SURF-IT Research Projects

 

Participants | Research Projects

The SURF-IoT program provides a unique 10-week summer research opportunity for UCI undergraduates to become immersed in research and applications related to the Internet of Things (IoT).

Calit2 faculty, students and research professionals with leading California technology companies conduct research in “living laboratories” focused on the scientific, technological, and social components related to the Internet of Things.

2017 SURF-IT Research Projects

The following faculty-mentored research projects are available during the 2017 SURF-IT Program. They are divided into their own unique areas of research. Select a link for an overview of the project, associated faculty mentors, project prerequisites, and related publications.

SURF-IoT Undergraduate Research Projects

    1) At Home Health Monitoring Using a Social Network 

    2) Cooperative Localization Algorithm Implementation over a Network of Robots Operating Under ROS: An Experimental Study 

    3) Edge/Fog Computing Service Development for Data Analytics in Healthcare Internet-of-Things Systems (2 Students) 

    4) Improving TextDB Interface for Powerful IoT Data Analytics 

    5) Interactive Projected Augmented Reality on Table-Top Objects 

    6) Optimizing Graphene Terahertz (THz) Field Effect Transistors 

    7) PET - A Personal Embodied Trainer to Promote Physical Therapy at Home 

    8) Projected Augmented Reality Games on Interactive Sandpit 

    9) Smart Pain Assessment Based on Internet-of-Things 

    10) Technology Supported Family Care Coordination for Stroke Survivors and Caregivers 




 Project #1:  At Home Health Monitoring Using a Social Network
Faculty Mentor:  Professor Mark BachmanElectrical Engineering & Computer Science

Description:  We are entering a time when people will be empowered to participate in their own health maintenance and optimization through a wide variety of enabling technologies. Various consumer grade health devices will become ubiquitous in homes. Such devices include monitoring devices (e.g., bathroom scales, blood pressure cuffs, and other physiological monitors), intervention devices (e.g., exercise devices, rehabilitation devices), assistive devices (e.g., reminder devices, medication dispensers), and other related devices (e.g., cognition games, communication devices).

An important feature of these devices is the need to communicate data to and from a personal database, typically in the cloud. This data may be necessary to control the device (such as medication schedules) or may be provided from the device (such as physiological results). Today, most devices utilize their own software and their own databases to manage this data, making interoperability between devices impossible and making it difficult to share data with other stakeholders such as medical personnel, caregivers and family members. Ideally, devices could connect to a shared database making it easier for people to use multiple devices and share with key people.

The Iris project, led by Calit2 and the Irvine Health Foundation, is a developing a social network for healthy living that manages members data easily and securely, enabling members to collect, curate, and share data relating to their health and lifestyle. Iris represents an ideal platform for connecting to consumer health devices and sharing health data.

This SURF-IoT project will develop and demonstrate the ability to connect external health devices to the Iris social network in the cloud, allowing members to use multiple devices and share their data with relevant stakeholders.

Student’s Involvement and Expected Outcomes:

Students will work with an existing development team to assist in developing web-based code and user interfaces for health-related devices that connect to the Iris social network. Specific tasks and outcomes will be determined based on the experience and aptitude of each student. Students may also prepare promotional and communication materials for the project, as well as participate in developing business strategies around the project. Students will give formal presentation every two weeks on their progress.

Prerequisites: Students should have some experience in web design and/or programming (especially HTML5/Javascript). Students should have high energy, be motivated, responsible, with strong work ethic and the ability to work independently. Students should also have a strong interest in human health, especially for seniors and the aging population.

Recommended Web sites and publications: 
   : www.irislocal.com



 Project #2:  Cooperative Localization Algorithm Implementation over a Network of Robots Operating Under ROS: An Experimental Study
Faculty Mentor:  Professor Solmaz KiaMechanical & Aerospace Engineering

Description:  This project is involved with implementing a distributed cooperative localization algorithm developed in Prof. Kia’s Lab over a group of five robots functioning under the Robot Operating System (ROS). The main focus of this work is on developing programs for robots motion generation, Kinect camera measurements, and object tracking using an overhead camera system. This project will expose the students to programing for multi-platform devices connected to each other through wireless connections.

