Physical Sciences and Mathematics Commons^™

Meningioma Brain Tumor Detection And Classifcation Using Hybrid Cnn Method And Ridgelet Transform, B.V Prakash, A. Rajiv Kanna, N. Santhiyakumari, S. Kumarganesh, D. Siva Sundhara Raja, J. Jasmine Hephzipah, K. Martin Sagayam, Marc Pomplun, Helen Dang

Faculty Works: MCS (1984-2023)

The detection of meningioma tumors is the most crucial task compared with other tumors because of their lower pixel intensity. Modern medical platforms require a fully automated system for meningioma detection. Hence, this study proposes a novel and highly efficient hybrid Convolutional neural network (HCNN) classifier to distinguish meningioma brain images from non-meningioma brain images. The HCNN classification technique consists of the Ridgelet transform, feature computations, classifier module, and segmentation algorithm. Pixel stability during the decomposition process was improved by the Ridgelet transform, and the features were computed from the coefficient of the Ridgelet. These features were classified using the …

Lung_Paynet: A Pyramidal Attention Based Deep Learning Network For Lung Nodule Segmentation, P. Malin Bruntha, S. Immanuel Alex Pandian, K. Martin Sagayam, Shivargha Bandopadhyay, Marc Pomplun, Helen Dang

Faculty Works: MCS (1984-2023)

Accurate and reliable lung nodule segmentation in computed tomography (CT) images is required for early diagnosis of lung cancer. Some of the difficulties in detecting lung nodules include the various types and shapes of lung nodules, lung nodules near other lung structures, and similar visual aspects. This study proposes a new model named Lung_PAYNet, a pyramidal attention-based architecture, for improved lung nodule segmentation in low-dose CT images. In this architecture, the encoder and decoder are designed using an inverted residual block and swish activation function. It also employs a feature pyramid attention network between the encoder and decoder to extract …

Privacy Preserving Attribute-Focused Anonymization Scheme For Healthcare Data Publishing, J. Andrew Onesimu, Karthikeyan J, Jennifer Eunice, Marc Pomplun, Helen Dang

Faculty Works: MCS (1984-2023)

Advancements in Industry 4.0 brought tremendous improvements in the healthcare sector, such as better quality of treatment, enhanced communication, remote monitoring, and reduced cost. Sharing healthcare data with healthcare providers is crucial for harnessing the benefits of such improvements. In general, healthcare data holds sensitive information about individuals. Hence, sharing such data is challenging because of various security and privacy issues. According to privacy regulations and ethical requirements, it is essential to preserve the privacy of patients before sharing data for medical research. State-of-the-art literature on privacy preserving studies either uses cryptographic approaches to protect the privacy or uses anonymizing …

Super-Resolution Reconstruction Of Brain Magnetic Resonance Images Via Lightweight Autoencoder, J. Andrew, T.S.R. Mhatesh, Robin D. Sebastin, K. Martin Sagayam, Jennifer Eunice, Marc Pomplun, Helen Dang

Faculty Works: MCS (1984-2023)

Magnetic Resonance Imaging (MRI) is useful to provide detailed anatomical information such as images of tissues and organs within the body that are vital for quantitative image analysis. However, typically the MR images acquired lacks adequate resolution because of the constraints such as patients’ comfort and long sampling duration. Processing the low resolution MRI may lead to an incorrect diagnosis. Therefore, there is a need for super resolution techniques to obtain high resolution MRI images. Single image super resolution (SR) is one of the popular techniques to enhance image quality. Reconstruction based SR technique is a category of single image …

Automated Sleep Stage Classification In Sleep Apnoea Using Convolutional Neural Networks, G. Naveen Sundar, D. Narmadha, A. Amir Anton Jone, K. Martin Sagayam, Helen Dang, Marc Pomplun

Faculty Works: MCS (1984-2023)

