Master of Computer Science (M.C.S.), University of Dayton, 2021, Computer Science

The human eye perceives up to 80% of all the impressions and acts as the best shield from threat. While it is believed and accepted that vision is a predominant sense in people, as per the World Health Organization, around 40 million individuals on the planet are blind, and 250 million have some type of visual disability. As a result, a lot of research and papers are being suggested to create accurate and efficient navigation models utilizing computer vision and deep learning approaches. These models should be fast and efficient, and they should be able to run on low-power mobile devices to provide real-time outdoor assistance. Our objective is to extract and categorize the information from the live stream and provide audio feedback to the user within the University campus. The classification of the objects in the stream is done by a CNN model and sent as an input for the voice feedback, which is divided into several frames using the OpenCV library and converted to audio information for the user in the real-time environment using the Google text to speech module. The results generated by the CNN model for image classification have an accuracy of over 95 percent, and real-time audio conversion is a rapid transition technique, resulting in an algorithm that performs competing with other prior state-of-art methods. We also want to integrate the application in smartphones, into our mobile app to provide a more user-friendly experience for the end-users.

Committee: Dr. Mehdi R. Zargham (Advisor) Subjects: Computer Science

Doctor of Philosophy (PhD), Wright State University, 2019, Computer Engineering

Human brain analysis and understanding pose several challenges due to the great complexity of the structural organization and the functional connectivity that characterizes the human brain. The ability of the brain to adapt in dynamic changes over time such as normal aging, neurodegenerative diseases or congenital brain malformations renders the brain's exploration a particularly demanding and difficult task. In recent years, advances in brain imaging modalities and lately the multimodal fusion, combined with improvements in related technologies have greatly assisted the development of brain maps by providing insights regarding the overall brain structure and functionality. Even though the existence of sensory and motor maps for the human brain is known to some degree, the formation process is still subject to research. Electroencephalography (EEG) and functional magnetic resonance imaging (fMRI) are the two mostly used non-invasive brain imaging modalities that can track the changes in brain activity. Due to their complementary nature, high temporal resolution from EEG and high spatial resolution from fMRI, the fusion of simultaneous acquired EEG and fMRI recordings aims to provide complementary information about the brain functionality. In an effort to extend the current research in the field of brain understanding, a novel Brain Mapping Model (BMM) based on EEG and fMRI is proposed within this Ph.D. dissertation. The proposed BMM is based on the synergy of state-of-the-art computational techniques to associate the brain regional activities provided by the EEG-fMRI fusion. In more details, first, a novel formal model for the EEG signals' representation is proposed. The proposed formal model enables the analysis and extraction of structural EEG features. The proposed method is based on the Syntactic Aggregate approXimation (SAX) algorithm, that in this work is improved by the Local-Global (LG) graph technique, to compose a Context Free-Grammar (CFG). Moreover (open full item for complete abstract)

Committee: Nikolaos G. Bourbakis Ph.D. (Advisor); Soon M. Chung Ph.D. (Committee Member); Bin Wang Ph.D. (Committee Member); Konstantinos Michalopoulos Ph.D. (Committee Member) Subjects: Computer Engineering

Ph.D., Antioch University, 2019, Leadership and Change

Blind and visually impaired people in the United States face a dire employment situation within professional careers and corporate employment. The purpose of this research study was to gain insights into the phenomenon of employment of blind people through analyzing the lived experience of successfully employed blind adults through ethnographic interviews. Previous research has shown that seven out of ten blind adults are not in the workforce, that a large percentage of those who are employed consider themselves underemployed, and that these numbers have not improved over time. Missing from previous research were insights into the conditions leading to successful and meaningful employment for blind adults. My top research questions were: what experiences and relationships were most significant in the lives of successfully employed blind adults in U.S. corporations, and what the most significant factors were, from employers' perspectives, leading to these successes. Based on semi-structured interviews of 11 blind adults who self-identified as successfully and meaningfully employed in corporate America, I found successfully employed blind adults have largely forged their own paths, with family support, valuable knowledge, skills, and abilities, and a strong sense of agency playing crucial roles. Corporate inclusion of blind employees is in its infancy. The implications for social change revolve around changing societal perceptions of the capabilities of blind people, transforming corporate cultures to ones of integration rather than differentiation, and building family, school, community, and service provider mechanisms to instill a strong sense of agency in young blind people. My recommendations to others are to focus on a leveraging difference framework of diversity and inclusion, in which every individual is valued for their unique characteristics, and make sure that blind people are positioned to be part of this societal transformation. This dissertation is availa (open full item for complete abstract)

Committee: Philomena Essed PhD (Committee Chair); Aqeel Tirmizi PhD (Committee Member); Heather Wishik JD (Committee Member) Subjects: Biographies; Business Administration; Business Community; Business Costs; Business Education; Education; Educational Leadership; Families and Family Life; Individual and Family Studies; Minority and Ethnic Groups; Multicultural Education; Personal Relationships; Public Administration; Public Health; Public Health Education; Public Policy; Rehabilitation; Social Work; Special Education; Vocational Education

Master of Science, The Ohio State University, 2019, Computer Science and Engineering

Detecting the presence of objects for spatial orientation and avoiding them for mobility is extremely difficult for People with Visual Disabilities. 285 million people worldwide are estimated to have a visual disability, of which 39 million are blind and another 246 million have low vision. Many day-to-day tasks that the rest of the population consider routine, are in fact excessively complex for these individuals to perform. It is difficult to have a perception of space and to be able to navigate both indoors and outdoors safely, confidently and effectively without visual information about the surroundings. The use of smartphones is popular among the people with visual disabilities for simple navigational assistance such as finding the current location, and reading out directions which typically leverage the availability of GPS in outdoor environments. But when it comes to indoor environments there is a deficit of such GPS-based accurate location services and this makes it more challenging to localize themselves with respect to the environment and navigate from one location to another. Existing solutions rely on the user to scan the environment (e.g., Ultracane, Smartcane) and build and maintain a mental model of the environment. Additionally, due to their heavy computational needs and power-hungry sensors (e.g., stereo camera, lidar and radar), existing solutions require significant amount of energy leading to short usable periods between chargings unless heavy battery packs are carried. I present two solutions. The first one is a lightweight single camera-based solution for Localization & Navigation (VisualLoc) and the second is an inexpensive, power-efficient depth-mapping solution (CaneScanner) for assisting Visually Impaired in Indoor Environments. Together these two tools help to achieve the following: 1) find one's relative position (distance & direction) with respect to the objects in the environment and subsequently keeping track of these self-to-objec (open full item for complete abstract)

Committee: Prasun Sinha Dr. (Advisor); Rajiv Ramnath Dr. (Committee Member) Subjects: Computer Engineering; Computer Science

Master of Science (MS), Ohio University, 2018, Journalism (Communication)

Films are something everyone should be able to enjoy either independently or with others. For the blind and visually impaired, enjoying films without Descriptive Video Service (DVS), is much more difficult, if not impossible. DVS provides an audio description of the film's visual images so they are accessible to the blind and visually impaired. The number of films with DVS is increasing after many years when the technique was available, but it is not widely used by movie producers. This thesis traces the history and development of DVS into what it is today. The researcher conducted a content analysis of films with DVS to study the films' defining characteristics, and relate those characteristics to the box office of the films. Of the 250 films in the sample size, 93 did not break even. In the final regression, only production cost, cumulative U.S. gross, sequel, and blindness were statistically significant. DVS is not affecting box office so much as high production costs. Films that did not break even had a higher box office mean difference of $65 million, but also a higher production cost of $80 million (mean = 81.30). The production cost between films that did and did not break even showed a negative difference of $22.86 million. The research shows that there are several more components to be studied, including a deeper look at film characteristics, economic inflation, disability and how it is classified in the United States, and a much deeper look at the laws surrounding DVS.