Background information about cooperative localization algorithms: Location is a vital dimension of the IoT concept that encompasses the ability of "things" to sense and communicate their geographic position. ``Location of things'' is proposed as one of the vital organizing principles for anything connected to Internet. Currently Global Positioning System (GPS) is one of the main technologies used for self-localization of smart devices/agents. However, the accuracy attained by GPS (unassisted one) is in the order of meters, which may not be adequate for some applications, for example, for driving smart driverless cars. Also, positioning via GPS requires unobstructed access to four GPS satellites that may not be always possible, e.g., in indoor environments or places with tall infrastructures. To compensate for GPS's limitations, various positioning systems mostly based on using measurements taken from well-defined features and markers in structured environments has been proposed and investigated. Relaying on external features for localization comes with complex sensing, recognition and data association overheads. Pre-installed beacons and markers with known identities and locations can decrease this overhead but installing such markers comes with extra cost, and, moreover, may not be possible in every environment. An alternative localization technique, which can resolve these issues, can be Cooperative localization (CL). In CL a group of mobile agents, each with sensing, processing and communication capabilities, use relative measurements with respect to one another as a feedback signal to jointly estimate the pose of team members, resulting in an overall increase in accuracy of the entire team.

Student’s Involvement and Expected Outcomes: This is a supervised independent research. The student will work with a Ph.D. student on implementing an existing CL algorithm over a robotic testbed in Prof. Kia’s Cooperative Systems Lab. The student needs to be familiar with C++ or Python to program the algorithm for ROS. The outcome of this project is going to be a fully decentralized implementation of a CL algorithm.

Prerequisites: Strong background in C++, familiarity with Payton familiarity with Linux/Ubuntu

Recommended Web sites and publications: 
   S.S. Kia, S Rounds, S Martinez, “Cooperative Localization for Mobile Agents: A Recursive Decentralized Algorithm Based on Kalman-Filter Decoupling”, IEEE Control Systems 36 (2), 86-101.:
   ROS Tutorial: http://wiki.ros.org



 Project #3:  Edge/Fog Computing Service Development for Data Analytics in Healthcare Internet-of-Things Systems (2 Students)
Faculty Mentor:  Professor Nikil D. DuttComputer Science

Description:  Internet of Things enabled healthcare provides connection between things (i.e., wearable and environmental objects) to enhance healthcare services and subsequently the quality of life. Heterogeneous medical and environmental data (e.g., vital signs, physical activity and environment data) can be collected continuously via various sensors. In order to utilize the full potential of the collected information, data analytics is needed. In most of IoT-based healthcare systems, especially at smart homes or hospitals, a bridging point (i.e., gateway) is needed between sensor infrastructure network and the Internet. The gateway at the edge of the network often just performs basic functions such as translating between the protocols used in the Internet and sensor networks. These gateways have beneficial knowledge and constructive control over both the sensor network and the data to be transmitted through the Internet. In this project, we exploit the strategic position of such gateways at the edge of the network to offer several higher-level services such as local storage, real-time local data processing, embedded data mining, etc., presenting thus a Smart e-Health Gateway. This project will develop a prototype of a Smart e-Health Gateway where some of the discussed higher-level features have been implemented. The student is expected to work closely with the existing team in various medical data analytics tasks.

Students’ Involvement and Expected Outcomes:

Student 1:
Developing interfaces on the gateway, which is an embedded computing board (e.g., Pandaboard) running Linux OS, to read sensory data from sensors over wireless communication (e.g., Bluetooth or WiFi)
Programming Microcontroller-based sensor nodes (e.g., Arduino) to transfer data to the gateway
Developing light-weight signal processing (noise filtering) at the gateway

Student 2:
Linking the gateway to the cloud
Developing medical data analytics (e.g., feature extraction, machine learning) hierarchically at the gateway and the cloud
User interface (Dashboard) development at the cloud to stream and display the data and the results

Additional Mentor: Dr. Amir M. Rahmani

Prerequisites: Student 1: C or C++ programming skills preferably for microcontrollers, Preferably some experience in wireless sensor networks (WSN) and embedded software development, Some experience in digital signal processing, Python programming

Student 2: Some experience in digital signal processing and machine learning, Python programming, Programming cloud service, Basic knowledge of data-base design and programming (e.g., MYSQL)

