skip to main content


This content will become publicly available on June 1, 2024

Title: Physics-Informed Deep Learning for Traffic State Estimation: A Survey and the Outlook
For its robust predictive power (compared to pure physics-based models) and sample-efficient training (compared to pure deep learning models), physics-informed deep learning (PIDL), a paradigm hybridizing physics-based models and deep neural networks (DNNs), has been booming in science and engineering fields. One key challenge of applying PIDL to various domains and problems lies in the design of a computational graph that integrates physics and DNNs. In other words, how the physics is encoded into DNNs and how the physics and data components are represented. In this paper, we offer an overview of a variety of architecture designs of PIDL computational graphs and how these structures are customized to traffic state estimation (TSE), a central problem in transportation engineering. When observation data, problem type, and goal vary, we demonstrate potential architectures of PIDL computational graphs and compare these variants using the same real-world dataset.  more » « less
Award ID(s):
2038984
NSF-PAR ID:
10447567
Author(s) / Creator(s):
; ; ;
Date Published:
Journal Name:
Algorithms
Volume:
16
Issue:
6
ISSN:
1999-4893
Page Range / eLocation ID:
305
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Raynal, Ann M. ; Ranney, Kenneth I. (Ed.)
    Most research in technologies for the Deaf community have focused on translation using either video or wearable devices. Sensor-augmented gloves have been reported to yield higher gesture recognition rates than camera-based systems; however, they cannot capture information expressed through head and body movement. Gloves are also intrusive and inhibit users in their pursuit of normal daily life, while cameras can raise concerns over privacy and are ineffective in the dark. In contrast, RF sensors are non-contact, non-invasive and do not reveal private information even if hacked. Although RF sensors are unable to measure facial expressions or hand shapes, which would be required for complete translation, this paper aims to exploit near real-time ASL recognition using RF sensors for the design of smart Deaf spaces. In this way, we hope to enable the Deaf community to benefit from advances in technologies that could generate tangible improvements in their quality of life. More specifically, this paper investigates near real-time implementation of machine learning and deep learning architectures for the purpose of sequential ASL signing recognition. We utilize a 60 GHz RF sensor which transmits a frequency modulation continuous wave (FMWC waveform). RF sensors can acquire a unique source of information that is inaccessible to optical or wearable devices: namely, a visual representation of the kinematic patterns of motion via the micro-Doppler signature. Micro-Doppler refers to frequency modulations that appear about the central Doppler shift, which are caused by rotational or vibrational motions that deviate from principle translational motion. In prior work, we showed that fractal complexity computed from RF data could be used to discriminate signing from daily activities and that RF data could reveal linguistic properties, such as coarticulation. We have also shown that machine learning can be used to discriminate with 99% accuracy the signing of native Deaf ASL users from that of copysigning (or imitation signing) by hearing individuals. Therefore, imitation signing data is not effective for directly training deep models. But, adversarial learning can be used to transform imitation signing to resemble native signing, or, alternatively, physics-aware generative models can be used to synthesize ASL micro-Doppler signatures for training deep neural networks. With such approaches, we have achieved over 90% recognition accuracy of 20 ASL signs. In natural environments, however, near real-time implementations of classification algorithms are required, as well as an ability to process data streams in a continuous and sequential fashion. In this work, we focus on extensions of our prior work towards this aim, and compare the efficacy of various approaches for embedding deep neural networks (DNNs) on platforms such as a Raspberry Pi or Jetson board. We examine methods for optimizing the size and computational complexity of DNNs for embedded micro-Doppler analysis, methods for network compression, and their resulting sequential ASL recognition performance. 
    more » « less
  2. Ruiz, F. ; Dy, J. ; Meent, J.-W. (Ed.)
    Prediction algorithms, such as deep neural networks (DNNs), are used in many domain sciences to directly estimate internal parameters of interest in simulator-based models, especially in settings where the observations include images or complex high-dimensional data. In parallel, modern neural density estimators, such as normalizing flows, are becoming increasingly popular for uncertainty quantification, especially when both parameters and observations are high-dimensional. However, parameter inference is an inverse problem and not a prediction task; thus, an open challenge is to construct conditionally valid and precise confidence regions, with a guaranteed probability of covering the true parameters of the data-generating process, no matter what the (unknown) parameter values are, and without relying on large-sample theory. Many simulator-based inference (SBI) methods are indeed known to produce biased or overly con- fident parameter regions, yielding misleading uncertainty estimates. This paper presents WALDO, a novel method to construct confidence regions with finite-sample conditional validity by leveraging prediction algorithms or posterior estimators that are currently widely adopted in SBI. WALDO reframes the well-known Wald test statistic, and uses a computationally efficient regression-based machinery for classical Neyman inversion of hypothesis tests. We apply our method to a recent high-energy physics problem, where prediction with DNNs has previously led to estimates with prediction bias. We also illustrate how our approach can correct overly confident posterior regions computed with normalizing flows. 
    more » « less
  3. Topological data analysis (TDA) is a branch of computational mathematics, bridging algebraic topology and data science, that provides compact, noise-robust representations of complex structures. Deep neural networks (DNNs) learn millions of parameters associated with a series of transformations defined by the model architecture resulting in high-dimensional, difficult to interpret internal representations of input data. As DNNs become more ubiquitous across multiple sectors of our society, there is increasing recognition that mathematical methods are needed to aid analysts, researchers, and practitioners in understanding and interpreting how these models' internal representations relate to the final classification. In this paper we apply cutting edge techniques from TDA with the goal of gaining insight towards interpretability of convolutional neural networks used for image classification. We use two common TDA approaches to explore several methods for modeling hidden layer activations as high-dimensional point clouds, and provide experimental evidence that these point clouds capture valuable structural information about the model's process. First, we demonstrate that a distance metric based on persistent homology can be used to quantify meaningful differences between layers and discuss these distances in the broader context of existing representational similarity metrics for neural network interpretability. Second, we show that a mapper graph can provide semantic insight as to how these models organize hierarchical class knowledge at each layer. These observations demonstrate that TDA is a useful tool to help deep learning practitioners unlock the hidden structures of their models. 
    more » « less
  4. A novel machine learning model is presented in this work to obtain the complex high-dimensional deformation of Multi-Walled Carbon Nanotubes (MWCNTs) containing millions of atoms. To obtain the deformation of these high dimensional systems, existing models like Atomistic, Continuum or Atomistic-Continuum models are very accurate and reliable but are computationally prohibitive for these large systems. This high computational requirement slows down the exploration of physics of these materials. To alleviate this problem, we developed a machine learning model that contains a) a novel dimensionality reduction technique which is combined with b) deep neural network based learning in the reduced dimension. The proposed non-linear dimensionality reduction technique serves as an extension of functional principal component analysis. This extension ensures that the geometric constraints of deformation are satisfied exactly and hence we termed this extension as constrained functional principal component analysis. The novelty of this technique is its ability to design a function space where all the functions satisfy the constraints exactly, not approximately. The efficient dimensionality reduction along with the exact satisfaction of the constraint bolster the deep neural network to achieve remarkable accuracy. The proposed model predicts the deformation of MWCNTs very accurately when compared with the deformation obtained through atomistic-physics-based model. To simulate the complex high-dimensional deformation the atomistic-physics-based models takes weeks high performance computing facility, whereas the proposed machine learning model can predict the deformation in seconds. This technique also extracts the universally dominant pattern of deformation in an unsupervised manner. These patterns are comprehensible to us and provides us a better explanation on the working of the model. The comprehensibility of the dominant modes of deformation yields the interpretability of the model.

