Matching Items (115)
Filtering by
- Creators: Arizona State University
- Creators: McDaniel, Troy
Description
Parkinson's disease (PD) is a neurodegenerative disorder that produces a characteristic set of neuromotor deficits that sometimes includes reduced amplitude and velocity of movement. Several studies have shown that people with PD improved their motor performance when presented with external cues. Other work has demonstrated that high velocity and large amplitude exercises can increase the amplitude and velocity of movement in simple carryover tasks in the upper and lower extremities. Although the cause for these effects is not known, improvements due to cueing suggest that part of the neuromotor deficit in PD is in the integration of sensory feedback to produce motor commands. Previous studies have documented some somatosensory deficits, but only limited information is available regarding the nature and magnitude of sensorimotor deficits in the shoulder of people with PD. The goals of this research were to characterize the sensorimotor impairment in the shoulder joint of people with PD and to investigate the use of visual feedback and large amplitude/high velocity exercises to target PD-related motor deficits. Two systems were designed and developed to use visual feedback to assess the ability of participants to accurately adjust limb placement or limb movement velocity and to encourage improvements in performance of these tasks. Each system was tested on participants with PD, age-matched control subjects and young control subjects to characterize and compare limb placement and velocity control capabilities. Results demonstrated that participants with PD were less accurate at placing their limbs than age-matched or young control subjects, but that their performance improved over the course of the test session such that by the end, the participants with PD performed as well as controls. For the limb velocity feedback task, participants with PD and age-matched control subjects were less accurate than young control subjects, but at the end of the session, participants with PD and age-matched control subjects were as accurate as the young control subjects. This study demonstrates that people with PD were able to improve their movement patterns based on visual feedback of performance and suggests that this feedback paradigm may be useful in exercise programs for people with PD.
ContributorsSmith, Catherine (Author) / Abbas, James J (Thesis advisor) / Ingalls, Todd (Thesis advisor) / Krishnamurthi, Narayanan (Committee member) / Buneo, Christopher (Committee member) / Rikakis, Thanassis (Committee member) / Arizona State University (Publisher)
Created2015
Description
The purpose of this study is to identify the needs of older adults with Alzheimer's disease (AD) and related dementias (ADRD) admitted to a rehabilitation setting where they are expected to physically and mentally function to their optimal level of health. To date, no studies have identified the needs and concerns of ADRD patients in rehabilitation settings. The Needs-Driven Dementia-Compromised Behavior (NDB) Model, the researcher's clinical experience, and the state of the current scientific literature will help guide the study. An exploratory qualitative research approach was employed to gather data and discover new information about the ADRD patient's needs and related behavioral outcomes. The qualitative findings on the discrepancies and similarities in perceptions of ADRD patient needs were obtained by examining formal and informal caregivers' perceptions. The researcher recruited registered nurses and certified nurse assistants (RNs and CNAs, formal) and family/friends (informal) who have provided care to patients in inpatient rehabilitation facilities to participate in focus groups and individualized focused interviews. The data were collated and analyzed using a thematic analysis approach. The overarching theme that developed as a result of this approach revealed discordant perceptions and expectations of ADRD patients' needs between the formal and informal caregivers with six subthemes: communication and information, family involvement, rehabilitation nurse philosophy, nursing care, belonging, and patient outcomes. The researcher provided recommendations to help support these needs. These findings will help guide the development of nurse-lead interventions for ADRD patients in a rehabilitation setting.
ContributorsAllen, Angela Marie (Author) / Coon, David W. (Thesis advisor) / McCarthy, Marianne (Committee member) / Uriri-Glover, Johannah (Committee member) / Arizona State University (Publisher)
Created2014
Description
This action research study is the culmination of several action cycles investigating cognitive information processing and learning strategies based on students approach to learning theory and assessing students' meta-cognitive learning, motivation, and reflective development suggestive of deep learning. The study introduces a reading assignment as an integrative teaching method with the purpose of challenging students' assumptions and requiring them to think from multiple perspectives thus influencing deep learning. The hypothesis is that students who are required to critically reflect on their own perceptions will develop the deep learning skills needed in the 21st century. Pre and post surveys were used to assess for changes in students' preferred approach to learning and reflective practice styles. Qualitative data was collected in the form of student stories and student literature circle transcripts to further describe student perceptions of the experience. Results indicate stories that include examples of critical reflection may influence students to use more transformational types of reflective learning actions. Approximately fifty percent of the students in the course increased their preference for deep learning by the end of the course. Further research is needed to determine the effect of narratives on student preferences for deep learning.