Recommended Web sites and publications: 
   Amir M. Rahmani, Tuan Nguyen Gia, Behailu Negash, Arman Anzanpour, Iman Azimi, Mingzhe Jiang, Pasi Liljeberg, "Exploiting Smart E-Health Gateways at the Edge of Healthcare Internet-of-Things: A Fog Computing Approach," Elsevier Journal of Future Generation Computer Systems (Elsevier- FGCS), 2017.: https://www.researchgate.net/publication/313471512_Exploiting_Smart_E-Health_Gateways_at_the_Edge_of_Healthcare_Internet-of-Things_A_Fog_Computing_Approach
   Exploiting Smart E-Health Gateways at the Edge of Healthcare Internet-of-Things: A Fog Computing Approach: https://www.researchgate.net/publication/313471512_Exploiting_Smart_E-Health_Gateways_at_the_Edge_of_Healthcare_Internet-of-Things_A_Fog_Computing_Approach
   Tuan Nguyen Gia, Ming-Zhe Jiang, Amir M. Rahmani, Tomi Westerlund, Pasi Liljeberg, Hannu Tenhunen, “Fog Computing in Healthcare Internet-of-Things: A Case Study on ECG Feature Extraction,” in Proc. of IEEE International Conference on Computer and Information Technology (CIT’15), 2015, UK.: https://www.researchgate.net/publication/281176022_Fog_Computing_in_Healthcare_Internet-of- Things_A_Case_Study_on_ECG_Feature_Extraction
   Arman Anzanpour, Amir M. Rahmani, Pasi Liljeberg, Hannu Tenhunen, “Context-Aware Early Warning System for In-Home Healthcare Using Internet-of-Things”, in Proc. of International Conference on IoT Technologies for HealthCare (HealthyIoT’15), Springer LNICST, 2015, Italy.: https://www.researchgate.net/publication/281175785_Context-Aware_Early_Warning_System_for_In- Home_Healthcare_Using_Internet-of-Things



 Project #4:  Improving TextDB Interface for Powerful IoT Data Analytics
Faculty Mentor:  Professor Chen LiComputer Science

Description:  Many companies and organizations need software solutions to harvest valuable knowledge from large amounts of data especially in IoT applications. One of the important IoT domains is social media (e.g., tweets, Facebook messages, and Weibo), where humans are acting “as sensors” to produce a huge amount of information at an unprecedented speed. Analyzing this type of information is very critical to researchers and practitioners to gain insights and make time-critical decisions.

To achieve the goal, we are actively developing an open source project called TextDB [1], a data-analysis system to support declarative and GUI-based text analytics. Our goal is to (1) modularize common computation as basic operators; (2) provide a GUI for developers to form a workflow plan declaratively without writing code; (3) allow developers to debug the plan by pausing/resuming its execution, exploring and tracing intermediate results; (4) support indexing whatever possible to improve performance; (5) allow other packages in various languages (e.g., Python, R) to be wrapped and integrated; and (6) support text analytics as a Web-based service. Our vision is to free developers from low-level computation so that they can focus on their main business logic. The system is currently used by Public Health researchers at UCI to conduct tweet analysis related to climate change.

Student Involvement and Expected outcome: The selected student will work closely with the TextDB team to improve the existing user interface (UI) of TextDB [2] to increase its usability and add more functionalities. Since the project is open source and follows a rigorous software engineering practice, the student will have an excellent opportunity to gain experience of software development. The student will have the chance to learn various techniques and tools such as git, wiki, Java, maven, and javascript. The student will also interact with existing users of the system to collect their feedback for improvements. The expected outcome will be a more powerful UI for the system.

TextDB is a success of previous SURF programs. The leading student of the system was a SURF fellow in 2016, who made significant contributions to the system and benefited from the project. Also a demo paper of the system [3] recently won the Best Demo paper award at the ICDE 2017 conference, a prestigious venue in the database research community. We expect the new SURF fellow to continue the success in the project.

Prerequisites: Candidates should have experiences in frontend development and are familiar with HTML, CSS, JavaScript, JQuery, and Angular2. More importantly, they should also have a strong desire to learn new knowledge and “get things done” before deadlines.

Recommended Web sites and publications: 
   TextDB project: https://github.com/TextDB/textdb
   Current GUI: http://textdb.ics.uci.edu/climate
   ICDE 2017 demo paper: https://chenli.ics.uci.edu/files/icde2017-textdb-demo.pdf



 Project #5:  Interactive Projected Augmented Reality on Table-Top Objects
Faculty Mentor:  Professor Aditi MajumderComputer Science

Description:  Additional Faculty Mentor: Gopi Meenakshisundaram, Computer Science (gopi@uci.edu)

iGravi has been a pioneer in creating immersive virtual reality environments where multiple projectors are used to illuminate large surfaces to create a seamless display in which one or more users can navigate through virtual environments and interact with them.

