arXiv subjects

Heng Zhang

Publications and source records attributed to Heng Zhang.

At least 199 records · Page 11Linked to original sources

arXiv2022

Multi-Robot Object Transport Motion Planning with a Deformable Sheet

Using a deformable sheet to handle objects is convenient and found in many practical applications. For object manipulation through a deformable sheet that is held by multiple mobile robots, it is a challenging task to model the object-sheet interactions. We present a computational model and algorithm to capture the object position on the deformable sheet with changing robotic team formations. A virtual variable cables model (VVCM) is proposed to simplify the modeling of the robot-sheet-object system. With the VVCM, we further present a motion planner for the robotic team to transport the object in a three-dimensional (3D) cluttered environment. Simulation and experimental results with different robot team sizes show the effectiveness and versatility of the proposed VVCM. We also compare and demonstrate the planning results to avoid the obstacle in 3D space with the other benchmark planner.

cs.RO↗

arXiv2022

Model-free Value Iteration Algorithm for Continuous-time Stochastic Linear Quadratic Optimal Control Problems

This paper presents a novel value iteration (VI) algorithm for finding the optimal control for a kind of infinite-horizon stochastic linear quadratic (SLQ) problem with unknown systems. First, an off-line algorithm is estabilished to obtain the optimal feedback control of our problem. Then, based on the off-line algorithm, the VI-based model-free algorithm and its convergence proof is provided. The main feature of the model-free algorithm is that a stabilizing control is not needed to initiate the algorithm. Finally, we validate our results with a simulation example.

math.OC↗

arXiv2022

A Hard and Soft Hybrid Slicing Framework for Service Level Agreement Guarantee via Deep Reinforcement Learning

Network slicing is a critical driver for guaranteeing the diverse service level agreements (SLA) in 5G and future networks. Recently, deep reinforcement learning (DRL) has been widely utilized for resource allocation in network slicing. However, existing related works do not consider the performance loss associated with the initial exploration phase of DRL. This paper proposes a new performance-guaranteed slicing strategy with a soft and hard hybrid slicing setting. Mainly, a common slice setting is applied to guarantee slices' SLA when training the neural network. Moreover, the resource of the common slice tends to precisely redistribute to slices with the training of DRL until it converges. Furthermore, experiment results confirm the effectiveness of our proposed slicing framework: the slices' SLA of the training phase can be guaranteed, and the proposed algorithm can achieve the near-optimal performance in terms of the SLA satisfaction ratio, isolation degree and spectrum maximization after convergence.

cs.NI↗

arXiv2021

Characterizing the Program Expressive Power of Existential Rule Languages

Existential rule languages are a family of ontology languages that have been widely used in ontology-mediated query answering (OMQA). However, for most of them, the expressive power of representing domain knowledge for OMQA, known as the program expressive power, is not well-understood yet. In this paper, we establish a number of novel characterizations for the program expressive power of several important existential rule languages, including tuple-generating dependencies (TGDs), linear TGDs, as well as disjunctive TGDs. The characterizations employ natural model-theoretic properties, and automata-theoretic properties sometimes, which thus provide powerful tools for identifying the definability of domain knowledge for OMQA in these languages.

cs.LO↗

arXiv2021

WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training

Multi-modal pre-training models have been intensively explored to bridge vision and language in recent years. However, most of them explicitly model the cross-modal interaction between image-text pairs, by assuming that there exists strong semantic correlation between the text and image modalities. Since this strong assumption is often invalid in real-world scenarios, we choose to implicitly model the cross-modal correlation for large-scale multi-modal pre-training, which is the focus of the Chinese project `WenLan' led by our team. Specifically, with the weak correlation assumption over image-text pairs, we propose a two-tower pre-training model called BriVL within the cross-modal contrastive learning framework. Unlike OpenAI CLIP that adopts a simple contrastive learning method, we devise a more advanced algorithm by adapting the latest method MoCo into the cross-modal scenario. By building a large queue-based dictionary, our BriVL can incorporate more negative samples in limited GPU resources. We further construct a large Chinese multi-source image-text dataset called RUC-CAS-WenLan for pre-training our BriVL model. Extensive experiments demonstrate that the pre-trained BriVL model outperforms both UNITER and OpenAI CLIP on various downstream tasks.

cs.CV↗

arXiv2021

DADgraph: A Discourse-aware Dialogue Graph Neural Network for Multiparty Dialogue Machine Reading Comprehension

