Timothy C. Havens

Steven A. Senczyszyn, Timothy C. Havens, Nathaniel Rice et al.

As reinforcement learning (RL) deployments expand into safety-critical domains, existing evaluation methods fail to systematically identify hazards arising from the black-box nature of neural network enabled policies and distributional shift between training and deployment. This paper introduces Reinforcement Learning System-Theoretic Process Analysis (RL-STPA), a framework that adapts conventional STPA's systematic hazard analysis to address RL's unique challenges through three key contributions: hierarchical subtask decomposition using both temporal phase analysis and domain expertise to capture emergent behaviors, coverage-guided perturbation testing that explores the sensitivity of state-action spaces, and iterative checkpoints that feed identified hazards back into training through reward shaping and curriculum design. We demonstrate RL-STPA in the safety-critical test case of autonomous drone navigation and landing, revealing potential loss scenarios that can be missed by standard RL evaluations. The proposed framework provides practitioners with a toolkit for systematic hazard analysis, quantitative metrics for safety coverage assessment, and actionable guidelines for establishing operational safety bounds. While RL-STPA cannot provide formal guarantees for arbitrary neural policies, it offers a practical methodology for systematically evaluating and improving RL safety and robustness in safety-critical applications where exhaustive verification methods remain intractable.

Ali Awad, Ashraf Saleem, Sidike Paheding et al.

Underwater imagery often suffers from severe degradation resulting in low visual quality and reduced object detection performance. This work aims to evaluate state-of-the-art image enhancement models, investigate their effects on underwater object detection, and explore their potential to improve detection performance. To this end, we apply nine recent underwater image enhancement models, covering physical, non-physical and learning-based categories, to two recent underwater image datasets. Following this, we conduct joint qualitative and quantitative analyses on the original and enhanced images, revealing the discrepancy between the two analyses, and analyzing changes in the quality distribution of the images after enhancement. We then train three recent object detection models on the original datasets, selecting the best-performing detector for further analysis. This detector is subsequently re-trained on the enhanced datasets to evaluate changes in detection performance, highlighting the adverse effect of enhancement on detection performance at the dataset level. Next, we perform a correlation study to examine the relationship between various enhancement metrics and the mean Average Precision (mAP). Finally, we conduct an image-level analysis that reveals images of improved detection performance after enhancement. The findings of this study demonstrate the potential of image enhancement to improve detection performance and provide valuable insights for researchers to further explore the effects of enhancement on detection at the individual image level, rather than at the dataset level. This could enable the selective application of enhancement for improved detection. The data generated, code developed, and supplementary materials are publicly available at: https://github.com/RSSL-MTU/Enhancement-Detection-Analysis.

Anthony Geglio, Eisa Hedayati, Mark Tascillo et al.

This work investigates a practical and novel method for automated unsupervised fault detection in vehicles using a fully convolutional autoencoder. The results demonstrate the algorithm we developed can detect anomalies which correspond to powertrain faults by learning patterns in the multivariate time-series data of hybrid-electric vehicle powertrain sensors. Data was collected by engineers at Ford Motor Company from numerous sensors over several drive cycle variations. This study provides evidence of the anomaly detecting capability of our trained autoencoder and investigates the suitability of our autoencoder relative to other unsupervised methods for automatic fault detection in this data set. Preliminary results of testing the autoencoder on the powertrain sensor data indicate the data reconstruction approach availed by the autoencoder is a robust technique for identifying the abnormal sequences in the multivariate series. These results support that irregularities in hybrid-electric vehicles' powertrains are conveyed via sensor signals in the embedded electronic communication system, and therefore can be identified mechanistically with a trained algorithm. Additional unsupervised methods are tested and show the autoencoder performs better at fault detection than outlier detectors and other novel deep learning techniques.

Eisa Hedayati, Timothy C. Havens, Jeremy P. Bos

Light field imaging introduced the capability to refocus an image after capturing. Currently there are two popular methods for refocusing, shift-and-sum and Fourier slice methods. Neither of these two methods can refocus the light field in real-time without any pre-processing. In this paper we introduce a machine learning based refocusing technique that is capable of extracting 16 refocused images with refocusing parameters of α=0.125,0.250,0.375,...,2.0 in real-time. We have trained our network, which is called RefNet, in two experiments. Once using the Fourier slice method as the training -- i.e., "ground truth" -- data and another using the shift-and-sum method as the training data. We showed that in both cases, not only is the RefNet method at least 134x faster than previous approaches, but also the color prediction of RefNet is superior to both Fourier slice and shift-and-sum methods while having similar depth of field and focus distance performance.

Eisa Hedayati, Timothy C. Havens, Jeremy P. Bos

Light field (LF) imaging has gained significant attention due to its recent success in 3-dimensional (3D) displaying and rendering as well as augmented and virtual reality usage. Nonetheless, because of the two extra dimensions, LFs are much larger than conventional images. We develop a JPEG-assisted learning-based technique to reconstruct an LF from a JPEG bitstream with a bit per pixel ratio of 0.0047 on average. For compression, we keep the LF's center view and use JPEG compression with 50% quality. Our reconstruction pipeline consists of a small JPEG enhancement network (JPEG-Hance), a depth estimation network (Depth-Net), followed by view synthesizing by warping the enhanced center view. Our pipeline is significantly faster than using video compression on pseudo-sequences extracted from an LF, both in compression and decompression, while maintaining effective performance. We show that with a 1% compression time cost and 18x speedup for decompression, our methods reconstructed LFs have better structural similarity index metric (SSIM) and comparable peak signal-to-noise ratio (PSNR) compared to the state-of-the-art video compression techniques used to compress LFs.

Muhammad Aminul Islam, Derek T. Anderson, Anthony J. Pinar et al.

Information fusion is an essential part of numerous engineering systems and biological functions, e.g., human cognition. Fusion occurs at many levels, ranging from the low-level combination of signals to the high-level aggregation of heterogeneous decision-making processes. While the last decade has witnessed an explosion of research in deep learning, fusion in neural networks has not observed the same revolution. Specifically, most neural fusion approaches are ad hoc, are not understood, are distributed versus localized, and/or explainability is low (if present at all). Herein, we prove that the fuzzy Choquet integral (ChI), a powerful nonlinear aggregation function, can be represented as a multi-layer network, referred to hereafter as ChIMP. We also put forth an improved ChIMP (iChIMP) that leads to a stochastic gradient descent-based optimization in light of the exponential number of ChI inequality constraints. An additional benefit of ChIMP/iChIMP is that it enables eXplainable AI (XAI). Synthetic validation experiments are provided and iChIMP is applied to the fusion of a set of heterogeneous architecture deep models in remote sensing. We show an improvement in model accuracy and our previously established XAI indices shed light on the quality of our data, model, and its decisions.

Radha Chitta, Rong Jin, Timothy C. Havens et al.

Kernel-based clustering algorithms have the ability to capture the non-linear structure in real world data. Among various kernel-based clustering algorithms, kernel k-means has gained popularity due to its simple iterative nature and ease of implementation. However, its run-time complexity and memory footprint increase quadratically in terms of the size of the data set, and hence, large data sets cannot be clustered efficiently. In this paper, we propose an approximation scheme based on randomization, called the Approximate Kernel k-means. We approximate the cluster centers using the kernel similarity between a few sampled points and all the points in the data set. We show that the proposed method achieves better clustering performance than the traditional low rank kernel approximation based clustering schemes. We also demonstrate that its running time and memory requirements are significantly lower than those of kernel k-means, with only a small reduction in the clustering quality on several public domain large data sets. We then employ ensemble clustering techniques to further enhance the performance of our algorithm.