In this project we are going to use the same techniques to light table-top objects with multiple mobile pico-projectors which are observed by multiple mobile cameras. The observations from the camera allow us to align the imagery from multiple projectors to create 360 degrees wrap-around imagery and then interact with it using multiple modalities like laser pointers or hand gestures to change the appearance of the table top object. All the devices are connected wirelessly to the cloud while most of the computing happens in the cloud using a software as service model. This creates next generation internet of devices systems for creating unique visual experiences that can applied in multiple domain including education, entertainment, digital signage, and audio-visual technology.

Student’s Involvement and Expected Outcomes: The graduate students in iGravi have created the first generation proof-of-concept system ironing out all the algorithmic details to create a projected augmented reality system for table-top objects. However, most of the code was developed in MATLAB since the focus was on algorithm development. Therefore, this system does not have the interactive element which is essential for interaction with users. Therefore, this system is currently non-interactive.

The summer intern will work closely with graduate students and Prof. Aditi Majumder to port different components of the system to C/C++ and OpenGL as is appropriate; (b) create an interactive user interaction that can allow interaction with the table top object via tablet, mobile phone, laser pointers or hand gestures.

The summer intern will therefore get unique experience of working with projectors and cameras to design projected augmented reality systems which promise to be the VR/AR systems of the future due to their capability to accommodating more than one user, unlike the AR/VR glasses than can only work with single users. He will also get unique exposure to auto- calibration methodologies essential to work with any network of visual sensors or displays.

Additional Graduate Student Mentors: Mahdi Abbaspour Tehrani, Mehdi Rahimzadeh

Prerequisites: Students who have taken at least two of CS 111, CS 112, CS 114, CS 116 and CS 117 (the more the better) are adequately prepared for this project. Students must have good C/C++ coding skills. They must have taken all the basic CS major core courses in algorithms, data structures and programming. We prefer junior or senior students.

Recommended Web sites and publications: 
   Advances in Large Area Displays: The Changing Face of Visualization, Aditi Majumder, Behzad Sajadi, IEEE Computer, 2013 (Paper): http://www.ics.uci.edu/~majumder/pub.html
   Advances in Large Area Displays: The Changing Face of Visualization, Aditi Majumder, Behzad Sajadi, IEEE Computer, 2013 (Video): http://www.ics.uci.edu/~majumder/docs/ieee13-video.mp4
   Markerless View Independent Geometric Registration of Multiple Distorted Projectors on Vertically Extruded Surfaces Using a Single Uncalibrated Camera, Behzad Sajadi, Aditi Majumder, IEEE Transactions on Visualization and Computer Graphics, 2009 (Paper): http://www.ics.uci.edu/~majumder/docs/VIS09CURVED.pdf
   Markerless View Independent Geometric Registration of Multiple Distorted Projectors on Vertically Extruded Surfaces Using a Single Uncalibrated Camera, Behzad Sajadi, Aditi Majumder, IEEE Transactions on Visualization and Computer Graphics, 2009 (Video): http://www.ics.uci.edu/~majumder/pub.html
   A Scalable Distributed Paradigm for Multi-User Interaction with Tiled Rear Projection Display Walls, Pablo Roman, Maxim Lazarov, Aditi Majumder, IEEE Transactions on Visualization and Computer Graphics, 2010 (Paper): http://www.ics.uci.edu/~majumder/docs/VIS10.pdf
   A Scalable Distributed Paradigm for Multi-User Interaction with Tiled Rear Projection Display Walls, Pablo Roman, Maxim Lazarov, Aditi Majumder, IEEE Transactions on Visualization and Computer Graphics, 2010 (Video): http://www.ics.uci.edu/~majumder/pub.html



 Project #6:  Optimizing Graphene Terahertz (THz) Field Effect Transistors
Faculty Mentor:  Professor Peter J. BurkeElectrical Engineering & Computer Science

Description:  The Internet of things (IoT) will heavily rely on the implementation of novel wireless sensors and communication devices. As such, two-dimensional materials like graphene stand as ideal candidates for use in high-speed electronics due to extremely high carrier mobilities and nanoscale dimensions. A major challenge when fabricating graphene field effect transistors (GEFTs) is the diminished electrical properties that result during device fabrication. An undergraduate researcher will explore new methods to improve the electrical properties of GFETs by implementing unexplored graphene transfer methodologies. These developed techniques will be characterized and compared to existing protocol. Researchers will get the opportunity to learn skills such as graphene growth and transfer, along with a myriad of material characterization techniques including microscopy, electrical measurement, and data analysis.

