Multiple Correlated Sources Research Articles

Deep Transfer Learning Based Stroke Risk Prediction

Abstract: Stroke is a medical condition that occurs when there is any blockage or bleeding of the blood vessels either interrupts or reduces the supply of blood to the brain. It causes the disability of multiple organs or unexpected death, if that patient’s recognise and address risks at the right time, up to 80% of stroke occurrences can be averted. With the advancement of machine learning in medical science, the early recognition of stroke is very much possible that plays a vital role in diagnosis and getting read of this life taking disease. But it requires large well-labeled data. Due to the strict privacy protection policy in health-care systems, stroke data is usually distributed among different hospitals in small pieces. In addition, the positive and negative instances of such data are extremely imbalanced. Transfer learning can solve small data issue by exploiting the knowledge of a correlated domain, especially when multiple sources of data are available. In this work, deep Transfer Learning based Stroke Risk Prediction scheme is proposed to exploit the knowledge structure from multiple correlated sources and used bayesian optimization for selecting the best parameter. This model is tested in synthetic and real-world scenarios and the random forest gives more accuracy than other models like support vector machines (SVM), decision trees (DT), random forests (RF) and voting classifiers. It also shows the potential of real-world deployment among multiple hospitals aided with 5 G/B5G infrastructures.

Spatial modeling of Mycobacterium tuberculosis transmission with dyadic genetic relatedness data.

Understanding factors that contribute to the increased likelihood of pathogen transmission between two individuals is important for infection control. However, analyzing measures of pathogen relatedness to estimate these associations is complicated due to correlation arising from the presence of the same individual across multiple dyadic outcomes, potential spatial correlation caused by unmeasured transmission dynamics, and the distinctive distributional characteristics of some of the outcomes. We develop two novel hierarchical Bayesian spatial methods for analyzing dyadic pathogen genetic relatedness data, in the form of patristic distances and transmission probabilities, that simultaneously address each of these complications. Using individual-level spatially correlated random effect parameters, we account for multiple sources of correlation between the outcomes as well as other important features of their distribution. Through simulation, we show the limitations of existing approaches in terms of estimating key associations of interest, and the ability of the new methodology to correct for these issues across datasets with different levels of correlation. All methods are applied to Mycobacterium tuberculosis data from the Republic of Moldova, where we identify previously unknown factors associated with disease transmission and, through analysis of the random effect parameters, key individuals, and areas with increased transmission activity. Model comparisons show the importance of the new methodology in this setting. The methods are implemented in the R package GenePair.

Heterogeneous spatial dynamic panels with an application to US housing data

ABSTRACT This paper proposes two models that incorporate both heterogeneity and multiple sources of spatial correlation for dynamic panels. One uses convex combinations of them to form a single weight matrix. The second one includes explicitly different spatial weight matrices to form a higher order model. We use a Bayesian scheme for model estimation by deriving the full conditional distributions of heterogeneous parameters. Our Monte Carlo experiments demonstrate their finite-sample performance relative to a baseline model. In our empirical study we find the importance of including both geographical and non-geographical information in capturing correlations in real house price growth in the United States.

Stroke Risk Prediction With Hybrid Deep Transfer Learning Framework

Stroke has become a leading cause of death and long-term disability in the world with no effective treatment. Deep learning-based approaches have the potential to outperform existing stroke risk prediction models, but they rely on large well-labeled data. Due to the strict privacy protection policy in health-care systems, stroke data is usually distributed among different hospitals in small pieces. In addition, the positive and negative instances of such data are extremely imbalanced. Transfer learning can solve small data issue by exploiting the knowledge of a correlated domain, especially when multiple source of data are available. In this work, we propose a novel Hybrid Deep Transfer Learning-based Stroke Risk Prediction (HDTL-SRP) scheme to exploit the knowledge structure from multiple correlated sources (i.e., external stroke data, chronic diseases data, such as hypertension and diabetes). The proposed framework has been extensively tested in synthetic and real-world scenarios, and it outperforms the state-of-the-art stroke risk prediction models. It also shows the potential of real-world deployment among multiple hospitals aided with 5G/B5G infrastructures.