Multiparty Dialogue Machine Reading Comprehension (MRC) differs from traditional MRC as models must handle the complex dialogue discourse structure, previously unconsidered in traditional MRC. To fully exploit such discourse structure in multiparty dialogue, we present a discourse-aware dialogue graph neural network, DADgraph, which explicitly constructs the dialogue graph using discourse dependency links and discourse relations. To validate our model, we perform experiments on the Molweni corpus, a large-scale MRC dataset built over multiparty dialogue annotated with discourse structure. Experiments on Molweni show that our discourse-aware model achieves statistically significant improvements compared against strong neural network MRC baselines.

cs.CL↗

arXiv2021

Design and Control of a Highly Redundant Rigid-Flexible Coupling Robot to Assist the COVID-19 Oropharyngeal-Swab Sampling

The outbreak of novel coronavirus pneumonia (COVID-19) has caused mortality and morbidity worldwide. Oropharyngeal-swab (OP-swab) sampling is widely used for the diagnosis of COVID-19 in the world. To avoid the clinical staff from being affected by the virus, we developed a 9-degree-of-freedom (DOF) rigid-flexible coupling (RFC) robot to assist the COVID-19 OP-swab sampling. This robot is composed of a visual system, UR5 robot arm, micro-pneumatic actuator and force-sensing system. The robot is expected to reduce risk and free up the clinical staff from the long-term repetitive sampling work. Compared with a rigid sampling robot, the developed force-sensing RFC robot can facilitate OP-swab sampling procedures in a safer and softer way. In addition, a varying-parameter zeroing neural network-based optimization method is also proposed for motion planning of the 9-DOF redundant manipulator. The developed robot system is validated by OP-swab sampling on both oral cavity phantoms and volunteers.

cs.RO↗

arXiv2021

Using Full-text Content of Academic Articles to Build a Methodology Taxonomy of Information Science in China

Research on the construction of traditional information science methodology taxonomy is mostly conducted manually. From the limited corpus, researchers have attempted to summarize some of the research methodology entities into several abstract levels (generally three levels); however, they have been unable to provide a more granular hierarchy. Moreover, updating the methodology taxonomy is traditionally a slow process. In this study, we collected full-text academic papers related to information science. First, we constructed a basic methodology taxonomy with three levels by manual annotation. Then, the word vectors of the research methodology entities were trained using the full-text data. Accordingly, the research methodology entities were clustered and the basic methodology taxonomy was expanded using the clustering results to obtain a methodology taxonomy with more levels. This study provides new concepts for constructing a methodology taxonomy of information science. The proposed methodology taxonomy is semi-automated; it is more detailed than conventional schemes and the speed of taxonomy renewal has been enhanced.

cs.DL↗

arXiv2021

Chronological Citation Recommendation with Time Preference

Citation recommendation is an important task to assist scholars in finding candidate literature to cite. Traditional studies focus on static models of recommending citations, which do not explicitly distinguish differences between papers that are caused by temporal variations. Although, some researchers have investigated chronological citation recommendation by adding time related function or modeling textual topics dynamically. These solutions can hardly cope with function generalization or cold-start problems when there is no information for user profiling or there are isolated papers never being cited. With the rise and fall of science paradigms, scientific topics tend to change and evolve over time. People would have the time preference when citing papers, since most of the theoretical basis exist in classical readings that published in old time, while new techniques are proposed in more recent papers. To explore chronological citation recommendation, this paper wants to predict the time preference based on user queries, which is a probability distribution of citing papers published in different time slices. Then, we use this time preference to re-rank the initial citation list obtained by content-based filtering. Experimental results demonstrate that task performance can be further enhanced by time preference and it's flexible to be added in other citation recommendation frameworks.

cs.IR↗

arXiv2020

Context-Aware Collaborative-Intelligence with Spatio-Temporal In-Sensor-Analytics in a Large-Area IoT Testbed