Student’s Involvement and Expected Outcomes:

• GFET bottom-up fabrication (substrate modification using wet chemistry, graphene transfer including wet etch and electrochemical delamination, GFET electrical measurement, and material characterization).
• Characterization and benchmarking techniques to demonstrate improved electrical properties
• Outcome: Student will learn cutting edge techniques for bottom-up nanoscale device fabrication, along with workhorse material characterization techniques. These skills and techniques can be applied to material science, chemistry, and electrical engineering in general.

Prerequisites: We seek students with a strong desire to learn cutting edge material science methods. Students with the goal to continue research throughout the school year.

Recommended Web sites and publications: 
   : http://pubs.rsc.org/-/content/articlehtml/2015/tc/c5tc01771h
   : http://onlinelibrary.wiley.com/doi/10.1002/adma.201101340/full
   : http://pubs.acs.org/doi/abs/10.1021/acs.chemmater.6b01826



 Project #7:  PET - A Personal Embodied Trainer to Promote Physical Therapy at Home
Faculty Mentor:  Dr. Sergio Gago MasagueBiomedical Engineering

Description:  Additional Mentor: Sergio Masague, Calit2 (sgagomas@calit2.uci.edu)

Embodied Trainers may provide two important advantages when added to conventional or digital systems to promote physical therapies: (1) Providing an animated biped model as an interface to represent exercises to be mimicked by the user, and (2) delivering verbal and nonverbal communication (e.g. intonation, mood and facial expression) to improve communication, enjoyment and build a social bond that may drive the user’s attitude towards a particular goal, for instance, training harder or for longer periods. Previous research in the field suggests that Embodied Trainers have many potential features to empower home therapies. The increasing proliferation of affordable computational technologies and its subsequent prevalence within households set the scene for this new technology to take place.

Meanwhile, the world population is growing older, bringing a greater demand for strategies to promote healthy lifestyles. Wellness programs, remote health and self-care in the home setting are becoming increasingly important in long-term care to support rehabilitation and the elderly population. For instance, physical training for rehabilitation is of particular importance for covering motor skills and preventing secondary conditions, such as frailty, cognitive disorders and depression The purpose of the present study is to implement an application including an animated embodied trainer as a persuasive technology to conveniently promote physical exercise or therapies at home by providing users with (a) guidance and (b) motivation and/or enjoyment in a cost-effective way. Hence this technology can be affordable by most users. This project also aims to explore the potential of video casting to the TV and augmented/virtual reality as an alternative delivery method of the content.

Students' Involvement and Expected Outcomes

The students mentored in this project will work in a proactive research team guided by the faculty listed above to design and identify available digital technologies to implement the innovative application proposed. Specifically, the students will conduct research in one or some of the following topics:

1. Physical exercise at home for wellness and rehabilitation. It’s expected to focus on population who present a sedentary live or who could benefit from physical exercise for other reasons, such as the elderly and survivors after a body injury who have the need of conducting physical rehabilitation.
2. Human-Computer interaction; human-centric interfaces to motivate and engage users.
3. Digital Arts to model and animate content and 3D characters (Embodied Trainer).
4. Embedded Systems to design and choose the right sensing technology to track user’s performance.
5. Database technologies to manage data generated by the user and the target device/s and store it in a cloud server accessible by a web interface, which will be used by healthcare providers or caregivers to assess users’ progress.
6. Machine learning and predictive analytics to create training patterns and provide adaptative feedback.
7. Patients’ privacy and data confidentiality that build a secure access protocol that will be integrated in the aforementioned framework.

Prerequisites: This project is highly interdisciplinary; we are looking for students with interests in several fields; Sociology, Psychology, Orthopaedics, Public Health, Informatics and Computer Sciences, Arts and Engineering, who care about state-of-art health technologies to improve population’s wellness and quality of life. Innovative thinkers with relevant experience are encouraged to apply. Hands on experiences in 2D/3D modeling and animation tools (3Ds Max, Iclone, Maya, Poser) and graphic design (Photoshop, Illustrator) are preferred for students majoring in Art. Java, C++, C#, Unity3D, ActionScript, Swift and Objective C programming experience is preferred for Engineering and ICS students.

