Showing papers by "Andreas Spanias published in 2015"

Kernel sparse models for automated tumor segmentation

Abstract: A robust method to automatically segment and identify tumor regions in medical images is extremely valuable for clinical diagnosis and disease modeling. In various embodiments, an efficient algorithm uses sparse models in feature spaces to identify pixels belonging to tumorous regions. By fusing both intensity and spatial location information of the pixels, this technique can automatically localize tumor regions without user intervention. Using a few expert-segmented training images, a sparse coding-based classifier is learned. For a new test image, the sparse code obtained from every pixel is tested with the classifier to determine if it belongs to a tumor region. Particular embodiments also provide a highly accurate, low-complexity procedure for cases when the user can provide an initial estimate of the tumor in a test image.

Learning Stable Multilevel Dictionaries for Sparse Representations

Abstract: Sparse representations using learned dictionaries are being increasingly used with success in several data processing and machine learning applications. The increasing need for learning sparse models in large-scale applications motivates the development of efficient, robust, and provably good dictionary learning algorithms. Algorithmic stability and generalizability are desirable characteristics for dictionary learning algorithms that aim to build global dictionaries, which can efficiently model any test data similar to the training samples. In this paper, we propose an algorithm to learn dictionaries for sparse representations from large scale data, and prove that the proposed learning algorithm is stable and generalizable asymptotically. The algorithm employs a 1-D subspace clustering procedure, the $K$ -hyperline clustering, to learn a hierarchical dictionary with multiple levels. We also propose an information-theoretic scheme to estimate the number of atoms needed in each level of learning and develop an ensemble approach to learn robust dictionaries. Using the proposed dictionaries, the sparse code for novel test data can be computed using a low-complexity pursuit procedure. We demonstrate the stability and generalization characteristics of the proposed algorithm using simulations. We also evaluate the utility of the multilevel dictionaries in compressed recovery and subspace learning applications.

Robust Consensus in the Presence of Impulsive Channel Noise

Abstract: A distributed average consensus algorithm robust to a wide range of impulsive channel noise distributions is proposed. This work is the first of its kind in the literature to propose a consensus algorithm which relaxes the requirement of finite moments on the communication noise. It is shown that the nodes reach consensus asymptotically to a finite random variable whose expectation is the desired sample average of the initial observations with a variance that depends on the step size of the algorithm and the receiver nonlinear function. The asymptotic performance is characterized by deriving the asymptotic covariance matrix using results from stochastic approximation theory. Simulations corroborate our analytical findings and highlight the robustness of the proposed algorithm.

Within and cross-corpus speech emotion recognition using latent topic model-based features

Abstract: Owing to the suprasegmental behavior of emotional speech, turn-level features have demonstrated a better success than frame-level features for recognition-related tasks. Conventionally, such features are obtained via a brute-force collection of statistics over frames, thereby losing important local information in the process which affects the performance. To overcome these limitations, a novel feature extraction approach using latent topic models (LTMs) is presented in this study. Speech is assumed to comprise of a mixture of emotion-specific topics, where the latter capture emotionally salient information from the co-occurrences of frame-level acoustic features and yield better descriptors. Specifically, a supervised replicated softmax model (sRSM), based on restricted Boltzmann machines and distributed representations, is proposed to learn naturally discriminative topics. The proposed features are evaluated for the recognition of categorical or continuous emotional attributes via within and cross-corpus experiments conducted over acted and spontaneous expressions. In a within-corpus scenario, sRSM outperforms competing LTMs, while obtaining a significant improvement of 16.75% over popular statistics-based turn-level features for valence-based classification, which is considered to be a difficult task using only speech. Further analyses with respect to the turn duration show that the improvement is even more significant, 35%, on longer turns (>6 s), which is highly desirable for current turn-based practices. In a cross-corpus scenario, two novel adaptation-based approaches, instance selection, and weight regularization are proposed to reduce the inherent bias due to varying annotation procedures and cultural perceptions across databases. Experimental results indicate a natural, yet less severe, deterioration in performance - only 2.6% and 2.7%, thereby highlighting the generalization ability of the proposed features.

Adaptive emergency scenery video communications using HEVC for responsive decision support in disaster incidents

Abstract: 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.

Multipath Effects in GPS Receivers: A Primer

Abstract: Autonomous vehicles use global navigation satellite systems (GNSS) to provide a position within a few centimeters of truth. Centimeter positioning requires accurate measurement of each satellite's direct path propagation time. Multipath corrupts the propagation time estimate by creating a time-varying bias. A GNSS receiver model is developed and the effects of multipath are investigated. MATLABtm code is provided to enable readers to run simple GNSS receiver simulations. More specifically, GNSS signal models are presented and multipath mitigation techniques are described for various multipath conditions. Appendices are included in the booklet to derive some of the basics on early minus late code synchronization methods. Details on the numerically controlled oscillator and its properties are also given in the appendix.

