Matching Items (33)
Filtering by
- All Subjects: Depression
- Creators: Department of Psychology
- Creators: Panchanathan, Sethuraman
- Resource Type: Text
Description
Real-world environments are characterized by non-stationary and continuously evolving data. Learning a classification model on this data would require a framework that is able to adapt itself to newer circumstances. Under such circumstances, transfer learning has come to be a dependable methodology for improving classification performance with reduced training costs and without the need for explicit relearning from scratch. In this thesis, a novel instance transfer technique that adapts a "Cost-sensitive" variation of AdaBoost is presented. The method capitalizes on the theoretical and functional properties of AdaBoost to selectively reuse outdated training instances obtained from a "source" domain to effectively classify unseen instances occurring in a different, but related "target" domain. The algorithm is evaluated on real-world classification problems namely accelerometer based 3D gesture recognition, smart home activity recognition and text categorization. The performance on these datasets is analyzed and evaluated against popular boosting-based instance transfer techniques. In addition, supporting empirical studies, that investigate some of the less explored bottlenecks of boosting based instance transfer methods, are presented, to understand the suitability and effectiveness of this form of knowledge transfer.
ContributorsVenkatesan, Ashok (Author) / Panchanathan, Sethuraman (Thesis advisor) / Li, Baoxin (Committee member) / Ye, Jieping (Committee member) / Arizona State University (Publisher)
Created2011
Description
The Beck Depression Inventory II (BDI-II) and the Patient Health Questionnaire 9 (PHQ-9) are highly valid depressive testing tools used to measure the symptom profile of depression globally and in South Asia, respectively (Steer et al., 1998; Kroenke et al, 2001). Even though the South Asian population comprises only 23% of the world’s population, it represents one-fifth of the world’s mental health disorders (Ogbo et al., 2018). Although this population is highly affected by mental disorders, there is a lack of culturally relevant research on specific subsections of the South Asian population.<br/><br/>As such, the goal of this study is to investigate the differences in the symptom profile of depression in native and immigrant South Asian populations. We investigated the role of collective self-esteem and perceived discrimination on mental health. <br/><br/>For the purpose of this study, participants were asked a series of questions about their depressive symptoms, self-esteem and perceived discrimination using various depressive screening measures, a self-esteem scale, and a perceived discrimination scale.<br/><br/>We found that immigrants demonstrated higher depressive symptoms than Native South Asians as immigration was viewed as a stressor. First-generation and second-generation South Asian immigrants identified equally with somatic and psychological symptoms. These symptoms were positively correlated with perceived discrimination, and collective self-esteem was shown to increase the likelihood of these symptoms.<br/><br/>This being said, the results from this study may be generalized only to South Asian immigrants who come from highly educated and high-income households. Since seeking professional help and being aware of one’s mental health is vital for wellbeing, the results from this study may spark the interest in an open communication about mental health within the South Asian immigrant community as well as aid in the restructuring of a highly reliable and valid measurement to be specific to a culture.
ContributorsMurthy, Nithara (Co-author) / Swaminathan, Manasa (Co-author) / Vogel, Joanne (Thesis director) / Kwan, Sau (Committee member) / Department of Psychology (Contributor) / School of Human Evolution & Social Change (Contributor) / Barrett, The Honors College (Contributor)
Created2021-05
Description
The rapid escalation of technology and the widespread emergence of modern technological equipments have resulted in the generation of humongous amounts of digital data (in the form of images, videos and text). This has expanded the possibility of solving real world problems using computational learning frameworks. However, while gathering a large amount of data is cheap and easy, annotating them with class labels is an expensive process in terms of time, labor and human expertise. This has paved the way for research in the field of active learning. Such algorithms automatically select the salient and exemplar instances from large quantities of unlabeled data and are effective in reducing human labeling effort in inducing classification models. To utilize the possible presence of multiple labeling agents, there have been attempts towards a batch mode form of active learning, where a batch of data instances is selected simultaneously for manual annotation. This dissertation is aimed at the development of novel batch mode active learning algorithms to reduce manual effort in training classification models in real world multimedia pattern recognition applications. Four major contributions are proposed in this work: $(i)$ a framework for dynamic batch mode active learning, where the batch size and the specific data instances to be queried are selected adaptively through a single formulation, based on the complexity of the data stream in question, $(ii)$ a batch mode active learning strategy for fuzzy label classification problems, where there is an inherent imprecision and vagueness in the class label definitions, $(iii)$ batch mode active learning algorithms based on convex relaxations of an NP-hard integer quadratic programming (IQP) problem, with guaranteed bounds on the solution quality and $(iv)$ an active matrix completion algorithm and its application to solve several variants of the active learning problem (transductive active learning, multi-label active learning, active feature acquisition and active learning for regression). These contributions are validated on the face recognition and facial expression recognition problems (which are commonly encountered in real world applications like robotics, security and assistive technology for the blind and the visually impaired) and also on collaborative filtering applications like movie recommendation.
