arXiv subjects

Jin Liu

Publications and source records attributed to Jin Liu.

At least 163 records · Page 9Linked to original sources

arXiv2021

Effectiveness of Artificial Intelligence in Stock Market Prediction based on Machine Learning

This paper tries to address the problem of stock market prediction leveraging artificial intelligence (AI) strategies. The stock market prediction can be modeled based on two principal analyses called technical and fundamental. In the technical analysis approach, the regression machine learning (ML) algorithms are employed to predict the stock price trend at the end of a business day based on the historical price data. In contrast, in the fundamental analysis, the classification ML algorithms are applied to classify the public sentiment based on news and social media. In the technical analysis, the historical price data is exploited from Yahoo Finance, and in fundamental analysis, public tweets on Twitter associated with the stock market are investigated to assess the impact of sentiments on the stock market's forecast. The results show a median performance, implying that with the current technology of AI, it is too soon to claim AI can beat the stock markets.

q-fin.ST↗

arXiv2021

Nanoscale positioning approaches for integrating single epitaxial quantum emitters with photonic nanostructures

Deterministically integrating single solid-state quantum emitters with photonic nanostructures serves as a key enabling resource in the context of photonic quantum technology. Due to the random spatial location of many widely-used solid-state quantum emitters, a number of positoning approaches for locating the quantum emitters before nanofabrication have been explored in the last decade. Here, we review the working principles of several nanoscale positioning methods and the most recent progress in this field, covering techniques including atomic force microscopy, scanning electron microscopy, confocal microscopy with \textit{in situ} lithography, and wide-field fluorescence imaging. A selection of representative device demonstrations with high-performance is presented, including high-quality single-photon sources, bright entangled-photon pairs, strongly-coupled cavity QED systems, and other emerging applications. The challenges in applying positioning techniques to different material systems and opportunities for using these approaches for realizing large-scale quantum photonic devices are discussed.

physics.optics↗

arXiv2021

Dual-Resonance Enhanced Quantum Light-Matter Interactions In Deterministically Coupled Quantum-Dot-Micopillars

Optical microcavities have widely been employed to enhance either the optical excitation or the photon emission processes for boosting light matter interactions at nanoscale. When both the excitation and emission processes are simultaneously facilitated by the optical resonances provided by the microcavities, as referred to the dual-resonance condition in this article, the performances of many nanophotonic devices approach to the optima. In this work, we present versatile accessing of dual-resonance conditions in deterministically coupled quantum-dot(QD)-micopillars, which enables emission from exciton (X) - charged exciton (CX) transition with improved single-photon purity. In addition, the rarely observed up-converted single-photon emission process is achieved under dual-resonance condition. We further exploit the vectorial nature of the high-order cavity modes to significantly improve the excitation efficiency under the dual-resonance condition. The dual-resonance enhanced light-matter interactions in the quantum regime provides a viable path for developing integrated quantum photonic devices based on cavity quantum electrodynamics (QED) effect e.g., highly-efficient quantum light sources and quantum logical gates.

physics.optics↗

arXiv2021

LI-Net: Large-Pose Identity-Preserving Face Reenactment Network

Face reenactment is a challenging task, as it is difficult to maintain accurate expression, pose and identity simultaneously. Most existing methods directly apply driving facial landmarks to reenact source faces and ignore the intrinsic gap between two identities, resulting in the identity mismatch issue. Besides, they neglect the entanglement of expression and pose features when encoding driving faces, leading to inaccurate expressions and visual artifacts on large-pose reenacted faces. To address these problems, we propose a Large-pose Identity-preserving face reenactment network, LI-Net. Specifically, the Landmark Transformer is adopted to adjust driving landmark images, which aims to narrow the identity gap between driving and source landmark images. Then the Face Rotation Module and the Expression Enhancing Generator decouple the transformed landmark image into pose and expression features, and reenact those attributes separately to generate identity-preserving faces with accurate expressions and poses. Both qualitative and quantitative experimental results demonstrate the superiority of our method.

cs.CV↗

arXiv2021

Predicting Crash Fault Residence via Simplified Deep Forest Based on A Reduced Feature Set

