Search

Despite the myriad peer-reviewed papers demonstrating novel Artificial Intelligence (AI)-based solutions to COVID-19 challenges during the pandemic, few have made significant clinical impact. The impact of artificial intelligence during the COVID-19 pandemic was greatly limited by lack of model transparency. This systematic review examines the use of Explainable Artificial Intelligence (XAI) during the pandemic and how its use could overcome barriers to real-world success. We find that successful use of XAI can improve model performance, instill trust in the end-user, and provide the value needed to affect user decision-making. We introduce the reader to common XAI techniques, their utility, and specific examples of their application. Evaluation of XAI results is also discussed as an important step to maximize the value of AI-based clinical decision support systems. We illustrate the classical, modern, and potential future trends of XAI to elucidate the evolution of novel XAI techniques. Finally, we provide a checklist of suggestions during the experimental design process supported by recent publications. Common challenges during the implementation of AI solutions are also addressed with specific examples of potential solutions. We hope this review may serve as a guide to improve the clinical impact of future AI-based solutions., Comment: 23 pages, 13 figures, submitting to IEEE

We introduce the notion of a properly ordered coloring (POC) of a weighted graph, that generalizes the notion of vertex coloring of a graph. Under a POC, if $xy$ is an edge, then the larger weighted vertex receives a larger color; in the case of equal weights of $x$ and $y$, their colors must be different. In this paper, we shall initiate the study of this special coloring in graphs. For a graph $G$, we introduce the function $f(G)$ which gives the maximum number of colors required by a POC over all weightings of $G$. We show that $f(G)=\ell(G)$, where $\ell(G)$ is the number of vertices of a longest path in $G$. Another function we introduce is $\chi_{POC}(G;t)$ giving the minimum number of colors required over all weightings of $G$ using $t$ distinct weights. We show that the ratio of $\chi_{POC}(G;t)-1$ to $\chi(G)-1$ can be bounded by $t$ for any graph $G$; in fact, the result is shown by determining $\chi_{POC}(G;t)$ when $G$ is a complete multipartite graph. We also determine the minimum number of colors to give a POC on a vertex-weighted graph in terms of the number of vertices of a longest directed path in an orientation of the underlying graph. This extends the so called Gallai-Hasse-Roy-Vitaver theorem, a classical result concerning the relationship between the chromatic number of a graph $G$ and the number of vertices of a longest directed path in an orientation of $G$., Comment: To appear in "Order"

On basis of functional magnetic resonance imaging (fMRI), researchers are devoted to designing visual encoding models to predict the neuron activity of human in response to presented image stimuli and analyze inner mechanism of human visual cortices. Deep network structure composed of hierarchical processing layers forms deep network models by learning features of data on specific task through big dataset. Deep network models have powerful and hierarchical representation of data, and have brought about breakthroughs for visual encoding, while revealing hierarchical structural similarity with the manner of information processing in human visual cortices. However, previous studies almost used image features of those deep network models pre-trained on classification task to construct visual encoding models. Except for deep network structure, the task or corresponding big dataset is also important for deep network models, but neglected by previous studies. Because image classification is a relatively fundamental task, it is difficult to guide deep network models to master high-level semantic representations of data, which causes into that encoding performance for high-level visual cortices is limited. In this study, we introduced one higher-level vision task: image caption (IC) task and proposed the visual encoding model based on IC features (ICFVEM) to encode voxels of high-level visual cortices. Experiment demonstrated that ICFVEM obtained better encoding performance than previous deep network models pre-trained on classification task. In addition, the interpretation of voxels was realized to explore the detailed characteristics of voxels based on the visualization of semantic words, and comparative analysis implied that high-level visual cortices behaved the correlative representation of image content.

