Showing papers by "Huawei published in 2018"

PointCNN: convolution on Χ -transformed points

Abstract: We present a simple and general framework for feature learning from point clouds. The key to the success of CNNs is the convolution operator that is capable of leveraging spatially-local correlation in data represented densely in grids (e.g. images). However, point clouds are irregular and unordered, thus directly convolving kernels against features associated with the points will result in desertion of shape information and variance to point ordering. To address these problems, we propose to learn an Χ-transformation from the input points to simultaneously promote two causes: the first is the weighting of the input features associated with the points, and the second is the permutation of the points into a latent and potentially canonical order. Element-wise product and sum operations of the typical convolution operator are subsequently applied on the Χ-transformed features. The proposed method is a generalization of typical CNNs to feature learning from point clouds, thus we call it PointCNN. Experiments show that PointCNN achieves on par or better performance than state-of-the-art methods on multiple challenging benchmark datasets and tasks.

A Tutorial on UAVs for Wireless Networks: Applications, Challenges, and Open Problems

Abstract: The use of flying platforms such as unmanned aerial vehicles (UAVs), popularly known as drones, is rapidly growing. In particular, with their inherent attributes such as mobility, flexibility, and adaptive altitude, UAVs admit several key potential applications in wireless systems. On the one hand, UAVs can be used as aerial base stations to enhance coverage, capacity, reliability, and energy efficiency of wireless networks. On the other hand, UAVs can operate as flying mobile terminals within a cellular network. Such cellular-connected UAVs can enable several applications ranging from real-time video streaming to item delivery. In this paper, a comprehensive tutorial on the potential benefits and applications of UAVs in wireless communications is presented. Moreover, the important challenges and the fundamental tradeoffs in UAV-enabled wireless networks are thoroughly investigated. In particular, the key UAV challenges such as three-dimensional deployment, performance analysis, channel modeling, and energy efficiency are explored along with representative results. Then, open problems and potential research directions pertaining to UAV communications are introduced. Finally, various analytical frameworks and mathematical tools such as optimization theory, machine learning, stochastic geometry, transport theory, and game theory are described. The use of such tools for addressing unique UAV problems is also presented. In a nutshell, this tutorial provides key guidelines on how to analyze, optimize, and design UAV-based wireless communication systems.

Ultrareliable and Low-Latency Wireless Communication: Tail, Risk, and Scale

Abstract: Ensuring ultrareliable and low-latency communication (URLLC) for 5G wireless networks and beyond is of capital importance and is currently receiving tremendous attention in academia and industry. At its core, URLLC mandates a departure from expected utility-based network design approaches, in which relying on average quantities (e.g., average throughput, average delay, and average response time) is no longer an option but a necessity. Instead, a principled and scalable framework which takes into account delay, reliability, packet size, network architecture and topology (across access, edge, and core), and decision-making under uncertainty is sorely lacking. The overarching goal of this paper is a first step to filling this void. Towards this vision, after providing definitions of latency and reliability, we closely examine various enablers of URLLC and their inherent tradeoffs. Subsequently, we focus our attention on a wide variety of techniques and methodologies pertaining to the requirements of URLLC, as well as their applications through selected use cases. These results provide crisp insights for the design of low-latency and high-reliability wireless networks.

Network Slicing and Softwarization: A Survey on Principles, Enabling Technologies, and Solutions

Abstract: Network slicing has been identified as the backbone of the rapidly evolving 5G technology. However, as its consolidation and standardization progress, there are no literatures that comprehensively discuss its key principles, enablers, and research challenges. This paper elaborates network slicing from an end-to-end perspective detailing its historical heritage, principal concepts, enabling technologies and solutions as well as the current standardization efforts. In particular, it overviews the diverse use cases and network requirements of network slicing, the pre-slicing era, considering RAN sharing as well as the end-to-end orchestration and management, encompassing the radio access, transport network and the core network. This paper also provides details of specific slicing solutions for each part of the 5G system. Finally, this paper identifies a number of open research challenges and provides recommendations toward potential solutions.