A sleep disorder is a condition that adversely impacts one's ability to sleep well on a regular schedule. It also occurs as a consequence of numerous neurological sicknesses. These types of disorders can be investigated using laboratory-based polysomnography (PSG) signals. The detection of neurological disorders is exact and efficient thanks to the automated monitoring of sleep relegation stages. This automation method publicly presents a flexible deep learning model and machine learning approach utilizing raw electroencephalogram (EEG) signals. The deep learning model is a Deep Convolutional Neural Network (CNN) that analyses invariant time capacities and frequency actualities and collects assessment adaptations. …

Visual-Saliency-Based Abnormality Detection For Mri Brain Images—Alzheimer’S Disease Analysis, A. Diana Andrushia, K. Martin Sagayam, Helen Dang, Marc Pomplun, Lien Quach

Faculty Works: MCS (1984-2023)

In recent years, medical image analysis has played a vital role in detecting diseases in their early stages. Medical images are rapidly becoming available for various applications to solve human problems. Therefore, complex medical features are needed to develop a diagnostic system for physicians to provide better treatment. Traditional methods of abnormality detection suffer from misidentification of abnormal regions in the given data. Visual-saliency detection methods are used to locate abnormalities to improve the accuracy of the proposed work. This study explores the role of a visual saliency map in the classification of Alzheimer’s disease (AD). Bottom-up saliency corresponds to …

A Novel Hybrid K-Means And Gmm Machine Learning Model For Breast Cancer Detection, P. Esther Jebarani, N. Umadevi, Helen Dang, Marc Pomplun

Faculty Works: MCS (1984-2023)

Breast cancer is the second leading cause of death among a large number of women worldwide. It may be challenging for radiologists to diagnose and treat breast cancer. Consequently, primary care improves disease prevention and death. Early detection increases treatment options and saves life, which is the major target of this research. This research indicates the versatility of the methodology by integrating contemporary segmentation approaches with machine learning methods, which are developing areas of research. In the pre-processing process, an adaptive median filter is utilized for noise removal, enhancement of image quality, conservation of edges, and smoothing. This research makes …

Using Microsoft Excel To Teach Simulation Concepts To Business Students, Robert F. Gordon Ph.D.

Faculty Works: MCS (1984-2023)

The application of computers to solving business problems, the area of study known as decision support systems, is an important component in the education of business students today. One major type of decision support system is computer simulation, which is the technique most often used to solve queuing problems in the industry. This paper describes how to teach the concepts of computer simulation, explain the key components of simulation software, and provide hands-on experience to solve these problems by using Microsoft Excel.

Why It Is Difficult To Apply Revenue Management Techniques To The Car Rental Business And What Can Be Done About It, Robert F. Gordon Ph.D.

Faculty Works: MCS (1984-2023)

Revenue management systems are used by airlines, hotels, and cruise lines to manipulate prices and availability of inventory in real-time, in order to increase profit. We discuss the reasons that the revenue management problem is more complex when applied to the car rental business. We then show how to simplify the model formulation and provide the human-computer interaction, organization, and procedures to make the problem tractable for the car rental business.

Rule-Based Run Control And Evaluation For Simulation, Robert F. Gordon Ph.D., Kow C. Chang, Edward A. Macnair

Faculty Works: MCS (1984-2023)

RC 19494 (84719)

Modeling projects are often faced with a large parameter space that has to be explored in order to produce a set of performance measures representing the behavior of the systems under study. In this paper, we describe a software component that provides the analyst with the functionality to specify a design of experiments and execute a search algorithm over the resulting parameter space. The component invokes the associated simulation runs and compares the results to a goal to determine the solution. This component has been implemented as the run control mechanism in the RESearch Queueing Modeling Environment …

An Introduction To The Research Queueing Package For Modeling Computer Systems And Communication Networks, Robert F. Gordon Ph.D., Edward A. Macnair

Faculty Works: MCS (1984-2023)

A queueing network is an important tool for modeling systems where performance is principally affected by contention for resources. Such systems include computer systems, communication networks and manufacturing lines. In order to effectively use queuing networks as performance models, appropriate software is necessary for definition ofthe networks to be solved, for solution ofthe networks and for examination of the performance measures obtained. The RESearch Queueing Package (RESQ) and the RESearch Queueing Package Modeling Environment (RESQME) form a system for constructing, solving and analyzing extended queueing network models. We refer to the class of RESQ networks as "extended" because of characteristics …

