Fuzzy kernel evidence Random Forest for identifying pseudouridine sites

Pseudouridine is an RNA modification that is widely distributed in both prokaryotes and eukaryotes, and plays a critical role in numerous biological activities. Despite its importance, the precise identification of pseudouridine sites through experimental approaches poses significant challenges, requiring substantial time and resources.Therefore, there is a growing need for computational techniques that can reliably and quickly identify pseudouridine sites from vast amounts of RNA sequencing data. In this study, we propose fuzzy kernel evidence Random Forest (FKeERF) to identify pseudouridine sites. This method is called PseU-FKeERF, which demonstrates high accuracy in identifying pseudouridine sites from RNA sequencing data. The PseU-FKeERF model selected four RNA feature coding schemes with relatively good performance for feature combination, and then input them into the newly proposed FKeERF method for category prediction. FKeERF not only uses fuzzy logic to expand the original feature space, but also combines kernel methods that are easy to interpret in general for category prediction. Both cross-validation tests and independent tests on benchmark datasets have shown that PseU-FKeERF has better predictive performance than several state-of-the-art methods. This new method not only improves the accuracy of pseudouridine site identification, but also provides a certain reference for disease control and related drug development in the future.

A distance-based kernel for classification via Support Vector Machines

Support Vector Machines (SVMs) are a type of supervised machine learning algorithm widely used for classification tasks. In contrast to traditional methods that split the data into separate training and testing sets, here we propose an innovative approach where subsets of the original data are randomly selected to train the model multiple times. This iterative training process aims to identify a representative data subset, leading to improved inferences about the population. Additionally, we introduce a novel distance-based kernel specifically designed for binary-type features based on a similarity matrix that efficiently handles both binary and multi-class classification problems. Computational experiments on publicly available datasets of varying sizes demonstrate that our proposed method significantly outperforms existing approaches in terms of classification accuracy. Furthermore, the distance-based kernel achieves superior performance compared to other well-known kernels from the literature and those used in previous studies on the same datasets. These findings validate the effectiveness of our proposed classification method and distance-based kernel for SVMs. By leveraging random subset selection and a unique kernel design, we achieve notable improvements in classification accuracy. These results have significant implications for diverse classification problems in Machine Learning and data analysis.

In defense of local descriptor-based few-shot object detection

State-of-the-art image object detection computational models require an intensive parameter fine-tuning stage (using deep convolution network, etc). with tens or hundreds of training examples. In contrast, human intelligence can robustly learn a new concept from just a few instances (i.e., few-shot detection). The distinctive perception mechanisms between these two families of systems enlighten us to revisit classical handcraft local descriptors (e.g., SIFT, HOG, etc.) as well as non-parametric visual models, which innately require no learning/training phase. Herein, we claim that the inferior performance of these local descriptors mainly results from a lack of global structure sense. To address this issue, we refine local descriptors with spatial contextual attention of neighbor affinities and then embed the local descriptors into discriminative subspace guided by Kernel-InfoNCE loss. Differing from conventional quantization of local descriptors in high-dimensional feature space or isometric dimension reduction, we actually seek a brain-inspired few-shot feature representation for the object manifold, which combines data-independent primitive representation and semantic context learning and thus helps with generalization. The obtained embeddings as pattern vectors/tensors permit us an accelerated but non-parametric visual similarity computation as the decision rule for final detection. Our approach to few-shot object detection is nearly learning-free, and experiments on remote sensing imageries (approximate 2-D affine space) confirm the efficacy of our model.

An accelerated failure time regression model for illness-death data: A frailty approach

This work presents a new model and estimation procedure for the illness-death survival data where the hazard functions follow accelerated failure time (AFT) models. A shared frailty variate induces positive dependence among failure times of a subject for handling the unobserved dependency between the nonterminal and the terminal failure times given the observed covariates. The motivation behind the proposed modeling approach is to leverage the well-known interpretability advantage of AFT models with respect to the observed covariates, while also benefiting from the simple and intuitive interpretation of the hazard functions. A semiparametric maximum likelihood estimation procedure is developed via a kernel smoothed-aided expectation-maximization algorithm, and variances are estimated by weighted bootstrap. We consider existing frailty-based illness-death models and place particular emphasis on highlighting the contribution of our current research. The breast cancer data of the Rotterdam tumor bank are analyzed using the proposed as well as existing illness-death models. The results are contrasted and evaluated based on a new graphical goodness-of-fit procedure. Simulation results and data analysis nicely demonstrate the practical utility of the shared frailty variate with the AFT regression model under the illness-death framework.

Kernel-based joint independence tests for multivariate stationary and non-stationary time series

Multivariate time-series data that capture the temporal evolution of interconnected systems are ubiquitous in diverse areas. Understanding the complex relationships and potential dependencies among co-observed variables is crucial for the accurate statistical modelling and analysis of such systems. Here, we introduce kernel-based statistical tests of joint independence in multivariate time series by extending the d-variable Hilbert-Schmidt independence criterion to encompass both stationary and non-stationary processes, thus allowing broader real-world applications. By leveraging resampling techniques tailored for both single- and multiple-realization time series, we show how the method robustly uncovers significant higher-order dependencies in synthetic examples, including frequency mixing data and logic gates, as well as real-world climate, neuroscience and socio-economic data. Our method adds to the mathematical toolbox for the analysis of multivariate time series and can aid in uncovering high-order interactions in data.