Decades of continuous scaling has reduced the energy of unit computing to virtually zero, while energy-efficient communication has remained the primary bottleneck in achieving fully energy-autonomous IoT nodes. This paper presents and analyzes the trade-offs between the energies required for communication and computation in a wireless sensor network, deployed in a mesh architecture over a 2400-acre university campus, and is targeted towards multi-sensor measurement of temperature, humidity and water nitrate concentration for smart agriculture. Several scenarios involving In-Sensor-Analytics (ISA), Collaborative Intelligence (CI) and Context-Aware-Switching (CAS) of the cluster-head during CI has been considered. A real-time co-optimization algorithm has been developed for minimizing the energy consumption in the network, hence maximizing the overall battery lifetime of individual nodes. Measurement results show that the proposed ISA consumes ~467X lower energy as compared to traditional Bluetooth Low Energy (BLE) communication, and ~69,500X lower energy as compared with Long Range (LoRa) communication. When the ISA is implemented in conjunction with LoRa, the lifetime of the node increases from a mere 4.3 hours to 66.6 days with a 230 mAh coin cell battery, while preserving more than 98% of the total information. The CI and CAS algorithms help in extending the worst-case node lifetime by an additional 50%, thereby exhibiting an overall network lifetime of ~104 days, which is >90% of the theoretical limits as posed by the leakage currents present in the system, while effectively transferring information sampled every second. A web-based monitoring system was developed to archive the measured data in a continuous manner, and to report anomalies in the measured data.

cs.NI↗

arXiv2020

Localize to Classify and Classify to Localize: Mutual Guidance in Object Detection

Most deep learning object detectors are based on the anchor mechanism and resort to the Intersection over Union (IoU) between predefined anchor boxes and ground truth boxes to evaluate the matching quality between anchors and objects. In this paper, we question this use of IoU and propose a new anchor matching criterion guided, during the training phase, by the optimization of both the localization and the classification tasks: the predictions related to one task are used to dynamically assign sample anchors and improve the model on the other task, and vice versa. Despite the simplicity of the proposed method, our experiments with different state-of-the-art deep learning architectures on PASCAL VOC and MS COCO datasets demonstrate the effectiveness and generality of our Mutual Guidance strategy.

cs.CV↗

arXiv2020

Multispectral Fusion for Object Detection with Cyclic Fuse-and-Refine Blocks

Multispectral images (e.g. visible and infrared) may be particularly useful when detecting objects with the same model in different environments (e.g. day/night outdoor scenes). To effectively use the different spectra, the main technical problem resides in the information fusion process. In this paper, we propose a new halfway feature fusion method for neural networks that leverages the complementary/consistency balance existing in multispectral features by adding to the network architecture, a particular module that cyclically fuses and refines each spectral feature. We evaluate the effectiveness of our fusion method on two challenging multispectral datasets for object detection. Our results show that implementing our Cyclic Fuse-and-Refine module in any network improves the performance on both datasets compared to other state-of-the-art multispectral object detection methods.

cs.CV↗

arXiv2020

Differences in Sb2Te3 growth by pulsed laser and sputter deposition

High quality Van der Waals chalcogenides are important for phase change data storage, thermoelectrics, and spintronics. Using a combination of statistical design of experiments and density functional theory, we clarify how the out-of-equilibrium van der Waals epitaxial deposition methods can improve the crystal quality of Sb2Te3 films. We compare films grown by radio frequency sputtering and pulsed laser deposition (PLD). The growth factors that influence the crystal quality for each method are different. For PLD grown films a thin amorphous Sb2Te3 seed layer most significantly influences the crystal quality. In contrast, the crystalline quality of films grown by sputtering is rather sensitive to the deposition temperature and less affected by the presence of a seed layer. This difference is somewhat surprising as both methods are out-of-thermal-equilibrium plasma-based methods. Non-adiabatic quantum molecular dynamics simulations show that this difference originates from the density of excited atoms in the plasma. The PLD plasma is more intense and with higher energy than that used in sputtering, and this increases the electronic temperature of the deposited atoms, which concomitantly increases the adatom diffusion lengths in PLD. In contrast, the adatom diffusivity is dominated by the thermal temperature for sputter grown films. These results explain the wide range of Sb2Te3 and superlattice crystal qualities observed in the literature. These results indicate that, contrary to popular belief, plasma-based deposition methods are suitable for growing high quality crystalline chalcogenides.

cond-mat.mtrl-sci↗

arXiv2020

Long-Lived Charge Separation Following Pump-Energy Dependent Ultrafast Charge Transfer in Graphene/WS$_2$ Heterostructures

Van der Waals heterostructures consisting of graphene and transition metal dichalcogenides (TMDCs) have recently shown great promise for high-performance optoelectronic applications. However, an in-depth understanding of the critical processes for device operation, namely interfacial charge transfer (CT) and recombination, has so far remained elusive. Here, we investigate these processes in graphene-WS$_2$ heterostructures, by complementarily probing the ultrafast terahertz photoconductivity in graphene and the transient absorption dynamics in WS$_2$ following photoexcitation. We find that CT across graphene-WS$_2$ interfaces occurs via photo-thermionic emission for sub-A-exciton excitation, and direct hole transfer from WS$_2$ to the valence band of graphene for above-A-exciton excitation. Remarkably, we observe that separated charges in the heterostructure following CT live extremely long: beyond 1 ns, in contrast to ~1 ps charge separation reported in previous studies. This leads to efficient photogating of graphene. These findings provide relevant insights to optimize further the performance of optoelectronic devices, in particular photodetection.

cond-mat.mtrl-sci↗

arXiv2020

Restricted Chase Termination for Existential Rules: a Hierarchical Approach and Experimentation

The chase procedure for existential rules is an indispensable tool for several database applications, where its termination guarantees the decidability of these tasks. Most previous studies have focused on the skolem chase variant and its termination analysis. It is known that the restricted chase variant is a more powerful tool in termination analysis provided a database is given. But all-instance termination presents a challenge since the critical database and similar techniques do not work. In this paper, we develop a novel technique to characterize the activeness of all possible cycles of a certain length for the restricted chase, which leads to the formulation of a parameterized class of the finite restricted chase, called $k$-$\mathsf{safe}(Φ)$. This approach applies to any class of finite skolem chase identified with a condition of acyclicity. More generally, we show that the approach can be applied to the hierarchy of bounded rule sets previously only defined for the skolem chase. Experiments on a collection of ontologies from the web show the applicability of the proposed methods on real-world ontologies. Under consideration in Theory and Practice of Logic Programming (TPLP).

cs.LO↗

arXiv2020

Model-theoretic Characterizations of Existential Rule Languages

Existential rules, a.k.a. dependencies in databases, and Datalog+/- in knowledge representation and reasoning recently, are a family of important logical languages widely used in computer science and artificial intelligence. Towards a deep understanding of these languages in model theory, we establish model-theoretic characterizations for a number of existential rule languages such as (disjunctive) embedded dependencies, tuple-generating dependencies (TGDs), (frontier-)guarded TGDs and linear TGDs. All these characterizations hold for arbitrary structures, and most of them also work on the class of finite structures. As a natural application of these characterizations, complexity bounds for the rewritability of above languages are also identified.

cs.AI↗

arXiv2019

Towards Universal Languages for Tractable Ontology Mediated Query Answering

An ontology language for ontology mediated query answering (OMQA-language) is universal for a family of OMQA-languages if it is the most expressive one among this family. In this paper, we focus on three families of tractable OMQA-languages, including first-order rewritable languages and languages whose data complexity of the query answering is in AC0 or PTIME. On the negative side, we prove that there is, in general, no universal language for each of these families of languages. On the positive side, we propose a novel property, the locality, to approximate the first-order rewritability, and show that there exists a language of disjunctive embedded dependencies that is universal for the family of OMQA-languages with locality. All of these results apply to OMQA with query languages such as conjunctive queries, unions of conjunctive queries and acyclic conjunctive queries.

cs.AI↗

arXiv2019

A Data-Center FPGA Acceleration Platform for Convolutional Neural Networks

Intensive computation is entering data centers with multiple workloads of deep learning. To balance the compute efficiency, performance, and total cost of ownership (TCO), the use of a field-programmable gate array (FPGA) with reconfigurable logic provides an acceptable acceleration capacity and is compatible with diverse computation-sensitive tasks in the cloud. In this paper, we develop an FPGA acceleration platform that leverages a unified framework architecture for general-purpose convolutional neural network (CNN) inference acceleration at a data center. To overcome the computation bound, 4,096 DSPs are assembled and shaped as supertile units (SUs) for different types of convolution, which provide up to 4.2 TOP/s 16-bit fixed-point performance at 500 MHz. The interleaved-task-dispatching method is proposed to map the computation across the SUs, and the memory bound is solved by a dispatching-assembling buffering model and broadcast caches. For various non-convolution operators, a filter processing unit is designed for general-purpose filter-like/pointwise operators. In the experiment, the performances of CNN models running on server-class CPUs, a GPU, and an FPGA are compared. The results show that our design achieves the best FPGA peak performance and a throughput at the same level as that of the state-of-the-art GPU in data centers, with more than 50 times lower latency.

cs.CV↗