Digital Commons Network^™

Audio Scene Segementation Using A Microphone Array And Auditory Features, Harikrishnan Unnikrishnan

University of Kentucky Master's Theses

Auditory stream denotes the abstract effect a source creates in the mind of the listener. An auditory scene consists of many streams, which the listener uses to analyze and understand the environment. Computer analyses that attempt to mimic human analysis of a scene must first perform Audio Scene Segmentation (ASS). ASS find applications in surveillance, automatic speech recognition and human computer interfaces. Microphone arrays can be employed for extracting streams corresponding to spatially separated sources. However, when a source moves to a new location during a period of silence, such a system loses track of the source. This results in …

Modeling Changes In Biomass Composition During Microwave-Based Alkali Pretreatment Of Switchgrass, Deepak R. Keshwani, Jay J. Cheng

Department of Agricultural and Biological Systems Engineering: Faculty Publications

This study used two different approaches to model changes in biomass composition during microwave-based pretreatment of switchgrass: kinetic modeling using a time-dependent rate coefficient, and a Mamdani-type fuzzy inference system. In both modeling approaches, the dielectric loss tangent of the alkali reagent and pretreatment time were used as predictors for changes in amounts of lignin, cellulose, and xylan during the pretreatment. Training and testing data sets for development and validation of the models were obtained from pretreatment experiments conducted using 1–3% w/v NaOH (sodium hydroxide) and pretreatment times ranging from 5 to 20 minutes. The kinetic modeling approach for lignin …

Adaptive Neuro-Fuzzy Inference System To Improve The Power Quality Of Variable-Speed Wind Power Generation System, Yüksel Oğuz, Kami̇l Ri̇fat İrfan Güney

Turkish Journal of Electrical Engineering and Computer Sciences

In this study, an adaptive neuro-fuzzy inference system is designed for output voltage and frequency control of a variable-speed wind power generation system. Variable-speed wind power generation systems (VSWPGS) provide the opportunity to capture more power than fixed speed turbines. On the other hand, the variable-speed wind turbine output can be variable voltage and variable frequency for fluctuating wind speeds. The quality of output power can be improved if adequate controls are incorporated in the system. To bring the output voltage and frequency of system by means of control of blade pitch angle of wind turbine to a desirable value, …

Modeling Biological Structures Via Abstract Grammars To Solve Common Problems In Computational Biology, David J. Russell

Department of Electrical and Computer Engineering: Dissertations, Theses, and Student Research

Grammars are generally understood to be the set of rules that define the relationships between elements of a language. However, grammars can also be used to elucidate structural relationships within sequences constructed from any finite alphabet. In this work abstract grammars are used to model the primary and secondary structures present in biological data. These grammar models are inferred and applied to efficiently solve various sequence analysis problems in computational biology, including multiple sequence alignment, fragment assembly, database redundancy removal, and structural prediction.

The primary structures, or sequential ordering of symbols, of biological data are first modeled with Lempel-Ziv (LZ) …

Application Planning, Jochen Albrecht, Clare Davies

Publications and Research

No abstract provided.

Evaluating Sensorineural Hearing Loss With An Auditory Nerve Model Using A Mean Structural Similarity Measure, Andrew Hines, Naomi Harte

Conference papers

Hearing loss research has traditionally been based on perceptual criteria, speech intelligibility and threshold levels. The development of computational models of the auditory-periphery has allowed experimentation via simulation to provide quantitative, repeatable results at a more granular level than would be practical with clinical research on human subjects. This work seeks to create an objective measure to automate this inspection process and ranks hearing losses based on auditory-nerve discharge patterns. A systematic way of assessing phonemic degradation using the outputs of an auditory nerve model for a range of sensorineural hearing losses would aid in rapid prototyping development of speech-processing …

Extraction And Prediction Of System Properties Using Variable-N-Gram Modeling And Compressive Hashing, Muthulakshmi Muthukumarasamy

