Search

Mixed reality (MR) is a key technology which promises to change the future of warfare. An MR hybrid of physical outdoor environments and virtual military training will enable engagements with long distance enemies, both real and simulated. To enable this technology, a large-scale 3D model of a physical environment must be maintained based on live sensor observations. 3D reconstruction algorithms should utilize the low cost and pervasiveness of video camera sensors, from both overhead and soldier-level perspectives. Mapping speed and 3D quality can be balanced to enable live MR training in dynamic environments. Given these requirements, we survey several 3D reconstruction algorithms for large-scale mapping for military applications given only live video. We measure 3D reconstruction performance from common structure from motion, visual-SLAM, and photogrammetry techniques. This includes the open source algorithms COLMAP, ORB-SLAM3, and NeRF using Instant-NGP. We utilize the autonomous driving academic benchmark KITTI, which includes both dashboard camera video and lidar produced 3D ground truth. With the KITTI data, our primary contribution is a quantitative evaluation of 3D reconstruction computational speed when considering live video., Accepted to 2022 Interservice/Industry Training, Simulation, and Education Conference (I/ITSEC), 13 pages

We focus on the problem of producing well-calibrated out-of-distribution (OOD) detectors, in order to enable safe deployment of medical image classifiers. Motivated by the difficulty of curating suitable calibration datasets, synthetic augmentations have become highly prevalent for inlier/outlier specification. While there have been rapid advances in data augmentation techniques, this paper makes a striking finding that the space in which the inliers and outliers are synthesized, in addition to the type of augmentation, plays a critical role in calibrating OOD detectors. Using the popular energy-based OOD detection framework, we find that the optimal protocol is to synthesize latent-space inliers along with diverse pixel-space outliers. Based on empirical studies with multiple medical imaging benchmarks, we demonstrate that our approach consistently leads to superior OOD detection ($15\% - 35\%$ in AUROC) over the state-of-the-art in a variety of open-set recognition settings.

With increased interest in adopting AI methods for clinical diagnosis, a vital step towards safe deployment of such tools is to ensure that the models not only produce accurate predictions but also do not generalize to data regimes where the training data provide no meaningful evidence. Existing approaches for ensuring the distribution of model predictions to be similar to that of the true distribution rely on explicit uncertainty estimators that are inherently hard to calibrate. In this paper, we propose to train a loss estimator alongside the predictive model, using a contrastive training objective, to directly estimate the prediction uncertainties. Interestingly, we find that, in addition to producing well-calibrated uncertainties, this approach improves the generalization behavior of the predictor. Using a dermatology use-case, we show the impact of loss estimators on model generalization, in terms of both its fidelity on in-distribution data and its ability to detect out of distribution samples or new classes unseen during training.

Explanation techniques that synthesize small, interpretable changes to a given image while producing desired changes in the model prediction have become popular for introspecting black-box models. Commonly referred to as counterfactuals, the synthesized explanations are required to contain discernible changes (for easy interpretability) while also being realistic (consistency to the data manifold). In this paper, we focus on the case where we have access only to the trained deep classifier and not the actual training data. While the problem of inverting deep models to synthesize images from the training distribution has been explored, our goal is to develop a deep inversion approach to generate counterfactual explanations for a given query image. Despite their effectiveness in conditional image synthesis, we show that existing deep inversion methods are insufficient for producing meaningful counterfactuals. We propose DISC (Deep Inversion for Synthesizing Counterfactuals) that improves upon deep inversion by utilizing (a) stronger image priors, (b) incorporating a novel manifold consistency objective and (c) adopting a progressive optimization strategy. We find that, in addition to producing visually meaningful explanations, the counterfactuals from DISC are effective at learning classifier decision boundaries and are robust to unknown test-time corruptions., Comment: Neurips 2021

Graph Neural Networks (GNNs), a generalization of neural networks to graph-structured data, are often implemented using message passes between entities of a graph. While GNNs are effective for node classification, link prediction and graph classification, they are vulnerable to adversarial attacks, i.e., a small perturbation to the structure can lead to a non-trivial performance degradation. In this work, we propose Uncertainty Matching GNN (UM-GNN), that is aimed at improving the robustness of GNN models, particularly against poisoning attacks to the graph structure, by leveraging epistemic uncertainties from the message passing framework. More specifically, we propose to build a surrogate predictor that does not directly access the graph structure, but systematically extracts reliable knowledge from a standard GNN through a novel uncertainty-matching strategy. Interestingly, this uncoupling makes UM-GNN immune to evasion attacks by design, and achieves significantly improved robustness against poisoning attacks. Using empirical studies with standard benchmarks and a suite of global and target attacks, we demonstrate the effectiveness of UM-GNN, when compared to existing baselines including the state-of-the-art robust GCN.

