Sponsored by:
NSF logo
Contact Information:
Oakland University

2011 Projects

Advisor: Dr. Zohdy
In the project, self organized computation is trained to identify, categorize and hence better understand Diana monkey key words especially in danger. Dynamic features are postulated in joint time-frequency domain where actual and simulated sound bytes are used. Several new contributions are made to improve the self organization performance in quality, speed, and accuracy. Correlation and memory enhancements are attempted together with new mixed metrics and more effective Sammon initialization of learning process.
Advisor: Dr. Patel
Patients with various medical conditions who are unable to control their vocal loudness, vocal softness or rate of speech need continuous assistance during speech therapy. Such individuals may be in treatment with a speech-language pathologist for medical conditions such as vocal cord lesions, vocal cord paralysis, stuttering, Parkinson's, or neurologic disorders. Continuous assistance of speech therapist for such treatment is both time and cost prohibitive. This project aims at designing and developing a low cost speech therapy system that can continuously monitor, analyze and guide patients with such disabilities. Two specific objectives of this project are; (1) development of low cost real-time speech analysis and feedback generation algorithms; and (2) a field study to analyze effectiveness of automated speech therapy. A structured system evaluation will be performed to analyze benefits and effectiveness of proposed system to the target patient population.
Advisor: Dr. Fu
With so many people inputting their private information into smartphones, the privacy of the users is a growing concern.This project presents various growing concerns about smartphone privacy issues. Our research covers current concepts of networking, security and privacy in 3G and 3GPP with respect to hardware, software, and application implementations on contemporary smartphones. After analysis of these recommended protocols, we will address ways to compromise users' privacy rights, and potentially develop fixes to these attacks.
Advisor: Dr. Li
The long term goal of this project is to build intra-vehicle wireless sensor network using UWB technology. The application requires small low profile UWB antennas operate in a vast frequency range. Antenna miniaturization techniques have important performance trade-offs for large miniaturization factors. In this ten week summer program, we are going to measure the performance of two miniature UWB antennas designed by our collaborator and propose possible improvement in antenna design.
Advisor: Dr. Qu
In this project, we will investigate methods for medical error detection and clinical behavior analysis. The team will work to design a new logging system on the top of the existing acute pain system (APS) that the information including patient medical records, nurses daily rounding, inpatient/outpatient follow ups and surgery procedure will be captured and also the uses of the APS system. Upon the collected data, instance based learning methods will be deployed. Once we have these two functions implemented, we will be able to answer the following questions in collaborating with the doctors: 1) what are the main reasons to cause medical errors? 2) how to avoid medical errors? 3) who is the nearest neighbor(s) for a specified patient?