Numerical Analysis and Scientific Computing Commons^™

Analyzing Sports Training Data With Machine Learning Techniques, Rehana Mahfuz, Zeinab Mourad, Aly El Gamal

The Summer Undergraduate Research Fellowship (SURF) Symposium

In the sports industry, there has not been enough effort in analyzing the personalized monitoring data of athletes collected during training sessions. This research is an attempt to find meaningful patterns in the Purdue Women’s Soccer training data that could help the coach design more efficient training sessions. We are specifically interested in studying this problem as an unsupervised learning problem. Our initial attempt is to cluster the players as well as drills into groups using k-means, c-means and spectral clustering algorithms, combined with feature transformation and reduction steps. These basic algorithms serve as a benchmark to measure performance improvements …

Hpcnmf: A High-Performance Toolbox For Non-Negative Matrix Factorization, Karthik Devarajan, Guoli Wang

COBRA Preprint Series

Non-negative matrix factorization (NMF) is a widely used machine learning algorithm for dimension reduction of large-scale data. It has found successful applications in a variety of fields such as computational biology, neuroscience, natural language processing, information retrieval, image processing and speech recognition. In bioinformatics, for example, it has been used to extract patterns and profiles from genomic and text-mining data as well as in protein sequence and structure analysis. While the scientific performance of NMF is very promising in dealing with high dimensional data sets and complex data structures, its computational cost is high and sometimes could be critical for …

Prediction Of Laser Ablation In Brain: Sensitivity, Calibration, And Validation, Samuel J. Fahrenholtz

Dissertations and Theses (Open Access)

The surgical planning of MR-guided laser induced thermal therapy (MRgLITT) stands to benefit from predictive computational modeling. The dearth of physical model parameter data leads to modeling uncertainty. This work implements a well-accepted framework with three key steps for model-building: model-parameter sensitivity analysis, model calibration, and model validation.

The sensitivity study is via generalized polynomial chaos (gPC) paired with a transient finite element (FEM) model. Uniform probability distribution functions (PDFs) capture the plausible range of values suggested by the literature for five model parameters. The five PDFs are input separately into the FEM model to gain a probabilistic sensitivity response …

Improving Patient Flow With Data-Driven Patient Prioritization Method In The Emergency Department, Kar Way Tan, Sean Shao Wei Lam

Research Collection School Of Computing and Information Systems

We aim to improve the length-of-stay (LOS) of patients in the Emergency Department (ED) ambulatory care area. We propose the use of real-time computerized physician order entry data and ED patient flow management system to estimate the consultation time of patients re-entering the queue to consult a doctor again after receiving treatment or results of tests. The estimation allows decision-makers to apply dynamic prioritization strategies that help the ED to identify patients who can complete their ED treatment process quickly, freeing up resources in the ED and lowering overall LOS.

Bridging The Vocabulary Gap Between Health Seekers And Healthcare Knowledge, Liqiang Nie, Yiliang Zhao, Akbari Mohammad, Jialie Shen, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

The vocabulary gap between health seekers and providers has hindered the cross-system operability and the interuser reusability. To bridge this gap, this paper presents a novel scheme to code the medical records by jointly utilizing local mining and global learning approaches, which are tightly linked and mutually reinforced. Local mining attempts to code the individual medical record by independently extracting the medical concepts from the medical record itself and then mapping them to authenticated terminologies. A corpus-aware terminology vocabulary is naturally constructed as a byproduct, which is used as the terminology space for global learning. Local mining approach, however, may …

Automated Prediction Of Glasgow Outcome Scale For Traumatic Brain Injury, Bolan Su, Thien Anh Dinh, A. K. Ambastha, Tianxia Gong, Tomi Silander, Shijian Lu, C. C. Tchoyoson Lim, Boon Chuan Pang, Cheng Kiang Lee, Tze-Yun Leong, Chew Lim Tan

Research Collection School Of Computing and Information Systems

Clinical features found in brain CT scan images are widely used in traumatic brain injury (TBI) as indicators for Glasgow Outcome Scale (GOS) prediction. However, due to the lack of automated methods to measure and quantify the CT scan image features, the computerized prediction of GOS in TBI has not been well studied. This paper introduces an automated GOS prediction system for traumatic brain CT images. Different from most existing systems that perform the prognosis based on pre-processed data, our system directly works on brain CT scan images based on the image features. Our system can also be extended to …

Renal Cryoablation: Investigation Of Periprocedural Visualization To Ols And Treatment Response Quantification, Katherine L. Dextraze

Dissertations and Theses (Open Access)

Cryoablation for small renal tumors has demonstrated sufficient clinical efficacy over the past decade as a non-surgical nephron-sparing approach for treating renal masses for patients who are not surgical candidates. Minimally invasive percutaneous cryoablations have been performed with image guidance from CT, ultrasound, and MRI. During the MRI-guided cryoablation procedure, the interventional radiologist visually compares the iceball size on monitoring images with respect to the original tumor on separate planning images. The comparisons made during the monitoring step are time consuming, inefficient and sometimes lack the precision needed for decision making, requiring the radiologist to make further changes later in …