In the visual decoding domain, visually reconstructing presented images given the corresponding human brain activity monitored by functional magnetic resonance imaging (fMRI) is difficult, especially when reconstructing viewed natural images. Visual reconstruction is a conditional image generation on fMRI data and thus generative adversarial network (GAN) for natural image generation is recently introduced for this task. Although GAN-based methods have greatly improved, the fidelity and naturalness of reconstruction are still unsatisfactory due to the small number of fMRI data samples and the instability of GAN training. In this study, we proposed a new GAN-based Bayesian visual reconstruction method (GAN-BVRM) that includes a classifier to decode categories from fMRI data, a pre-trained conditional generator to generate natural images of specified categories, and a set of encoding models and evaluator to evaluate generated images. GAN-BVRM employs the pre-trained generator of the prevailing BigGAN to generate masses of natural images, and selects the images that best matches with the corresponding brain activity through the encoding models as the reconstruction of the image stimuli. In this process, the semantic and detailed contents of reconstruction are controlled by decoded categories and encoding models, respectively. GAN-BVRM used the Bayesian manner to avoid contradiction between naturalness and fidelity from current GAN-based methods and thus can improve the advantages of GAN. Experimental results revealed that GAN-BVRM improves the fidelity and naturalness, that is, the reconstruction is natural and similar to the presented image stimuli., Comment: brain decoding; visual reconstruction; generative adversarial network (GAN); Bayesian framework. under review in Neuroscience of Elsevier

Deep Learning has thrived on the emergence of biomedical big data. However, medical datasets acquired at different institutions have inherent bias caused by various confounding factors such as operation policies, machine protocols, treatment preference and etc. As the result, models trained on one dataset, regardless of volume, cannot be confidently utilized for the others. In this study, we investigated model robustness to dataset bias using three large-scale Chest X-ray datasets: first, we assessed the dataset bias using vanilla training baseline; second, we proposed a novel multi-source domain generalization model by (a) designing a new bias-regularized loss function; and (b) synthesizing new data for domain augmentation. We showed that our model significantly outperformed the baseline and other approaches on data from unseen domain in terms of accuracy and various bias measures, without retraining or finetuning. Our method is generally applicable to other biomedical data, providing new algorithms for training models robust to bias for big data analysis and applications. Demo training code is publicly available., Comment: 9 pages, 5 figures

Recently, visual encoding based on functional magnetic resonance imaging (fMRI) have realized many achievements with the rapid development of deep network computation. Visual encoding model is aimed at predicting brain activity in response to presented image stimuli. Currently, visual encoding is accomplished mainly by firstly extracting image features through convolutional neural network (CNN) model pre-trained on computer vision task, and secondly training a linear regression model to map specific layer of CNN features to each voxel, namely voxel-wise encoding. However, the two-step manner model, essentially, is hard to determine which kind of well features are well linearly matched for beforehand unknown fMRI data with little understanding of human visual representation. Analogizing computer vision mostly related human vision, we proposed the end-to-end convolution regression model (ETECRM) in the region of interest (ROI)-wise manner to accomplish effective and efficient visual encoding. The end-to-end manner was introduced to make the model automatically learn better matching features to improve encoding performance. The ROI-wise manner was used to improve the encoding efficiency for many voxels. In addition, we designed the selective optimization including self-adapting weight learning and weighted correlation loss, noise regularization to avoid interfering of ineffective voxels in ROI-wise encoding. Experiment demonstrated that the proposed model obtained better predicting accuracy than the two-step manner of encoding models. Comparative analysis implied that end-to-end manner and large volume of fMRI data may drive the future development of visual encoding., Comment: under review in Computational Intelligence and Neuroscience

Recently, visual encoding and decoding based on functional magnetic resonance imaging (fMRI) have realized many achievements with the rapid development of deep network computation. Despite the hierarchically similar representations of deep network and human vision, visual information flows from primary visual cortices to high visual cortices and vice versa based on the bottom-up and top-down manners, respectively. Inspired by the bidirectional information flows, we proposed a bidirectional recurrent neural network (BRNN)-based method to decode the categories from fMRI data. The forward and backward directions in the BRNN module characterized the bottom-up and top-down manners, respectively. The proposed method regarded the selected voxels of each visual cortex region (V1, V2, V3, V4, and LO) as one node in the sequence fed into the BRNN module and combined the output of the BRNN module to decode the categories with the subsequent fully connected layer. This new method allows the efficient utilization of hierarchical information representations and bidirectional information flows in human visual cortices. Experiment results demonstrated that our method improved the accuracy of three-level category decoding than other methods, which implicitly validated the hierarchical and bidirectional human visual representations. Comparative analysis revealed that the category representations of human visual cortices were hierarchical, distributed, complementary, and correlative., Comment: submitted to the Frontiers in neuroscience

