End-to-end physics-informed deep neural network optimization of sub-Nyquist lenses.

In this paper, an approach for optimizing sub-Nyquist lenses using an end-to-end physics-informed deep neural network is presented. The simulation and optimization of these sub-Nyquist lenses is investigated for image quality, classification performance, or both. This approach integrates a diffractive optical model with a deep learning classifier, forming a unified optimization framework that facilitates simultaneous simulation and optimization. Lenses in this work span numerical apertures from approximately 0.1 to 1.0, and a total of 707 models are trained using the PyTorch-Lightning deep learning framework. Results demonstrate that the optimized lenses produce better image quality in terms of mean squared error (MSE) compared to analytical lenses by reducing the impact of diffraction order aliasing. When combined with the classifier, the optimized lenses show improved classification performance and reduced variability across the focal range. Additionally, the absence of correlation between the MSE measurement of image quality and classification performance suggests that images that appear good according to the MSE metric may not necessarily be beneficial for the classifier.

Extending the Morphological Hit-or-Miss Transform to Deep Neural Networks.

While most deep learning architectures are built on convolution, alternative foundations such as morphology are being explored for purposes such as interpretability and its connection to the analysis and processing of geometric structures. The morphological hit-or-miss operation has the advantage that it considers both foreground information and background information when evaluating the target shape in an image. In this article, we identify limitations in the existing hit-or-miss neural definitions and formulate an optimization problem to learn the transform relative to deeper architectures. To this end, we model the semantically important condition that the intersection of the hit and miss structuring elements (SEs) should be empty and present a way to express Don't Care (DNC), which is important for denoting regions of an SE that are not relevant to detecting a target pattern. Our analysis shows that convolution, in fact, acts like a hit-to-miss transform through semantic interpretation of its filter differences. On these premises, we introduce an extension that outperforms conventional convolution on benchmark data. Quantitative experiments are provided on synthetic and benchmark data, showing that the direct encoding hit-or-miss transform provides better interpretability on learned shapes consistent with objects, whereas our morphologically inspired generalized convolution yields higher classification accuracy. Finally, qualitative hit and miss filter visualizations are provided relative to single morphological layer.

Survey and Insights into Unmanned Aerial-Vehicle-Based Detection and Documentation of Clandestine Graves and Human Remains.

Numerous biological and archaeological studies have demonstrated the legitimacy of remote sensing in anthropology. This article focuses on detecting and documenting terrestrial clandestine graves and surface remains (CGSR) of humans using unmanned aerial vehicles (UAVs), sensors, and automatic processing algorithms. CGSR is a problem of complex decision making under uncertainty that requires the identification and intelligent reasoning about direct evidence of human remains and their environmental fingerprints. As such, it is as much an engineering and geospatial problem as it is an anthropology problem. This article is an effort to survey existing work across disciplines and to provide insights and recommendations to assist future research. To support our claims, preliminary experiments were performed at the Forensic Anthropological Research Facility at Texas State University using UAVs, hyperspectral imaging, thermal imaging, and structure from motion. Prior work, our experience, and preliminary results indicate that both great potential and extreme challenges face remote sensing of CGSR.

Fusion of an Ensemble of Augmented Image Detectors for Robust Object Detection.

A significant challenge in object detection is accurate identification of an object's position in image space, whereas one algorithm with one set of parameters is usually not enough, and the fusion of multiple algorithms and/or parameters can lead to more robust results. Herein, a new computational intelligence fusion approach based on the dynamic analysis of agreement among object detection outputs is proposed. Furthermore, we propose an online versus just in training image augmentation strategy. Experiments comparing the results both with and without fusion are presented. We demonstrate that the augmented and fused combination results are the best, with respect to higher accuracy rates and reduction of outlier influences. The approach is demonstrated in the context of cone, pedestrian and box detection for Advanced Driver Assistance Systems (ADAS) applications.

Estimation of adult skeletal age-at-death using the Sugeno fuzzy integral.

Age-at-death estimation of an individual skeleton is important to forensic and biological anthropologists for identification and demographic analysis, but it has been shown that the current aging methods are often unreliable because of skeletal variation and taphonomic factors. Multifactorial methods have been shown to produce better results when determining age-at-death than single indicator methods. However, multifactorial methods are difficult to apply to single or poorly preserved skeletons, and they rarely provide the investigator with information about the reliability of the estimate. The goal of this research is to examine the validity of the Sugeno fuzzy integral as a multifactorial method for modeling age-at-death of an individual skeleton. This approach is novel because it produces an informed decision of age-at-death utilizing multiple age indicators while also taking into consideration the accuracies of the methods and the condition of the bone being examined. Additionally, the Sugeno fuzzy integral does not require the use of a population and it qualitatively produces easily interpreted graphical results. Examples are presented applying three commonly used aging methods on a known-age skeletal sample from the Terry Anatomical Collection. This method produces results that are more accurate and with smaller intervals than single indicator methods.

Relational analysis of CpG islands methylation and gene expression in human lymphomas using possibilistic C-means clustering and modified cluster fuzzy density.

Heterogeneous genetic and epigenetic alterations are commonly found in human non-Hodgkin's lymphomas (NHL). One such epigenetic alteration is aberrant methylation of gene promoter-related CpG islands, where hypermethylation frequently results in transcriptional inactivation of target genes, while a decrease or loss of promoter methylation (hypomethylation) is frequently associated with transcriptional activation. Discovering genes with these relationships in NHL or other types of cancers could lead to a better understanding of the pathobiology of these diseases. The simultaneous analysis of promoter methylation using Differential Methylation Hybridization (DMH) and its associated gene expression using Expressed CpG Island Sequence Tag (ECIST) microarrays generates a large volume of methylation-expression relational data. To analyze this data, we propose a set of algorithms based on fuzzy sets theory, in particular Possibilistic c-Means (PCM) and cluster fuzzy density. For each gene, these algorithms calculate measures of confidence of various methylation-expression relationships in each NHL subclass. Thus, these tools can be used as a means of high volume data exploration to better guide biological confirmation using independent molecular biology methods.