Search

The electric grid is a key enabling infrastructure for the ambitious transition towards carbon neutrality as we grapple with climate change. With deepening penetration of renewable energy resources and electrified transportation, the reliable and secure operation of the electric grid becomes increasingly challenging. In this paper, we present PSML, a first-of-its-kind open-access multi-scale time-series dataset, to aid in the development of data-driven machine learning (ML) based approaches towards reliable operation of future electric grids. The dataset is generated through a novel transmission + distribution (T+D) co-simulation designed to capture the increasingly important interactions and uncertainties of the grid dynamics, containing electric load, renewable generation, weather, voltage and current measurements over multiple spatio-temporal scales. Using PSML, we provide state-of-the-art ML baselines on three challenging use cases of critical importance to achieve: (i) early detection, accurate classification and localization of dynamic disturbance events; (ii) robust hierarchical forecasting of load and renewable energy with the presence of uncertainties and extreme events; and (iii) realistic synthetic generation of physical-law-constrained measurement time series. We envision that this dataset will enable advances for ML in dynamic systems, while simultaneously allowing ML researchers to contribute towards carbon-neutral electricity and mobility.

The explosive increase of multimodal data makes a great demand in many cross-modal applications that follow the strict prior related assumption. Thus researchers study the definition of cross-modal correlation category and construct various classification systems and predictive models. However, those systems pay more attention to the fine-grained relevant types of cross-modal correlation, ignoring lots of implicit relevant data which are often divided into irrelevant types. What's worse is that none of previous predictive models manifest the essence of cross-modal correlation according to their definition at the modeling stage. In this paper, we present a comprehensive analysis of the image-text correlation and redefine a new classification system based on implicit association and explicit alignment. To predict the type of image-text correlation, we propose the Association and Alignment Network according to our proposed definition (namely AnANet) which implicitly represents the global discrepancy and commonality between image and text and explicitly captures the cross-modal local relevance. The experimental results on our constructed new image-text correlation dataset show the effectiveness of our model.

Accurate estimation of the tire slip ratio is critical for vehicle safety, as it is necessary for vehicle control purposes. In this paper, an intelligent tire system is presented to develop a novel slip ratio estimation model using machine learning algorithms. The accelerations, generated by a triaxial accelerometer installed onto the inner liner of the tire, are varied when the tire rotates to update the contact patch. Meanwhile, the slip ratio reference value can be measured by the MTS Flat-Trac tire test platform. Then, by analyzing the variation between the accelerations and slip ratio, highly useful features are discovered, which are especially promising for assessing vertical acceleration. For these features, machine learning (ML) algorithms are trained to build the slip ratio estimation model, in which the ML algorithms include artificial neural networks (ANNs), gradient boosting machines (GBMs), random forests (RFs), and support vector machines (SVMs). Finally, the estimated NRMS errors are evaluated using 10-fold cross-validation (CV). The proposed estimation model is able to estimate the slip ratio continuously and stably using only the acceleration from the intelligent tire system, and the estimated slip ratio range can reach 30%. The estimation results have high robustness to vehicle velocity and load, where the best NRMS errors can reach 4.88%. In summary, the present study with the fusion of an intelligent tire system and machine learning paves the way for the accurate estimation of the tire slip ratio under different driving conditions, which create new opportunities for autonomous vehicles, intelligent tires, and tire slip ratio estimation., Comment: 12 pages, 25 figures, 2 tables

Machine learning potential enables molecular dynamics simulations of systems beyond the capability of classical force fields. The traditional approach to develop structural sets for training machine learning potential typically generate a great number of redundant configurations, which will result in unnecessary computational costs. This work investigates the possibility of reducing redundancy in an initial data set containing 6183 configurations for a Li-Si machine learning potential. Starting from the initial data set, we constructed a series of subsets ranging from 25 to 1500 configurations by combining a structural similarity analysis algorithm and the farthest point sampling method. Results show that the machine learning potential trained from a data set containing 400 configurations can achieve an accuracy comparable to the one developed from the initial data set of 6183 configurations in describing potential energies, atomic forces, and structural properties of Li-Si systems. In addition, the redundancy reducing approach also demonstrates advantages over the classic stochastic method for constructing a concise training data set for Li-Si systems., Comment: 38 pages, 10 figures

