arXiv subjects

Teng Li

Publications and source records attributed to Teng Li.

At least 73 records · Page 4Linked to original sources

arXiv2022

CoAvoid: Secure, Privacy-Preserved Tracing of Contacts for Infectious Diseases

To fight against infectious diseases (e.g., SARS, COVID-19, Ebola, etc.), government agencies, technology companies and health institutes have launched various contact tracing approaches to identify and notify the people exposed to infection sources. However, existing tracing approaches can lead to severe privacy and security concerns, thereby preventing their secure and widespread use among communities. To tackle these problems, this paper proposes CoAvoid, a decentralized, privacy-preserved contact tracing system that features good dependability and usability. CoAvoid leverages the Google/Apple Exposure Notification (GAEN) API to achieve decent device compatibility and operating efficiency. It utilizes GPS along with Bluetooth Low Energy (BLE) to dependably verify user information. In addition, to enhance privacy protection, CoAvoid applies fuzzification and obfuscation measures to shelter sensitive data, making both servers and users agnostic to information of both low and high-risk populations. The evaluation demonstrates good efficacy and security of CoAvoid. Compared with four state-of-art contact tracing applications, CoAvoid can reduce upload data by at least 90% and simultaneously resist wormhole and replay attacks in various scenarios.

cs.CR↗

arXiv2022

Automated Noncontact Trapping of Moving Micro-particle with Ultrasonic Phased Array System and Microscopic Vision

Noncontact particle manipulation (NPM) technology has significantly extended mankind's analysis capability into micro and nano scale, which in turn greatly promoted the development of material science and life science. Though NPM by means of electric, magnetic, and optical field has achieved great success, from the robotic perspective, it is still labor-intensive manipulation since professional human assistance is somehow mandatory in early preparation stage. Therefore, developing automated noncontact trapping of moving particles is worthwhile, particularly for applications where particle samples are rare, fragile or contact sensitive. Taking advantage of latest dynamic acoustic field modulating technology, and particularly by virtue of the great scalability of acoustic manipulation from micro-scale to sub-centimeter-scale, we propose an automated noncontact trapping of moving micro-particles with ultrasonic phased array system and microscopic vision in this paper. The main contribution of this work is for the first time, as far as we know, we achieved fully automated moving micro-particle trapping in acoustic NPM field by resorting to robotic approach. In short, the particle moving status is observed and predicted by binocular microscopic vision system, by referring to which the acoustic trapping zone is calculated and generated to capture and stably hold the particle. The problem of hand-eye relationship of noncontact robotic end-effector is also solved in this work. Experiments demonstrated the effectiveness of this work.

cs.RO↗

arXiv2022

Representation-Agnostic Shape Fields

3D shape analysis has been widely explored in the era of deep learning. Numerous models have been developed for various 3D data representation formats, e.g., MeshCNN for meshes, PointNet for point clouds and VoxNet for voxels. In this study, we present Representation-Agnostic Shape Fields (RASF), a generalizable and computation-efficient shape embedding module for 3D deep learning. RASF is implemented with a learnable 3D grid with multiple channels to store local geometry. Based on RASF, shape embeddings for various 3D shape representations (point clouds, meshes and voxels) are retrieved by coordinate indexing. While there are multiple ways to optimize the learnable parameters of RASF, we provide two effective schemes among all in this paper for RASF pre-training: shape reconstruction and normal estimation. Once trained, RASF becomes a plug-and-play performance booster with negligible cost. Extensive experiments on diverse 3D representation formats, networks and applications, validate the universal effectiveness of the proposed RASF. Code and pre-trained models are publicly available https://github.com/seanywang0408/RASF

