arXiv subjects

Jun Ma

Publications and source records attributed to Jun Ma.

At least 343 records · Page 19Linked to original sources

arXiv2021

Global Iterative Sliding Mode Control of an Industrial Biaxial Gantry System for Contouring Motion Tasks

This paper proposes a global iterative sliding mode control approach for high-precision contouring tasks of a flexure-linked biaxial gantry system. For such high-precision contouring tasks, it is the typical situation that the involved multi-axis cooperation is one of the most challenging problems. As also would be inevitably encountered, various factors render the multi-axis cooperation rather difficult; such as the strong coupling (which naturally brings nonlinearity) between different axes due to its mechanical structure, the backlash and deadzone caused by the friction, and the difficulties in system identification, etc. To overcome the above-mentioned issues, this work investigates an intelligent model-free contouring control method for such a multi-axis motion stage. Essentially in the methodology developed here, it is firstly ensured that all the coupling, friction, nonlinearity, and disturbance (regarded as uncertain dynamics in each axis) are suitably posed as `uncertainties'. Then, a varying-gain sliding mode control method is proposed to adaptively compensate for the matched unknown dynamics in the time domain, while an iterative learning law is applied to suppress the undesirable effects (arising from the repetitive matched and unmatched uncertainties in the iteration domain). With this approach, the chattering that typically results from the overestimated control gains in the sliding mode control is thus suppressed during the iterations. To analyze the contouring performance and show the improved outcomes, rigorous proof is furnished on both the stability in the time domain and the convergence in the iteration domain; and the real-time experiments also illustrate that the requirements of precision motion control towards high-speed and complex-curvature references can be satisfied using the proposed method, without prior knowledge of the boundary to the unknown dynamics.

eess.SY↗

arXiv2021

DRQN-based 3D Obstacle Avoidance with a Limited Field of View

In this paper, we propose a map-based end-to-end DRL approach for three-dimensional (3D) obstacle avoidance in a partially observed environment, which is applied to achieve autonomous navigation for an indoor mobile robot using a depth camera with a narrow field of view. We first train a neural network with LSTM units in a 3D simulator of mobile robots to approximate the Q-value function in double DRQN. We also use a curriculum learning strategy to accelerate and stabilize the training process. Then we deploy the trained model to a real robot to perform 3D obstacle avoidance in its navigation. We evaluate the proposed approach both in the simulated environment and on a robot in the real world. The experimental results show that the approach is efficient and easy to be deployed, and it performs well for 3D obstacle avoidance with a narrow observation angle, which outperforms other existing DRL-based models by 15.5% on success rate.

cs.RO↗

arXiv2021

Deep Learning methods for automatic evaluation of delayed enhancement-MRI. The results of the EMIDEC challenge

A key factor for assessing the state of the heart after myocardial infarction (MI) is to measure whether the myocardium segment is viable after reperfusion or revascularization therapy. Delayed enhancement-MRI or DE-MRI, which is performed several minutes after injection of the contrast agent, provides high contrast between viable and nonviable myocardium and is therefore a method of choice to evaluate the extent of MI. To automatically assess myocardial status, the results of the EMIDEC challenge that focused on this task are presented in this paper. The challenge's main objectives were twofold. First, to evaluate if deep learning methods can distinguish between normal and pathological cases. Second, to automatically calculate the extent of myocardial infarction. The publicly available database consists of 150 exams divided into 50 cases with normal MRI after injection of a contrast agent and 100 cases with myocardial infarction (and then with a hyperenhanced area on DE-MRI), whatever their inclusion in the cardiac emergency department. Along with MRI, clinical characteristics are also provided. The obtained results issued from several works show that the automatic classification of an exam is a reachable task (the best method providing an accuracy of 0.92), and the automatic segmentation of the myocardium is possible. However, the segmentation of the diseased area needs to be improved, mainly due to the small size of these areas and the lack of contrast with the surrounding structures.

eess.IV↗

arXiv2021

AbdomenCT-1K: Is Abdominal Organ Segmentation A Solved Problem?

