arXiv subjects

Jun Wu

Publications and source records attributed to Jun Wu.

At least 181 records · Page 10Linked to original sources

arXiv2021

A Right Invariant Extended Kalman Filter for Object based SLAM

With the recent advance of deep learning based object recognition and estimation, it is possible to consider object level SLAM where the pose of each object is estimated in the SLAM process. In this paper, based on a novel Lie group structure, a right invariant extended Kalman filter (RI-EKF) for object based SLAM is proposed. The observability analysis shows that the proposed algorithm automatically maintains the correct unobservable subspace, while standard EKF (Std-EKF) based SLAM algorithm does not. This results in a better consistency for the proposed algorithm comparing to Std-EKF. Finally, simulations and real world experiments validate not only the consistency and accuracy of the proposed algorithm, but also the practicability of the proposed RI-EKF for object based SLAM problem. The MATLAB code of the algorithm is made publicly available.

cs.RO↗

arXiv2021

Dual-band nonreciprocal thermal radiation by coupling optical Tamm states in magnetophotonic multilayers

Kirchhoff s law is one of the most fundamental law in thermal radiation. The violation of traditional Kirchhoff s law provides opportunities for higher energy conversion efficiency. Various micro-structures have been proposed to realize single-band nonreciprocal thermal emitters. However, dual-band nonreciprocal thermal emitters remain barely investigated. In this paper, we introduce magneto-optical material into a cascading one-dimensional (1-D) magnetophotonic crystal (MPC) heterostructure composed of two 1-D MPCs and a metal layer. Assisted by the nonreciprocity of the magneto-optical material and the coupling effect of two optical Tamm states (OTSs), a dual-band nonreciprocal lithography-free thermal emitter is achieved. The emitter exhibits strong dual-band nonreciprocal radiation at the wavelengths of 15.337 um and 15.731 um when the external magnetic field is 3 T and the angle of incidence is 56 degree. Besides, the magnetic field distribution is also calculated to confirm that the dual-band nonreciprocal radiation originates from the coupling effect between two OTSs. Our work may pave the way for constructing dual-band and multi-band nonreciprocal thermal emitters.

physics.optics↗

arXiv2021

RF-LighGBM: A probabilistic ensemble way to predict customer repurchase behaviour in community e-commerce

It is reported that the number of online payment users in China has reached 854 million; with the emergence of community e-commerce platforms, the trend of integration of e-commerce and social applications is increasingly intense. Community e-commerce is not a mature and sound comprehensive e-commerce with fewer categories and low brand value. To effectively retain community users and fully explore customer value has become an important challenge for community e-commerce operators. Given the above problems, this paper uses the data-driven method to study the prediction of community e-commerce customers' repurchase behaviour. The main research contents include 1. Given the complex problem of feature engineering, the classic model RFM in the field of customer relationship management is improved, and an improved model is proposed to describe the characteristics of customer buying behaviour, which includes five indicators. 2. In view of the imbalance of machine learning training samples in SMOTE-ENN, a training sample balance using SMOTE-ENN is proposed. The experimental results show that the machine learning model can be trained more effectively on balanced samples. 3. Aiming at the complexity of the parameter adjustment process, an automatic hyperparameter optimization method based on the TPE method was proposed. Compared with other methods, the model's prediction performance is improved, and the training time is reduced by more than 450%. 4. Aiming at the weak prediction ability of a single model, the soft voting based RF-LightgBM model was proposed. The experimental results show that the RF-LighTGBM model proposed in this paper can effectively predict customer repurchase behaviour, and the F1 value is 0.859, which is better than the single model and previous research results.

