When sensing goes pervasive

In line with the pervasive vision, pervasive sensing allows the provision of ubiquitous and pervasive monitoring and heterogeneous data collection. In the past decade, two dominant pervasive sensing paradigms have emerged: a mostly human-free paradigm centered around wireless sensor networks and a human-centric paradigm fueled by the rise of personal smart devices (smartphones and wearables). In this paper, we review the key advances in these areas and outline our vision for future directions and developments.     

基于三维胞元空间的MA双向并行路由算法

针对传统移动代理(MA)在监测无线传感器网络(WSNs)的感兴趣信息时产生的延迟较大和能耗较多问题,提出了基于三维胞元空间的MA双向并行(3D-BPMA)路由算法.3D-BPMA将MA与传统的客户/服务器(c/S)模式相结合,在胞元内利用C/S模式搜集信息,在单层胞元系统和路由器与路由器之间采用MA双向并行的策略进行传输.仿真结果表明:3D-BPMA与LCF,DSG-MIP算法相比减少了平均响应时间和网络平均能耗,提高了MA发送率.     

Distributed wireless power transfer in sensor networks with multiple Mobile Chargers

We investigate the problem of efficient wireless power transfer in wireless sensor networks. In our approach, special mobile entities (called the Mobile Chargers) traverse the network and wirelessly replenish the energy of sensor nodes. In contrast to most current approaches, we envision methods that are distributed and use limited network information. We propose four new protocols for efficient charging, addressing key issues which we identify, most notably (i) what are good coordination procedures for the Mobile Chargers and (ii) what are good trajectories for the Mobile Chargers. Two of our protocols (DC, DCLK) perform distributed, limited network knowledge coordination and charging, while two others (CC, CCGK) perform centralized, global network knowledge coordination and charging. As detailed simulations demonstrate, one of our distributed protocols outperforms a known state of the art method, while its performance gets quite close to the performance of the powerful centralized global knowledge method.     

Input-to-state learning of recurrent neural networks with delay and disturbance

This article deals with the issue of input-to-state stabilization for recurrent neural networks with delay and external disturbance. The goal is to design a suitable weight-learning law to make the considered network input-to-state stable with a predefined -gain. Based on the solution of linear matrix inequalities, two schemes for the desired learning law are presented via using decay-rate-dependent and decay-rate-independent Lyapunov functionals, respectively. It is shown that, in the absence of external disturbance, the proposed learning law also guarantees the exponential stability of the network. To illustrate the applicability of the present weight-learning law, two numerical examples with simulations are given.     

LPPTE: A lightweight privacy-preserving trust evaluation scheme for facilitating distributed data fusion in cooperative vehicular safety applications

Vehicular networks have tremendous potential to improve road safety, traffic efficiency, and driving comfort, where cooperative vehicular safety applications are a significant branch. In cooperative vehicular safety applications, through the distributed data fusion for large amounts of data from multiple nearby vehicles, each vehicle can intelligently perceive the surrounding conditions beyond the capability of its own onboard sensors. Trust evaluation and privacy preservation are two primary concerns for facilitating the distributed data fusion in cooperative vehicular safety applications. They have conflicting requirements and a good balance between them is urgently needed. Meanwhile, the computation, communication, and storage overheads will all influence the applicability of a candidate scheme. In this paper, we propose a Lightweight Privacy-Preserving Trust Evaluation (LPPTE) scheme which can primely balance the trust evaluation and privacy preservation with low overheads for facilitating the distributed data fusion in cooperative vehicular safety applications. Furthermore, we provide exhaustive theoretical analysis and simulation evaluation for the LPPTE scheme, and the results demonstrate that the LPPTE scheme can obviously improve the accuracy of fusion results and is significantly superior to the state-of-the-art schemes in multiple aspects.     