cs.CV↗

arXiv2021

Sample-Efficient Neural Architecture Search by Learning Action Space

Neural Architecture Search (NAS) has emerged as a promising technique for automatic neural network design. However, existing MCTS based NAS approaches often utilize manually designed action space, which is not directly related to the performance metric to be optimized (e.g., accuracy), leading to sample-inefficient explorations of architectures. To improve the sample efficiency, this paper proposes Latent Action Neural Architecture Search (LaNAS), which learns actions to recursively partition the search space into good or bad regions that contain networks with similar performance metrics. During the search phase, as different action sequences lead to regions with different performance, the search efficiency can be significantly improved by biasing towards the good regions. On three NAS tasks, empirical results demonstrate that LaNAS is at least an order more sample efficient than baseline methods including evolutionary algorithms, Bayesian optimizations, and random search. When applied in practice, both one-shot and regular LaNAS consistently outperform existing results. Particularly, LaNAS achieves 99.0% accuracy on CIFAR-10 and 80.8% top1 accuracy at 600 MFLOPS on ImageNet in only 800 samples, significantly outperforming AmoebaNet with 33x fewer samples. Our code is publicly available at https://github.com/facebookresearch/LaMCTS.

cs.LG↗

arXiv2020

Realising square and diamond lattice $S=1/2$ Heisenberg antiferromagnet models in the $α$ and $β$ phases of the coordination framework, KTi(C$_2$O$_4$)$_2\cdot$\textit{x}H$_2$O

We report the crystal structures and magnetic properties of two psuedo-polymorphs of the $S=1/2$ Ti$^{3+}$ coordination framework, KTi(C$_2$O$_4$)$_2\cdot$xH$_2$O. Single-crystal X-ray and powder neutron diffraction measurements on $α$-KTi(C$_2$O$_4$)$_2\cdot$xH$_2$O confirm its structure in the tetragonal $I4/mcm$ space group with a square planar arrangement of Ti$^{3+}$ ions. Magnetometry and specific heat measurements reveal weak antiferromagnetic interactions, with $J_1\approx7$ K and $J_2/J_1=0.11$ indicating a slight frustration of nearest- and next-nearest-neighbor interactions. Below $1.8$ K, $α$ undergoes a transition to G-type antiferromagnetic order with magnetic moments aligned along the $c$ axis of the tetragonal structure. The estimated ordered moment of Ti$^{3+}$ in $α$ is suppressed from its spin-only value to $0.62(3)~μ_B$, thus verifying the two-dimensional nature of the magnetic interactions within the system. $β$-KTi(C$_2$O$_4$)$_2\cdot$2H$_2$O, on the other hand, realises a three-dimensional diamond-like magnetic network of Ti$^{3+}$ moments within a hexagonal $P6_222$ structure. An antiferromagnetic exchange coupling of $J\approx54$ K -- an order of magnitude larger than in $α$ -- is extracted from magnetometry and specific heat data. $β$ undergoes Néel ordering at $T_N=28$ K, with the magnetic moments aligned within the $ab$ plane and a slightly reduced ordered moment of $0.79~μ_B$ per Ti$^{3+}$. Through density-functional theory calculations, we address the origin of the large difference in the exchange parameters between the $α$ and $β$ psuedo-polymorphs. Given their observed magnetic behaviors, we propose $α$-KTi(C$_2$O$_4$)$_2\cdot$xH$_2$O and $β$-KTi(C$_2$O$_4$)$_2\cdot$2H$_2$O as close to ideal model $S=1/2$ Heisenberg square and diamond lattice antiferromagnets, respectively.

cond-mat.str-el↗

arXiv2020

PyTorch Distributed: Experiences on Accelerating Data Parallel Training

This paper presents the design, implementation, and evaluation of the PyTorch distributed data parallel module. PyTorch is a widely-adopted scientific computing package used in deep learning research and applications. Recent advances in deep learning argue for the value of large datasets and large models, which necessitates the ability to scale out model training to more computational resources. Data parallelism has emerged as a popular solution for distributed training thanks to its straightforward principle and broad applicability. In general, the technique of distributed data parallelism replicates the model on every computational resource to generate gradients independently and then communicates those gradients at each iteration to keep model replicas consistent. Despite the conceptual simplicity of the technique, the subtle dependencies between computation and communication make it non-trivial to optimize the distributed training efficiency. As of v1.5, PyTorch natively provides several techniques to accelerate distributed data parallel, including bucketing gradients, overlapping computation with communication, and skipping gradient synchronization. Evaluations show that, when configured appropriately, the PyTorch distributed data parallel module attains near-linear scalability using 256 GPUs.