Design And Optimization Of Four-Dimensional Cone-Beam Computed To Mography In Image-Guided Radiation Therapy, Moiz Ahmad

Dissertations and Theses (Open Access)

The influence of respiratory motion on patient anatomy poses a challenge to accurate radiation therapy, especially in lung cancer treatment. Modern radiation therapy planning uses models of tumor respiratory motion to account for target motion in targeting. The tumor motion model can be verified on a per-treatment session basis with four-dimensional cone-beam computed tomography (4D-CBCT), which acquires an image set of the dynamic target throughout the respiratory cycle during the therapy session. 4D-CBCT is undersampled if the scan time is too short. However, short scan time is desirable in clinical practice to reduce patient setup time. This dissertation presents the …

Comparative Study Of Various Data Collection Software Used For Seat-Belt Observation Surveys, Atul Sancheti, Puneet Lakhanpal, Sergio Contreras, Pushkin Kachroo, Masha Wilson

College of Engineering: Graduate Celebration Programs

Every year, Click It or Ticket (CIOT) mobilization is held in U.S. which aims at increasing seat-belt usage awareness among the people. Data collection for assessing current seat-belt usage rates and campaign design for influencing mass audience are the two most important components of the mobilization. This paper presents a comparative study of various data collections software used for seat-belt observational surveys. The comparison is based on the speed and accuracy of the data collected from different software at the same locations and at the same time of the day.

Housing With Support Marketing Study Tool, Gary M. Travis

All Graduate Theses, Dissertations, and Other Capstone Projects

Housing for persons with serious mental illness (SMI) that is permanent, affordable, and supportive is very limited because the availability of these resources is inadequate and subject to significant demand by persons that are disabled or on a limited income. The limited access to housing for persons with SMI is contributing to homelessness and Minnesota has seen a steady rise since 1994 in the rate and number of people that are homeless and coping with mental illness (Wilder Research, 2010a). While some of the impact of disability, homelessness, and limited affordable housing access is known, what remains uncertain is a …

Toward Effective Concept Representation In Decision Support To Improve Patient Safety, Tze-Yun Leong

Research Collection School Of Computing and Information Systems

Patient safety is an emerging, major health care discipline with significance accentuated in the influential Institute of Medicine (IOM) reports in the United States “To Err is Human” and “Crossing the Quality Chasm”. These reports highlighted the danger and prevalence of medical errors and preventable adverse events, explained the three main sources of system-related, human factors-related and cognitive-related errors, and recommended the use of information and decision support technologies to help alleviate the problem. A number of studies and reports from all over the world with similar findings have since followed, culminating in the 55th World Health Assembly Resolution on …

An Optical Machine Vision System For Applications In Cytopathology, Jonathan Blackledge, Dmitry Dubovitskiy

Articles

This paper discusses a new approach to the processes of object detection, recognition and classification in a digital image focusing on problem in Cytopathology. A unique self learning procedure is presented in order to incorporate expert knowledge. The classification method is based on the application of a set of features which includes fractal parameters such as the Lacunarity and Fourier dimension. Thus, the approach includes the characterisation of an object in terms of its fractal properties and texture characteristics. The principal issues associated with object recognition are presented which include the basic model and segmentation algorithms. The self-learning procedure for …

Brain Tumor Progression Assessment Using Multiple Mri Volumes, Yufei Shen

Electrical & Computer Engineering Theses & Dissertations

Predicting and assessing tumor progression is important in brain tumor treatment. We attempt to use machine learning techniques to achieve consistency in assessing brain tumor progression. This thesis presents a prediction method of brain tumor progression by exploring a large MR database, which contains two patients ' complete records covering all their visits in the past two years. All ten MRI series, namely, apparent diffusion coefficient (ADC) , diffusion tensor imaging (DTI) , fractional anisotropy (FA), fluid attenuated inversion recovery (FLAIR), max eigenvalue (MAX), mid eigenvalue (MID), min eigenvalue (MIN) , post-contrast T₁-weighted, T₁- weighted, and …

Text Mining In Radiology Reports, Tianxia Gong, Chew Lim Tan, Tze-Yun Leong, Cheng Kiang Lee, Boon Chuan Pang, C. C. Tchoyoson Lim, Qi Tian, Suisheng Tang, Zhuo Zhang

Research Collection School Of Computing and Information Systems

Medical text mining has gained increasing interest in recent years. Radiology reports contain rich information describing radiologist's observations on the patient's medical conditions in the associated medical images. However as most reports are in free text format, the valuable information contained in those reports cannot be easily accessed and used, unless proper text mining has been applied. In this paper we propose a text mining system to extract and use the information in radiology reports. The system consists of three main modules: a medical finding extractor a report and image retriever and a text-assisted image feature extractor In evaluation, the …

Learning Causal Models For Noisy Biological Data Mining: An Application To Ovarian Cancer Detection, Ghim-Eng Yap, Ah-Hwee Tan, Hwee Hwa Pang

