is to assess and analyze student experience in an academic environment at different points in students’ career and to potentially correlate themes with social identity categories.
Faculty: Javier Sanchez
Department: CSSE
Email: javiergs@calpoly.edu
Co-Advisor: Dev Sisodia, CSSE
Number of Students: 1
Funded By: College of Engineering DEI Initiative
Application Link Coming Soon
Description: Latinxs are severely underrepresented in STEM fields, partly because they face systemic barriers and typically arrive at college with a weaker science foundation from their K-12 education. Thus, they are less likely to be drawn to STEM majors. Beyond grappling with the content, Latinx students reach college with assumptions about who belongs in STEAM practices and professions; one of the highly impacted fields is Computer Science which is often viewed as challenging and boring by students.
Educators require resources and support to engage students using interactive teaching methods. Robots offer a valuable tool to enhance student engagement by allowing students to apply Computational Thinking skills in real-time. Particularly scenarios training collaborative robots (cobots), intended to be responsible for repetitive tasks while closely interacting and communicating with a human worker, could be used. Lack of experience using robots may hinder instructors from incorporating them into their teaching, particularly in underrepresented communities.
In that context, this summer’s undergraduate research project focuses on (1) Developing a software framework of components for allowing the implementation of collaborative adaptive behaviors in low-cost robots by K12 students, (2) Generating a set of lessons to the taught and learning outcomes, (3) Supporting, possibly, outreach and assessment of the potential of this approach during the summer interacting with K12 students on campus.
The student working on this project will work closely with the two students working on “Enhancing Cybersecurity Education with a Bilingual Networked Robotics Teaching Platform.” It is preferred that the student have some level of Spanish proficiency and is available to perform outreach activities during the Fall term (paid outside of SURP).
Faculty: Javier Gonzalez Sanchez
Department: CSSE
Email: javiergs@calpoly.edu
Co-PI: Rafael Guerra-Silva, OCOB
Funded by The Noyce School of Applied Computing.
Number of Students: 1
Description: A collaborative robot (cobot) is intended for direct human-robot interaction within a shared space or where humans and robots are close. The Cobot is responsible for repetitive, menial tasks, while a human worker completes more complex and thought-intensive tasks. Humanrobot collaboration and communication are critical challenges that must be addressed for trust and safety. Affective states in a human influence cognitive processes like memory and attention, and Cognition might trigger affective behaviors. Affective states and Cognitive factors are critical in the human decision-making process. While cooperation and communication could come naturally to humans, among others, due to our capacity to identify other humans’ affective and cognitive states, this capability is missing in Human-Robot interaction. In that context, this summer’s undergraduate research project focuses on (1) Developing collaborative adaptive behaviors for low-cost robots (mechanical arms) to examine the human response; (2) using a low-cost Brain-Computer Interface device (Emotiv EPOC) to gather affective and cognitive data from humans while realizing manufacturing tasks; (3) Build a model that identifies relevant affective and cognitive states and trigger robot behaviors; and (4) explore the potential of this approach for skilled and unskilled human users.
Faculty: Christopher Heylman
Department: BMED
Email: cheylman@calpoly.edu
Number of Students: 1
Funded By: College of Engineering
Description: Biomedical engineering graduate students are currently working in my lab to create a microfluidic “tumor-on-a-chip” device that will allow for the growth and maintenance of 3D vascularized human colorectal cancer tumors. These tumor tissues will be used for screening the effects of novel drugs on human colorectal cancer before resorting to costly pre-clinic animal models and human clinical trials. These devices are created by injecting a mixture of human fibroblasts, endothelial cells, colorectal cancer cells and extracellular matrix proteins into a central incubation chamber in a microfluidic device. Cell culture medium is then perfused through the tissue using the fluidic channels of the device. Given the appropriate ratio of cell types, nutrients in the medium, and flow rates, a 3D tumor with an integrated network of blood vessels can be grown. This summer research project aims to optimize existing protocols for growing these 3D vascular tumors on a chip and develop new methods for characterizing them using fluorescent microscopy. The skill sets that students will develop in this project include human cell culture, microfluidic device fabrication, fluorescent microscopy, and image analysis using ImageJ software. Successful completion of the aims of this project will open the door for further research and use of these devices to screen drugs for efficacy in treating colorectal cancer. Establishing protocols for imaging and quantitative analysis of these vascularized tumor tissues will increase the validity, reliability, and efficiency of data collection within this line of research.
