arXiv subjects

Jie Li

Publications and source records attributed to Jie Li.

At least 631 records · Page 35Linked to original sources

arXiv2019

Trident Segmentation CNN: A Spatiotemporal Transformation CNN for Punctate White Matter Lesions Segmentation in Preterm Neonates

Accurate segmentation of punctate white matter lesions (PWML) in preterm neonates by an automatic algorithm can better assist doctors in diagnosis. However, the existing algorithms have many limitations, such as low detection accuracy and large resource consumption. In this paper, a novel spatiotemporal transformation deep learning method called Trident Segmentation CNN (TS-CNN) is proposed to segment PWML in MR images. It can convert spatial information into temporal information, which reduces the consumption of computing resources. Furthermore, a new improved training loss called Self-balancing Focal Loss (SBFL) is proposed to balance the loss during the training process. The whole model is evaluated on a dataset of 704 MR images. Overall the method achieves median DSC, sensitivity, specificity, and Hausdorff distance of 0.6355, 0.7126, 0.9998, and 24.5836 mm which outperforms the state-of-the-art algorithm. (The code is now available on https://github.com/YalongLiu/Trident-Segmentation-CNN)

eess.IV↗

arXiv2019

AF-DCGAN: Amplitude Feature Deep Convolutional GAN for Fingerprint Construction in Indoor Localization Systems

With widely deployed WiFi network and the uniqueness feature (fingerprint) of wireless channel information, fingerprinting based WiFi positioning is currently the mainstream indoor positioning method, in which fingerprint database construction is crucial. However, for accuracy, this approach requires enough data to be sampled at many reference points, which consumes excessive efforts and time. In this paper, we collect Channel State Information (CSI) data at reference points by the method of device-free localization, then we convert collected CSI data into amplitude feature maps and extend the fingerprint database using the proposed Amplitude-Feature Deep Convolutional Generative Adversarial Network (AF-DCGAN) model. The use of AF-DCGAN accelerates convergence during the training phase, and substantially increases the diversity of the CSI amplitude feature map. The extended fingerprint database both reduces the human effort involved in fingerprint database construction and the accuracy of an indoor localization system, as demonstrated in the experiments.

cs.NI↗

arXiv2019

Node similarity distribution of complex networks and its application in link prediction

Over the years, quantifying the similarity of nodes has been a hot topic in complex networks, yet little has been known about the distributions of node-similarity. In this paper, we consider a typical measure of node-similarity called the common neighbor based similarity (CNS). By means of the generating function, we propose a general framework for calculating the CNS distributions of node sets in various complex networks. In particular, we show that for the Erdös-Rényi (ER) random network, the CNS distribution of node sets of any particular size obeys the Poisson law. We also connect the node-similarity distribution to the link prediction problem. We found that the performance of link prediction depends solely on the CNS distributions of the connected and unconnected node pairs in the network. Furthermore, we derive theoretical solutions of two key evaluation metrics in link prediction: i) precision and ii) area under the receiver operating characteristic curve (AUC). We show that for any link prediction method, if the similarity distributions of the connected and unconnected node pairs are identical, the AUC will be $0.5$. The theoretical solutions are elegant alternatives of the traditional experimental evaluation methods with nevertheless much lower computational cost.

cs.SI↗

arXiv2019

ViLiVO: Virtual LiDAR-Visual Odometry for an Autonomous Vehicle with a Multi-Camera System

In this paper, we present a multi-camera visual odometry (VO) system for an autonomous vehicle. Our system mainly consists of a virtual LiDAR and a pose tracker. We use a perspective transformation method to synthesize a surround-view image from undistorted fisheye camera images. With a semantic segmentation model, the free space can be extracted. The scans of the virtual LiDAR are generated by discretizing the contours of the free space. As for the pose tracker, we propose a visual odometry system fusing both the feature matching and the virtual LiDAR scan matching results. Only those feature points located in the free space area are utilized to ensure the 2D-2D matching for pose estimation. Furthermore, bundle adjustment (BA) is performed to minimize the feature points reprojection error and scan matching error. We apply our system to an autonomous vehicle equipped with four fisheye cameras. The testing scenarios include an outdoor parking lot as well as an indoor garage. Experimental results demonstrate that our system achieves a more robust and accurate performance comparing with a fisheye camera based monocular visual odometry system.

cs.CV↗

arXiv2019

Identifying significant edges via neighborhood information

Heterogeneous nature of real networks implies that different edges play different roles in network structure and functions, and thus to identify significant edges is of high value in both theoretical studies and practical applications. We propose the so-called second-order neighborhood (SN) index to quantify an edge's significance in a network. We compare SN index with many other benchmark methods based on 15 real networks via edge percolation. Results show that the proposed SN index outperforms other well-known methods.

