Time-series is ubiquitous across applications, such as transportation, finance and healthcare. Time-series is often influenced by external factors, especially in the form of asynchronous events, making forecasting difficult. However, existing models
are mainly designated for either synchronous time-series or asynchronous event sequence, and can hardly provide a synthetic way to capture the relation between them. We propose Variational Synergetic Multi-Horizon Network (VSMHN), a novel deep conditional generative model. To learn complex correlations across heterogeneous sequences, a tailored encoder is devised to combine the advances in deep point processes models and variational recurrent neural networks. In addition, an aligned time coding and an auxiliary transition scheme are carefully devised for batched training on unaligned sequences. Our model can be trained effectively using stochastic variational inference and generates probabilistic predictions with Monte-Carlo simulation. Furthermore, our model produces accurate, sharp and more realistic probabilistic forecasts. We also show that modeling asynchronous event sequences is crucial for multi-horizon time-series forecasting.
We study ridge correlations of the glasma in pp collisions at $sqrt{s_{mathrm{NN}}}=7$ TeV by using the color glass condensate (CGC) formalism. The azimuthal collimation at long range rapidity is intrinsic to glasma dynamics and is reproduced here. W
hen rapidity window enlarges, ridge correlations in two dimensional $Delta y$-$Deltaphi$ distribution and one dimensional $Deltaphi$ distribution at long range rapidity gap are enhanced. The enhancements are demonstrated to be the contributions of source gluons. The quantum evolution of the gluons presents unique correlation patterns in differential correlation function. These characters of two gluon correlations open a way of testing the production mechanism from experimental measurements.
This work presents a rigorous theory for topological photonic materials in one dimension. The main focus is on the existence and stability of interface modes that are induced by topological properties of the bulk structure. For a general 1D photonic
structure with time-reversal symmetry, the associated Zak phase (or Berry phase) may not be quantized. We investigate the existence of an interface mode which is induced by a Dirac point upon perturbation. Specifically, we establish conditions on the perturbation which guarantee the opening of a band gap around the Dirac point and the existence of an interface mode. For a periodic photonic structure with both time-reversal and inversion symmetry, the Zak phase is quantized, taking only two values $0, pi$. We show that the Zak phase is determined by the parity (even or odd) of the Bloch modes at the band edges. For a photonic structure consisting of two semi-infinite systems on the two sides of an interface with distinct topological indices, we show the existence of an interface mode inside the common gap. The stability of the mode under perturbations is also investigated. Finally, we study resonances for finite topological structures. Our results are based on the transfer matrix method and the oscillation theory for Sturm-Liouville operators. The methods and results can be extended to general topological Sturm-Liouville systems in one dimension.
Simultaneous EEG-fMRI acquisition and analysis technology has been widely used in various research fields of brain science. However, how to remove the ballistocardiogram (BCG) artifacts in this scenario remains a huge challenge. Because it is impossi
ble to obtain clean and BCG-contaminated EEG signals at the same time, BCG artifact removal is a typical unpaired signal-to-signal problem. To solve this problem, this paper proposed a new GAN training model - Single Shot Reversible GAN (SSRGAN). The model is allowing bidirectional input to better combine the characteristics of the two types of signals, instead of using two independent models for bidirectional conversion as in the past. Furthermore, the model is decomposed into multiple independent convolutional blocks with specific functions. Through additional training of the blocks, the local representation ability of the model is improved, thereby improving the overall model performance. Experimental results show that, compared with existing methods, the method proposed in this paper can remove BCG artifacts more effectively and retain the useful EEG information.
We study quantum quenches of helical liquids with spin-flip inelastic scattering. Counterpropagating charge packets in helical edges can be created by an ultrashort electric pulse applied across a 2D topological insulator. Localized hot spots that fo
rm due to scattering enable two types of strongly nonlinear wave dynamics. First, propagating packets develop self-focusing shock fronts. Second, colliding packets with opposite charge can exhibit near-perfect retroreflection, despite strong dissipation. This leads to frequency doubling that could be detected experimentally from emitted terahertz radiation.
