14878 research outputs found
Sort by
Applying machine learning to track and analyze human movement
No full textTraditional statistical methods comparing movement kinematics in biomechanics involvecalculating discrete variables and comparing between pre-defined groups based on age, sex, pathology, or condition. However, this method generalizes that the movement patterns of individuals within a group are similar and inherently different from those of the group being compared to, which might not be the case. Clustering analysis, which takes an unlabeled set of data and organizes them into homogenous groups, may provide a unique way to distinguish movement patterns within a group of individuals. However, there are many things to consider when clustering any dataset including each clustering algorithm and evaluation measure taking different approaches, leading to different clustering results. This dissertation proposed a method of determining the most appropriate clustering model by comparing k-means and hierarchical clustering (HCA) on different types of biomechanics time-series data using several evaluation measures. Using a majority ranking method, we were able to generate movement profiles of lumbar and pelvis angles during a trunk flexion/extension, head and trunk anterior-posterior (AP) acceleration during steady-state gait, and pelvis AP linear acceleration and vertical (V) angular velocity during a timed up and go (TUG) test. Overall, it was found that most clusters generated on each dataset did not contain a single age or sex demographic. The differences observed between movement profiles were the magnitude and timing of the clustered variable. Clustering analysis was able to separate participants that may have compromised ability to control the head during steady state walking and were slower at turning during the turn-around subphase of the TUG test. Overall, our findings underscore the utility of clustering analysis in elucidating subtle variations in movement behavior in a wide range of different movement evaluations, thereby enhancing our understanding of functional mobility and falls risk assessment in diverse populations
Tin Whiskers Mitigation by Co-electroplating Antimony
No full textElectroplating Sn coatings are used extensively in the electronics industry because of their excellent solderability, ductility, electrical conductivity, and corrosion resistance. However, tin whiskers have been observed to grow spontaneously from the electroplating tin coatings for over 70 years. This filament-type structure can lead to short circuits and device failures by bridging adjacent electronics. Over the last several decades, adding a small amount of lead (Pb) has been the most widely adopted method for mitigating Sn whiskers growth. However, this 70-year-old issue of whisker growth has reemerged due to the ban on the use of Pb from Sn-based plating and solders enforced by the European legislation on Restriction of Hazardous Substances (RoHS). The actual mitigation provided by the co-electroplating lead reamins unclear. Some have attributed the mitigation to the formation of equiaxial grains in a Sn-Pb plating process. Others have attributed it to reducing stress buildup in the film while doping Pb. This study proposes an innovative controllable way to mitigate Sn whiskers growth by electroplating Sn-xSb alloys (x=3 wt.%, 10 w.t%, 15 wt.%). In effect validation, a fixture was designed to apply high wide-plane compressive stress rather than using a hardness indenter to accelerate whisker growth. The results revealed that no whisker growth was observed on any Sn-xSb surface, while pure Sn samples produced whiskers up to 200 um under the same conditions. Adding a minor quantity of Sb could refine the Sn grains, however, the Sn grain size was not further refined with the increase in Sb content. In correspondence, the mitigation effect on whiskers growth was not further improved with the increase in Sb content. As confirmed by a series of EBSD studies, the addition of Sb changed the grain structure from a monolayer columnar structure to a multilayer equiaxed structure, which is favorable in whisker mitigation. The inhibition effect of Sb addition on whisker growth can be ascribed to the assistance of dynamic recrystallization and produces horizontal grain boundaries of Sn grains. This dissertation details the following studies: background of tin whisker problems; development and validation of an effective co-electroplating recipe for tin whisker mitigation using advanced analysis tools; identification of the primary mechanisms of the whisker growth mitigatio
The effects of spiritual leadership on emotional and behavioral regulation in children participating in faith-based recreational team sports: parents’ perspectives