physics.soc-ph↗

arXiv2019

Crash dynamics of interdependent networks

The emergence and evolution of real-world systems have been extensively studied in the last few years. However, equally important phenomena are related to the dynamics of systems' collapse, which has been less explored, especially when they can be cast into interdependent systems. In this paper, we develop a dynamical model that allows scrutinizing the collapse of systems composed of two interdependent networks. Specifically, we explore the dynamics of the system's collapse under two scenarios: in the first one, the condition for failure should be satisfied for the focal node as well as for its corresponding node in the other network; while in the second one, it is enough that failure of one of the nodes occurs in either of the two networks. We report extensive numerical simulations of the dynamics performed in different setups of interdependent networks, and analyze how the system behavior depends on the previous scenarios as well as on the topology of the interdependent system. Our results can provide valuable insights into the crashing dynamics and evolutionary properties of interdependent complex systems.

physics.soc-ph↗

arXiv2019

Universal Perturbation Attack Against Image Retrieval

Universal adversarial perturbations (UAPs), a.k.a. input-agnostic perturbations, has been proved to exist and be able to fool cutting-edge deep learning models on most of the data samples. Existing UAP methods mainly focus on attacking image classification models. Nevertheless, little attention has been paid to attacking image retrieval systems. In this paper, we make the first attempt in attacking image retrieval systems. Concretely, image retrieval attack is to make the retrieval system return irrelevant images to the query at the top ranking list. It plays an important role to corrupt the neighbourhood relationships among features in image retrieval attack. To this end, we propose a novel method to generate retrieval-against UAP to break the neighbourhood relationships of image features via degrading the corresponding ranking metric. To expand the attack method to scenarios with varying input sizes or untouchable network parameters, a multi-scale random resizing scheme and a ranking distillation strategy are proposed. We evaluate the proposed method on four widely-used image retrieval datasets, and report a significant performance drop in terms of different metrics, such as mAP and mP@10. Finally, we test our attack methods on the real-world visual search engine, i.e., Google Images, which demonstrates the practical potentials of our methods.

cs.CV↗

arXiv2019

Possible Realization and Protection of Valley-Polarized Quantum Hall Effect in Mn/WS2

By using the first-principles calculations and model analyses, we found that the combination of defected tungsten disulfide monolayer and sparse manganese adsorption may give a KK` valley spin splitting up to 210 meV. This system also has a tunable magnetic anisotropy energy, a clean band gap, and an appropriate band alignment, with the Fermi level sitting right above the top of valence bands at the K-valleys. Therefore, it can be used for the realization of the valley-polarized anomalous Hall effect and for the exploration of other valley related physics without using optical methods. A protective environment can be formed by covering it with a hexagonal BN layer, without much disturbance to the benign properties of Mn/WS2.

cond-mat.mes-hall↗

arXiv2019

The Design and Implementation of a Real Time Visual Search System on JD E-commerce Platform

We present the design and implementation of a visual search system for real time image retrieval on JD.com, the world's third largest and China's largest e-commerce site. We demonstrate that our system can support real time visual search with hundreds of billions of product images at sub-second timescales and handle frequent image updates through distributed hierarchical architecture and efficient indexing methods. We hope that sharing our practice with our real production system will inspire the middleware community's interest and appreciation for building practical large scale systems for emerging applications, such as ecommerce visual search.

cs.IR↗

arXiv2019

SleepGuardian: An RF-based Healthcare System Guarding Your Sleep from Afar

The ever accelerating process of urbanization urges more and more population into the swelling cities. While city residents are enjoying an entertaining life supported by advanced informatics techniques like 5G and cloud computing, the same technologies have also gradually deprived their sleep, which is crucial for their wellness. Therefore, sleep monitoring has drawn significant attention from both research and industry communities. In this article, we first review the sleep monitoring issue and point out three essential properties of an ideal sleep healthcare system, i.e., realtime guarding, fine-grained logging, and cost-effectiveness. Based on the analysis, we present SleepGuardian, a Radio Frequence (RF) based sleep healthcare system leveraging signal processing, edge computing and machine learning.SleepGuardian offers an offline sleep logging service and an online abnormality warning service. The offline service provides a fine-grained sleep log like timing and regularity of bed time, onset of sleep and night time awakenings. The online service keeps guarding the subject for any abnormal behaviors during sleep like intensive body twitches and a sudden seizure attack. Once an abnormality happens,it will automatically warn the designated contacts like a nearby emergency room or a closeby relative.We prototype SleepGuardian with low-cost WiFi devices and evaluate it in real scenarios. Experimental results demonstrate that SleepGuardian is very effective.