Impact of Bit Allocation Strategies on Machine Learning Performance in Rate Limited Systems

Intelligent entities such as self-driving vehicles, with their data being processed by machine learning units (MLU), are developing into an intertwined part of networks. These units handle distorted input but their sensitivity to noisy observations varies for different input attributes. Since blind transport of massive data burdens the system, identifying and delivering relevant information to MLUs leads in improved system performance and efficient resource utilization. Here, we study the integer bit allocation problem for quantizing multiple correlated sources providing input of a MLU with a bandwidth constraint. Unlike conventional distance measures between original and quantized input attributes, a new Kullback-Leibler divergence based distortion measure is defined to account for accuracy of MLU decisions. The proposed criterion is applicable to many practical cases with no prior knowledge on data statistics and independent of selected MLU instance. Here, we examine an inverted pendulum on a cart with a neural network controller assuming scalar quantization. Simulation results present a significant performance gain, particularly for regions with smaller available bandwidth. Furthermore, the pattern of successful rate allocations demonstrates higher relevancy of some features for the MLU and the need to quantize them with higher accuracy.

Bit-Plane Coding in Extractable Source Coding: Optimality, Modeling, and Application to 360° Data

In extractable source coding, multiple correlated sources are jointly compressed but can be individually accessed in the compressed domain. Performance is measured in terms of storage and transmission rates. This problem has multiple applications in interactive video compression such as Free Viewpoint Television or navigation in 360° videos. In this letter, we analyze and improve a practical coding scheme. We consider a binarized coding scheme, which insures a low decoding complexity. First, we show that binarization does not impact the transmission rate but only slightly the storage with respect to a symbol based approach. Second, we propose a Q-ary symmetric model to represent the pairwise joint distribution of the sources instead of the widely used Laplacian model. Third, we introduce a novel pre-estimation strategy, which allows to infer the symbols of some bit planes without any additional data and therefore permits to reduce the storage and transmission rates. In the context of 360° images, the proposed scheme allows to save 14% and 34% bitrate in storage and transmission rates respectively.

Performance evaluation of different computational methods to estimate Wood’s lactation curve by nonlinear mixed-effects models

Nonlinear mixed-effects models allow modeling repeated measures over time. The fixed effects of these models allow incorporating covariates, whereas the random effects reflect the multiple sources of heterogeneity and correlation between and within the units. To estimate the parameters of these models, it is necessary to use iterative processes, which can be done through different approaches, some of which are applied by the statistical software SAS. In this work, through simulation, we studied the performance of the estimators of a Wood’s incomplete gamma function, obtained through three different methods: linearization method through a Taylor series expansion on the empirical best linear unbiased predictor of random effects, applied by the NLINMIX macro, and expansion around the expected value of random effects, applied by both the NLINMIX macro and the NLMIXED procedure. We also investigated the impact of an incorrect specification of the covariance matrix for random errors. The linearization method through a Taylor series expansion on the empirical best linear unbiased predictor of random effects, applied by the NLINMIX macro, provided estimators with good performance, approximately normally distributed and with biases lower than those obtained with the other methods, even when the covariance matrix for random errors was incorrectly specified.

Asymptotic independence of regenerative processes with a special dependence structure

We identify some conditions under which regenerative processes with a certain dependence structure among them are asymptotically independent. The result is applied to various models, in particular independent Levy processes with dependent secondary jumps at the origin (for example, workloads of parallel M/G/1 queues with server vacations), the asymptotic performance of systems with multiple correlated sources that generate real-time status updates measured by the limiting probability of an updated system, and asymptotic results for clearing processes with dependent arrivals of clearings. Finally, the asymptotic distribution of the classic Jackson network is discussed as yet another example.

A Comparison of Statistical Methods for the Discovery of Genetic Risk Factors Using Longitudinal Family Study Designs.