Background: Building visual encoding models to accurately predict visual responses is a central challenge for current vision-based brain-machine interface techniques. To achieve high prediction accuracy on neural signals, visual encoding models should include precise visual features and appropriate prediction algorithms. Most existing visual encoding models employ hand-craft visual features (e.g., Gabor wavelets or semantic labels) or data-driven features (e.g., features extracted from deep neural networks (DNN)). They also assume a linear mapping between feature representation to brain activity. However, it remains unknown whether such linear mapping is sufficient for maximizing prediction accuracy. New Method: We construct a new visual encoding framework to predict cortical responses in a benchmark functional magnetic resonance imaging (fMRI) dataset. In this framework, we employ the transfer learning technique to incorporate a pre-trained DNN (i.e., AlexNet) and train a nonlinear mapping from visual features to brain activity. This nonlinear mapping replaces the conventional linear mapping and is supposed to improve prediction accuracy on brain activity. Results: The proposed framework can significantly predict responses of over 20% voxels in early visual areas (i.e., V1-lateral occipital region, LO) and achieve unprecedented prediction accuracy. Comparison with Existing Methods: Comparing to two conventional visual encoding models, we find that the proposed encoding model shows consistent higher prediction accuracy in all early visual areas, especially in relatively anterior visual areas (i.e., V4 and LO). Conclusions: Our work proposes a new framework to utilize pre-trained visual features and train non-linear mappings from visual features to brain activity.

Despite the remarkable similarities between convolutional neural networks (CNN) and the human brain, CNNs still fall behind humans in many visual tasks, indicating that there still exist considerable differences between the two systems. Here, we leverage adversarial noise (AN) and adversarial interference (AI) images to quantify the consistency between neural representations and perceptual outcomes in the two systems. Humans can successfully recognize AI images as corresponding categories but perceive AN images as meaningless noise. In contrast, CNNs can correctly recognize AN images but mistakenly classify AI images into wrong categories with surprisingly high confidence. We use functional magnetic resonance imaging to measure brain activity evoked by regular and adversarial images in the human brain, and compare it to the activity of artificial neurons in a prototypical CNN-AlexNet. In the human brain, we find that the representational similarity between regular and adversarial images largely echoes their perceptual similarity in all early visual areas. In AlexNet, however, the neural representations of adversarial images are inconsistent with network outputs in all intermediate processing layers, providing no neural foundations for perceptual similarity. Furthermore, we show that voxel-encoding models trained on regular images can successfully generalize to the neural responses to AI images but not AN images. These remarkable differences between the human brain and AlexNet in the representation-perception relation suggest that future CNNs should emulate both behavior and the internal neural presentations of the human brain.

In recent years, research on decoding brain activity based on functional magnetic resonance imaging (fMRI) has made remarkable achievements. However, constraint-free natural image reconstruction from brain activity is still a challenge. The existing methods simplified the problem by using semantic prior information or just reconstructing simple images such as letters and digitals. Without semantic prior information, we present a novel method to reconstruct nature images from fMRI signals of human visual cortex based on the computation model of convolutional neural network (CNN). Firstly, we extracted the units output of viewed natural images in each layer of a pre-trained CNN as CNN features. Secondly, we transformed image reconstruction from fMRI signals into the problem of CNN feature visualizations by training a sparse linear regression to map from the fMRI patterns to CNN features. By iteratively optimization to find the matched image, whose CNN unit features become most similar to those predicted from the brain activity, we finally achieved the promising results for the challenging constraint-free natural image reconstruction. As there was no use of semantic prior information of the stimuli when training decoding model, any category of images (not constraint by the training set) could be reconstructed theoretically. We found that the reconstructed images resembled the natural stimuli, especially in position and shape. The experimental results suggest that hierarchical visual features can effectively express the visual perception process of human brain.