A novel approach to attention mechanism using kernel functions: Kerformer

Artificial Intelligence (AI) is driving advancements across various fields by simulating and enhancing human intelligence. In Natural Language Processing (NLP), transformer models like the Kerformer, a linear transformer based on a kernel approach, have garnered success. However, traditional attention mechanisms in these models have quadratic calculation costs linked to input sequence lengths, hampering efficiency in tasks with extended orders. To tackle this, Kerformer introduces a nonlinear reweighting mechanism, transforming maximum attention into feature-based dot product attention. By exploiting the non-negativity and non-linear weighting traits of softmax computation, separate non-negativity operations for Query(Q) and Key(K) computations are performed. The inclusion of the SE Block further enhances model performance. Kerformer significantly reduces attention matrix time complexity from O(N2) to O(N), with N representing sequence length. This transformation results in remarkable efficiency and scalability gains, especially for prolonged tasks. Experimental results demonstrate Kerformer's superiority in terms of time and memory consumption, yielding higher average accuracy (83.39%) in NLP and vision tasks. In tasks with long sequences, Kerformer achieves an average accuracy of 58.94% and exhibits superior efficiency and convergence speed in visual tasks. This model thus offers a promising solution to the limitations posed by conventional attention mechanisms in handling lengthy tasks.

Propensity score analysis with local balance

Most propensity score (PS) analysis methods rely on a correctly specified parametric PS model, which may result in biased estimation of the average treatment effect (ATE) when the model is misspecified. More flexible nonparametric models for treatment assignment alleviate this issue, but they do not always guarantee covariate balance. Methods that force balance in the means of covariates and their transformations between the treatment groups, termed global balance in this article, do not always lead to unbiased estimation of ATE. Their estimated propensity scores only ensure global balance but not the balancing property, which is defined as the conditional independence between treatment assignment and covariates given the propensity score. The balancing property implies not only global balance but also local balance-the mean balance of covariates in propensity score stratified sub-populations. Local balance implies global balance, but the reverse is false. We propose the propensity score with local balance (PSLB) methodology, which incorporates nonparametric propensity score models and optimizes local balance. Extensive numerical studies showed that the proposed method can substantially outperform existing methods that estimate the propensity score by optimizing global balance, when the model is misspecified. The proposed method is implemented in the R package PSLB.

Benzodiazepine-related dementia risks and protopathic biases revealed by multiple-kernel learning with electronic medical records

Objectives

To simultaneously estimate how the risk of incident dementia nonlinearly varies with the administration period and cumulative dose of benzodiazepines, the duration of disorders with an indication for benzodiazepines, and other potential confounders, with the goal of settling the controversy over the role of benzodiazepines in the development of dementia.

Methods

The classical hazard model was extended using the techniques of multiple-kernel learning. Regularised maximum-likelihood estimation, including determination of hyperparameter values with 10-fold cross-validation, bootstrap goodness-of-fit test, and bootstrap estimation of confidence intervals, was applied to cohorts retrospectively extracted from electronic medical records of our university hospitals between 1 November 2004 and 31 July 2020. The analysis was mainly focused on 8160 patients aged 40 or older with new onset of insomnia, affective disorders, or anxiety disorders, who were followed up for 4.10 ± 3.47 years.

Results

Besides previously reported risk associations, we detected significant nonlinear risk variations over 2-4 years attributable to the duration of insomnia and anxiety disorders, and to the administration period of short-acting benzodiazepines. After nonlinear adjustment for potential confounders, we observed no significant risk associations with long-term use of benzodiazepines.

Conclusions

The pattern of the detected nonlinear risk variations suggested reverse causation and confounding. Their putative bias effects over 2-4 years suggested similar biases in previously reported results. These results, together with the lack of significant risk associations with long-term use of benzodiazepines, suggested the need to reconsider previous results and methods for future analysis.

Generalization Performance of Quantum Metric Learning Classifiers

Quantum computing holds great promise for a number of fields including biology and medicine. A major application in which quantum computers could yield advantage is machine learning, especially kernel-based approaches. A recent method termed quantum metric learning, in which a quantum embedding which maximally separates data into classes is learned, was able to perfectly separate ant and bee image training data. The separation is achieved with an intrinsically quantum objective function and the overall approach was shown to work naturally as a hybrid classical-quantum computation enabling embedding of high dimensional feature data into a small number of qubits. However, the ability of the trained classifier to predict test sample data was never assessed. We assessed the performance of quantum metric learning on test ants and bees image data as well as breast cancer clinical data. We applied the original approach as well as variants in which we performed principal component analysis (PCA) on the feature data to reduce its dimensionality for quantum embedding, thereby limiting the number of model parameters. If the degree of dimensionality reduction was limited and the number of model parameters was constrained to be far less than the number of training samples, we found that quantum metric learning was able to accurately classify test data.