The etiology of immune-related diseases or traits is often complex, involving many genetic and environmental factors and their interactions. While methodological approaches focusing on an outcome measured at one time point have succeeded in identifying genetic factors involved in immune-related traits, they fail to capture complex disease mechanisms that fluctuate over time. It is increasingly recognized that longitudinal studies, where an outcome is measured at multiple time points, have great potential to shed light on complex disease mechanisms involving genetic factors. However, longitudinal data require specialized statistical methods, especially in family studies where multiple sources of correlation in the data must be modeled. Using simulated data with known genetic effects, we examined the performance of different analytical methods for investigating associations between genetic factors and longitudinal phenotypes in twin data. The simulations were modeled on data from the Québec Newborn Twin Study, an ongoing population-based longitudinal study of twin births with multiple phenotypes, such as cortisol levels and body mass index, collected multiple times in infancy and early childhood and with sequencing data on immune-related genes and pathways. We compared approaches that we classify as (1) family-based methods applied to summaries of the observations over time, (2) longitudinal-based methods with simplifications of the familial correlation, and (3) Bayesian family-based method with simplifications of the temporal correlation. We found that for estimation of the genetic main and interaction effects, all methods gave estimates close to the true values and had similar power. If heritability estimation is desired, approaches of type (1) also provide heritability estimates close to the true value. Our work shows that the simpler approaches are likely adequate to detect genetic effects; however, interpretation of these effects is more challenging.

Cyclostationary analysis with logarithmic variance stabilisation

Second order cyclostationary (CS2) components in vibration or acoustic emission signals are typical symptoms of a wide variety of faults in rotating and alternating mechanical systems. The square envelope spectrum (SES), obtained via Hilbert transform of the original signal, is at the basis of the most common indicators used for detection of CS2 components. It has been shown that the SES is equivalent to an autocorrelation of the signal׳s discrete Fourier transform, and that CS2 components are a cause of high correlations in the frequency domain of the signal, thus resulting in peaks in the SES. Statistical tests have been proposed to determine if peaks in the SES are likely to belong to a normal variability in the signal or if they are proper symptoms of CS2 components. Despite the need for automated fault recognition and the theoretical soundness of these tests, this approach to machine diagnostics has been mostly neglected in industrial applications. In fact, in a series of experimental applications, even with proper pre-whitening steps, it has been found that healthy machines might produce high spectral correlations and therefore result in a highly biased SES distribution which might cause a series of false positives. In this paper a new envelope spectrum is defined, with the theoretical intent of rendering the hypothesis test variance-free. This newly proposed indicator will prove unbiased in case of multiple CS2 sources of spectral correlation, thus reducing the risk of false alarms.

Randomness and Dependencies Extraction via Polarization, With Applications to Slepian–Wolf Coding and Secrecy

The polarization phenomenon for a single source is extended to a framework with multiple correlated sources. It is shown in addition to extracting the randomness of the source, the polar transforms take the original arbitrary dependencies to extremal dependencies. Polar coding schemes for the Slepian-Wolf (SW) coding problem and for secret key generations are then proposed based on this phenomenon. In particular, secret keys achieving the secrecy capacity and compression schemes achieving the SW capacity region are obtained with a complexity of O(n log (n)) .

Steepest-Descent Optimization of CDMA Signatures for Multiple Correlated Sources With Applications to Joint Source-Channel Coding