cs.LG↗

arXiv2021

Stress Topology Analysis for Porous Infill Optimization

The optimization of porous infill structures via local volume constraints has become a popular approach in topology optimization. In some design settings, however, the iterative optimization process converges only slowly, or not at all even after several hundreds or thousands of iterations. This leads to regions in which a distinct binary design is difficult to achieve. Interpreting intermediate density values by applying a threshold results in large solid or void regions, leading to sub-optimal structures. We find that this convergence issue relates to the topology of the stress tensor field that is simulated when applying the same external forces on the solid design domain. In particular, low convergence is observed in regions around so-called trisector degenerate points. Based on this observation, we propose an automatic initialization process that prescribes the topological skeleton of the stress field into the material field as solid simulation elements. These elements guide the material deposition around the degenerate points, but can also be remodelled or removed during the optimization. We demonstrate significantly improved convergence rates in a number of use cases with complex stress topologies. The improved convergence is demonstrated for infill optimization under homogeneous as well as spatially varying local volume constraints.

cs.CE↗

arXiv2021

QoS-aware User Grouping Strategy for Downlink Multi-Cell NOMA Systems

In multi-cell non-orthogonal multiple access (NOMA) systems, designing an appropriate user grouping strategy is an open problem due to diverse quality of service (QoS) requirements and inter-cell interference. In this paper, we exploit both game theory and graph theory to study QoS-aware user grouping strategies, aiming at minimizing power consumption in downlink multi-cell NOMA systems. Under different QoS requirements, we derive the optimal successive interference cancellation (SIC) decoding order with inter-cell interference, which is different from existing SIC decoding order of increasing channel gains, and obtain the corresponding power allocation strategy. Based on this, the exact potential game model of the user grouping strategies adopted by multiple cells is formulated. We prove that, in this game, the problem for each player to find a grouping strategy can be converted into the problem of searching for specific negative loops in the graph composed of users. Bellman-Ford algorithm is expanded to find these negative loops. Furthermore, we design a greedy based suboptimal strategy to approach the optimal solution with polynomial time. Extensive simulations confirm the effectiveness of grouping users with consideration of QoS and inter-cell interference, and show that the proposed strategies can considerably reduce total power consumption comparing with reference strategies.

cs.IT↗

arXiv2021

Non-invasive time-sorting in radio-frequency compressed ultrafast electron diffraction

We demonstrate a non-invasive time-sorting method for ultrafast electron diffraction (UED) experiments with radio-frequency (rf) compressed electron beams. We show that electron beam energy and arrival time at the sample after rf compression are strongly correlated such that the arrival time jitter may be corrected through measurement of the beam energy. The method requires minimal change to the infrastructure of most of the UED machines and is applicable to both keV and MeV UED. In our experiment with ~3 MeV beam, the timing jitter after rf compression is corrected with 35 fs root-mean-square (rms) accuracy, limited by the 3x10^-4 energy stability. For keV UED with high energy stability, sub-10 fs accuracy in time-sorting should be readily achievable. This time-sorting technique allows us to retrieve the 2.5 THz oscillation related to coherent A1g phonon in laser excited Bismuth film and extends the temporal resolution of UED to a regime far beyond the 100-200 fs rms jitter limitation.

physics.acc-ph↗

arXiv2021

Mass transference principle from rectangles to rectangles in Diophantine approximation

By introducing a ubiquity property for rectangles, we prove the mass transference principle from rectangles to rectangles, i.e., if a sequence of rectangles forms a ubiquity system (a full measure property), then the limsup set defined by shrinking these rectangles to smaller rectangles has full Hausdorff measure or to say transfer a full measure property to a full Hausdorff measure property for brevity. The limsup sets generated by balls or generated by rectangles appear at the most fundamental level in Diophantine approximation: one follows from Dirichlet's theorem, the other follows from Minkowski's theorem. So the result sets up a general principle for the Hausdorff measure theory for high dimensional Diophantine approximation which, together with the landmark work of Beresnevich & Velani in 2006 where a transference principle from balls to balls is established, gives a coherent Hausdorff measure theory for metric Diophantine approximation. The dimensional theory for limsup sets generated by rectangles also underpins the dimensional theory in multiplicative Diophantine approximation where unexpected phenomenon occurs and the usually used methods or even their generalizations fail to work.