Reconfigurable Intelligent Surfaces for Energy Efficiency in Wireless Communication

Abstract: The adoption of a Reconfigurable Intelligent Surface (RIS) for downlink multi-user communication from a multi-antenna base station is investigated in this paper. We develop energy-efficient designs for both the transmit power allocation and the phase shifts of the surface reflecting elements, subject to individual link budget guarantees for the mobile users. This leads to non-convex design optimization problems for which to tackle we propose two computationally affordable approaches, capitalizing on alternating maximization, gradient descent search, and sequential fractional programming. Specifically, one algorithm employs gradient descent for obtaining the RIS phase coefficients, and fractional programming for optimal transmit power allocation. Instead, the second algorithm employs sequential fractional programming for the optimization of the RIS phase shifts. In addition, a realistic power consumption model for RIS-based systems is presented, and the performance of the proposed methods is analyzed in a realistic outdoor environment. In particular, our results show that the proposed RIS-based resource allocation methods are able to provide up to $300\%$ higher energy efficiency, in comparison with the use of regular multi-antenna amplify-and-forward relaying.

Fluorine-donating electrolytes enable highly reversible 5-V-class Li metal batteries

Abstract: Lithium metal has gravimetric capacity ∼10× that of graphite which incentivizes rechargeable Li metal batteries (RLMB) development. A key factor that limits practical use of RLMB is morphological instability of Li metal anode upon electrodeposition, reflected by the uncontrolled area growth of solid–electrolyte interphase that traps cyclable Li, quantified by the Coulombic inefficiency (CI). Here we show that CI decreases approximately exponentially with increasing donatable fluorine concentration of the electrolyte. By using up to 7 m of Li bis(fluorosulfonyl)imide in fluoroethylene carbonate, where both the solvent and the salt donate F, we can significantly suppress anode porosity and improve the Coulombic efficiency to 99.64%. The electrolyte demonstrates excellent compatibility with 5-V LiNi0.5Mn1.5O4 cathode and Al current collector beyond 5 V. As a result, an RLMB full cell with only 1.4× excess lithium as the anode was demonstrated to cycle above 130 times, at industrially significant loading of 1.83 mAh/cm2 and 0.36 C. This is attributed to the formation of a protective LiF nanolayer, which has a wide bandgap, high surface energy, and small Burgers vector, making it ductile at room temperature and less likely to rupture in electrodeposition.

Approaching the capacity limit of lithium cobalt oxide in lithium ion batteries via lanthanum and aluminium doping

Abstract: Lithium cobalt oxides (LiCoO2) possess a high theoretical specific capacity of 274 mAh g–1. However, cycling LiCoO2-based batteries to voltages greater than 4.35 V versus Li/Li+ causes significant structural instability and severe capacity fade. Consequently, commercial LiCoO2 exhibits a maximum capacity of only ~165 mAh g–1. Here, we develop a doping technique to tackle this long-standing issue of instability and thus increase the capacity of LiCoO2. La and Al are concurrently doped into Co-containing precursors, followed by high-temperature calcination with lithium carbonate. The dopants are found to reside in the crystal lattice of LiCoO2, where La works as a pillar to increase the c axis distance and Al as a positively charged centre, facilitating Li+ diffusion, stabilizing the structure and suppressing the phase transition during cycling, even at a high cut-off voltage of 4.5 V. This doped LiCoO2 displays an exceptionally high capacity of 190 mAh g–1, cyclability with 96% capacity retention over 50 cycles and significantly enhanced rate capability. Lithium cobalt oxides are used as a cathode material in batteries for mobile devices, but their high theoretical capacity has not yet been realized. Here, the authors present a doping method to enhance diffusion of Li ions as well as to stabilize structures during cycling, leading to impressive electrochemical performance.

The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking

Abstract: With the advantage of high mobility, Unmanned Aerial Vehicles (UAVs) are used to fuel numerous important applications in computer vision, delivering more efficiency and convenience than surveillance cameras with fixed camera angle, scale and view. However, very limited UAV datasets are proposed, and they focus only on a specific task such as visual tracking or object detection in relatively constrained scenarios. Consequently, it is of great importance to develop an unconstrained UAV benchmark to boost related researches. In this paper, we construct a new UAV benchmark focusing on complex scenarios with new level challenges. Selected from 10 hours raw videos, about 80, 000 representative frames are fully annotated with bounding boxes as well as up to 14 kinds of attributes (e.g., weather condition, flying altitude, camera view, vehicle category, and occlusion) for three fundamental computer vision tasks: object detection, single object tracking, and multiple object tracking. Then, a detailed quantitative study is performed using most recent state-of-the-art algorithms for each task. Experimental results show that the current state-of-the-art methods perform relative worse on our dataset, due to the new challenges appeared in UAV based real scenes, e.g., high density, small object, and camera motion. To our knowledge, our work is the first time to explore such issues in unconstrained scenes comprehensively. The dataset and all the experimental results are available in https://sites.google.com/site/daviddo0323/.