Recommended Web sites and publications: 
   Babu, S, Catherine Zanbaka, J Jackson, and TO Chung. 2005. “Virtual Human Physiotherapist Framework for Personalized Training and Rehabilitation.” Graphics Interface, 2.: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.118.8726\nhttp://www.cs.ubc.ca/~van/GI2005/ Posters/VHP.pdf.
   Brown, Marybeth, David R. Sinacore, Ali A. Ehsani, Ellen F. Binder, John O. Holloszy, and Wendy M. Kohrt. 2000. “Low-Intensity Exercise as a Modifier of Physical Frailty in Older Adults.” Archives of Physical Medicine and Rehabilitation 81 (7): 960–65. doi:10.1053/apmr.2000.4425.:
   Buttussi, Fabio, and Luca Chittaro. 2008. “MOPET: A Context-Aware and User-Adaptive Wearable System for Fitness Training.” Artificial Intelligence in Medicine 42 (2): 153–63. doi:10.1016/j.artmed.2007.11.004.:
   Dancu, A, A C M Special Interest Group on Computer-Human Interaction, and I T University of Copenhagen. 2012. “Motor Learning in a Mixed Reality Environment.” 7th Nordic Conference on Human-Computer Interaction: Making Sense Through Design, NordiCHI 2012, 811–12. doi:10.1145/2399016.2399160.:
   Dawe, D, and R Moore-Orr. 1995. “Low-Intensity, Range-of-Motion Exercise: Invaluable Nursing Care for Elderly Patients.” Journal of Advanced Nursing 21 (4): 675–81. doi:10.1046/j.1365-2648.1995.21040675.x.:
   Eike Dehling, Dennis Reidsma, Job Zwiers, Herwin Welbergen. 2011. “The Reactive Virtual Trainer.” University of Twente.:
   Fasola, Juan, and M Mataric. 2011. “Comparing Physical and Virtual Embodiment in a Socially Assistive Robot Exercise Coach for the Elderly.” Center for Robotics and Embedded Systems.: http://cres.usc.edu/Research/files/Fasola_11_003.pdf.
   Jung, Hee-Tae, Jennifer Baird, Yu-Kyong Choe, and Roderic A. Grupen. 2011. “Upper-Limb Exercises for Stroke Patients through the Direct Engagement of an Embodied Agent.” Proceedings of the 6th International Conference on Human-Robot Interaction - HRI ’11, March.:
   Matthews, Judith T., Gustavo J. M. Almeida, Elizabeth A. Schlenk, Reid Simmons, Portia Taylor, and Renato Ramos Da Silva. 2012. “Usability of a Virtual Coach System for Therapeutic Exercise for Osteoarthritis of the Knee.” IROS 2012 Workshop on Motivational Aspects of Robotics in Physical Therapy, October.:
   Reidsma, D, E Dehling, and H Welbergen. 2011. “Leading and Following with a Virtual Trainer.” 4th International Workshop on Whole Body Interaction in Games and Entertainment, 4.: http://purl.utwente.nl/publications/79497\nhttp://doc.utwente.nl/79497/.
   Gago S, Fortier M, Martinez A. PainBuddy – Using Virtual Characters to Improve Home-Based Therapy for Children Suffering from Cancer. In: Medicine 2.0 Conference. JMIR Publications Inc., Toronto, Canada; 2014. Accessed April 17, 2015.: http://www.medicine20congress.com/ocs/index.php/med/med2014/paper/view/2747



 Project #8:  Projected Augmented Reality Games on Interactive Sandpit
Faculty Mentor:  Professor Aditi MajumderComputer Science

Description:  Additional Faculty Mentor: Gopi Meenakshisundaram, Computer Science (gopi@uci.edu)

iGravi has been a pioneer in creating immersive virtual reality environments where multiple projectors are used to illuminate large surfaces to create a seamless display in which one or more users can navigate through virtual environments and interact with them.

In this project we are going to use the same techniques to light a sandpit with multiple projectors and create projected augmented reality games. We will focus on two games.

The first game deals with real-time adaptation of the projected imagery to changing shape of the illuminated sandpit. In this game, we envision one of more users using their hands to change the sandpit shape and the illumination adapting to the modified shape thus created by projecting fluid (e.g. water) motions that abides by the constraints imposed by the changing shapes.

The second game deals with using a dynamic (movable) projector being moved by a user to project an animated object on the illuminated sandpit such that the animated object moves by following the constraints of the physical shape or projected content. For example, a walking human projected from a moving projector climbs the hills created in the sandpit or walks through the projected roads on the sandpit geometry.

All the devices are connected wirelessly to the cloud while most of the computing happens in the cloud using a software as service model. This creates a next generation internet of devices systems for creating interactive projected augmented reality gaming experiences that can be used for many edutainment applications.

Student’s Involvement and Expected Outcomes: The graduate students in iGravi have created the first generation proof-of-concept system ironing out all the algorithmic details to create proof-of-concept games. However, most of the code was developed in matlab since the focus was on algorithm development. Therefore, this system does not have the interactive element which is essential interactive games.