Committee: Hugh Martin Ph.D. (Committee Chair); Michael Sweeney Ph.D. (Committee Member); JW Smith Ph.D. (Committee Member) Subjects: Economics; Film Studies; Law; Mass Media; Motion Pictures; Statistics

Master of Science, Miami University, 2017, Computational Science and Engineering

Assistive technology helps improve the day to day activities for people with disabilities. One of the methods utilized by assistive technologists employs the use of robots. These are called service robots. This thesis explores the idea of a service robot for the visually impaired to assist with navigation and is inspired by the use of guide dogs. The focus of this thesis is to develop a robot to achieve autonomous indoor navigation using computer vision to identify image based goals in an unfamiliar environment. The method presented in this thesis utilizes a deep learning framework, called Faster R-CNN, to train a computer to classify and localize exit signs in real time. A proof of concept is presented using NVIDIA Jetson, and TurtleBot, a robot kit, which runs a robot software development framework Robot Operating System (ROS). The model is trained successfully using Faster R-CNN and is validated. The model is used for real-time object classification on the prototype robot.

Committee: Yamuna Rajasekhar (Advisor); John Femiani (Committee Member); Donald Ucci (Committee Member) Subjects: Computer Science; Electrical Engineering; Robotics

MDES, University of Cincinnati, 2016, Design, Architecture, Art and Planning: Design

Visually impaired people have high demands of mobility in both outdoor and indoor navigation. There're many existing technologies, solutions and products for supporting their outdoor mobilities. While, there's less designer or engineers pay much attention to the demand of internal navigation for the small community. Existing products or services mainly focus on detecting and avoiding obstacles. Seldom products or services can help visually impaired people to find a specific items or spaces. Technology advance in smart phone industry bringing powerful computing ability and other new interaction methods through integrated hardware. Many visually impaired people are using smart phone by voice command, others are all have high motivation to buy one or at least have a trial. The author collaborated with Cincinnati Association for The Blind and Visually Impaired (CABVI) and try to figure out the problem mentioned above. Solid secondary research has been made prior to this study for understanding human demands, current solutions and its' restrictions. Several interviews, tests and co-creations have done to verify the effectiveness of using smartphone based interactions and navigation system and preferences of interactions from visually impaired people and specialists: including test of human senses, preferences for interactions, preferences for wearable / nonwearable devices and tests between audio based notification system and vibration based notification system. There are two main factors in internal navigation for visually impaired people: 1). notifying orientation and distance; 2). identifying objects. A series of studies achieved in this thesis also provide a strong support for voice command and linear interval vibration which can notify navigation information (including orientations and distance). The navigation system include a passive RFID system and a smart phone to identify different object easily and quickly. A series of passive RFID tags can be attached to a (open full item for complete abstract)

Committee: Craig Vogel M.I.D. (Committee Chair); Gerald Michaud M.A. (Committee Member) Subjects: Design

Master of Liberal Studies, University of Toledo, 2014, Liberal Studies

The eugenics movement targeted people who were blind and visually impaired as part of "the unfit" members of society who needed to be prevented from passing on their blindness to successive generations. In the late-nineteenth and early-twentieth centuries, eugenicists, blindness professionals, and even other blind people believed that the best way to eliminate blindness was through the restriction of marriages between blind people. Ophthalmologist Lucien Howe repeatedly attempted to secure legislation barring blind people from marrying. Blindness professionals, especially educators, stressed the importance of the separation of the sexes in residential schools for the blind as the way in which to prevent blind marriages and intermarriages, and thus to prevent future generations of blind people. Blind people's assessment of their own marriageability was complex and sometimes contradictory. While some shirked contemporary views, most others accepted and promoted the eugenic idea that hereditary blindness should not be passed to the next generation. Many historians have previously overlooked the unique and rich history of blind people in the United States. This research hopes to illuminate an important aspect of that history.

