Digital Commons Network^™

Obtaining Speech Assets For Judgement Analysis On Low-Pass Filtered Emotional Speech, John Snel, Charlie Cullen

Conference papers

Investigating the emotional content in speech from acoustic characteristics requires separating the semantic con- tent from the acoustic channel. For natural emotional speech, a widely used method to separate the two channels is the use of cue masking. Our objective is to investigate the use of cue masking in non-acted emotional speech by analyzing the extent to which filtering impacts the perception of emotional content of the modified speech material. However, obtaining a corpus of emotional speech can be quite difficult whereby verifying the emotional content is an issue thoroughly discussed. Currently, speech research is showing a tendency toward constructing …

Concept-Driven Multi-Modality Fusion For Video Search, Xiao-Yong Wei, Yu-Gang Jiang, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

As it is true for human perception that we gather information from different sources in natural and multi-modality forms, learning from multi-modalities has become an effective scheme for various information retrieval problems. In this paper, we propose a novel multi-modality fusion approach for video search, where the search modalities are derived from a diverse set of knowledge sources, such as text transcript from speech recognition, low-level visual features from video frames, and high-level semantic visual concepts from supervised learning. Since the effectiveness of each search modality greatly depends on specific user queries, prompt determination of the importance of a modality …

Network Traffic Data Analysis, Harish Kapri

LSU Master's Theses

The desire to conceptualize network traffic in a prevailing communication network is a facet for many types of network research studies. In this research, real traffic traces collected over trans-Pacific backbone links (the MAWI repository, providing publicly available anonymized traces) are analyzed to study the underlying traffic patterns. All data analysis and visualization is carried out using Matlab (Matlab is a trademark of The Mathworks, Inc.). At packet level, we first measure parameters such as distribution of packet lengths, distribution of protocol types, and then fit following analytical models. Next, the concept of flow is introduced and flow based analysis …

An Investigation On Fast And Frugal Model For New Project Screening, Antonie J. Jetter, Fatima M. Albar

Engineering and Technology Management Faculty Publications and Presentations

Research in psychology is increasingly interested in decision-makers' use of heuristics or rules of thumb because they have accuracies close to more complex decision rules and seem particularly useful in difficult decision-making contexts when uncertainty is high and speed is of the essence. One particularly difficult decision setting is the fuzzy front-end of new product development because a large number of product ideas need to be screened to identify the few that should be developed further. This process is currently poorly supported through decision tools and mainly occurs on the basis of managerial “gut-feel”. This study explores managerial “gut-feel” by …

Design Of Multi Agent Based Crowd Injury Model, Emin Kugu

Electrical & Computer Engineering Theses & Dissertations

A major concern of many government agencies is to predict and control the behavior of crowds in different situations. Many times such gatherings are legal, legitimate, and peaceful. But there are times when they can turn violent, run out of control, result in material damages and even casualties. It then becomes the duty of governments to bring them under control using a variety of techniques, including non-lethal and lethal weapons, if necessary.

In order to aid decision makers on the course of action in crowd control, there are modeling and simulation tools that can provide guidelines by giving programmed rules …

Universal Approximation With Uninorm-Based Fuzzy Neural Networks, Andre Lemos, Vladik Kreinovich, Walmir Caminhas, Fernando Gomide

Departmental Technical Reports (CS)

Fuzzy neural networks are hybrid models capable to approximate functions with high precision and to generate transparent models, enabling the extraction of valuable information from the resulting topology. In this paper we will show that the recently proposed fuzzy neural network based on weighted uninorms aggregations uniformly approximates any real functions on any compact set. We will describe the network topology and inference mechanism and show that the universal approximation property of this network is valid for a given choice of operators.

Automobile Exhaust Gas Detection Based On Fuzzy Temperature Compensation System, Zhiyong Wang, Hao Ding, Fufei Hao, Zhaoxia Wang, Zhen Sun, Shujin Li

Research Collection School Of Computing and Information Systems

A temperature compensation scheme of detecting automobile exhaust gas based on fuzzy logic inference is presented in this paper. The principles of the infrared automobile exhaust gas analyzer and the influence of the environmental temperature on analyzer are discussed. A fuzzy inference system is designed to improve the measurement accuracy of the measurement equipment by reducing the measurement errors caused by environmental temperature. The case studies demonstrate the effectiveness of the proposed method. The fuzzy compensation scheme is promising as demonstrated by the simulation results in this paper.

