VTechWorks Repository :: Browsing by Author "Kelliher, Aisling"

Browsing by Author "Kelliher, Aisling"

Now showing 1 - 18 of 18

Assessing Limb Symmetry using the Clinically Accessible loadsol®
Renner, Kristen Elizaberth (Virginia Tech, 2019-04-23)
Decreased gait symmetry has been correlated with an increased fall risk, abnormal joint loading and decreased functional outcomes. Therefore, symmetry is focused on in the rehabilitation of many patient populations. Currently, load based symmetry is collected using expensive and immobile devices that are not clinically accessible, but there is a clinical need for an objective measure of loading symmetry during daily tasks like walking. Therefore, the purpose of this dissertation was to 1) assess the validity and reliability of the loadsol® to capture ground reaction force data, 2) use the loadsol® to determine the differences in symmetry between adults with a TKA and their healthy peers and 3) explore the potential of a commercially available biofeedback system to acutely improve gait symmetry in adults. The results of this work indicate that the loadsol® is a valid and reliable method of collecting loading measures during walking in both young and older adults. TKA patients who are 12-24 months post-TKA have lower symmetry in the weight acceptance peak force, propulsive peak force and impulse when compared to their healthy peers. Finally, a case study with four asymmetric adults demonstrated that a 10-minute biofeedback intervention with the loadsol® resulted in an acute improvement in symmetry. Future work is needed to determine the potential of this intervention to improve symmetry in patient populations and to determine whether the acute response is retained following the completion of the intervention.
Automated Movement Assessment in Stroke Rehabilitation
Ahmed, Tamim; Thopalli, Kowshik; Rikakis, Thanassis; Turaga, Pavan; Kelliher, Aisling; Huang, Jia-Bin; Wolf, Steven L. (2021-08-19)
We are developing a system for long term Semi-Automated Rehabilitation At the Home (SARAH) that relies on low-cost and unobtrusive video-based sensing. We present a cyber-human methodology used by the SARAH system for automated assessment of upper extremity stroke rehabilitation at the home. We propose a hierarchical model for automatically segmenting stroke survivor's movements and generating training task performance assessment scores during rehabilitation. The hierarchical model fuses expert therapist knowledge-based approaches with data-driven techniques. The expert knowledge is more observable in the higher layers of the hierarchy (task and segment) and therefore more accessible to algorithms incorporating high level constraints relating to activity structure (i.e., type and order of segments per task). We utilize an HMM and a Decision Tree model to connect these high level priors to data driven analysis. The lower layers (RGB images and raw kinematics) need to be addressed primarily through data driven techniques. We use a transformer based architecture operating on low-level action features (tracking of individual body joints and objects) and a Multi-Stage Temporal Convolutional Network(MS-TCN) operating on raw RGB images. We develop a sequence combining these complimentary algorithms effectively, thus encoding the information from different layers of the movement hierarchy. Through this combination, we produce a robust segmentation and task assessment results on noisy, variable and limited data, which is characteristic of low cost video capture of rehabilitation at the home. Our proposed approach achieves 85% accuracy in per-frame labeling, 99% accuracy in segment classification and 93% accuracy in task completion assessment. Although the methodology proposed in this paper applies to upper extremity rehabilitation using the SARAH system, it can potentially be used, with minor alterations, to assist automation in many other movement rehabilitation contexts (i.e., lower extremity training for neurological accidents).
Calibrating Video Capture Systems To Aid Automated Analysis And Expert Rating Of Human Movement Performance
Yeshala, Sai krishna (Virginia Tech, 2022-06-27)
We propose a methodology for calibrating the activity space and the cameras involved in video capture systems for upper extremity stroke rehabilitation. We discuss an in-home stroke rehabilitation system called Semi-Automated Rehabilitation At Home System (SARAH) and a clinic-based system called Action Research Arm Test (ARAT) developed by the Interactive Neuro-Rehabilitation Lab (INR) at Virginia Tech. We propose a calibration workflow for achieving invariant video capture across multiple therapy sessions. This ensures that the captured data is less noisy. In addition, there is prior knowledge of the captured activity space and patient location in the video frames provided to the Computer Vision algorithms analyzing the captured data. Such a standardized calibration approach improved machine learning analysis of patient movements and a higher rate of agreement across multiple therapists regarding the captured patient performance. We further propose a Multi-Camera Calibration approach to perform stereo camera calibration in SARAH and ARAT capture systems to help perform a 3D reconstruction of the activity space from 2D videos. The importance of the proposed activity space and camera calibration workflows, including new research paths opened as a result of our approach, are discussed in this thesis.