The UG summer intern will work closely with graduate students and Prof. Aditi Majumder to port different components of the system to C/C++ and OpenGL as is appropriate to enable real time gaming experience for one or more users.

The summer intern will therefore get unique experience of working with projectors and cameras to design new generation projected augmented reality gaming systems with unique capability of providing multi-user games, unlike the AR/VR glasses than can only work with single users. The summer intern will also get unique exposure to methodologies essential to work with any network of visual sensors or displays.

Additional Graduate Student Mentor: Mahdi Abbaspour Tehrani

Prerequisites: Students who have taken at least two of CS 111, CS 112, CS 114, CS 116 and CS 117 (the more the better) are adequately prepared for this project. Students must have good C/C++ coding skills. They must have taken all the basic CS major core courses in algorithms, data structures and programming. We prefer junior or senior students.

Recommended Web sites and publications: 
   Advances in Large Area Displays: The Changing Face of Visualization, Aditi Majumder, Behzad Sajadi, IEEE Computer, 2013 (Paper): http://www.ics.uci.edu/~majumder/pub.html
   Advances in Large Area Displays: The Changing Face of Visualization, Aditi Majumder, Behzad Sajadi, IEEE Computer, 2013 (Video): http://www.ics.uci.edu/~majumder/docs/ieee13-video.mp4
   Markerless View Independent Geometric Registration of Multiple Distorted Projectors on Vertically Extruded Surfaces Using a Single Uncalibrated Camera, Behzad Sajadi, Aditi Majumder, IEEE Transactions on Visualization and Computer Graphics, 2009 (Paper): http://www.ics.uci.edu/~majumder/docs/VIS09CURVED.pdf
   Markerless View Independent Geometric Registration of Multiple Distorted Projectors on Vertically Extruded Surfaces Using a Single Uncalibrated Camera, Behzad Sajadi, Aditi Majumder, IEEE Transactions on Visualization and Computer Graphics, 2009 (Video): http://www.ics.uci.edu/~majumder/pub.html
   A Scalable Distributed Paradigm for Multi-User Interaction with Tiled Rear Projection Display Walls, Pablo Roman, Maxim Lazarov, Aditi Majumder, IEEE Transactions on Visualization and Computer Graphics, 2010 (Paper): http://www.ics.uci.edu/~majumder/docs/VIS10.pdf
   A Scalable Distributed Paradigm for Multi-User Interaction with Tiled Rear Projection Display Walls, Pablo Roman, Maxim Lazarov, Aditi Majumder, IEEE Transactions on Visualization and Computer Graphics, 2010 (Video): http://www.ics.uci.edu/~majumder/pub.html



 Project #9:  Smart Pain Assessment Based on Internet-of-Things
Faculty Mentor:  Professor Nikil D. DuttComputer Science

Description:  In the near future, it is predictable that any gadget will be identified by a unique address. This will lead to an addressable sequence of computers, sensors, actuators, PDAs and mobile phones. As defined by European Commission Information Society, the Internet of Things (IoT) is a manageable set of convergent developments in sensing, identification, communication, networking, and informatics devices and systems. The IoT is in the revolutionary road and it will remodel the healthcare sector on the way in terms of social benefits and penetration as well as economics. Enabled by ubiquitous computing, all the healthcare system entities (individuals, appliances, medicine) can be monitored and managed continuously. The IoT’s connectivity provide a way to monitor, store and utilize health and wellbeing related data (diagnosis, treatment, recovery, medication, finance, and even daily activity) on a 24/7 basis.

The objective of this project is to benefit from the offered features of the IoT and sensor networks to provide an automatic tool which can detect and assess pain employing behavioral and physiologic indicators. We aim to assess pain based on changes in electromyographic (EMG) activity in facial muscles, i.e. changes in facial expressions and simultaneously use physiologic signs such as heart rate, blood pressure, and intracranial pressure as adjunct measures to develop an algorithm for pain assessment in critically ill patients. At present, patients’ pain is detected primarily through behavioral assessment while physiologic signs are secondary and only supportive for pain evaluation. Assessment of pain is particularly difficult in patients with minimal or no possibilities of indicating pain such as during critical illness. The aim of this project is to develop an algorithm based on Internet of Things -system to detect and assess pain in a reliable and objective way to replace inaccurate and subjective pain assessment methods performed by caregivers.