The software inevitably encounters the crash, which will take developers a large amount of effort to find the fault causing the crash (short for crashing fault). Developing automatic methods to identify the residence of the crashing fault is a crucial activity for software quality assurance. Researchers have proposed methods to predict whether the crashing fault resides in the stack trace based on the features collected from the stack trace and faulty code, aiming at saving the debugging effort for developers. However, previous work usually neglected the feature preprocessing operation towards the crash data and only used traditional classification models. In this paper, we propose a novel crashing fault residence prediction framework, called ConDF, which consists of a consistency based feature subset selection method and a state-of-the-art deep forest model. More specifically, first, the feature selection method is used to obtain an optimal feature subset and reduce the feature dimension by reserving the representative features. Then, a simplified deep forest model is employed to build the classification model on the reduced feature set. The experiments on seven open source software projects show that our ConDF method performs significantly better than 17 baseline methods on three performance indicators.

cs.SE↗

arXiv2021

DeepMI: Deep Multi-lead ECG Fusion for Identifying Myocardial Infarction and its Occurrence-time

Myocardial Infarction (MI) has the highest mortality of all cardiovascular diseases (CVDs). Detection of MI and information regarding its occurrence-time in particular, would enable timely interventions that may improve patient outcomes, thereby reducing the global rise in CVD deaths. Electrocardiogram (ECG) recordings are currently used to screen MI patients. However, manual inspection of ECGs is time-consuming and prone to subjective bias. Machine learning methods have been adopted for automated ECG diagnosis, but most approaches require extraction of ECG beats or consider leads independently of one another. We propose an end-to-end deep learning approach, DeepMI, to classify MI from normal cases as well as identifying the time-occurrence of MI (defined as acute, recent and old), using a collection of fusion strategies on 12 ECG leads at data-, feature-, and decision-level. In order to minimise computational overhead, we employ transfer learning using existing computer vision networks. Moreover, we use recurrent neural networks to encode the longitudinal information inherent in ECGs. We validated DeepMI on a dataset collected from 17,381 patients, in which over 323,000 samples were extracted per ECG lead. We were able to classify normal cases as well as acute, recent and old onset cases of MI, with AUROCs of 96.7%, 82.9%, 68.6% and 73.8%, respectively. We have demonstrated a multi-lead fusion approach to detect the presence and occurrence-time of MI. Our end-to-end framework provides flexibility for different levels of multi-lead ECG fusion and performs feature extraction via transfer learning.

eess.SP↗

arXiv2020

Multi-grained Trajectory Graph Convolutional Networks for Habit-unrelated Human Motion Prediction

Human motion prediction is an essential part for human-robot collaboration. Unlike most of the existing methods mainly focusing on improving the effectiveness of spatiotemporal modeling for accurate prediction, we take effectiveness and efficiency into consideration, aiming at the prediction quality, computational efficiency and the lightweight of the model. A multi-grained trajectory graph convolutional networks based and lightweight framework is proposed for habit-unrelated human motion prediction. Specifically, we represent human motion as multi-grained trajectories, including joint trajectory and sub-joint trajectory. Based on the advanced representation, multi-grained trajectory graph convolutional networks are proposed to explore the spatiotemporal dependencies at the multiple granularities. Moreover, considering the right-handedness habit of the vast majority of people, a new motion generation method is proposed to generate the motion with left-handedness, to better model the motion with less bias to the human habit. Experimental results on challenging datasets, including Human3.6M and CMU Mocap, show that the proposed model outperforms state-of-the-art with less than 0.12 times parameters, which demonstrates the effectiveness and efficiency of our proposed method.

cs.CV↗

arXiv2020

BOLT-SSI: A Statistical Approach to Screening Interaction Effects for Ultra-High Dimensional Data