Capturing Upper Body Kinematics and Localization with Low-Cost Sensors for Rehabilitation Applications
Sarker, Anik; Emenonye, Don-Roberts; Kelliher, Aisling; Rikakis, Thanassis; Buehrer, R. Michael; Asbeck, Alan T. (MDPI, 2022-03-16)
For upper extremity rehabilitation, quantitative measurements of a person’s capabilities during activities of daily living could provide useful information for therapists, including in telemedicine scenarios. Specifically, measurements of a person’s upper body kinematics could give information about which arm motions or movement features are in need of additional therapy, and their location within the home could give context to these motions. To that end, we present a new algorithm for identifying a person’s location in a region of interest based on a Bluetooth received signal strength (RSS) and present an experimental evaluation of this and a different Bluetooth RSS-based localization algorithm via fingerprinting. We further present algorithms for and experimental results of inferring the complete upper body kinematics based on three standalone inertial measurement unit (IMU) sensors mounted on the wrists and pelvis. Our experimental results for localization find the target location with a mean square error of 1.78 m. Our kinematics reconstruction algorithms gave lower errors with the pelvis sensor mounted on the person’s back and with individual calibrations for each test. With three standalone IMUs, the mean angular error for all of the upper body segment orientations was close to 21 degrees, and the estimated elbow and shoulder angles had mean errors of less than 4 degrees.
Designing for Reflection: Utilizing slow technology to create tangible interactive designs for reducing technostress
Behzad Behbahani, Armaghan (Virginia Tech, 2019-11-12)
Technostress is an emerging and significant psychological phenomenon associated with the use of technology. It impacts human behavior and distracts from living a healthy and meaningful life. As humans increasingly encounter computational technology on a daily basis, there is a need to understand and manage the anxieties and tensions that can result from these interactions. Using the lens of critical design, this thesis explores this concept of technology induced stress and promotes reflection, personal growth and awareness through three different design research methods. It further builds on the topic of slow technology which unfolds in the form of a design fiction, design probe and design artifacts, challenging our understanding of technostress while embracing constructive discussions and creative designs to speculate the human-technology relationship.
Designing Telehealth Rehabilitation Systems for Diverse Stakeholder Needs
Clark, Juliet Ariana (Virginia Tech, 2021-05-26)
The strengthening of community care and the development of co-managed telehealth systems are vital components in addressing growing critical healthcare issues encountered worldwide. The global COVID pandemic highlights the challenges in providing appropriate co-managed home-based care in a systemic and financially viable way at scale. To develop practical and sustainable solutions it is important to understand the individual, institutional, and socio-technical opportunities and barriers potentially encountered when attempting to design and implement telehealth systems as part of a broader social healthcare network. In this thesis, I describe my work assessing the feasibility of deploying telehealth systems within the context of home based physical rehabilitation. I conducted an online survey and in-depth interviews with occupational and physical therapists to determine the issues impacting their current practices and the likelihood that a telehealth rehabilitation system might support or hinder their practice. Findings from this qualitative work highlighted the importance of maintaining the patient/therapist relationship, the need to empower the caregiver, and the potential for telehealth systems to provide quantitative and qualitative proof of care and patient progress. Building on these insights, I designed an interactive tablet application to assist therapists with the efficient and seamless installation and calibration of a telehealth system for stroke rehabilitation in the home. The application was evaluated in two studies with non-expert and expert users. The results from these studies indicate the efficiency of the application resulting from this design approach and the rich potential for integration of the system into clinical practice.
Extended Reality Simulator for Advanced Training Life Support System
Donekal Chandrashekar, Nikitha (Virginia Tech, 2023-02-08)
This research focuses on the design of an Extended Reality simulator for training medical professionals in Advanced Trauma Life Support (ATLS) and pulse palpation. Existing pulse simulators have the disadvantages of being bulky, expensive, and unsuitable to be used as training tools. In addition, none of the simulators were designed to incorporate the auditory feedback of the pulse, a crucial component of continuous pulse monitoring. The developed simulator incorporates haptic, visual, and auditory feedback modes. In this work, we also conduct a comparative user study to determine the effect of multimodal feedback on different participants. Participants trained in the Audio-Haptic scenario outperformed those trained in the Haptic only scenario. These values could also be correlated with qualitative user feedback indicating that Audio-Haptic interactions were perceived as superior. With this simulator, we hope to provide medical professionals with an immersive and realistic training tool for learning the skill of palpating pulse.