Faculty: Stephen Kwok Choon
Department: ME
Email: skwokcho@calpoly.edu
Number of Students: 2
Funded By: Bonderson Project Fund
Description: I would like to submit a joint proposal for two students working on different aspects of the same project. Whereby each student would have their own deliverables and their combined work would allow for the creation of an integrated Hardware-In-The-Loop Reaction Wheel Testbed that can track, follow and adjust its orientation through the use of an on-board camera. This project is collectively focused on the design, development, and testing of a hardware-in-theloop reaction wheel testbed that can be used for research and teaching applications related to satellite navigation and control. With the goal that the collective work completed can be submitted for a conference publication. The proposed project would have both Student 1 and Student 2 initially working on the fabrication, design, and preliminary testing of the hardware required for the reaction wheel testbed. Then at the start of week 3 once the necessary parts and components have been purchased. Student 2 would focus on the computer vision – object tracking, and control required for the reaction wheel testbed through the use of a raspberry pi. Whilst, student 1 will focus on the completion of the reaction wheel testbed, and implementation of the speed control of the wheel.
Faculty: Behnam Ghalamchi
Department: ME
Email: bghalamc@calpoly.edu
Number of Students: 1
Funded By: Bonderson Project Fund
Description: This project aims to build on existing theoretical and practical knowledge of external mechanical control systems on mobile machines. Existing approaches tend to rely on electrical signals to activate mechanical switches controlling movement via servomotors, but there are associated costs in complexity, expense, speed, and responsiveness. By focusing on an externally operated, manual control mechanism, these associated costs may be reduced. Specifically, by using an Arduino uno microcontroller board as the basis, a [reverse servomotor] will translate external, mechanical feedback into control commands. Research results could benefit applications in a range of fields where improvements in complexity, economics, speed, and responsiveness can impact the use of human-controlled, mobile devices in operations.
Faculty: Jenny Wang
Department: CSSE
Co-PI: Xuan Wang, IME
Email: jwang96@calpoly.edu
Funded by The Noyce School of Applied Computing.
Number of Students: 1
Description: OpenAI is a leading research organization in the field of artificial intelligence (AI) that has developed advanced AI models, such as GPT-3 and DALL-E, which excel at generating human-like language and performing various natural language processing (NLP) tasks. However, integrating domainspecific knowledge into these models can be challenging for organizations and industries. The proposed research project aims to address this challenge by investigating innovative approaches for the secure and privacy-enabled integration of human expert knowledge with OpenAI and an advanced AI model, ChatGPT. The project will explore methods for acquiring knowledge from human experts while ensuring privacy and security controls are in place to protect sensitive information. By incorporating domain-specific knowledge and expertise from human experts, AI models can be tailored to specific industries or domains, which can have significant benefits for organizations and communities. By advancing the state-of-the-art in AI, this project will have interdisciplinary implications by enabling the integration of expert knowledge from various domains into AI models. The results of this research could benefit a wide range of fields, including higher-education, healthcare, finance, and law, by enhancing the accuracy and reliability of AI models through the incorporation of human expertise. Furthermore, the findings from this project could have important societal impacts by enabling the development of trustworthy and privacy-respecting AI models.
Faculty: Sumona Mukhopadhyay
Department: CSSE
Email: mukhopad@calpoly.edu
Funded by Gary Bloom.
Number of Students: 1
Description: This project proposes a machine learning approach for search and rescue (S & R) by extracting behavioral patterns from data collected using smartphone sensors. Building on the work done initially as a SURP 2021 project and continued through the 2021-22 academic year, the focus for this project will be on the use of computer technology for locating a missing person using machine learning/deep learning techniques for recognition. The unique physiological signals collected from smart wearable devices will be used to predict the location of the person during search and rescue. The data generated from the wearable sensor devices provide qualitative information that will be mined to extract information about the person’s behavior and situation. Sporadic activities are different from periodic activities such as walking, hiking, lying, standing and running occur less frequently. The detection of these sporadic activities are of interest during a search and rescue task which is a challenging problem. The research findings and developed techniques can be extended for other applications such as security defense, disaster rescue, health, and sleep monitoring.