Students’ Involvement and Expected Outcomes: Setting up a network of wearable sensors (smart wristband, chest-strap, etc.) to collect pain related bio- signals, developing LabVIEW-based platform to read and process EMG and physiological bio-signals from wearable sensors, developing medical signal processing (filtering, feature extraction) and data analytics on the sensory data.

Additional Mentor: Dr. Amir M. Rahmani

Prerequisites: C or C++ programming skills preferably for microcontrollers, preferably some experience in wireless sensor networks (WSN) and embedded software development, some experience in digital signal processing, LabVIEW visual programming language and environment.

Recommended Web sites and publications: 
   Ming-Zhe Jiang, Amir M. Rahmani, Tomi Westerlund, Pasi Liljeberg, Hannu Tenhunen, “Facial expression recognition with sEMG method”, in Proc. of IEEE International Conference on Computer and Information Technology (CIT’15), 2015, UK.: https://www.researchgate.net/publication/281175928_Facial_Expression_Recognition_with_sEMG_Meth od
   Ming-Zhe Jiang, Tuan Nguyen Gia, Arman Anzanpour, Amir M. Rahmani, Tomi Westerlund, Sanna Salenträ, Pasi Liljeberg, and Hannu Tenhunen, "IoT-based Remote Facial Expression Monitoring System with sEMG Signal," IEEE Sensors Applications Symposium (SAS’16), 2016, Italy.: https://research.utu.fi/converis/getfile?id=18220050&portal=true



 Project #10:  Technology Supported Family Care Coordination for Stroke Survivors and Caregivers
Faculty Mentor:  Professor Yunan ChenInformatics

Description:  According to the Centers for Disease Control and Prevention, stroke is a leading cause of serious and long-term disability in America. After being discharged from the hospital, stroke patients face a sudden transition from healthy states to disability. Stroke patients still have to go through long and tedious rehabilitation processes, such as speech recovery, cognitive recovery, rehabilitations of the limbs, fingers, etc. Due to the stroke survivors’ mental and physical limitations, such as memory barrier and immobility, the care work places a huge burden on family caregivers, who become the mind and brains of two persons. Both the sudden change and the care tasks have led to notable psychological and physical burdens for family caregivers. Meanwhile, many stroke survivors tend to face social isolation due to the limited mobility.

The goal of this project is to investigate the impact of technology supported family care coordination on the quality of life of stroke survivors and caregivers. The project aims to design a system that leverages IoT technologies (such as activity trackers and blood pressure monitors), tablets, smartphones, and social media, to help stroke survivors, caregivers, and other family members to coordinate the care and recovery for stroke patients. An example scenario is to enable caregivers to list the tasks related with taking care of the stroke survivors, making them accessible to their family members, and then enable family members to select tasks that are appropriate for them. The tasks’ distribution, assignment, and social interactions can be displayed on a tablet on the wall of patients’ homes; they can also be accessed through a mobile app for other family members. Such tasks may include those that help stroke survivors and caregivers improve the quality of their recovery, life, and play.

Student’s Involvement and Expected Outcomes: Students are expected to iteratively design a functional prototype to be used in the home environment for stroke survivors. The goal of the study is to investigate the impact of technology supported collaborative family care on the quality of life of stroke survivors and caregivers as well as family relationships. Another goal is to understand how caregivers and family members collaborate and distribute care tasks.

Prerequisites: Strong in programming, preferably mobile development; prior knowledge of user-centered design; interest in health and well-being. Preference is usually given to students who have junior or senior standing, but that is not a strict requirement. Students expecting to graduate in June or September 2017 will receive low priority.

Recommended Web sites and publications: 
   Berry, A,.Lim, C., Hartzler, A., Hirsch, T., Wagner, E.H., Ludman, E., Ralston, J.D.(2017) How Values Shape Collaboration Between Patients with Multiple Chronic Conditions and Spousal Caregivers. In Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems (to appear):
   Hong, M. K., Wilcox, L., Machado, D., Olson, T. A., & Simoneaux, S. F. (2016). Care Partnerships: Toward Technology to Support Teens' Participation in Their Health Care. In Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems (pp. 5337-5349). ACM.:
   Cameron, J. I., & Gignac, M. A. (2008). “Timing It Right”: A conceptual framework for addressing the support needs of family caregivers to stroke survivors from the hospital to the home. Patient education and counseling, 70(3), 305-314.:
   Norval, C., Arnott, J. L., & Hanson, V. L. (2014). What's on your mind?: investigating recommendations for inclusive social networking and older adults. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (pp. 3923-3932). ACM.: