Computer Sciences Commons^™

The Algorithmic Composition Of Classical Music Through Data Mining, Tom Donald Richmond, Imad Rahal

All College Thesis Program, 2016-2019

The desire to teach a computer how to algorithmically compose music has been a topic in the world of computer science since the 1950’s, with roots of computer-less algorithmic composition dating back to Mozart himself. One limitation of algorithmically composing music has been the difficulty of eliminating the human intervention required to achieve a musically homogeneous composition. We attempt to remedy this issue by teaching a computer how the rules of composition differ between the six distinct eras of classical music by having it examine a dataset of musical scores, rather than explicitly telling the computer the formal rules of …

Text Classification Of Installation Support Contract Topic Models For Category Management, William C. Sevier

Theses and Dissertations

Air Force Installation Contracting Agency manages nearly 18 percent of total Air Force spend, equating to approximately 57 billion dollars. To improve strategic sourcing, the organization is beginning to categorize installation-support spend and assign accountable portfolio managers to respective spend categories. A critical task in this new strategic environment includes the appropriate categorization of Air Force contracts into newly created, manageable spend categories. It has been recognized that current composite categories have the opportunity to be further distinguished into sub-categories leveraging text analytics on the contract descriptions. Furthermore, upon establishing newly constructed categories, future contracts must be classified into these …

Opportunity Identification For New Product Planning: Ontological Semantic Patent Classification, Farshad Madani

Dissertations and Theses

Intelligence tools have been developed and applied widely in many different areas in engineering, business and management. Many commercialized tools for business intelligence are available in the market. However, no practically useful tools for technology intelligence are available at this time, and very little academic research in technology intelligence methods has been conducted to date.

Patent databases are the most important data source for technology intelligence tools, but patents inherently contain unstructured data. Consequently, extracting text data from patent databases, converting that data to meaningful information and generating useful knowledge from this information become complex tasks. These tasks are currently …

Unified Locally Linear Classifiers With Diversity-Promoting Anchor Points, Chenghao Liu, Teng Zhang, Peilin Zhao, Jianling Sun, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

Locally Linear Support Vector Machine (LLSVM) has been actively used in classification tasks due to its capability of classifying nonlinear patterns. However, existing LLSVM suffers from two drawbacks: (1) a particular and appropriate regularization for LLSVM has not yet been addressed; (2) it usually adopts a three-stage learning scheme composed of learning anchor points by clustering, learning local coding coordinates by a predefined coding scheme, and finally learning for training classifiers. We argue that this decoupled approaches oversimplifies the original optimization problem, resulting in a large deviation due to the disparate purpose of each step. To address the first issue, …

Clicking Into Mortgage Arrears: A Study Into Arrears Prediction With Clickstream Data, Gavin O'Brien

Dissertations

This research project investigates the predictive capability of clickstream data when used for the purpose of mortgage arrears prediction. With an ever growing number of people switching to digital channels to handle their daily banking requirements, there is a wealth of ever increasing online usage data, otherwise known as clickstream data. If leveraged correctly, this clickstream data can be a powerful data source for organisations as it provides detailed information about how their customers are interacting with their digital channels. Much of the current literature associated with clickstream data relates to organisations employing it within their customer relationship management mechanisms …

Detecting Fake News In Social Media Networks, Monther Aldwairi, Ali Alwahedi

All Works

© 2018 The Authors. Published by Elsevier Ltd. Fake news and hoaxes have been there since before the advent of the Internet. The widely accepted definition of Internet fake news is: fictitious articles deliberately fabricated to deceive readers'. Social media and news outlets publish fake news to increase readership or as part of psychological warfare. Ingeneral, the goal is profiting through clickbaits. Clickbaits lure users and entice curiosity with flashy headlines or designs to click links to increase advertisements revenues. This exposition analyzes the prevalence of fake news in light of the advances in communication made possible by the emergence …

Deep Learning-Based Framework For Autism Functional Mri Image Classification, Xin Yang, Saman Sarraf, Ning Zhang

Journal of the Arkansas Academy of Science

The purpose of this paper is to introduce deep learning-based framework LeNet-5 architecture and implement the experiments for functional MRI image classification of Autism spectrum disorder. We implement our experiments under the NVIDIA deep learning GPU Training Systems (DIGITS). By using the Convolutional Neural Network (CNN) LeNet-5 architecture, we successfully classified functional MRI image of Autism spectrum disorder from normal controls. The results show that we obtained satisfactory results for both sensitivity and specificity.

Multiclass Classification Of Risk Factors For Cervical Cancer Using Artificial Neural Networks, Abdullah Al Mamun

College of Graduate Studies: Theses & Dissertations

World Health Organization statistics show that cervical cancer is the fourth most frequent cancer in women with an estimated 530,000 new cases in 2012. Cervical cancer diagnosis typically involves liquid-based cytology (LBC) followed by a pathologist review. The accuracy of decision is therefore highly influenced by the expert’s skills and experience, resulting in relatively high false positive and/or false negative rates. Moreover, given the fact that the data being analyzed is highly dimensional, same reviewer’s decision is inherently affected by inconsistencies in interpreting the data. In this study, we use an Artificial Neural Network based model that aims to considerably …

Effect Of Intuitionistic Fuzzy Normalization In Microarray Gene Selection, Prema Ramasamy, Premalatha Kandhasamy

Turkish Journal of Electrical Engineering and Computer Sciences

Analysis of gene expression data is essential in microarray gene expression in order to retrieve the required information. Gene expression data generally contain a large number of genes but a small number of samples. The complicated relations among the different genes make analysis more difficult, and removing irrelevant genes improves the quality of results. This paper presents two fuzzy preprocessing techniques, using a fuzzy set (FS) and intuitionistic fuzzy set (IFS), to normalize datasets. In the feature selection part, four statistical methods were used. Using three publicly available gene expression datasets, the fuzzy normalization techniques were compared with two standard …

Topological Feature Extraction Of Nonlinear Signals And Trajectories And Its Application In Eeg Signals Classification, Saleh Lashkari, Ali Sheikhani, Mohammad Reza Hashemi Golpayegani, Ali Moghimi, Hamid Reza Kobravi

Turkish Journal of Electrical Engineering and Computer Sciences

This study introduces seven topological features that characterize attractor dynamic of nonlinear and chaotic trajectories in a phase space. These features quantify volume, occupied space, nonuniformity, and curvature of trajectory. The features are evaluated as initial point invariant measures by a practical approach, which means that a feature is only sensitive to dynamic changes. The Lorenz and Rossler system trajectories are employed in this evaluation. Moreover, the proposed features are used in a real world application, i.e. epileptic seizure electroencephalogram signal classification. As the result shows, these features are efficient in this task in comparison with others studies that used …

Machine Learning Methods For Septic Shock Prediction, Aiman A. Darwiche

CCAC Theses and Dissertations

Sepsis is an organ dysfunction life-threatening disease that is caused by a dysregulated body response to infection. Sepsis is difficult to detect at an early stage, and when not detected early, is difficult to treat and results in high mortality rates. Developing improved methods for identifying patients in high risk of suffering septic shock has been the focus of much research in recent years. Building on this body of literature, this dissertation develops an improved method for septic shock prediction. Using the data from the MMIC-III database, an ensemble classifier is trained to identify high-risk patients. A robust prediction model …

The Impact Of Cost On Feature Selection For Classifiers, Richard Clyde Mccrae

CCAC Theses and Dissertations

Supervised machine learning models are increasingly being used for medical diagnosis. The diagnostic problem is formulated as a binary classification task in which trained classifiers make predictions based on a set of input features. In diagnosis, these features are typically procedures or tests with associated costs. The cost of applying a trained classifier for diagnosis may be estimated as the total cost of obtaining values for the features that serve as inputs for the classifier. Obtaining classifiers based on a low cost set of input features with acceptable classification accuracy is of interest to practitioners and researchers. What makes this …

Generating Classification Rules From Training Samples, Arun D. Kulkarni

Computer Science Faculty Publications and Presentations

In this paper, we describe an algorithm to extract classification rules from training samples using fuzzy membership functions. The algorithm includes steps for generating classification rules, eliminating duplicate and conflicting rules, and ranking extracted rules. We have developed software to implement the algorithm using MATLAB scripts. As an illustration, we have used the algorithm to classify pixels in two multispectral images representing areas in New Orleans and Alaska. For each scene, we randomly selected 10 per cent of the samples from our training set data for generating an optimized rule set and used the remaining 90 per cent of samples …

Deep Convolutional Neural Networks Enable Discrimination Of Heterogeneous Digital Pathology Images, Pegah Khosravi, Ehsan Kazemi, Marcin Imielinski, Olivier Elemento, Iman Hajirasouliha

Publications and Research

Pathological evaluation of tumor tissue is pivotal for diagnosis in cancer patients and automated image analysis approaches have great potential to increase precision of diagnosis and help reduce human error.

In this study, we utilize several computational methods based on convolutional neural networks (CNN) and build a stand-alone pipeline to effectively classify different histopathology images across different types of cancer.

In particular, we demonstrate the utility of our pipeline to discriminate between two subtypes of lung cancer, four biomarkers of bladder cancer, and five biomarkers of breast cancer. In addition, we apply our pipeline to discriminate among four immunohistochemistry …

Multiclass Classification Using Support Vector Machines, Duleep Prasanna W. Rathgamage Don

College of Graduate Studies: Theses & Dissertations

In this thesis, we discuss different SVM methods for multiclass classification and introduce the Divide and Conquer Support Vector Machine (DCSVM) algorithm which relies on data sparsity in high dimensional space and performs a smart partitioning of the whole training data set into disjoint subsets that are easily separable. A single prediction performed between two partitions eliminates one or more classes in a single partition, leaving only a reduced number of candidate classes for subsequent steps. The algorithm continues recursively, reducing the number of classes at each step until a final binary decision is made between the last two classes …

Fuzziness-Based Active Learning Framework To Enhance Hyperspectral Image Classification Performance For Discriminative And Generative Classifiers, Muhammad Ahmad, Stanislav Protasov, Adil Mehmood Khan, Rasheed Hussain, Asad Masood Khattak, Wajahat Ali Khan

All Works

© 2018 Ahmad et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Hyperspectral image classification with a limited number of training samples without loss of accuracy is desirable, as collecting such data is often expensive and time-consuming. However, classifiers trained with limited samples usually end up with a large generalization error. To overcome the said problem, we propose a fuzziness-based active learning framework (FALF), in which we implement the idea of selecting optimal …

Last Level Cache Partitioning Via Multiverse Thread Classification, Burak Sezi̇n Ovant, İsa Ahmet Güney, Muhammed Emi̇n Savaş, Gürhan Küçük

Turkish Journal of Electrical Engineering and Computer Sciences

Last level caches (LLCs) are part of the last line of defense against the famous memory wall problem. Today, almost all processors utilize a LLC for the same reason. This study extends our previous work, which proposed a cache-partitioning mechanism using thread classification. Here, we propose three enhancements to the existing system: 1) an adaptive traffic threshold mechanism for more portable classification hardware, 2) a new method for classifying way-hungry threads, and finally, 3) a thorough comparison of two design alternatives. Compared to the original way- partitioning mechanism, we show that the proposed mechanism's performance improved by around 6%, on …

Modified Stacking Ensemble Approach To Detect Network Intrusion, Necati̇ Demi̇r, Gökhan Dalkiliç

Turkish Journal of Electrical Engineering and Computer Sciences

Detecting intrusions in a network traffic has remained an issue for researchers over the years. Advances in the area of machine learning provide opportunities to researchers to detect network intrusion without using a signature database. We studied and analyzed the performance of a stacking technique, which is an ensemble method that is used to combine different classification models to create a better classifier, on the KDD'99 dataset. In this study, the stacking method is improved by modifying the model generation and selection techniques and by using different classifications algorithms as a combiner method. Model generation is performed using subsets of …

Classification Of Surface Electromyogram Signals Based On Directed Acyclic Graphs And Support Vector Machines, Xinhui Hu, Jiangming Kan, Wenbin Li

