arXiv subjects

Jie Xu

Publications and source records attributed to Jie Xu.

At least 451 records · Page 25Linked to original sources

arXiv2021

UAV-Enabled Wireless Power Transfer: A Tutorial Overview

Unmanned aerial vehicle (UAV)-enabled wireless power transfer (WPT) has recently emerged as a promising technique to provide sustainable energy supply for widely distributed low-power ground devices (GDs) in large-scale wireless networks. Compared with the energy transmitters (ETs) in conventional WPT systems which are deployed at fixed locations, UAV-mounted aerial ETs can fly flexibly in the three-dimensional (3D) space to charge nearby GDs more efficiently. This paper provides a tutorial overview on UAV-enabled WPT and its appealing applications, in particular focusing on how to exploit UAVs' controllable mobility via their 3D trajectory design to maximize the amounts of energy transferred to all GDs in a wireless network with fairness. First, we consider the single-UAV-enabled WPT scenario with one UAV wirelessly charging multiple GDs at known locations. To solve the energy maximization problem in this case, we present a general trajectory design framework consisting of three innovative approaches to optimize the UAV trajectory, which are multi-location hovering, successive-hover-and-fly, and time-quantization-based optimization, respectively. Next, we consider the multi-UAV-enabled WPT scenario where multiple UAVs cooperatively charge many GDs in a large area. Building upon the single-UAV trajectory design, we propose two efficient schemes to jointly optimize multiple UAVs' trajectories, based on the principles of UAV swarming and GD clustering, respectively. Furthermore, we consider two important extensions of UAV-enabled WPT, namely UAV-enabled wireless powered communication networks (WPCN) and UAV-enabled wireless powered mobile edge computing (MEC).

cs.IT↗

arXiv2021

Slow wave and truly rainbow trapping in one-way terahertz waveguide

Slow or even stop electromagnetic (EM) waves attract researchers' attentions for its potential applications in energy storage, optical buffer and nonlinearity enhancement. However, in most cases of the EM waves trapping, the EM waves are not truly trapped due to the existence of reflection. In this paper, a novel metal-semiconductor-semiconductor-metal (MSSM) structure, and a novel truly rainbow trapping in a tapered MSSM model at terahertz frequencies are demonstrated by theoretical analysis and numerical simulations. More importantly, functional devices such as optical buffer, optical switch and optical filter are achieved in our designed MSSM structure based on truly rainbow trapping theory. Owing to the property of one-way propagation, these new types of optical devices can be high-performance and are expected to be used in integrated optical circuits.

physics.optics↗

arXiv2021

Autodidactic Neurosurgeon: Collaborative Deep Inference for Mobile Edge Intelligence via Online Learning

Recent breakthroughs in deep learning (DL) have led to the emergence of many intelligent mobile applications and services, but in the meanwhile also pose unprecedented computing challenges on resource-constrained mobile devices. This paper builds a collaborative deep inference system between a resource-constrained mobile device and a powerful edge server, aiming at joining the power of both on-device processing and computation offloading. The basic idea of this system is to partition a deep neural network (DNN) into a front-end part running on the mobile device and a back-end part running on the edge server, with the key challenge being how to locate the optimal partition point to minimize the end-to-end inference delay. Unlike existing efforts on DNN partitioning that rely heavily on a dedicated offline profiling stage to search for the optimal partition point, our system has a built-in online learning module, called Autodidactic Neurosurgeon (ANS), to automatically learn the optimal partition point on-the-fly. Therefore, ANS is able to closely follow the changes of the system environment by generating new knowledge for adaptive decision making. The core of ANS is a novel contextual bandit learning algorithm, called $μ$LinUCB, which not only has provable theoretical learning performance guarantee but also is ultra-lightweight for easy real-world implementation. We implement our system on a video stream object detection testbed to validate the design of ANS and evaluate its performance. The experiments show that ANS significantly outperforms state-of-the-art benchmarks in terms of tracking system changes and reducing the end-to-end inference delay.

cs.LG↗

arXiv2021

Personalized Education in the AI Era: What to Expect Next?