eess.SP↗

arXiv2019

PosNeg-Balanced Anchors with Aligned Features for Single-Shot Object Detection

We introduce a novel single-shot object detector to ease the imbalance of foreground-background class by suppressing the easy negatives while increasing the positives. To achieve this, we propose an Anchor Promotion Module (APM) which predicts the probability of each anchor as positive and adjusts their initial locations and shapes to promote both the quality and quantity of positive anchors. In addition, we design an efficient Feature Alignment Module (FAM) to extract aligned features for fitting the promoted anchors with the help of both the location and shape transformation information from the APM. We assemble the two proposed modules to the backbone of VGG-16 and ResNet-101 network with an encoder-decoder architecture. Extensive experiments on MS COCO well demonstrate our model performs competitively with alternative methods (40.0\% mAP on \textit{test-dev} set) and runs faster (28.6 \textit{fps}).

cs.CV↗

arXiv2019

Entangling two magnon modes via magnetostrictive interaction

We present a scheme to entangle two magnon modes in a cavity magnomechanical system. The two magnon modes are embodied by collective motions of a large number of spins in two macroscopic ferrimagnets, and couple to a single microwave cavity mode via magnetic dipole interaction. We show that by activating the nonlinear magnetostrictive interaction in one ferrimagnet, realized by driving the magnon mode with a strong red-detuned microwave field, the two magnon modes can be prepared in an entangled state. The entanglement is achieved by exploiting the nonlinear magnon-phonon coupling and the linear magnon-cavity coupling, and is in the steady state and robust against temperature. The entangled magnon modes in two massive ferrimagnets represent genuinely macroscopic quantum states, and may find applications in the study of macroscopic quantum mechanics and quantum information processing based on magnonics.

quant-ph↗

arXiv2019

Refined-Segmentation R-CNN: A Two-stage Convolutional Neural Network for Punctate White Matter Lesion Segmentation in Preterm Infants

Accurate segmentation of punctate white matter lesion (PWML) in infantile brains by an automatic algorithm can reduce the potential risk of postnatal development. How to segment PWML effectively has become one of the active topics in medical image segmentation in recent years. In this paper, we construct an efficient two-stage PWML semantic segmentation network based on the characteristics of the lesion, called refined segmentation R-CNN (RS RCNN). We propose a heuristic RPN (H-RPN) which can utilize surrounding information around the PWMLs for heuristic segmentation. Also, we design a lightweight segmentation network to segment the lesion in a fast way. Densely connected conditional random field (DCRF) is used to optimize the segmentation results. We only use T1w MRIs to segment PWMLs. The result shows that our model can well segment the lesion of ordinary size or even pixel size. The Dice similarity coefficient reaches 0.6616, the sensitivity is 0.7069, the specificity is 0.9997, and the Hausdorff distance is 52.9130. The proposed method outperforms the state-of-the-art algorithm. (The code of this paper is available on https://github.com/YalongLiu/Refined-Segmentation-R-CNN)

eess.IV↗

arXiv2019

TESS Hunt for Young and Maturing Exoplanets (THYME): A planet in the 45 Myr Tucana-Horologium association

Young exoplanets are snapshots of the planetary evolution process. Planets that orbit stars in young associations are particularly important because the age of the planetary system is well constrained. We present the discovery of a transiting planet larger than Neptune but smaller than Saturn in the 45 Myr Tucana-Horologium young moving group. The host star is a visual binary, and our follow-up observations demonstrate that the planet orbits the G6V primary component, DS Tuc A (HD 222259A, TIC 410214986). We first identified transits using photometry from the Transiting Exoplanet Survey Satellite (TESS; alerted as TOI 200.01). We validated the planet and improved the stellar parameters using a suite of new and archival data, including spectra from SOAR/Goodman, SALT/HRS and LCO/NRES; transit photometry from Spitzer; and deep adaptive optics imaging from Gemini/GPI. No additional stellar or planetary signals are seen in the data. We measured the planetary parameters by simultaneously modeling the photometry with a transit model and a Gaussian process to account for stellar variability. We determined that the planetary radius is $5.70\pm0.17$ Earth radii and that the orbital period is 8.1 days. The inclination angles of the host star's spin axis, the planet's orbital axis, and the visual binary's orbital axis are aligned within 15 degrees to within the uncertainties of the relevant data. DS Tuc Ab is bright enough (V=8.5) for detailed characterization using radial velocities and transmission spectroscopy.