With increasing reliance on the outcomes of black-box models in critical applications, post-hoc explainability tools that do not require access to the model internals are often used to enable humans understand and trust these models. In particular, we focus on the class of methods that can reveal the influence of input features on the predicted outputs. Despite their wide-spread adoption, existing methods are known to suffer from one or more of the following challenges: computational complexities, large uncertainties and most importantly, inability to handle real-world domain shifts. In this paper, we propose PRoFILE (Producing Robust Feature Importances using Loss Estimates), a novel feature importance estimation method that addresses all these challenges. Through the use of a loss estimator jointly trained with the predictive model and a causal objective, PRoFILE can accurately estimate the feature importance scores even under complex distribution shifts, without any additional re-training. To this end, we also develop learning strategies for training the loss estimator, namely contrastive and dropout calibration, and find that it can effectively detect distribution shifts. Using empirical studies on several benchmark image and non-image data, we show significant improvements over state-of-the-art approaches, both in terms of fidelity and robustness.

Exploiting known semantic relationships between fine-grained tasks is critical to the success of recent model agnostic approaches. These approaches often rely on meta-optimization to make a model robust to systematic task or domain shifts. However, in practice, the performance of these methods can suffer, when there are no coherent semantic relationships between the tasks (or domains). We present Invenio, a structured meta-learning algorithm to infer semantic similarities between a given set of tasks and to provide insights into the complexity of transferring knowledge between different tasks. In contrast to existing techniques such as Task2Vec and Taskonomy, which measure similarities between pre-trained models, our approach employs a novel self-supervised learning strategy to discover these relationships in the training loop and at the same time utilizes them to update task-specific models in the meta-update step. Using challenging task and domain databases, under few-shot learning settings, we show that Invenio can discover intricate dependencies between tasks or domains, and can provide significant gains over existing approaches in terms of generalization performance. The learned semantic structure between tasks/domains from Invenio is interpretable and can be used to construct meaningful priors for tasks or domains., Semantic structure development for tasks/domains essential for efficient knowledge transfer

Modern audio source separation techniques rely on optimizing sequence model architectures such as, 1D-CNNs, on mixture recordings to generalize well to unseen mixtures. Specifically, recent focus is on time-domain based architectures such as Wave-U-Net which exploit temporal context by extracting multi-scale features. However, the optimality of the feature extraction process in these architectures has not been well investigated. In this paper, we examine and recommend critical architectural changes that forge an optimal multi-scale feature extraction process. To this end, we replace regular $1-$D convolutions with adaptive dilated convolutions that have innate capability of capturing increased context by using large temporal receptive fields. We also investigate the impact of dense connections on the extraction process that encourage feature reuse and better gradient flow. The dense connections between the downsampling and upsampling paths of a U-Net architecture capture multi-resolution information leading to improved temporal modelling. We evaluate the proposed approaches on the MUSDB test dataset. In addition to providing an improved performance over the state-of-the-art, we also provide insights on the impact of different architectural choices on complex data-driven solutions for source separation.

Modern data analysis pipelines are becoming increasingly complex due to the presence of multi-view information sources. While graphs are effective in modeling complex relationships, in many scenarios a single graph is rarely sufficient to succinctly represent all interactions, and hence multi-layered graphs have become popular. Though this leads to richer representations, extending solutions from the single-graph case is not straightforward. Consequently, there is a strong need for novel solutions to solve classical problems, such as node classification, in the multi-layered case. In this paper, we consider the problem of semi-supervised learning with multi-layered graphs. Though deep network embeddings, e.g. DeepWalk, are widely adopted for community discovery, we argue that feature learning with random node attributes, using graph neural networks, can be more effective. To this end, we propose to use attention models for effective feature learning, and develop two novel architectures, GrAMME-SG and GrAMME-Fusion, that exploit the inter-layer dependencies for building multi-layered graph embeddings. Using empirical studies on several benchmark datasets, we evaluate the proposed approaches and demonstrate significant performance improvements in comparison to state-of-the-art network embedding strategies. The results also show that using simple random features is an effective choice, even in cases where explicit node attributes are not available.

