| Mentor: Professor Ernst L. Leiss |
| Project Title: |
Data-Centric Privacy, Various Projects (Code: EL1) |
| Mentor: |
Professor Ernst Leiss |
| Description: |
There is greatly increased concern about privacy. Some of it is driven by legal requirements (HIPAA, FERPA). In many cases, the concern is directly related to technological capabilities that threaten privacy. This overarching topic (really a family of topics) looks at some threat to privacy and explores technological means for averting this threat. This may be inference control in statistical databases, obscuring location information in cell-phone communications (something like TOR for voice), preserving privacy in data mining operations, or exploring techniques that prevent the use of certain biometric measurements for identification of individuals (e. g., face recognition, gait recognition, voice recognition, or keystroke dynamics). In each case, a student starts by researching the specific threat, then examines the technologies that are typically used to threaten privacy within the context of the scenario, and finally develops technologies that disable or impede the use of these technologies and verifies rigorously that these techniques improve the privacy of the subjects involved. |
| Research Objective: |
Enable individuals to preserve their privacy in specific circumstances. |
| Student Learning: |
Become familiar with privacy and technologies that threaten it. Explore technologies that counteract these threats. |
| Mentor: Professor Ioannis A. Kakadiaris |
| Project Title: |
Data-Driven Detection of Counterfeit Vaccines using Social Media Analysis (Code: IK1) |
| Mentor: |
Professor Ioannis Kakadiaris |
| Description: |
The sale of counterfeit goods online poses a risk to both consumers and legitimate sellers. One way to detect this illegal activity is through algorithms that perform social media analysis. This project is part of a larger project on the detection of counterfeit medicines.
|
| Research Objective: |
Develop and evaluate a method to detect counterfeit vaccines using social network analysis. |
| Student Learning: |
Students will become familiar with social network analysis and computer vision techniques. |
| Project Title: |
AI-Driven Analysis for the progression of COVID-19 (Code: IK2) |
| Mentor: |
Professor Ioannis Kakadiaris |
| Description: |
It is clear that individuals infected with the coronavirus follow different trajectories in their progression of the disease. Some of them develop pneumonia with all its associated symptoms or develop acute respiratory distress syndrome (ARDS), sepsis, kidney, and other organ failures. This project aims to model the progression of COVID-19 and identify the top risk factors that lead to the next stage while proposing interventions to the modifiable ones.
|
| Research Objective: |
Develop and evaluate an AI-based technique to predict the progression to the next stage of the disease along with the key contributing factors. The evaluation will be performed on real-world data.
|
| Student Learning: |
Students will become familiar with developing and evaluating AI/ML methods applied to clinical problems while working with a vibrant and pioneering team.
|
| Project Title: |
AI-based, disaster-resilient food supply chains for pandemics (Code: IK3) |
| Mentor: |
Professor Ioannis Kakadiaris |
Description: |
It is unclear how the nutritional needs of Houston's vulnerable populations will be addressed amidst multiple disasters, including hurricanes and flooding, COVID-19, economic disruptions, and systemic food insecurity. The Houston Food Bank (HFB) serves the Greater Houston area and collaborates with over 1,500 partners to address families' needs experiencing food insecurity. Disaster preparation and response decisions have been mainly based on incomplete data, human intuition, and pro-bono input from consulting firms.
|
| Research Objective: |
Develop and evaluate decision-making tools for disaster management using computational game theory and deep reinforcement learning.
|
| Student Learning: |
Students will become familiar with developing and evaluating game theory and deep reinforcement learning techniques.
|
| Project Title: |
Transportation for All: Data-Driven Etiquette Compliance (Code: IK4) |
| Mentor: |
Professor Ioannis Kakadiaris |
Description: |
Encouraging the use of public transportation becomes easier when the passengers comply with sneezing and coughing etiquette. With the proliferation of video data from public transit, there is an increased need to recognize specific actions performed by human subjects. For example, compliance with sneezing and coughing etiquette will help attract new passengers. Current action analysis methods rely on either full-frame video analysis or analysis of regions of interest identified by heatmaps or other attention-based mechanisms. However, there is no consideration for the frame's size, whether it is night or day, or the compression method used by the camera used for data acquisition. We propose the design, development, and evaluation of a technique that will capture passengers' compliance in sneezing and coughing etiquette.
|
| Research Objective: |
Develop a technique to perform action recognition for actions that do not have the same temporal duration, happening in uncontrolled environments, and for which there is very little training data.
|
| Student Learning: |
Students will become familiar with computer vision techniques (including person detection and action recognition in unconstrained environments) and machine learning techniques addressing training data's sparsity.