Transportation Network Resiliency: A Fuzzy Systems Approach, Nayel Urena Serulle

All Graduate Theses and Dissertations, Spring 1920 to Summer 2023

Every day the dependence on transportation grows as local, regional, national, and international independence increases. Resilient transportation systems are needed to secure the highest possible level of service during disruptive events, including natural and man-made disasters. Because of limited resources, decision makers need guidance on how, when, and where to invest to improve resiliency of their networks. The research objective is to develop a method to assess and quantify resiliency, at pre-event conditions, using a fuzzy inference approach. This research expands previous work, refining key variable definitions, adjusting model interactions, and increasing transparency between metrics. This thesis presents the method …

Study Of Stemming Algorithms, Savitha Kodimala

UNLV Theses, Dissertations, Professional Papers, and Capstones

Automated stemming is the process of reducing words to their roots. The stemmed words are typically used to overcome the mismatch problems associated with text searching.

In this thesis, we report on the various methods developed for stemming. In particular, we show the effectiveness of n-gram stemming methods on a collection of documents.

Web-Based Intelligent Computational Argumentation Based Conflict Resolution In Air Traffic Management, Xiaoqing Frank Liu, Ravi Santosh Arvapally, Hojong Baik, Rubal Wanchoo

Computer Science Faculty Research & Creative Works

Collaborative decision making (CDM) is a process of reaching consensus on a potential solution of an issue through the evaluation of the different possible alternatives. the web-Based intelligent computational argumentation system allows concerned stakeholders to post their arguments on different alternatives, assign weights and priorities to the arguments and reach the most favorable alternative using fuzzy intelligent techniques over the Internet. Exchange of information among the stakeholders improves the collaboration and drives towards the collective intelligence. in this paper, we show how our tool facilitates resolution of conflicts in air traffic management. It could enhance the Ground Delay Program (GDP) …

Comparison Of Classical Analytic Hierarchy Process (Ahp) Approach And Fuzzy Ahp Approach In Multiple-Criteria Decision Making For Commercial Vehicle Information Systems And Networks (Cvisn) Project, Liyuan Zhang

Department of Industrial and Management Systems Engineering: Dissertations, Theses, and Student Research

Radio Frequency Identification (RFID) has emerged as an important technology with many possible applications in a wide variety of fields. It is said that RFID can perform well in transportation system. Nebraska Department of Motor Vehicles (NEDMV) is using this technique to perform an analysis on utilizing RFID license plates to assist with Commercial Vehicle Information Systems and Networks (CVISN) program with the cooperation of many other stakeholders. Previous House of Quality (HOQ) analysis evaluates stakeholders’ needs and provides the pairwise comparison values of six important technical requirements for each stakeholder. Based on these, this research aims to seek for …

Intelligent Coordinated Control Of A Wind Farm And Distributed Smartparks, Pinaki Mitra, Ganesh K. Venayagamoorthy

Electrical and Computer Engineering Faculty Research & Creative Works

Energy storage is generally recommended in presence of an intermittent source like wind farm for a better control over the power generation from the wind turbine with the variation of the wind speed. In this paper, the potential of plug-in electric vehicle parking lot (SmartPark) as an energy storage in a power system with a large wind farm has been investigated. Also, a fuzzy logic based coordination controller of the wind farm and the distributed SmartParks has been proposed in this paper. The fuzzy controller uses the total state-of-charge of the SmartParks and the difference between instantaneous demand and the …

Electroencephalogram Artifact Removal Using A Wavelet Neural Network, Hoang-Anh T. Nguyen

Electrical & Computer Engineering Theses & Dissertations

A wavelet neural network (WNN) technique rs developed for electroencephalogram (EEG) artifact removal without electrooculographic (EOG) recordings. The algorithm combines the universal approximation characteristics of neural networks and the time/frequency property of wavelet, where the neural network was trained on a simulated dataset with known ground truths. The contribution of this thesis is two-fold. First, many EEG artifact removal algorithms, including regression based methods, require reference EOG signals, which are not always available. To remove EEG ai1ifacts, a WNN tries to learn the characteristics of the artifacts first and does not need reference EOG signals once trained. Second, WNNs are …

Signal Detection Framework Using Semantic Text Mining Techniques, Sithu D. Sudarsan

Theses and Dissertations

Signal detection is a challenging task for regulatory and intelligence agencies. Subject matter experts in those agencies analyze documents, generally containing narrative text in a time bound manner for signals by identification, evaluation and confirmation, leading to follow-up action e.g., recalling a defective product or public advisory for potential flu outbreak. Technical challenges to achieve effective signal detection include mining unstructured data, increasing document collections, and presence of multi-domain vocabulary. Lack of annotation and multi-domain vocabulary makes traditional semantic web mining ineffective. Use of heuristics to enhance bag-of-words type text mining to semantic text mining is a novel idea attempted …

Visualization To Support The Discovery Of Prosodic Contours Related To Turn-Taking, Nigel Ward, Joshua L. Mccartney

Departmental Technical Reports (CS)

