Engineering Commons^™

Machine Learning In Support Of Electric Distribution Asset Failure Prediction, Robert D. Flamenbaum, Thomas Pompo, Christopher Havenstein, Jade Thiemsuwan

SMU Data Science Review

In this paper, we present novel approaches to predicting as- set failure in the electric distribution system. Failures in overhead power lines and their associated equipment in particular, pose significant finan- cial and environmental threats to electric utilities. Electric device failure furthermore poses a burden on customers and can pose serious risk to life and livelihood. Working with asset data acquired from an electric utility in Southern California, and incorporating environmental and geospatial data from around the region, we applied a Random Forest methodology to predict which overhead distribution lines are most vulnerable to fail- ure. Our results provide evidence …

Comparative Analysis Of Feature Selection Methods To Identify Biomarkers In A Stroke-Related Dataset, Thomas Clifford, Justin Bruce, Tayo Obafemi-Ajayi, John Matta

Electrical and Computer Engineering Faculty Research & Creative Works

This paper applies machine learning feature selection techniques to the REGARDS stroke-related dataset to identify health-related biomarkers. A data-driven methodological framework is presented to evaluate multiple feature selection methods. In applying the framework, three classifiers are chosen in conjunction with two wrappers, and their performance with diverse classification targets such as Current Smoker, Current Alcohol Use, and Deceased is evaluated. The performance across logistic regression, random forest and naïve Bayes classifier methods, as quantified by the ROC Area Under Curve metric and selected features, was similar. However, significant differences were observed in running time. Performance of the selected features was …

Direct-To-Patient Survey For Diagnosis Of Benign Paroxysmal Positional Vertigo, Heidi Richburg, Richard J. Povinelli, David Friedland

Electrical and Computer Engineering Faculty Research and Publications

Given the high incidence of dizziness and its frequent misdiagnosis, we aim to create a clinical support system to classify the presence or absence of benign paroxysmal positional vertigo with high accuracy and specificity. This paper describes a three-phase study currently underway for classification of benign paroxysmal positional vertigo, which includes diagnosis by a specialist in a clinical setting. Patient background information is collected by a survey on an Android tablet and machine learning techniques are applied for classification. Decision trees and wrappers are employed for their ability to provide information about the question set. One goal of the study …

Computer-Aided Classification Of Impulse Oscillometric Measures Of Respiratory Small Airways Function In Children, Nancy Selene Avila

Open Access Theses & Dissertations

Computer-aided classification of respiratory small airways dysfunction is not an easy task. There is a need to develop more robust classifiers, specifically for children as the classification studies performed to date have the following limitations: 1) they include features derived from tests that are not suitable for children and 2) they cannot distinguish between mild and severe small airway dysfunction.

This Dissertation describes the classification algorithms with high discriminative capacity to distinguish different levels of respiratory small airways function in children (Asthma, Small Airways Impairment, Possible Small Airways Impairment, and Normal lung function). This ability came from innovative feature selection, …

Classification Of Generic System Dynamics Model Outputs Via Supervised Time Series Pattern Discovery, Mert Edali, Mustafa Gökçe Baydoğan, Gönenç Yücel

Turkish Journal of Electrical Engineering and Computer Sciences

System dynamics (SD) is a simulation-based approach for analyzing feedback-rich systems. An ideal SD modeling cycle requires evaluating the qualitative pattern characteristics of a large set of time series model output for testing, validation, scenario analysis, and policy analysis purposes. This traditionally requires expert judgement, which limits the extent of experimentation due to time constraints. Although time series recognition approaches can help to automate such an evaluation, utilization of them has been limited to a hidden Markov model classifier, namely the Indirect Structure Testing Software (ISTS) algorithm. Despite being used within several automated model-analysis tools, ISTS has several shortcomings. In …

Polyhedral Conic Kernel-Like Functions For Svms, Gürkan Öztürk, Emre Çi̇men

Turkish Journal of Electrical Engineering and Computer Sciences

In this study, we propose a new approach that can be used as a kernel-like function for support vector machines (SVMs) in order to get nonlinear classification surfaces. We combined polyhedral conic functions (PCFs) with the SVM method. To get nonlinear classification surfaces, kernel functions are used with SVMs. However, the parameter selection of the kernel function affects the classification accuracy. Generally, in order to get successful classifiers which can predict unknown data accurately, best parameters are explored with the grid search method which is computationally expensive. We solved this problem with the proposed method. There is no need to …

A Novel Hybrid Teaching-Learning-Based Optimization Algorithm For The Classification Of Data By Using Extreme Learning Machines, Ender Sevi̇nç, Tansel Dökeroğlu

Turkish Journal of Electrical Engineering and Computer Sciences

Data classification is the process of organizing data by relevant categories. In this way, the data can be understood and used more efficiently by scientists. Numerous studies have been proposed in the literature for the problem of data classification. However, with recently introduced metaheuristics, it has continued to be riveting to revisit this classical problem and investigate the efficiency of new techniques. Teaching-learning-based optimization (TLBO) is a recent metaheuristic that has been reported to be very effective for combinatorial optimization problems. In this study, we propose a novel hybrid TLBO algorithm with extreme learning machines (ELM) for the solution of …

Classification Of The Likelihood Of Colon Cancer With Machine Learning Techniques Using Ftir Signals Obtained From Plasma, Suat Toraman, Mustafa Gi̇rgi̇n, Bi̇lal Üstündağ, İbrahi̇m Türkoğlu

Turkish Journal of Electrical Engineering and Computer Sciences

Colon cancer is one of the major causes of human mortality worldwide and the same can be said for Turkey. Various methods are used for the determination of cancer. One of these methods is Fourier transform infrared (FTIR) spectroscopy, which has the ability to reveal biochemical changes. The most common features used to distinguish patients with cancer and healthy subjects are peak densities, peak height ratios, and peak area ratios. The greatest challenge of studies conducted to distinguish cancer patients from healthy subjects using FTIR signals is that the signals of cancer patients and healthy subjects are similar. In the …

Extracting Accent Information From Urdu Speech For Forensic Speaker Recognition, Falak Tahir, Sajid Saleem, Ayaz Ahmad

Turkish Journal of Electrical Engineering and Computer Sciences

This paper presents a new method for extraction of accent information from Urdu speech signals. Accent is used in speaker recognition system especially in forensic cases and plays a vital role in discriminating people of different groups, communities and origins due to their different speaking styles. The proposed method is based on Gaussian mixture model-universal background model (GMM-UBM), mel-frequency cepstral coefficients (MFCC), and a data augmentation (DA) process. The DA process appends features to base MFCC features and improves the accent extraction and forensic speaker recognition performances of GMM-UBM. Experiments are performed on an Urdu forensic speaker corpus. The experimental …

An Improved Tree Model Based On Ensemble Feature Selection For Classification, Chandralekha M, Shenbagavadivu N

Turkish Journal of Electrical Engineering and Computer Sciences

Researchers train and build specific models to classify the presence and absence of a disease and the accuracy of such classification models is continuously improved. The process of building a model and training depends on the medical data utilized. Various machine learning techniques and tools are used to handle different data with respect to disease types and their clinical conditions. Classification is the most widely used technique to classify disease and the accuracy of the classifier largely depends on the attributes. The choice of the attribute largely affects the diagnosis and performance of the classifier. Due to growing large volumes …

An Automated Snick Detection And Classification Scheme As A Cricket Decision Review System, Aftab Khan, Syed Qadir Hussain, Muhammad Waleed, Ashfaq Khan, Umair Khan

Turkish Journal of Electrical Engineering and Computer Sciences

Umpire decisions can greatly affect the outcome of a cricket game. When there is doubt about the umpire?s call for a decision, a decision review system (DRS) may be brought into play by a batsman or bowler to validate the decision. Recently, the latest technologies, including Hotspot, Hawk-eye, and Snickometer, have been employed when there is doubt among the on-field umpire, batsman, or bowlers. This research is a step forward in gaging the true class of a snick generated from the contact of the cricket ball with either (i) the bat, (ii) gloves, (iii) pad, or (iv) a combination of …

Word Sense Disambiguation Using Semantic Kernels With Class-Based Term Values, Ayşe Berna Altinel, Murat Can Gani̇z, Bi̇lge Şi̇pal, Eren Can Erkaya, Onur Can Yücedağ, Muhammed Ali̇ Doğan

Turkish Journal of Electrical Engineering and Computer Sciences

In this study, we propose several semantic kernels for word sense disambiguation (WSD). Our approaches adapt the intuition that class-based term values help in resolving ambiguity of polysemous words in WSD. We evaluate our proposed approaches with experiments, utilizing various sizes of training sets of disambiguated corpora (SensEval). With these experiments we try to answer the following questions: 1.) Do our semantic kernel formulations yield higher classification performance than traditional linear kernel?, 2.) Under which conditions a kernel design performs better than others?, 3.) Does the addition of class labels into standard term-document matrix improve the classification accuracy?, 4.) Is …

A Depth-Based Nearest Neighbor Algorithmfor High-Dimensional Data Classification, Sandhya Harikumar, Akhil A.S, Ramachandra Kaimal

Turkish Journal of Electrical Engineering and Computer Sciences

Nearest neighbor algorithms like k-nearest neighbors (kNN) are fundamental supervised learning techniques to classify a query instance based on class labels of its neighbors. However, quite often, huge volumes of datasets are not fully labeled and the unknown probability distribution of the instances may be uneven. Moreover, kNN suffers from challenges like curse of dimensionality, setting the optimal number of neighbors, and scalability for high-dimensional data. To overcome these challenges, we propose an improvised approach of classification via depth representation of subspace clusters formed from high-dimensional data. We offer a consistent and principled approach to dynamically choose the nearest neighbors …

Heart Attack Mortality Prediction: An Application Of Machine Learning Methods, Issam Salman

Turkish Journal of Electrical Engineering and Computer Sciences

The heart is an important organ in the human body, and acute myocardial infarction (AMI) is the leading cause of death in most countries. Researchers are doing a lot of data analysis work to assist doctors in predicting the heart problem. An analysis of the data related to different health problems and its functions can help in predicting the wellness of this organ with a degree of certainty. Our research reported in this paper consists of two main parts. In the first part of the paper, we compare different predictive models of hospital mortality for patients with AMI. All results …

Deep Neural Network Learning-Based Classifier Design For Big-Data Analytics, Krishnan Raghavan

Doctoral Dissertations

"In this digital age, big-data sets are commonly found in the field of healthcare, manufacturing and others where sustainable analysis is necessary to create useful information. Big-data sets are often characterized by high-dimensionality and massive sample size. High dimensionality refers to the presence of unwanted dimensions in the data where challenges such as noise, spurious correlation and incidental endogeneity are observed. Massive sample size, on the other hand, introduces the problem of heterogeneity because complex and unstructured data types must analyzed. To mitigate the impact of these challenges while considering the application of classification, a two step analysis approach is …

Multi-Column Neural Networks And Sparse Coding Novel Techniques In Machine Learning, Ammar O. Hoori

Theses and Dissertations

Accurate and fast machine learning (ML) algorithms are highly vital in artificial intelligence (AI) applications. In complex dataset problems, traditional ML methods such as radial basis function neural network (RBFN), sparse coding (SC) using dictionary learning, and particle swarm optimization (PSO) provide trivial results, large structure, slow training, and/or slow testing. This dissertation introduces four novel ML techniques: the multi-column RBFN network (MCRN), the projected dictionary learning algorithm (PDL) and the multi-column adaptive and non-adaptive particle swarm optimization techniques (MC-APSO and MC-PSO). These novel techniques provide efficient alternatives for traditional ML techniques. Compared to traditional ML techniques, the novel ML …