Search

Your search keyword '"Spanias, Andreas"' showing total 761 results
Start Over Author "Spanias, Andreas"

Refine your results

more »

more »

more »

more »
761 results on '"Spanias, Andreas"'

751. Online Modules to Introduce Students to Solar Array Control using Neural Nets.

Author

Narayanaswamy, Vivek Sivaraman, Shanthamallu, Uday Shankar, Dixit, Abhinav, Rao, Sunil, Ayyanar, Raja, Tepedelenlioglu, Cihan, Spanias, Andreas S., Banavar, Mahesh K., Katoch, Sameeksha, Pedersen, Emma, Spanias, Photini, Turaga, Pavan, and Khondoker, Farib

Abstract

The growth in the field of machine learning (ML) can be attributed in part to the success of several algorithms such as neural networks as well as the availability of cloud computing resources. Recently, neural networks combined with signal processing analytics have found applications in renewable energy systems. With machine learning tools for solar array systems becoming popular, there is a need to train undergraduate students on these concepts and tools. In our undergraduate signal processing classes, we have developed self-contained modules to train students in this field. We specifically focused on developing modules with built-in software for applying neural nets (NN) to solar array systems where the NNs are used for solar panel fault detection and solar array connection topology optimization which are essentially ML classification tasks. We initially developed software modules in MATLAB and also developed these models on the user-friendly HTML-5 JavaDSP (JDSP) online simulation environment. J-DSP allows us to create and disseminate web-based laboratory exercises to train undergraduate students from different disciplines, in neural network applications. In this paper, we describe our efforts to enable students understand the properties of the main features of the data used, the types of ML algorithms that can be applied on solar energy systems, and the statistics of the overall results. The modules are injected in our undergraduate DSP class. The project outcomes are assessed using pre and post quizzes and student interviews. [ABSTRACT FROM AUTHOR]

Published
2019

752. Coverage-Based Designs Improve Sample Mining and Hyperparameter Optimization.

Author

Muniraju, Gowtham, Kailkhura, Bhavya, Thiagarajan, Jayaraman J., Bremer, Peer-Timo, Tepedelenlioglu, Cihan, and Spanias, Andreas

Subjects
*SUPERVISED learning, *COMPUTER graphics, *MACHINE learning, *MINES & mineral resources, *IMAGE analysis, *PREDICTION models, *EXPLORATORY factor analysis
Abstract

Sampling one or more effective solutions from large search spaces is a recurring idea in machine learning (ML), and sequential optimization has become a popular solution. Typical examples include data summarization, sample mining for predictive modeling, and hyperparameter optimization. Existing solutions attempt to adaptively trade off between global exploration and local exploitation, in which 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 developing algorithms for effective sample synthesis. Using experiments in sample mining and hyperparameter optimization for supervised learning, we show that our approach consistently outperforms the existing exploratory sampling methods in both blind exploration and sequential search with Bayesian optimization. [ABSTRACT FROM AUTHOR]

Published
2021
Full Text
View/download PDF

753. GrAMME: Semisupervised Learning Using Multilayered Graph Attention Models.

Author

Shanthamallu, Uday Shankar, Thiagarajan, Jayaraman J., Song, Huan, and Spanias, Andreas

Subjects
*INFORMATION resources, *ARTIFICIAL neural networks, *DATA analysis, *MACHINE learning
Abstract

Modern data analysis pipelines are becoming increasingly complex due to the presence of multiview 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, multilayered 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 multilayered case. In this article, we consider the problem of semisupervised learning with multilayered 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 interlayer dependences for building multilayered graph embeddings. Using empirical studies on several benchmark data sets, we evaluate the proposed approaches and demonstrate significant performance improvements in comparison with the 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. [ABSTRACT FROM AUTHOR]