|
| Mentor: Professor Ioannis Pavlidis |
| Project Title: |
Bio and Behavioral Feedback (B2-Feedback) in Transitional Vehicle Technology (Code: IP1) |
| Mentor: |
Professor Ioannis Pavlidis |
| Description: |
There have been tremendous developments in the area of automobile assistive systems, which aim to make driving safer. Currently, such systems range from auto-braking to auto-parking. In this research project, we aim to develop the next generation of assistive systems that will quantify the stress and performance levels of drivers, determining if their apparent and hidden states are within safe margins. If these states found to be unsafe, then the system will notify the drivers, who will have to correct their behaviors (e.g., by disengaging from a texting distraction), in order for the complex system to return to homeostasis. This research draws on tera-bytes of simulator and field experimental data that the UH Computational Physiology Lab collects in collaboration with the Texas A&M Transportation Institute under separate federal funding (http://cpl.uh.edu/projects/stress-studies/dds/). |
| Research Objective: |
In an increasingly computer-assisted driving world, this research aims to bring harmony between the states of the computerized car and the driver, which are now merging into a complex cyber-physical-human system. |
| Student Learning: |
Students will engage in sophisticated multi-modal data analytics and biofeedback algorithm development, drawing on the massive and unique UH-A&M experimental dataset. |
| Project Title: |
Hidden Patterns and Drivers of Academic Scholarship (Code: IP2) |
| Mentor: |
Professor Ioannis Pavlidis |
| Description: |
The UH Computational Physiology Lab in collaboration with Northwestern’s Kellogg School of Management have been amassing a comprehensive biographic, bibliographic, and funding dataset for academic researchers in the United States. The dataset is publicly visualized via the Scholar Plot interface (http://www.scholarplot.com). This dataset provides unique capabilities to computational researchers in the science of science area. |
| Research Objective: |
Investigate patterns of cross-disciplinary collaboration and hidden drivers of academic success that may inform the science policy of the future. |
| Student Learning: |
Students will engage in social network data analytics and multiple linear regressions. |
| Mentor: Professor Rakesh Verma |
| Project Title: |
Linguistic Markers for Deception (Code: RV1) |
| Mentor: |
Professor Rakesh Verma |
| Description: |
Are there general linguistic traces of deception? This project will investigate in the context of 4-5 different kinds of deceptive attacks including fake news and social engineering attacks such as spearphishing and business email compromise.
|
| Research Objective: |
To determine whether or not general linguistic markers exist for deception. |
| Student Learning: |
Statistical learning techniques, Natural Language Processing, cybersecurity |
| Project Title: |
Defending Against Adversarial Attacks on Email Classifiers (Code: RV2) |
| Mentor: |
Professor Rakesh Verma |
| Description: |
A lot of research has been conducted for classifying phishing emails. However, there is now considerable work that shows the brittleness of these classifiers under small perturbations in the input. This project will study the effectiveness of adversarial attacks on phishing email classifiers and then work on making the classifiers robust to such attacks.
|
| Research Objective: |
To design robust classifiers for phishing emails. |
| Student Learning: |
Statistical learning techniques, Natural Language Processing, cybersecurity. |
| Project Title: |
Anomaly Detection for the Class Imbalance Problem (Code: RV3) |
| Mentor: |
Professor Rakesh Verma |
| Description: |
We will test state of the art anomaly detection methods against state of the art imbalanced learning methods on several cybersecurity datasets. We will investigate how dataset characteristics affect the performance of the methods. |
| Research Objective: |
To design performance prediction techniques for Machine Learning models. |
| Student Learning: |
Data science and machine learning theory and practice. |
| Mentor: Professor Stephen Huang |
| Project Title: |
Host-Intrusion Detection: A Cyber Behavior Approach (Code: SH1) |
| Mentor: |
Professor Stephen Huang |
| Description: |
By cyber behavior, we mean a user's interaction with a computer and the indirect effects caused by such interactions. We have observed that user activities in cyberspace always leave some information mined and used for identification. A behavioral log is typically a collection of time series from users, "normal" or "attack." Our task is to find behavioral discrepancies between the two groups of users to detect the attackers. |
| Research Objective: |
To better understand and model intruders' cyber behavior to prevent security breaches. |
| Student Learning: |
In this project, a student will learn basic computer security concepts, cyber behavior, machine learning algorithms, and modeling of behavior. Students will also be involved in design experiments and collect data to validate the model. |
| Project Title: |
Real-Time Network Intrusion Detection to Prevent Data Breach (Code: SH2) |
| Mentor: |
Professor Stephen Huang |
| Description: |
To avoid being detected, computer hackers typically go through a long chain of computers to break into a target machine. The evasion can be achieved using a chain of "stepping-stones" hosts or anonymity networks such as Tor or proxy. We are interested in developing real-time software that can detect such intruders effectively. The project involves integrating algorithm design, network protocol, and computer security techniques into a system.
|
| Research Objective: |
To better understand and detect network intruders in real-time to prevent a data breach. |
| Student Learning: |
Students will learn basic computer security concepts, stepping-stone detection, anonymity networks, network protocols, Wireshark, and various machine learning algorithms. Students will also be involved in design experiments and collect network packets for testing and analysis.
|