astro-ph.EP↗

arXiv2019

Macroscopic entanglement of two magnon modes via quantum correlated microwave fields

We present a scheme to entangle two magnon modes in two macroscopic yttrium-iron-garnet spheres. The two spheres are placed inside two microwave cavities, which are driven by a two-mode squeezed microwave field. By using the linear state-swap interaction between the cavity and the magnon mode in each cavity, the quantum correlation of the two driving fields is with high efficiency transferred to the two magnon modes. Considerable entanglement could be achieved under experimentally achievable conditions $g \gg κ_a \gg κ_m$, where $g$ is the cavity-magnon coupling rate and $κ_a$, $κ_m$ are the decay rates of the cavity and magnon modes, respectively. The entanglement is in the steady state and robust against temperature, surviving up to hundreds of milliKelvin with experimentally accessible two-mode squeezed source.

quant-ph↗

arXiv2019

TOI-150b and TOI-163b: two transiting hot Jupiters, one eccentric and one inflated, revealed by TESS near and at the edge of the JWST CVZ

We present the discovery of TYC9191-519-1b (TOI-150b, TIC 271893367) and HD271181b (TOI-163b, TIC 179317684), two hot Jupiters initially detected using 30-minute cadence Transiting Exoplanet Survey Satellite TESS photometry from Sector 1 and thoroughly characterized through follow-up photometry (CHAT, Hazelwood, LCO/CTIO, El Sauce, TRAPPIST-S), high-resolution spectroscopy (FEROS, CORALIE) and speckle imaging (Gemini/DSSI), confirming the planetary nature of the two signals. A simultaneous joint fit of photometry and radial velocity using a new fitting package juliet reveals that TOI-150b is a $1.254\pm0.016\ R_J$, massive ($2.61^{+0.19}_{-0.12}\ M_J$) hot Jupiter in a $5.857$-day orbit, while TOI-163b is an inflated ($R_P$ = $1.478^{+0.022}_{-0.029} R_J$, $M_P$ = $1.219\pm0.11 M_J$) hot Jupiter on a $P$ = $4.231$-day orbit; both planets orbit F-type stars. A particularly interesting result is that TOI-150b shows an eccentric orbit ($e=0.262^{+0.045}_{-0.037}$), which is quite uncommon among hot Jupiters. We estimate that this is consistent, however, with the circularization timescale which is slightly larger than the age of the system. These two hot Jupiters are both prime candidates for further characterization --- in particular, both are excellent candidates for determining spin-orbit alignments via the Rossiter-McLaughlin (RM) effect and for characterizing atmospheric thermal structures using secondary eclipse observations considering they are both located closely to the James Webb Space Telescope (JWST) Continuous Viewing Zone (CVZ).

astro-ph.EP↗

arXiv2019

A sparse annotation strategy based on attention-guided active learning for 3D medical image segmentation

3D image segmentation is one of the most important and ubiquitous problems in medical image processing. It provides detailed quantitative analysis for accurate disease diagnosis, abnormal detection, and classification. Currently deep learning algorithms are widely used in medical image segmentation, most algorithms trained models with full annotated datasets. However, obtaining medical image datasets is very difficult and expensive, and full annotation of 3D medical image is a monotonous and time-consuming work. Partially labelling informative slices in 3D images will be a great relief of manual annotation. Sample selection strategies based on active learning have been proposed in the field of 2D image, but few strategies focus on 3D images. In this paper, we propose a sparse annotation strategy based on attention-guided active learning for 3D medical image segmentation. Attention mechanism is used to improve segmentation accuracy and estimate the segmentation accuracy of each slice. The comparative experiments with three different strategies using datasets from the developing human connectome project (dHCP) show that, our strategy only needs 15% to 20% annotated slices in brain extraction task and 30% to 35% annotated slices in tissue segmentation task to achieve comparative results as full annotation.

cs.CV↗

arXiv2019

Unveiling the Electric-current-limiting and Photodetection Effect in Two-dimensional Hydrogenated Borophene

The electronic transport and photoelectric properties of hydrogenated borophene B4H4, which was realized in a recent experiment by Nishino [J. Am. Chem. Soc. 139, 13761 (2017)], are systematically investigated using the density functional theory and non-equilibrium Green's function methods. We find that B4H4 exhibits a perfect current-limiting effect and has high (along the zigzag direction) and low (along the armchair one) optional levels due to its strong electrical anisotropy. Moreover, B4H4 can generate sizable photocurrents under illumination, with strong photoelectronic response to blue/green light along the zigzag/armchair direction. Our work demonstrates that B4H4 is promising for the applications of current limiter and photodetectors.

cond-mat.mes-hall↗