With widespread adoption of electronic health records, there is an increased emphasis for predictive models that can effectively deal with clinical time-series data. Powered by Recurrent Neural Network (RNN) architectures with Long Short-Term Memory (LSTM) units, deep neural networks have achieved state-of-the-art results in several clinical prediction tasks. Despite the success of RNNs, its sequential nature prohibits parallelized computing, thus making it inefficient particularly when processing long sequences. Recently, architectures which are based solely on attention mechanisms have shown remarkable success in transduction tasks in NLP, while being computationally superior. In this paper, for the first time, we utilize attention models for clinical time-series modeling, thereby dispensing recurrence entirely. We develop the \textit{SAnD} (Simply Attend and Diagnose) architecture, which employs a masked, self-attention mechanism, and uses positional encoding and dense interpolation strategies for incorporating temporal order. Furthermore, we develop a multi-task variant of \textit{SAnD} to jointly infer models with multiple diagnosis tasks. Using the recent MIMIC-III benchmark datasets, we demonstrate that the proposed approach achieves state-of-the-art performance in all tasks, outperforming LSTM models and classical baselines with hand-engineered features., Comment: AAAI 2018

Sampling one or more effective solutions from large search spaces is a recurring idea in machine learning, and sequential optimization has become a popular solution. Typical examples include data summarization, sample mining for predictive modeling and hyper-parameter optimization. Existing solutions attempt to adaptively trade-off between global exploration and local exploitation, wherein the initial exploratory sample is critical to their success. While discrepancy-based samples have become the de facto approach for exploration, results from computer graphics suggest that coverage-based designs, e.g. Poisson disk sampling, can be a superior alternative. In order to successfully adopt coverage-based sample designs to ML applications, which were originally developed for 2-d image analysis, we propose fundamental advances by constructing a parameterized family of designs with provably improved coverage characteristics, and by developing algorithms for effective sample synthesis. Using experiments in sample mining and hyper-parameter optimization for supervised learning, we show that our approach consistently outperforms existing exploratory sampling methods in both blind exploration, and sequential search with Bayesian optimization.

A quantile is defined as a value below which random draws from a given distribution falls with a given probability. In a centralized setting where the cumulative distribution function (CDF) is unknown, the empirical CDF (ECDF) can be used to estimate such quantiles after aggregating the data. In a fully distributed sensor network, however, it is challenging to estimate quantiles. This is because each sensor node observes local measurement data with limited storage and data transmission power which make it difficult to obtain the global ECDF. This paper proposes consensus-based quantile estimation for such a distributed network. The states of the proposed algorithm are recursively updated with two-steps at each iteration: one is a local update based on the measurement data and the current state, and the other is averaging the updated states with neighboring nodes. We consider the realistic case of communication links between nodes being corrupted by independent random noise. It is shown that the estimated state sequence is asymptotically unbiased and converges toward the sample quantile in the mean-square sense. The two step-size sequences corresponding to the averaging and local update steps result in a mixed-time scale algorithm with proper decay rates in order to achieve convergence. We also provide applications to distributed estimation of trimmed mean, computation of median, maximum, or minimum values and identification of outliers through simulation.

Integrating sensing and machine learning is important in elevating precision in several Internet of Things (IoT) and mobile applications. In our Electrical Engineering classes, we have begun developing self-contained modules to train students in this area. We focus specifically in developing modules in machine learning including pre-processing, feature extraction and classification. We have also embedded in these modules software to provide hands-on training. In this paper, we describe our efforts to develop an online simulation environment that will support web-based laboratories for training undergraduate students from Electrical Engineering and other disciplines in sensors and machine learning. We also present our efforts to enable students to visualize and understand the inner workings of various machine learning algorithms along with descriptions of their performance with several types of synthetic and sensor data.