Some meaningful prosodic patterns can be usefully represented with pitch contours, however the development of such descriptions is a labor-intensive process. To assist in the discovery of contours, visualization tools may be helpful. Edlund et al. (2009) presented the idea of superimposing hundreds of pitch curves from a corpus as a way to see the overall patterns. In this paper we refine and extend this method and illustrate its utility in the discovery of a prosodic cue to back-channels in Chinese. We also discuss issues in relating a contour-based description to one in terms of a conjunction of features, and …

Studies In The Use Of Time Into Utterance As A Predictive Feature For Language Modeling, Nigel Ward, Alejandro Vega

Departmental Technical Reports (CS)

In (Ward and Vega 2008) we examined how how word probabilities vary with time into utterance, and proposed a method for using this information to improve a language model. In this report we examine some ancillary issues in the modeling and exploitation of these regularities.

Pattern Recognition For Fault Detection, Classification, And Localization In Electrical Power Systems, Qais Hashim Alsafasfeh

Dissertations

The longer it takes to identify and repair a fault, the more damage may result in the electrical power system, especially in periods of peak loads, which could lead to the collapse of the system, causing the power outage to extend for a longer period and larger parts of the electrical network. Reducing the outage time and immediate restoration of service can be achieved if the fault type and location are determined in a timely and precise manner.

An integrated algorithm that is based on generating unique signatures from the electric current signal to detect, classify, and localize a fault …

Fuzzy Logic Approach To Stability Control, Jeffery Anderson

All Theses

Traditional Electronic Stability Control (ESC) for automobiles is usually accomplished through the use of estimated vehicle dynamics from simplified models. Starting with the conventional two degree-of-freedom vehicle model, one can estimate the vehicle states from the driver steering input. From this estimate, vehicle sideslip angle can be found and this is generally used with a threshold value to initiate a control action. The input/output relationship of the model depends heavily on the accuracy of the parameters used and various means to correct model inaccuracies. Specifically, these models depend on the tire cornering stiffness which is prone to change with age …

Remote Usability Testing - A New Approach Facilitated By Virtual Worlds, Kapil Chalil Madathil

All Theses

Synchronous remote usability testing, involves a facilitator conducting a usability test in real time, interacting with a participant who is remote. This study proposes a new methodology for conducting these studies using a three-dimensional virtual world, Wonderland, and compares it with two other commonly used synchronous usability test methods: the traditional lab approach and WebEx, a web-based conferencing and screen sharing approach.
The study involved 48 participants in total, 36 test subjects and 12 test facilitators. These 36 were equally divided among the three environments with the 12 test facilitators being paired with one participant in each of the environments. …

Global Competence: Determination Of Its Importance For Engineers Working In A Global Environment, Gregg M. Warnick

Department of Educational Administration: Dissertations, Theses, and Student Research

We live and work in a world that is even more interconnected and interdependent than ever before. Engineers must now not only develop technical engineering competence, but must also develop additional skills and competencies including global competence to obtain success within a global engineering environment.

The purpose of this study was to determine whether multinational companies considered global competence an important skill in mechanical engineering graduates when making hiring decisions. The study was an exploratory study that utilized an extensive literature review to identify eight global competencies for engineering success within a global environment and also included a survey instrument …

An Analytic Hierarchy Process Approach To Assess Health Service Quality, Yan Li

Theses and Dissertations - UTB/UTPA

While improving quality in health care is currently at the forefront of professional, political, and managerial attention, the key dimensions constituting health-care quality have not been fully understood. Also, few valid approaches have been proposed to the measurement of health-care quality. In this research, the Analytic Hierarchy Process (AHP) approach is applied to study the structure of health-care quality and deducted relative importance weights for each of the quality elements. A statistical quality model is derived to assess medical equipment quality which is an important part constituting the general health-care quality. Finally, the application of the AHP model to assess …

Hybrid Time-Frequency Domain Analysis For Inverter-Fed Induction Motor Fault Detection, T. W. Chua, W. W. Tan, Zhaoxia Wang, C. S. Chang

Research Collection School Of Computing and Information Systems

The detection of faults in an induction motor is important as a part of preventive maintenance. Stator current is one of the most popular signals used for utility-supplied induction motor fault detection as a current sensor can be installed nonintrusively. In variable speeds operation, the use of an inverter to drive the induction motor introduces noise into the stator current so stator current based fault detection techniques become less reliable. This paper presents a hybrid algorithm, which combines time and frequency domain analysis, for broken rotor bar and bearing fault detection. Cluster information obtained by using Independent Component Analysis (ICA) …

Hrc Enews — 2010 Summer, Megan K. Svarz

Publications (HRC)

This issue contains staff accomplishments and announcements, event listings, and a "new faces" listing for new staff, affiliates, and researchers.

