Louisiana State University in Shreveport is a branch institution of the Louisiana State University System located in Shreveport, Louisiana. LSUS opened in 1967 as a two-year community college but transitioned into a four-year college five years later in 1972. LSUS enrolled 4,051 students in the Fall 2014 semester and is accredited by the Southern Association of Colleges and Schools. The school's athletic programs, nicknamed the Pilots, are members of the National Association of Intercollegiate Athletics and the Red River Athletic Conference. LSUS offers more than 70 extra-curricular organizations. LSUS operates Red River Radio, a public radio network based in Shreveport. Wikipedia.
Celebi M.E.,Louisiana State University in Shreveport |
Kingravi H.A.,Georgia Institute of Technology |
Vela P.A.,Georgia Institute of Technology
Expert Systems with Applications | Year: 2013
K-means is undoubtedly the most widely used partitional clustering algorithm. Unfortunately, due to its gradient descent nature, this algorithm is highly sensitive to the initial placement of the cluster centers. Numerous initialization methods have been proposed to address this problem. In this paper, we first present an overview of these methods with an emphasis on their computational efficiency. We then compare eight commonly used linear time complexity initialization methods on a large and diverse collection of data sets using various performance criteria. Finally, we analyze the experimental results using non-parametric statistical tests and provide recommendations for practitioners. We demonstrate that popular initialization methods often perform poorly and that there are in fact strong alternatives to these methods. © 2012 Elsevier Ltd. All rights reserved.
Celebi M.E.,Louisiana State University in Shreveport |
Zornberg A.,Half Hollow Hills High School West
IEEE Systems Journal | Year: 2014
Dermoscopy is a noninvasive skin imaging technique, which permits visualization of features of pigmented melanocytic neoplasms that are not discernable by examination with the naked eye. Color information is indispensable for the clinical diagnosis malignant melanoma, the most deadly form of skin cancer. For this reason, most of the currently accepted dermoscopic scoring systems either directly or indirectly incorporate color as a diagnostic criterion. For example, both the asymmetry, border, colors, and dermoscopic (ABCD) rule of dermoscopy and the more recent color, architecture, symmetry, and homogeneity (CASH) algorithm include the number of clinically significant colors in their calculation of malignancy scores. In this paper, we present a machine learning approach to the automated quantification of clinically significant colors in dermoscopy images. Given a true-color dermoscopy image with N colors, we first reduce the number of colors in this image to a small number K, i.e., K N, using the K-means clustering algorithm incorporating a spatial term. The optimal K value for the image is estimated separately using five commonly used cluster validity criteria. We then train a symbolic regression algorithm using the estimates given by these criteria, which are calculated on a set of 617 images. Finally, the mathematical equation given by the regression algorithm is used for two-class (benign versus malignant) classification. The proposed approach yields a sensitivity of 62% and a specificity of 76% on an independent test set of 297 images. © 2014 IEEE.
Munker R.,University of Houston |
Munker R.,Louisiana State University in Shreveport |
Calin G.A.,University of Houston
Clinical Science | Year: 2011
The diagnosis of cancer has undergone major changes in the last 40 years. Once based purely on morphology, diagnosis has come to incorporate immunological, cytogenetic and molecular methods. Many cancers, especially leukaemias, are now defined by molecular markers. Gene expression profiling based on mRNA has led to further refinement of the classification and diagnosis of cancer. More recently, miRNAs (microRNAs), among other small non-coding RNA molecules, have been discovered and found to be major players in cell biology. miRNAs, having both oncogenic and tumour-suppressive functions, are dysregulated in many types of cancer. miRNAs also interfere with metastasis, apoptosis and invasiveness of cancer cells. In the present review, we discuss recent advances in miRNA profiling in human cancer. We discuss both frequent and rare tumour types and give an outlook on future developments. © The Authors Journal compilation. © 2011 Biochemical Society.
Celebi M.E.,Louisiana State University in Shreveport
Image and Vision Computing | Year: 2011
Color quantization is an important operation with many applications in graphics and image processing. Most quantization methods are essentially based on data clustering algorithms. However, despite its popularity as a general purpose clustering algorithm, k-means has not received much respect in the color quantization literature because of its high computational requirements and sensitivity to initialization. In this paper, we investigate the performance of k-means as a color quantizer. We implement fast and exact variants of k-means with several initialization schemes and then compare the resulting quantizers to some of the most popular quantizers in the literature. Experiments on a diverse set of images demonstrate that an efficient implementation of k-means with an appropriate initialization strategy can in fact serve as a very effective color quantizer. © 2010 Elsevier B.V. All rights reserved.
Cielo C.M.,Childrens Hospital of Philadelphia |
Gungor A.,Louisiana State University in Shreveport
Current Problems in Pediatric and Adolescent Health Care | Year: 2016
There are a variety of therapies available for the treatment of pediatric obstructive sleep apnea syndrome (OSAS). In children with enlarged adenoids or tonsils, adenotonsillectomy (AT) is the preferred treatment, but other surgical options include partial tonsillectomy and lingual tonsillectomy. In specific populations, craniofacial or bariatric surgery may be indicated, and tracheostomy should be reserved for cases where there is no other therapeutic option. Positive airway pressure (PAP) is the most effective non-surgical therapy for OSAS as it can be successfully used in even cases of severe OSAS. Nasal steroids and leukotriene receptor antagonists may be used in the treatment of mild or moderate OSAS. Rapid maxillary expansion and dental appliances may be effective in select populations with dental problems. Other non-surgical therapies, such as positional therapy, supplemental oxygen, and weight loss have not been shown to be effective in most pediatric populations.