An approach to transmitting multiple correlated sources over a Gaussian multiple-access channel (GMAC) using code-division multiple-access (CDMA) is investigated. A block coordinate descent (BCD) algorithm is presented which can be used to optimize CDMA signatures for a given source covariance matrix under individual transmitter power constraints. This algorithm can be used to design non-orthogonal CDMA signatures for GMACs with arbitrary input alphabets, fading, and colored noise. While the main focus has been the design of signatures which minimize the mean square error (MSE) of linear decoding, the algorithm can also be used to design signatures which maximize the input-output mutual information of the channel. This paper investigates the uncoded transmission of Gaussian sources and the coded transmission of binary sources over a GMAC using joint source-channel (JSC) optimized CDMA signatures under constraints on transmitter power and channel bandwidth, scenarios relevant to wireless sensor networks. By using simple coding schemes which only rely on linear multi-user detection and independent channel decoding of a large number of sources, it is demonstrated that CDMA-based JSC coding can exploit inter-source correlation to achieve lower distortion (Gaussian sources) or higher rates (binary sources) compared to conventional separate source-channel (SSC) coding over the same channel bandwidth.

Optimal Rate for Joint Source-Channel Coding of Correlated Sources Over Orthogonal Channels

Joint source-channel coding of multiple correlated sources transmitted over orthogonal channels is considered. Two optimization problems related to coding schemes are formulated: maximal common rate, and maximal sum rate. These two problems model different power saving situations in energy-constrained wireless sensor networks. Solutions of these problems for an arbitrary number of sources are described, and some specific examples are given.

Inclusion of source extent and coherence in a finite-impedance ground reflection model with atmospheric turbulence

Acoustic data collected in static rocket tests are typically influenced by ground reflections. Furthermore, the partial coherence of the ground interaction due to atmospheric turbulence can play a significant role for larger propagation distances. Because the rocket plume is an extended radiator whose directionality is the result of significant source correlation, assessment of the impact of ground reflections in the data must include these effects. In this paper, a finite impedance-ground, single-source interference approach [G. A. Daigle, J. Acoust. Soc. Am. 65, 45–49 (1979)] that incorporates both amplitude and phase variations due to turbulence is extended to distributions of correlated monopoles. The theory for obtaining the mean-square pressure from multiple correlated sources in the presence of atmospheric turbulence is described. The effects of source correlation and extent, ground effective flow resistivity, and turbulence parameters are examined in terms differences in relative sound pressure level across a realistic parameter space. Finally, the model prediction is compared favorably against data from horizontal firings of large solid rocket motors. [Work supported by NASA MSFC and Blue Ridge Research and Consulting, LLC.]

MEG source imaging method using fast L1 minimum-norm and its applications to signals with brain noise and human resting-state source amplitude images

The present study developed a fast MEG source imaging technique based on Fast Vector-based Spatio-Temporal Analysis using a L1-minimum-norm (Fast-VESTAL) and then used the method to obtain the source amplitude images of resting-state magnetoencephalography (MEG) signals for different frequency bands. The Fast-VESTAL technique consists of two steps. First, L1-minimum-norm MEG source images were obtained for the dominant spatial modes of sensor-waveform covariance matrix. Next, accurate source time-courses with millisecond temporal resolution were obtained using an inverse operator constructed from the spatial source images of Step 1. Using simulations, Fast-VESTAL's performance was assessed for its 1) ability to localize multiple correlated sources; 2) ability to faithfully recover source time-courses; 3) robustness to different SNR conditions including SNR with negative dB levels; 4) capability to handle correlated brain noise; and 5) statistical maps of MEG source images. An objective pre-whitening method was also developed and integrated with Fast-VESTAL to remove correlated brain noise. Fast-VESTAL's performance was then examined in the analysis of human median-nerve MEG responses. The results demonstrated that this method easily distinguished sources in the entire somatosensory network. Next, Fast-VESTAL was applied to obtain the first whole-head MEG source-amplitude images from resting-state signals in 41 healthy control subjects, for all standard frequency bands. Comparisons between resting-state MEG sources images and known neurophysiology were provided. Additionally, in simulations and cases with MEG human responses, the results obtained from using conventional beamformer technique were compared with those from Fast-VESTAL, which highlighted the beamformer's problems of signal leaking and distorted source time-courses.

Bayesian multiple imputation for missing multivariate longitudinal data from a Parkinson's disease clinical trial.