Application research of pulse signal physiology and pathology feature mining in the field of disease diagnosis

This experiment is based on the principle of traditional Chinese medicine (TCM) pulse diagnosis, the human pulse signal collected by the sensor is organized into a dataset, and the algorithms are designed to apply feature extraction. After denoising, smoothing and eliminating baseline drift of the photoelectric sensors pulse data of several groups of subjects, we designed three algorithms to describe the difference between the two-dimensional images of the pulse data of normal people and patients with chronic diseases. Convert the calculated feature values into multi-dimensional arrays, enter the decision tree (DT) to balance the differences in human physiological conditions, then train in the support vector machine kernel method (SVM-KM) classifier. Experimental results show that the application of these feature mining algorithms to disease detection greatly improves the reliability of TCM diagnosis.

Predictive generalized varying-coefficient longitudinal model

We propose a nonparametric bivariate varying coefficient generalized linear model to predict a mean response trajectory in the future given an individual's characteristics at present or an earlier time point in a longitudinal study. Given the measurement time of the predictors, the coefficients vary as functions of the future time over which the prediction of the mean response is concerned and illustrate the dynamic association between the future response and the earlier measured predictors. We use a nonparametric approach that takes advantage of features of both the kernel and the spline methods for estimation. The resulting coefficient estimator is asymptotically consistent under mild regularity conditions. We also develop a new bootstrap approach to construct simultaneous confidence bands for statistical inference about the coefficients and the predicted response trajectory based on the coverage rate of bootstrap estimates. We use the Framingham Heart Study to illustrate the methodology. The proposed procedure is applied to predict the probability trajectory of hypertension risk given individuals' health condition in early adulthood and to examine the impact of risk factors in early adulthood on a long-term risk of hypertension over several decades.

Biologically-Inspired Pulse Signal Processing for Intelligence at the Edge

There is an ever-growing mismatch between the proliferation of data-intensive, power-hungry deep learning solutions in the machine learning (ML) community and the need for agile, portable solutions in resource-constrained devices, particularly for intelligence at the edge. In this paper, we present a fundamentally novel approach that leverages data-driven intelligence with biologically-inspired efficiency. The proposed Sparse Embodiment Neural-Statistical Architecture (SENSA) decomposes the learning task into two distinct phases: a training phase and a hardware embedment phase where prototypes are extracted from the trained network and used to construct fast, sparse embodiment for hardware deployment at the edge. Specifically, we propose the Sparse Pulse Automata via Reproducing Kernel (SPARK) method, which first constructs a learning machine in the form of a dynamical system using energy-efficient spike or pulse trains, commonly used in neuroscience and neuromorphic engineering, then extracts a rule-based solution in the form of automata or lookup tables for rapid deployment in edge computing platforms. We propose to use the theoretically-grounded unifying framework of the Reproducing Kernel Hilbert Space (RKHS) to provide interpretable, nonlinear, and nonparametric solutions, compared to the typical neural network approach. In kernel methods, the explicit representation of the data is of secondary nature, allowing the same algorithm to be used for different data types without altering the learning rules. To showcase SPARK’s capabilities, we carried out the first proof-of-concept demonstration on the task of isolated-word automatic speech recognition (ASR) or keyword spotting, benchmarked on the TI-46 digit corpus. Together, these energy-efficient and resource-conscious techniques will bring advanced machine learning solutions closer to the edge.

MRI-aided kernel PET image reconstruction method based on texture features

We investigate the reconstruction of low-count positron emission tomography (PET) projection, which is an important, but challenging, task. Using the texture feature extraction method of radiomics, i.e. the gray-level co-occurrence matrix (GLCM), texture features can be extracted from magnetic resonance imaging images with high-spatial resolution. In this work, we propose a kernel reconstruction method combining autocorrelation texture features derived from the GLCM. The new kernel function includes the correlations of both the intensity and texture features from the prior image. By regarding the GLCM as a discrete approximation of a probability density function, the asymptotically gray-level-invariant autocorrelation texture feature is generated, which can maintain the accuracy of texture features extracted from small image regions by reducing the number of quantized image gray levels. A computer simulation shows that the proposed method can effectively reduce the noise in the reconstructed image compared to the maximum likelihood expectation maximum method and improve the image quality and tumor region accuracy compared to the original kernel method for low-count PET reconstruction. A simulation study on clinical patient images also shows that the proposed method can improve the whole image quality and that the reconstruction of a high-uptake lesion is more accurate than that achieved by the original kernel method.