University of Kentucky Doctoral Dissertations

In modern computer systems, memory accesses and power management are the two major performance limiting factors. Accesses to main memory are very slow when compared to operations within a processor chip. Hardware write buffers, caches, out-of-order execution, and prefetch logic, are commonly used to reduce the time spent waiting for main memory accesses. Compiler loop interchange and data layout transformations also can help. Unfortunately, large data structures often have access patterns for which none of the standard approaches are useful. Using smaller data structures can significantly improve performance by allowing the data to reside in higher levels of the memory …

Simulation Optimisation Methods In Supply Chain Applications: A Review, Amr Arisha, Waleed Abo-Hamad

Articles

The competitiveness and dynamic nature of today’s marketplace is due to rapid advances in information technology, short product life cycles and the continuing trend in global outsourcing. Managing the resulting supply chain networks effectively is challenged by high levels of uncertainty in supply and demand, confl ict objectives, vagueness of information, numerous decision variables and constraints. With such levels of complexity, supply chain optimisation has the potential to make a signifi cant contribution in resolving these challenges. In this paper, a literature review – based on more than 100 peer-reviewed articles – of state-of-the-art simulation-based optimisation techniques in the context …

Complex Systems Architecting Using Design Primitives, Comparative Analysis And Fuzzy Analytical Feedback, Jason Paul Dauby, Cihan H. Dagli

Engineering Management and Systems Engineering Faculty Research & Creative Works

Modern systems are increasing in complexity. It is advantageous to understand and control this complexity as early in the design lifecycle as possible. The system architecting community must reconcile the inherent ambiguity in a system description with the need for analytical assessments of system attributes so as to increase the likelihood of developmental success. Presently, it is commonplace to decompose systems and subsystems using assumptions of idealized severability and reliance on superposition to estimate composite performance. It is suggested that these assumptions can result in errant oversimplification and represent an opportunity for new systems engineering research. This paper introduces a …

Crctol: A Semantic Based Domain Ontology Learning System, Xing Jiang, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Domain ontologies play an important role in supporting knowledge‐based applications in the Semantic Web. To facilitate the building of ontologies, text mining techniques have been used to perform ontology learning from texts. However, traditional systems employ shallow natural language processing techniques and focus only on concept and taxonomic relation extraction. In this paper we present a system, known as Concept‐Relation‐Concept Tuple‐based Ontology Learning (CRCTOL), for mining ontologies automatically from domain‐specific documents. Specifically, CRCTOL adopts a full text parsing technique and employs a combination of statistical and lexico‐syntactic methods, including a statistical algorithm that extracts key concepts from a document collection, …

Computational Intelligence Methods In Wireless Sensor Networks, Raghavendra V. Kulkarni

Doctoral Dissertations

"Wireless sensor networks (WSNs) are networks of autonomous nodes that sense, compute and communicate in order to monitor an environment collectively. Ad hoc deployment, dynamic environment and resource constraints in nodes need to be considered while addressing WSN challenges such as deployment, localization, routing and scheduling. Adaptive mechanisms that exhibit intelligent behavior in complex and dynamic environments are desirable to address these challenges. The potential of computational intelligence ( CI) based approaches for addressing WSN challenges is investigated in this study. Contributions of this dissertation are in the following three areas: critical literature analysis, new architectures and approaches, and new …

Design Of A Fuzzy Gain Scheduling Controller Having Input Saturation: A Comparative Study, Yan-Wen Huang, Pi-Cheng Tung

Journal of Marine Science and Technology–Taiwan

A fuzzy gain scheduling proportional controllers that exhibits the improved performance than the conventional linear fixed gain controller having input saturation is proposed in this paper. We proposed an adaptive anti-windup control system in which the gain of a proportional controller is dynamically tuned by a fuzzy PD system. The methodology employed in the analysis is based on the describing function (DF), which is determined the range of the universal discourse for the output of the fuzzy PD system. Other approaches are the linear quadratic regulator (LQR) method and combined back-calculation and generalized conditioning anti-windup. In this paper, a comparison …