ContributorsBradshaw, Vicki (Author) / Carlson, David L. (Thesis advisor) / Jordan, Michelle (Committee member) / Gagnon, Marie (Committee member) / Arizona State University (Publisher)
Created2012
Description
This dissertation presents a portable methodology for holistic planning and optimization of right of way infrastructure rehabilitation that was designed to generate monetary savings when compared to planning that only considers single infrastructure components. Holistic right of way infrastructure planning requires simultaneous consideration of the three right of way infrastructure components that are typically owned and operated under the same municipal umbrella: roads, sewer, and water. The traditional paradigm for the planning of right way asset management involves operating in silos where there is little collaboration amongst different utility departments in the planning of maintenance, rehabilitation, and renewal projects. By collaborating across utilities during the planning phase, savings can be achieved when collocated rehabilitation projects from different right of way infrastructure components are synchronized to occur at the same time. These savings are in the form of shared overhead and mobilization costs, and roadway projects providing open space for subsurface utilities. Individual component models and a holistic model that utilize evolutionary algorithms to optimize five year maintenance, rehabilitation, and renewal plans for the road, sewer, and water components were created and compared. The models were designed to be portable so that they could be used with any infrastructure condition rating, deterioration modeling, and criticality assessment systems that might already be in place with a municipality. The models attempt to minimize the overall component score, which is a function of the criticality and condition of the segments within each network, by prescribing asset management activities to different segments within a component network while subject to a constraining budget. The individual models were designed to represent the traditional decision making paradigm and were compared to the holistic model. In testing at three different budget levels, the holistic model outperformed the individual models in the ability to generate five year plans that optimized prescribed maintenance, rehabilitation and renewal for various segments in order to achieve the goal of improving the component score. The methodology also achieved the goal of being portable, in that it is compatible with any condition rating, deterioration, and criticality system.
ContributorsCarey, Brad David (Author) / Lueke, Jason S (Thesis advisor) / Ariaratnam, Samuel (Committee member) / Bashford, Howard (Committee member) / Arizona State University (Publisher)
Created2012
Description
In rehabilitation settings, activity limitation can be a significant barrier to recovery. This study sought to examine the effects of state and trait level benefit finding, positive affect, and catastrophizing on activity limitation among individuals with a physician-confirmed diagnosis of either Osteoarthritis (OA), Fibromyalgia (FM), or a dual diagnosis of OA/FM. Participants (106 OA, 53 FM, and 101 OA/FM) who had no diagnosed autoimmune disorder, a pain rating above 20 on a 0-100 scale, and no involvement in litigation regarding their condition were recruited in the Phoenix metropolitan area for inclusion in the current study. After initial questionnaires were completed, participants were trained to complete daily diaries on a laptop computer and instructed to do so a half an hour before bed each night for 30 days. In each diary, participants rated their average daily pain, benefit finding, positive affect, catastrophizing, and activity limitation. A single item, "I thought about some of the good things that have come from living with my pain" was used to examine the broader construct of benefit finding. It was hypothesized that state and trait level benefit finding would have a direct relation with activity limitation and a partially mediated relationship, through positive affect. Multilevel modeling with SAS PROC MIXED revealed that benefit finding was not directly related to activity limitation. Increases in benefit finding were associated, however, with decreases in activity limitation through a significant mediated relationship with positive affect. Individuals who benefit find had a higher level of positive affect which was associated with decreased activity limitation. A suppression effect involving pain and benefit finding at the trait level was also found. Pain appeared to increase the predictive validity of the relation of benefit finding to activity limitation. These findings have important implications for rehabilitation psychologists and should embolden clinicians to encourage patients to increase positive affect by employing active approach-oriented coping strategies like benefit finding to reduce activity limitation.