ContributorsChakraborty, Shayok (Author) / Panchanathan, Sethuraman (Thesis advisor) / Balasubramanian, Vineeth N. (Committee member) / Li, Baoxin (Committee member) / Mittelmann, Hans (Committee member) / Ye, Jieping (Committee member) / Arizona State University (Publisher)
Created2013
Description
This paper presents work that was done to create a system capable of facial expression recognition (FER) using deep convolutional neural networks (CNNs) and test multiple configurations and methods. CNNs are able to extract powerful information about an image using multiple layers of generic feature detectors. The extracted information can be used to understand the image better through recognizing different features present within the image. Deep CNNs, however, require training sets that can be larger than a million pictures in order to fine tune their feature detectors. For the case of facial expression datasets, none of these large datasets are available. Due to this limited availability of data required to train a new CNN, the idea of using naïve domain adaptation is explored. Instead of creating and using a new CNN trained specifically to extract features related to FER, a previously trained CNN originally trained for another computer vision task is used. Work for this research involved creating a system that can run a CNN, can extract feature vectors from the CNN, and can classify these extracted features. Once this system was built, different aspects of the system were tested and tuned. These aspects include the pre-trained CNN that was used, the layer from which features were extracted, normalization used on input images, and training data for the classifier. Once properly tuned, the created system returned results more accurate than previous attempts on facial expression recognition. Based on these positive results, naïve domain adaptation is shown to successfully leverage advantages of deep CNNs for facial expression recognition.
ContributorsEusebio, Jose Miguel Ang (Author) / Panchanathan, Sethuraman (Thesis director) / McDaniel, Troy (Committee member) / Venkateswara, Hemanth (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2016-05
Description
This paper presents the design and evaluation of a haptic interface for augmenting human-human interpersonal interactions by delivering facial expressions of an interaction partner to an individual who is blind using a visual-to-tactile mapping of facial action units and emotions. Pancake shaftless vibration motors are mounted on the back of a chair to provide vibrotactile stimulation in the context of a dyadic (one-on-one) interaction across a table. This work explores the design of spatiotemporal vibration patterns that can be used to convey the basic building blocks of facial movements according to the Facial Action Unit Coding System. A behavioral study was conducted to explore the factors that influence the naturalness of conveying affect using vibrotactile cues.
ContributorsBala, Shantanu (Author) / Panchanathan, Sethuraman (Thesis director) / McDaniel, Troy (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor) / Department of Psychology (Contributor)
Created2014-05
Description
The purpose of the study was to examine the effectiveness of two modes of exercise on depression in adolescents with Down syndrome (DS). Twelve participants randomly completed one of two exercise interventions. The interventions were: 1) Voluntary Cycling (VC), in which participants cycled at their self-selected pedaling rate 2) Assisted Cycling (AC), in which the participants' voluntary pedaling rates were augmented with a motor to ensure the maintenance of 80 rpms. In each intervention, the participant completed three cycling sessions each week for a total of eight weeks. Depression scores did decrease or improved after both AC and VC, but not significantly. There was a greater mean improvement for participants in the AC group than VC when analyzing total score and t-score. Future research will include a greater sample size and control group to reach significant results as well as try and reveal the mechanisms involved in these mental health improvements found after an acute bout of assisted cycling in adolescents with DS.
ContributorsTeslevich, Jennifer Lynn (Author) / Ringenbach, Shannon (Thesis director) / Kulinna, Pamela (Committee member) / Barrett, The Honors College (Contributor) / School of Nutrition and Health Promotion (Contributor) / Department of Psychology (Contributor)
Created2013-12
Description
The fields of pattern recognition and machine learning are on a fundamental quest to design systems that can learn the way humans do. One important aspect of human intelligence that has so far not been given sufficient attention is the capability of humans to express when they are certain about a decision, or when they are not. Machine learning techniques today are not yet fully equipped to be trusted with this critical task. This work seeks to address this fundamental knowledge gap. Existing approaches that provide a measure of confidence on a prediction such as learning algorithms based on the Bayesian theory or the Probably Approximately Correct theory require strong assumptions or often produce results that are not practical or reliable. The recently developed Conformal Predictions (CP) framework - which is based on the principles of hypothesis testing, transductive inference and algorithmic randomness - provides a game-theoretic approach to the estimation of confidence with several desirable properties such as online calibration and generalizability to all classification and regression methods. This dissertation builds on the CP theory to compute reliable confidence measures that aid decision-making in real-world problems through: (i) Development of a methodology for learning a kernel function (or distance metric) for optimal and accurate conformal predictors; (ii) Validation of the calibration properties of the CP framework when applied to multi-classifier (or multi-regressor) fusion; and (iii) Development of a methodology to extend the CP framework to continuous learning, by using the framework for online active learning. These contributions are validated on four real-world problems from the domains of healthcare and assistive technologies: two classification-based applications (risk prediction in cardiac decision support and multimodal person recognition), and two regression-based applications (head pose estimation and saliency prediction in images). The results obtained show that: (i) multiple kernel learning can effectively increase efficiency in the CP framework; (ii) quantile p-value combination methods provide a viable solution for fusion in the CP framework; and (iii) eigendecomposition of p-value difference matrices can serve as effective measures for online active learning; demonstrating promise and potential in using these contributions in multimedia pattern recognition problems in real-world settings.