Improved identification of abdominal aortic aneurysm using the Kernelized Expectation Maximization algorithm

Abdominal aortic aneurysm (AAA) monitoring and risk of rupture is currently assumed to be correlated with the aneurysm diameter. Aneurysm growth, however, has been demonstrated to be unpredictable. Using PET to measure uptake of [¹⁸F]-NaF in calcified lesions of the abdominal aorta has been shown to be useful for identifying AAA and to predict its growth. The PET low spatial resolution, however, can affect the accuracy of the diagnosis. Advanced edge-preserving reconstruction algorithms can overcome this issue. The kernel method has been demonstrated to provide noise suppression while retaining emission and edge information. Nevertheless, these findings were obtained using simulations, phantoms and a limited amount of patient data. In this study, the authors aim to investigate the usefulness of the anatomically guided kernelized expectation maximization (KEM) and the hybrid KEM (HKEM) methods and to judge the statistical significance of the related improvements. Sixty-one datasets of patients with AAA and 11 from control patients were reconstructed with ordered subsets expectation maximization (OSEM), HKEM and KEM and the analysis was carried out using the target-to-blood-pool ratio, and a series of statistical tests. The results show that all algorithms have similar diagnostic power, but HKEM and KEM can significantly recover uptake of lesions and improve the accuracy of the diagnosis by up to 22% compared to OSEM. The same improvements are likely to be obtained in clinical applications based on the quantification of small lesions, like for example cancer. This article is part of the theme issue 'Synergistic tomographic image reconstruction: part 1'.

Dynamic PET image reconstruction utilizing intrinsic data-driven HYPR4D denoising kernel

PURPOSE

Reconstructed PET images are typically noisy, especially in dynamic imaging where the acquired data are divided into several short temporal frames. High noise in the reconstructed images translates to poor precision/reproducibility of image features. One important role of "denoising" is therefore to improve the precision of image features. However, typical denoising methods achieve noise reduction at the expense of accuracy. In this work, we present a novel four-dimensional (4D) denoised image reconstruction framework, which we validate using 4D simulations, experimental phantom, and clinical patient data, to achieve 4D noise reduction while preserving spatiotemporal patterns/minimizing error introduced by denoising.

METHODS

Our proposed 4D denoising operator/kernel is based on HighlY constrained backPRojection (HYPR), which is applied either after each update of OSEM reconstruction of dynamic 4D PET data or within the recently proposed kernelized reconstruction framework inspired by kernel methods in machine learning. Our HYPR4D kernel makes use of the spatiotemporal high frequency features extracted from a 4D composite, generated within the reconstruction, to preserve the spatiotemporal patterns and constrain the 4D noise increment of the image estimate.

RESULTS

Results from simulations, experimental phantom, and patient data showed that the HYPR4D kernel with our proposed 4D composite outperformed other denoising methods, such as the standard OSEM with spatial filter, OSEM with 4D filter, and HYPR kernel method with the conventional 3D composite in conjunction with recently proposed High Temporal Resolution kernel (HYPRC3D-HTR), in terms of 4D noise reduction while preserving the spatiotemporal patterns or 4D resolution within the 4D image estimate. Consequently, the error in outcome measures obtained from the HYPR4D method was less dependent on the region size, contrast, and uniformity/functional patterns within the target structures compared to the other methods. For outcome measures that depend on spatiotemporal tracer uptake patterns such as the nondisplaceable Binding Potential (BP_ND ), the root mean squared error in regional mean of voxel BP_ND values was reduced from ~8% (OSEM with spatial or 4D filter) to ~3% using HYPRC3D-HTR and was further reduced to ~2% using our proposed HYPR4D method for relatively small target structures (~10 mm in diameter). At the voxel level, HYPR4D produced two to four times lower mean absolute error in BP_ND relative to HYPRC3D-HTR.

CONCLUSION

As compared to conventional methods, our proposed HYPR4D method can produce more robust and accurate image features without requiring any prior information.

A Pathway-Based Kernel Boosting Method for Sample Classification Using Genomic Data

The analysis of cancer genomic data has long suffered "the curse of dimensionality." Sample sizes for most cancer genomic studies are a few hundreds at most while there are tens of thousands of genomic features studied. Various methods have been proposed to leverage prior biological knowledge, such as pathways, to more effectively analyze cancer genomic data. Most of the methods focus on testing marginal significance of the associations between pathways and clinical phenotypes. They can identify informative pathways but do not involve predictive modeling. In this article, we propose a Pathway-based Kernel Boosting (PKB) method for integrating gene pathway information for sample classification, where we use kernel functions calculated from each pathway as base learners and learn the weights through iterative optimization of the classification loss function. We apply PKB and several competing methods to three cancer studies with pathological and clinical information, including tumor grade, stage, tumor sites and metastasis status. Our results show that PKB outperforms other methods and identifies pathways relevant to the outcome variables.

High Temporal-Resolution Dynamic PET Image Reconstruction Using a New Spatiotemporal Kernel Method

Current clinical dynamic PET has an effective temporal resolution of 5-10 seconds, which can be adequate for traditional compartmental modeling but is inadequate for exploiting the benefit of more advanced tracer kinetic modeling for characterization of diseases (e.g., cancer and heart disease). There is a need to improve dynamic PET to allow fine temporal sampling of 1-2 seconds. However, the reconstruction of these short-time frames from tomographic data is extremely challenging as the count level of each frame is very low and high noise presents in both spatial and temporal domains. Previously, the kernel framework has been developed and demonstrated as a statistically efficient approach to utilizing image prior for low-count PET image reconstruction. Nevertheless, the existing kernel methods mainly explore spatial correlations in the data and only have a limited ability in suppressing temporal noise. In this paper, we propose a new kernel method which extends the previous spatial kernel method to the general spatiotemporal domain. The new kernelized model encodes both spatial and temporal correlations obtained from image prior information and are incorporated into the PET forward projection model to improve themaximumlikelihood(ML) image reconstruction. Computer simulations and an application to real patient scan have shown that the proposed approach can achieve effective noise reduction in both spatial and temporal domains and outperform the spatial kernel method and conventional ML reconstruction method for improving the high temporal-resolution dynamic PET imaging.