Research Collection School Of Computing and Information Systems

Undetected errors in the expression measurements from highthroughput DNA microarrays and protein spectroscopy could seriously affect the diagnostic reliability in disease detection. In addition to a high resilience against such errors, diagnostic models need to be more comprehensible so that a deeper understanding of the causal interactions among biological entities like genes and proteins may be possible. In this paper, we introduce a robust knowledge discovery approach that addresses these challenges. First, the causal interactions among the genes and proteins in the noisy expression data are discovered automatically through Bayesian network learning. Then, the diagnosis of a disease based on …

Interdependency Of Pharmacokinetic Parameters: A Chicken-And-Egg Problem? Not!, Reza Mehvar

Pharmacy Faculty Articles and Research

Pharmacokinetic (PK) software packages are widely used by scientists in different disciplines to estimate PK parameters. However, their use without a clear understanding of physiological parameters affecting the PK parameters and how different PK parameters are related to each other may result in erroneous interpretation of data. Often, mathematical relationships used for the estimation of PK parameters obscure the true physiological relationships among these parameters, prompting a discussion of which parameter came first and giving the appearance of the-chicken-and-the-egg dilemma. In this article, the author attempts to show how different PK parameters are related to physiological parameters and each other …

Incremental Genetic K-Means Algorithm And Its Application In Gene Expression Data Analysis, Yi Lu, Shiyong Lu, Farshad Fotouhi, Youping Deng, Susan J. Brown

Wayne State University Associated BioMed Central Scholarship

Abstract

Background

In recent years, clustering algorithms have been effectively applied in molecular biology for gene expression data analysis. With the help of clustering algorithms such as K-means, hierarchical clustering, SOM, etc, genes are partitioned into groups based on the similarity between their expression profiles. In this way, functionally related genes are identified. As the amount of laboratory data in molecular biology grows exponentially each year due to advanced technologies such as Microarray, new efficient and effective methods for clustering must be developed to process this growing amount of biological data.

Results

In this paper, we propose a new clustering …

Mining Of Correlated Rules In Genome Sequences, L. Lin, L. Wong, Tze-Yun Leong, P. S. Lai

Research Collection School Of Computing and Information Systems

With the huge amount of data collected by scientists in the molecular genetics community in recent years, there exists a need to develop some novel algorithms based on existing data mining techniques to discover useful information from genome databases. We propose an algorithm that integrates the statistical method, association rule mining, and classification rule mining in the discovery of allelic combinations of genes that are peculiar to certain phenotypes of diseased patients.

A New Soft Tissue Analysis : To Establish Facial Esthetic Norms In Young Adult Females, Anne Béress

Loma Linda University Electronic Theses, Dissertations & Projects

Two hundred and fifty-five articles, books, and masters theses were reviewed for the most frequently applied soft tissue measurements in the literature in order to develop a new soft tissue analysis computer program that includes established soft tissue measurements and the newly developed globe analysis. A meta analysis of 20 normal occlusion studies, was performed to obtain mean values and standard deviations to form a large sample size. Inclusion criteria for articles in the meta analysis were normal occlusion, no orthodontic treatment, pleasing faces, statement on age, race, and lip position of the population. For the lateral view, angular and …

Assessment Of The Accuracy Of Three Methods Of Computerized Growth Prediction Of The Soft Tissue Profile, In Untreated Individuals, Pat Diciccio

Loma Linda University Electronic Theses, Dissertations & Projects

This study was performed to determine the accuracy and reliability of the long range growth predictions for profile structures by three computer software systems (QuickCeph™ for Apple Macintosh™ systems. Rocky Mountain Data Systems™ for IBM™ mainframe systems, and Facial Print™ for IBM™ personal computers), on untreated individuals. The total sample consisted of 90 Caucasian children from the Burlington Growth Centre. These were subdivided into groups of 15 children in each of mesiofacial, dolichofacial, and brachyfacial growth types for both males and females, with Angle class I occlusions, normal overbite, and normal overjet. Points measured consisted of 14 skeletal and soft …

Cephalometrics For The Oral Surgeon In The Diagnosis Of Facial Deformities, Frederick J. Mantz

Loma Linda University Electronic Theses, Dissertations & Projects

Surgical orthodontics presents a challenge to the oral surgeon. By the nature of the oral surgeon's training and discipline he should be the one best qualified to treat the surgical aspect of the surgical orthodontic case. The establishment of a proper diagnosis and means of communication between the oral surgeon and orthodontist are essential in achieving a good final result for the surgically treated case. Fortunately, a scientific method of diagnosis is available that can provide both specialties with a common language. Computerized cephalometric analysis can provide the diagnosis and link of communication for the discussion of goals and treatment. …

A Computerized Study Of Midpalatal Suture Expansion, Clelan G. Ehrler

Loma Linda University Electronic Theses, Dissertations & Projects

An investigation has been conducted to consider the effects of midpalatal suture expansion on the cranial-facial complex. Nine patients were treated that had constricted maxillae. Data was obtained from frontal and lateral headplate radiographs which were taken at four intervals during treatment. The Rocky Mountain Data Systems diagnosis was utilized to interpret the radiographic data.

The data from the nine cases were averaged to obtain a composit [sic] change at each of the four times.

Examination of the lateral headplate data revealed that no permanent significant alteration occurred to the positions of the mandible or maxilla in a vertical or …