Detecting interaction effects among predictors on the response variable is a crucial step in various applications. In this paper, we first propose a simple method for sure screening interactions (SSI). Although its computation complexity is $O(p^2n)$, SSI works well for problems of moderate dimensionality (e.g., $p=10^3\sim10^4$), without the heredity assumption. To ultra-high dimensional problems (e.g., $p = 10^6$), motivated by discretization associated Boolean representation and operations and the contingency table for discrete variables, we propose a fast algorithm, named "BOLT-SSI". The statistical theory has been established for SSI and BOLT-SSI, guaranteeing their sure screening property. The performance of SSI and BOLT-SSI are evaluated by comprehensive simulation and real case studies. Numerical results demonstrate that SSI and BOLT-SSI can often outperform their competitors in terms of computational efficiency and statistical accuracy. The proposed method can be applied for fully detecting interactions with more than 300,000 predictors. Based on this study, we believe that there is a great need to rethink the relationship between statistical accuracy and computational efficiency. We have shown that the computational performance of a statistical method can often be greatly improved by exploring the advantages of computational architecture with a tolerable loss of statistical accuracy.

stat.ME↗

arXiv2020

Generative Learning With Euler Particle Transport

We propose an Euler particle transport (EPT) approach for generative learning. The proposed approach is motivated by the problem of finding an optimal transport map from a reference distribution to a target distribution characterized by the Monge-Ampere equation. Interpreting the infinitesimal linearization of the Monge-Ampere equation from the perspective of gradient flows in measure spaces leads to a stochastic McKean-Vlasov equation. We use the forward Euler method to solve this equation. The resulting forward Euler map pushes forward a reference distribution to the target. This map is the composition of a sequence of simple residual maps, which are computationally stable and easy to train. The key task in training is the estimation of the density ratios or differences that determine the residual maps. We estimate the density ratios (differences) based on the Bregman divergence with a gradient penalty using deep density-ratio (difference) fitting. We show that the proposed density-ratio (difference) estimators do not suffer from the "curse of dimensionality" if data is supported on a lower-dimensional manifold. Numerical experiments with multi-mode synthetic datasets and comparisons with the existing methods on real benchmark datasets support our theoretical results and demonstrate the effectiveness of the proposed method.

cs.LG↗

arXiv2020

Accounting for correlated horizontal pleiotropy in two-sample Mendelian randomization using correlated instrumental variants

Mendelian randomization (MR) is a powerful approach to examine the causal relationships between health risk factors and outcomes from observational studies. Due to the proliferation of genome-wide association studies (GWASs) and abundant fully accessible GWASs summary statistics, a variety of two-sample MR methods for summary data have been developed to either detect or account for horizontal pleiotropy, primarily based on the assumption that the effects of variants on exposure (γ) and horizontal pleiotropy (α) are independent. This assumption is too strict and can be easily violated because of the correlated horizontal pleiotropy (CHP). To account for this CHP, we propose a Bayesian approach, MR-Corr2, that uses the orthogonal projection to reparameterize the bivariate normal distribution for γ and α, and a spike-slab prior to mitigate the impact of CHP. We develop an efficient algorithm with paralleled Gibbs sampling. To demonstrate the advantages of MR-Corr2 over existing methods, we conducted comprehensive simulation studies to compare for both type-I error control and point estimates in various scenarios. By applying MR-Corr2 to study the relationships between pairs in two sets of complex traits, we did not identify the contradictory causal relationship between HDL-c and CAD. Moreover, the results provide a new perspective of the causal network among complex traits. The developed R package and code to reproduce all the results are available at https://github.com/QingCheng0218/MR.Corr2.

stat.ME↗

arXiv2020

Large few-layer hexagonal boron nitride flakes for nonlinear optics

Hexagonal boron nitride (hBN) is a layered dielectric material with a wide range of applications in optics and photonics. In this work, we demonstrate a fabrication method for few-layer hBN flakes with areas up to 5000 $\rm μm$. We show that hBN in this form can be integrated with photonic microstructures: as an example, we use a circular Bragg grating (CBG). The layer quality of the exfoliated hBN flake on a CBG is confirmed by second-harmonic generation (SHG) microscopy. We show that the SHG signal is uniform across the hBN sample outside the CBG and is amplified in the centre of the CBG.