Turkish Journal of Electrical Engineering and Computer Sciences

This paper presents a novel classification approach for surface electromyogram (sEMG) signals. The proposed classification approach involves two steps: (1) feature extraction from an sEMG, in which a 7-dimensional feature vector is extracted from 27 types of features of the sEMG by linear discriminant analysis (LDA), and (2) a novel classifier, DAGSVMerr, based on a directed acyclic graph (DAG) and support vector machine (SVM), in which a separability measure function based on erroneous recognition rates (ERRs) is defined to determine the initial operation list. The proposed approach takes advantage of the feedback idea to improve the performance of the classification. …

Feature Selection Algorithm For No-Reference Image Quality Assessment Using Natural Scene Statistics, Imran Fareed Nizami, Muhammad Majid, Khawar Khurshid

Turkish Journal of Electrical Engineering and Computer Sciences

Images play an essential part in our daily lives and the performance of various imaging applications is dependent on the user?s quality of experience. No-reference image quality assessment (NR-IQA) has gained importance to assess the perceived quality, without using any prior information of the nondistorted version of the image. Different NR-IQA techniques that utilize natural scene statistics classify the distortion type based on groups of features and then these features are used for estimating the image quality score. However, every type of distortion has a different impact on certain sets of features. In this paper, a new feature selection algorithm …

Enlarging Multiword Expression Dataset By Co-Training, Senem Kumova Meti̇n

Turkish Journal of Electrical Engineering and Computer Sciences

In multiword expressions (MWEs), multiple words unite to build a new unit in language. When MWE identification is accepted as a binary classification task, one of the most important factors in performance is to train the classifier with enough number of labelled samples. Since manual labelling is a time-consuming task, the performances of MWE recognition studies are limited with the size of the training sets. In this study, we propose the comparison-based and common-decision co-training approaches in order to enlarge the MWE dataset. In the experiments, the performances of the proposed approaches were compared to those of the standard co-training …

Improved Method Of Heuristic Classification Of Vowels From An Acoustic Signal, Josef Krocil, Zdenek Machacek, Jiri Koziorek, Radek Martinek, Jan Nedoma, Marcel Fajkus

Turkish Journal of Electrical Engineering and Computer Sciences

This paper describes research in the field of the improved methodology of the classification of vowels /a, a:/, /$\varepsilon$, $\varepsilon$:/, /ı, i:/, /o, o:/, and /u, u:/ (vowel symbols according to IPA, i.e. International Phonetic Alphabet). The aim is to develop an improved method enabling the automatic allocation of vowel symbols to the corresponding time segments of acoustic recordings of an undisturbed speech signal. The combined classification method is based on finding frequencies of the first two local maxims (formants) in a smoothed linear predictive amplitude spectrum (LPC, linear predictive coding) and zero-crossing values of each speech active voiced short-term …

Artificial Immune System Based Wastewater Parameter Estimation, Cengi̇z Sertkaya, Ni̇lüfer Yurtay

Turkish Journal of Electrical Engineering and Computer Sciences

The basis of a wastewater treatment system is to achieve the desired characteristics of the wastewater treatment process. An estimation of the obtained wastewater treatment characteristics provides the information needed to set up the current process steps, and it is important to have an optimum treatment. In this study, an artificial immune system (AIS) structure is developed to estimate important wastewater output parameters such as pH, DBO, DQO, and SS for the first time. The proposed AIS models are based on the clonal selection principle, and the dataset is provided from the University of California Irvine (UCI) Machine Learning Library. …

Automated Species Classification Methods For Passive Acoustic Monitoring Of Beaked Whales, John Lebien

LSU New Orleans Theses and Dissertations

The Littoral Acoustic Demonstration Center has collected passive acoustic monitoring data in the northern Gulf of Mexico since 2001. Recordings were made in 2007 near the Deepwater Horizon oil spill that provide a baseline for an extensive study of regional marine mammal populations in response to the disaster. Animal density estimates can be derived from detections of echolocation signals in the acoustic data. Beaked whales are of particular interest as they remain one of the least understood groups of marine mammals, and relatively few abundance estimates exist. Efficient methods for classifying detected echolocation transients are essential for mining long-term passive …

Process Models Discovery And Traces Classification: A Fuzzy-Bpmn Mining Approach., Kingsley Okoye Dr, Usman Naeem Dr, Syed Islam Dr, Abdel-Rahman H. Tawil Dr, Elyes Lamine Dr