     
    more » « less
  5. - (Ed.)
    Shape sensing is an emerging technique for the reconstruction of deformed shapes using data from a discrete network of strain sensors. The prominence is due to its suitability in promising applications such as structural health monitoring in multiple engineering fields and shape capturing in the medical field. In this work, a physics-informed deep learning model, named SenseNet, was developed for shape sensing applications. Unlike existing neural network approaches for shape sensing, SenseNet incorporates the knowledge of the physics of the problem, so its performance does not rely on the choices of the training data. Compared with numerical physics-based approaches, SenseNet is a mesh-free method, and therefore it offers convenience to problems with complex geometries. SenseNet is composed of two parts: a neural network to predict displacements at the given input coordinates, and a physics part to compute the loss using a function incorporated with physics information. The prior knowledge considered in the loss function includes the boundary conditions and physics relations such as the strain–displacement relation, material constitutive equation, and the governing equation obtained from the law of balance of linear momentum.SenseNet was validated with finite-element solutions for cases with nonlinear displacement fields and stress fields using bending and fixed tension tests, respectively, in both two and three dimensions. A study of the sensor density effects illustrated the fact that the accuracy of the model can be improved using a larger amount of strain data. Because general three dimensional governing equations are incorporated in the model, it was found that SenseNet is capable of reconstructing deformations in volumes with reasonable accuracy using just the surface strain data. Hence, unlike most existing models, SenseNet is not specialized for certain types of elements, and can be extended universally for even thick-body applications. 
    more » « less