Machine learning of XY model on a spherical Fibonacci lattice

We study the XY model on a spherical surface by using Monte Carlo simulations and machine learning methods. Instead of a traditional latitude-longitude lattice, we consider a much more homogeneous spherical lattice, the Fibonacci lattice. After obtaining the equilibrium spin configurations by classical Monte Carlo annealing, we propose a graph-convolutional-network based method to recognize different phases, and successfully predict the phase transition temperature. We also apply the density-based spatial clustering of applications with noise, a powerful machine learning algorithm, to unravel the merging path of two vortices with different topological charges on the sphere. Our results provide reliable predictions for future space-based experiments on ultracold atomic gases confined on spherical lattice in the microgravity environment.

Discrete Boltzmann Modeling of Plasma Shock Wave

Plasma shock waves widely exist and play an important role in high-energy-density environment, especially in the inertial confinement fusion. Due to the large gradient of macroscopic physical quantities and the coupled thermal, electrical, magnetic and optical phenomena, there exist not only hydrodynamic non-equilibrium (HNE) effects, but also strong thermodynamic non-equilibrium (TNE) effects around the wavefront. In this work, a two-dimensional single-fluid discrete Boltzmann model is proposed to investigate the physical structure of ion shock. The electron is assumed inertialess and always in thermodynamic equilibrium. The Rankine-Hugoniot relations for single fluid theory of plasma shock wave is derived. It is found that the physical structure of shock wave in plasma is significantly different from that in normal fluid and somewhat similar to that of detonation wave from the sense that a peak appears in the front. The non-equilibrium effects around the shock front become stronger with increasing Mach number. The charge of electricity deviates oppositely from neutrality in upstream and downstream of the shock wave. The large inertia of the ions causes them to lag behind, so the wave front charge is negative and the wave rear charge is positive. The variations of HNE and TNE with Mach number are numerically investigated. The characteristics of TNE can be used to distinguish plasma shock wave from detonation wave.

Evolutionary Ensemble Learning for Multivariate Time Series Prediction

Multivariate time series (MTS) prediction plays a key role in many fields such as finance, energy and transport, where each individual time series corresponds to the data collected from a certain data source, so-called channel. A typical pipeline of building an MTS prediction model (PM) consists of selecting a subset of channels among all available ones, extracting features from the selected channels, and building a PM based on the extracted features, where each component involves certain optimization tasks, i.e., selection of channels, feature extraction (FE) methods, and PMs as well as configuration of the selected FE method and PM. Accordingly, pursuing the best prediction performance corresponds to optimizing the pipeline by solving all of its involved optimization problems. This is a non-trivial task due to the vastness of the solution space. Different from most of the existing works which target at optimizing certain components of the pipeline, we propose a novel evolutionary ensemble learning framework to optimize the entire pipeline in a holistic manner. In this framework, a specific pipeline is encoded as a candidate solution and a multi-objective evolutionary algorithm is applied under different population sizes to produce multiple Pareto optimal sets (POSs). Finally, selective ensemble learning is designed to choose the optimal subset of solutions from the POSs and combine them to yield final prediction by using greedy sequential selection and least square methods. We implement the proposed framework and evaluate our implementation on two real-world applications, i.e., electricity consumption prediction and air quality prediction. The performance comparison with state-of-the-art techniques demonstrates the superiority of the proposed approach.

Multi-Objective Optimization of Electric Vehicle Charging Schedule with Time of Use Tariff

The increased uptake of electric vehicles (EVs) leads to increased demand for electricity, and sometime pressure to power grids. Uncoordinated charging of EVs may result in putting pressure on distribution networks, and often some form of optimisation is required in the charging process. Optimal coordinated charging is a multi-objective optimisation problem in nature, with objective functions such as minimum price charging and minimum disruptions to the grid. In this manuscript, we propose a general multi-objective EV charging/discharging schedule (MOEVCS) framework, where the time of use (TOU) tariff is designed according to the load request at each time stamp. To obtain the optimal scheduling scheme and balance the competing benefits from different stakeholders, such as EV owners, EV charging stations (EVCS), and the grid operator, we design three conflicting objective functions including EV owner cost, EVCS profit, and the network impact. Moreover, we create four application scenarios with different charging request distributions over the investigated periods. We use a constraint multi-objective evolutionary algorithm (MOEA) to solve the problem. Our results demonstrate the effectiveness of MOEVCS in making a balance between three conflicting objectives.

Extended Tactile Perception: Vibration Sensing through Tools and Grasped Objects

Humans display the remarkable ability to sense the world through tools and other held objects. For example, we are able to pinpoint impact locations on a held rod and tell apart different textures using a rigid probe. In this work, we consider how we can enable robots to have a similar capacity, i.e., to embody tools and extend perception using standard grasped objects. We propose that vibro-tactile sensing using dynamic tactile sensors on the robot fingers, along with machine learning models, enables robots to decipher contact information that is transmitted as vibrations along rigid objects. This paper reports on extensive experiments using the BioTac micro-vibration sensor and a new event dynamic sensor, the NUSkin, capable of multi-taxel sensing at 4~kHz. We demonstrate that fine localization on a held rod is possible using our approach (with errors less than 1 cm on a 20 cm rod). Next, we show that vibro-tactile perception can lead to reasonable grasp stability prediction during object handover, and accurate food identification using a standard fork. We find that multi-taxel vibro-tactile sensing at sufficiently high sampling rate (above 2 kHz) led to the best performance across the various tasks and objects. Taken together, our results provides both evidence and guidelines for using vibro-tactile perception to extend tactile perception, which we believe will lead to enhanced competency with tools and better physical human-robot-interaction.