ContributorsNallure Balasubramanian, Vineeth (Author) / Panchanathan, Sethuraman (Thesis advisor) / Ye, Jieping (Committee member) / Li, Baoxin (Committee member) / Vovk, Vladimir (Committee member) / Arizona State University (Publisher)
Created2010
Description
Major Depressive Disorder (MDD) affects over 300 million people worldwide, with the hippocampus showing decreased volume and activity in patients with MDD. The current study investigated whether a novel preclinical model of depression, unpredictable intermittent restraint (UIR), would decrease hippocampal neuronal dendritic complexity. Adult Sprague Dawley rats (24 male, 24 female) were equally divided into 4 groups: control males (CON-M), UIR males (UIR-M), control females (CON-F) and UIR females (UIR-F). UIR groups received restraint and shaking on an orbital shaker on a randomized schedule for 30 or 60 minutes/day for two to six days in a row for 26 days (21 total UIR days) before behavioral testing commenced. UIR continued and was interspersed between behavioral test days. At the end of behavioral testing, brains were processed. The behavior is published and not part of my honor’s thesis; my contribution involved quantifying and analyzing neurons in the hippocampus. Several neuronal types are found in the CA3 subregion of the hippocampus and I focused on short shaft (SS) neurons, which show different sensitivities to stress than the more common long shaft (LS) variety. Brains sections were mounted to slides and Golgi stained. SS neurons were drawn using a microscope with camera lucida attachment and quantified using the number of bifurcations and dendritic intersections as metrics for dendritic complexity in the apical and basal areas separately. The hypothesis that SS neurons in the CA3 region of the hippocampus would exhibit apical dendritic simplification in both sexes after UIR was not supported by our findings. In contrast, following UIR, SS apical dendrites were more complex in both sexes compared to controls. Although unexpected, we believe that the UIR paradigm was an effective stressor, robust enough to illicit neuronal adaptations. It appears that the time from the end of UIR to when the brain tissue was collected, or the post-stress recovery period, and/or repeated behavioral testing may have played a role in the observed increased neuronal complexity. Future studies are needed to parse out these potential effects.
ContributorsAcuna, Amanda Marie (Author) / Conrad, Cheryl (Thesis director) / Corbin, William (Committee member) / Olive, M. Foster (Committee member) / School of Life Sciences (Contributor) / Department of Psychology (Contributor) / Barrett, The Honors College (Contributor)
Created2020-12
Description
Prior research suggests that African American adults are more likely than White adults to experience negative alcohol use outcomes such as alcohol use disorder (AUD) despite reporting lower rates of alcohol consumption. Research also shows that African Americans experience higher rates of depression, which can increase risk for alcohol consumption and AUD through drinking to cope. The current study examined the role of depressive symptoms and drinking to cope in alcohol consumption and AUD symptoms among White and Black/African American college students. Participants completed an online survey during the fall (T1) and spring semester (T2) of their first year of college (N = 2,168, 62.8% female, 75.8% White). Path analyses were conducted to examine whether depressive symptoms and drinking to cope mediated the association between race/ethnicity and alcohol consumption and AUD symptoms, as well as whether race/ethnicity moderated the associations between depressive symptoms, drinking to cope, and alcohol use outcomes. Results indicated that White participants had higher levels of depressive symptoms and alcohol consumption than African American participants. Drinking to cope at T1 was also associated with more depressive symptoms at T1, higher levels of alcohol consumption at T2, and higher levels of AUD symptoms at T2. Also, there was an indirect effect of depressive symptoms on AUD symptoms via drinking to cope. Results from multigroup path analyses suggested that depressive symptoms were more strongly associated with drinking to cope for White students than African American students. There were no significant racial/ethnic differences in the associations between depressive symptoms or drinking to cope and alcohol use outcomes. Future research should examine the roles of race, depression, and drinking to cope in alcohol use outcomes for college students.
ContributorsTaylor, Nicole (Author) / Su, Jinni (Thesis director) / Corbin, William (Committee member) / Chassin, Laurie (Committee member) / Sanford School of Social and Family Dynamics (Contributor) / Department of Psychology (Contributor) / Barrett, The Honors College (Contributor)
Created2020-12
Description
It is interesting to reflect that the American legal system has not seriously applied any significant technological advances in many decades. It is fascinating that the same processes used to draft a will or estate plan are virtually the same as they were in the 1960’s. This seems to be a problem that should be concerning in this modern age. We would be hard pressed to observe doctors in the U.S. currently performing medical procedures as they would have in 1960 considering the technological advancements that have taken place in society since then. Many of the processes in the legal system are extremely static and even archaic. It seems to be an opportune time to revolutionize the whole system as advancements continue; but, this revolution must take into account both the positive and negative repercussions that are possible moving forward.
ContributorsWilladson, Conor Calista Carolena (Author) / Koretz, Lora (Thesis director) / Forst, Bradley (Committee member) / Dean, W.P. Carey School of Business (Contributor) / Department of Psychology (Contributor) / Barrett, The Honors College (Contributor)
Created2020-05