Committee: Kim Nielsen (Committee Chair); Liat Ben-Moshe (Committee Member); Diane Britton (Committee Member) Subjects: American History; Education History; Gender Studies; History; Personal Relationships; Special Education

Doctor of Philosophy (PhD), Wright State University, 2009, Computer Science and Engineering PhD

The need for assistive devices has, had and will have a large merit in many engineering research arenas. This dissertation deals with the design, modeling, implementation and experimentation of the navigation component of a wearable assistive system for blind and visually impaired people, called TYFLOS (ΤΥΦΛΟΣ) which is the Greek word for “Blind”.The current prototype consists of two mini cameras attached to a pair of conventional eye-glasses, a 2D tactile display vibration array) which consists of 16 vibrating elements arranged in a 4x4 manner, attached to an elastic vest worn on the user‟s abdomen, a portable computer, an ear-speaker and a microphone. The Tyflos Navigator is an Electronic Travel Aid (ETA) with primary goal to help users towards their independent mobility in indoor environment. Its main sensor unit, the stereo vision system, captures environmental information from the user's field-of-view. 3D representations are created and moving objects are identified using stereoscopic vision and motion detection methodologies. The high resolution output of the methodologies is projected on the low resolution vibration array via a high-to-low methodology based on navigation criteria and modeled with a formal language called Vibration Array Language (VAL). The spatial distribution and temporal characteristics (varying frequencies) of the vibrating elements of the vibration array can inform the user for safe navigation paths and obstacles, giving distance and location information. All parts of the system will be continuously adapted until the users' needs are fulfilled or the technological constraints are reached. A step towards that goal will be shown at the last part of this work with the development of a tactile vocabulary and the experimentation with users where they provide feedback giving us directions for refinements, changes and future work.

Committee: Nikolaos Bourbakis PhD (Advisor); Mateen Rizki PhD (Committee Member); John Gallagher PhD (Committee Member); David Reynolds PhD (Committee Member); Partha Banerjee PhD (Committee Member) Subjects: Computer Science; Engineering

MARCH, University of Cincinnati, 2010, Design, Architecture, Art and Planning: Architecture

Architecture is largely considered and judged as a visual medium. As described by Architect and author Juhani Pallasmaa, the ocularcentrism paradigm of our current culture weakens the sense of materiality and the holistic architecture experience. Could architecture be as Meaningful and Engaging if we are to take sight away from it? This thesis investigates the possibilities of designing for the visually impaired, approaching this topic through material investigation, literary and original research. The course of the thesis is organized in the following points. 1. How by concentrating on designing for the Visually Impaired could contribute to the architectural experience of the sighted as well. 2. How, by exploring different methods of representation (non- conventional),this will increase awareness of non-sighted related experiences. 3. How these representations might inform and perhaps guide the design process. The outcome of this process will be a new design for the Ohio State School for the Blind. This facility will integrate stimuli for the senses, resulting in a built environment that is not only engaging and interesting to people with visual impairments,but also enriches the architectural experience of the sighted individual.

Committee: George Bible MCiv.Eng (Committee Chair); Elizabeth Riorden MARCH (Committee Chair) Subjects: Architecture

Doctor of Philosophy, The Ohio State University, 2003, Art Education

How can visual, cultural art experiences be made accessible to individuals who are visually impaired or blind? This case study examined how a local artist, Queen Brooks, met this challenge by creating an art exhibition for the visually impaired and blind. Using guidance supplied by a group of junior high students who attended the Ohio State School for the Blind, Ms. Brooks created artwork designed to be experienced through touch, smell, sight, hearing, and movement. The show was intended to be open and accessible to everyone. Data was gathered through a review of pertinent literature, documents, field notes, observations, and semi-structured interviews. The outcomes of the study contribute new information to the field of art education and to the education of blind and visually impaired individuals by providing educators with pragmatic tools and strategies to use in their classrooms and schools that will facilitate learning by students with visual impairments. This study also supplies a conceptual framework for artists, museum personnel, and gallery owners to implement when fostering cultural art opportunities designed to be accessible for all members of the community, including individuals who are visually impaired or blind.

Committee: Patricia Stuhr (Advisor) Subjects: