Satish Bukkapatnam

Yuhao Zhong, Anirban Bhattacharya, Satish Bukkapatnam

We propose EBLIME to explain black-box machine learning models and obtain the distribution of feature importance using Bayesian ridge regression models. We provide mathematical expressions of the Bayesian framework and theoretical outcomes including the significance of ridge parameter. Case studies were conducted on benchmark datasets and a real-world industrial application of locating internal defects in manufactured products. Compared to the state-of-the-art methods, EBLIME yields more intuitive and accurate results, with better uncertainty quantification in terms of deriving the posterior distribution, credible intervals, and rankings of the feature importance.

Akash Tiwari, Satish Bukkapatnam

Changes in real-world dynamic processes are often described in terms of differences in energies $\textbf{E}(\underlineα)$ of a set of spectral-bands $\underlineα$. Given continuous spectra of two classes $A$ and $B$, or in general, two stochastic processes $S^{(A)}(f)$ and $S^{(B)}(f)$, $f \in \mathbb{R}^+$, we address the ubiquitous problem of identifying a subset of intervals of $f$ called spectral-bands $\underlineα \subset \mathbb{R}^+$ such that the energies $\textbf{E}(\underlineα)$ of these bands can optimally discriminate between the two classes. We introduce EGO-MDA, an unsupervised method to identify optimal spectral-bands $\underlineα^*$ for given samples of spectra from two classes. EGO-MDA employs a statistical approach that iteratively minimizes an adjusted multinomial log-likelihood (deviance) criterion $\mathcal{D}(\underlineα,\mathcal{M})$. Here, Mixture Discriminant Analysis (MDA) aims to derive MLE of two GMM distribution parameters, i.e., $\mathcal{M}^* = \underset{\mathcal{M}}{\rm argmin}~\mathcal{D}(\underlineα, \mathcal{M})$ and identify a classifier that optimally discriminates between two classes for a given spectral representation. The Efficient Global Optimization (EGO) finds the spectral-bands $\underlineα^* = \underset{\underlineα}{\rm argmin}~\mathcal{D}(\underlineα,\mathcal{M})$ for given GMM parameters $\mathcal{M}$. For pathological cases of low separation between mixtures and model misspecification, we discuss the effect of the sample size and the number of iterations on the estimates of parameters $\mathcal{M}$ and therefore the classifier performance. A case study on a synthetic data set is provided. In an engineering application of optimal spectral-banding for anomaly tracking, EGO-MDA achieved at least 70% improvement in the median deviance relative to other methods tested.

Abhishek Hanchate, Himanshu Balhara, Vishal S. Chindepalli et al.

We present HiRA-Pro, a novel procedure to align, at high spatio-temporal resolutions, multimodal signals from real-world processes and systems that exhibit diverse transient, nonlinear stochastic dynamics, such as manufacturing machines. It is based on discerning and synchronizing the process signatures of salient kinematic and dynamic events in these disparate signals. HiRA-Pro addresses the challenge of aligning data with sub-millisecond phenomena, where traditional timestamp, external trigger, or clock-based alignment methods fall short. The effectiveness of HiRA-Pro is demonstrated in a smart manufacturing context, where it aligns data from 13+ channels acquired during 3D-printing and milling operations on an Optomec-LENS MTS 500 hybrid machine. The aligned data is then voxelized to generate 0.25 second aligned data chunks that correspond to physical voxels on the produced part. The superiority of HiRA-Pro is further showcased through case studies in additive manufacturing, demonstrating improved machine learning-based predictive performance due to precise multimodal data alignment. Specifically, testing classification accuracies improved by almost 35% with the application of HiRA-Pro, even with limited data, allowing for precise localization of artifacts. The paper also provides a comprehensive discussion on the proposed method, its applications, and comparative qualitative analysis with a few other alignment methods. HiRA-Pro achieves temporal-spatial resolutions of 10-1000 us and 100 um in order to generate datasets that register with physical voxels on the 3D-printed and milled part. These resolutions are at least an order of magnitude finer than the existing alignment methods that employ individual timestamps, statistical correlations, or common clocks, which achieve precision of hundreds of milliseconds.

Antonios Alexos, Junze Liu, Akash Tiwari et al.

In Inertial Confinement Fusion (ICF) process, roughly a 2mm spherical shell made of high density carbon is used as target for laser beams, which compress and heat it to energy levels needed for high fusion yield. These shells are polished meticulously to meet the standards for a fusion shot. However, the polishing of these shells involves multiple stages, with each stage taking several hours. To make sure that the polishing process is advancing in the right direction, we are able to measure the shell surface roughness. This measurement, however, is very labor-intensive, time-consuming, and requires a human operator. We propose to use machine learning models that can predict surface roughness based on the data collected from a vibration sensor that is connected to the polisher. Such models can generate surface roughness of the shells in real-time, allowing the operator to make any necessary changes to the polishing for optimal result.

Navid Aftabi, Abhishek Hanchate, Satish Bukkapatnam et al.

