Nondestructive testing is used extensively throughout the industry for quality assessment and detection of defects in engineering materials. The range and variety of anomalies is enormous and critical assessment of their location and size is often complicated. Depending upon final operational considerations, some of these anomalies may be critical and their detection and classification is therefore of importance. Despite the several advantages of using Nondestructive testing for flaw detection, the conventional NDT techniques based on the heuristic experience-based pattern identification methods have many drawbacks in terms of cost, length and result in erratic analysis and thus lead to discrepancies in results. The use of several statistical and soft computing techniques in the evaluation and classification operations result in the development of an automatic decision support system for defect characterization that offers the possibility of an impartial standardized performance. The present work evaluates the application of both supervised and unsupervised classification techniques for flaw detection and classification in a semi-infinite half space. Finite element models to simulate the MASW test in the presence and absence of voids were developed using the commercial package LS-DYNA. To simulate anomalies, voids of different sizes were inserted on elastic medium. Features for the discrimination of received responses were extracted in time and frequency domains by applying suitable transformations. The compact feature vector is then classified by different techniques: supervised classification (backpropagation neural network, adaptive neuro-fuzzy inference system, k-nearest neighbor classifier, linear discriminate classifier) and unsupervised classification (fuzzy c-means clustering). The classification results show that the performance of k-nearest Neighbor Classifier proved superior when compared with the other techniques with an overall accuracy of 94% in detection of presence of voids and an accuracy of 81% in determining the size of the void in the medium. The assessment of the various classifiers’ performance proved to be valuable in comparing the different techniques and establishing the applicability of simplified classification methods such as k-NN in defect characterization. The obtained classification accuracies for the detection and classification of voids are very encouraging, showing the suitability of the proposed approach to the development of a decision support system for non-destructive testing of materials for defect characterization.

Nondestructive testing is used extensively throughout the industry for quality assessment and detection of defects in engineering materials. The range and variety of anomalies is enormous and critical assessment of their location and size is often complicated. Depending upon final operational considerations, some of these anomalies may be critical and their detection and classification is therefore of importance. Despite the several advantages of using Nondestructive testing for flaw detection, the conventional NDT techniques based on the heuristic experience-based pattern identification methods have many drawbacks in terms of cost, length and result in erratic analysis and thus lead to discrepancies in results. The use of several statistical and soft computing techniques in the evaluation and classification operations result in the development of an automatic decision support system for defect characterization that offers the possibility of an impartial standardized performance. The present work evaluates the application of both supervised and unsupervised classification techniques for flaw detection and classification in a semi-infinite half space. Finite element models to simulate the MASW test in the presence and absence of voids were developed using the commercial package LS-DYNA. To simulate anomalies, voids of different sizes were inserted on elastic medium. Features for the discrimination of received responses were extracted in time and frequency domains by applying suitable transformations. The compact feature vector is then classified by different techniques: supervised classification (backpropagation neural network, adaptive neuro-fuzzy inference system, k-nearest neighbor classifier, linear discriminate classifier) and unsupervised classification (fuzzy c-means clustering). The classification results show that the performance of k-nearest Neighbor Classifier proved superior when compared with the other techniques with an overall accuracy of 94% in detection of presence of voids and an accuracy of 81% in determining the size of the void in the medium. The assessment of the various classifiers’ performance proved to be valuable in comparing the different techniques and establishing the applicability of simplified classification methods such as k-NN in defect characterization. The obtained classification accuracies for the detection and classification of voids are very encouraging, showing the suitability of the proposed approach to the development of a decision support system for non-destructive testing of materials for defect characterization.

<p>The computer vision task of classifying natural images is a primary driving force behind modern AI algorithms. Deep Convolutional Neural Networks (CNNs) demonstrate state of the art performance in large scale multi-class image classification tasks. However, due to the many layers and millions of parameters these models are considered to be black box algorithms. The decisions of these models are further obscured due to a cumbersome multi-class decision process. There exists another approach called class binarization in the literature which determines the multi-class prediction outcome through a sequence of binary decisions.The focus of this dissertation is on the integration of the class-binarization approach to multi-class classification with deep learning models, such as CNNs, for addressing large scale image classification problems. Three works are presented to address the integration.</p> <p>In the first work, Error Correcting Output Codes (ECOCs) are integrated into CNNs by inserting a latent-binarization layer prior to the CNNs final classification layer.  This approach encapsulates both encoding and decoding steps of ECOC into a single CNN architecture. EM and Gibbs sampling algorithms are combined with back-propagation to train CNN models with Latent Binarization (LB-CNN). The training process of LB-CNN guides the model to discover hidden relationships similar to the semantic relationships known apriori between the categories. The proposed models and algorithms are applied to several image recognition tasks, producing excellent results.</p> <p>In the second work, Hierarchically Decodeable Output Codes (HD-OCs) are proposedto compactly describe a hierarchical probabilistic binary decision process model over the features of a CNN. HD-OCs enforce more homogeneous assignments of the categories to the dichotomy labels. A novel concept called average decision depth is presented to quantify the average number of binary questions needed to classify an input. An HD-OC is trained using a hierarchical log-likelihood loss that is empirically shown to orient the output of the latent feature space to resemble the hierarchical structure described by the HD-OC. Experiments are conducted at several different scales of category labels. The experiments demonstrate strong performance and powerful insights into the decision process of the model.</p> <p>In the final work, the literature of enumerative combinatorics and partially ordered sets isused to establish a unifying framework of class-binarization methods under the Multivariate Bernoulli family of models. The unifying framework theoretically establishes simple relationships for transitioning between the different binarization approaches. Such relationships provide useful investigative tools for the discovery of statistical dependencies between large groups of categories. They are additionally useful for incorporating taxonomic information as well as enforcing structural model constraints. The unifying framework lays the groundwork for future theoretical and methodological work in addressing the fundamental issues of large scale multi-class classification.</p> <p><br></p>