Published
2020
Full Text
View/download PDF

754. Optimizing Kernel Machines Using Deep Learning.

Author

Song, Huan, J. Thiagarajan, Jayaraman, Sattigeri, Prasanna, and Spanias, Andreas

Subjects
*DEEP learning, *KERNEL (Mathematics)
Abstract

Building highly nonlinear and nonparametric models is central to several state-of-the-art machine learning systems. Kernel methods form an important class of techniques that induce a reproducing kernel Hilbert space (RKHS) for inferring non-linear models through the construction of similarity functions from data. These methods are particularly preferred in cases where the training data sizes are limited and when prior knowledge of the data similarities is available. Despite their usefulness, they are limited by the computational complexity and their inability to support end-to-end learning with a task-specific objective. On the other hand, deep neural networks have become the de facto solution for end-to-end inference in several learning paradigms. In this paper, we explore the idea of using deep architectures to perform kernel machine optimization, for both computational efficiency and end-to-end inferencing. To this end, we develop the deep kernel machine optimization framework, that creates an ensemble of dense embeddings using Nyström kernel approximations and utilizes deep learning to generate task-specific representations through the fusion of the embeddings. Intuitively, the filters of the network are trained to fuse information from an ensemble of linear subspaces in the RKHS. Furthermore, we introduce the kernel dropout regularization to enable improved training convergence. Finally, we extend this framework to the multiple kernel case, by coupling a global fusion layer with pretrained deep kernel machines for each of the constituent kernels. Using case studies with limited training data, and lack of explicit feature sources, we demonstrate the effectiveness of our framework over conventional model inferencing techniques. [ABSTRACT FROM AUTHOR]

Published
2018
Full Text
View/download PDF

755. Nonlinear Amplify-and-Forward Distributed Estimation Over Nonidentical Channels.

Author

Santucci, Robert, Banavar, Mahesh K., Tepedelenlioglu, Cihan, and Spanias, Andreas

Subjects
*ADDITIVE white Gaussian noise channels, *TRANSMITTERS (Communication), *MULTIPLE access protocols (Computer network protocols), *ELECTRONIC amplifiers, *RADIO frequency, *DISTRIBUTED amplifiers
Abstract

This paper presents the use of nonlinear distributed estimation in a wireless system transmitting over channels with random gains. Specifically, we discuss the development of estimators and analytically determine their attainable variance for two conditions: 1) when full channel state information (CSI) is available at the transmitter and receiver; and 2) when only channel gain statistics and phase information are available. For the case where full CSI is available, we formulate an optimization problem to allocate power among each of the transmitting sensors while minimizing the estimate variance. We show that minimizing the estimate variance when the transmitter is operating in its most nonlinear region can be formulated in a manner very similar to optimizing sensor gains with full CSI and linear transmitters. Furthermore, we show that the solution to this optimization problem in most scenarios is approximately equivalent to one of two low-complexity power allocation systems. [ABSTRACT FROM AUTHOR]

Published
2015
Full Text
View/download PDF

756. Efficient image representations using multiscale AM-FM decompositions derived from multiple Gabor filterbanks and medical applications

Author

Παττίχης, Κωνσταντίνος, Χριστοδούλου, Χρίστος, Χρυσάνθου, Γιώργος, Κωνσταντινίδης, Αντώνης, Σπανιάς, Ανδρέας, Pattichis, Constantinos, Christodoulou, Christos, Chrysanthou, Yiorgos, Konstantinides, Antones, Spanias, Andreas, Πανεπιστήμιο Κύπρου, Σχολή Θετικών και Εφαρμοσμένων Επιστημών, Τμήμα Πληροφορικής, University of Cyprus, Faculty of Pure and Applied Sciences, Department of Computer Science, and Παττίχης, Κωνσταντίνος [0000-0003-1271-8151]

Subjects
DECOMPOSITION, Imaging systems -- Image quality, ΑΠΟΔΟΜΗΣΗ, ΚΛΙΜΑΚΩΤΗ ΑΠΟΔΟΜΗΣΗ, ΚΑΤΕΥΘΥΝΟΜΕΝΗ ΑΠΟΔΟΜΗΣΗ, ΑΝΑΠΑΡΑΣΤΑΣΗ AM-FM, MULTIPLE GABOR FILTERBANKS, ΚΛΙΜΑΚΩΤΗΣ ΠΟΙΟΤΗΤΑΣ ΑΠΟΔΟΜΗΣΗ, SCALABLE DECOMPOSITION, Image compression -- Standards, AM-FM REPRESENTATION, Image processing, ΠΟΛΛΑΠΛΕΣ ΟΙΚΟΓΕΝΕΙΕΣ ΦΙΛΤΡΩΝ GABOR, ΑΡΑΙΗ ΑΝΑΠΑΡΑΣΤΑΣΗ, SSIM, DIRECTIONAL DECOMPOSITION, Imaging systems, Computer vision, Decomposition method, SCALABLE QUALITY DECOMPOSITION, Image processing -- Digital techniques, SPARES REPRESENTATION
Abstract

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.