Rolling Element Bearing Fault Diagnosis under Impulsive Noise Environment Based on Cyclic Correntropy Spectrum

Rolling element bearings are widely used in various industrial machines. Fault diagnosis of rolling element bearings is a necessary tool to prevent any unexpected accidents and improve industrial efficiency. Although proved to be a powerful method in detecting the resonance band excited by faults, the spectral kurtosis (SK) exposes an obvious weakness in the case of impulsive background noise. To well process the bearing fault signal in the presence of impulsive noise, this paper proposes a fault diagnosis method based on the cyclic correntropy (CCE) function and its spectrum. Furthermore, an important parameter of CCE function, namely kernel size, is analyzed to emphasize its critical influence on the fault diagnosis performance. Finally, comparisons with the SK-based Fast Kurtogram are conducted to highlight the superiority of the proposed method. The experimental results show that the proposed method not only largely suppresses the impulsive noise, but also has a robust self-adaptation ability. The application of the proposed method is validated on a simulated signal and real data, including rolling element bearing data of a train axle.

Effect of PET-MR Inconsistency in the Kernel Image Reconstruction Method

Anatomically-driven image reconstruction algorithms have become very popular in positron emission tomography (PET) where they have demonstrated improved image resolution and quantification. This work, consider the effect of spatial inconsistency between MR and PET images in hot and cold regions of the PET image. We investigate these effects on the kernel method from machine learning, in particular, the hybrid kernelized expectation maximization (HKEM). These were applied to Jaszczak phantom and patient data acquired with the Biograph Siemens mMR. The results show that even a small shift can cause a significant change in activity concentration. In general, the PET-MR inconsistencies can induce the partial volume effect, more specifically the 'spill-in' of the affected cold regions and the 'spill-out' from the hot regions. The maximum change was about 100% for the cold region and 10% for the hot lesion using KEM, against the 37% and 8% obtained with HKEM. The findings of this work suggest that including PET information in the kernel enhances the flexibility of the reconstruction in case of spatial inconsistency. Nevertheless, accurate registration and choice of the appropriate MR image for the creation of the kernel is essential to avoid artifacts, blurring, and bias.

Kernel Sparse Representation with Hybrid Regularization for On-Road Traffic Sensor Data Imputation

The problem of missing values (MVs) in traffic sensor data analysis is universal in current intelligent transportation systems because of various reasons, such as sensor malfunction, transmission failure, etc. Accurate imputation of MVs is the foundation of subsequent data analysis tasks since most analysis algorithms need complete data as input. In this work, a novel MVs imputation approach termed as kernel sparse representation with elastic net regularization (KSR-EN) is developed for reconstructing MVs to facilitate analysis with traffic sensor data. The idea is to represent each sample as a linear combination of other samples due to inherent spatiotemporal correlation, as well as periodicity of daily traffic flow. To discover few yet correlated samples and make full use of the valuable information, a combination of l₁-norm and l₂-norm is employed to penalize the combination coefficients. Moreover, the linear representation among samples is extended to nonlinear representation by mapping input data space into high-dimensional feature space, which further enhances the recovery performance of our proposed approach. An efficient iterative algorithm is developed for solving KSR-EN model. The proposed method is verified on both an artificially simulated dataset and a public road network traffic sensor data. The results demonstrate the effectiveness of the proposed approach in terms of MVs imputation.

A similarity-based approach to leverage multi-cohort medical data on the diagnosis and prognosis of Alzheimer's disease

Motivation

Heterogeneous diseases such as Alzheimer's disease (AD) manifest a variety of phenotypes among populations. Early diagnosis and effective treatment offer cost benefits. Many studies on biochemical and imaging markers have shown potential promise in improving diagnosis, yet establishing quantitative diagnostic criteria for ancillary tests remains challenging.

Results

We have developed a similarity-based approach that matches individuals to subjects with similar conditions. We modeled the disease with a Gaussian process, and tested the method in the Alzheimer's Disease Big Data DREAM Challenge. Ranked the highest among submitted methods, our diagnostic model predicted cognitive impairment scores in an independent dataset test with a correlation score of 0.573. It differentiated AD patients from control subjects with an area under the receiver operating curve of 0.920. Without knowing longitudinal information about subjects, the model predicted patients who are vulnerable to conversion from mild-cognitive impairment to AD through the similarity network. This diagnostic framework can be applied to other diseases with clinical heterogeneity, such as Parkinson's disease.