Advances in speech and audio processing and coding

Abstract: This plenary session will cover speech processing research advances with the emphasis on speech and audio coding methods. In the session, we will discuss the fundamental principles, techniques, and algorithms used in current coding applications including a summary of codecs for telecommunication standards. The session will start with a discussion on: the basic speech representation methods, the performance measures used to evaluate coded speech, and the role of the standards. Brief algorithm descriptions include: ADPCM, sub-band coding, adaptive transform coding, sinusoidal transform coding (STC), linear predictive coding (LPC), and analysis-by-synthesis LPC (sparse excitation, code excited LPC, and ACELP). The presentation will feature audio, and computer demonstrations of recent speech coding standards including voice-over IP algorithms. The plenary session will also cover wideband audio standards such as MPEG audio and other layers (e.g., MP3, AAC). Recent algorithms will also be described including the following: Variable-Rate Multimode Wideband (VMR-WB), Speex, G722.1, OGG Vorbis 2012, iLBC, SELT, SILK, Opus 2013, Qualcomm wideband 5G codecs. At the end of the session, we will cover briefly recent applications that use voice features for detecting speech pathologies, and also discuss how long-term speech parameters can be used as predictors of other diseases such as tremors, Alzheimer's etc.

Node counting in wireless sensor networks

Abstract: A distributed consensus algorithm for estimating the number of nodes in a wireless sensor network in the presence of communication noise is proposed. The idea is based on estimating the norm of available samples at nodes. Each node generates its own random initial measurements and updates its state by only communicating with its neighbors: the algorithm is fully distributed with no assumptions about the structure of the network. We also show that there is a trade-off between the estimation error and the storage at each node.

Nonlinear diffusion adaptation with bounded transmission over distributed networks

Abstract: This paper introduces diffusion adaptation strategies over distributed networks with nonlinear transmissions, motivated by the necessity for bounded transmit power. Local information is exchanged in real-time with neighboring nodes in order to estimate a common parameter vector via constrained nonlinear transmissions, using an adaptive learning algorithm. We propose nonlinear diffusion strategies for such an adaptive estimation. We will study convergence properties of the proposed algorithm in the mean and the mean-square sense. Simulations support the performance analysis and show that the proposed algorithm performs close to the linear case with the added advantage of power savings.

Removing data with noisy responses in regression analysis

Abstract: In regression analysis, outliers in the data can induce a bias in the learned function, resulting in larger errors. In this paper we derive an empirically estimable bound on the regression error based on a Euclidean minimum spanning tree generated from the data. Using this bound as motivation, we propose an iterative approach to remove data with noisy responses from the training set. We evaluate the performance of the algorithm on experiments with real-world pathological speech (speech from individuals with neurogenic disorders). Comparative results show that removing noisy examples during training using the proposed approach yields better predictive performance on out-of- sample data.

Nonlinear Amplify-and-Forward Distributed Estimation Over Nonidentical Channels

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.

Irradiance estimation for a smart PV array

Abstract: Electrical mismatch between modules in a PV array due to partial shading causes energy losses beyond the shaded module. This occurs because unshaded modules are forced to operate away from their maximum power point in order to compensate for the shading. Here we present an irradiance estimation algorithm for use in a mismatch mitigation system. Irradiance is estimated using measurements of module voltage, current, and back surface temperature. These estimates may be used to optimize an array's electrical configuration and reduce the mismatch losses caused by partial shading. Propagation of error in the estimation is examined; we find that accuracy is sufficient for use in the proposed mismatch mitigation application.

A New Asymmetric Correlation Kernel for GNSS Multipath Mitigation

Abstract: Multipath is the dominant error source in precise positioning Global Navigation Satellite Systems (GNSS) such as the United States Global Positioning System (GPS). These systems utilize the satellite signal time of arrival estimates to solve for position. Multipath corrupts the time of arrival estimates by distorting the signal tracking phase discriminator; which results in a slowly time- varying phase bias. This bias ranges from several centimeters to tens of meters. The submeter bias is the most problematic for centimeter positioning systems. Moreover, in addition to multipath, the GPS spread spectrum code is unbalanced for certain space vehicles which can lead to a code tracking phase bias. A new correlation kernel is proposed as part of a multipath mitigating delay-locked- loop code phase discriminator that does not suffer a tracking bias due to unbalanced spreading codes. This new algorithm performance is compared to existing techniques with respect to position bias and robustness.