Millimeter Wave Communication: A Comprehensive Survey

Abstract: Millimeter wave (mmWave) communication has raised increasing attentions from both academia and industry due to its exceptional advantages. Compared with existing wireless communication techniques, such as WiFi and 4G, mmWave communications adopt much higher carrier frequencies and thus come with advantages including huge bandwidth, narrow beam, high transmission quality, and strong detection ability. These advantages can well address difficult situations caused by recent popular applications using wireless technologies. For example, mmWave communications can significantly alleviate the skyrocketing traffic demand of wireless communication from video streaming. Meanwhile, mmWave communications have several natural disadvantages, e.g., severe signal attenuation, easily blocked by obstacles, and small coverage, due to its short wavelengths. Hence, the major challenge is how to overcome its shortcomings while fully utilizing its advantages. In this paper, we present a taxonomy based on the layered model and give an extensive review on mmWave communications. Specially, we divide existing efforts into four categories that investigate: physical layer, medium access control (MAC) layer, network layer, and cross layer optimization, respectively. First, we present an overview of some technical details in physical layer. Second, we summarize available literature in MAC layer that pertains to protocols and scheduling schemes. Third, we make an in-depth survey of related research work in network layer, providing brain storming and methodology for enhancing the capacity and coverage of mmWave networks. Fourth, we analyze available research work related to cross layer allocation/optimization for mmWave communications. Fifth, we make a review of mmWave applications to illustrate how mmWave technology can be employed to satisfy other services. At the end of each section described above, we point out the inadequacy of existing work and identify the future work. Sixth, we present some available resources for mmWave communications, including related books about mmWave, commonly used mmWave frequencies, existing protocols based on mmWave, and experimental platforms. Finally, we have a simple summary and point out several promising future research directions.

Diagrammatic routes to nonlocal correlations beyond dynamical mean field theory

Abstract: Strong electronic correlations pose one of the biggest challenges to solid state theory. We review recently developed methods that address this problem by starting with the local, eminently important correlations of dynamical mean field theory (DMFT). On top of this, non-local correlations on all length scales are generated through Feynman diagrams, with a local two-particle vertex instead of the bare Coulomb interaction as a building block. With these diagrammatic extensions of DMFT long-range charge-, magnetic-, and superconducting fluctuations as well as (quantum) criticality can be addressed in strongly correlated electron systems. We provide an overview of the successes and results achieved---hitherto mainly for model Hamiltonians---and outline future prospects for realistic material calculations.

AI Benchmark: Running Deep Neural Networks on Android Smartphones

Abstract: Over the last years, the computational power of mobile devices such as smartphones and tablets has grown dramatically, reaching the level of desktop computers available not long ago. While standard smartphone apps are no longer a problem for them, there is still a group of tasks that can easily challenge even high-end devices, namely running artificial intelligence algorithms. In this paper, we present a study of the current state of deep learning in the Android ecosystem and describe available frameworks, programming models and the limitations of running AI on smartphones. We give an overview of the hardware acceleration resources available on four main mobile chipset platforms: Qualcomm, HiSilicon, MediaTek and Samsung. Additionally, we present the real-world performance results of different mobile SoCs collected with AI Benchmark (http://ai-benchmark.com) that are covering all main existing hardware configurations.

A Survey of Enabling Technologies for Network Localization, Tracking, and Navigation

Abstract: Location information for events, assets, and individuals, mostly focusing on two dimensions so far, has triggered a multitude of applications across different verticals, such as consumer, networking, industrial, health care, public safety, and emergency response use cases. To fully exploit the potential of location awareness and enable new advanced location-based services, localization algorithms need to be combined with complementary technologies including accurate height estimation, i.e., three dimensional location, reliable user mobility classification, and efficient indoor mapping solutions. This survey provides a comprehensive review of such enabling technologies. In particular, we present cellular localization systems including recent results on 5G localization, and solutions based on wireless local area networks, highlighting those that are capable of computing 3D location in multi-floor indoor environments. We overview range-free localization schemes, which have been traditionally explored in wireless sensor networks and are nowadays gaining attention for several envisioned Internet of Things applications. We also present user mobility estimation techniques, particularly those applicable in cellular networks, that can improve localization and tracking accuracy. Regarding the mapping of physical space inside buildings for aiding tracking and navigation applications, we study recent advances and focus on smartphone-based indoor simultaneous localization and mapping approaches. The survey concludes with service availability and system scalability considerations, as well as security and privacy concerns in location architectures, discusses the technology roadmap, and identifies future research directions.

Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration

Abstract: Previous works utilized ''smaller-norm-less-important'' criterion to prune filters with smaller norm values in a convolutional neural network. In this paper, we analyze this norm-based criterion and point out that its effectiveness depends on two requirements that are not always met: (1) the norm deviation of the filters should be large; (2) the minimum norm of the filters should be small. To solve this problem, we propose a novel filter pruning method, namely Filter Pruning via Geometric Median (FPGM), to compress the model regardless of those two requirements. Unlike previous methods, FPGM compresses CNN models by pruning filters with redundancy, rather than those with ''relatively less'' importance. When applied to two image classification benchmarks, our method validates its usefulness and strengths. Notably, on CIFAR-10, FPGM reduces more than 52% FLOPs on ResNet-110 with even 2.69% relative accuracy improvement. Moreover, on ILSVRC-2012, FPGM reduces more than 42% FLOPs on ResNet-101 without top-5 accuracy drop, which has advanced the state-of-the-art. Code is publicly available on GitHub: this https URL

Energy Efficient Multi-User MISO Communication Using Low Resolution Large Intelligent Surfaces

Abstract: We consider a multi-user Multiple-Input Single-Output (MISO) communication system comprising of a multiantenna base station communicating in the downlink simultaneously with multiple single-antenna mobile users. This communication is assumed to be assisted by a Large Intelligent Surface (LIS) that consists of many nearly passive antenna elements, whose parameters can be tuned according to desired objectives. The latest design advances on these surfaces suggest cheap elements effectively acting as low resolution (even 1-bit resolution) phase shifters, whose joint configuration affects the electromagnetic behavior of the wireless propagation channel. In this paper, we investigate the suitability of LIS for green communications in terms of Energy Efficiency (EE), which is expressed as the number of bits per Joule. In particular, for the considered multi-user MISO system, we design the transmit powers per user and the values for the surface elements that jointly maximize the system's EE performance. Our representative simulation results show that LIS-assisted communication, even with nearly passive 1-bit resolution antenna elements, provides significant EE gains compared to conventional relay-assisted communication.

BlocHIE: A BLOCkchain-Based Platform for Healthcare Information Exchange

Abstract: Nowadays, a great number of healthcare data are generated every day from both medical institutions and individuals. Healthcare information exchange (HIE) has been proved to benefit the medical industry remarkably. To store and share such large amount of healthcare data is important while challenging. In this paper, we propose BlocHIE, a Blockchain-based platform for healthcare information exchange. First, we analyze the different requirements for sharing healthcare data from different sources. Based on the analysis, we employ two loosely-coupled Blockchains to handle different kinds of healthcare data. Second, we combine off-chain storage and on-chain verification to satisfy the requirements of both privacy and authenticability. Third, we propose two fairness-based packing algorithms to improve the system throughput and the fairness among users jointly. To demonstrate the practicability and effectiveness of BlocHIE, we implement BlocHIE in a minimal-viable-product way and evaluate the proposed packing algorithms extensively.

Metrology for the next generation of semiconductor devices

Abstract: The semiconductor industry continues to produce ever smaller devices that are ever more complex in shape and contain ever more types of materials. The ultimate sizes and functionality of these new devices will be affected by fundamental and engineering limits such as heat dissipation, carrier mobility and fault tolerance thresholds. At present, it is unclear which are the best measurement methods needed to evaluate the nanometre-scale features of such devices and how the fundamental limits will affect the required metrology. Here, we review state-of-the-art dimensional metrology methods for integrated circuits, considering the advantages, limitations and potential improvements of the various approaches. We describe how integrated circuit device design and industry requirements will affect lithography options and consequently metrology requirements. We also discuss potentially powerful emerging technologies and highlight measurement problems that at present have no obvious solution.