physics.app-ph↗

arXiv2020

A highly efficient integrated source of twisted single-photons

Photons with a helical phase front (twisted photons) can carry a discrete, in principle, unbounded amount of orbital angular momentum (OAM). Twisted single-photons have been demonstrated as a high-dimensional quantum system with information processing ability far beyond the widely used two-level qubits. To date, the generations of single-photons carrying OAM merely rely on the non-linear process in bulk crystals, e.g., spontaneous parametric down-conversion (SPDC), which unavoidably limits both the efficiency and the scalability of the source. Therefore, an on-demand OAM quantum light source on a semiconductor chip is yet illusive and highly desirable for integrated photonic quantum technologies. Here we demonstrate highly-efficient emission of twisted single-photons from solid-state quantum emitters embedded in a microring with angular gratings. The cavity QED effect allows the generations of single-photons and encoding OAM in the same nanostructure and therefore enables the realization of devices with very small footprints and great scalability. The OAM states of singe-photons are clearly identified via quantum interference of single-photons with themselves. Our device may boost the development of integrated quantum photonic devices with potential applications towards high-dimensional quantum information processing.

physics.optics↗

arXiv2020

TrajectoryNet: a new spatio-temporal feature learning network for human motion prediction

Human motion prediction is an increasingly interesting topic in computer vision and robotics. In this paper, we propose a new 2D CNN based network, TrajectoryNet, to predict future poses in the trajectory space. Compared with most existing methods, our model focuses on modeling the motion dynamics with coupled spatio-temporal features, local-global spatial features and global temporal co-occurrence features of the previous pose sequence. Specifically, the coupled spatio-temporal features describe the spatial and temporal structure information hidden in the natural human motion sequence, which can be mined by covering the space and time dimensions of the input pose sequence with the convolutional filters. The local-global spatial features that encode different correlations of different joints of the human body (e.g. strong correlations between joints of one limb, weak correlations between joints of different limbs) are captured hierarchically by enlarging the receptive field layer by layer and residual connections from the lower layers to the deeper layers in our proposed convolutional network. And the global temporal co-occurrence features represent the co-occurrence relationship that different subsequences in a complex motion sequence are appeared simultaneously, which can be obtained automatically with our proposed TrajectoryNet by reorganizing the temporal information as the depth dimension of the input tensor. Finally, future poses are approximated based on the captured motion dynamics features. Extensive experiments show that our method achieves state-of-the-art performance on three challenging benchmarks (e.g. Human3.6M, G3D, and FNTU), which demonstrates the effectiveness of our proposed method. The code will be available if the paper is accepted.

cs.CV↗

arXiv2020

A Novel Recurrent Encoder-Decoder Structure for Large-Scale Multi-view Stereo Reconstruction from An Open Aerial Dataset

A great deal of research has demonstrated recently that multi-view stereo (MVS) matching can be solved with deep learning methods. However, these efforts were focused on close-range objects and only a very few of the deep learning-based methods were specifically designed for large-scale 3D urban reconstruction due to the lack of multi-view aerial image benchmarks. In this paper, we present a synthetic aerial dataset, called the WHU dataset, we created for MVS tasks, which, to our knowledge, is the first large-scale multi-view aerial dataset. It was generated from a highly accurate 3D digital surface model produced from thousands of real aerial images with precise camera parameters. We also introduce in this paper a novel network, called RED-Net, for wide-range depth inference, which we developed from a recurrent encoder-decoder structure to regularize cost maps across depths and a 2D fully convolutional network as framework. RED-Net's low memory requirements and high performance make it suitable for large-scale and highly accurate 3D Earth surface reconstruction. Our experiments confirmed that not only did our method exceed the current state-of-the-art MVS methods by more than 50% mean absolute error (MAE) with less memory and computational cost, but its efficiency as well. It outperformed one of the best commercial software programs based on conventional methods, improving their efficiency 16 times over. Moreover, we proved that our RED-Net model pre-trained on the synthetic WHU dataset can be efficiently transferred to very different multi-view aerial image datasets without any fine-tuning. Dataset are available at http://gpcv.whu.edu.cn/data.