We introduce the cross spectrum based FRB (Fast Radio Burst) search method for VLBI observation. This method optimizes the fringe fitting scheme in geodetic VLBI data post processing, which fully utilizes the cross spectrum fringe phase information and therefore maximizes the power of single pulse signals. Working with cross spectrum greatly reduces the effect of radio frequency interference (RFI) compared with using auto spectrum. Single pulse detection confidence increases by cross identifying detections from multiple baselines. By combining the power of multiple baselines, we may improve the detection sensitivity. Our method is similar to that of coherent beam forming, but without the computational expense to form a great number of beams to cover the whole field of view of our telescopes. The data processing pipeline designed for this method is easy to implement and parallelize, which can be deployed in various kinds of VLBI observations. In particular, we point out that VGOS observations are very suitable for FRB search., Comment: Accepted for publication in AJ

In neuroscience, all kinds of computation models were designed to answer the open question of how sensory stimuli are encoded by neurons and conversely, how sensory stimuli can be decoded from neuronal activities. Especially, functional Magnetic Resonance Imaging (fMRI) studies have made many great achievements with the rapid development of the deep network computation. However, comparing with the goal of decoding orientation, position and object category from activities in visual cortex, accurate reconstruction of image stimuli from human fMRI is a still challenging work. In this paper, the capsule network (CapsNet) architecture based visual reconstruction (CNAVR) method is developed to reconstruct image stimuli. The capsule means containing a group of neurons to perform the better organization of feature structure and representation, inspired by the structure of cortical mini column including several hundred neurons in primates. The high-level capsule features in the CapsNet includes diverse features of image stimuli such as semantic class, orientation, location and so on. We used these features to bridge between human fMRI and image stimuli. We firstly employed the CapsNet to train the nonlinear mapping from image stimuli to high-level capsule features, and from high-level capsule features to image stimuli again in an end-to-end manner. After estimating the serviceability of each voxel by encoding performance to accomplish the selecting of voxels, we secondly trained the nonlinear mapping from dimension-decreasing fMRI data to high-level capsule features. Finally, we can predict the high-level capsule features with fMRI data, and reconstruct image stimuli with the CapsNet. We evaluated the proposed CNAVR method on the dataset of handwritten digital images, and exceeded about 10% than the accuracy of all existing state-of-the-art methods on the structural similarity index (SSIM).

Photonic quantum technologies have been extensively studied in quantum information science, owing to the high-speed transmission and outstanding low-noise properties of photons. However, applications based on photonic entanglement are restricted due to the diffraction limit. In this work, we demonstrate for the first time the maintaining of quantum polarization entanglement in a nanoscale hybrid plasmonic waveguide composed of a fiber taper and a silver nanowire. The transmitted state throughout the waveguide has a fidelity of 0.932 with the maximally polarization entangled state {\Phi}+. Furthermore, the Clauser, Horne, Shimony, and Holt (CHSH) inequality test performed, resulting in value of 2.495+/-0.147 > 2, demonstrates the violation of the hidden variable model. Because the plasmonic waveguide confines the effective mode area to subwavelength scale, it can bridge nanophotonics and quantum optics and may be used as near-field quantum probe in a quantum near-field micro/nanoscope, which can realize high spatial resolution, ultrasensitive, fiber-integrated, and plasmon-enhanced detection., Comment: 14 pages, 4 figures

A graph is said to be a cover graph if it is the underlying graph of the Hasse diagram of a finite partially ordered set. The direct product G X H of graphs G and H is the graph having vertex set V(G) X V(H) and edge set E(G X H) = {(g_i,h_s)(g_j,h_t): g_ig_j belongs to E(G) and h_sh_t belongs to E(H)}. We prove that the direct product M_m(G) X M_n(H) of the generalized Mycielskians of G and H is a cover graph if and only if G or H is bipartite., Comment: 9 pages, accepted by Ars Combinatoria on May 13, 2010