Journal of International Technology and Information Management

The discovery of useful or worthwhile process models must be performed with due regards to the transformation that needs to be achieved. The blend of the data representations (i.e data mining) and process modelling methods, often allied to the field of Process Mining (PM), has proven to be effective in the process analysis of the event logs readily available in many organisations information systems. Moreover, the Process Discovery has been lately seen as the most important and most visible intellectual challenge related to the process mining. The method involves automatic construction of process models from event logs about any domain …

Automatic Loop-Invariant Generation And Refinement Through Selective Sampling, Jiaying Li, Jun Sun, Li Li, Quang Loc Le, Shang-Wei Lin

Research Collection School Of Computing and Information Systems

Automatic loop-invariant generation is important in program analysis and verification. In this paper, we propose to generate loop-invariants automatically through learning and verification. Given a Hoare triple of a program containing a loop, we start with randomly testing the program, collect program states at run-time and categorize them based on whether they satisfy the invariant to be discovered. Next, classification techniques are employed to generate a candidate loop-invariant automatically. Afterwards, we refine the candidate through selective sampling so as to overcome the lack of sufficient test cases. Only after a candidate invariant cannot be improved further through selective sampling, we …

Scalable Online Kernel Learning, Jing Lu

Dissertations and Theses Collection (Open Access)

One critical deficiency of traditional online kernel learning methods is their increasing and unbounded number of support vectors (SV’s), making them inefficient and non-scalable for large-scale applications. Recent studies on budget online learning have attempted to overcome this shortcoming by bounding the number of SV’s. Despite being extensively studied, budget algorithms usually suffer from several drawbacks.
First of all, although existing algorithms attempt to bound the number of SV’s at each iteration, most of them fail to bound the number of SV’s for the final averaged classifier, which is commonly used for online-to-batch conversion. To solve this problem, we propose …

Methods For Real-Time Prediction Of The Mode Of Travel Using Smartphone-Based Gps And Accelerometer Data, Bryan D. Martin, Vittorio Addona, Julian Wolfson, Gediminas Adomavicius, Yingling Fan

Faculty Publications

We propose and compare combinations of several methods for classifying transportation activity data from smartphone GPS and accelerometer sensors. We have two main objectives. First, we aim to classify our data as accurately as possible. Second, we aim to reduce the dimensionality of the data as much as possible in order to reduce the computational burden of the classification. We combine dimension reduction and classification algorithms and compare them with a metric that balances accuracy and dimensionality. In doing so, we develop a classification algorithm that accurately classifies five different modes of transportation (i.e., walking, biking, car, bus and rail) …

Effect Of Label Noise On The Machine-Learned Classification Of Earthquake Damage, Jared Frank, Umaa Rebbapragada, James Bialas, Thomas Oommen, Timothy C. Havens

Michigan Tech Publications, Part 1

Automated classification of earthquake damage in remotely-sensed imagery using machine learning techniques depends on training data, or data examples that are labeled correctly by a human expert as containing damage or not. Mislabeled training data are a major source of classifier error due to the use of imprecise digital labeling tools and crowdsourced volunteers who are not adequately trained on or invested in the task. The spatial nature of remote sensing classification leads to the consistent mislabeling of classes that occur in close proximity to rubble, which is a major byproduct of earthquake damage in urban areas. In this study, …

Constructing Interactive Visual Classification, Clustering And Dimension Reduction Models For N-D Data, Boris Kovalerchuk, Dmytro Dovhalets

Computer Science Faculty Scholarship

The exploration of multidimensional datasets of all possible sizes and dimensions is a long-standing challenge in knowledge discovery, machine learning, and visualization. While multiple efficient visualization methods for n-D data analysis exist, the loss of information, occlusion, and clutter continue to be a challenge. This paper proposes and explores a new interactive method for visual discovery of n-D relations for supervised learning. The method includes automatic, interactive, and combined algorithms for discovering linear relations, dimension reduction, and generalization for non-linear relations. This method is a special category of reversible General Line Coordinates (GLC). It produces graphs in 2-D that represent …