No description available.

This dissertation discusses a method that will aid in diagnosing the root causes of product and process variability in complex manufacturing processes when large quantities of multivariate in-process measurement data are available. As in any data mining application, this dissertation has as its objective the extraction of useful information from the data. A linear structured model, similar to the standard factor analysis model, is used to generically represent the variation patterns that result from the root causes. Blind source separation methods are investigated to identify spatial variation patterns in manufacturing data. Further, the existing blind source separation methods are extended, enhanced and improved to be a more effective, accurate and widely applicable method for manufacturing variation diagnosis. An overall strategy is offered to guide the use of the presented methods in conjunction with alternative methods.

Hearing aid devices are used to help people with hearing impairment. The number of people that requires hearingaid devices are possibly constant over the years, however the number of people that now have access to hearing aiddevices increasing rapidly. The hearing aid devices must be small, consume very little power, and be fairly accurate.Even though it is normally more important for the user that hearing impairment look good (are discrete). Once thehearing aid device prescribed to the user, she/he needs to train and adjust the device to compensate for the individualimpairment.We are within the framework of this project researching on hearing aid devices that can be trained by the hearingimpaired person her-/himself. This project is about finding suitable noise cancellation algorithm for the hearing-aiddevice. We consider several types of algorithms like, microphone array signal processing, Independent ComponentAnalysis (ICA) based on double microphone called Blind Source Separation (BSS) and DRNPE algorithm.We run this current and most sophisticated and robust algorithms in certain noise backgrounds like Cocktail noise,street, public places, train, babble situations to test the efficiency. The BSS algorithm was well in some situation andgave average results in some situations. Where one microphone gave steady results in all situations. The output isgood enough to listen targeted audio.The functionality and performance of the proposed algorithm is evaluated with different non-stationary noisebackgrounds. From the performance results it can be concluded that, by using the proposed algorithm we are able toreduce the noise to certain level. SNR, system delay, minimum error and audio perception are the vital parametersconsidered to evaluate the performance of algorithms. Based on these parameters an algorithm is suggested forheairng-aid. / Hearing-Aid

Magnetic Resonance Imaging is an established technology for both imaging and functional studies in clinical and research environments. The field is still very research intense. Two major research areas are acquisition time and signal quality. The last decade has provided tools for more efficient possibilities of trading these factors against each other through parallel imaging. In this thesis one parallel imaging method, Sensitivity Encoding for fast MRI (SENSE) is examined. An alternative solution CCASENSE is developed. CCASENSE reduces the acquisition time by estimating the sensitivity maps required for SENSE to work instead of running a reference scan. The estimation process is done by Blind Source Separation through Canonical Correlation Analysis. It is shown that CCASENSE appears to estimate the sensitivity maps better than ICASENSE which is a similar algorithm.

Blind source separation methods such as independent component analysis (ICA) and second order blind identification (SOBI) have shown considerable potential in the area of ambient vibration system identification. The objective of these methods is to separate the modal responses, or sources, from the measured output responses, without the knowledge of excitation. Several frequency domain and time domain methods have been proposed and successfully implemented in the literature. Whereas frequency-domain methods pose several challenges typical of dealing with signals in the frequency-domain, popular time-domain methods such as NExT/ERA and SSI pose limitations in dealing with noise, low sensor density, modes having low energy content, or in dealing with systems having closely-spaced modes, such as those found in structures with passive energy dissipation devices, for example, tuned mass dampers.Motivated by these challenges, the current research focuses on developing methods to address the problem of separability of sources with low energy content, closely-spaced modes, and under-determined blind identification, that is, when the number of response measurements is less than the number of sources. These methods, requiring the time and frequency diversities of the measured outputs, are referred to as hybrid time and time-frequency source separation methods. The hybrid methods are classified into two categories. In the first one, the basic principles of modified SOBI are extended using the stationary wavelet transform (SWT) in order to improve the separability of sources, thereby improving the quality of identification. In the second category, empirical mode decomposition is employed to extract the intrinsic mode functions from measurements, followed by an estimation of the mode shape matrix using iterative and/or non iterative procedures within the framework of modified-SOBI. Both experimental and large-scale structural simulation results are included to demonstrate the applicability of these hybrid approaches to structural system identification problems.

No description available.

Thesis (M.S.)--Cleveland State University, 2009. / Abstract. Title from PDF t.p. (viewed on Dec. 2, 2009). Includes bibliographical references (p. 65-72). Available online via the OhioLINK ETD Center and also available in print.