Αντικείμενο της διατριβής ήταν η ανάπτυξη υπολογιστικών μεθόδων διάγνωσης και εκτίμησης της κατάστασης της υγείας του εμβρύου. Οι προτεινόμενες μεθοδολογίες αναλύουν και εξάγουν πληροφορίες από το σήμα της ΕΚΣ καθώς το συγκεκριμένο σήμα αποτελεί ένα από τα λιγοστά διαθέσιμα εργαλεία για την εκτίμηση της οξυγόνωσης του εμβρύου και της αξιολόγησης της κατάστασης της υγείας του κατά τη διάρκεια του τοκετού. Για την αξιολόγηση των μεθόδων εξετάστηκε η συσχέτιση της Εμβρυϊκής Καρδιακής Συχνότητας (ΕΚΣ) με βραχυπρόθεσμες αξιόπιστες ενδείξεις για την κατάσταση του εμβρύου και πιο συγκεκριμένα χρησιμοποιήθηκε η συσχέτιση της τιμής του pH του αίματος του εμβρύου η οποία αποτελεί μια έμμεση ένδειξη για την ανάπτυξη υποξίας κατά τη διάρκεια του τοκετού. Στα πλαίσια της διατριβής χρησιμοποιήθηκε για πρώτη φορά η μέθοδος της ανάλυσης σε ανεξάρτητες συνιστώσες για την εξαγωγή χαρακτηριστικών από το σήμα της ΕΚΣ. Επίσης προτάθηκαν και χρησιμοποιήθηκαν Κρυφά Μοντέλα Markov σε μια προσπάθεια να «συλληφθεί» η χρονική εξέλιξη του φαινομένου της μεταβολής της κατάστασης του εμβρύου. Επιπλέον προτάθηκαν νέα χαρακτηριστικά εξαγόμενα με τη χρήση του Διακριτού Μετασχηματισμού Κυματιδίου. Με χρήση μιας υβριδική μέθοδος, που βασίζεται στη χρήση εξελικτικής γραμματικής «κατασκευάστηκαν» νέα χαρακτηριστικά παραγόμενα από τα χαρακτηριστικά που είχαν ήδη εξαχθεί με συμβατικές μεθόδους. Επιπρόσθετα στα πλαίσια της διατριβής χρησιμοποιήθηκαν για πρώτη φορά (και η μόνη μέχρι στιγμής) μηχανές διανυσμάτων υποστήριξης για την ταξινόμηση και προτάθηκε και χρησιμοποιήθηκε για πρώτη φορά η μέθοδος βελτιστοποίησης με σμήνος σωματιδίων για τη ρύθμιση των παραμέτρων τους. Τέλος προτάθηκε και χρησιμοποιήθηκε για πρώτη φορά η μέθοδος βελτιστοποίησης με σμήνος σωματιδίων για την εκπαίδευση μιας νέας οικογένειας νευρωνικών δικτύων, των νευρωνικών δικτύων κυματιδίου. Μέσα από τα πειράματα τα οποία διεξήγαμε καταφέραμε να δείξουμε ότι τα δεδομένα της ΕΚΣ διαθέτουν σημαντική πληροφορία η οποία με τη χρήση κατάλληλων προηγμένων μεθόδων επεξεργασίας και ταξινόμησης μπορεί να συσχετιστεί με την τιμή του pH του εμβρύου, κάτι το οποίο θεωρούνταν ουτοπικό στη δεκαετία του 90. / This Dissertation dealt with the development of computational methods for the diagnosis and estimation of fetal condition. The proposed methods analyzed and extracted information from the Fetal Heart Rate (FHR) signal, since this is one of the few available tools for the estimation of fetal oxygenation and the assessment of fetal condition during labor. For the evaluation of the proposed methods the correlation of the FHR signal with short term indices were employed and to be more specific, its correlation with the pH values of fetal blood, which is an indirect sign of the development of fetal hypoxia during labor. In the context of this Dissertation, Independent Component Analysis (ICA) for feature extraction from the FHR signal was used for the first time. Moreover we used Hidden Markov Models in an attempt to “capture” the evolution in time of the fetal condition. Furthermore, new features based on the Discrete Wavelet Transform were proposed and used. Using a new hybrid method based on grammatical evolution new features were constructed based on already extracted features by conventional methods. Moreover, for the first (and only) time, Support Vector Machine (SVM) classifiers were employed in the field of FHR processing and the Particle Swarm Optimization (PSO) method was proposed for tuning their parameters. Finally, a new family of neural networks, the Wavelet Neural Networks (WNN) was proposed and used, trained using the PSO method. By conducting a number of experiments we managed to show that the FHR signal conveys valuable information, which by the use of advanced data processing and classification techniques can be associated with fetal pH, something which was not regarded feasible during the 90’s.