The Role of Caching in Future Communication Systems and Networks

Abstract: This paper has the following ambitious goal: to convince the reader that content caching is an exciting research topic for the future communication systems and networks. Caching has been studied for more than 40 years, and has recently received increased attention from industry and academia. Novel caching techniques promise to push the network performance to unprecedented limits, but also pose significant technical challenges. This tutorial provides a brief overview of existing caching solutions, discusses seminal papers that open new directions in caching, and presents the contributions of this special issue. We analyze the challenges that caching needs to address today, also considering an industry perspective, and identify bottleneck issues that must be resolved to unleash the full potential of this promising technique.

Continuous-Variable Quantum Key Distribution with Gaussian Modulation—The Theory of Practical Implementations

Abstract: Quantum key distribution using weak coherent states and homodyne detection is a promising candidate for practical quantum-cryptographic implementations due to its compatibility with existing telecom equipment and high detection efficiencies. However, despite the actual simplicity of the protocol, the security analysis of this method is rather involved compared to discrete-variable QKD. In this article we review the theoretical foundations of continuous-variable quantum key distribution (CV-QKD) with Gaussian modulation and rederive the essential relations from scratch in a pedagogical way. The aim of this paper is to be as comprehensive and self-contained as possible in order to be well intelligible even for readers with little pre-knowledge on the subject. Although the present article is a theoretical discussion of CV-QKD, its focus lies on practical implementations, taking into account various kinds of hardware imperfections and suggesting practical methods to perform the security analysis subsequent to the key exchange. Apart from a review of well known results, this manuscript presents a set of new original noise models which are helpful to get an estimate of how well a given set of hardware will perform in practice.

Self-attentive Speaker Embeddings for Text-independent Speaker Verification

Abstract: This paper introduces a new method to extract speaker embeddings from a deep neural network (DNN) for text-independent speaker verification. Usually, speaker embeddings are extracted from a speaker-classification DNN that averages the hidden vectors over the frames of a speaker; the hidden vectors produced from all the frames are assumed to be equally important. We relax this assumption and compute the speaker embedding as a weighted average of a speaker’s frame-level hidden vectors, and their weights are automatically determined by a self-attention mechanism. The effect of multiple attention heads are also investigated to capture different aspects of a speaker’s input speech. Finally, a PLDA classifier is used to compare pairs of embeddings. The proposed self-attentive speaker embedding system is compared with a strong DNN embedding baseline on NIST SRE 2016. We find that the self-attentive embeddings achieve superior performance. Moreover, the improvement produced by the self-attentive speaker embeddings is consistent with both short and long testing utterances.

Federated Meta-Learning with Fast Convergence and Efficient Communication

Abstract: Statistical and systematic challenges in collaboratively training machine learning models across distributed networks of mobile devices have been the bottlenecks in the real-world application of federated learning. In this work, we show that meta-learning is a natural choice to handle these issues, and propose a federated meta-learning framework FedMeta, where a parameterized algorithm (or meta-learner) is shared, instead of a global model in previous approaches. We conduct an extensive empirical evaluation on LEAF datasets and a real-world production dataset, and demonstrate that FedMeta achieves a reduction in required communication cost by 2.82-4.33 times with faster convergence, and an increase in accuracy by 3.23%-14.84% as compared to Federated Averaging (FedAvg) which is a leading optimization algorithm in federated learning. Moreover, FedMeta preserves user privacy since only the parameterized algorithm is transmitted between mobile devices and central servers, and no raw data is collected onto the servers.

Deep Learning for Environmentally Robust Speech Recognition: An Overview of Recent Developments

Abstract: Eliminating the negative effect of non-stationary environmental noise is a long-standing research topic for automatic speech recognition but still remains an important challenge. Data-driven supervised approaches, especially the ones based on deep neural networks, have recently emerged as potential alternatives to traditional unsupervised approaches and with sufficient training, can alleviate the shortcomings of the unsupervised methods in various real-life acoustic environments. In this light, we review recently developed, representative deep learning approaches for tackling non-stationary additive and convolutional degradation of speech with the aim of providing guidelines for those involved in the development of environmentally robust speech recognition systems. We separately discuss single- and multi-channel techniques developed for the front-end and back-end of speech recognition systems, as well as joint front-end and back-end training frameworks. In the meanwhile, we discuss the pros and cons of these approaches and provide their experimental results on benchmark databases. We expect that this overview can facilitate the development of the robustness of speech recognition systems in acoustic noisy environments.

Towards Massive Connectivity Support for Scalable mMTC Communications in 5G Networks

Abstract: The fifth generation of cellular communication systems is foreseen to enable a multitude of new applications and use cases with very different requirements. A new 5G multi-service air interface needs to enhance broadband performance as well as provide new levels of reliability, latency, and supported number of users. In this paper, we focus on the massive Machine Type Communications (mMTC) service within a multi-service air interface. Specifically, we present an overview of different physical and medium access techniques to address the problem of a massive number of access attempts in mMTC and discuss the protocol performance of these solutions in a common evaluation framework.

Connected Roads of the Future: Use Cases, Requirements, and Design Considerations for Vehicle-to-Everything Communications

Abstract: The ultimate goal of next-generation vehicle-toeverything (V2X) communication systems is enabling accident-free, cooperative automated driving that uses the available roadway efficiently. To achieve this goal, the communication system will need to enable a diverse set of use cases, each with a specific set of requirements. We discuss the main usecase categories, analyze their requirements, and compare them against the capabilities of currently available communication technologies. Based on the analysis, we identify a gap and indicate possible system designs for the fifth-generation (5G) V2X that could close the gap. Furthermore, we discuss an architecture of the 5G V2X radio access network (RAN) that incorporates diverse communication technologies, including current and cellular systems in centimeter wave (cm-wave) and millimeter wave (mm-wave), IEEE Standard 802.11p [1], and vehicular visible light communications (VVLC). Finally, we discuss the role of future 5G V2X systems in enabling more efficient vehicular transportation: from improved traffic flow and reduced intervehicle spacing on highways to coordinated intersections in cities (the cheapest way to increasing the road capacity) to automated smart parking (no more visits to the parking garage!), all of which will ultimately enable seamless end-to-end personal mobility.

Spectrum for 5G: Global Status, Challenges, and Enabling Technologies

Abstract: Availability of widely harmonized mobile spectrum is crucial for the success of 5G mobile communications, fulfilling the visions and requirements and delivering the full range of potential capabilities for 5G. This article introduces the global situation of spectrum for 5G, both below and above 6 GHz, in both the regulatory status and technical aspects. In particular, the technical challenges of supporting 5G in millimeter-wave spectrum, such as coverage limitation and implementation aspects, are discussed.

Paraphrase Generation with Deep Reinforcement Learning

Abstract: Automatic generation of paraphrases from a given sentence is an important yet challenging task in natural language processing (NLP). In this paper, we present a deep reinforcement learning approach to paraphrase generation. Specifically, we propose a new framework for the task, which consists of a generator and an evaluator, both of which are learned from data. The generator, built as a sequence-to-sequence learning model, can produce paraphrases given a sentence. The evaluator, constructed as a deep matching model, can judge whether two sentences are paraphrases of each other. The generator is first trained by deep learning and then further fine-tuned by reinforcement learning in which the reward is given by the evaluator. For the learning of the evaluator, we propose two methods based on supervised learning and inverse reinforcement learning respectively, depending on the type of available training data. Experimental results on two datasets demonstrate the proposed models (the generators) can produce more accurate paraphrases and outperform the state-of-the-art methods in paraphrase generation in both automatic evaluation and human evaluation.

Energy Efficient Multi-User MISO Communication using Low Resolution Large Intelligent Surfaces

Abstract: We consider a multi-user Multiple-Input Single-Output (MISO) communication system comprising of a multi-antenna base station communicating in the downlink simultaneously with multiple single-antenna mobile users. This communication is assumed to be assisted by a Large Intelligent Surface (LIS) that consists of many nearly passive antenna elements, whose parameters can be tuned according to desired objectives. The latest design advances on these surfaces suggest cheap elements effectively acting as low resolution (even $1$-bit resolution) phase shifters, whose joint configuration affects the electromagnetic behavior of the wireless propagation channel. In this paper, we investigate the suitability of LIS for green communications in terms of Energy Efficiency (EE), which is expressed as the number of bits per Joule. In particular, for the considered multi-user MISO system, we design the transmit powers per user and the values for the surface elements that jointly maximize the system's EE performance. Our representative simulation results show that LIS-assisted communication, even with nearly passive $1$-bit resolution antenna elements, provides significant EE gains compared to conventional relay-assisted communication.