cs.CV↗

arXiv2020

Old Story New Tell: The Graphite to Diamond Transition Revisited

Graphite and diamond are two well-known allotropes of carbon with distinct physical properties due to different atomic connectivity. Graphite has a layered structure in which the honeycomb carbon sheets can easily glide, while atoms in diamond are strongly bonded in all three dimensions. The transition from graphite to diamond has been a central subject in physical science. One way to turn graphite into diamond is to apply the high pressure and high temperature (HPHT) conditions. However, atomistic mechanism of this transition is still under debate. From a series of large-scale molecular dynamics (MD) simulations, we report a mechanism that the diamond nuclei originate at the graphite grain boundaries and propagate in two preferred directions. In addition to the widely accepted [001] direction, we found that the growth along [120] direction of graphite is even faster. In this scenario, cubic diamond (CD) is the kinetically favorable product, while hexagonal diamond (HD) would appear as minor amounts of twinning structures in two main directions. Following the crystallographic orientation relationship, the coherent interface t-(100)gr//(11-1)cd + [010]gr//[1-10]cd was also confirmed by high-resolution transmission electron microscopy (HR-TEM) experiment. The proposed phase transition mechanism does not only reconcile the longstanding debate regarding the role of HD in graphite-diamond transition, but also yields the atomistic insight into microstructure engineering via controlled solid phase transition.

cond-mat.mtrl-sci↗

arXiv2020

Learning Implicit Generative Models with Theoretical Guarantees

We propose a \textbf{uni}fied \textbf{f}ramework for \textbf{i}mplicit \textbf{ge}nerative \textbf{m}odeling (UnifiGem) with theoretical guarantees by integrating approaches from optimal transport, numerical ODE, density-ratio (density-difference) estimation and deep neural networks. First, the problem of implicit generative learning is formulated as that of finding the optimal transport map between the reference distribution and the target distribution, which is characterized by a totally nonlinear Monge-Ampère equation. Interpreting the infinitesimal linearization of the Monge-Ampère equation from the perspective of gradient flows in measure spaces leads to the continuity equation or the McKean-Vlasov equation. We then solve the McKean-Vlasov equation numerically using the forward Euler iteration, where the forward Euler map depends on the density ratio (density difference) between the distribution at current iteration and the underlying target distribution. We further estimate the density ratio (density difference) via deep density-ratio (density-difference) fitting and derive explicit upper bounds on the estimation error. Experimental results on both synthetic datasets and real benchmark datasets support our theoretical findings and demonstrate the effectiveness of UnifiGem.

cs.LG↗

arXiv2020

A Support Detection and Root Finding Approach for Learning High-dimensional Generalized Linear Models

Feature selection is important for modeling high-dimensional data, where the number of variables can be much larger than the sample size. In this paper, we develop a support detection and root finding procedure to learn the high dimensional sparse generalized linear models and denote this method by GSDAR. Based on the KKT condition for $\ell_0$-penalized maximum likelihood estimations, GSDAR generates a sequence of estimators iteratively. Under some restricted invertibility conditions on the maximum likelihood function and sparsity assumption on the target coefficients, the errors of the proposed estimate decays exponentially to the optimal order. Moreover, the oracle estimator can be recovered if the target signal is stronger than the detectable level. We conduct simulations and real data analysis to illustrate the advantages of our proposed method over several existing methods, including Lasso and MCP.

stat.ML↗

arXiv2019

Room temperature nanocavity laser with interlayer excitons in 2D heterostructures

Atomically thin layered two dimensional (2D) material has provided a rich library for both fundamental research and device applications. One of the special advantages is that, bandgap engineering and controlled material response can be achieved by stacking different 2D materials. Recently several types of excitonic lasers have been reported based on Transition metal dichalcogenide (TMDC) monolayers, however, the emission is still the intrinsic energy bandgap of the monolayers and lasers harnessing the flexibility of Van der Waals heterostructures have not been demonstrated yet. Here, we report for the first time a room temperature interlayer exciton laser with MoS2/WSe2 heterostructures. The onset of lasing action was identified by a combination of distinct kink in the 'L-L' curve and the noticeable collapse of spectral linewidth. Different from visible emission of intralayer excitons for both MoS2 and WSe2, our interlayer exciton laser works in the infrared range, which is fully compatible with the well-established technologies in silicon photonics. Thanks to the long lifetime of interlayer excitons, the requirement of the cavity quality factor is relaxed by orders of magnitude. The demonstration of room temperature interlayer exciton laser might open new perspectives for the development of coherent light source with tailored optical properties on silicon photonics platform.

cond-mat.mes-hall↗