Predictive Modeling of Microbiome Data Using a Phylogeny-Regularized Generalized Linear Mixed Model

Recent human microbiome studies have revealed an essential role of the human microbiome in health and disease, opening up the possibility of building microbiome-based predictive models for individualized medicine. One unique characteristic of microbiome data is the existence of a phylogenetic tree that relates all the microbial species. It has frequently been observed that a cluster or clusters of bacteria at varying phylogenetic depths are associated with some clinical or biological outcome due to shared biological function (clustered signal). Moreover, in many cases, we observe a community-level change, where a large number of functionally interdependent species are associated with the outcome (dense signal). We thus develop "glmmTree," a prediction method based on a generalized linear mixed model framework, for capturing clustered and dense microbiome signals. glmmTree uses the similarity between microbiomes, which is defined based on the microbiome composition and the phylogenetic tree, to predict the outcome. The effects of other predictive variables (e.g., age, sex) can be incorporated readily in the regression framework. Additional tuning parameters enable a data-adaptive approach to capture signals at different phylogenetic depth and abundance level. Simulation studies and real data applications demonstrated that "glmmTree" outperformed existing methods in the dense and clustered signal scenarios.

Biologically-Inspired Spike-Based Automatic Speech Recognition of Isolated Digits Over a Reproducing Kernel Hilbert Space

This paper presents a novel real-time dynamic framework for quantifying time-series structure in spoken words using spikes. Audio signals are converted into multi-channel spike trains using a biologically-inspired leaky integrate-and-fire (LIF) spike generator. These spike trains are mapped into a function space of infinite dimension, i.e., a Reproducing Kernel Hilbert Space (RKHS) using point-process kernels, where a state-space model learns the dynamics of the multidimensional spike input using gradient descent learning. This kernelized recurrent system is very parsimonious and achieves the necessary memory depth via feedback of its internal states when trained discriminatively, utilizing the full context of the phoneme sequence. A main advantage of modeling nonlinear dynamics using state-space trajectories in the RKHS is that it imposes no restriction on the relationship between the exogenous input and its internal state. We are free to choose the input representation with an appropriate kernel, and changing the kernel does not impact the system nor the learning algorithm. Moreover, we show that this novel framework can outperform both traditional hidden Markov model (HMM) speech processing as well as neuromorphic implementations based on spiking neural network (SNN), yielding accurate and ultra-low power word spotters. As a proof of concept, we demonstrate its capabilities using the benchmark TI-46 digit corpus for isolated-word automatic speech recognition (ASR) or keyword spotting. Compared to HMM using Mel-frequency cepstral coefficient (MFCC) front-end without time-derivatives, our MFCC-KAARMA offered improved performance. For spike-train front-end, spike-KAARMA also outperformed state-of-the-art SNN solutions. Furthermore, compared to MFCCs, spike trains provided enhanced noise robustness in certain low signal-to-noise ratio (SNR) regime.

Direct Patlak Reconstruction From Dynamic PET Data Using the Kernel Method With MRI Information Based on Structural Similarity

Positron emission tomography (PET) is a functional imaging modality widely used in oncology, cardiology, and neuroscience. It is highly sensitive, but suffers from relatively poor spatial resolution, as compared with anatomical imaging modalities, such as magnetic resonance imaging (MRI). With the recent development of combined PET/MR systems, we can improve the PET image quality by incorporating MR information into image reconstruction. Previously, kernel learning has been successfully embedded into static and dynamic PET image reconstruction using either PET temporal or MRI information. Here, we combine both PET temporal and MRI information adaptively to improve the quality of direct Patlak reconstruction. We examined different approaches to combine the PET and MRI information in kernel learning to address the issue of potential mismatches between MRI and PET signals. Computer simulations and hybrid real-patient data acquired on a simultaneous PET/MR scanner were used to evaluate the proposed methods. Results show that the method that combines PET temporal information and MRI spatial information adaptively based on the structure similarity index has the best performance in terms of noise reduction and resolution improvement.

A Kernel-Based Low-Rank (KLR) Model for Low-Dimensional Manifold Recovery in Highly Accelerated Dynamic MRI

While many low rank and sparsity-based approaches have been developed for accelerated dynamic magnetic resonance imaging (dMRI), they all use low rankness or sparsity in input space, overlooking the intrinsic nonlinear correlation in most dMRI data. In this paper, we propose a kernel-based framework to allow nonlinear manifold models in reconstruction from sub-Nyquist data. Within this framework, many existing algorithms can be extended to kernel framework with nonlinear models. In particular, we have developed a novel algorithm with a kernel-based low-rank model generalizing the conventional low rank formulation. The algorithm consists of manifold learning using kernel, low rank enforcement in feature space, and preimaging with data consistency. Extensive simulation and experiment results show that the proposed method surpasses the conventional low-rank-modeled approaches for dMRI.

Kernel-Based Relevance Analysis with Enhanced Interpretability for Detection of Brain Activity Patterns

We introduce Enhanced Kernel-based Relevance Analysis (EKRA) that aims to support the automatic identification of brain activity patterns using electroencephalographic recordings. EKRA is a data-driven strategy that incorporates two kernel functions to take advantage of the available joint information, associating neural responses to a given stimulus condition. Regarding this, a Centered Kernel Alignment functional is adjusted to learning the linear projection that best discriminates the input feature set, optimizing the required free parameters automatically. Our approach is carried out in two scenarios: (i) feature selection by computing a relevance vector from extracted neural features to facilitating the physiological interpretation of a given brain activity task, and (ii) enhanced feature selection to perform an additional transformation of relevant features aiming to improve the overall identification accuracy. Accordingly, we provide an alternative feature relevance analysis strategy that allows improving the system performance while favoring the data interpretability. For the validation purpose, EKRA is tested in two well-known tasks of brain activity: motor imagery discrimination and epileptic seizure detection. The obtained results show that the EKRA approach estimates a relevant representation space extracted from the provided supervised information, emphasizing the salient input features. As a result, our proposal outperforms the state-of-the-art methods regarding brain activity discrimination accuracy with the benefit of enhanced physiological interpretation about the task at hand.