Linguistic Analysis Of Natural Language Engineering Requirements, Carl Lamar

All Theses

In engineering design, the needs of the customer are expressed through engineering requirement statements. These requirement statements are often expressed using natural language because they are easily created and read. However, there are several problems associated with natural language requirements including but not limited to ambiguity, incompleteness, understandability, testability and over specificity. Several representation and analysis tools have been proposed to address these problems within a requirement statement. These tools include formal languages, such as UML and SysML, requirement management tools, such as IBM Telelogic Doors, and natural language processors such as QuARS. These tools assist in the systematic elicitation …

Adaptive Type-2 Fuzzy Maintenance Advisor For Offshore Power Systems, Zhaoxia Wang, C. S. Chang, Fan Yang, W. W. Tan

Research Collection School Of Computing and Information Systems

Proper maintenance strategies are very desirable for minimizing the operational and maintenance costs of power systems without sacrificing reliability. Condition-based maintenance has largely replaced time-based maintenance because of the former's potential economic benefits. As offshore substations are often remotely located, they experience more adverse environments, higher failures, and therefore need more powerful analytical tools than their onshore counterpart. As reliability information collected during operation of an offshore substation can rarely avoid uncertainties, it is essential to obtain consistent estimates of reliability measures under changing environmental and operating conditions. Some attempts with type-1 fuzzy logic were made with limited success in …

A Clustering Based Discretization For Supervised Learning, Ankit Gupta, Kishan Mehrotra, Chilukuri K. Mohan

Electrical Engineering and Computer Science - All Scholarship

We address the problem of discretization of continuous variables for machine learning classification algorithms. Existing procedures do not use interdependence between the variables towards this goal. Our proposed method uses clustering to exploit such interdependence. Numerical results show that this improves the classification performance in almost all cases. Even if an existing algorithm can successfully operate with continuous variables, better performance is obtained if variables are first discretized. An additional advantage of discretization is that it reduces the overall time-complexity.

Contribution Based Priority Assessment In A Web-Based Intelligent Argumentation Network For Collaborative Software Development, Xiaoqing Frank Liu, Maithili Satyavolu, Ming-Chuan Leu

Computer Science Faculty Research & Creative Works

Decision making is an important aspect in a collaborative software development process which involves a complex process of conflict resolution. the priority of the participants plays a vital role in conflict resolution as the decision-making process involves many participants from multiple perspectives. the priority assessment methods used in the process so far are usually static in nature, i.e., the priorities of the participants remain constant throughout the decision-making process. in order to make the collaborative system closer to real world scenarios, we incorporate dynamic priority assessment into a web-Based collaborative system based on intelligent computational argumentation, which was developed in …

Santa Clara Magazine, Volume 51 Number 2, Fall 2009, Santa Clara University

Santa Clara Magazine

16 - POLITICS AND RELIGION: STILL ON A COLLISION COURSE? An interview with Avraham Burg, former speaker of the Israeli Knesset. Plus excerpts from talks by E.J. Dionne Jr., Lisa Sowle Cahill '70, and Michael Eric Dyson.

20 - THE GULF OF WONDER By Emily Elrod '05. With a movie, Patrick McVeigh '78 offers investors a unique opportunity: Wake up the citizens of America and help them save one of the Seven Natural Wonders of the World. Plus, a 30 percent return.

24 - SEASON PREMIERE: "RESURRECTION" By Karen Crocker Snell. Forensic investigator Horatio Caine lies facedown in a pool …

Semantic Context Transfer Across Heterogeneous Sources For Domain Adaptive Video Search, Yu-Gang Jiang, Chong-Wah Ngo, Shih-Fu Chang

Research Collection School Of Computing and Information Systems

Automatic video search based on semantic concept detectors has recently received significant attention. Since the number of available detectors is much smaller than the size of human vocabulary, one major challenge is to select appropriate detectors to response user queries. In this paper, we propose a novel approach that leverages heterogeneous knowledge sources for domain adaptive video search. First, instead of utilizing WordNet as most existing works, we exploit the context information associated with Flickr images to estimate query-detector similarity. The resulting measurement, named Flickr context similarity (FCS), reflects the co-occurrence statistics of words in image context rather than textual …