The objective of personalized learning is to design an effective knowledge acquisition track that matches the learner's strengths and bypasses her weaknesses to ultimately meet her desired goal. This concept emerged several years ago and is being adopted by a rapidly-growing number of educational institutions around the globe. In recent years, the boost of artificial intelligence (AI) and machine learning (ML), together with the advances in big data analysis, has unfolded novel perspectives to enhance personalized education in numerous dimensions. By taking advantage of AI/ML methods, the educational platform precisely acquires the student's characteristics. This is done, in part, by observing the past experiences as well as analyzing the available big data through exploring the learners' features and similarities. It can, for example, recommend the most appropriate content among numerous accessible ones, advise a well-designed long-term curriculum, connect appropriate learners by suggestion, accurate performance evaluation, and the like. Still, several aspects of AI-based personalized education remain unexplored. These include, among others, compensating for the adverse effects of the absence of peers, creating and maintaining motivations for learning, increasing diversity, removing the biases induced by the data and algorithms, and the like. In this paper, while providing a brief review of state-of-the-art research, we investigate the challenges of AI/ML-based personalized education and discuss potential solutions.

cs.CY↗

arXiv2021

Unfolding the Neutron Spectra from a Water-Pumping-Injection Multi-layered Concentric Sphere Neutron Spectrometer Using a Self-Adaptive Differential Evolution Algorithm

A self-adaptive differential evolution neutron spectrum unfolding algorithm (SDENUA) was established in this paper to unfold the neutron spectra obtained from a Water-pumping-injection Multi-layered concentric sphere Neutron Spectrometer (WMNS). Specifically, the neutron fluence bounds were estimated to accelerate the algorithm convergence, the minimum error between the optimal solution and the input neutron counts with relative uncertainties was limited to 10-6 to avoid useless calculation. Furthermore, the crossover probability and scaling factor were controlled self-adaptively. FLUKA Monte Carlo was used to simulate the readings of the WMNS under (1) a spectrum of Cf-252 and (2) its spectrum after being moderated, (3) a spectrum used for BNCT, and (4) a reactor spectrum, and the measured neutron counts unfolded by using the SDENUA. The uncertainties of the measured neutron count and the response matrix are considered in the SDENUA, which does not require complex parameter tuning and the priori default spectrum. Results indicate that the solutions of the SDENUA are more in agreement with the IAEA spectra than that of the MAXED and GRAVEL in UMG 3.1, and the errors of the final results calculated by SDENUA are under 12%. The established SDENUA has potential applications for unfolding spectra from the WMNS.

physics.ins-det↗

arXiv2021

Bandwidth Allocation for Multiple Federated Learning Services in Wireless Edge Networks

This paper studies a federated learning (FL) system, where \textit{multiple} FL services co-exist in a wireless network and share common wireless resources. It fills the void of wireless resource allocation for multiple simultaneous FL services in the existing literature. Our method designs a two-level resource allocation framework comprising \emph{intra-service} resource allocation and \emph{inter-service} resource allocation. The intra-service resource allocation problem aims to minimize the length of FL rounds by optimizing the bandwidth allocation among the clients of each FL service. Based on this, an inter-service resource allocation problem is further considered, which distributes bandwidth resources among multiple simultaneous FL services. We consider both cooperative and selfish providers of the FL services. For cooperative FL service providers, we design a distributed bandwidth allocation algorithm to optimize the overall performance of multiple FL services, meanwhile cater to the fairness among FL services and the privacy of clients. For selfish FL service providers, a new auction scheme is designed with the FL service owners as the bidders and the network provider as the auctioneer. The designed auction scheme strikes a balance between the overall FL performance and fairness. Our simulation results show that the proposed algorithms outperform other benchmarks under various network conditions.

cs.NI↗

arXiv2021

Passenger Mobility Prediction via Representation Learning for Dynamic Directed and Weighted Graph

In recent years, ride-hailing services have been increasingly prevalent as they provide huge convenience for passengers. As a fundamental problem, the timely prediction of passenger demands in different regions is vital for effective traffic flow control and route planning. As both spatial and temporal patterns are indispensable passenger demand prediction, relevant research has evolved from pure time series to graph-structured data for modeling historical passenger demand data, where a snapshot graph is constructed for each time slot by connecting region nodes via different relational edges (e.g., origin-destination relationship, geographical distance, etc.). Consequently, the spatiotemporal passenger demand records naturally carry dynamic patterns in the constructed graphs, where the edges also encode important information about the directions and volume (i.e., weights) of passenger demands between two connected regions. However, existing graph-based solutions fail to simultaneously consider those three crucial aspects of dynamic, directed, and weighted (DDW) graphs, leading to limited expressiveness when learning graph representations for passenger demand prediction. Therefore, we propose a novel spatiotemporal graph attention network, namely Gallat (Graph prediction with all attention) as a solution. In Gallat, by comprehensively incorporating those three intrinsic properties of DDW graphs, we build three attention layers to fully capture the spatiotemporal dependencies among different regions across all historical time slots. Moreover, the model employs a subtask to conduct pretraining so that it can obtain accurate results more quickly. We evaluate the proposed model on real-world datasets, and our experimental results demonstrate that Gallat outperforms the state-of-the-art approaches.

cs.LG↗

arXiv2020

A Deep Reinforcement Learning Based Multi-Criteria Decision Support System for Textile Manufacturing Process Optimization

Textile manufacturing is a typical traditional industry involving high complexity in interconnected processes with limited capacity on the application of modern technologies. Decision-making in this domain generally takes multiple criteria into consideration, which usually arouses more complexity. To address this issue, the present paper proposes a decision support system that combines the intelligent data-based random forest (RF) models and a human knowledge based analytical hierarchical process (AHP) multi-criteria structure in accordance to the objective and the subjective factors of the textile manufacturing process. More importantly, the textile manufacturing process is described as the Markov decision process (MDP) paradigm, and a deep reinforcement learning scheme, the Deep Q-networks (DQN), is employed to optimize it. The effectiveness of this system has been validated in a case study of optimizing a textile ozonation process, showing that it can better master the challenging decision-making tasks in textile manufacturing processes.

cs.AI↗

arXiv2020

Multi-Objective Optimization of the Textile Manufacturing Process Using Deep-Q-Network Based Multi-Agent Reinforcement Learning

Multi-objective optimization of the textile manufacturing process is an increasing challenge because of the growing complexity involved in the development of the textile industry. The use of intelligent techniques has been often discussed in this domain, although a significant improvement from certain successful applications has been reported, the traditional methods failed to work with high-as well as human intervention. Upon which, this paper proposed a multi-agent reinforcement learning (MARL) framework to transform the optimization process into a stochastic game and introduced the deep Q-networks algorithm to train the multiple agents. A utilitarian selection mechanism was employed in the stochastic game, which (-greedy policy) in each state to avoid the interruption of multiple equilibria and achieve the correlated equilibrium optimal solutions of the optimizing process. The case study result reflects that the proposed MARL system is possible to achieve the optimal solutions for the textile ozonation process and it performs better than the traditional approaches.

cs.AI↗

arXiv2020

Over-the-Air Computing for Wireless Data Aggregation in Massive IoT

Wireless data aggregation (WDA), referring to aggregating data distributed at devices (e.g., sensors and smartphone), is a common operation in 5G-and-beyond machine-type communications to support Internet-of-Things (IoT), which lays the foundation for diversified applications such as distributed sensing, learning, and control. Conventional WDA techniques that are designed based on a separated-communication-and-computation principle encounter difficulty in accommodating the massive access under the limited radio resource and stringent latency constraints imposed by emerging applications (e.g, auto-driving). To address this issue, over-the-air computation (AirComp) is being developed as a new WDA solution by seamlessly integrating computation and communication. By exploiting the waveform superposition property of a multiple-access channel, AirComp turns the air into a computer for computing and communicating functions of distributed data at many devices, thereby allowing low-latency WDA over massive devices. In view of growing interests on AirComp, this article provides a timely overview of the technology by introducing basic principles, discussing advanced techniques and applications, and identifying promising research opportunities.

cs.NI↗

arXiv2020

Optimized Power Control for Over-the-Air Federated Edge Learning

Over-the-air federated edge learning (Air-FEEL) is a communication-efficient solution for privacy-preserving distributed learning over wireless networks. Air-FEEL allows "one-shot" over-the-air aggregation of gradient/model-updates by exploiting the waveform superposition property of wireless channels, and thus promises an extremely low aggregation latency that is independent of the network size. However, such communication efficiency may come at a cost of learning performance degradation due to the aggregation error caused by the non-uniform channel fading over devices and noise perturbation. Prior work adopted channel inversion power control (or its variants) to reduce the aggregation error by aligning the channel gains, which, however, could be highly suboptimal in deep fading scenarios due to the noise amplification. To overcome this issue, we investigate the power control optimization for enhancing the learning performance of Air-FEEL. Towards this end, we first analyze the convergence behavior of the Air-FEEL by deriving the optimality gap of the loss-function under any given power control policy. Then we optimize the power control to minimize the optimality gap for accelerating convergence, subject to a set of average and maximum power constraints at edge devices. The problem is generally non-convex and challenging to solve due to the coupling of power control variables over different devices and iterations. To tackle this challenge, we develop an efficient algorithm by jointly exploiting the successive convex approximation (SCA) and trust region methods. Numerical results show that the optimized power control policy achieves significantly faster convergence than the benchmark policies such as channel inversion and uniform power transmission.

cs.IT↗

arXiv2020

Asymmetric Interference Cancellation for 5G Non-Public Network with Uplink-Downlink Spectrum Sharing

Different from public 4G/5G networks that are dominated by downlink traffic, emerging 5G non-public networks (NPNs) need to support significant uplink traffic to enable emerging applications such as industrial Internet of things (IIoT). The uplink-and-downlink spectrum sharing is becoming a viable solution to enhance the uplink throughput of NPNs, which allows the NPNs to perform the uplink transmission over the time-frequency resources configured for downlink transmission in coexisting public networks. To deal with the severe interference from the downlink public base station (BS) transmitter to the coexisting uplink non-public BS receiver, we propose an adaptive asymmetric successive interference cancellation (SIC) approach, in which the non-public BS receiver is enabled to have the capability of decoding the downlink signals transmitted from the public BS and successively cancelling them for interference mitigation. In particular, this paper studies a basic uplink-and-downlink spectrum sharing scenario when an uplink non-public BS and a downlink public BS coexist in the same area, each communicating with multiple users via orthogonal frequency-division multiple access (OFDMA). Under this setup, we aim to maximize the common uplink throughput of all non-public users, under the condition that the downlink throughput of each public user is above a certain threshold. The decision variables include the subcarrier allocation and user scheduling for both non-public (uplink) and public (downlink) BSs, the decoding mode of the non-public BS over each subcarrier (i.e., with or without SIC), as well as the rate and power control over subcarriers. Numerical results show that the proposed adaptive asymmetric SIC design significantly improves the common uplink throughput as compared to benchmark schemes without such design.

cs.IT↗

arXiv2020

Max-Min Fairness in IRS-Aided Multi-Cell MISO Systems with Joint Transmit and Reflective Beamforming

This paper investigates an intelligent reflecting surface (IRS)-aided multi-cell multiple-input single-output (MISO) system with several multi-antenna base stations (BSs) each communicating with a single-antenna user, in which an IRS is dedicatedly deployed for assisting the wireless transmission and suppressing the inter-cell interference. Under this setup, we jointly optimize the coordinated transmit beamforming at the BSs and the reflective beamforming at the IRS, for the purpose of maximizing the minimum weighted signal-to-interference-plus-noise ratio (SINR) at the users, subject to the individual maximum transmit power at the BSs and the reflection constraints at the IRS. To solve the non-convex problem, we first present an exact-alternating-optimization design to optimize the transmit and reflective beamforming vectors in an alternating manner, in which the transmit and reflective beamforming optimization subproblems are solved exactly by using the technique of semi-definite relaxation (SDR). However, it has high computational complexity and may lead to compromised performance due to the uncertainty of randomization in SDR. To avoid these drawbacks, we further propose an inexact-alternating-optimization design, in which the transmit and reflective beamforming optimization subproblems are solved inexactly based on the principle of successive convex approximation (SCA). In addition, to further reduce the complexity, we propose a low-complexity inexact-alternating-optimization design, in which the reflective beamforming optimization subproblem is solved more inexactly. Numerical results show that the significant performance gains achieved by the proposed three designs against benchmark schemes. Moreover, the inexact-alternating-optimization designs outperform the exact-alternating-optimization one in terms of both the achieved min-weighted-SINR value and the computational complexity.

eess.SP↗

arXiv2020

Parallel Interactive Networks for Multi-Domain Dialogue State Generation

The dependencies between system and user utterances in the same turn and across different turns are not fully considered in existing multidomain dialogue state tracking (MDST) models. In this study, we argue that the incorporation of these dependencies is crucial for the design of MDST and propose Parallel Interactive Networks (PIN) to model these dependencies. Specifically, we integrate an interactive encoder to jointly model the in-turn dependencies and cross-turn dependencies. The slot-level context is introduced to extract more expressive features for different slots. And a distributed copy mechanism is utilized to selectively copy words from historical system utterances or historical user utterances. Empirical studies demonstrated the superiority of the proposed PIN model.

cs.CL↗

arXiv2020

Impermeable Inorganic Walls Sandwiching Photoactive Layer toward Inverted Perovskite Solar and Indoor-Photovoltaic Devices

Interfaces between the perovskite active layer and the charge-transport layers (CTLs) play a critical role in both efficiency and stability of halide-perovskite photovoltaics. One of the major concerns is that surface defects of perovskite could cause detrimental nonradiative recombination and material degradation. In this work, we addressed this challenging problem by inserting ultrathin alkali-fluoride (AF) films between the tri-cation lead-iodide perovskite layer and both CTLs. This bilateral inorganic walls strategy makes use of both physical-blocking and chemical-anchoring functionalities of the continuous, uniform and compact AF framework: on the one hand, the uniformly distributed alkali-iodine coordination at the perovskite-AF interfaces effectively suppresses the formation of iodine-vacancy defects at the surfaces and grain boundaries of the whole perovskite film, thus reducing the trap-assisted recombination at the perovskite-CTL interfaces and therewith the open-voltage loss; on the other hand, the impermeable AF buffer layers effectively prevent the bidirectional ion migration at the perovskite-CTLs interfaces even under harsh working conditions. As a result, a power-conversion efficiency (PCE) of 22.02% (certified efficiency 20.4%) with low open-voltage deficit (< 0.4V) was achieved for the low-temperature processed inverted planar perovskite solar cells. Exceptional operational stability (500 h, ISOS-L-2) and thermal stability (1000 h, ISOS-D-2) were obtained. Meanwhile, a 35.7% PCE was obtained under dim-light source (1000 lux white LED light) with the optimized device, which is among the best records in perovskite indoor photovoltaics.

cond-mat.mtrl-sci↗

arXiv2020

Neural Dialogue State Tracking with Temporally Expressive Networks

Dialogue state tracking (DST) is an important part of a spoken dialogue system. Existing DST models either ignore temporal feature dependencies across dialogue turns or fail to explicitly model temporal state dependencies in a dialogue. In this work, we propose Temporally Expressive Networks (TEN) to jointly model the two types of temporal dependencies in DST. The TEN model utilizes the power of recurrent networks and probabilistic graphical models. Evaluating on standard datasets, TEN is demonstrated to be effective in improving the accuracy of turn-level-state prediction and the state aggregation.

cs.CL↗

arXiv2020

An Optimal Computing Budget Allocation Tree Policy for Monte Carlo Tree Search

We analyze a tree search problem with an underlying Markov decision process, in which the goal is to identify the best action at the root that achieves the highest cumulative reward. We present a new tree policy that optimally allocates a limited computing budget to maximize a lower bound on the probability of correctly selecting the best action at each node. Compared to widely used Upper Confidence Bound (UCB) tree policies, the new tree policy presents a more balanced approach to manage the exploration and exploitation trade-off when the sampling budget is limited. Furthermore, UCB assumes that the support of reward distribution is known, whereas our algorithm relaxes this assumption. Numerical experiments demonstrate the efficiency of our algorithm in selecting the best action at the root.

eess.SY↗

arXiv2020

A(DP)$^2$SGD: Asynchronous Decentralized Parallel Stochastic Gradient Descent with Differential Privacy

As deep learning models are usually massive and complex, distributed learning is essential for increasing training efficiency. Moreover, in many real-world application scenarios like healthcare, distributed learning can also keep the data local and protect privacy. A popular distributed learning strategy is federated learning, where there is a central server storing the global model and a set of local computing nodes updating the model parameters with their corresponding data. The updated model parameters will be processed and transmitted to the central server, which leads to heavy communication costs. Recently, asynchronous decentralized distributed learning has been proposed and demonstrated to be a more efficient and practical strategy where there is no central server, so that each computing node only communicates with its neighbors. Although no raw data will be transmitted across different local nodes, there is still a risk of information leak during the communication process for malicious participants to make attacks. In this paper, we present a differentially private version of asynchronous decentralized parallel SGD (ADPSGD) framework, or A(DP)$^2$SGD for short, which maintains communication efficiency of ADPSGD and prevents the inference from malicious participants. Specifically, R{é}nyi differential privacy is used to provide tighter privacy analysis for our composite Gaussian mechanisms while the convergence rate is consistent with the non-private version. Theoretical analysis shows A(DP)$^2$SGD also converges at the optimal $\mathcal{O}(1/\sqrt{T})$ rate as SGD. Empirically, A(DP)$^2$SGD achieves comparable model accuracy as the differentially private version of Synchronous SGD (SSGD) but runs much faster than SSGD in heterogeneous computing environments.

cs.LG↗