Subscribe to RSS Feed (Opens in New Window)

Presented Papers

Characterization of Gait Patterns in Common Gait Rehabilitation Exercises

Jared Green, Rochester Institute of Technology
Elizabeth DeBartolo, Rochester Institute of Technology
Kathleen Lamkin-Kennard, Rochester Institute of Technology

Abstract - Gait training is an important part of recovery from stroke or surgery, or treatment for neurological disorders such as Parkinson's disease or Multiple Sclerosis. A gait monitor that uses infrared sensing technology has been developed at RIT and proven to successfully monitor an individual's walking patterns over a variety of different terrain types.

Deaf STEM Community Alliance: Establishing a model virtual academic community

Lisa B. Elliot
Donna Easton
E. William Clymer

Abstract - This presentation describes the incremental and iterative development of the Deaf STEM Community Alliance’s virtual academic community, the Deaf and Hard of Hearing Virtual Academic Community (DHHVAC). The DHHVAC components address three critical barriers to the success of students who are deaf or hard-of-hearing: student preparation, socialization, and access to media.

Developing An Atrial Activity-Based Algorithm For Detection Of Atrial Fibrillation

Steven Ladavich
Behnaz Ghoraani

Abstract - In this study we propose a novel atrial activity based method for atrial fibrillation (AF) identification that detects the absence of normal sinus rhythm (SR) P-waves from the surface ECG. The proposed algorithm extracts nine features from P-waves during SR and develops a statistical model to describe the distribution of the features. The Expectation- Maximization algorithm is applied to a training set to create a multivariate Gaussian Mixture Model (GMM) of the feature space. This model is used to identify P-wave absence (PWA) and, in turn, AF. An optional post-processing stage, which takes a majority vote of successive outputs, is applied to improve classier performance. The algorithm was tested on 20 records in the MIT-BIH Atrial Fibrillation Database. Classification combining seven beats showed a sensitivity of 99.28%, a specificity of 90.21%. The presented algorithm has a classification performance comparable to current Heartratebased algorithms yet is rate-independent and capable of making an AF determination in a few beats.

Entropy and Frequency Analysis of New Electrocardiogram Lead Placement

Baabak Mamaghani
Mark Sterling
Donna Gruendike
Mark Hamer
Behnaz Ghoraani

Abstract - This is a preliminary study that explores ideal lead placements for quantification of atrial fibrillation. Data was collected at the Rochester Cardiopulmonary Group where two Atrial Fibrillation (AF) patients were monitored for one hour using a 12-lead Holter Recording setup. Lead placement was different than the clinical ECG lead placement. Two leads were placed at V1 and V2 followed by 5 leads to the left of the sternum and 5 to the right. For every lead pairing, the Shannon entropy as well as the Dominant Frequency of the bipolar signal were calculated and then compared based upon the lead locations (left only, right only, left and right). The results suggest that a reduced lead setup from a left-right combination could allow for an ambulatory AF detection device while preserving AF detection accuracy.

Get Mobile Captioning Anywhere

Michael Stinson
Donna Easton
Lisa Elliot
Justin Mahar
Pamela Francis

Abstract - This paper describes the C-Print technology and highlights a recent development, C-Print Mobile, which is currently being evaluated with National Science Foundation funding. The C-Print captioning technology is used to produce a text display of spoken information for individuals who are deaf or hard of hearing (or other individuals who may have difficulty understanding speech). The C-Print service has most often been provided in educational settings, primarily to provide communication access for a deaf student enrolled in a class with primarily hearing students. C-Print may also be used in business and community meetings, presentations, and many other situations. The new C-Print Mobile app allows users to view captioning in a variety of settings: for example, in traditional classrooms, labs, and meetings. Users can also use the Mobile app to view captioning in remote settings, such as a classroom field trip. In July 2013 the app for viewing C-Print real-time captions on mobile devices was released to the general public as a free download from the Apple iTunes and Google Play stores.

Learning to Generate Understandable Animations of American Sign Language

Matt Huenerfauth

Abstract - Standardized testing has revealed that many deaf adults in the U.S. have lower levels of written English literacy; providing American Sign Language (ASL) on websites can make information and services more accessible. Unfortunately, video recordings of human signers are difficult to update when information changes, and there is no way to support just-in-time generation of web content from a query. Software is needed that can automatically synthesize understandable animations of a virtual human performing ASL, based on an easy-to-update script as input. The challenge is for this software to select the details of such animations so that they are linguistically accurate, understandable, and acceptable to users. Our research seeks models that underlie the accurate and natural movements of virtual human characters performing ASL, using the following methodology: experimental evaluation studies with native ASL signers, motion-capture data collection from signers, linguistic analysis of this data, statistical modeling techniques, and animation synthesis.

Programmable Sound Detection

Joseph S. Stanislow
Gary W. Behm

Abstract - The development of the project is to design, develop and build a notification device that will allow deaf/hard-of-hearing (DHH) people to be notified when a device such as toaster, microwave oven, smoke alarm, door bell or instruments produce sounds. The name of the project is “Programmable Sound Detection (PSD)”. The function is to record a specified sound of the device, store it in Programmable Sound Detection Device (PSD) and notify a person when the sound is activated. PSD stores several different audible sounds of different devices. Based on which specified audible sound from the device, the PSD can notify a person which device by flashing light, vibration, or message.

Self-Adjusting Biofeedback with a Dynamic Feedback Signal Set (DyFSS)

Laurence I. Sugarman
Brian L. Garrison
Anna E. Hope

Abstract - A lack of control over their autonomic nervous system presents a major challenge for many children with Autism Spectrum Disorder (ASD). Autonomic biofeedback training is a promising treatment for managing anxiety and ASD symptoms more generally. We describe software that tunes four autonomic measurements to the best abilities and needs of each individual patient. Using this dynamic feedback signal set (DyFSS), a strength-based, self-customizing algorithm, we aim to address the autonomic heterogeneity of youth with ASD. The DyFSS may improve autonomic biofeedback training for the user by making it more understandable and easier to accomplish. Because it is self-adjusting, it may also ease the integration of autonomic biofeedback training into clinical work. Initial feasibility testing of this algorithm in youth with ASD with a five-session autonomic biofeedback training protocol showed improved behavior in relation to ASD symptoms Initial reactions show that youth with ASD are readily engaged through technological interventions such as autonomic biofeedback.

Using iPads to improve academic gains for students with disabilities

Nicole Quick

Abstract - Students with disabilities have a difficult time making academic progress in the classroom. Depending on the type of disability, students need various modifications and support to assist with academic tasks. This literature review examines the effectiveness of the use of iPads to help improve achievement for students with disabilities. Both benefits and difficulties of using iPads in the classroom are explored with an emphasis on how iPads can be used to improve instruction for students receiving special education services. The findings of this literature review confirm that iPads are an effective piece of technology in the classroom, and suggestions for implementing iPads into daily classroom instruction are provided. In addition, areas of further investigation and research are identified.

Wear Assessment of a Novel Squeeze-Film Artificial Hip Joint

S.A. Coots, Rochester Institute of Technology
s Boedo, Rochester Institute of Technology

Abstract— This paper investigates the wear characteristics of a novel hip implant design. Key features of the design are elastic elements attached to the cup which provide a mechanical means for ball separation during the swing phase of the gait loading cycle. An Archard-based wear formulation was implemented utilizing the ANSYS finite element analysis program which relates contact pressure and sliding distance to linear wear depth. It is found that low-modulus elastic elements with bonded high-modulus metal coatings offer significant predicted improvement in linear and volumetric wear rates when compared with conventional implant geometries for gait cycle loading and kinematic conditions found in practice.