No full textPediatric mental health disorders have risen dramatically in the last five years. Mental health is expressed through emotional and behavioral regulation. There is limited research on the benefits of spiritual coaches’ impact on children’s emotions and behaviors. The purpose of this study was to understand the effects of the spiritual leader coach on emotional and behavioral regulation in children 6 to 12 years-old. The theoretical foundation is from Fry’s Spiritual Leadership Theory. This is a quasi-experimental, pre- and post-test design with a comparison group. This study compared children’s emotional and behavioral regulation in faith-based and non-faith-based recreational team sports. Five programs were examined over 10 to 13 weeks. The intervention was the addition of motivational, spirituality-based discussions provided in the faith-based basketball programs. Parents of both faith-based and non-faith-based players completed a demographic questionnaire, the Strengths and Difficulties Questionnaire, and The Coaching Servant Leadership Scale during the first and last two weeks of the basketball programs. Paired samples t-test analysis compared the pre- and post-season questionnaires for the faith-based and non-faith-based programs. Created change variables represented the difference of pre- and post-season questionnaires. Independent samples t-test analysis compared the change variable between the faith-based and non-faith-based programs. Correlation coefficients were calculated between the Coaching Servant Leadership Scale, the change variables, and demographic data for both programs. The faith-based and non-faith-based programs had a significant, positive impact on children’s emotional and behavioral regulation. All of the coaches in both programs were rated with spiritual leadership qualities. Motivational spiritual discussions were the most impactful in the faith-based older age group. The first two years of participation in the basketball programs, and the older the player was during participation, generated greater improvement in emotional and behavioral regulation. This research can be utilized in pediatric, family, and community health nursing. These fields of nursing encounter children who are struggling with mental health disparities. Faith and non-faith-based sports may provide families of children who are struggling with behavioral or emotional regulation a resource to improve their child’s behavio
41st Annual Women and Gender Studies Film Festival Poster - Landfall - A film by Cecilia Aldarondo
No full textExploring Diversity in Anatomy: Perspectives of High School Students in Saturday Academy Session
No full textTransportation Related Algorithm Design and Application
No full textIn this thesis several algorithms are proposed and developed to solve a variety of transportation related problems. First we considered, a dynamic programming approach to create an exact solver to minimize distance in a vehicle routing problemwith time windows (VRPTW) variant. Several new tests are developed to reduce the size of the state space and ultimately reduce the number of state transitions
Minutes of the Meeting of the University Senate, September 19, 2024
No full text1. Information Items: Graduate Program Modifications; Undergraduate Program Modifications; Combined Graduate and Undergraduate Modifications (none); Strategic Plan Update; Introduction of Assistant Vice President of Advising; Combined UG/Grad Programs Update; Exploring - No Major Program (Fall 2024); MySAIL Updates; Senator Updates, Fall 2024; Senate Committee Co-Chairs, 2024-2025; Provost Updates. | 2. Roll Call | 3. Approval of the Minutes from April 18, 2024 | 4. Unfinished Business (none) | 5. New Business: Updates and changes, Senate Standing Committees | Good and Welfare | 7. Adjourn
Application of Several Machine Learning Algorithms for Multiple Stage Inference Data
No full textHistorically, machine learning techniques have been dependent on utilizing data from two distinct phases to predict and identify particular occurrences. The outcomes of these studies may exhibit either validity or inaccuracy, represented by binary values of one or zero. An alternative term for this is a prognostication of one of two potential results. Several issues are present in this approach, which have the potential to yield inaccurate outcomes. The issues encompassed in this context consist of data imbalance, overfitting, and error propagation. This study aims to employ and use a multiple stage outcome approach to enhance accuracy and optimize the performance of outcomes. In this step of our research, we will be implementing the Multiclass Classification One-vs.-All methodology to analyze the data collected from various stages of the experiment's conclusion. In the subsequent phase, it is necessary to engage in the utilization or investigation of a diverse range of potential supervised models, which are trained through the application of machine learning algorithms. Subsequently, the determination of the model that exhibits a superior level of accuracy will be made by designating it as the victor. In our study, we employ and evaluate five distinct machine learning algorithms, namely Support Vector Machines (SVM), Logistic Regression (LR), Random Forest (RF), Gradient Tree Boosting (GTB), and Extremely Randomized Trees (ERF). These algorithms are used within our machine learning framework to analyze multi-stage data and ascertain the technique that exhibits the highest accuracy in predicting outcome stages. This multi-stage conclusion would effectively narrow down the problem or difficulties at hand, reduce the potential for errors, and enhance the ability to accurately predict and diagnose medical diseases or cyber security threats. A Python-based model was developed to execute the proposed methodology. The utilized notion employs a binary format, which has been substantiated by empirical evidence and offers two potential outcomes. Upon the completion of our research, it was determined that the Logistic Regression and Support Vector Machine algorithms exhibited better performance compared to the other algorithms when a multiple stage outcome was employed. The results were assessed in terms of accuracy, precision, recall, and the F measur