Automated segmentation of individual calf muscle compartments from 3D magnetic resonance (MR) images is essential for developing quantitative biomarkers for muscular disease progression and its prediction. Achieving clinically acceptable results is a
challenging task due to large variations in muscle shape and MR appearance. Although deep convolutional neural networks (DCNNs) achieved improved accuracy in various image segmentation tasks, certain problems such as utilizing long-range information and incorporating high-level constraints remain unsolved. We present a novel fully convolutional network (FCN), called FilterNet, that utilizes contextual information in a large neighborhood and embeds edge-aware constraints for individual calf muscle compartment segmentations. An encoder-decoder architecture with flexible backbone blocks is used to systematically enlarge convolution receptive field and preserve information at all resolutions. Edge positions derived from the FCN output muscle probability maps are explicitly regularized using kernel-based edge detection in an end-to-end optimization framework. Our FilterNet was evaluated on 40 T1-weighted MR images of 10 healthy and 30 diseased subjects by 4-fold cross-validation. Mean DICE coefficients of 88.00%--91.29% and mean absolute surface positioning errors of 1.04--1.66 mm were achieved for the five 3D muscle compartments.
This work presents a new super-resolution imaging approach by using subwavelength hole resonances. We employ a subwavelength structure in which an array of tiny holes are etched in a metallic slab with the neighboring distance $ell$ that is smaller t
han half of the wavelength. By tuning the incident wave at resonant frequencies, the subwavelength structure generates strong illumination patterns that are able to probe both low and high spatial frequency components of the imaging sample sitting above the structure. The image of the sample is obtained by performing stable numerical reconstruction from the far-field measurement of the diffracted wave. It is demonstrated that a resolution of $ell/2$ can be obtained for reconstructed images, thus one can achieve super-resolution by arranging multiple holes within one wavelength. The proposed approach may find applications in wave-based imaging such as electromagnetic and ultrasound imaging. It attains two advantages that are important for practical realization. It avoids the difficulty to control the distance the between the probe and the sample surface with high precision. In addition, the numerical reconstructed images are very stable against noise by only using the low frequency band of the far-field data in the numerical reconstruction.
Voice traffic prediction is significant for network deployment optimization thus to improve the network efficiency. The real entropy based theorectical bound and corresponding prediction models have demonstrated their success in mobility prediction.
In this paper, the real entropy based predictability analysis and prediction models are introduced into voice traffic prediction. For this adoption, the traffic quantification methods is proposed and discussed. Based on the real world voice traffic data, the prediction accuracy of N-order Markov models, diffusion based model and MF model are presented, among which, 25-order Markov models performs best and approach close to the maximum predictability. This work demonstrates that, the real entropy can also predict voice traffic well which broaden the understanding on the real entropy based prediction theory.
State-of-the-art automated segmentation algorithms are not 100% accurate especially when segmenting difficult to interpret datasets like those with severe osteoarthritis (OA). We present a novel interactive method called just-enough interaction (JEI)
, which adds a fast correction step to the automated layered optimal graph segmentation of multiple objects and surfaces (LOGISMOS). After LOGISMOS segmentation in knee MRI, the JEI user interaction does not modify boundary surfaces of the bones and cartilages directly. Local costs of underlying graph nodes are modified instead and the graph is re-optimized, providing globally optimal corrected results. Significant performance improvement ($p ll 0.001$) was observed when comparing JEI-corrected results to the automated. The algorithm was extended from 3D JEI to longitudinal multi-3D (4D) JEI allowing simultaneous visualization and interaction of multiple-time points of the same patient.
We present a fully automated learning-based approach for segmenting knee cartilage in the presence of osteoarthritis (OA). The algorithm employs a hierarchical set of two random forest classifiers. The first is a neighborhood approximation forest, th
e output probability map of which is utilized as a feature set for the second random forest (RF) classifier. The output probabilities of the hierarchical approach are used as cost functions in a Layered Optimal Graph Segmentation of Multiple Objects and Surfaces (LOGISMOS). In this work, we highlight a novel post-processing interaction called just-enough interaction (JEI) which enables quick and accurate generation of a large set of training examples. Disjoint sets of 15 and 13 subjects were used for training and tested on another disjoint set of 53 knee datasets. All images were acquired using a double echo steady state (DESS) MRI sequence and are from the osteoarthritis initiative (OAI) database. Segmentation performance using the learning-based cost function showed significant reduction in segmentation errors ($p< 0.05$) in comparison with conventional gradient-based cost functions.