Λαμβάνοντας υπ’ όψη τις διάφορες τεχνικές Blind Source Separation (BSS) που αναφέρονται στη βιβλιογραφία και που εφαρμόζονται σε πολλά πεδία ενδιαφέροντος, αποφασίσαμε να τις εφαρμόσουμε σε ανθρώπινο μαγνητοεγκεφαλογράφημα. Οι τεχνικές αυτές προσπαθούν να εξάγουν πηγές από σήμα το οποίο είναι γραμμικός συνδυασμός των πηγών. Απαραίτητη προϋπόθεση τα σήματα από τις πηγές να είναι στατιστικώς ανεξάρτητα. Πιο συγκεκριμένα, θεωρώντας τις πηγές στον εγκέφαλο ανεξάρτητες, η τεχνική που επιλέχθηκε είναι η Independent Component Analysis (ICA) και κάποιες παραλλαγές της που χρησιμοποιούν κυματίδια ώστε να εισάγουμε τη δυνατότητα περιορισμού στο χρόνο ή στο χώρο. Επιλέγοντας χωρικά ή χρονικά την περιοχή ενδιαφέροντος εστιάζουμε σε κάποια περιοχή του εγκεφάλου ή σε κάποια συγκεκριμένη χρονική στιγμή π.χ. μετά από κάποιο ερέθισμα. Θα χρησιμοποιήσουμε αυτές τις τεχνικές για να αναλύσουμε ανθρώπινο μαγνητοεγκεφαλογράφημα (MEG). Τα δεδομένα των καταγραφών είναι από το ινστιτούτο Riken στην Ιαπωνία. / Bearing in mind the Blind Source Separation Techniques mentioned in the literature and applied to many fields of interest, we decided to apply them on human MEG. These techniques extract sources from the initial signal, which is considered as linear combination of theses sources. It is required that the recorded signals are statistically independent. More specifically, considering the sources in the brain as independent, the method used is called Independent Component Analysis (ICA) and some versions which use wavelets in order to introduce spatial and temporal constraints. By selecting the region of interest either in space or in time, we focus on a region in the brain or on a specified latency e.g. after a stimulus. We use these methods to analyse MEG. The data are recorded in RIKEN institute in Japan.

This dissertation discusses a method that will aid in diagnosing the root causes of product and process variability in complex manufacturing processes when large quantities of multivariate in-process measurement data are available. As in any data mining application, this dissertation has as its objective the extraction of useful information from the data. A linear structured model, similar to the standard factor analysis model, is used to generically represent the variation patterns that result from the root causes. Blind source separation methods are investigated to identify spatial variation patterns in manufacturing data. Further, the existing blind source separation methods are extended, enhanced and improved to be a more effective, accurate and widely applicable method for manufacturing variation diagnosis. An overall strategy is offered to guide the use of the presented methods in conjunction with alternative methods.

Blind source separation methods such as independent component analysis (ICA) and second order blind identification (SOBI) have shown considerable potential in the area of ambient vibration system identification. The objective of these methods is to separate the modal responses, or sources, from the measured output responses, without the knowledge of excitation. Several frequency domain and time domain methods have been proposed and successfully implemented in the literature. Whereas frequency-domain methods pose several challenges typical of dealing with signals in the frequency-domain, popular time-domain methods such as NExT/ERA and SSI pose limitations in dealing with noise, low sensor density, modes having low energy content, or in dealing with systems having closely-spaced modes, such as those found in structures with passive energy dissipation devices, for example, tuned mass dampers.Motivated by these challenges, the current research focuses on developing methods to address the problem of separability of sources with low energy content, closely-spaced modes, and under-determined blind identification, that is, when the number of response measurements is less than the number of sources. These methods, requiring the time and frequency diversities of the measured outputs, are referred to as hybrid time and time-frequency source separation methods. The hybrid methods are classified into two categories. In the first one, the basic principles of modified SOBI are extended using the stationary wavelet transform (SWT) in order to improve the separability of sources, thereby improving the quality of identification. In the second category, empirical mode decomposition is employed to extract the intrinsic mode functions from measurements, followed by an estimation of the mode shape matrix using iterative and/or non iterative procedures within the framework of modified-SOBI. Both experimental and large-scale structural simulation results are included to demonstrate the applicability of these hybrid approaches to structural system identification problems.