Scalable Detection Of Partial Near-Duplicate Videos By Visual-Temporal Consistency, Hung-Khoon Tan, Chong-Wah Ngo, Richang Hong, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Following the exponential growth of social media, there now exist huge repositories of videos online. Among the huge volumes of videos, there exist large numbers of near-duplicate videos. Most existing techniques either focus on the fast retrieval of full copies or near-duplicates, or consider localization in a heuristic manner. This paper considers the scalable detection and localization of partial near-duplicate videos by jointly considering visual similarity and temporal consistency. Temporal constraints are embedded into a network structure as directed edges. Through the structure, partial alignment is novelly converted into a network flow problem where highly efficient solutions exist. To precisely …

Detecting Automotive Exhaust Gas Based On Fuzzy Inference System, Li. Shujin, Ming Bai, Quan Wang, Bo Chen, Xiaobing Zhao, Ting Yang, Zhaoxia Wang

Research Collection School Of Computing and Information Systems

This paper proposes a method of detecting automotive exhaust gas based on fuzzy logic inference after analyzing the principle of the infrared automobile exhaust gas analyzer and the influence of the environmental temperature on analyzer. This paper analyses the measurement error caused by environmental temperature, and then makes a non-linear error correction of temperature for the infrared sensor using fuzzy inference. The results of simulation have clearly demonstrated that the proposed fuzzy compensation scheme is better than the non-fuzzy method.

Artificial Intelligence – I: Subjective Decision Making Using Type-2 Fuzzy Logic Advisor, Owais Malik

International Conference on Information and Communication Technologies

In this paper, we present and compare two-stage type-2 fuzzy logic advisor (FLA) for subjective decision making in the domain of students' performance evaluation. We test our proposed model for evaluating students' performance in our computer science and engineering department at HBCC/KFUPM in two domains namely cooperating training and capstone/senior project assessment where we find these FLAs very useful and promising. In our proposed model, the assessment criteria for different components of cooperative training and senior project are transformed into linguistic labels and evaluation information is extracted into the form of IF-THEN rules from the experts. These rules are modeled …

Large-Scale Near-Duplicate Web Video Search: Challenge And Opportunity, Wan-Lei Zhao, Song Tan, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

The massive amount of near-duplicate and duplicate web videos has presented both challenge and opportunity to multimedia computing. On one hand, browsing videos on Internet becomes highly inefficient for the need to repeatedly fast-forward videos of similar content. On the other hand, the tremendous amount of somewhat duplicate content also makes some traditionally difficult vision tasks become simple and easy. For example, annotating pictures can be as simple as recycling the tags of Internet images retrieved from image search engines. Such tasks, of either to eliminate or to recycle near-duplicates, can usually be achieved by the nearest neighbor search of …

Hardware Implementation Of A Mamdani Fuzzy Logic Controller For A Static Compensator In A Multimachine Power System, Salman Mohagheghi, Ganesh K. Venayagamoorthy, Satish Rajagopalan, Ronald G. Harley

Electrical and Computer Engineering Faculty Research & Creative Works

A Mamdani-type fuzzy logic controller is designed and implemented in hardware for controlling a static compensator (STATCOM), which is connected to a ten-bus multimachine power system. Such a controller does not need any mathematical model of the plant to be controlled and can efficiently provide control signals for the STATCOM over a wide range of operating conditions of the power system and during different disturbances. The proposed controller is implemented using the M67 digital signal processor board and is interfaced to the multimachine power system simulated on a real-time digital simulator. Experimental results are provided, showing that the proposed Mamdani …

Decision Analysis For Construction Contract Risk-Sharing, Teh-Chang Lee, Ta-Hsing Lee, Ching-Hwang Wang