ContributorsKinderdietz, Jeffrey Scott (Author) / Zautra, Alex (Thesis advisor) / Davis, Mary (Committee member) / Barrera, Manuel (Committee member) / Okun, Morris (Committee member) / Arizona State University (Publisher)
Created2012
Description
Discriminative learning when training and test data belong to different distributions is a challenging and complex task. Often times we have very few or no labeled data from the test or target distribution, but we may have plenty of labeled data from one or multiple related sources with different distributions. Due to its capability of migrating knowledge from related domains, transfer learning has shown to be effective for cross-domain learning problems. In this dissertation, I carry out research along this direction with a particular focus on designing efficient and effective algorithms for BioImaging and Bilingual applications. Specifically, I propose deep transfer learning algorithms which combine transfer learning and deep learning to improve image annotation performance. Firstly, I propose to generate the deep features for the Drosophila embryo images via pretrained deep models and build linear classifiers on top of the deep features. Secondly, I propose to fine-tune the pretrained model with a small amount of labeled images. The time complexity and performance of deep transfer learning methodologies are investigated. Promising results have demonstrated the knowledge transfer ability of proposed deep transfer algorithms. Moreover, I propose a novel Robust Principal Component Analysis (RPCA) approach to process the noisy images in advance. In addition, I also present a two-stage re-weighting framework for general domain adaptation problems. The distribution of source domain is mapped towards the target domain in the first stage, and an adaptive learning model is proposed in the second stage to incorporate label information from the target domain if it is available. Then the proposed model is applied to tackle cross lingual spam detection problem at LinkedIn’s website. Our experimental results on real data demonstrate the efficiency and effectiveness of the proposed algorithms.
ContributorsSun, Qian (Author) / Ye, Jieping (Committee member) / Xue, Guoliang (Committee member) / Liu, Huan (Committee member) / Li, Jing (Committee member) / Arizona State University (Publisher)
Created2015
Description
Olecranon fractures account for approximately 10% of upper extremity fractures and 95% of them require surgical fixation. Most of the clinical, retrospective and biomechanical studies have supported plate fixation over other surgical fixation techniques since plates have demonstrated low incidence of reoperation, high fixation stability and resumption of activities of daily living (ADL) earlier. Thus far, biomechanical studies have been helpful in evaluating and comparing different plate fixation constructs based on fracture stability. However, they have not provided information that can be used to design rehabilitation protocols such as information that relates load at the hand with tendon tension or load at the interface between the plate and the bone. The set-ups used in biomechanical studies have included simple mechanical testing machines that either measured construct stiffness by cyclic loading the specimens or construct strength by performing ramp load until failure. Some biomechanical studies attempted to simulate tendon tension but the in-vivo tension applied to the tendon remains unknown. In this study, a novel procedure to test the olecranon fracture fixation using modern olecranon plates was developed to improve the biomechanical understanding of failures and to help determine the weights that can be safely lifted and the range of motion (ROM) that should be performed during rehabilitation procedures.
Design objectives were defined based on surgeon's feedback and analysis of unmet needs in the area of biomechanical testing. Four pilot cadaveric specimens were prepared to run on an upper extremity feedback controller and the set-up was validated based on the design objectives. Cadaveric specimen preparation included a series of steps such as dissection, suturing and potting that were standardized and improved iteratively after pilot testing. Additionally, a fracture and plating protocol was developed and fixture lengths were standardized based on anthropometric data. Results from the early pilot studies indicated shortcomings in the design, which was then iteratively refined for the subsequent studies. The final pilot study demonstrated that all of the design objectives were met. This system is planned for use in future studies that will assess olecranon fracture fixation and that will investigate the safety of rehabilitation protocols.