Faculty: Nandeesh Hiremath
Department: AERO
Email: nhiremat@calpoly.edu
Number of Students: 1
Funded By: NNSS
Description: Building a rotating test stand for dynamically changing bluff body orientations subjected to high-speed f lows is the goal of this project. The rotating test stand is a crucial component in characterizing aerodynamics of bodies of arbitrary shapes at arbitrary orientations subjected to supersonic speeds. A similar test setup (PI’s own efforts) has proven to be successful and is in practice inside the Cal Poly lowspeed wind tunnel. Adapting the design to supersonic wind tunnel will require significant changes to the test stand geometry, assessing wind tunnel access points, axes of rotations, and vibrational load limits. In relation to ongoing testing in the low-speed wind tunnel where the Reynolds number effects are being evaluated, such a rotating test stand will enable evaluating Mach number effects at high-speed flows under dynamic conditions. The project will aim at designing and fabricating a test stand coupled with stepper/brushless motor and gears suitable to test canonical shapes like spheres and cubes similar to atmospheric re-entry/debris objects. Shadowgraph imaging technique will be used to validate the design limitations of the rotating test stand. The work emphasizes on tying in concepts from structural mechanics, kinematics, design, and fabrication, suitable for an undergraduate student to gain exposure to wind tunnel testing and building a test setup.
Faculty: Stephen Beard
Department: CSSE/CPE
Email: srbeard@calpoly.edu
Funded by The Noyce School of Applied Computing.
Number of Students: 1
Description: Touchscreen-based mobile devices, such as smart phones, are integral to many of our lives. They are increasingly responsible for everything from communication to to managing our finances on the go. Unfortunately, their batteries are not infinite and we often we need to charge them on the go as well in places like cars, airports, and offices. While it is well known that this is unsafe, recent work has demonstrated a surprising new attack: namely that an attacker can infer a 4-digit PIN with 99.3% accuracy by simply measuring the power draw from a charging cable while the PIN is entered. By combining the methods of that paper with some cipher based attacks, I believe this attack can be extended to recreating keyboard-based text entry on a smartphone via analysis of the power trace. A team of students is currently recreating the power trace capture and PIN inference systems. This project will extend their work to include text inference. While this project will include elements of signal processing, convolutional neural networks (CNN), and text analysis, students need not have deep familiarity with any of these areas.
Faculty: Jill Speece
Department: IME
Email: jespeece@calpoly.edu
Number of Students: 1
Funded By: Bonderson Project Fund
Description: The primary role of the radiologist is to produce a report based on diagnostic imaging that helps the referring clinician develop a plan of care for their patients. Continued increase in imaging volume, a decline in radiology labor, and ever-fluctuating payor reimbursements has necessitated the development of a faster way to compose high quality reports. With voice recognition, the most common method of composing a report, the radiologist dictates custom phrases for each section of the report and the conclusion. It is a highly labor-intensive method of report composition, prone to voice recognition errors, and requires the radiologist to edit each dictated sentence to ensure accuracy. An advanced macro-button toolbar system was developed that helps the radiologist decrease report turnaround time and increase report quality. With the click of a button, the report is populated instantly with standardized error-free text. The result is reduced report composition and editing time, and overall faster report turnaround time. Additional benefits of macro button report creation include reduced radiologist fatigue, standardization of reports across the practice, and the ability to satisfy reporting requirements needed for systematic reimbursement. The proposed research opportunity is to study the advanced macro-button toolbar system in use at a local outpatient imaging center and perform a statistical analysis to verify the abovementioned benefits and assess barriers to adoption.
Faculty: Amanda Johnston
Department: ME
Email: acjohnst@calpoly.edu
Number of Students: 1
Funded By: College of Engineering
Description: Description of Research Project: Engineering students are often more engaged and motivated when they see the purposes of their work and the ways that their work will help the world. However, foundational level courses are often taught with decontextualized problems and examples. The purpose of this project is to incorporate context focused on sociotechnical thinking into engineering statics and dynamics courses. The SURP student will conduct a work on developing projects and activities to be integrated into statics and dynamics courses that integrate sociotechnical thinking skills. The goal of this SURP project is to work with the faculty member to develop background information and initial work to submit an NSF grant for funding for a community of practice of faculty members to implement and test the curriculum into statics and dynamics courses at Cal Poly.