This study proposes a unifying framework for m-Health video communication systems that provides for the joint optimization of video quality, bitrate demands, and encoding time. The framework is video modality and infrastructure independent and facilitates adaptation to the best available encoding mode that satisfies underlying technology and application imposed constraints. The scalability of the proposed algorithm is demonstrated using different HEVC encoding configurations and realistic modelling of 802.11× wireless infrastructure for emergency scenery and response videos. Extensive experimentation shows that a jointly optimal solution in the encoding time, bitrate, and video quality space is feasible. © 2015 IEEE. 2015-November 173 176 Sponsors: Conference code: 116805 Cited By :4

Information divergence functions play a critical role in statistics and information theory. In this paper we show that a non-parametric f-divergence measure can be used to provide improved bounds on the minimum binary classification probability of error for the case when the training and test data are drawn from the same distribution and for the case where there exists some mismatch between training and test distributions. We confirm the theoretical results by designing feature selection algorithms using the criteria from these bounds and by evaluating the algorithms on a series of pathological speech classification tasks., 12 pages, 5 figures

Sparse representations with learned dictionaries have been successful in several image analysis applications. In this paper, we propose and analyze the framework of ensemble sparse models, and demonstrate their utility in image restoration and unsupervised clustering. The proposed ensemble model approximates the data as a linear combination of approximations from multiple \textit{weak} sparse models. Theoretical analysis of the ensemble model reveals that even in the worst-case, the ensemble can perform better than any of its constituent individual models. The dictionaries corresponding to the individual sparse models are obtained using either random example selection or boosted approaches. Boosted approaches learn one dictionary per round such that the dictionary learned in a particular round is optimized for the training examples having high reconstruction error in the previous round. Results with compressed recovery show that the ensemble representations lead to a better performance compared to using a single dictionary obtained with the conventional alternating minimization approach. The proposed ensemble models are also used for single image superresolution, and we show that they perform comparably to the recent approaches. In unsupervised clustering, experiments show that the proposed model performs better than baseline approaches in several standard datasets.

Java-DSP is a freely accessible web-based software, primarily used in signal processing education and research. In this paper, we present Java-DSP modules that have been developed for the study and analysis of the MPEG-1 Layer III algorithm. We have embedded JLayer1.0, an open source MP3 library, to Java-DSP and developed an intuitive interface to expose undergraduate and graduate students to the several modules in the encoding/decoding process. The Java-DSP MP3 decoder block is an interactive function which can be used to examine the characteristics and visualize outputs of different modules in the algorithm. Some of the important functions incorporated in the proposed interface include the analysis of the hybrid filter bank, polyphase filters and the window switching based on perceptual criteria. The MP3 algorithm represents a compelling framework for teaching certain aspects in DSP. We are using this module to introduce filter banks and windowing to undergraduate students. © 2011 IEEE. 168 173 Sponsors: Inst. Electr. Electron. Eng. (IEEE) Signal Process. Soc. Conference code: 84554 Cited By :1

Advances in video compression, network technologies, and computer technologies have contributed to the rapid growth of mobile health (m-health) systems and services. Wide deployment of such systems and services is expected in the near future, and it's foreseen that they will soon be incorporated in daily clinical practice. This study focuses in describing the basic components of an end-to-end wireless medical video telemedicine system, providing a brief overview of the recent advances in the field, while it also highlights future trends in the design of telemedicine systems that are diagnostically drivenv. © 2010 IEEE. 1045 1048 Conference code: 83008 Cited By :12

A relationship between the Fisher information and the characteristic function is established with the help of two inequalities. A necessary and sufficient condition for equality is found. These results are used to determine the asymptotic efficiency of a distributed estimation algorithm that uses constant modulus transmissions over Gaussian multiple access channels. The loss in efficiency of the distributed estimation scheme relative to the centralized approach is quantified for different sensing noise distributions. It is shown that the distributed estimator does not incur an efficiency loss if and only if the sensing noise distribution is Gaussian., Comment: Submitted to IEEE Transactions on Information Theory; 8 pages; 3 figures

This NSF Phase 3 CCLI multidisciplinary project consists of a collaborative implementation and national dissemination effort that involves Arizona State University (ASU), Johns Hopkins University (JHU), Prairie View A&M University, University of Washington-Bothell (UWB), Rose-Hulman Institute of Technology, University of New Mexico (UNM), and the University of Cyprus (UCY). The project involves significant educational technology innovations and software extensions that will enable the online software J-DSP to be used in multiple disciplines including digital signal processing, earth systems, renewable energy, biologically-inspired sensors, and arts and media. Problems addressed include the delivery of technologyenhanced laboratory experiences to undergraduate students using novel Java tools and the requirement of a broad assessment of these practices at several universities. © 2009 IEEE. Sponsors: American Society for Engineering Society, ASEE IEEE IEEE Computer Society ATM San Antonio College, SAC Conference code: 79825