With the unprecedented developments in deep learning, automatic segmentation of main abdominal organs seems to be a solved problem as state-of-the-art (SOTA) methods have achieved comparable results with inter-rater variability on many benchmark datasets. However, most of the existing abdominal datasets only contain single-center, single-phase, single-vendor, or single-disease cases, and it is unclear whether the excellent performance can generalize on diverse datasets. This paper presents a large and diverse abdominal CT organ segmentation dataset, termed AbdomenCT-1K, with more than 1000 (1K) CT scans from 12 medical centers, including multi-phase, multi-vendor, and multi-disease cases. Furthermore, we conduct a large-scale study for liver, kidney, spleen, and pancreas segmentation and reveal the unsolved segmentation problems of the SOTA methods, such as the limited generalization ability on distinct medical centers, phases, and unseen diseases. To advance the unsolved problems, we further build four organ segmentation benchmarks for fully supervised, semi-supervised, weakly supervised, and continual learning, which are currently challenging and active research topics. Accordingly, we develop a simple and effective method for each benchmark, which can be used as out-of-the-box methods and strong baselines. We believe the AbdomenCT-1K dataset will promote future in-depth research towards clinical applicable abdominal organ segmentation methods. The datasets, codes, and trained models are publicly available at https://github.com/JunMa11/AbdomenCT-1K.

cs.CV↗

arXiv2021

Improving Transformer-based Sequential Recommenders through Preference Editing

One of the key challenges in Sequential Recommendation (SR) is how to extract and represent user preferences. Traditional SR methods rely on the next item as the supervision signal to guide preference extraction and representation. We propose a novel learning strategy, named preference editing. The idea is to force the SR model to discriminate the common and unique preferences in different sequences of interactions between users and the recommender system. By doing so, the SR model is able to learn how to identify common and unique user preferences, and thereby do better user preference extraction and representation. We propose a transformer based SR model, named MrTransformer (Multi-preference Transformer), that concatenates some special tokens in front of the sequence to represent multiple user preferences and makes sure they capture different aspects through a preference coverage mechanism. Then, we devise a preference editing-based self-supervised learning mechanism for training MrTransformer which contains two main operations: preference separation and preference recombination. The former separates the common and unique user preferences for a given pair of sequences. The latter swaps the common preferences to obtain recombined user preferences for each sequence. Based on the preference separation and preference recombination operations, we define two types of SSL loss that require that the recombined preferences are similar to the original ones, and the common preferences are close to each other. We carry out extensive experiments on two benchmark datasets. MrTransformer with preference editing significantly outperforms state-of-the-art SR methods in terms of Recall, MRR and NDCG. We find that long sequences whose user preferences are harder to extract and represent benefit most from preference editing.

cs.IR↗

arXiv2021

Semi-Supervised Variational Reasoning for Medical Dialogue Generation

Medical dialogue generation aims to provide automatic and accurate responses to assist physicians to obtain diagnosis and treatment suggestions in an efficient manner. In medical dialogues two key characteristics are relevant for response generation: patient states (such as symptoms, medication) and physician actions (such as diagnosis, treatments). In medical scenarios large-scale human annotations are usually not available, due to the high costs and privacy requirements. Hence, current approaches to medical dialogue generation typically do not explicitly account for patient states and physician actions, and focus on implicit representation instead. We propose an end-to-end variational reasoning approach to medical dialogue generation. To be able to deal with a limited amount of labeled data, we introduce both patient state and physician action as latent variables with categorical priors for explicit patient state tracking and physician policy learning, respectively. We propose a variational Bayesian generative approach to approximate posterior distributions over patient states and physician actions. We use an efficient stochastic gradient variational Bayes estimator to optimize the derived evidence lower bound, where a 2-stage collapsed inference method is proposed to reduce the bias during model training. A physician policy network composed of an action-classifier and two reasoning detectors is proposed for augmented reasoning ability. We conduct experiments on three datasets collected from medical platforms. Our experimental results show that the proposed method outperforms state-of-the-art baselines in terms of objective and subjective evaluation metrics. Our experiments also indicate that our proposed semi-supervised reasoning method achieves a comparable performance as state-of-the-art fully supervised learning baselines for physician policy learning.

cs.CL↗

arXiv2021

A Characteristic Function-based Algorithm for Geodesic Active Contours

Active contour models have been widely used in image segmentation, and the level set method (LSM) is the most popular approach for solving the models, via implicitly representing the contour by a level set function. However, the LSM suffers from high computational burden and numerical instability, requiring additional regularization terms or re-initialization techniques. In this paper, we use characteristic functions to implicitly represent the contours, propose a new representation to the geodesic active contours and derive an efficient algorithm termed as the iterative convolution-thresholding method (ICTM). Compared to the LSM, the ICTM is simpler and much more efficient. In addition, the ICTM enjoys most desired features of the level set-based methods. Extensive experiments, on 2D synthetic, 2D ultrasound, 3D CT, and 3D MR images for nodule, organ and lesion segmentation, demonstrate that the proposed method not only obtains comparable or even better segmentation results (compared to the LSM) but also achieves significant acceleration.

cs.CV↗

arXiv2021

Element abundance analysis of the metal-rich stellar halo and high-velocitythick disk in the galaxy

Based on the second Gaia data release (DR2) and APOGEE (DR16) spectroscopic surveys, wedefined two kinds of star sample: high-velocity thick disk (HVTD) with $vϕ>90km/s$ and metal-richstellar halo (MRSH) with $vϕ<90km/s$. Due to high resolution spectra data from APOGEE (DR16),we can analyze accurately the element abundance distribution of HVTD and MRSH. These elementsabundance constituted a multidimensional data space, and we introduced an algorithm method forprocessing multi-dimensional data to give the result of dimensionality reduction clustering. Accordingto chemical properties analysis, we derived that some HVTD stars could origin from the thin disk,and some MRSH stars from dwarf galaxies, but those stars which have similar chemical abundancecharacteristics in both sample may form in-situ.

astro-ph.GA↗

arXiv2021

The MICCAI Hackathon on reproducibility, diversity, and selection of papers at the MICCAI conference

The MICCAI conference has encountered tremendous growth over the last years in terms of the size of the community, as well as the number of contributions and their technical success. With this growth, however, come new challenges for the community. Methods are more difficult to reproduce and the ever-increasing number of paper submissions to the MICCAI conference poses new questions regarding the selection process and the diversity of topics. To exchange, discuss, and find novel and creative solutions to these challenges, a new format of a hackathon was initiated as a satellite event at the MICCAI 2020 conference: The MICCAI Hackathon. The first edition of the MICCAI Hackathon covered the topics reproducibility, diversity, and selection of MICCAI papers. In the manner of a small think-tank, participants collaborated to find solutions to these challenges. In this report, we summarize the insights from the MICCAI Hackathon into immediate and long-term measures to address these challenges. The proposed measures can be seen as starting points and guidelines for discussions and actions to possibly improve the MICCAI conference with regards to reproducibility, diversity, and selection of papers.

cs.CV↗

arXiv2021

On the Correlation Between Atomic Gas and Bars in Galaxies

We analyze the correlation between properties of large-scale bars and atomic gas content of galaxies to explore the role of HI gas on bar evolution in galaxies. We show that the absolute bar size depends strongly on total stellar mass of galaxies and does not change significantly with HI gas fraction at fixed stellar mass. Furthermore, the physical size of the bar is small and nearly constant in high Hi gas fraction and low-mass galaxies, and becomes larger with increasing galactic stellar mass in low gas fraction galaxies. When the stellar masses are fixed, the relative bar length normalized to the disk shows a decrease with increasing HI gas fraction due to the larger disks in gas-richer galaxies. We measure the gas deficiency of the samples and find that the gas-rich galaxies have longer and stronger bars compared with the Hi gas-deficient galaxies at fixed stellar mass, especially for the massive ones. When splitting the samples into star forming and quiescent subgroups, the star forming galaxies tend to have longer bars than the quiescent ones at fixed stellar mass and gas deficiency. In addition, our results suggest two different types of bar properties, in which the bars in gas-rich galaxies grow longer but retain similar axial ratio over time, while they grow longer and fatter over time in gas-poor galaxies.

astro-ph.GA↗

arXiv2021

Parallel Split-Join Networks for Shared-account Cross-domain Sequential Recommendations

Sequential recommendation is a task in which one models and uses sequential information about user behavior for recommendation purposes. We study sequential recommendation in a particularly challenging context, in which multiple individual users share asingle account (i.e., they have a shared account) and in which user behavior is available in multiple domains (i.e., recommendations are cross-domain). These two characteristics bring new challenges on top of those of the traditional sequential recommendation task. First, we need to identify the behavior associated with different users and different user roles under the same account in order to recommend the right item to the right user role at the right time. Second, we need to identify behavior in one domain that might be helpful to improve recommendations in other domains. In this work, we study shared account cross-domain sequential recommendation and propose Parallel Split-Join Network (PSJNet), a parallel modeling network to address the two challenges above. We present two variants of PSJNet, PSJNet-I and PSJNet-II. PSJNet-I is a "split-by-join" framework that splits the mixed representations to get role-specific representations and joins them to obtain cross-domain representations at each timestamp simultaneously. PSJNet-II is a "split-and-join" framework that first splits role-specific representations at each timestamp, and then the representations from all timestamps and all roles are joined to obtain cross-domain representations. We use two datasets to assess the effectiveness of PSJNet. Our experimental results demonstrate that PSJNet outperforms state-of-the-art sequential recommendation baselines in terms of MRR and Recall.

cs.IR↗

arXiv2021

Excedance-type polynomials and gamma-positivity

The object of this paper is to give a systematic treatment of excedance-type polynomials. We first give a sufficient condition for a sequence of polynomials to have alternatingly increasing property, and then we present a systematic study of the joint distribution of excedances, fixed points and cycles of permutations and derangements, signed or not, colored or not. Let $p\in [0,1]$ and $q\in [0,1]$ be two given real numbers. We prove that the cyc q-Eulerian polynomials of permutations are bi-gamma-positive, and the fix and cyc (p,q)-Eulerian polynomials of permutations are alternatingly increasing, and so they are unimodal with modes in the middle, where fix and cyc are the fixed point and cycle statistics. When p=1 and q=1/2, we find a combinatorial interpretation of the bi-gamma-coefficients of the (p,q)-Eulerian polynomials. We then study excedance and flag excedance statistics of signed permutations and colored permutations. In particular, we establish the relationships between the (p,q)-Eulerian polynomials and some multivariate Eulerian polynomials. Our results unify and generalize a variety of recent results.

math.CO↗

arXiv2021

Receding Horizon Motion Planning for Multi-Agent Systems: A Velocity Obstacle Based Probabilistic Method

In this paper, a novel and innovative methodology for feasible motion planning in the multi-agent system is developed. On the basis of velocity obstacles characteristics, the chance constraints are formulated in the receding horizon control (RHC) problem, and geometric information of collision cones is used to generate the feasible regions of velocities for the host agent. By this approach, the motion planning is conducted at the velocity level instead of the position level. Thus, it guarantees a safer collision-free trajectory for the multi-agent system, especially for the systems with high-speed moving agents. Moreover, a probability threshold of potential collisions can be satisfied during the motion planning process. In order to validate the effectiveness of the methodology, different scenarios for multiple agents are investigated, and the simulation results clearly show that the proposed approach can effectively avoid potential collisions with a collision probability less than a specific threshold.

cs.RO↗

arXiv2021

Generalized Iterative Super-Twisting Sliding Mode Control: A Case Study on Flexure-Joint Dual-Drive H-Gantry Stage

Mechatronic systems are commonly used in the industry, where fast and accurate motion performance is always required to guarantee manufacturing precision and efficiency. Nevertheless, the system model and parameters are difficult to be obtained accurately. Moreover, the high-order modes, strong coupling in the multi-axis systems, or unmodeled frictions will bring uncertain dynamics to the system. To overcome the above-mentioned issues and enhance the motion performance, this paper introduces a novel intelligent and totally model-free control method for mechatronic systems with unknown dynamics. In detail, a 2-degree-of-freedom (DOF) architecture is designed, which organically merges a generalized super-twisting algorithm with a unique iterative learning law. The controller solely utilizes the input-output data collected in iterations such that it works without any knowledge of the system parameters. The rigorous proof of convergence ability is given and a case study on flexture-joint dual-drive H-gantry stage is shown to validate the effectiveness of the proposed method.

