Yabo Xu. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2003. / Includes bibliographical references (leaves 57-60). / Abstracts in English and Chinese. / Abstract --- p.i / Acknowledgement --- p.iii / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Frequent Pattern Mining --- p.1 / Chapter 1.2 --- Biosequence Pattern Mining --- p.2 / Chapter 1.3 --- Organization of the Thesis --- p.4 / Chapter 2 --- PP-Mine: Fast Mining Frequent Patterns In-Memory --- p.5 / Chapter 2.1 --- Background --- p.5 / Chapter 2.2 --- The Overview --- p.6 / Chapter 2.3 --- PP-tree Representations and Its Construction --- p.7 / Chapter 2.4 --- PP-Mine --- p.8 / Chapter 2.5 --- Discussions --- p.14 / Chapter 2.6 --- Performance Study --- p.15 / Chapter 3 --- Fast Biosequence Patterns Mining --- p.20 / Chapter 3.1 --- Background --- p.21 / Chapter 3.1.1 --- Differences in Biosequences --- p.21 / Chapter 3.1.2 --- Mining Sequential Patterns --- p.22 / Chapter 3.1.3 --- Mining Long Patterns --- p.23 / Chapter 3.1.4 --- Related Works in Bioinformatics --- p.23 / Chapter 3.2 --- The Overview --- p.24 / Chapter 3.2.1 --- The Problem --- p.24 / Chapter 3.2.2 --- The Overview of Our Approach --- p.25 / Chapter 3.3 --- The Segment Phase --- p.26 / Chapter 3.3.1 --- Finding Frequent Segments --- p.26 / Chapter 3.3.2 --- The Index-based Querying --- p.27 / Chapter 3.3.3 --- The Compression-based Querying --- p.30 / Chapter 3.4 --- The Pattern Phase --- p.32 / Chapter 3.4.1 --- The Pruning Strategies --- p.34 / Chapter 3.4.2 --- The Querying Strategies --- p.37 / Chapter 3.5 --- Experiment --- p.40 / Chapter 3.5.1 --- Synthetic Data Sets --- p.40 / Chapter 3.5.2 --- Biological Data Sets --- p.46 / Chapter 4 --- Conclusion --- p.55 / Bibliography --- p.60

No description available.

Thesis (Ph.D)--Stanford University, 1999. / Title from pdf t.p. (viewed May 9, 2002). "May 1999." "Adminitrivia V1/Prg/19990528"--Metadata.

Thesis (Ph. D.)--Ohio State University, 2006. / Title from first page of PDF file. Includes bibliographical references (p. 147-155).

Computer algorithms are routinely used to aid in the identification of biological patterns not easily detected with standard statistics. Currently, observed changes in normal patterns of feeding behavior (FB) are used to identify morbid feedlot cattle. The objective of this study was to use pattern classification techniques to develop algorithms capable of identifying morbid (M) cattle earlier than traditional pen checking methods. In two separate studies, individual feeding behaviour was obtained from 384 feedlot steers (228 ± 22.7 kg, initial BW) in a 226 d trial (model dataset), and 384 feedlot heifers (322 ± 34.7 kg, initial BW) in a 142 d trial (naive dataset). Data was collected using an automated feed bunk monitoring system. FB variables calculated included feeding duration, inter-meal interval (min., max., avg., SD and total; min/d) and feeding frequency (visits/d). Animal health records including the number of times treated, d in the hospital and d on feed were also collected. Ninety-three and 53 morbid (M) animals were identified in each trial respectively, and were categorized into low, moderate and high groups, based on severity of sickness. FB data for 68 cattle from the model dataset (45 classified as Moderate and 25 classified as High) was analyzed to develop an algorithm which would aid in identifying morbid FB. This algorithm was later tested on 18 M animals (12 classified as Moderate and 6 as High) in the naive dataset. The pattern recognition procedure involved reducing data dimensionality via Principal Component Analysis, followed by K-means clustering and finally the development of a binary string to aid in the classification of M feeding behaviour. The developed procedure resulted in an overall classification accuracy of 84 % (82.5 and 85 % accuracy for H and M, respectively) for the model dataset, and 75 % overall (100 and 50 % accuracy for H and M, respectively) for the naive dataset. The model predicted morbidity on average 3.3 and 1.2 d earlier than pen checkers could for each trial respectively. The application of pattern recognition algorithms to FB shows value as a method of identifying morbid cattle in advance of overt physical signs of morbidity.