Neighboring Structure Visualization on a Grid-based Layout

Here, we describe an algorithm to visualize chemical structures on a grid-based layout in such a way that similar structures are neighboring. It is based on structure reordering with the help of the Hilbert Schmidt Independence Criterion, representing an empirical estimate of the Hilbert-Schmidt norm of the cross-covariance operator. The method can be applied to any layout of bi- or three-dimensional shape. The approach is demonstrated on a set of dopamine D5 ligands visualized on squared, disk and spherical layouts.

Anatomical image-guided fluorescence molecular tomography reconstruction using kernel method

Fluorescence molecular tomography (FMT) is an important in vivo imaging modality to visualize physiological and pathological processes in small animals. However, FMT reconstruction is ill-posed and ill-conditioned due to strong optical scattering in deep tissues, which results in poor spatial resolution. It is well known that FMT image quality can be improved substantially by applying the structural guidance in the FMT reconstruction. An approach to introducing anatomical information into the FMT reconstruction is presented using the kernel method. In contrast to conventional methods that incorporate anatomical information with a Laplacian-type regularization matrix, the proposed method introduces the anatomical guidance into the projection model of FMT. The primary advantage of the proposed method is that it does not require segmentation of targets in the anatomical images. Numerical simulations and phantom experiments have been performed to demonstrate the proposed approach’s feasibility. Numerical simulation results indicate that the proposed kernel method can separate two FMT targets with an edge-to-edge distance of 1 mm and is robust to false-positive guidance and inhomogeneity in the anatomical image. For the phantom experiments with two FMT targets, the kernel method has reconstructed both targets successfully, which further validates the proposed kernel method.

Robust Pedestrian Classification Based on Hierarchical Kernel Sparse Representation

Vision-based pedestrian detection has become an active topic in computer vision and autonomous vehicles. It aims at detecting pedestrians appearing ahead of the vehicle using a camera so that autonomous vehicles can assess the danger and take action. Due to varied illumination and appearance, complex background and occlusion pedestrian detection in outdoor environments is a difficult problem. In this paper, we propose a novel hierarchical feature extraction and weighted kernel sparse representation model for pedestrian classification. Initially, hierarchical feature extraction based on a CENTRIST descriptor is used to capture discriminative structures. A max pooling operation is used to enhance the invariance of varying appearance. Then, a kernel sparse representation model is proposed to fully exploit the discrimination information embedded in the hierarchical local features, and a Gaussian weight function as the measure to effectively handle the occlusion in pedestrian images. Extensive experiments are conducted on benchmark databases, including INRIA, Daimler, an artificially generated dataset and a real occluded dataset, demonstrating the more robust performance of the proposed method compared to state-of-the-art pedestrian classification methods.

PET image reconstruction using kernel method

Image reconstruction from low-count positron emission tomography (PET) projection data is challenging because the inverse problem is ill-posed. Prior information can be used to improve image quality. Inspired by the kernel methods in machine learning, this paper proposes a kernel based method that models PET image intensity in each pixel as a function of a set of features obtained from prior information. The kernel-based image model is incorporated into the forward model of PET projection data and the coefficients can be readily estimated by the maximum likelihood (ML) or penalized likelihood image reconstruction. A kernelized expectation-maximization algorithm is presented to obtain the ML estimate. Computer simulations show that the proposed approach can achieve better bias versus variance trade-off and higher contrast recovery for dynamic PET image reconstruction than the conventional maximum likelihood method with and without post-reconstruction denoising. Compared with other regularization-based methods, the kernel method is easier to implement and provides better image quality for low-count data. Application of the proposed kernel method to a 4-D dynamic PET patient dataset showed promising results.

Kernel-based variance component estimation and whole-genome prediction of pre-corrected phenotypes and progeny tests for dairy cow health traits

Prediction of complex trait phenotypes in the presence of unknown gene action is an ongoing challenge in animals, plants, and humans. Development of flexible predictive models that perform well irrespective of genetic and environmental architectures is desirable. Methods that can address non-additive variation in a non-explicit manner are gaining attention for this purpose and, in particular, semi-parametric kernel-based methods have been applied to diverse datasets, mostly providing encouraging results. On the other hand, the gains obtained from these methods have been smaller when smoothed values such as estimated breeding value (EBV) have been used as response variables. However, less emphasis has been placed on the choice of phenotypes to be used in kernel-based whole-genome prediction. This study aimed to evaluate differences between semi-parametric and parametric approaches using two types of response variables and molecular markers as inputs. Pre-corrected phenotypes (PCP) and EBV obtained for dairy cow health traits were used for this comparison. We observed that non-additive genetic variances were major contributors to total genetic variances in PCP, whereas additivity was the largest contributor to variability of EBV, as expected. Within the kernels evaluated, non-parametric methods yielded slightly better predictive performance across traits relative to their additive counterparts regardless of the type of response variable used. This reinforces the view that non-parametric kernels aiming to capture non-linear relationships between a panel of SNPs and phenotypes are appealing for complex trait prediction. However, like past studies, the gain in predictive correlation was not large for either PCP or EBV. We conclude that capturing non-additive genetic variation, especially epistatic variation, in a cross-validation framework remains a significant challenge even when it is important, as seems to be the case for health traits in dairy cows.