The recent release of large-scale healthcare datasets has greatly propelled the research of data-driven deep learning models for healthcare applications. However, due to the nature of such deep black-boxed models, concerns about interpretability, fairness, and biases in healthcare scenarios where human lives are at stake call for a careful and thorough examinations of both datasets and models. In this work, we focus on MIMIC-IV (Medical Information Mart for Intensive Care, version IV), the largest publicly available healthcare dataset, and conduct comprehensive analyses of dataset representation bias as well as interpretability and prediction fairness of deep learning models for in-hospital mortality prediction. In terms of interpretabilty, we observe that (1) the best performing interpretability method successfully identifies critical features for mortality prediction on various prediction models; (2) demographic features are important for prediction. In terms of fairness, we observe that (1) there exists disparate treatment in prescribing mechanical ventilation among patient groups across ethnicity, gender and age; (2) all of the studied mortality predictors are generally fair while the IMV-LSTM (Interpretable Multi-Variable Long Short-Term Memory) model provides the most accurate and unbiased predictions across all protected groups. We further draw concrete connections between interpretability methods and fairness metrics by showing how feature importance from interpretability methods can be beneficial in quantifying potential disparities in mortality predictors.

Perturbation theory is a kind of estimation method based on theorem of Taylor expansion, and is useful to investigate electromagnetic solutions of small changes. By considering a sharp boundary as a limit of smoothed systems, previous study has solved the problem when applying standard perturbation theory to Maxwell's equations for small shifts in isotropic dielectric interfaces. However, when dealing with anisotropic materials, an approximation is conducted and leads to an unsatisfactory error. Here we develop a modified perturbation theory for small shifts in anisotropically dielectric interfaces. By using optimized smoothing function for each component of permittivity, we obtain a method to calculate the intrinsic frequency shifts of anisotropic permittivity field when boundaries shift, without approximation. Our method shows accurate results when calculating eigenfrequency's shifts in strong-anisotropy materials, and can be widely used for small shifts in anisotropically dielectric interfaces.

Tire slip angle is a vital parameter in tire/vehicle dynamics and control. This paper proposes an accurate estimation method by the fusion of intelligent tire technology and machine-learning techniques. The intelligent tire is equipped by MEMS accelerometers attached to its inner liner. First, we describe the intelligent tire system along with the implemented testing apparatus. Second, experimental results under different loading and velocity conditions are provided. Then, we show the procedure of data processing, which will be used for training three different machine learning techniques to estimate tire slip angles. The results show that the machine learning techniques, especially in frequency domain, can accurately estimate tire slip angles up to 10 degrees. More importantly, with the accurate tire slip angle estimation, all other states and parameters can be easily and precisely obtained, which is significant to vehicle advanced control, and thus this study has a high potential to obviously improve the vehicle safety especially in extreme maneuvers.

The concept of intelligent tires has drawn attention of researchers in the areas of autonomous driving, advanced vehicle control, and artificial intelligence. The focus of this paper is on intelligent tires and the application of machine learning techniques to tire force estimation. We present an intelligent tire system with a tri-axial acceleration sensor, which is installed onto the inner liner of the tire, and Neural Network techniques for real-time processing of the sensor data. The accelerometer is capable of measuring the acceleration in x,y, and z directions. When the accelerometer enters the tire contact patch, it starts generating signals until it fully leaves it. Simultaneously, by using MTS Flat-Trac test platform, tire actual forces are measured. Signals generated by the accelerometer and MTS Flat-Trac testing system are used for training three different machine learning techniques with the purpose of online prediction of tire forces. It is shown that the developed intelligent tire in conjunction with machine learning is effective in accurate prediction of tire forces under different driving conditions. The results presented in this work will open a new avenue of research in the area of intelligent tires, vehicle systems, and tire force estimation., Comment: 10 pages,20 figures, Accepted for publication at IEEE Transactions on Intelligent Transportation Systems, the link of this work is https://ieeexplore.ieee.org/document/9284471

Deep Neural Networks, despite their great success in diverse domains, are provably sensitive to small perturbations on correctly classified examples and lead to erroneous predictions. Recently, it was proposed that this behavior can be combatted by optimizing the worst case loss function over all possible substitutions of training examples. However, this can be prone to weighing unlikely substitutions higher, limiting the accuracy gain. In this paper, we study adversarial robustness through randomized perturbations, which has two immediate advantages: (1) by ensuring that substitution likelihood is weighted by the proximity to the original word, we circumvent optimizing the worst case guarantees and achieve performance gains; and (2) the calibrated randomness imparts differentially-private model training, which additionally improves robustness against adversarial attacks on the model outputs. Our approach uses a novel density-based mechanism based on truncated Gumbel noise, which ensures training on substitutions of both rare and dense words in the vocabulary while maintaining semantic similarity for model robustness.