Computer algorithms are routinely used to aid in the identification of biological patterns not easily detected with standard statistics. Currently, observed changes in normal patterns of feeding behavior (FB) are used to identify morbid feedlot cattle. The objective of this study was to use pattern classification techniques to develop algorithms capable of identifying morbid (M) cattle earlier than traditional pen checking methods. In two separate studies, individual feeding behaviour was obtained from 384 feedlot steers (228 ± 22.7 kg, initial BW) in a 226 d trial (model dataset), and 384 feedlot heifers (322 ± 34.7 kg, initial BW) in a 142 d trial (naive dataset). Data was collected using an automated feed bunk monitoring system. FB variables calculated included feeding duration, inter-meal interval (min., max., avg., SD and total; min/d) and feeding frequency (visits/d). Animal health records including the number of times treated, d in the hospital and d on feed were also collected. Ninety-three and 53 morbid (M) animals were identified in each trial respectively, and were categorized into low, moderate and high groups, based on severity of sickness. FB data for 68 cattle from the model dataset (45 classified as Moderate and 25 classified as High) was analyzed to develop an algorithm which would aid in identifying morbid FB. This algorithm was later tested on 18 M animals (12 classified as Moderate and 6 as High) in the naive dataset. The pattern recognition procedure involved reducing data dimensionality via Principal Component Analysis, followed by K-means clustering and finally the development of a binary string to aid in the classification of M feeding behaviour. The developed procedure resulted in an overall classification accuracy of 84 % (82.5 and 85 % accuracy for H and M, respectively) for the model dataset, and 75 % overall (100 and 50 % accuracy for H and M, respectively) for the naive dataset. The model predicted morbidity on average 3.3 and 1.2 d earlier than pen checkers could for each trial respectively. The application of pattern recognition algorithms to FB shows value as a method of identifying morbid cattle in advance of overt physical signs of morbidity.

Optical music recognition (OMR) allows pages of sheet music to be interpreted by a computer, and converted into a versatile machine-readable format. There are many advantages of such a system. For instance, a soloist could have the computer play an accompaniment for rehearsal; a user could build music database occupying less memory; or a musicologist could make an edition, modification, or print of the captured image. Typically, OCR techniques can not be used in music score recognition since music notation presents a two dimensional structure: in a staff the horizontal position denotes different duration for notes and the vertical position defines the height of the note. That the quality or the typesetting of a score is not the same, or some of the man-made factors make many related researches could not process flexibility, or could only recognize with restriction. The paper covers two fields of knowledge: one is image processing technology, mainly based on projection, which is employed to extract horizontal and vertical line to abridge the recognition field, and morphology, which recognize musical symbols. The other is music metric, which provides the help on the analysis, and corrects the errors after recognizing. This system divides into three phases. It starts with all the pre-processing that is needed to de-skew input image, which afford to staff line detection and removal. Then, the symbol recognition, detects the vertical and non-vertical line musical symbol respectively, which are combined into a notation to refine by metric. Finally, the results are stored in a musical representation language, which could be converted into the MIDI format and the music can be played on a MIDI synthesizer. The experiment shows this system could get a satisfied result successfully in short time, and there is no hard-and-fast claim for image resolution.

Abstract With the rapid progress of the MEMs process, the cost and the size of accelerometers are reducing rapidly. As a result, accelerometers have found many new applications in industrial, entertainment and medical domains. One of such an applications is to acquire information about human body movement. The objective of this work is to use knee acceleration signal for indentity verification. Comparing with traditional biometric methods, this approach has several distinct features. First, it can aquire a large amount of data efficiently and conventiently. Second, it is relatively difficult to duplicate. In designing the verification algorithm, this study has developed a neural network method a hyperspherical classifier method. The experimental results demonstrated that hyperspherical classifier provide better performances in this application. By setting the sensitively to 85%, the specificity achieved by the hyperspherical classifier is at least 95%.

Thesis (Ph. D.)--State University of New York at Buffalo, 1998. / "June 1998." Includes bibliographical references (leaves 158-166). Also available in print.

Thesis (Ph.D.)--City University of Hong Kong, 2009. / "Submitted to Department of Computer Science in partial fulfillment of the requirements for the degree of Doctor of Philosophy." Includes bibliographical references (leaves 122-133)