arXiv subjects

Yan Zhao

Publications and source records attributed to Yan Zhao.

At least 127 records · Page 7Linked to original sources

arXiv2021

Adaptive Logit Adjustment Loss for Long-Tailed Visual Recognition

Data in the real world tends to exhibit a long-tailed label distribution, which poses great challenges for the training of neural networks in visual recognition. Existing methods tackle this problem mainly from the perspective of data quantity, i.e., the number of samples in each class. To be specific, they pay more attention to tail classes, like applying larger adjustments to the logit. However, in the training process, the quantity and difficulty of data are two intertwined and equally crucial problems. For some tail classes, the features of their instances are distinct and discriminative, which can also bring satisfactory accuracy; for some head classes, although with sufficient samples, the high semantic similarity with other classes and lack of discriminative features will bring bad accuracy. Based on these observations, we propose Adaptive Logit Adjustment Loss (ALA Loss) to apply an adaptive adjusting term to the logit. The adaptive adjusting term is composed of two complementary factors: 1) quantity factor, which pays more attention to tail classes, and 2) difficulty factor, which adaptively pays more attention to hard instances in the training process. The difficulty factor can alleviate the over-optimization on tail yet easy instances and under-optimization on head yet hard instances. The synergy of the two factors can not only advance the performance on tail classes even further, but also promote the accuracy on head classes. Unlike previous logit adjusting methods that only concerned about data quantity, ALA Loss tackles the long-tailed problem from a more comprehensive, fine-grained and adaptive perspective. Extensive experimental results show that our method achieves the state-of-the-art performance on challenging recognition benchmarks, including ImageNet-LT, iNaturalist 2018, and Places-LT.

cs.CV↗

arXiv2021

4-D Epanechnikov Mixture Regression in Light Field Image Compression

With the emergence of light field imaging in recent years, the compression of its elementary image array (EIA) has become a significant problem. Our coding framework includes modeling and reconstruction. For the modeling, the covariance-matrix form of the 4-D Epanechnikov kernel (4-D EK) and its correlated statistics were deduced to obtain the 4-D Epanechnikov mixture models (4-D EMMs). A 4-D Epanechnikov mixture regression (4-D EMR) was proposed based on this 4-D EK, and a 4-D adaptive model selection (4-D AMLS) algorithm was designed to realize the optimal modeling for a pseudo video sequence (PVS) of the extracted key-EIA. A linear function based reconstruction (LFBR) was proposed based on the correlation between adjacent elementary images (EIs). The decoded images realized a clear outline reconstruction and superior coding efficiency compared to high-efficiency video coding (HEVC) and JPEG 2000 below approximately 0.05 bpp. This work realized an unprecedented theoretical application by (1) proposing the 4-D Epanechnikov kernel theory, (2) exploiting the 4-D Epanechnikov mixture regression and its application in the modeling of the pseudo video sequence of light field images, (3) using 4-D adaptive model selection for the optimal number of models, and (4) employing a linear function-based reconstruction according to the content similarity.

eess.IV↗

arXiv2021

Estimates for eigenvalues of the Neumann and Steklov problems

We prove Li-Yau-Kröger type bounds for Neumann-type eigenvalues of the poly-harmonic operator and of the biharmonic operator on bounded domains in a Euclidean space. We also prove sharp estimates for lower order eigenvalues of a biharmonic Steklov problem and of the Laplacian, which directly implies two sharp Reilly-type inequalities for the corresponding first nonzero eigenvalue.

math.DG↗

arXiv2021

Data Lake Ingestion Management

Data Lake (DL) is a Big Data analysis solution which ingests raw data in their native format and allows users to process these data upon usage. Data ingestion is not a simple copy and paste of data, it is a complicated and important phase to ensure that ingested data are findable, accessible, interoperable and reusable at all times. Our solution is threefold. Firstly, we propose a metadata model that includes information about external data sources, data ingestion processes, ingested data, dataset veracity and dataset security. Secondly, we present the algorithms that ensure the ingestion phase (data storage and metadata instanciation). Thirdly, we introduce a developed metadata management system whereby users can easily consult different elements stored in DL.