Sponsors: BOEING Conference code: 77079

The intima-media thickness (IMT) of the common carotid artery (CCA) is widely used as an early indicator of cardiovascular disease (CVD). It was proposed but not thoroughly investigated that the media layer (ML), its composition and texture, may be indicative for identifying the risk of stroke and differentiating between patients of high and low risk. In this study we investigate the usefulness of texture analysis of the ML of the CCA. The study was performed on 100 longitudinal ultrasound images acquired from asymptomatic subjects at risk of atherosclerosis. The images were separated into three different age groups, namely below 50, 50 to 60, and above 60 years old. A total of 61 different texture features were extracted from the intima-media complex (IMC), ML and the intima layer (IL). The IMC and ML were segmented manually by a neurovascular expert and automatically by a snakes segmentation system. It was shown that texture features extracted from the IL, ML and IMC are significantly different (mean, gray scale median (GSM), standard deviation, contrast, difference variance, periodicity) and that some of them can be associated with the increase (difference variance, entropy) or decrease (GSM) of patient's age. It was also shown that the GSM of the ML falls linearly with increasing ML thickness (MLT) and with increasing age. Further research on more subjects is required for estimating other features that may provide information for patients at risk of stroke. Conference code: 77628

Περιέχει βιβλιογραφικές παραπομπές. Αριθμός δεδηλωμένων πηγών στη βιβλιογραφία: 141 Διατριβή (Διδακτορική) -- Πανεπιστήμιο Κύπρου, Σχολή Θετικών και Εφαρμοσμένων Επιστημών, Τμήμα Πληροφορικής, 2018. Η βιβλιοθήκη διαθέτει αντίτυπο της διατριβής σε έντυπη μορφή. Η πολύ-κλιμακωτή αποδόμηση μη στατικών εικόνων μέσω της αναπαράστασης AM-FM έχει αποδειχθεί ότι αποτελεί μια εύρωστη μεθοδολογία ανάλυσης εικόνων. Επιπλέον τα μοντέλα AM-FM έχουν συσχετισθεί με τα μαθηματικά μοντέλα του οπτικού φλοιού. Σε μια τυπική εφαρμογή AM-FM, η αποδόμηση γίνεται μέσω μίας οικογένειας φίλτρων Gabor, αφού προηγηθεί ο μετασχηματισμός Hilbert. Ωστόσο το ανθρώπινο οπτικό σύστημα είναι γνωστό ότι χρησιμοποιεί ένα μεγάλο αριθμό από φίλτρα Gabor τα οποία ξεπερνούν κατά πολύ τον αριθμό των φίλτρων μιας οικογένειας. Στην παρούσα διατριβή υποστηρίζουμε ότι η χρήση πολλαπλών οικογενειών φίλτρων μπορεί να οδηγήσει σε μεθοδολογίες αναπαράστασης AM-FM της εικόνας οι οποίες είναι αποδοτικότερες από τις τωρινές μεθοδολογίες αποδόμησης που κάνουν χρήση μόνο μιας οικογένειας φίλτρων. Για να ποσοτικοποιήσουμε τα πλεονεκτήματα της χρήσης πολλαπλών οικογενειών φίλτρων, εφαρμόζουμε τις μεθοδολογίες αναπαράστασης AM-FM σε πραγματικές εικόνες. Για το σκοπό αυτό αναπτύξαμε τρεις νέες μεθοδολογίες αποδόμησης AM-FM: α) τη μεθοδολογία αποδόμησης βασισμένη σε κλιμακωτή αύξηση της ποιότητας ανακατασκευής, β) τη μεθοδολογία κλιμακωτής αποδόμησης και γ) τη μεθοδολογία κατευθυνόμενης αποδόμησης. Από τα αποτελέσματα της εφαρμογής των προαναφερθεισών μεθοδολογιών είναι φανερό ότι η χρήση πολλαπλών οικογενειών φίλτρων προσφέρει σημαντικά οφέλη στην ακρίβεια εκτίμησης του στιγμιαίου πλάτους, της στιγμιαίας συχνότητας και της ποιότητας ανακατασκευής εν σύγκριση με κλασσικές μεθοδολογίες και με τη χρήση μιας οικογένειας φίλτρων. Επιπλέον εφαρμόσαμε τις προτεινόμενες μεθοδολογίες στην κατηγοριοποίηση του γυναικολογικού καρκίνου του ενδομήτριου με πολύ καλά αποτελέσματα. Multiscale AM-FM decompositions have provided effective methods for representing non-stationary content in digital images. Furthermore, AM-FM models have long been associated with mathematical models of the human visual system. In a standard application, AM-FM decompositions are derived from the outputs of a Gabor filterbank, after possible pre-filtering by a 2D Hilbert Transformer. Yet, the human visual system is known to use a large number of Gabor filters that significantly outnumber the ones found in a single filterbank. In this dissertation it is documented that the use of multiple Gabor filterbanks can lead into more efficient image representations that perform significantly better compared to the current use of a single Gabor filterbank. To quantify the advantages of using multiple filterbanks, the thesis explores their application in the computation of multiscale AM-FM decompositions and the analysis of real images. For this purpose, we developed three new AM-FM decomposition methodologies: a) a decomposition methodology based on a stepwise scalable-quality increase in the reconstruction quality, b) a multiscale decomposition methodology and c) a directional decomposition methodology. From the results of the application of the above-mentioned methodologies it is evident that the use of multiple families of filterbanks offers significant benefits to the precision of estimating the instantaneous amplitude, instantaneous frequency and reconstruction quality as compared to conventional methodologies and using only one family of filterbanks. We also applied the proposed methodologies in the classification of gynecological endometrial cancer with very good results.