Resqme And Stand-Alone Simulation On A Workstation, Robert F. Gordon Ph.D., Paul G. Loewner, G J. Burkland, J-C Chen, Edward A. Macnair

Faculty Works: MCS (1984-2023)

RC 16037 (#71232)

The Research Queueing Package Modeling Environment (RESQME) provides a graphical environment for constructing and solving extended queueing network models ofmanufacturing systems, for plotting graphs of results and for viewdng animations of models. The modeling environment can be run entirely on a workstation or optionally can execute large simulations on a host system using cooperative processing. In this paper we give a brief introduction to RESQME and to the RESQ modeling elements. We demonstrate how to use the package by constructing a simple model of part of a manufacturing line and solve this model to produce charts of …

Management Information Sources And Corporate Intelligence Systems, Robert F. Gordon Ph.D.

Faculty Works: MCS (1984-2023)

In this book the word “intelligence” is used in several different contexts. Intelligence can refer to the process of gathering data; it can refer to the data itself; and it can refer to the application of knowledge to product useful information from the data. We will see in this chapter how the computer can be used in business to further all three aspects of intelligence: capturing the data, storing the data in an accessible form, and adding value to the data by transforming it into useful information for decision making. This chapter is organized according to these three areas of …

Higher Level Modeling In Resqme, Robert F. Gordon Ph.D., Kurtiss J. Gordon

Faculty Works: MCS (1984-2023)

RC 13554 (#60544)

The RESearch Queueing Package Modeling Environment (RESQME) is a graphical workstation environment for iteratively constructing, running and analyzing models of resource contention systems. It is built on top of the RESearch Queueing Package (RESQ) which provides the functionality to evaluate extended queueing networks. In this paper we describe the high-level building component design for RESQME. The modeler is provided with tools to create his own icons and to associate them with submodels. He then uses ilicsc building blocks to construct his model. This capability extends the funtlaiiicnlal building blocks of RESQ and allows the user to create …

Sight - A Tool For Building Multi-Media Structured-Document Interactive Editing And Formatting Applications, Robert F. Gordon Ph.D., George B. Leeman Jr, Christian L. Cesar, Mark A. Martin

Faculty Works: MCS (1984-2023)

SIGHT is a tool for building applications that edit and format multi-media structured documents. The media supported include text, line graphics, handwriting, images and audio. These information media are maintained in a single integrated hierarchical database. The document architecture models documents as trees in which nodes can be shared, i.e., as directed acyclic graphs. For each document there is a logical (or abstract) represention tree and one or more physical (or layout) representation trees. A physical representation is the result of applying the formatter to a logical representation. Both trees are separate but share document content data. The physical representation …

Application Interface Development Environment, Robert F. Gordon Ph.D., Barry E. Willner

Faculty Works: MCS (1984-2023)

RC 11160 (#50246)

The user of interactive systems must learn a different interface for each system he uses. Furthermore the designer of such systems has limited guidelines to create good user interfaces. We describe an application interface development environment, AIDE, in which one can create and select multiple interfaces easily for a given application, and conversely one can create multiple applications with a given interface. This benefits the end-user by providing the possibility of familiar, even identical, interfaces among wide ranges of products, and this helps the designer by supporting Human Factors testing of interfaces. We formulate a model of …

Concepts And Implications Of Interactive Recovery, Robert F. Gordon Ph.D., George B. Leeman Jr, Clayton H. Lewis

Faculty Works: MCS (1984-2023)

RC 10562 (#47293)

When working interactively on the computer, it is valuable to be able to undo a series of commands in order to return to a previous state. We identify contradictions and limitations in the basic concepts of undo. We introduce three types of undo functions with which we examine the characteristics of undo, explain these limitations, and determine the minimum requirements for a recovery facility. Then we discuss the implications of undo for user interfaces and suggest au.xiliary functions to display and simplify the resulting history structure and to view and recover prior states.