Digital Commons Network^™

Application Of Support Vector Machine In Predicting The Market's Monthly Trend Direction, Ali Alali

Dissertations and Theses

In this work, we investigate different techniques to predict the monthly trend direction of the S&P 500 market index. The techniques use a machine learning classifier with technical and macroeconomic indicators as input features. The Support Vector Machine (SVM) classifier was explored in-depth in order to optimize the performance using four different kernels; Linear, Radial Basis Function (RBF), Polynomial, and Quadratic. A result found was the performance of the classifier can be optimized by reducing the number of macroeconomic features needed by 30% using Sequential Feature Selection. Further performance enhancement was achieved by optimizing the RBF kernel and SVM parameters …

Exploiting Contextual Information For Prosodic Event Detection Using Auto-Context, Junhong Zhao, Wei-Qiang Zhang, Hua Yang, Michael T. Johnson, Jia Liu, Shanhong Xia

Electrical and Computer Engineering Faculty Research and Publications

Prosody and prosodic boundaries carry significant information regarding linguistics and paralinguistics and are important aspects of speech. In the field of prosodic event detection, many local acoustic features have been investigated; however, contextual information has not yet been thoroughly exploited. The most difficult aspect of this lies in learning the long-distance contextual dependencies effectively and efficiently. To address this problem, we introduce the use of an algorithm called auto-context. In this algorithm, a classifier is first trained based on a set of local acoustic features, after which the generated probabilities are used along with the local features as contextual information …

On Evaluation Model Of Circular Economy For Iron And Steel Enterprise Based On Support Vector Machines With Heuristic Algorithm For Tuning Hyper-Parameters, Zhifang Zhou, Xiaohong Chen, Xu Xiao

Applied Mathematics & Information Sciences

With more severe resource scarcity and environmental problems, the evaluation of circular economy in microcosmic level has become the focus of the academic world. Based on the concept of circular economy, this paper not only structures the evaluation index system of circular economy for iron and steel enterprises, builds the evaluation model of circular economy for iron and steel enterprises based on Support Vector Machine (SVM) with Radial Basis Function (RBF) kernel, but achieves the optimization of kernel function parameters, penalty factors and insensitive parameters based on a heuristic algorithm for tuning hyper-parameters. Furthermore, the evaluation model is tested for …

Smoothness Without Smoothing: Why Gaussian Naive Bayes Is Not Naive For Multi-Subject Searchlight Studies, Rajeev D.S Raizada, Yune-Sang Lee

Dartmouth Scholarship

Spatial smoothness is helpful when averaging fMRI signals across multiple subjects, as it allows different subjects' corresponding brain areas to be pooled together even if they are slightly misaligned. However, smoothing is usually not applied when performing multivoxel pattern-based analyses (MVPA), as it runs the risk of blurring away the information that fine-grained spatial patterns contain. It would therefore be desirable, if possible, to carry out pattern-based analyses which take unsmoothed data as their input but which produce smooth images as output. We show here that the Gaussian Naive Bayes (GNB) classifier does precisely this, when it is used in …

Use Of Support Vector Machines And Fabry-Perot Interferometry To Classify States Of A Laser, John Motley Mckinnon

Master's Theses and Doctoral Dissertations

This thesis develops an algorithm that can determine if a laser is functioning correctly over a long period of time. A Fourier fit is created to model fringe profiles from a Fabry-Perot interferometer, and singular value decomposition is used to reduce noise in each signal. Levenberg-Marquardt gradient descent is performed to correctly locate the center of each image and to optimize each fit with respect to the spatial frequency. The Fourier fit is used to extract important information from each image to be used for separating the image types from one another. Principal component analysis is used to reduce the …

Efindsite: Improved Prediction Of Ligand Binding Sites In Protein Models Using Meta-Threading, Machine Learning And Auxiliary Ligands, Michal Brylinski, Wei P. Feinstein

Faculty Publications

Molecular structures and functions of the majority of proteins across different species are yet to be identified. Much needed functional annotation of these gene products often benefits from the knowledge of protein-ligand interactions. Towards this goal, we developed eFindSite, an improved version of FINDSITE, designed to more efficiently identify ligand binding sites and residues using only weakly homologous templates. It employs a collection of effective algorithms, including highly sensitive meta-threading approaches, improved clustering techniques, advanced machine learning methods and reliable confidence estimation systems. Depending on the quality of target protein structures, eFindSite outperforms geometric pocket detection algorithms by 15-40 % …

Geometric Approach To Support Vector Machines Learning For Large Datasets, Robert Strack

Theses and Dissertations

The dissertation introduces Sphere Support Vector Machines (SphereSVM) and Minimal Norm Support Vector Machines (MNSVM) as the new fast classification algorithms that use geometrical properties of the underlying classification problems to efficiently obtain models describing training data. SphereSVM is based on combining minimal enclosing ball approach, state of the art nearest point problem solvers and probabilistic techniques. The blending of the three speeds up the training phase of SVMs significantly and reaches similar (i.e., practically the same) accuracy as the other classification models over several big and large real data sets within the strict validation frame of a double (nested) …

A Survey Of Systems For Predicting Stock Market Movements, Combining Market Indicators And Machine Learning Classifiers, Jeffrey Allan Caley

Dissertations and Theses

In this work, we propose and investigate a series of methods to predict stock market movements. These methods use stock market technical and macroeconomic indicators as inputs into different machine learning classifiers. The objective is to survey existing domain knowledge, and combine multiple techniques into one method to predict daily market movements for stocks. Approaches using nearest neighbor classification, support vector machine classification, K-means classification, principal component analysis and genetic algorithms for feature reduction and redefining the classification rule were explored. Ten stocks, 9 companies and 1 index, were used to evaluate each iteration of the trading method. The classification …

A Novel Algorithm For Validating Peptide Identification From A Shotgun Proteomics Search Engine, Ling Jian, Xinnan Niu, Zhonghang Xia, Parimal Samir, Chiranthani Sumanasekera, Zheng Mu, Jennifer L. Jennings, Kristen L. Hoek, Tara Allos, Leigh M. Howard, Kathryn M. Edwards, P. Anthony Weil, Andrew J. Link

Chemistry Faculty Research

Liquid chromatography coupled with tandem mass spectrometry (LC–MS/MS) has revolutionized the proteomics analysis of complexes, cells, and tissues. In a typical proteomic analysis, the tandem mass spectra from a LC–MS/MS experiment are assigned to a peptide by a search engine that compares the experimental MS/MS peptide data to theoretical peptide sequences in a protein database. The peptide spectra matches are then used to infer a list of identified proteins in the original sample. However, the search engines often fail to distinguish between correct and incorrect peptides assignments. In this study, we designed and implemented a novel algorithm called De-Noise to …

Towards Personalized Medicine Using Systems Biology And Machine Learning, Calin Voichita

Wayne State University Dissertations

The rate of acquiring biological data has greatly surpassed our ability to interpret it. At the same time, we have started to understand that evolution of many diseases such as cancer, are the results of the interplay between the disease itself and the immune system of the host. It is now well accepted that cancer is not a single disease, but a “complex collection of distinct genetic diseases united by common hallmarks”. Understanding the differences between such disease subtypes is key not only in providing adequate treatments for known subtypes but also identifying new ones. These unforeseen disease subtypes are …

Hybrid Spr Algorithm To Select Predictive Genes For Effectual Cancer Classification, Aruna Sundaram, Nandakishore Lellapalli Venkata, Rajagopalan Sarukai Parthasarathy

Turkish Journal of Electrical Engineering and Computer Sciences

Designing an automated system for classifying DNA microarray data is an extremely challenging problem because of its high dimension and low amount of sample data. In this paper, a hybrid statistical pattern recognition algorithm is proposed to reduce the dimensionality and select the predictive genes for the classification of cancer. Colon cancer gene expression profiles having 62 samples of 2000 genes were used for the experiment. A gene subset of 6 highly informative genes was selected by the algorithm, which provided a classification accuracy of 93.5%.

A Combined Protective Scheme For Fault Classification And Identification Of Faulty Section In Series Compensated Transmission Lines, Resul Çöteli̇

Turkish Journal of Electrical Engineering and Computer Sciences

The fault detection process is very difficult in transmission lines with a fixed series capacitor because of the nonlinear behavior of protection device and series-parallel resonance. This paper proposes a new method based on S-transform (ST) and support vector machines (SVMs) for fault classification and identification of a faulty section in a transmission line with a fixed series capacitor placed at the middle of the line. In the proposed method, the fault detection process is carried out by using distinctive features of 3-line signals (line voltages and currents) and zero sequence current. The relevant features of these signals are obtained …

Detection Of Microcalcification Clusters In Digitized X-Ray Mammograms Using Unsharp Masking And Image Statistics, Peli̇n Kuş, İrfan Karagöz

Turkish Journal of Electrical Engineering and Computer Sciences

A fully automated method for detecting microcalcification (MC) clusters in regions of interest (ROIs) extracted from digitized X-ray mammograms is proposed. In the first stage, an unsharp masking is used to perform the contrast enhancement of the MCs. In the second stage, the ROIs are decomposed into a 2-level contourlet representation and the reconstruction is obtained by eliminating the low-frequency subband in the second level. In the third stage, statistical textural features are extracted from the ROIs and they are classified using support vector machines. To test the performance of the method, 57 ROIs selected from the Mammographic Image Analysis …

Seqnls: Nuclear Localization Signal Prediction Based On Frequent Pattern Mining And Linear Motif Scoring, J.-R. Lin, Jianjun Hu

Faculty Publications

Nuclear localization signals (NLSs) are stretches of residues in proteins mediating their importing into the nucleus. NLSs are known to have diverse patterns, of which only a limited number are covered by currently known NLS motifs. Here we propose a sequential pattern mining algorithm SeqNLS to effectively identify potential NLS patterns without being constrained by the limitation of current knowledge of NLSs. The extracted frequent sequential patterns are used to predict NLS candidates which are then filtered by a linear motif-scoring scheme based on predicted sequence disorder and by the relatively local conservation (IRLC) based masking.

The experiment results on …

A Video-Based Eye Pupil Detection System For Diagnosing Bipolar Disorder, Gökay Akinci, Edi̇z Polat, Orhan Murat Koçak

Turkish Journal of Electrical Engineering and Computer Sciences

Eye pupil detection systems have become increasingly popular in image processing and computer vision applications in medical systems. In this study, a video-based eye pupil detection system is developed for diagnosing bipolar disorder. Bipolar disorder is a condition in which people experience changes in cognitive processes and abilities, including reduced attentional and executive capabilities and impaired memory. In order to detect these abnormal behaviors, a number of neuropsychological tests are also designed to measure attentional and executive abilities. The system acquires the position and radius information of eye pupils in video sequences using an active contour snake model with an …

Interpreting Individual Classifications Of Hierarchical Networks, Will Landecker, Michael David Thomure, Luis M.A. Bettencourt, Melanie Mitchell, Garrett T. Kenyon, Steven P. Brumby

Computer Science Faculty Publications and Presentations

Hierarchical networks are known to achieve high classification accuracy on difficult machine-learning tasks. For many applications, a clear explanation of why the data was classified a certain way is just as important as the classification itself. However, the complexity of hierarchical networks makes them ill-suited for existing explanation methods. We propose a new method, contribution propagation, that gives per-instance explanations of a trained network's classifications. We give theoretical foundations for the proposed method, and evaluate its correctness empirically. Finally, we use the resulting explanations to reveal unexpected behavior of networks that achieve high accuracy on visual object-recognition tasks using well-known …