Includes bibliography (p. 167-176). Number of sources in the bibliography: 135 Thesis (Ph. D.) -- University of Cyprus, Faculty of Engineering, Department of Electrical and Computer Engineering, 2012. The University of Cyprus Library holds the printed form of the thesis. Η ανάγκη για την επεξεργασία και ταξινόμηση των σημάτων, συναντάται σε πολλές εφαρμογές. Τα σήματα είναι άφθονα στη φύση και μπορούν να προκύψουν από πολλές πηγές. Σε πολλές περιπτώσεις όμως, τα σήματα περιέχουν, επίσης, υψηλά επίπεδα θορύβου. Αυτό αποτελεί μια μοναδική πρόκληση κατά την επεξεργασία των σημάτων προκειμένου κάποιος να λάβει χρήσιμες πληροφορίες που απαιτούνται για την ταξινόμηση. Στην παρούσα εργασία, δείχνουμε ότι με τη χρήση ενός κατάλληλου μετασχηματισμού στην αναπαράσταση του σήματος και με πυρήνες (kernels), μπορούμε να ελαχιστοποιήσουμε την επίδραση του θορύβου. Περιγράφουμε ένα βιολογικά εμπνευσμένο σύστημα ταξινόμησης μέσα από το οποίο μπορούν να χαρακτηρισθούν διάφοροι τύποι σημάτων, χωρίς την ανάγκη για εκτεταμένη προ-επεξεργασία στο σήμα. Έχουμε εισαγάγει την έννοια των πυρήνων σειράς κατάταξης (rank order kernels) που χρησιμοποιούν κωδικοποίηση σειράς κατάταξης (rank order coding). H κωδικοποίηση σειράς κατάταξης είναι ένα είδος κωδικοποίησης που έχει προταθεί ως μια πιθανή εξήγηση για το πώς οι νευρώνες κωδικοποιούν πληροφορίες. Έχουμε διαμορφώσει ένα μέτρο με βάση τα τους πυρήνες και το χρησιμοποιούμε για ταξινόμηση. Εστιάζουμε την προσοχή μας στο πρόβλημα της αυτόματης αναγνώρισης ομιλίας, προκειμένου να αποδείξουμε την ικανότητα του συστήματος ταξινόμησης. Η αναγνώριση της ομιλίας είναι ένα σημαντικό στοιχείο στην επικοινωνία του ανθρώπου με τον υπολογιστή. Ένα από τα κύρια εμπόδια είναι το πρόβλημα του θορύβου. Με τη μεθοδολογία μας, έχουμε μετατρέψει τα σήματα ομιλίας σε δύο διαστάσεις. Δημιουργούμε αναπαραστάσεις χρόνου-συχνότητας και τις ταξινομούμε με τους πυρήνες. Στην προσπάθειά μας να δημιουργήσουμε το σύστημα αναγνώρισης ομιλίας βρήκαμε ότι ήταν επίσης αναγκαίο να αναπτυχθεί ένα σύστημα ανίχνευσης τελικών σημείων (endpoint detection). Στην παρούσα εργασία παρουσιάζεται ως εκ τούτου, επίσης, ένα σύστημα ανίχνευσης τελικών σημείων το οποίο χρησιμοποιεί φασματογράφημα της φωνής και πυρήνες διακύμανσης (variance kernels) προκειμένου να διαχωρίσει την ομιλία από την μη-ομιλία. Το σύστημα ανίχνευσης τελικών σημείων χρησιμοποιείται ως προ-επεξεργασία για την ομιλία στο σύστημα αναγνώρισης. Ο αλγόριθμος για την ανίχνευση τελικών σημείων και οι πυρήνες σειράς κατάταξης μπορούν επίσης να εφαρμοστούν και σε άλλα είδη σημάτων. Έχουμε δείξει πώς ο αλγόριθμος ανίχνευσης τελικών σημείων μπορεί να χρησιμοποιηθεί