HOMER: An Interactive System for Home Based Stroke Rehabilitation
Kelliher, Aisling; Choi, Jinwoo; Huang, Jia-Bin; Rikakis, Thanassis; Kitani, Kris (ACM, 2017)
Delivering long term, unsupervised stroke rehabilitation in the home is a complex challenge that requires robust, low cost, scalable, and engaging solutions. We present HOMER, an interactive system that uses novel therapy artifacts, a computer vision approach, and a tablet interface to provide users with a flexible solution suitable for home based rehabilitation. HOMER builds on our prior work developing systems for lightly supervised rehabilitation use in the clinic, by identifying key features for functional movement analysis, adopting a simplified classification assessment approach, and supporting transferability of therapy outcomes to daily living experiences through the design of novel rehabilitation artifacts. A small pilot study with unimpaired subjects indicates the potential of the system in effectively assessing movement and establishing a creative environment for training.
Human Computer Interaction for Complex Machine Learning
Zilevu, Kobla Setor (Virginia Tech, 2022-05-09)
This dissertation focuses on taking a human-centric approach to utilize human intelligence best to inform machine learning models. More specifically, the complex relationship between the changes in movement functionality to movement quality. I designed and evaluated the Tacit Computable Empowering methodology across two domains: in-home rehabilitation and clinical assessment. My methodology has three main objectives: first, to transform tacit expert knowledge into explicit knowledge. Second, to transform explicit knowledge into a computable framework that machine learning can understand and replicate. Third, synergize human intelligence with computational machine learning to empower, not replace, the human. Finally, my methodology uses assistive interfaces to allow clinicians and machine learning models to draw parallels between movement functionality and movement quality. The results from my dissertation inform researchers and clinicians on how best to create a standardized framework to capture and assess human movement data for embodied learning scenarios
Inclusion of Clinicians in the Development and Evaluation of Clinical Artificial Intelligence Tools: A Systematic Literature Review
Jesso, Stephanie Tulk; Kelliher, Aisling; Sanghavi, Harsh; Martin, Thomas; Parker, Sarah H. (Frontiers, 2022-04-07)
The application of machine learning (ML) and artificial intelligence (AI) in healthcare domains has received much attention in recent years, yet significant questions remain about how these new tools integrate into frontline user workflow, and how their design will impact implementation. Lack of acceptance among clinicians is a major barrier to the translation of healthcare innovations into clinical practice. In this systematic review, we examine when and how clinicians are consulted about their needs and desires for clinical AI tools. Forty-five articles met criteria for inclusion, of which 24 were considered design studies. The design studies used a variety of methods to solicit and gather user feedback, with interviews, surveys, and user evaluations. Our findings show that tool designers consult clinicians at various but inconsistent points during the design process, and most typically at later stages in the design cycle (82%, 19/24 design studies). We also observed a smaller amount of studies adopting a human-centered approach and where clinician input was solicited throughout the design process (22%, 5/24). A third (15/45) of all studies reported on clinician trust in clinical AI algorithms and tools. The surveyed articles did not universally report validation against the “gold standard” of clinical expertise or provide detailed descriptions of the algorithms or computational methods used in their work. To realize the full potential of AI tools within healthcare settings, our review suggests there are opportunities to more thoroughly integrate frontline users’ needs and feedback in the design process.
Interactive Interfaces for Capturing and Annotating Videos of Human Movement
Zilevu, Kobla Setor (Virginia Tech, 2019-07-11)
In this thesis, I describe the iterative service design process I used in identifying and understanding the needs of diverse stakeholders, the development of technologies to support their mutually beneficial needs, and the evaluation of the end-user experience with these technologies. Over three iterative design cycles, the set of identified end-user customers expanded to include the patient, the supervising therapist, the annotating therapist, and other members of the development team. Multiple versions of interactive movement capture and annotation tools were developed as the needs of these stakeholders were clarified and evolved, and the optimal data forms and structures became evident. Interactions between the stakeholders and the developed technologies operating in various environments were evaluated and assessed to help improve and optimize the entire service ecosystem. Results and findings from these three design cycles are being used to direct and shape my ongoing and future doctoral research
Intimate Narratives: An Assets-Based Approach To Develop Holistic Perspectives of Student Mothers' Lives and Their Use of Technology in Parenting
Bhatti, Neelma; Mbakwe, Amarachi; Nnadi, Sandra; Clarke, Geetha; Gautam, Aakash; McCrickard, D. Scott; Kelliher, Aisling (ACM, 2022-11-11)
This paper details our collaborative approach in capturing a holistic understanding of parental technology use through an assets-based framework. We steer the focus away from the design of technology as the central force of technological innovation, and instead support participants to reflect and describe intimate details that highlight specific use-contexts of technology in their lives. We leverage a group of foreign graduate student mothers’ self-described unique strengths to gain an in-depth account of their lived experiences with technology. As research participants and co-authors, our collaborators elicit intimate narratives about meaningful events in their lives, bringing social and cultural aspects of their lived experience to the forefront, and thus providing broader context of their use of technology. We detail and reflect upon our approach of promoting user agency by creating an affinity group, fostering a safe and intimate space for research engagement, and describe the implications of using our adapted research methodology in intimate settings. We conclude by highlighting the various ways in which technology facilitates foreign student parenting, as well as the ways in which it serves as a temporary band-aid solution, prompting consideration of larger social issues.