Industry 4.0's highly networked Machine Tool Controllers (MTCs) are prime targets for replay attacks that use outdated sensor data to manipulate actuators. Dynamic watermarking can reveal such tampering, but current schemes assume linear-Gaussian dynamics and use constant watermark statistics, making them vulnerable to the time-varying, partly proprietary behavior of MTCs. We close this gap with DynaMark, a reinforcement learning framework that models dynamic watermarking as a Markov decision process (MDP). It learns an adaptive policy online that dynamically adapts the covariance of a zero-mean Gaussian watermark using available measurements and detector feedback, without needing system knowledge. DynaMark maximizes a unique reward function balancing control performance, energy consumption, and detection confidence dynamically. We develop a Bayesian belief updating mechanism for real-time detection confidence in linear systems. This approach, independent of specific system assumptions, underpins the MDP for systems with linear dynamics. On a Siemens Sinumerik 828D controller digital twin, DynaMark achieves a reduction in watermark energy by 70% while preserving the nominal trajectory, compared to constant variance baselines. It also maintains an average detection delay equivalent to one sampling interval. A physical stepper-motor testbed validates these findings, rapidly triggering alarms with less control performance decline and exceeding existing benchmarks.

Imtiaz Ahmed, Satish Bukkapatnam, Bhaskar Botcha et al.

An autonomous experimentation platform in manufacturing is supposedly capable of conducting a sequential search for finding suitable manufacturing conditions by itself or even for discovering new materials with minimal human intervention. The core of the intelligent control of such platforms is a policy to decide where to conduct the next experiment based on what has been done thus far. Such policy inevitably trades off between exploitation and exploration. Currently, the prevailing approach is to use various acquisition functions in the Bayesian optimization framework. We discuss whether it is beneficial to trade off exploitation versus exploration by measuring the element and degree of surprise associated with the immediate past observation. We devise a surprise-reacting policy using two existing surprise metrics, known as the Shannon surprise and Bayesian surprise. Our analysis shows that the surprise-reacting policy appears to be better suited for quickly characterizing the overall landscape of a response surface under resource constraints. We do not claim that we have a fully autonomous experimentation system but believe that the surprise-reacting capability benefits the automation of sequential decisions in autonomous experimentation.

Kahkashan Afrin, Parikshit Verma, Sanjay S. Srivatsa et al.

Recent introduction of wearable single-lead ECG devices of diverse configurations has caught the intrigue of the medical community. While these devices provide a highly affordable support tool for the caregivers for continuous monitoring and to detect acute conditions, such as arrhythmia, their utility for cardiac diagnostics remains limited. This is because clinical diagnosis of many cardiac pathologies is rooted in gleaning patterns from synchronous 12-lead ECG. If synchronous 12-lead signals of clinical quality can be synthesized from these single-lead devices, it can transform cardiac care by substantially reducing the costs and enhancing access to cardiac diagnostics. However, prior attempts to synthesize synchronous 12-lead ECG have not been successful. Vectorcardiography (VCG) analysis suggests that cardiac axis synthesized from earlier attempts deviates significantly from that estimated from 12-lead and/or Frank lead measurements. This work is perhaps the first successful attempt to synthesize clinically equivalent synchronous 12-lead ECG from single-lead ECG. Our method employs a random forest machine learning model that uses a subject's historical 12-lead recordings to estimate the morphology including the actual timing of various ECG events (relative to the measured single-lead ECG) for all 11 missing leads of the subject. Our method was validated on two benchmark datasets as well as paper ECG and AliveCor-Kardia data obtained from the Heart, Artery, and Vein Center of Fresno, California. Results suggest that this approach can synthesize synchronous ECG with accuracies (R2) exceeding 90%. Accurate synthesis of 12-lead ECG from a single-lead device can ultimately enable its wider application and improved point-of-care (POC) diagnostics.

Ashif Sikandar Iquebal, Satish Bukkapatnam

Advances in the image-based diagnostics of complex biological and manufacturing processes have brought unsupervised image segmentation to the forefront of enabling automated, on the fly decision making. However, most existing unsupervised segmentation approaches are either computationally complex or require manual parameter selection (e.g., flow capacities in max-flow/min-cut segmentation). In this work, we present a fully unsupervised segmentation approach using a continuous max-flow formulation over the image domain while optimally estimating the flow parameters from the image characteristics. More specifically, we show that the maximum a posteriori estimate of the image labels can be formulated as a continuous max-flow problem given the flow capacities are known. The flow capacities are then iteratively obtained by employing a novel Markov random field prior over the image domain. We present theoretical results to establish the posterior consistency of the flow capacities. We compare the performance of our approach on two real-world case studies including brain tumor image segmentation and defect identification in additively manufactured components using electron microscopic images. Comparative results with several state-of-the-art supervised as well as unsupervised methods suggest that the present method performs statistically similar to the supervised methods, but results in more than 90% improvement in the Dice score when compared to the state-of-the-art unsupervised methods.

Kahkashan Afrin, Gurudev Illangovan, Sanjay S. Srivatsa et al.

Accuracies of survival models for life expectancy prediction as well as critical-care applications are significantly compromised due to the sparsity of samples and extreme imbalance between the survival (usually, the majority) and mortality class sizes. While a recent random survival forest (RSF) model overcomes the limitations of the proportional hazard assumption, an imbalance in the data results in an underestimation (overestimation) of the hazard of the mortality (survival) classes. A balanced random survival forests (BRSF) model, based on training the RSF model with data generated from a synthetic minority sampling scheme is presented to address this gap. Theoretical results on the effect of balancing on prediction accuracies in BRSF are reported. Benchmarking studies were conducted using five datasets with different levels of class imbalance from public repositories and an imbalanced dataset of 267 acute cardiac patients, collected at the Heart, Artery, and Vein Center of Fresno, CA. Investigations suggest that BRSF provides an improved discriminatory strength between the survival and the mortality classes. It outperformed both optimized Cox (without and with balancing) and RSF with an average reduction of 55\% in the prediction error over the next best alternative.