για υπερηχητικά σήματα, και οι πυρήνες σειράς κατάταξης μπορούν να χρησιμοποιηθούν για την ταξινόμηση φασμάτων Ράμαν (Raman). The need to process and classify signals is encountered in many applications. Signals are abundant in nature and can arise from numerous sources. In many cases however, signals also contain high levels of noise. This poses a unique challenge when processing the signals in order to obtain useful information needed for classification. In this thesis, we show that by using an appropriate representation transformation of the signal and by kernel-based feature-extraction methods, we can mitigate the effect of noise. We describe a biologically-inspired classification system which can classify various types of noisy signals, without the need to perform extensive pre-processing on the signal. We introduce the concept of rank order kernels which employ rank order coding. Rank order coding is a type of temporal coding which has been proposed as a possible explanation of how neurons encode information. We formulate an image distance metric based on rank order kernels and use it for classification. We focus on the problem of Automatic Speech Recognition (ASR) in order to demonstrate the capability of our classification system. The accurate recognition of speech is a vital element in human-computer interfaces. One of the main obstacles to building robust ASR systems is the problem of noise. With our methodology, we transform speech signals to two-dimensional time-frequency image representations and classify them using the rank order kernel distance metric. In our attempt to create a noise-robust speech recognition system we found that it was also necessary to develop an endpoint detection system which was also robust to noise. This thesis therefore also presents an endpoint detection system which uses a spectrogram representation of speech and variance kernels in order to separate speech from non-speech. Our endpoint detection system is used as a pre-processing step to our speech recognition system. Our endpoint detection algorithm and rank order kernel method can also be applied to other types of signals. We show how the endpoint detection algorithm is used to detect the endpoints of micro-Doppler signatures in ultrasound signals, and how the rank order kernels can be used to classify Raman spectra obtained from bacterial samples. The classification system we develop in this thesis can be used on any type of signal by first converting the signal to an appropriate two-dimensional image representation and then performing classification using the rank order kernel distance metric.