Faculty: Amanda Johnston
Department: ME
Email: acjohnst@calpoly.edu
Number of Students: 1
Funded By: Bonderson
Description: The Cal Poly, SLO mechanical engineering department is rare among engineering programs in that it requires a course that involves design in each of the four years of undergraduate study. The purpose of this project is to better understand how students’ conceptualizations and understanding of design change and develop over these courses, with the goal of better understandings of how to support student learning and improve the courses. The goal of this SURP project is to support data collection from mechanical engineering students at a variety of points in their academic careers and to conduct initial data analysis. The data will consist of survey data, which will be collected during the spring 2023 quarter prior to the SURP, and interview data, which will be collected during summer 2023 during the SURP project and which the SURP student will assist with. The SURP students will work on data analysis of the survey data, which will consist of qualitative data analysis.
Faculty: Christopher Heylman
Department: BMED
Email: cheylman@calpoly.edu
Number of Students: 1
Funded By: College of Engineering
Description: Biomedical engineering graduate students are currently working in my lab to create a microfluidic “tumor-on-a-chip” device that will allow for the growth and maintenance of 3D vascularized human colorectal cancer tumors. These tumor tissues will be used for screening the effects of novel drugs on human colorectal cancer before resorting to costly pre-clinic animal models and human clinical trials. These devices are created by injecting a mixture of human fibroblasts, endothelial cells, colorectal cancer cells and extracellular matrix proteins into a central incubation chamber in a microfluidic device. Cell culture medium is then perfused through the tissue using the fluidic channels of the device. Given the appropriate ratio of cell types, nutrients in the medium, and flow rates, a 3D tumor with an integrated network of blood vessels can be grown. This summer research project aims to test and validate a newly constructed live-cell imaging system. This system is an incubation chamber that allows control of the temperature and pH of a live cell culture while on a microscope stage. This allows for microscopic imaging of live cells and tissues, such that time-lapse videos of the culture can be generated. The skill sets that students will develop in this project include human cell culture, fluorescent microscopy, and image analysis using ImageJ software. Successful completion of the aims of this project will open the door for further research and use of this live-cell imaging system to assess an array of cells and tissues. The ability to assess the same cells and tissues over time allows for an array of interesting scientific queries using our tumor model, particularly with respect to it’s main intended use as a tool for screening drug compounds.
Faculty: Alan Zhang
Department: ME
Email: zhangas@calpoly.edu
Number of Students: 2
Funded By: College of Engineering
Note: The students working on this project will work directly with the student working on the project Upper Limb Tensegrity Exoskeletons – Designing for Social Justice
Description: Tensegrity structures are composed of stiff rods and elastic cables suspended in a flexible tension network. Their inherent properties have several key advantages when used in assistive medical devices such as supportive braces or rehabilitation exoskeletons: 1) the light weight and natural compliance reduce the power consumption required to operate the system; 2) the system stiffness and pretension can be individually tuned to accommodate the user’s needs; and 3) the impact-resistant properties can protect users in the event of collisions and falls. This project will explore the design space of assistive tensegrity devices to augment human dexterity in the upper limb. The SURP student will build suitable tensegrity configurations through rapid prototyping and then characterize their performance in experiment. The work will contribute to a new data-driven framework for the long-term goals of the work: advancing the capability of automated tensegrity system design and contributing low-cost, custom tensegrity devices to the next generation of assistive medical devices.
Faculty: Alan Zhang
Department: ME
Email: zhangas@calpoly.edu
Number of Students: 1
Funded By: College of Engineering DEI Initiative
Note: The student working on this project will work directly with the students working on Upper Limb Tensegrity Exoskeletons.
Description: Tensegrity structures are composed of stiff rods and elastic cables suspended in a flexible tension network. Their inherent properties have several key advantages when used in assistive medical devices such as supportive braces or rehabilitation exoskeletons: 1) the light weight and natural compliance reduce the power consumption required to operate the system; 2) the system stiffness and pretension can be individually tuned to accommodate the user’s needs; 3) the impact-resistant properties can protect users in the event of collisions and falls; and 4) the system can be built with off-the-shelf components to reduce costs and provide accessible devices for low-income communities.
This project will explore the design space of assistive tensegrity devices to augment human dexterity in the upper limb. The SURP student will create a design framework for social justice by researching the local context and structural inequalities surrounding access to assistive medical devices. Specifically, they will characterize user needs, risk and cost analyses, and healthcare access in low-income communities. Potential applications for the devices include passive support to reduce muscle fatigue from manual labor, strength training for physical therapy, and fully powered systems to assist human motion and improve quality of life.