Libero
Mittra, Anirudh (Virginia Tech, 2017-03-27)
Libero is a 2D video game that aims to explore the concepts of dealing with personal issues such as insomnia and anxiety. It is a 2D stealth puzzle game that takes influence from older dungeon-crawlers and rogue-likes from the 1990s as well as inspiration from modern games designed for mobile platforms such as iOS and Android phones. The game experiments with new 2D normal mapping technologies for a unique take on pixel art.
Printing on Objects: Curved Layer Fused Filament Fabrication on Scanned Surfaces with a Parallel Deposition Machine
Coe, Edward Olin (Virginia Tech, 2019-06-21)
Consumer additive manufacturing (3D printing) has rapidly grown over the last decade. While the technology for the most common type, Fused Filament Fabrication (FFF), has systematically improved and sales have increased, fundamentally, the capabilities of the machines have remained the same. FFF printers are still limited to depositing layers onto a flat build plate. This makes it difficult to combine consumer AM with other objects. While consumer AM promises to allow us to customize our world, the reality has fallen short. The ability to directly modify existing objects presents numerous possibilities to the consumer: personalization, adding functionality, improving functionality, repair, and novel multi-material manufacturing processes. Indeed, similar goals for industrial manufacturing drove the research and development of technologies like direct write and directed energy deposition which can deposit layers onto uneven surfaces. Replicating these capabilities on consumer 3-axis FFF machines is difficult mainly due to issues with reliability, repeatability, and quality. This thesis proposes, demonstrates, and tests a method for scanning and printing dimensionally-accurate (unwarped) digital forms onto physical objects using a modified consumer-grade 3D printer. It then provides an analysis of the machine design considerations and critical process parameters.
Supporting User Interactions with Smart Built Environments
Handosa, Mohamed Hussein Hafez (Virginia Tech, 2019-02-04)
Before the recent advances in sensing, actuation, computing and communication technologies, the integration between the digital and the physical environment was limited. Humans linked those two worlds by collecting data about the physical environment before feeding it into the digital environment, and by changing the state of the physical environment based on the state of the digital environment. The incorporation of computing, communication, sensing, and actuation technologies into everyday physical objects has empowered the vision of the Internet of Things (IoT). Things can autonomously collect data about the physical environment, exchange information with other things, and take actions on behalf of humans. Application domains that can benefit from IoT include smart buildings, smart cities, smart water, smart agriculture, smart animal farming, smart metering, security and emergencies, retail, logistics, industrial control, and health care. For decades, building automation, intelligent buildings, and more recently smart buildings have received a considerable attention in both academia and industry. We use the term smart built environments (SBE) to describe smart, intelligent, physical, built, architectural spaces ranging from a single room to a whole city. Legacy SBEs were often closed systems operating their own standards and custom protocols. SBEs evolved to Internet-connected systems leveraging the Internet technologies and services (e.g., cloud services) to unleash new capabilities. IoT-enabled SBEs, as one of the various applications of the IoT, can change the way we experience our homes and workplaces significantly and make interacting with technology almost inevitable. This can provide several benefits to modern society and help to make our life easier. Meanwhile, security, privacy, and safety concerns should be addressed appropriately. Unlike traditional computing devices, things usually have no or limited input/output (I/O) capabilities. Leveraging the ubiquity of general-purpose computing devices (e.g., smartphones), thing vendors usually provide interfaces for their products in the form of mobile apps or web-based portals. Interacting with different things using different mobile apps or web-based portals does not scale well. Requiring the user to switch between tens or hundreds of mobile apps and web-based portals to interact with different things in different smart spaces may not be feasible. Moreover, it can be tricky for non-domestic users (e.g., visitors) of a given SBE to figure out, without guidance, what mobile apps or web-based portals they need to use to interact with the surrounding. While there has been a considerable research effort to address a variety of challenges associated with the thing-to-thing interaction, human-to-thing interaction related research is limited. Many of the proposed approaches and industry-adopted techniques rely on more traditional, well understood and widely used Human-Computer Interaction (HCI) methods and techniques to support interaction between humans and things. Such techniques have mostly originated in a world of desktop computers that have a screen, mouse, and keyboard. However, SBEs introduce a radically different interaction context where there are no centralized, easily identifiable input and output devices. A desktop computer of the past is being replaced with the whole SBE. Depending on the task at hand and personal preferences, a user may prefer to use one interaction modality over another. For instance, turning lights on/off using an app may be more cumbersome or time-consuming compared to using a simple physical switch. This research focuses on leveraging the recent advances in IoT and related technologies to support user interactions with SBEs. We explore how to support flexible and adaptive multimodal interfaces and interactions while providing a consistent user experience in an SBE based on the current context and the available user interface and interaction capabilities.