Journal of Marine Science and Technology–Taiwan

As the risk-sharing provisions in domestic public construction contracts are not completely fair and reasonable, contract disputes often arise as a result which in turn cause delays, quality impacts, and other problems that urgently need improvement. Introduced in this article is the development of a decision system for risk-sharing in public construction contracts. Said system was developed through literature review, questionnaire and interviews of experts, fuzzy synthetic evaluation in conjunction of analytic hierarchy process, definition of risks in public construction contracts, and establishment of decision models for risk-sharing. Subsequently, the “escalation” risk was employed as an example to select suitable …

Looking For Entropy Rate Constancy In Spoken Dialog, Alejandro Vega, Nigel Ward

Departmental Technical Reports (CS)

The entropy constancy principle describes the tendency for information in language to be conveyed at a constant rate. We explore the possible role of this principle in spoken dialog, using the ``summed entropy rate,'' that is, the sum of the entropies of the words of both speakers per second of time. Using the Switchboard corpus of casual dialogs and a standard ngram language model to estimate entropy, we examine patterns in entropy rate over time and the distribution of entropy across the two speakers. The results show effects that can be taken as support for the principle of constant entropy, …

A System For Natural Language Unmarked Clausal Transformations In Text-To-Text Applications, Daniel Miller

Master's Theses

A system is proposed which separates clauses from complex sentences into simpler stand-alone sentences. This is useful as an initial step on raw text, where the resulting processed text may be fed into text-to-text applications such as Automatic Summarization, Question Answering, and Machine Translation, where complex sentences are difficult to process. Grammatical natural language transformations provide a possible method to simplify complex sentences to enhance the results of text-to-text applications. Using shallow parsing, this system improves the performance of existing systems to identify and separate marked and unmarked embedded clauses in complex sentence structure resulting in syntactically simplified source for …

2009 - The Fourteenth Annual Symposium Of Student Scholars

Symposium of Student Scholars Program Books

The full program book from the Fourteenth Annual Symposium of Student Scholars, held on April 13, 2009. Includes abstracts from the presentations and posters.

Auditory Coding Based Speech Enhancement, Yao Ren, Michael T. Johnson

Dr. Dolittle Project: A Framework for Classification and Understanding of Animal Vocalizations

This paper demonstrates a speech enhancement system based on an efficient auditory coding approach, coding of time-relative structure using spikes. The spike coding method can more compactly represent the non-stationary characteristics of speech signals than the Fourier transform or wavelet transform. Enhancement is accomplished through the use of MMSE thresholding on the spike code. Experimental results show that compared with the spectral domain logSTSA filter, both the subjective spectrogram evaluation and objective SSNR improvement for the proposed approach is better in suppressing noise in high noise situations, with fewer musical artifacts.P

Optimal Distributed Microphone Phase Estimation, Marek B. Trawicki, Michael T. Johnson

Dr. Dolittle Project: A Framework for Classification and Understanding of Animal Vocalizations

This paper presents a minimum mean-square error spectral phase estimator for speech enhancement in the distributed multiple microphone scenario. The estimator uses Gaussian models for both the speech and noise priors under the assumption of a diffuse incoherent noise field representing ambient noise in a widely dispersed microphone configuration. Experiments demonstrate significant benefits of using the optimal multichannel phase estimator as compared to the noisy phase of a reference channel.

On The Role Of Assertions For Conceptual Modeling As Enablers Of Composable Simulation Solutions, Robert Dennis King

Computational Modeling & Simulation Engineering Theses & Dissertations

This research provides a much needed systematic review of the roles that assertions play in model composability and simulation interoperability. In doing so, this research contributes a partial solution to one of the problems of model composability and simulation interoperability—namely, why do simulation systems fail to achieve the maximum level of interoperability possible? It demonstrates the importance of the assertions that are made during model development and simulation implementation, particularly as they reflect the unique viewpoint of each developer or user. It hypothesizes that it is possible to detect composability conflicts by means of a four-step process developed by the …