Pose-Guided Photorealistic Face Rotation

Abstract: Face rotation provides an effective and cheap way for data augmentation and representation learning of face recognition. It is a challenging generative learning problem due to the large pose discrepancy between two face images. This work focuses on flexible face rotation of arbitrary head poses, including extreme profile views. We propose a novel Couple-Agent Pose-Guided Generative Adversarial Network (CAPG-GAN) to generate both neutral and profile head pose face images. The head pose information is encoded by facial landmark heatmaps. It not only forms a mask image to guide the generator in learning process but also provides a flexible controllable condition during inference. A couple-agent discriminator is introduced to reinforce on the realism of synthetic arbitrary view faces. Besides the generator and conditional adversarial loss, CAPG-GAN further employs identity preserving loss and total variation regularization to preserve identity information and refine local textures respectively. Quantitative and qualitative experimental results on the Multi-PIE and LFW databases consistently show the superiority of our face rotation method over the state-of-the-art.

Modeling Localness for Self-Attention Networks

Abstract: Self-attention networks have proven to be of profound value for its strength of capturing global dependencies. In this work, we propose to model localness for self-attention networks, which enhances the ability of capturing useful local context. We cast localness modeling as a learnable Gaussian bias, which indicates the central and scope of the local region to be paid more attention. The bias is then incorporated into the original attention distribution to form a revised distribution. To maintain the strength of capturing long distance dependencies while enhance the ability of capturing short-range dependencies, we only apply localness modeling to lower layers of self-attention networks. Quantitative and qualitative analyses on Chinese-English and English-German translation tasks demonstrate the effectiveness and universality of the proposed approach.

The University of Sussex-Huawei Locomotion and Transportation Dataset for Multimodal Analytics With Mobile Devices

Abstract: Scientific advances build on reproducible researches which need publicly available benchmark data sets. The computer vision and speech recognition communities have led the way in establishing benchmark data sets. There are much less data sets available in mobile computing, especially for rich locomotion and transportation analytics. This paper presents a highly versatile and precisely annotated large-scale data set of smartphone sensor data for multimodal locomotion and transportation analytics of mobile users. The data set comprises seven months of measurements, collected from all sensors of four smartphones carried at typical body locations, including the images of a body-worn camera, while three participants used eight different modes of transportation in the south-east of the U.K., including in London. In total, 28 context labels were annotated, including transportation mode, participant’s posture, inside/outside location, road conditions, traffic conditions, presence in tunnels, social interactions, and having meals. The total amount of collected data exceed 950 GB of sensor data, which corresponds to 2812 h of labeled data and 17 562 km of traveled distance. We present how we set up the data collection, including the equipment used and the experimental protocol. We discuss the data set, including the data curation process, the analysis of the annotations, and of the sensor data. We discuss the challenges encountered and present the lessons learned and some of the best practices we developed to ensure high quality data collection and annotation. We discuss the potential applications which can be developed using this large-scale data set. In particular, we present how a machine-learning system can use this data set to automatically recognize modes of transportations. Many other research questions related to transportation analytics, activity recognition, radio signal propagation and mobility modeling can be addressed through this data set. The full data set is being made available to the community, and a thorough preview is already published.

Age-optimal trajectory planning for UAV-assisted data collection

Abstract: Unmanned aerial vehicle (UAV)-aided data collection is a new and promising application in many practical scenarios. In this work, we study the age-optimal trajectory planning problem in UAV-enabled wireless sensor networks, where a UAV is dispatched to collect data from the ground sensor nodes (SNs). The age of information (AoI) collected from each SN is characterized by the data uploading time and the time elapsed since the UAV leaves this SN. We attempt to design two age-optimal trajectories, referred to as the Max-AoI-optimal and Ave-AoI-optimal trajectories, respectively. The Max-AoI-optimal trajectory planning is to minimize the age of the ‘oldest’ sensed information among the SNs. The Ave-AoI-optimal trajectory planning is to minimize the average AoI of all the SNs. Then, we show that each age-optimal flight trajectory corresponds to a shortest Hamiltonian path in the wireless sensor network where the distance between any two SNs represents the amount of inter-visit time. The dynamic programming (DP) method and genetic algorithm (GA) are adopted to find the two different age-optimal trajectories. Simulation results validate the effectiveness of the proposed methods, and show how the UAV's trajectory is affected by the two AoI metrics.