Design objectives were defined based on surgeon's feedback and analysis of unmet needs in the area of biomechanical testing. Four pilot cadaveric specimens were prepared to run on an upper extremity feedback controller and the set-up was validated based on the design objectives. Cadaveric specimen preparation included a series of steps such as dissection, suturing and potting that were standardized and improved iteratively after pilot testing. Additionally, a fracture and plating protocol was developed and fixture lengths were standardized based on anthropometric data. Results from the early pilot studies indicated shortcomings in the design, which was then iteratively refined for the subsequent studies. The final pilot study demonstrated that all of the design objectives were met. This system is planned for use in future studies that will assess olecranon fracture fixation and that will investigate the safety of rehabilitation protocols.
ContributorsJain, Saaransh (Author) / Abbas, James (Thesis advisor) / LaBelle, Jeffrey (Thesis advisor) / Jacofsky, Marc (Committee member) / Arizona State University (Publisher)
Created2015
Description
Computer Vision as a eld has gone through signicant changes in the last decade.
The eld has seen tremendous success in designing learning systems with hand-crafted
features and in using representation learning to extract better features. In this dissertation
some novel approaches to representation learning and task learning are studied.
Multiple-instance learning which is generalization of supervised learning, is one
example of task learning that is discussed. In particular, a novel non-parametric k-
NN-based multiple-instance learning is proposed, which is shown to outperform other
existing approaches. This solution is applied to a diabetic retinopathy pathology
detection problem eectively.
In cases of representation learning, generality of neural features are investigated
rst. This investigation leads to some critical understanding and results in feature
generality among datasets. The possibility of learning from a mentor network instead
of from labels is then investigated. Distillation of dark knowledge is used to eciently
mentor a small network from a pre-trained large mentor network. These studies help
in understanding representation learning with smaller and compressed networks.
The eld has seen tremendous success in designing learning systems with hand-crafted
features and in using representation learning to extract better features. In this dissertation
some novel approaches to representation learning and task learning are studied.
Multiple-instance learning which is generalization of supervised learning, is one
example of task learning that is discussed. In particular, a novel non-parametric k-
NN-based multiple-instance learning is proposed, which is shown to outperform other
existing approaches. This solution is applied to a diabetic retinopathy pathology
detection problem eectively.
In cases of representation learning, generality of neural features are investigated
rst. This investigation leads to some critical understanding and results in feature
generality among datasets. The possibility of learning from a mentor network instead
of from labels is then investigated. Distillation of dark knowledge is used to eciently
mentor a small network from a pre-trained large mentor network. These studies help
in understanding representation learning with smaller and compressed networks.
ContributorsVenkatesan, Ragav (Author) / Li, Baoxin (Thesis advisor) / Turaga, Pavan (Committee member) / Yang, Yezhou (Committee member) / Davulcu, Hasan (Committee member) / Arizona State University (Publisher)
Created2017
Description
The performance of most of the visual computing tasks depends on the quality of the features extracted from the raw data. Insightful feature representation increases the performance of many learning algorithms by exposing the underlying explanatory factors of the output for the unobserved input. A good representation should also handle anomalies in the data such as missing samples and noisy input caused by the undesired, external factors of variation. It should also reduce the data redundancy. Over the years, many feature extraction processes have been invented to produce good representations of raw images and videos.
The feature extraction processes can be categorized into three groups. The first group contains processes that are hand-crafted for a specific task. Hand-engineering features requires the knowledge of domain experts and manual labor. However, the feature extraction process is interpretable and explainable. Next group contains the latent-feature extraction processes. While the original feature lies in a high-dimensional space, the relevant factors for a task often lie on a lower dimensional manifold. The latent-feature extraction employs hidden variables to expose the underlying data properties that cannot be directly measured from the input. Latent features seek a specific structure such as sparsity or low-rank into the derived representation through sophisticated optimization techniques. The last category is that of deep features. These are obtained by passing raw input data with minimal pre-processing through a deep network. Its parameters are computed by iteratively minimizing a task-based loss.