Biogeography-Based Optimization Of Neuro-Fuzzy System Parameters For Diagnosis Of Cardiac Disease, Mirela Ovreiu, Daniel J. Simon

Electrical and Computer Engineering Faculty Publications

Cardiomyopathy refers to diseases of the heart muscle that becomes enlarged, thick, or rigid. These changes affect the electrical stability of the myocardial cells, which in turn predisposes the heart to failure or arrhythmias. Cardiomyopathy in its two common forms, dilated and hypertrophic, implies enlargement of the atria; therefore, we investigate its diagnosis through P wave features. In particular, we design a neuro-fuzzy network trained with a new evolutionary algorithm called biogeography-based optimization (BBO). The neuro-fuzzy network recognizes and classifies P wave features for the diagnosis of cardiomyopathy. In addition, we incorporate opposition-based learning in the BBO algorithm for improved …

Intelligibility Of Electrolarynx Speech Using A Novel Actuator, Brian Madden, Mark Nolan, Ted Burke, James Condron, Eugene Coyle

Conference Papers

During voiced speech, the larynx provides quasi-periodic acoustic excitation of the vocal tract. Following a laryngectomy, some people speak using an electrolarynx which replaces the excitatory function of the absent larynx. Drawbacks of conventional electrolarynx designs include the buzzing monotonic sound emitted, the need for a free hand to operate the device, and difficulty experienced by many laryngectomees in adapting to its use. Despite these shortcomings, it remains the preferred method of speech rehabilitation for a substantial minority of laryngectomees. In most electrolarynxes, mechanical vibrations are produced by a linear electromechanical actuator, the armature of which percusses against a metal …

La Traducción Del Software De Mindbody Al Español, Molly Kathryn Mcfarland

World Languages and Cultures

This project entails the translation of the business management software of MINDBODY to Spanish to facilitate international communication and commerce for the company. This translation is meant to better equip MINDBODY with the tools necessary to engage in bilingual international commerce. Translation of this software demo is intended to aid the company’s Spanish speaking clientele and prospective clients by breaking down many of the language barriers they currently face with the software in English, and also to promote the recognition of the growing need for bilingualism in the rapidly changing world, both within and outside the realm of business.

The …

Spot Off: The Gao Takes On The Tsa’S Behavior Detection Program, Ibpp Editor

International Bulletin of Political Psychology

The United States Government Accountability Office (GAO) has recently Issued Efforts to Validate TSA’s Passenger Screening Behavior Detection Program Underway, but Opportunities Exist to Strengthen Validation and Address Operational Problems (May 2010, GAO-10-763). This IBPP article will describe and comment on the main GAO findings and additional data on which the findings are based. The article will end with some basic challenges to behavior detection as a useful security measure.

Synthetic Corpora: A Synergy Of Linguistics And Computer Animation, Jerry C. Schnepp, Rosalee Wolfe, John Mcdonald

Visual Communications and Technology Education Faculty Publications

Synthetic corpora enable the creation of computer-generated animations depicting sign language and are the complement of corpora containing videotaped exemplars. Any design for a synthetic corpus needs to accommodate linguistic processes as well as support the generation of believable, acceptable synthesized utterances. This paper explores one possibility for representing linguistic and extralinguistic processes that involve the face and reports on the outcomes of a user test evaluating the clarity of utterances synthesized by this approach.

Electronic Discovery: A Fool’S Errand Where Angels Fear To Tread?, Milton Luoma, Vicki Luoma

Annual ADFSL Conference on Digital Forensics, Security and Law

Electronic discovery has transformed the discovery phase of civil litigation in recent years. The expectations of lawyers and parties were initially established in the Rowe and Zubulake cases that led to a complete revision of the electronic discovery rules contained in the Federal Rules of Civil Procedure. Subsequent cases have underscored the importance of document search methodologies and implications for attorneys, IT professionals, and digital forensics professionals. The authors review how electronic discovery has evolved thus far and offer recommendations regarding the electronic discovery process.

Keywords: Electronic discovery, e-discovery, keyword search, concept search,

An Information Technology Suitability Index For Mass Customization, Oscar Leonardo Barrenechea

Theses and Dissertations - UTB/UTPA

In today’s manufacturing world, high competitive markets are pushing companies to find better ways to satisfy their customer’s needs using several Mass Customization (MC) approaches. Consequently, new Information Technologies (IT) have taken a very important role in order to manage the increasing amount of data generated from those customers. The purpose of this thesis is to develop an IT suitability index for MC that would help to identify the critical IT factors to be addressed in order to efficiently support MC. A linear programming regression model was utilized to generate index values. Finally, the results of this model could be …