Synthesis of neural networks for spatio-temporal spike pattern recognition and processing

The advent of large scale neural computational platforms has highlighted the lack of algorithms for synthesis of neural structures to perform predefined cognitive tasks. The Neural Engineering Framework (NEF) offers one such synthesis, but it is most effective for a spike rate representation of neural information, and it requires a large number of neurons to implement simple functions. We describe a neural network synthesis method that generates synaptic connectivity for neurons which process time-encoded neural signals, and which makes very sparse use of neurons. The method allows the user to specify—arbitrarily—neuronal characteristics such as axonal and dendritic delays, and synaptic transfer functions, and then solves for the optimal input-output relationship using computed dendritic weights. The method may be used for batch or online learning and has an extremely fast optimization process. We demonstrate its use in generating a network to recognize speech which is sparsely encoded as spike times.

Kernel earth mover's distance for EEG classification

Here, we propose a new kernel approach based on the earth mover's distance (EMD) for electroencephalography (EEG) signal classification. The EEG time series are first transformed into histograms in this approach. The distance between these histograms is then computed using the EMD in a pair-wise manner. We bring the distances into a kernel form called kernel EMD. The support vector classifier can then be used for the classification of EEG signals. The experimental results on the real EEG data show that the new kernel method is very effective, and can classify the data with higher accuracy than traditional methods.

Integrated light dosimetry system for prostate photodynamic therapy

A light dosimetry system is developed for prostate PDT, which integrates four main components: a light fluence rate calculation engine, an optimization tool for treatment planning, a light delivery system, and an in vivo light fluence rate measurement system. Three-dimensional light fluence rate distribution in a prostate is calculated using a kernel algorithm, which takes into account of heterogeneous optical properties. A Cimmino optimization algorithm is used to optimize the parameters of the cylindrical diffusing fibers (CDFs) to generate uniform PDT dose (or light fluence rate under uniform drug distribution) to cover the heterogeneous prostate. The light delivery system is composed of a 12-channel beamsplitter and the intensities of each channel (i.e., source) are controlled individually by programmable motorized attenuators. Our tests show that the light fluence rate calculation is fast and the accuracy is close to that of a finite-element method model, and the approach that uses the treatment CDFs to determine optical properties, improves the accuracy of light fluence rate prediction. The light delivery system allows real time control of the light source intensities for both PDT dosimetry and PDT light delivery. Integrating the fast light fluence rate calculation, optimization, instant source intensity adjustment, and in vivo light fluence rate measurement, the dosimetry system is suitable for prostate PDT.

Non-parametric regression estimation from data contaminated by a mixture of Berkson and classical errors

Estimation of a regression function is a well-known problem in the context of errors in variables, where the explanatory variable is observed with random noise. This noise can be of two types, which are known as classical or Berkson, and it is common to assume that the error is purely of one of these two types. In practice, however, there are many situations where the explanatory variable is contaminated by a mixture of the two errors. In such instances, the Berkson component typically arises because the variable of interest is not directly available and can only be assessed through a proxy, whereas the inaccuracy that is related to the observation of the latter causes an error of classical type. We propose a non-parametric estimator of a regression function from data that are contaminated by a mixture of the two errors. We prove consistency of our estimator, derive rates of convergence and suggest a data-driven implementation. Finite sample performance is illustrated via simulated and real data examples.

Modeling light fluence rate distribution in optically heterogeneous prostate photodynamic therapy using a kernel method

To accurately calculate light fluence rate distribution for light dosimetry in prostate photodynamic therapy (PDT), heterogeneity of optical properties has to be taken into account. Previous study has shown that a finite-element method (FEM) can be an efficient tool to deal with the optical heterogeneity. However, the calculation speed of the FEM is not suitable for real time treatment planning. In this paper, two kernel models are developed. Because the kernels are based on analytic solutions of the diffusion equation, calculations are much faster. We derived our extensions of kernel from homogeneous medium to heterogeneous medium assuming spherically symmetrical heterogeneity of optical properties. The kernel models are first developed for a point source and then extended for a linear source, which is considered a summation of point sources uniformly spaced along a line. The kernel models are compared with the FEM calculation. In application of the two kernel models to a heterogeneous prostate PDT case, both kernel models give improved light fluence rate results compared with those derived assuming homogeneous medium. In addition, kernel model 2 predicts reasonable light fluence rates and is deemed suitable for treatment planning.