In this dissertation, I present four pieces of work where I create and learn suitable data representations. The first task employs hand-crafted features to perform clinically-relevant retrieval of diabetic retinopathy images. The second task uses latent features to perform content-adaptive image enhancement. The third task ranks a pair of images based on their aestheticism. The goal of the last task is to capture localized image artifacts in small datasets with patch-level labels. For both these tasks, I propose novel deep architectures and show significant improvement over the previous state-of-art approaches. A suitable combination of feature representations augmented with an appropriate learning approach can increase performance for most visual computing tasks.
The feature extraction processes can be categorized into three groups. The first group contains processes that are hand-crafted for a specific task. Hand-engineering features requires the knowledge of domain experts and manual labor. However, the feature extraction process is interpretable and explainable. Next group contains the latent-feature extraction processes. While the original feature lies in a high-dimensional space, the relevant factors for a task often lie on a lower dimensional manifold. The latent-feature extraction employs hidden variables to expose the underlying data properties that cannot be directly measured from the input. Latent features seek a specific structure such as sparsity or low-rank into the derived representation through sophisticated optimization techniques. The last category is that of deep features. These are obtained by passing raw input data with minimal pre-processing through a deep network. Its parameters are computed by iteratively minimizing a task-based loss.
In this dissertation, I present four pieces of work where I create and learn suitable data representations. The first task employs hand-crafted features to perform clinically-relevant retrieval of diabetic retinopathy images. The second task uses latent features to perform content-adaptive image enhancement. The third task ranks a pair of images based on their aestheticism. The goal of the last task is to capture localized image artifacts in small datasets with patch-level labels. For both these tasks, I propose novel deep architectures and show significant improvement over the previous state-of-art approaches. A suitable combination of feature representations augmented with an appropriate learning approach can increase performance for most visual computing tasks.
ContributorsChandakkar, Parag Shridhar (Author) / Li, Baoxin (Thesis advisor) / Yang, Yezhou (Committee member) / Turaga, Pavan (Committee member) / Davulcu, Hasan (Committee member) / Arizona State University (Publisher)
Created2017
Description
Progressive gait disorder in Parkinson's disease (PD) is usually exhibited as reduced step/stride length and gait speed. People with PD also exhibit stooped posture, which can contribute to reduced step length and arm swing. Since gait and posture deficits in people with PD do not respond well to pharmaceutical and surgical treatments, novel rehabilitative therapies to alleviate these impairments are necessary. Many studies have confirmed that people with PD can improve their walking patterns when external cues are presented. Only a few studies have provided explicit real-time feedback on performance, but they did not report how well people with PD can follow the cues on a step-by-step basis. In a single-session study using a novel-treadmill based paradigm, our group had previously demonstrated that people with PD could follow step-length and back angle feedback and improve their gait and posture during treadmill walking. This study investigated whether a long-term (6-week, 3 sessions/week) real-time feedback training (RTFT) program can improve overground gait, upright posture, balance, and quality of life. Three subjects (mean age 70 ± 2 years) with mild to moderate PD (Hoehn and Yahr stage III or below) were enrolled and participated in the program. The RTFT sessions involved walking on a treadmill while following visual feedback of step length and posture (one at any given time) displayed on a monitor placed in front of the subject at eye-level. The target step length was set between 110-120% of the step length obtained during a baseline non-feedback walking trial and the target back angle was set at the maximum upright posture exhibited during a quiet standing task. Two subjects were found to significantly improve their posture and overground walking at post-training and these changes were retained six weeks after RTFT (follow-up) and the third subject improved his upright posture and gait rhythmicity. Furthermore, the magnitude of the improvements observed in these subjects was greater than the improvements observed in reports on other neuromotor interventions. These results provide preliminary evidence that real-time feedback training can be used as an effective rehabilitative strategy to improve gait and upright posture in people with PD.
ContributorsBaskaran, Deepika (Author) / Krishnamurthi, Narayanan (Thesis advisor) / Abbas, James (Thesis advisor) / Honeycutt, Claire (Committee member) / Arizona State University (Publisher)
Created2017