math.NT↗

arXiv2021

Automatically Lock Your Neural Networks When You're Away

The smartphone and laptop can be unlocked by face or fingerprint recognition, while neural networks which confront numerous requests every day have little capability to distinguish between untrustworthy and credible users. It makes model risky to be traded as a commodity. Existed research either focuses on the intellectual property rights ownership of the commercialized model, or traces the source of the leak after pirated models appear. Nevertheless, active identifying users legitimacy before predicting output has not been considered yet. In this paper, we propose Model-Lock (M-LOCK) to realize an end-to-end neural network with local dynamic access control, which is similar to the automatic locking function of the smartphone to prevent malicious attackers from obtaining available performance actively when you are away. Three kinds of model training strategy are essential to achieve the tremendous performance divergence between certified and suspect input in one neural network. Extensive experiments based on MNIST, FashionMNIST, CIFAR10, CIFAR100, SVHN and GTSRB datasets demonstrated the feasibility and effectiveness of the proposed scheme.

cs.HC↗

arXiv2021

Search-based Kinodynamic Motion Planning for Omnidirectional Quadruped Robots

Autonomous navigation has played an increasingly significant role in quadruped robot system. However, most existing works on quadruped robots navigation using traditional search-based or sample-based methods do not consider the kinodynamic characteristics of quadruped robots, generating kinodynamically infeasible parts, that are difficult to track. In this paper, we introduce a complete navigation system considering the omnidirectional abilities of quadruped robots. First, we use kinodynamic path finding method to obtain smooth, dynamically feasible, time-optimal initial paths and add collision cost as a soft constraint to ensure safety. Then the trajectory is refined by the timed elastic band (TEB) method based on the omnidirectional model of quadruped robots. The superior performance of our work is demonstrated through simulating and real-world experiments on our quadruped robot Jueying Mini.

cs.RO↗

arXiv2021

QoS-Driven Resource Optimization for Intelligent Fog Radio Access Network: A Dynamic Power Allocation Perspective

The fog radio access network (Fog-RAN) has been considered a promising wireless access architecture to help shorten the communication delay and relieve the large data delivery burden over the backhaul links. However, limited by conventional inflexible communication design, Fog-RAN cannot be used in some complex communication scenarios. In this study, we focus on investigating a more intelligent Fog-RAN to assist the communication in a high-speed railway environment. Due to the train's continuously moving, the communication should be designed intelligently to adapt to channel variation. Specifically, we dynamically optimize the power allocation in the remote radio heads (RRHs) to minimize the total network power cost considering multiple quality-of-service (QoS) requirements and channel variation. The impact of caching on the power allocation is considered. The dynamic power optimization is analyzed to obtain a closed-form solution in certain cases. The inherent tradeoff among the total network cost, delay and delivery content size is further discussed. To evaluate the performance of the proposed dynamic power allocation, we present an invariant power allocation counterpart as a performance comparison benchmark. The result of our simulation reveals that dynamic power allocation can significantly outperform the invariant power allocation scheme, especially with a random caching strategy or limited caching resources at the RRHs.

cs.IT↗

arXiv2021

Cache Placement Optimization in Mobile Edge Computing Networks with Unaware Environment -- An Extended Multi-armed Bandit Approach

Caching high-frequency reuse contents at the edge servers in the mobile edge computing (MEC) network omits the part of backhaul transmission and further releases the pressure of data traffic. However, how to efficiently decide the caching contents for edge servers is still an open problem, which refers to the cache capacity of edge servers, the popularity of each content, and the wireless channel quality during transmission. In this paper, we discuss the influence of unknown user density and popularity of content on the cache placement solution at the edge server. Specifically, towards the implementation of the cache placement solution in the practical network, there are two problems needing to be solved. First, the estimation of unknown users' preference needs a huge amount of records of users' previous requests. Second, the overlapping serving regions among edge servers cause the wrong estimation of users' preference, which hinders the individual decision of caching placement. To address the first issue, we propose a learning-based solution to adaptively optimize the cache placement policy. We develop the extended multi-armed bandit (Extended MAB), which combines the generalized global bandit (GGB) and Standard Multi-armed bandit (MAB). For the second problem, a multi-agent Extended MAB-based solution is presented to avoid the mis-estimation of parameters and achieve the decentralized cache placement policy. The proposed solution determines the primary time slot and secondary time slot for each edge server. The proposed strategies are proven to achieve the bounded regret according to the mathematical analysis. Extensive simulations verify the optimality of the proposed strategies when comparing with baselines.

cs.NI↗

arXiv2021

Mahler's question for intrinsic Diophantine approximation on triadic Cantor set: the divergence theory

In this paper, we consider the intrinsic Diophantine approximation on the triadic Cantor set $\mathcal{K}$, i.e. approximating the points in $\mathcal{K}$ by rational numbers inside $\mathcal{K}$, a question posed by K. Mahler. By using another height function of a rational number in $\mathcal{K}$, i.e. the denominator obtained from its periodic 3-adic expansion, a complete metric theory for this variant intrinsic Diophantine approximation is presented which yields the divergence theory of Mahler's original question.

math.NT↗

arXiv2021

Diophantine analysis of the expansions of a fixed point under continuum many bases

In this paper, we study the Diophantine properties of the orbits of a fixed point in its expansions under continuum many bases. More precisely, let $T_β$ be the beta-transformation with base $β>1$, $\{x_{n}\}_{n\geq 1}$ be a sequence of real numbers in $[0,1]$ and $φ\colon \mathbb{N}\rightarrow (0,1]$ be a positive function. With a detailed analysis on the distribution of {\em full cylinders} in the base space $\{β>1\}$, it is shown that for any given $x\in(0,1]$, for almost all or almost no bases $β>1$, the orbit of $x$ under $T_β$ can $φ$-well approximate the sequence $\{x_{n}\}_{n\geq 1}$ according to the divergence or convergence of the series $\sum φ(n)$. This strengthens Schmeling's result significantly and complete all known results in this aspect. Moreover, the idea presented here can also be used to determine the Lebesgue measure of the set \begin{equation*} \{x\in [0,1]\colon|T^{n}_βx-L(x)|<φ(n) \text{ for infinitely many } n\in\mathbb{N}\}, \end{equation*} for a fixed base $β>1$, where $L\colon [0,1]\rightarrow[0,1]$ is a Lipschitz function.

math.NT↗

arXiv2021

A Universal Model for Cross Modality Mapping by Relational Reasoning

With the aim of matching a pair of instances from two different modalities, cross modality mapping has attracted growing attention in the computer vision community. Existing methods usually formulate the mapping function as the similarity measure between the pair of instance features, which are embedded to a common space. However, we observe that the relationships among the instances within a single modality (intra relations) and those between the pair of heterogeneous instances (inter relations) are insufficiently explored in previous approaches. Motivated by this, we redefine the mapping function with relational reasoning via graph modeling, and further propose a GCN-based Relational Reasoning Network (RR-Net) in which inter and intra relations are efficiently computed to universally resolve the cross modality mapping problem. Concretely, we first construct two kinds of graph, i.e., Intra Graph and Inter Graph, to respectively model intra relations and inter relations. Then RR-Net updates all the node features and edge features in an iterative manner for learning intra and inter relations simultaneously. Last, RR-Net outputs the probabilities over the edges which link a pair of heterogeneous instances to estimate the mapping results. Extensive experiments on three example tasks, i.e., image classification, social recommendation and sound recognition, clearly demonstrate the superiority and universality of our proposed model.

cs.CV↗

arXiv2021

REDE: End-to-end Object 6D Pose Robust Estimation Using Differentiable Outliers Elimination