This is a computational and experimental study for soot formation and radiative heat transfer in jet diffusion flames under normal gravity (1-g) and microgravity (0-g) conditions. Instantaneous soot volume fraction maps are measured using a full-field imaging absorption technique developed by the authors. A compact, self-contained drop rig is used for microgravity experiments in the 2.2-second drop tower facility at NASA Lewis Research Center. On modeling, we have coupled flame structure and soot formation models with detailed radiation transfer calculations. Favre-averaged boundary layer equations with a k-e-g turbulence model are used to predict the flow field, and a conserved scalar approach with an assumed Beta-pdf are used to predict gaseous species mole fraction. Scalar transport equations are used to describe soot volume fraction and number density distributions, with formation and oxidation terms modeled by one-step rate equations and thermophoretic effects included. An energy equation is included to couple flame structure and radiation analyses through iterations, neglecting turbulence-radiation interactions. The YIX solution for a finite cylindrical enclosure is used for radiative heat transfer calculations. The spectral absorption coefficient for soot aggregates is calculated from the Rayleigh solution using complex refractive index data from a Drude- Lorentz model. The exponential-wide-band model is used to calculate the spectral absorption coefficient for H20 and C02. It is shown that when compared to results from true spectral integration, the Rosseland mean absorption coefficient can provide reasonably accurate predictions for the type of flames studied. The soot formation model proposed by Moss, Syed, and Stewart seems to produce better fits to experimental data and more physically sound than the simpler model by Khan et al. Predicted soot volume fraction and temperature results agree well with published data for a normal gravity co-flow laminar flames and turbulent jet flames. Predicted soot volume fraction results also agree with our data for 1-g and 0-g laminar jet names as well as 1-g turbulent jet flames.

Radiation heat transfer in combustion systems has been receiving increasing interest. In the case of hydrocarbon fuels, a significant portion of the radiation comes from soot particles, justifying the need for detailed soot formation model and radiation transfer calculations. For laminar gas jet diffusion flames, results from this project (4/1/91 8/22/95) and another NASA study show that flame shape, soot concentration, and radiation heat fluxes are substantially different under microgravity conditions. Our emphasis is on including detailed soot transport models and a detailed solution for radiation heat transfer, and on coupling them with the flame structure calculations. In this paper, we will discuss the following three specific areas: (1) Comparing two existing soot formation models, and identifying possible improvements; (2) A simple yet reasonably accurate approach to calculating total radiative properties and/or fluxes over the spectral range; and (3) Investigating the convergence of iterations between the flame structure solver and the radiation heat transfer solver.

Most practical combustion processes, as well as fires and explosions, exhibit some characteristics of turbulent diffusion flames. For hydrocarbon fuels, the presence of soot particles significantly increases the level of radiative heat transfer from flames. In some cases, flame radiation can reach up to 75 percent of the heat release by combustion. Laminar diffusion flame results show that radiation becomes stronger under reduced gravity conditions. Therefore, detailed soot formation and radiation must be included in the flame structure analysis. A study of sooting turbulent diffusion flames under reduced-gravity conditions will not only provide necessary information for such practical issues as spacecraft fire safety, but also develop better understanding of fundamentals for diffusion combustion. In this paper, a summary of the work to date and of future plans is reported.

The article discusses the new normal of trade patterns in Asia following the financial crisis, focusing particularly on China's structural changes and challenges and opportunities represented by these changes. Topics discussed include the role of demographics in Asia's growth trends, increased unit labor costs in China as China approaches the turning point in its urbanization process and a change in the trade landscape in the next decade as China experiences an economic transition.

The article analyzes whether the decade of rapid price growth in China's housing market represents a housing bubble as of December 2012. Topics discussed include the changing landscape of the housing system after 1978, the effect of policies on homeownership, policy measures taken to keep prices from rising too fast, and housing policy lessons from other countries that may be relevant to China.