cs.DC↗

arXiv2020

MsCGAN: Multi-scale Conditional Generative Adversarial Networks for Person Image Generation

To synthesize high-quality person images with arbitrary poses is challenging. In this paper, we propose a novel Multi-scale Conditional Generative Adversarial Networks (MsCGAN), aiming to convert the input conditional person image to a synthetic image of any given target pose, whose appearance and the texture are consistent with the input image. MsCGAN is a multi-scale adversarial network consisting of two generators and two discriminators. One generator transforms the conditional person image into a coarse image of the target pose globally, and the other is to enhance the detailed quality of the synthetic person image through a local reinforcement network. The outputs of the two generators are then merged into a synthetic, discriminant and high-resolution image. On the other hand, the synthetic image is downsampled to multiple resolutions as the input to multi-scale discriminator networks. The proposed multi-scale generators and discriminators handling different levels of visual features can benefit to synthesizing high-resolution person images with realistic appearance and texture. Experiments are conducted on the Market-1501 and DeepFashion datasets to evaluate the proposed model, and both qualitative and quantitative results demonstrate the superior performance of the proposed MsCGAN.

cs.CV↗

arXiv2019

Adversarial Domain Adaptation with Domain Mixup

Recent works on domain adaptation reveal the effectiveness of adversarial learning on filling the discrepancy between source and target domains. However, two common limitations exist in current adversarial-learning-based methods. First, samples from two domains alone are not sufficient to ensure domain-invariance at most part of latent space. Second, the domain discriminator involved in these methods can only judge real or fake with the guidance of hard label, while it is more reasonable to use soft scores to evaluate the generated images or features, i.e., to fully utilize the inter-domain information. In this paper, we present adversarial domain adaptation with domain mixup (DM-ADA), which guarantees domain-invariance in a more continuous latent space and guides the domain discriminator in judging samples' difference relative to source and target domains. Domain mixup is jointly conducted on pixel and feature level to improve the robustness of models. Extensive experiments prove that the proposed approach can achieve superior performance on tasks with various degrees of domain shift and data complexity.

cs.CV↗

arXiv2019

Optimization of Wireless Sensor Network Deployment for Spatiotemporal Reconstruction and Prediction

This paper addresses the problem of optimizing sensor deployment locations to reconstruct and also predict a spatiotemporal field. A novel deep learning framework is developed to find a limited number of optimal sampling locations and based on that, improve the accuracy of spatiotemporal field reconstruction and prediction. The proposed approach first optimizes the sampling locations of a wireless sensor network to retrieve maximum information from a spatiotemporal field. A spatiotemporal reconstructor is then used to reconstruct and predict the spatiotemporal field, using collected in-situ measurements. A simulation is conducted using global climate datasets from the National Oceanic and Atmospheric Administration, to implement and validate the developed methodology. The results demonstrate a significant improvement made by the proposed algorithm. Specifically, compared to traditional approaches, the proposed method provides superior performance in terms of both reconstruction error and long-term prediction robustness.

eess.SP↗

arXiv2019

Threshold Greedy Based Task Allocation for Multiple Robot Operations

This paper deals with large-scale decentralised task allocation problems for multiple heterogeneous robots with monotone submodular objective functions. One of the significant challenges with the large-scale decentralised task allocation problem is the NP-hardness for computation and communication. This paper proposes a decentralised Decreasing Threshold Task Allocation (DTTA) algorithm that enables parallel allocation by leveraging a decreasing threshold to handle the NP-hardness. Then DTTA is upgraded to a more practical version Lazy Decreasing Threshold Task Allocation (LDTTA) by combining a variant of Lazy strategy. DTTA and LDTTA can release both computational and communicating burden for multiple robots in a decentralised network while providing an optimality bound of solution quality. To examine the performance of the proposed algorithms, this paper models a multi-target surveillance scenario and conducts Monte-Carlo simulations. Simulation results reveal that the proposed algorithms achieve similar function values but consume much less running time and consensus steps compared with benchmark decentralised task allocation algorithms.

cs.MA↗

arXiv2019

Coverage Sampling Planner for UAV-enabled Environmental Exploration and Field Mapping

Unmanned Aerial Vehicles (UAVs) have been implemented for environmental monitoring by using their capabilities of mobile sensing, autonomous navigation, and remote operation. However, in real-world applications, the limitations of on-board resources (e.g., power supply) of UAVs will constrain the coverage of the monitored area and the number of the acquired samples, which will hinder the performance of field estimation and mapping. Therefore, the issue of constrained resources calls for an efficient sampling planner to schedule UAV-based sensing tasks in environmental monitoring. This paper presents a mission planner of coverage sampling and path planning for a UAV-enabled mobile sensor to effectively explore and map an unknown environment that is modeled as a random field. The proposed planner can generate a coverage path with an optimal coverage density for exploratory sampling, and the associated energy cost is subjected to a power supply constraint. The performance of the developed framework is evaluated and compared with the existing state-of-the-art algorithms, using a real-world dataset that is collected from an environmental monitoring program as well as physical field experiments. The experimental results illustrate the reliability and accuracy of the presented coverage sampling planner in a prior survey for environmental exploration and field mapping.

cs.RO↗

arXiv2019

Sample Greedy Based Task Allocation for Multiple Robot Systems

This paper addresses the task allocation problem for multi-robot systems. The main issue with the task allocation problem is inherent complexity that makes finding an optimal solution within a reasonable time almost impossible. To hand the issue, this paper develops a task allocation algorithm that can be decentralised by leveraging the submodularity concepts and sampling process. The theoretical analysis reveals that the proposed algorithm can provide approximation guarantee of $1/2$ for the monotone submodular case and $1/4$ for the non-monotone submodular case in average sense with polynomial time complexity. To examine the performance of the proposed algorithm and validate the theoretical analysis results, we design a task allocation problem and perform numerical simulations. The simulation results confirm that the proposed algorithm achieves solution quality, which is comparable to a state-of-the-art algorithm in the monotone case, and much better quality in the non-monotone case with significantly less computational complexity.

cs.MA↗

arXiv2018

SRM: An Efficient Framework for Autonomous Robotic Exploration in Indoor Environments

In this paper, we propose an integrated framework for the autonomous robotic exploration in indoor environments. Specially, we present a hybrid map, named Semantic Road Map (SRM), to represent the topological structure of the explored environment and facilitate decision-making in the exploration. The SRM is built incrementally along with the exploration process. It is a graph structure with collision-free nodes and edges that are generated within the sensor coverage. Moreover, each node has a semantic label and the expected information gain at that location. Based on the concise SRM, we present a novel and effective decision-making model to determine the next-best-target (NBT) during the exploration. The model concerns the semantic information, the information gain, and the path cost to the target location. We use the nodes of SRM to represent the candidate targets, which enables the target evaluation to be performed directly on the SRM. With the SRM, both the information gain of a node and the path cost to the node can be obtained efficiently. Besides, we adopt the cross-entropy method to optimize the path to make it more informative. We conduct experimental studies in both simulated and real-world environments, which demonstrate the effectiveness of the proposed method.

cs.RO↗

arXiv2018

Fast submodular maximization subject to k-extendible system constraints

As the scales of data sets expand rapidly in some application scenarios, increasing efforts have been made to develop fast submodular maximization algorithms. This paper presents a currently the most efficient algorithm for maximizing general non-negative submodular objective functions subject to $k$-extendible system constraints. Combining the sampling process and the decreasing threshold strategy, our algorithm Sample Decreasing Threshold Greedy Algorithm (SDTGA) obtains an expected approximation guarantee of ($p-ε$) for monotone submodular functions and of ($p(1-p)-ε$) for non-monotone cases with expected computational complexity of only $O(\frac{pn}ε\ln\frac{r}ε)$, where $r$ is the largest size of the feasible solutions, $0<p \leq \frac{1}{1+k}$ is the sampling probability and $0< ε< p$. If we fix the sampling probability $p$ as $\frac{1}{1+k}$, we get the best approximation ratios for both monotone and non-monotone submodular functions which are $(\frac{1}{1+k}-ε)$ and $(\frac{k}{(1+k)^2}-ε)$ respectively. While the parameter $ε$ exists for the trade-off between the approximation ratio and the time complexity. Therefore, our algorithm can handle larger scale of submodular maximization problems than existing algorithms.

cs.DS↗

arXiv2018

Model-Free Control for Distributed Stream Data Processing using Deep Reinforcement Learning

In this paper, we focus on general-purpose Distributed Stream Data Processing Systems (DSDPSs), which deal with processing of unbounded streams of continuous data at scale distributedly in real or near-real time. A fundamental problem in a DSDPS is the scheduling problem with the objective of minimizing average end-to-end tuple processing time. A widely-used solution is to distribute workload evenly over machines in the cluster in a round-robin manner, which is obviously not efficient due to lack of consideration for communication delay. Model-based approaches do not work well either due to the high complexity of the system environment. We aim to develop a novel model-free approach that can learn to well control a DSDPS from its experience rather than accurate and mathematically solvable system models, just as a human learns a skill (such as cooking, driving, swimming, etc). Specifically, we, for the first time, propose to leverage emerging Deep Reinforcement Learning (DRL) for enabling model-free control in DSDPSs; and present design, implementation and evaluation of a novel and highly effective DRL-based control framework, which minimizes average end-to-end tuple processing time by jointly learning the system environment via collecting very limited runtime statistics data and making decisions under the guidance of powerful Deep Neural Networks. To validate and evaluate the proposed framework, we implemented it based on a widely-used DSDPS, Apache Storm, and tested it with three representative applications. Extensive experimental results show 1) Compared to Storm's default scheduler and the state-of-the-art model-based method, the proposed framework reduces average tuple processing by 33.5% and 14.0% respectively on average. 2) The proposed framework can quickly reach a good scheduling solution during online learning, which justifies its practicability for online control in DSDPSs.

cs.DC↗

arXiv2017

Autonomous Mobile Robot Navigation in Uneven and Unstructured Indoor Environments

Robots are increasingly operating in indoor environments designed for and shared with people. However, robots working safely and autonomously in uneven and unstructured environments still face great challenges. Many modern indoor environments are designed with wheelchair accessibility in mind. This presents an opportunity for wheeled robots to navigate through sloped areas while avoiding staircases. In this paper, we present an integrated software and hardware system for autonomous mobile robot navigation in uneven and unstructured indoor environments. This modular and reusable software framework incorporates capabilities of perception and navigation. Our robot first builds a 3D OctoMap representation for the uneven environment with the 3D mapping using wheel odometry, 2D laser and RGB-D data. Then we project multilayer 2D occupancy maps from OctoMap to generate the the traversable map based on layer differences. The safe traversable map serves as the input for efficient autonomous navigation. Furthermore, we employ a variable step size Rapidly Exploring Random Trees that could adjust the step size automatically, eliminating tuning step sizes according to environments. We conduct extensive experiments in simulation and real-world, demonstrating the efficacy and efficiency of our system.

cs.RO↗

arXiv2017

Design and Development of JUNO Event Data Model

The Jiangmen Underground Neutrino Observatory (JUNO) detector is designed to determine the neutrino mass hierarchy and precisely measure oscillation parameters. The general purpose design also allows measurements of neutrinos from many terrestrial and non-terrestrial sources. The JUNO Event Data Model (EDM) plays a central role in the offline software system, it describes the event data entities through all processing stages for both simulated and collected data, and provides persistency via the input/output system. Also, the EDM is designed to enable flexible event handling such as event navigation, as well as the splitting of MC IBD signals and mixing of MC backgrounds. This paper describes the design, implementation and performance of JUNO EDM.

physics.ins-det↗

arXiv2017

Application of SNiPER framework to BESIII physics analysis

A fast physics analysis framework has been developed based on SNiPER to process the increasingly large data sample collected by BESIII. In this framework, a reconstructed event data model with SmartRef is designed to improve the speed of Input/Output operations, and necessary physics analysis tools are migrated from BOSS to SNiPER. A real physics analysis $e^{+}e^{-} \rightarrow π^{+}π^{-}J/ψ$ is used to test the new framework, and achieves a factor of 10.3 improvement in Input/Output speed compared to BOSS. Further tests show that the improvement is mainly attributed to the new reconstructed event data model and the lazy-loading functionality provided by SmartRef.

hep-ex↗