Published
2018

757. Ταξινόμηση ανθεκτική στο θόρυβο με τη χρήση πυρήνων σειράς κατάταξης

Author

Kyriakides, Alexandros M., Pitris, Constantinos, Πολυκάρπου, Μάριος, Πίτρης, Κωνσταντίνος, Σπανιάς, Ανδρέας, Παττίχης, Κωνσταντίνος, Γεωργίου, Ιούλιος, Polycarpou, Marios, Spanias, Andreas, Pattichis, Constantinos, Georgiou, Julius, Πανεπιστήμιο Κύπρου, Πολυτεχνική Σχολή, Τμήμα Ηλεκτρολόγων Μηχανικών και Μηχανικών Υπολογιστών, University of Cyprus, Faculty of Engineering, Department of Electrical and Computer Engineering, and Pitris, Constantinos [0000-0002-5559-1050]

Subjects
Neural networks (Computer science), ΤΑΞΙΝΟΜΗΣΗ, NOISE-ROBUSTNESS, RANK ORDER CODING, ΠΥΡΗΝΕΣ ΣΕΙΡΑΣ ΚΑΤΑΤΑΞΗΣ, Speech perception, Automatic speech recognition, ΚΩΔΙΚΟΠΟΙΗΣΗ ΣΕΙΡΑΣ ΚΑΤΑΤΑΞΗΣ, Speech processing systems, ΑΝΘΕΚΤΙΚΟΤΗΤΑ ΣΤΟ ΘΟΡΥΒΟ, Classification, RANK ORDER KERNELS
Abstract

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.

Published
2012

758. Empirically Estimable Classification Bounds Based on a Nonparametric Divergence Measure.

Author

Berisha V, Wisler A, Hero AO, and Spanias A

Abstract

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.

Published
2016
Full Text
View/download PDF

759. Multiple kernel sparse representations for supervised and unsupervised learning.

Author

Thiagarajan JJ, Ramamurthy KN, and Spanias A

Subjects
Cluster Analysis, Databases, Factual, Flowers, Algorithms, Artificial Intelligence, Image Processing, Computer-Assisted methods, Pattern Recognition, Automated methods
Abstract

In complex visual recognition tasks, it is typical to adopt multiple descriptors, which describe different aspects of the images, for obtaining an improved recognition performance. Descriptors that have diverse forms can be fused into a unified feature space in a principled manner using kernel methods. Sparse models that generalize well to the test data can be learned in the unified kernel space, and appropriate constraints can be incorporated for application in supervised and unsupervised learning. In this paper, we propose to perform sparse coding and dictionary learning in the multiple kernel space, where the weights of the ensemble kernel are tuned based on graph-embedding principles such that class discrimination is maximized. In our proposed algorithm, dictionaries are inferred using multiple levels of 1D subspace clustering in the kernel space, and the sparse codes are obtained using a simple levelwise pursuit scheme. Empirical results for object recognition and image clustering show that our algorithm outperforms existing sparse coding based approaches, and compares favorably to other state-of-the-art methods.

Published
2014
Full Text
View/download PDF

760. Modeling Pathological Speech Perception From Data With Similarity Labels.

Author

Berisha V, Liss J, Sandoval S, Utianski R, and Spanias A

Abstract

The current state of the art in judging pathological speech intelligibility is subjective assessment performed by trained speech pathologists (SLP). These tests, however, are inconsistent, costly and, oftentimes suffer from poor intra- and inter-judge reliability. As such, consistent, reliable, and perceptually-relevant objective evaluations of pathological speech are critical. Here, we propose a data-driven approach to this problem. We propose new cost functions for examining data from a series of experiments, whereby we ask certified SLPs to rate pathological speech along the perceptual dimensions that contribute to decreased intelligibility. We consider qualitative feedback from SLPs in the form of comparisons similar to statements "Is Speaker A's rhythm more similar to Speaker B or Speaker C?" Data of this form is common in behavioral research, but is different from the traditional data structures expected in supervised (data matrix + class labels) or unsupervised (data matrix) machine learning. The proposed method identifies relevant acoustic features that correlate with the ordinal data collected during the experiment. Using these features, we show that we are able to develop objective measures of the speech signal degradation that correlate well with SLP responses.

Published
2014
Full Text
View/download PDF

761. Selecting Disorder-Specific Features for Speech Pathology Fingerprinting.

Author

Berisha V, Sandoval S, Utianski R, Liss J, and Spanias A

Abstract

The general aim of this work is to learn a unique statistical signature for the state of a particular speech pathology. We pose this as a speaker identification problem for dysarthric individuals. To that end, we propose a novel algorithm for feature selection that aims to minimize the effects of speaker-specific features (e.g., fundamental frequency) and maximize the effects of pathology-specific features (e.g., vocal tract distortions and speech rhythm). We derive a cost function for optimizing feature selection that simultaneously trades off between these two competing criteria. Furthermore, we develop an efficient algorithm that optimizes this cost function and test the algorithm on a set of 34 dysarthric and 13 healthy speakers. Results show that the proposed method yields a set of features related to the speech disorder and not an individual's speaking style. When compared to other feature-selection algorithms, the proposed approach results in an improvement in a disorder fingerprinting task by selecting features that are specific to the disorder.

Published
2013
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results