Small-Angle X-Ray Scattering Signatures of Conformational Heterogeneity and Homogeneity of Disordered Protein Ensembles

Physically, disordered ensembles of non-homopolymeric polypeptides are expected to be heterogeneous; i.e., they should differ from those homogeneous ensembles of homopolymers that harbor an essentially unique relationship between average values of end-to-end distance $R_{rm EE}$ and radius of gyration $R_{rm g}$. It was posited recently, however, that small-angle X-ray scattering (SAXS) data on conformational dimensions of disordered proteins can be rationalized almost exclusively by homopolymer ensembles. Assessing this perspective, chain-model simulations are used to evaluate the discriminatory power of SAXS-determined molecular form factors (MFFs) with regard to homogeneous versus heterogeneous ensembles. The general approach adopted here is not bound by any assumption about ensemble encodability, in that the postulated heterogeneous ensembles we evaluated are not restricted to those entailed by simple interaction schemes. Our analysis of MFFs for certain heterogeneous ensembles with more narrowly distributed $R_{rm EE}$ and $R_{rm g}$ indicates that while they deviates from MFFs of homogeneous ensembles, the differences can be rather small. Remarkably, some heterogeneous ensembles with asphericity and $R_{rm EE}$ drastically different from those of homogeneous ensembles can nonetheless exhibit practically identical MFFs, demonstrating that SAXS MFFs do not afford unique characterizations of basic properties of conformational ensembles in general. In other words, the ensemble to MFF mapping is practically many-to-one and likely non-smooth. Heteropolymeric variations of the $R_{rm EE}$--$R_{rm g}$ relationship were further showcased using an analytical perturbation theory developed here for flexible heteropolymers. Ramifications of our findings for interpretation of experimental data are discussed.

Near-Optimal Detection for Both Data and Sneak-Path Interference in Resistive Memories with Random Cell Selector Failures

Resistive random-access memory is one of the most promising candidates for the next generation of non-volatile memory technology. However, its crossbar structure causes severe sneak-path interference, which also leads to strong inter-cell correlation. Recent works have mainly focused on sub-optimal data detection schemes by ignoring inter-cell correlation and treating sneak-path interference as independent noise. We propose a near-optimal data detection scheme that can approach the performance bound of the optimal detection scheme. Our detection scheme leverages a joint data and sneak-path interference recovery and can use all inter-cell correlations. The scheme is appropriate for data detection of large memory arrays with only linear operation complexity.

Unsupervised Learning Facial Parameter Regressor for Action Unit Intensity Estimation via Differentiable Renderer

Facial action unit (AU) intensity is an index to describe all visually discernible facial movements. Most existing methods learn intensity estimator with limited AU data, while they lack generalization ability out of the dataset. In this paper, we present a framework to predict the facial parameters (including identity parameters and AU parameters) based on a bone-driven face model (BDFM) under different views. The proposed framework consists of a feature extractor, a generator, and a facial parameter regressor. The regressor can fit the physical meaning parameters of the BDFM from a single face image with the help of the generator, which maps the facial parameters to the game-face images as a differentiable renderer. Besides, identity loss, loopback loss, and adversarial loss can improve the regressive results. Quantitative evaluations are performed on two public databases BP4D and DISFA, which demonstrates that the proposed method can achieve comparable or better performance than the state-of-the-art methods. Whats more, the qualitative results also demonstrate the validity of our method in the wild.

Neutral Face Game Character Auto-Creation via PokerFace-GAN

Game character customization is one of the core features of many recent Role-Playing Games (RPGs), where players can edit the appearance of their in-game characters with their preferences. This paper studies the problem of automatically creating in-game characters with a single photo. In recent literature on this topic, neural networks are introduced to make game engine differentiable and the self-supervised learning is used to predict facial customization parameters. However, in previous methods, the expression parameters and facial identity parameters are highly coupled with each other, making it difficult to model the intrinsic facial features of the character. Besides, the neural network based renderer used in previous methods is also difficult to be extended to multi-view rendering cases. In this paper, considering the above problems, we propose a novel method named PokerFace-GAN for neutral face game character auto-creation. We first build a differentiable character renderer which is more flexible than the previous methods in multi-view rendering cases. We then take advantage of the adversarial training to effectively disentangle the expression parameters from the identity parameters and thus generate player-preferred neutral face (expression-less) characters. Since all components of our method are differentiable, our method can be easily trained under a multi-task self-supervised learning paradigm. Experiment results show that our method can generate vivid neutral face game characters that are highly similar to the input photos. The effectiveness of our method is verified by comparison results and ablation studies.

Unsupervised Facial Action Unit Intensity Estimation via Differentiable Optimization

The automatic intensity estimation of facial action units (AUs) from a single image plays a vital role in facial analysis systems. One big challenge for data-driven AU intensity estimation is the lack of sufficient AU label data. Due to the fact that AU annotation requires strong domain expertise, it is expensive to construct an extensive database to learn deep models. The limited number of labeled AUs as well as identity differences and pose variations further increases the estimation difficulties. Considering all these difficulties, we propose an unsupervised framework GE-Net for facial AU intensity estimation from a single image, without requiring any annotated AU data. Our framework performs differentiable optimization, which iteratively updates the facial parameters (i.e., head pose, AU parameters and identity parameters) to match the input image. GE-Net consists of two modules: a generator and a feature extractor. The generator learns to render a face image from a set of facial parameters in a differentiable way, and the feature extractor extracts deep features for measuring the similarity of the rendered image and input real image. After the two modules are trained and fixed, the framework searches optimal facial parameters by minimizing the differences of the extracted features between the rendered image and the input image. Experimental results demonstrate that our method can achieve state-of-the-art results compared with existing methods.