Style-Controllable Speech-Driven Gesture Synthesis Using Normalising Flows

Automatic synthesis of realistic gestures promises to transform the fields of animation, avatars and communicative agents. In off-line applications, novel tools can alter the role of an animator to that of a director, who provides only high-level input for the desired animation; a learned network then translates these instructions into an appropriate sequence of body poses. In interactive scenarios, systems for generating natural animations on the fly are key to achieving believable and relatable characters. In this paper we address some of the core issues towards these ends. By adapting a deep learning-based motion synthesis method called MoGlow, we propose a new generative model for generating state-of-the-art realistic speech-driven gesticulation. Owing to the probabilistic nature of the approach, our model can produce a battery of different, yet plausible, gestures given the same input speech signal. Just like humans, this gives a rich natural variation of motion. We additionally demonstrate the ability to exert directorial control over the output style, such as gesture level, speed, symmetry and spacial extent. Such control can be leveraged to convey a desired character personality or mood. We achieve all this without any manual annotation of the data. User studies evaluating upper-body gesticulation confirm that the generated motions are natural and well match the input speech. Our method scores above all prior systems and baselines on these measures, and comes close to the ratings of the original recorded motions. We furthermore find that we can accurately control gesticulation styles without unnecessarily compromising perceived naturalness. Finally, we also demonstrate an application of the same method to full-body gesticulation, including the synthesis of stepping motion and stance.     

Distributed privacy protection strategy for MEC enhanced wireless body area networks

With the rapid development and widespread application of Wireless Body Area Networks (WBANs), the traditional centralized system architecture cannot handle the massive data generated by the edge devices. Meanwhile, in order to ensure the security of physiological privacy data and the identity privacy of patients, this paper presents a privacy protection strategy for Mobile Edge Computing(MEC) enhanced WBANs, which leverages the blockchain-based decentralized MEC paradigm to support efficient transmission of privacy information with low latency, high reliability within a high-demand data security scenario. On this basis, the Merkle tree optimization model is designed to authenticate nodes and to verify the source of physiological data. Furthermore, a hybrid signature algorithm is devised to guarantee the node anonymity with unforgeability, data integrity and reduced delay. The security performance analysis and simulation results show that our proposed strategy not only reduces the delay, but also secures the privacy and transmission of sensitive WBANs data.     

Intuitive Facial Animation Editing Based On A Generative RNN Framework

For the last decades, the concern of producing convincing facial animation has garnered great interest, that has only been accelerating with the recent explosion of 3D content in both entertainment and professional activities. The use of motion capture and retargeting has arguably become the dominant solution to address this demand. Yet, despite high level of quality and automation performance-based animation pipelines still require manual cleaning and editing to refine raw results, which is a time- and skill-demanding process. In this paper, we look to leverage machine learning to make facial animation editing faster and more accessible to non-experts. Inspired by recent image inpainting methods, we design a generative recurrent neural network that generates realistic motion into designated segments of an existing facial animation, optionally following user-provided guiding constraints. Our system handles different supervised or unsupervised editing scenarios such as motion filling during occlusions, expression corrections, semantic content modifications, and noise filtering. We demonstrate the usability of our system on several animation editing use cases.     

Learning bipartite Bayesian networks under monotonicity restrictions

ABSTRACT

Learning parameters of a probabilistic model is a necessary step in machine learning tasks. We present a method to improve learning from small datasets by using monotonicity conditions. Monotonicity simplifies the learning and it is often required by users. We present an algorithm for Bayesian Networks parameter learning. The algorithm and monotonicity conditions are described, and it is shown that with the monotonicity conditions we can better fit underlying data. Our algorithm is tested on artificial and empiric datasets. We use different methods satisfying monotonicity conditions: the proposed gradient descent, isotonic regression EM, and non-linear optimization. We also provide results of unrestricted EM and gradient descent methods. Learned models are compared with respect to their ability to fit data in terms of log-likelihood and their fit of parameters of the generating model. Our proposed method outperforms other methods for small sets, and provides better or comparable results for larger sets.