In Parkinson's disease (PD) clinical trials, Parkinson's disease is studied using multiple outcomes of various types (e.g. binary, ordinal, continuous) collected repeatedly over time. The overall treatment effects across all outcomes can be evaluated based on a global test statistic. However, missing data occur in outcomes for many reasons, e.g. dropout, death, etc., and need to be imputed in order to conduct an intent-to-treat analysis. We propose a Bayesian method based on item response theory to perform multiple imputation while accounting for multiple sources of correlation. Sensitivity analysis is performed under various scenarios. Our simulation results indicate that the proposed method outperforms standard methods such as last observation carried forward and separate random effects model for each outcome. Our method is motivated by and applied to a Parkinson's disease clinical trial. The proposed method can be broadly applied to longitudinal studies with multiple outcomes subject to missingness.

Selfish Distributed Compression Over Networks: Correlation Induces Anarchy

We consider the min-cost multicast problem (under network coding) with multiple correlated sources where each terminal wants to losslessly reconstruct all the sources. We study the inefficiency brought forth by the selfish behavior of the terminals in this scenario by modeling it as a noncooperative game among the terminals. The degradation in performance due to the lack of regulation is measured by the Price of Anarchy (POA), which is defined as the ratio between the cost of the worst possible Wardrop equilibrium and the socially optimum cost. Our main result is that in contrast with the case of independent sources, the presence of source correlations can significantly increase the price of anarchy. Toward establishing this result, we first characterize the socially optimal flow and rate allocation in terms of four intuitive conditions. Next, we show that the Wardrop equilibrium is a socially optimal solution for a different set of (related) cost functions. Using this, we construct explicit examples that demonstrate that the POA >; 1 and determine near-tight upper bounds on the POA as well. The main techniques in our analysis are Lagrangian duality theory and the usage of the supermodularity of conditional entropy.

Enhancing the Signal of Corticomuscular Coherence

The availability of multichannel neuroimaging techniques, such as MEG and EEG, provides us with detailed topographical information of the recorded magnetic and electric signals and therefore gives us a good overview on the concomitant signals generated in the brain. To assess the location and the temporal dynamics of neuronal sources with noninvasive recordings, reconstruction tools such as beamformers have been shown to be useful. In the current study, we are in particular interested in cortical motor control involved in the isometric contraction of finger muscles. To this end we are measuring the interaction between the dynamics of brain signals and the electrical activity of hand muscles. We were interested to find out whether in addition to the well-known correlated activity between contralateral primary motor cortex and the hand muscles, additional functional connections can be demonstrated. We adopted coherence as a functional index and propose a so-called nulling beamformer method which is computationally efficient and addresses the localization of multiple correlated sources. In simulations of cortico-motor coherence, the proposed method was able to correctly localize secondary sources. The application of the approach on real electromyographic and magnetoencephalographic data collected during an isometric contraction and rest revealed an additional activity in the hemisphere ipsilateral to the hand involved in the task.

Methodological Advances in Brain Connectivity

Methodological Advances in Brain Connectivity

Application of multi-source minimum variance beamformers for reconstruction of correlated neural activity

Linearly constrained minimum variance beamformers are highly effective for analysis of weakly correlated brain activity, but their performance degrades when correlations become significant. Multiple constrained minimum variance (MCMV) beamformers are insensitive to source correlations but require a priori information about the source locations. Besides the question whether unbiased estimates of source positions and orientations can be obtained remained unanswered. In this work, we derive MCMV-based source localizers that can be applied to both induced and evoked brain activity. They may be regarded as a generalization of scalar minimum-variance beamformers for the case of multiple correlated sources. We show that for arbitrary noise covariance these beamformers provide simultaneous unbiased estimates of multiple source positions and orientations and remain bounded at singular points. We also propose an iterative search algorithm that makes it possible to find sources approximately without a priori assumptions about their locations and orientations. Simulations and analyses of real MEG data demonstrate that presented approach is superior to traditional single-source beamformers in situations where correlations between the sources are significant.