Technology and International Student Parenting: Implications for Research and Design of Digital Childcare Technologies
Bhatti, Neelma (Virginia Tech, 2022-08-02)
Digital technologies such as televisions, touch screen tablets, smartphones, and smart speakers are now frequently encountered and used by young children even before the age of one. These devices facilitate modern parents in their care-giving of young children due to their prevalence in the home environment. The use of these devices is especially common by international student mothers of young children who subscribe to a multiplicity of roles such as being a productive student, efficient mother, and dutiful partner in a new country. This dissertation summarizes four studies exploring the role of technology in international student mothers' life as a parent of young children, and the implications of design and research of technologies for parents based on the transferable learning from these studies. The first and second studies employ auto ethnographic and collaborative approach to involve these mothers as equal stakeholders and collaborators to understand their context of use of technology. The third and fourth studies explore the various uses of technology by caregivers and young children, to obtain certain gratifications. By engaging primary caregivers in in-depth efforts of understanding of their motivations and perceptions about early childhood media exposure, I set forth the praxis between the professional recommendations and their actual lived experiences with technology and young children. Building on these insights, I present a conceptual framework for research which considers the dyadic use of technology due to the close relationship between primary caregivers and young children. Based on the various roles of technology in international student mothers' parenting, I present implications for designing technologies which can assist parents in their care giving duties.
Technology on the Trail: Using Cultural Probes to Understand Hikers
Fields, Sarah Grace (Virginia Tech, 2017-08-21)
The definition of technology may have changed quite a bit over the years, but people have been bringing technology to remote, natural locations since long before concepts like recreational hiking or national parks existed. Nowadays, "digital" is usually implied before the word technology, and discussion of technology and trails often revolves around smartphones and GPS systems. However, a wide variety of hiking gear has benefited from precise engineering and product design. Even with more digital products hitting the shelves, many hikers go out on the trail to get away from or limit their use of technology, however they may define that word. Before any technology for the trail can be designed, the diverse perspectives of hikers must be explored rather than taking them for granted. Polling hikers through digital means or even delivering prototypes for research through design seems disingenuous when part of the target audience has negative attitudes towards technology. For this reason, cultural probes stood out as a useful method for understanding hikers and inspiring future directions for Technology on the Trail. The heart of the matter is indeed a question of culture, so probes are a logical choice for teasing out a variety of viewpoints. The goal of this study is not to design new technology. Rather, the goal is to find a way to make technology and nature more harmonious in the context of hiking. This could end up requiring new designs, but it could also be a matter of shifting perspective instead. No device or gear will ever be for everyone, and that's natural. Technology on the Trail can still seek to support both users of technology and the bystanders who are affected by the technology use of others.
Understanding the Effects of Virtual Education on Kindergarten Children and the Relationships between Teachers, Parents, and Children During a Global Pandemic
Jain, Yash (Virginia Tech, 2021-05-24)
The global COVID-19 pandemic dramatically altered learning experiences for children, parents, and teachers worldwide. For very young children, the scrambled introduction of complex virtual tools as a proxy for the classroom experience has been particularly challenging. I conducted interviews with kindergarten teachers and parents with young children to better understand their experiences navigating virtual learning during a stressful time. Insights from those discussions informed the iterative design process I used to generate alternative interactive interfaces for online kindergarten instruction. In this thesis, I present findings from the interviews, the multi-stage interface design process, participant responses to the interface design, and promising directions for future work.

Browsing by Author "Kelliher, Aisling"

Results Per Page

Sort Options