Object 6D pose estimation is a fundamental task in many applications. Conventional methods solve the task by detecting and matching the keypoints, then estimating the pose. Recent efforts bringing deep learning into the problem mainly overcome the vulnerability of conventional methods to environmental variation due to the hand-crafted feature design. However, these methods cannot achieve end-to-end learning and good interpretability at the same time. In this paper, we propose REDE, a novel end-to-end object pose estimator using RGB-D data, which utilizes network for keypoint regression, and a differentiable geometric pose estimator for pose error back-propagation. Besides, to achieve better robustness when outlier keypoint prediction occurs, we further propose a differentiable outliers elimination method that regresses the candidate result and the confidence simultaneously. Via confidence weighted aggregation of multiple candidates, we can reduce the effect from the outliers in the final estimation. Finally, following the conventional method, we apply a learnable refinement process to further improve the estimation. The experimental results on three benchmark datasets show that REDE slightly outperforms the state-of-the-art approaches and is more robust to object occlusion.

cs.CV↗

arXiv2020

Leveraging AI and Intelligent Reflecting Surface for Energy-Efficient Communication in 6G IoT

The ever-increasing data traffic, various delay-sensitive services, and the massive deployment of energy-limited Internet of Things (IoT) devices have brought huge challenges to the current communication networks, motivating academia and industry to move to the sixth-generation (6G) network. With the powerful capability of data transmission and processing, 6G is considered as an enabler for IoT communication with low latency and energy cost. In this paper, we propose an artificial intelligence (AI) and intelligent reflecting surface (IRS) empowered energy-efficiency communication system for 6G IoT. First, we design a smart and efficient communication architecture including the IRS-aided data transmission and the AI-driven network resource management mechanisms. Second, an energy efficiency-maximizing model under given transmission latency for 6G IoT system is formulated, which jointly optimizes the settings of all communication participants, i.e. IoT transmission power, IRS-reflection phase shift, and BS detection matrix. Third, a deep reinforcement learning (DRL) empowered network resource control and allocation scheme is proposed to solve the formulated optimization model. Based on the network and channel status, the DRL-enabled scheme facilities the energy-efficiency and low-latency communication. Finally, experimental results verified the effectiveness of our proposed communication system for 6G IoT.

eess.SP↗

arXiv2020

Sensing and Reconstruction of 3D Deformation on Pneumatic Soft Robots

Real-time proprioception is a challenging problem for soft robots, which have almost infinite degrees-of-freedom in body deformation. When multiple actuators are used, it becomes more difficult as deformation can also occur on actuators caused by interaction between each other. To tackle this problem, we present a method in this paper to sense and reconstruct 3D deformation on pneumatic soft robots by first integrating multiple low-cost sensors inside the chambers of pneumatic actuators and then using machine learning to convert the captured signals into shape parameters of soft robots. An exterior motion capture system is employed to generate the datasets for both training and testing. With the help of good shape parameterization, the 3D shape of a soft robot can be accurately reconstructed from signals obtained from multiple sensors. We demonstrate the effectiveness of this approach on two designs of soft robots -- a robotic joint and a deformable membrane. After parameterizing the deformation of these soft robots into compact shape parameters, we can effectively train the neural networks to reconstruct the 3D deformation from the sensor signals. The sensing and shape prediction pipeline can run at 50Hz in real-time on a consumer-level device.

cs.RO↗

arXiv2020

Fitting the Search Space of Weight-sharing NAS with Graph Convolutional Networks

Neural architecture search has attracted wide attentions in both academia and industry. To accelerate it, researchers proposed weight-sharing methods which first train a super-network to reuse computation among different operators, from which exponentially many sub-networks can be sampled and efficiently evaluated. These methods enjoy great advantages in terms of computational costs, but the sampled sub-networks are not guaranteed to be estimated precisely unless an individual training process is taken. This paper owes such inaccuracy to the inevitable mismatch between assembled network layers, so that there is a random error term added to each estimation. We alleviate this issue by training a graph convolutional network to fit the performance of sampled sub-networks so that the impact of random errors becomes minimal. With this strategy, we achieve a higher rank correlation coefficient in the selected set of candidates, which consequently leads to better performance of the final architecture. In addition, our approach also enjoys the flexibility of being used under different hardware constraints, since the graph convolutional network has provided an efficient lookup table of the performance of architectures in the entire search space.

cs.LG↗