Rosalyn Hobson Hargraves is an associate professor in the Department of Electrical and Computer Engineering. She is also an associate professor in the Department of Teaching and Learning within the School of Education. Her 18-year career has centered on inspiring underrepresented students in STEM fields.
Industry Expertise (2)
Areas of Expertise (4)
University of Virginia: Ph.D., Electrical Engineering 1998
University of Virginia: M.S., Electrical Engineering 1995
University of Virginia: B.S., Electrical Engineering 1991
Media Appearances (5)
Rosalyn Hobson Hargraves, Ph.D., Honored at 2015 PACME Ceremony
Virginia Commonwealth University
At Virginia Commonwealth University’s 2015 Presidential Awards for Community Multicultural Enrichment (PACME) Celebration on April 14, Gail Hackett, Ph.D., provost and vice president for academic affairs, honored Rosalyn Hobson Hargraves, Ph.D., for her contributions to diversity and inclusion. Hobson Hargraves received a Faculty Award as well as the capstone Riese-Melton Award, given for contributions to cross-cultural relations.
Transforming STEM-H Education
The community Idea Stations
Science, technology, engineering, math and health (STEM-H) are a daily part of life – the technology that is integral to most workplaces, the medication that treats illnesses, the roadways and buildings that provide routes to travel and shelters for housing.
'Education Drives America' Bus Tour Stops at VCU
Virginia Commonwealth University
The future of the United States depends on the ongoing education of its citizens, according to officials in the U.S. Department of Education.
Alliance for Minority Participation Gains Second NSF Grant
Virginia Commonwealth University and three other Virginia research institutions are gaining an edge on recruiting and retaining more minority students in STEM and health care fields through their participation in the Virginia-North Carolina Alliance for Minority Participation.
VCU’s research training programs give underrepresented students and faculty a platform for discovery
Last November, Virginia Commonwealth University senior Delisa Clay was one of the 96 students out of 2,035 picked to give an oral presentation of her research at the 15th Annual Biomedical Research Conference for Minority Students in Seattle. That alone was huge.
Selected Articles (5)
Developing a Hybrid Model to Predict Student First Year Retention in STEM Disciplines Using Machine Learning Techniques
Pelvic bone segmentation is a vital step in analyzing pelvic CT images, which assists physicians with diagnostic decision making in cases of traumatic pelvic injuries. Due to the limited resolution of the original CT images and the complexity of pelvic structures and their possible fractures, automatic pelvic bone segmentation in multiple CT slices is very difficult. In this study, an automatic pelvic bone segmentation approach is proposed using the combination of anatomical knowledge and computational techniques. It is developed for solving the problem of accurate and efficient bone segmentation using multiple consecutive pelvic CT slices obtained from each patient. Our proposed segmentation method is able to handle variation of bone shapes between slices there by making it less susceptible to inter-personal variability between different patients' data. Moreover, the designed training models are validated using a cross-validation process to demonstrate the effectiveness. The algorithm's capability is tested on a set of 20 CT data sets. Successful segmentation results and quantitative evaluations are present to demonstrate the effectiveness and robustness of proposed algorithm, well suited for pelvic bone segmentation purposes.
Abstract: Dental caries are one of the most prevalent chronic diseases. The management of dental caries demands detection of carious lesions at early stages. This study aims to design an automated system to detect and score caries lesions based on optical images of the occlusal tooth surface according to the International Caries Detection and Assessment System (ICDAS) guidelines. The system detects the tooth boundaries and irregular regions, and extracts 77 features from each image. These features include statistical measures of color space, grayscale image, as well as Wavelet Transform and Fourier Transform based features. Used in this study were 88 occlusal surface photographs of extracted teeth examined and scored by ICDAS experts. Seven ICDAS codes which show the different stages in caries development were collapsed into three classes: score 0, scores 1 and 2, and scores 3 to 6. The system shows accuracy of 86.3%, specificity of 91.7%, and sensitivity of 83.0% in ten-fold cross validation in classification of the tooth images. While the system needs further improvement and validation using larger datasets, it presents promising potential for clinical diagnostics with high accuracy and minimal cost. This is a notable advantage over existing systems requiring expensive imaging and external hardware.
Many chemical engineering students recall the feeling of being propelled into the curriculum without the appropriate analytical skills to successfully navigate through the courses. Many schools have implemented freshman engineering courses to serve as an introduction to the engineering field and basic engineering concepts. While retention rates have improved significantly, there is still much more to be accomplished if we are to meet society’s demand for engineering professionals. In the 2010-11 academic year, Virginia Commonwealth University launched a two course, introductory chemical engineering sequence to prepare students for the more rigorous, sophomore chemical engineering courses. The students needed freshmen engineering courses that would not only solidify their interest in a career in chemical engineering, but also provide a solid foundation in fundamental chemical engineering principles. Reflective interviews from these students, now in their senior year, revealed a sense of readiness among students, after taking the two course sequence.
Noise can compromise the extraction of some fundamental and important features from biomedical signals and hence prohibit accurate analysis of these signals. Baseline wander in electrocardiogram (ECG) signals is one such example, which can be caused by factors such as respiration, variations in electrode impedance, and excessive body movements. Unless baseline wander is effectively removed, the accuracy of any feature extracted from the ECG, such as timing and duration of the ST-segment, is compromised. This paper approaches this filtering task from a novel standpoint by assuming that the ECG baseline wander comes from an independent and unknown source. The technique utilizes a hierarchical method including a blind source separation (BSS) step, in particular independent component analysis, to eliminate the effect of the baseline wander. We examine the specifics of the components causing the baseline wander and the factors that affect the separation process. Experimental results reveal the superiority of the proposed algorithm in removing the baseline wander.