eess.SY↗

arXiv2021

Eulerian polynomials for multipermutations and signed multipermutations

In this paper, we study Eulerian polynomials for permutations and signed permutations of the multiset $\{1,1,2,2,\ldots,n,n\}$. Properties of these polynomials, including recurrence relations and unimodality are discussed. In particular, we give a unified proof of the fact that these polynomials are unimodal with modes in the middle.

math.CO↗

arXiv2021

Galaxy Clusters from the DESI Legacy Imaging Surveys. I. Cluster Detection

Based on the photometric redshift catalog of Zou H. et al. (2019), we apply a fast clustering algorithm to identify 540,432 galaxy clusters at $z\lesssim1$ in the DESI legacy imaging surveys, which cover a sky area of about 20,000 deg$^2$. Monte-Carlo simulations indicate that the false detection rate of our detecting method is about 3.1\%. The total masses of galaxy clusters are derived using a calibrated richness--mass relation that are based on the observations of X-ray emission and Sunyaev \& Zel'dovich effect. The median redshift and mass of our detected clusters are about 0.53 and $1.23\times10^{14} M_\odot$, respectively. Comparing with previous clusters identified using the data of the Sloan Digital Sky Survey (SDSS), we can recognize most of them, especially those with high richness. Our catalog will be used for further statistical studies on galaxy clusters and environmental effects on the galaxy evolution, etc.

astro-ph.GA↗

arXiv2021

Optimal Decentralized Control for Uncertain Systems by Symmetric Gauss-Seidel Semi-Proximal ALM

The H2 guaranteed cost decentralized control problem is investigated in this work. More specifically, on the basis of an appropriate H2 re-formulation that we put in place, the optimal control problem in the presence of parameter uncertainties is then suitably characterized by convex restriction and solved in parameter space. It is shown that a set of stabilizing decentralized controller gains for the uncertain system is parameterized in a convex set through appropriate convex restriction, and then an approximated conic optimization problem is constructed. This facilitates the use of the symmetric Gauss-Seidel (sGS) semi-proximal augmented Lagrangian method (ALM), which attains high computational effectiveness. A comprehensive analysis is given on the application of the approach in solving the optimal decentralized control problem; and subsequently, the preserved decentralized structure, robust stability, and robust performance are all suitably guaranteed with the proposed methodology. Furthermore, an illustrative example is presented to demonstrate the effectiveness of the proposed optimization approach.

math.OC↗

arXiv2021

Semi-Definite Relaxation Based ADMM for Cooperative Planning and Control of Connected Autonomous Vehicles

This paper investigates the cooperative planning and control problem for multiple connected autonomous vehicles (CAVs) in different scenarios. In the existing literature, most of the methods suffer from significant problems in computational efficiency. Besides, as the optimization problem is nonlinear and nonconvex, it typically poses great difficultly in determining the optimal solution. To address this issue, this work proposes a novel and completely parallel computation framework by leveraging the alternating direction method of multipliers (ADMM). The nonlinear and nonconvex optimization problem in the autonomous driving problem can be divided into two manageable subproblems; and the resulting subproblems can be solved by using effective optimization methods in a parallel framework. Here, the differential dynamic programming (DDP) algorithm is capable of addressing the nonlinearity of the system dynamics rather effectively; and the nonconvex coupling constraints with small dimensions can be approximated by invoking the notion of semi-definite relaxation (SDR), which can also be solved in a very short time. Due to the parallel computation and efficient relaxation of nonconvex constraints, our proposed approach effectively realizes real-time implementation and thus also extra assurance of driving safety is provided. In addition, two transportation scenarios for multiple CAVs are used to illustrate the effectiveness and efficiency of the proposed method.

cs.MA↗