Understanding the dynamic behavior of tires and their interactions with road plays an important role in designing integrated vehicle control strategies. Accordingly, having access to reliable information about the tire-road interactions through tire embedded sensors is very demanding for developing enhanced vehicle control systems. Thus, the main objectives of the present research work are i. to analyze data from an experimental accelerometer-based intelligent tire acquired over a wide range of maneuvers, with different vertical loads, velocities, and high slip angles; and ii. to develop a lateral force predictor based on a machine learning tool, more specifically the Gaussian Process Regression (GPR) technique. It is delineated that the proposed intelligent tire system can provide reliable information about the tire-road interactions even in the case of high slip angles. Besides, the lateral forces model based on GPR can predict forces with acceptable accuracy and provide level of uncertainties that can be very useful for designing vehicle control strategies.

In this proposal, a cost-effective energy harvesting and management system have been proposed. The regular power keeps around 200 Watt while the peak power can reach 300 Watt. The cost of this system satisfies the requirements and budget for residents in the rural area and live off-grid. It could be a potential solution to the global energy crisis, particularly the billions of people living in severe energy poverty. Also, it is an important renewable alternative to conventional fossil fuel electricity generation not only the cost of manufacturing is low and high efficiency, but also it is safe and eco-friendly., Comment: Entered the Pacific-Asia regional session of IEEE "Empower A Billion Lives" Contest in 2018 PEAC

Automatically verifying rumorous information has become an important and challenging task in natural language processing and social media analytics. Previous studies reveal that people's stances towards rumorous messages can provide indicative clues for identifying the veracity of rumors, and thus determining the stances of public reactions is a crucial preceding step for rumor veracity prediction. In this paper, we propose a hierarchical multi-task learning framework for jointly predicting rumor stance and veracity on Twitter, which consists of two components. The bottom component of our framework classifies the stances of tweets in a conversation discussing a rumor via modeling the structural property based on a novel graph convolutional network. The top component predicts the rumor veracity by exploiting the temporal dynamics of stance evolution. Experimental results on two benchmark datasets show that our method outperforms previous methods in both rumor stance classification and veracity prediction., Comment: EMNLP-IJCNLP 2019

We present the VASPKIT, a command-line program that aims at providing a powerful and user-friendly interface to perform high-throughput analysis of a variety of material properties from the raw data produced by the VASP code. It consists of mainly the pre- and post-processing modules. The former module is designed to prepare and manipulate input files such as the necessary input files generation, symmetry analysis, supercell transformation, k-path generation for a given crystal structure. The latter module is designed to extract and analyze the raw data about elastic mechanics, electronic structure, charge density, electrostatic potential, linear optical coefficients, wave function plots in real space, and etc. This program can run conveniently in either interactive user interface or command line mode. The command-line options allow the user to perform high-throughput calculations together with bash scripts. This article gives an overview of the program structure and presents illustrative examples for some of its usages. The program can run on Linux, MacOS, and Windows platforms. The executable versions of VASPKIT and the related examples, together with the tutorials, are available in its official website vaspkit.com., Comment: 33 pages, 19 figures

On-silicon inductors using a bulk 0.18 {\mu}m CMOS process have been designed. By shunting different metal layers in parallel, inductor values and quality factors were simulated. Selected inductors were then employed in two open-loop buck converters for comparison: the first used an off-chip discrete diode, and the second used an on-chip active diode. All inductors and converters were sent for fabrication. The fabricated inductors were then measured to have values more than 250 nH over a wide range of frequency, validating the simulation results. The buck converters were switched at 30 MHz with a fixed duty ratio of 0.5, to generate an output voltage of 1.2 V from an input voltage of 2.4 V. The peak efficiency was measured to be 69.1% for a light load current of 12.9 mA., Comment: Submitted to IEEE APCCAS 2019