An introductory signal processing course offered across the curriculum

Abstract: Signal processing algorithms and DSP chips are embedded nearly in every application that involves natural signal or data analysis and/or synthesis. Applications of digital signal processing (DSP) in engineering include electrical, mechanical, chemical, industrial and biomedical systems. Applications in other areas include entertainment, financial, health, computing, manufacturing, to name a few. At ASU we developed an elective course for an undergraduate program called Digital Culture that includes gaming, smart stages, computer music, visualization and other applications. We have offered the course online to arts majors in 2013. We begun adding multidisciplinary application content to this course and offered it again in 2015 as a hybrid online course with compulsory weekly on-campus sessions. Arrangements are being made to include it as an elective course in information management systems, computer informatics, mechanical engineering, and biomedical informatics. The course now includes several introductory topics in signal processing covered mostly at a qualitative and block diagram level; we added several simulations in MATLAB and in Java-DSP. The course covers basics of DSP starting from time and frequency domain analysis and sampling. It then covers digital FIR ad IIR filters and the FFT. About one third of the course covers applications which introduce qualitative descriptions of some advanced topics. For example, linear prediction and coding of speech are described at the block diagram level with MATLAB and Java simulations. Extensions to 2-D signal processing are covered as well with the focus on JPEG and MPEG applications. The syllabus, simulations and preliminary assessments of this course are presented in the paper.

A new signal processing course for digital culture

Abstract: Signal processing algorithms, software, and hardware are being used in several fields including non-engineering areas such as arts and media. Students in these fields and particularly in the new Digital Culture major at Arizona State University (ASU) use signal processing tools in several of their projects and artistic endeavors. Yet the blind use of these DSP tools in other disciplines, without understanding their properties has been a long-standing problem. In fact, the broader issue is the disconnect between engineers that develop tools and artists that use them to design the next generation digital art applications. In that context, ASU has formed the Arts Media and Engineering (AME) School and more recently, the multidisciplinary undergraduate Digital Culture degree granting program. In order to provide formal training in signal processing to students that are non-Electrical Engineering majors, we piloted a new course titled Signal Processing for Digital Culture. This course, which is being offered online, teaches non-majors some of the basics of signal processing and covers several applications. The only prerequisite to the course is general sophomore calculus. This new online course contains several topics and is focused on an approach that teaches concepts by connecting theory to compelling applications. Future plans include introducing this course at Clarkson University as a Knowledge Area course open to students from all majors.

Fast computation of excitation pattern, auditory pattern and loudness

Abstract: A method includes the steps of calculating a power spectrum from an auditory stimulus, filtering the power spectrum to obtain an effective power spectrum, calculating an intensity pattern from the effective power spectrum, calculating a median intensity pattern from the intensity pattern, determining an initial set of pruned detector locations, examining the initial set of pruned detector locations to determine an enhanced set of pruned detector locations, and calculating an excitation pattern from the effective power spectrum using the enhanced set of pruned detector locations. By determining the enhanced set of pruned detector locations from the initial set of pruned detector locations and computing the excitation pattern therefrom, the computational complexity of the above method can be significantly reduced when compared to conventional approaches while maintaining the accuracy thereof.

Audio modeling and loudness estimation with IJDSP mobile simulations

Abstract: Audio signal modeling and simulation is important in several coding, noise removal, and recognition applications. This paper focuses on implementing models for loudness estimation and their use in estimating parameters on iOS mobile devices (iPhones and iPads). We briefly address estimating excitation patterns and loudness through auditory models. These loudness estimation and other algorithms were implemented in the award winning educational iOS app iJDSP for performing DSP simulations on mobile devices. The modules were introduced to graduate students in the general signal processing area, to evaluate their effectiveness as teaching tools. The evaluation process involved giving the students a pre-quiz, guiding them through hands-on activities on the iOS app, and finally, a post-quiz. Assessments results were positive with noticeable improvement of student understanding of topics such as spectrograms and linear predictive coding.

Undergraduate Signal Processing Laboratories for the Android Operating System

Abstract: We present a DSP simulation environment that will enable students to perform laboratory exercises using Android mobile devices and tablets. Due to the pervasive nature of the mobile technology, education applications designed for mobile devices have the potential to stimulate student interest in addition to offering convenient access and interaction capabilities. This paper describes a portable signal processing laboratory for the Android platform. This software is intended to be an educational tool for students and instructors in DSP, and signals and systems courses. The development of Android JDSP (A-JDSP) is carried out using the Android SDK, which is a Java-based open source development platform. The proposed application contains basic DSP functions for convolution, sampling, FFT, filtering and frequency domain analysis, with a convenient graphical user interface. A description of the architecture, functions and planned assessments are presented in this paper.