Includes bibliography (p. 167-176). Number of sources in the bibliography: 135 Thesis (Ph. D.) -- University of Cyprus, Faculty of Engineering, Department of Electrical and Computer Engineering, 2012. The University of Cyprus Library holds the printed form of the thesis. Η ανάγκη για την επεξεργασία και ταξινόμηση των σημάτων, συναντάται σε πολλές εφαρμογές. Τα σήματα είναι άφθονα στη φύση και μπορούν να προκύψουν από πολλές πηγές. Σε πολλές περιπτώσεις όμως, τα σήματα περιέχουν, επίσης, υψηλά επίπεδα θορύβου. Αυτό αποτελεί μια μοναδική πρόκληση κατά την επεξεργασία των σημάτων προκειμένου κάποιος να λάβει χρήσιμες πληροφορίες που απαιτούνται για την ταξινόμηση. Στην παρούσα εργασία, δείχνουμε ότι με τη χρήση ενός κατάλληλου μετασχηματισμού στην αναπαράσταση του σήματος και με πυρήνες (kernels), μπορούμε να ελαχιστοποιήσουμε την επίδραση του θορύβου. Περιγράφουμε ένα βιολογικά εμπνευσμένο σύστημα ταξινόμησης μέσα από το οποίο μπορούν να χαρακτηρισθούν διάφοροι τύποι σημάτων, χωρίς την ανάγκη για εκτεταμένη προ-επεξεργασία στο σήμα. Έχουμε εισαγάγει την έννοια των πυρήνων σειράς κατάταξης (rank order kernels) που χρησιμοποιούν κωδικοποίηση σειράς κατάταξης (rank order coding). H κωδικοποίηση σειράς κατάταξης είναι ένα είδος κωδικοποίησης που έχει προταθεί ως μια πιθανή εξήγηση για το πώς οι νευρώνες κωδικοποιούν πληροφορίες. Έχουμε διαμορφώσει ένα μέτρο με βάση τα τους πυρήνες και το χρησιμοποιούμε για ταξινόμηση. Εστιάζουμε την προσοχή μας στο πρόβλημα της αυτόματης αναγνώρισης ομιλίας, προκειμένου να αποδείξουμε την ικανότητα του συστήματος ταξινόμησης. Η αναγνώριση της ομιλίας είναι ένα σημαντικό στοιχείο στην επικοινωνία του ανθρώπου με τον υπολογιστή. Ένα από τα κύρια εμπόδια είναι το πρόβλημα του θορύβου. Με τη μεθοδολογία μας, έχουμε μετατρέψει τα σήματα ομιλίας σε δύο διαστάσεις. Δημιουργούμε αναπαραστάσεις χρόνου-συχνότητας και τις ταξινομούμε με τους πυρήνες. Στην προσπάθειά μας να δημιουργήσουμε το σύστημα αναγνώρισης ομιλίας βρήκαμε ότι ήταν επίσης αναγκαίο να αναπτυχθεί ένα σύστημα ανίχνευσης τελικών σημείων (endpoint detection). Στην παρούσα εργασία παρουσιάζεται ως εκ τούτου, επίσης, ένα σύστημα ανίχνευσης τελικών σημείων το οποίο χρησιμοποιεί φασματογράφημα της φωνής και πυρήνες διακύμανσης (variance kernels) προκειμένου να διαχωρίσει την ομιλία από την μη-ομιλία. Το σύστημα ανίχνευσης τελικών σημείων χρησιμοποιείται ως προ-επεξεργασία για την ομιλία στο σύστημα αναγνώρισης. Ο αλγόριθμος για την ανίχνευση τελικών σημείων και οι πυρήνες σειράς κατάταξης μπορούν επίσης να εφαρμοστούν και σε άλλα είδη σημάτων. Έχουμε δείξει πώς ο αλγόριθμος ανίχνευσης τελικών σημείων μπορεί να χρησιμοποιηθεί για υπερηχητικά σήματα, και οι πυρήνες σειράς κατάταξης μπορούν να χρησιμοποιηθούν για την ταξινόμηση φασμάτων Ράμαν (Raman). The need to process and classify signals is encountered in many applications. Signals are abundant in nature and can arise from numerous sources. In many cases however, signals also contain high levels of noise. This poses a unique challenge when processing the signals in order to obtain useful information needed for classification. In this thesis, we show that by using an appropriate representation transformation of the signal and by kernel-based feature-extraction methods, we can mitigate the effect of noise. We describe a biologically-inspired classification system which can classify various types of noisy signals, without the need to perform extensive pre-processing on the signal. We introduce the concept of rank order kernels which employ rank order coding. Rank order coding is a type of temporal coding which has been proposed as a possible explanation of how neurons encode information. We formulate an image distance metric based on rank order kernels and use it for classification. We focus on the problem of Automatic Speech Recognition (ASR) in order to demonstrate the capability of our classification system. The accurate recognition of speech is a vital element in human-computer interfaces. One of the main obstacles to building robust ASR systems is the problem of noise. With our methodology, we transform speech signals to two-dimensional time-frequency image representations and classify them using the rank order kernel distance metric. In our attempt to create a noise-robust speech recognition system we found that it was also necessary to develop an endpoint detection system which was also robust to noise. This thesis therefore also presents an endpoint detection system which uses a spectrogram representation of speech and variance kernels in order to separate speech from non-speech. Our endpoint detection system is used as a pre-processing step to our speech recognition system. Our endpoint detection algorithm and rank order kernel method can also be applied to other types of signals. We show how the endpoint detection algorithm is used to detect the endpoints of micro-Doppler signatures in ultrasound signals, and how the rank order kernels can be used to classify Raman spectra obtained from bacterial samples. The classification system we develop in this thesis can be used on any type of signal by first converting the signal to an appropriate two-dimensional image representation and then performing classification using the rank order kernel distance metric.