cs.DB↗

arXiv2021

HIFI: Anomaly Detection for Multivariate Time Series with High-order Feature Interactions

Monitoring complex systems results in massive multivariate time series data, and anomaly detection of these data is very important to maintain the normal operation of the systems. Despite the recent emergence of a large number of anomaly detection algorithms for multivariate time series, most of them ignore the correlation modeling among multivariate, which can often lead to poor anomaly detection results. In this work, we propose a novel anomaly detection model for multivariate time series with \underline{HI}gh-order \underline{F}eature \underline{I}nteractions (HIFI). More specifically, HIFI builds multivariate feature interaction graph automatically and uses the graph convolutional neural network to achieve high-order feature interactions, in which the long-term temporal dependencies are modeled by attention mechanisms and a variational encoding technique is utilized to improve the model performance and robustness. Extensive experiments on three publicly available datasets demonstrate the superiority of our framework compared with state-of-the-art approaches.

cs.LG↗

arXiv2021

Three-dimensional Epanechnikov mixture regression in image coding

Kernel methods have been studied extensively in recent years. We propose a three-dimensional (3-D) Epanechnikov Mixture Regression (EMR) based on our Epanechnikov Kernel (EK) and realize a complete framework for image coding. In our research, we deduce the covariance-matrix form of 3-D Epanechnikov kernels and their correlated statistics to obtain the Epanechnikov mixture models. To apply our theories to image coding, we propose the 3-D EMR which can better model an image in smaller blocks compared with the conventional Gaussian Mixture Regression (GMR). The regressions are all based on our improved Expectation-Maximization (EM) algorithm with mean square error optimization. Finally, we design an Adaptive Mode Selection (AMS) algorithm to realize the best model pattern combination for coding. Our recovered image has clear outlines and superior coding efficiency compared to JPEG below 0.25bpp. Our work realizes an unprecedented theory application by: (1) enriching the theory of Epanechnikov kernel,(2) improving the EM algorithm using MSE optimization, (3) exploiting the EMR and its application in image coding, and (4) AMS optimal modeling combined with Gaussian and Epanechnikov kernel.

eess.IV↗

arXiv2021

A probabilistic model for missing traffic volume reconstruction based on data fusion

Traffic volume information is critical for intelligent transportation systems. It serves as a key input to transportation planning, roadway design, and traffic signal control. However, the traffic volume data collected by fixed-location sensors, such as loop detectors, often suffer from the missing data problem and low coverage problem. The missing data problem could be caused by hardware malfunction. The low coverage problem is due to the limited coverage of fixed-location sensors in the transportation network, which restrains our understanding of the traffic at the network level. To tackle these problems, we propose a probabilistic model for traffic volume reconstruction by fusing fixed-location sensor data and probe vehicle data. We apply the probabilistic principal component analysis (PPCA) to capture the correlations in traffic volume data. An innovative contribution of this work is that we also integrate probe vehicle data into the framework, which allows the model to solve both of the above-mentioned two problems. Using a real-world traffic volume dataset, we show that the proposed method outperforms state-of-the-art methods for the extensively studied missing data problem. Moreover, for the low coverage problem, which cannot be handled by most existing methods, the proposed model can also achieve high accuracy. The experiments also show that even when the missing ratio reaches 80%, the proposed method can still give an accurate estimate of the unknown traffic volumes with only a 10% probe vehicle penetration rate. The results validate the effectiveness and robustness of the proposed model and demonstrate its potential for practical applications.

physics.soc-ph↗

arXiv2021

A Lightweight Approach of Human-Like Playtesting

A playtest is the process in which human testers are recruited to play video games and to reveal software bugs. Manual testing is expensive and time-consuming, especially when there are many mobile games to test and every software version requires for extensive testing before being released. Existing testing frameworks (e.g., Android Monkey) are limited because they adopt no domain knowledge to play games. Learning-based tools (e.g., Wuji) involve a huge amount of training data and computation before testing any game. This paper presents LIT -- our lightweight approach to generalize playtesting tactics from manual testing, and to adopt the generalized tactics to automate game testing. LIT consists of two phases. In Phase I, while a human plays an Android game app G for a short period of time (e.g., eight minutes), \tool records the user's actions (e.g., swipe) and the scene before each action. Based on the collected data, LIT generalizes a set of \emph{context-aware, abstract playtesting tactics} which describe under what circumstances, what actions can be taken to play the game. In Phase II, LIT tests G based on the generalized tactics. Namely, given a randomly generated game scene, LIT searches match for the abstract context of any inferred tactic; if there is a match, LIT customizes the tactic and generates a feasible event to play the game. Our evaluation with nine games shows LIT to outperform two state-of-the-art tools. This implies that by automating playtest, LIT will significantly reduce manual testing and boost the quality of game apps.

cs.SE↗

arXiv2021

Accurate Correlation Energy Functional for Uniform Electron Gas from an Interpolation Ansatz without Fitting Parameters

We report an analytical representation of the correlation energy ec(rs, zeta) for a uniform electron gas (UEG), where rs is the Seitz radius or density parameter and zeta is the relative spin polarization. The new functional, called W20, is constructed to capture the known high-density and low-density limit (for zeta = 0 and 1) without any fitting parameters. The comparative assessment against the recent quantum Monte Carlo (QMC) results shows that the performance of the W20 functional is comparable to the popular parametrized UEG correlation functionals. On average, W20 agrees with QMC and PW92 [Phys. Rev. B 45, 13244 (1992)] within 0.01 eV, and W20 recovers the correct high- and low-density limits, whereas the QMC-data fitted UEG correlation functionals do not.

physics.chem-ph↗

arXiv2021

Covert Transmission Assisted by Intelligent Reflecting Surface

Covert transmission is studied for an intelligent reflecting surface (IRS) aided communication system, where Alice aims to transmit messages to Bob without being detected by the warden Willie. Specifically, an IRS is used to increase the data rate at Bob under a covert constraint. For the considered model, when Alice is equipped with a single antenna, the transmission power at Alice and phase shifts at the IRS are jointly optimized to maximize the covert transmission rate with either instantaneous or partial channel state information (CSI) of Willie's link. In addition, when multiple antennas are deployed at Alice, we formulate a joint transmit beamforming and IRS phase shift optimization problem to maximize the covert transmission rate. One optimal algorithm and two low-complexity suboptimal algorithms are proposed to solve the problem. Furthermore, for the case of imperfect CSI of Willie's link, the optimization problem is reformulated by using the triangle and the Cauchy-Schwarz inequalities. The reformulated optimization problems are solved using an alterative algorithm, semidefinite relaxation (SDR) and Gaussian randomization techniques. Finally, simulations are performed to verify our analysis. The simulation results show that an IRS can degrade the covert transmission rate when Willie is closer to the IRS than Bob.

cs.IT↗

arXiv2020

Designer spin order in diradical nanographenes

The magnetic properties of carbon materials are at present the focus of an intense research effort in physics, chemistry and materials science due to their potential applications in spintronics and quantum computations. Although the presence of spins in open-shell nanographenes has been recently confirmed, the ability to control magnetic coupling sign has remained elusive, but the most desirable. Here, we demonstrate an effective approach of engineering magnetic ground states in atomically precise open-shell bipartite/nonbipartite nanographenes using combined scanning probe techniques and mean-field Hubbard model calculations. The magnetic coupling sign between two spins has been controlled via breaking bipartite lattice symmetry of nanographenes. In addition, the exchange-interaction strength between two spins has been widely tuned by finely tailoring their spin density overlap, realizing a large exchange-interaction strength of 42 meV. Our demonstrated method provides ample opportunities for designer above-room-temperature magnetic phases and functionalities in graphene nanomaterials.

cond-mat.mes-hall↗

arXiv2020

Stratified and Time-aware Sampling based Adaptive Ensemble Learning for Streaming Recommendations

Recommender systems have played an increasingly important role in providing users with tailored suggestions based on their preferences. However, the conventional offline recommender systems cannot handle the ubiquitous data stream well. To address this issue, Streaming Recommender Systems (SRSs) have emerged in recent years, which incrementally train recommendation models on newly received data for effective real-time recommendations. Focusing on new data only benefits addressing concept drift, i.e., the changing user preferences towards items. However, it impedes capturing long-term user preferences. In addition, the commonly existing underload and overload problems should be well tackled for higher accuracy of streaming recommendations. To address these problems, we propose a Stratified and Time-aware Sampling based Adaptive Ensemble Learning framework, called STS-AEL, to improve the accuracy of streaming recommendations. In STS-AEL, we first devise stratified and time-aware sampling to extract representative data from both new data and historical data to address concept drift while capturing long-term user preferences. Also, incorporating the historical data benefits utilizing the idle resources in the underload scenario more effectively. After that, we propose adaptive ensemble learning to efficiently process the overloaded data in parallel with multiple individual recommendation models, and then effectively fuse the results of these models with a sequential adaptive mechanism. Extensive experiments conducted on three real-world datasets demonstrate that STS-AEL, in all the cases, significantly outperforms the state-of-the-art SRSs.

cs.IR↗

arXiv2020

Double-Wing Mixture of Experts for Streaming Recommendations

Streaming Recommender Systems (SRSs) commonly train recommendation models on newly received data only to address user preference drift, i.e., the changing user preferences towards items. However, this practice overlooks the long-term user preferences embedded in historical data. More importantly, the common heterogeneity in data stream greatly reduces the accuracy of streaming recommendations. The reason is that different preferences (or characteristics) of different types of users (or items) cannot be well learned by a unified model. To address these two issues, we propose a Variational and Reservoir-enhanced Sampling based Double-Wing Mixture of Experts framework, called VRS-DWMoE, to improve the accuracy of streaming recommendations. In VRS-DWMoE, we first devise variational and reservoir-enhanced sampling to wisely complement new data with historical data, and thus address the user preference drift issue while capturing long-term user preferences. After that, we propose a Double-Wing Mixture of Experts (DWMoE) model to first effectively learn heterogeneous user preferences and item characteristics, and then make recommendations based on them. Specifically, DWMoE contains two Mixture of Experts (MoE, an effective ensemble learning model) to learn user preferences and item characteristics, respectively. Moreover, the multiple experts in each MoE learn the preferences (or characteristics) of different types of users (or items) where each expert specializes in one underlying type. Extensive experiments demonstrate that VRS-DWMoE consistently outperforms the state-of-the-art SRSs.

cs.IR↗

arXiv2020

Note on Path-Connectivity of Complete Bipartite Graphs

For a graph $G=(V,E)$ and a set $S\subseteq V(G)$ of size at least $2$, a path in $G$ is said to be an $S$-path if it connects all vertices of $S$. Two $S$-paths $P_1$ and $P_2$ are said to be internally disjoint if $E(P_1)\cap E(P_2)=\emptyset$ and $V(P_1)\cap V(P_2)=S$. Let $π_G (S)$ denote the maximum number of internally disjoint $S$-paths in $G$. The $k$-path-connectivity $π_k(G)$ of $G$ is then defined as the minimum $π_G (S)$, where $S$ ranges over all $k$-subsets of $V(G)$. In [M. Hager, Path-connectivity in graphs, Discrete Math. 59(1986), 53--59], the $k$-path-connectivity of the complete bipartite graph $K_{a,b}$ was calculated, where $k\geq 2$. But, from his proof, only the case that $2\leq k\leq min\{a,b\}$ was considered. In this paper, we calculate the the situation that $min\{a,b\}+1\leq k\leq a+b$ and complete the result.

math.CO↗

arXiv2019

Comparison of counterstreaming suprathermal electron signatures of ICMEs with and without magnetic cloud: are all ICMEs flux ropes?

Magnetic clouds (MCs), as large-scale interplanetary magnetic flux ropes, are usually still connected to the sun at both ends near 1 AU. Many researchers believe that all non-MC interplanetary coronal mass ejections (ICMEs) also have magnetic flux rope structures, which are inconspicuous because the observing spacecraft crosses the flanks of the rope structures. If so, the field lines of non-MC ICMEs should also be usually connected to the Sun on both ends. Then we want to know whether the field lines of most non-MC ICMEs are still connected to the sun at both ends or not. This study examined the counterstreaming suprathermal electron (CSE) signatures of 266 ICMEs observed by the \emph{Advanced Composition Explorer} (\emph{ACE}) spacecraft from 1998 to 2008 and compared the CSE signatures of MCs and non-MC ICMEs. Results show that only 10 of the 101 MC events ($9.9\%$ ) and 75 of the 171 non-MC events ($43.9\%$) have no CSEs. Moreover, 21 of the non-MC ICMEs have high CSE percentages (more than $70\%$) and show relatively stable magnetic field components with slight rotations, which are in line with the expectations that spacecraft passes through the flank of magnetic flux ropes. So the 21 events may be magnetic flux ropes but the \emph{ACE} spacecraft passes through their flanks of magnetic flux ropes. Considering that most other non-MC events have disordered magnetic fields, we suggest that some non-MC ICMEs inherently have disordered magnetic fields, namely have no magnetic flux rope structures.

physics.space-ph↗

arXiv2019

Eigenvalue comparisons in Steklov eigenvalue problem and some other eigenvalue estimates

In this paper, two interesting eigenvalue comparison theorems for the first non-zero Steklov eigenvalue of the Laplacian have been established for manifolds with radial sectional curvature bounded from above. Besides, sharper bounds for the first non-zero eigenvalue of the Wentzell eigenvalue problem of the weighted Laplacian, which can be seen as a natural generalization of the classical Steklov eigenvalue problem, have been obtained.

math.DG↗

arXiv2019

Various methods for queue length and traffic volume estimation using probe vehicle trajectories

The rapid development of connected vehicle technology and the emergence of ride-hailing services have enabled the collection of a tremendous amount of probe vehicle trajectory data. Due to the large scale, the trajectory data have become a potential substitute for the widely used fixed-location sensors in terms of the performance measures of transportation networks. Specifically, for traffic volume and queue length estimation, most of the trajectory data based methods in the existing literature either require high market penetration of the probe vehicles to identify the shockwave or require the prior information about the queue length distribution and the penetration rate, which may not be feasible in the real world. To overcome the limitations of the existing methods, this paper proposes a series of novel methods based on probability theory. By exploiting the stopping positions of the probe vehicles in the queues, the proposed methods try to establish and solve a single-variable equation for the penetration rate of the probe vehicles. Once the penetration rate is obtained, it can be used to project the total queue length and the total traffic volume. The validation results using both simulation data and real-world data show that the methods would be accurate enough for assistance in performance measures and traffic signal control at intersections, even when the penetration rate of the probe vehicles is very low.

physics.soc-ph↗

arXiv2019

Green low-cost carbon nanodots-polyurethane composites with novel anisotropic anti-quenching mechanism for strain sensing

A new type of nontoxic low-cost sensor is reported here, whose photoluminescence (PL) intensity is instantly responsive to the external strain applied over a large range (up to 250% strain). Highly stretchable fluorescent composites of carbon dots (CDs) and polyurethane (PU) are fabricated via a scalable green chemistry method by conveniently dispersing CDs in the aqueous solution of PU. It is discovered that, upon tensile deformation, the PL peak of the CD-PU film remains non-shifted but displays varied intensity. The observed PL responses to strain are ascribed to the enlarged inter-particle distance of CDs along the tensile direction (z axis), although a higher degree of aggregation is resulted in the other two axes. The PL-dependence on the anisotropic patterns of CDs in solid state points to a new mechanism to overcome aggregation-induced quenching by controlling the distribution behaviors of the fluorescent species.

physics.app-ph↗