Analogical reasoning is an increasingly popular, lightweight solution to enable large language model (LLM)-level reasoning without computational complexity. Still, it has yet to be adopted due to its reliance on strictly hand-formatted data. Therefore, we propose Analogy2KG (“Analogy to Knowledge Graph’’), as an automatic pipeline that transforms text into a KG format via a fine-tuned version of information extraction (IE) algorithms for long-text analogies. The need to verify that the complex underlying analogical structure of the data is maintained was done via paired samples tests in the creation and validation of this pipeline. Graph density was used to evaluate the structural quality of the resulting KGs. Lastly, causal relationships were optionally detected using a novel, question-and-answer-based method. Analogy2KG was validated on the Rattermann and Wharton long-text datasets, which suggested that the proposed methodology maintains analogical structure when transforming from text to KGs. The resulting RattermannKG and WhartonKG datasets were introduced to the literature, which is the first instance of a the conversion of long-text analogy dataset into a KG format in the literature. Finally, Analogy2KG had superior performance among three LLM-enabled information extraction algorithms: ChatIE, Code4UIE, and InstructUIE for maintaining analogical structure, despite operating without the need for an LLM backend and a pre-defined relation extractor list; thus, making it an ideal lightweight solution.

Abstract Estimating the position and orientation of a rigid object from an image is critical for situational awareness in robotics and autonomous systems. This study explores relative pose estimation using an ultra-wide fisheye camera for unmanned aircraft inspection vehicles. Ultra-wide fisheye lenses introduce radial distortion and capture features beyond the rectilinear image plane, rendering rectilinear Perspective-n-Point (PnP) algorithms inadequate. Designing a bespoke ultra-wide fisheye localization algorithm requires consideration of both the feature detection method and the pose estimator itself. This study proposes a novel method that combines (1) a fisheye-to-cubemap reprojection, (2) a You Only Look Once (YOLO) convolutional neural network trained for arbitrary airborne perspectives, and (3) an Angle-Agnostic and Multiple-Frame PnP (AMP) pose estimation algorithm. Our pipeline achieves a 97% success rate for valid pose estimates, with a mean absolute translational error of less than 12 cm on real ultra-wide fisheye imagery, outperforming conventional techniques, including OpenCV.

The ongoing evolution of malware presents a formidable challenge to cybersecurity: identifying unknown threats. Traditional detection methods, such as signatures and various forms of static analysis , inherently lag behind these evolving threats. This research introduces a novel approach to malware detection by leveraging the robust statistical capabilities of L-moments and the structural insights provided by Abstract Syntax Trees (ASTs) and applying them to PowerShell. L-moments, recognized for their resilience to outliers and adaptability to diverse distributional shapes, are extracted from network analysis measures like degree centrality , betweenness centrality , and closeness centrality of ASTs. These measures provide a detailed structural representation of code, enabling a deeper understanding of its inherent behaviors and patterns. This approach aims to detect not only known malware but also uncover new, previously unidentified threats. A comprehensive comparison with traditional static analysis methods shows that this approach excels in key performance metrics such as accuracy, precision, recall, and F 1 score. These results demonstrate the significant potential of combining L-moments derived from network analysis with ASTs in enhancing malware detection. While static analysis remains an essential tool in cybersecurity, the integration of L-moments and advanced network analysis offers a more effective and efficient response to the dynamic landscape of cyber threats. This study paves the way for future research, particularly in extending the use of L-moments and network analysis into additional areas.

This article expands the methods for analyzing satellite reliability by presenting a framework of measures to determine the best statistical distribution to use in data parameterization, and applying robust regression to improve the fit of the Weibull distribution in the regression parameterization method when data outliers are present. The distribution identification framework is defined by four statistical goodness-of-fit measures, while the robust regression methodology is developed through comparing how least-squares and iteratively reweighted least squares robust linear regression can parameterize satellite reliability data. Both of these methodologies are then applied to deep space satellite reliability data to evaluate their performance. All four measures comprising the distributional assessment framework show agreement by selecting the Weibull distribution. These results serve as a proof of concept for the framework and warrant its inclusion in future satellite reliability studies. Robust regression's use in the regression parameterization method in the presence of outliers yielded positive results. Specifically, improvement is indicated through visual inspection of the resulting Weibull distribution, and by closer agreement of the robust regression Weibull parameters to the MLE parameters than the least-squares regression parameters. Ultimately, the improved fit produced by the use of robust regression in the regression parameterization method justifies its increased computational complexity as compared to traditional least-squares regression. Incorporation of these methods and framework provides quantitative enhancements to distribution fitting and parameter estimation in satellite reliability studies.

Probability of detection (POD) calculations in structural health monitoring (SHM) applications are complicated by the dependency of measurements obtained on the same structure, among other factors. This article presents a repeated measures method to extend POD signal-response modeling to correctly describe a population of repeated measurements while estimating the variance due to dependence in the observations. In particular, equations are presented which develop an autoregressive correlation structure to model continuous observations that are correlated in time. Software implementation of these models is discussed and methodology to simulate correlated datasets is presented. The combination of these tools enables a method of POD estimation in SHM applications through the appropriate mathematical extensions of the statistical modeling.

Abstract Achieving precise 6 degrees of freedom (6D) pose estimation of rigid objects from color images is a critical challenge with wide-ranging applications in robotics and close-contact aircraft operations. This study investigates key techniques in the application of YOLOv5 object detection convolutional neural network (CNN) for 6D pose localization of aircraft using only color imagery. Traditional object detection labeling methods suffer from inaccuracies due to perspective geometry and being limited to visible key points. This research demonstrates that with precise labeling, a CNN can predict object features with near-pixel accuracy, effectively learning the distinct appearance of the object due to perspective distortion with a pinhole camera. Additionally, we highlight the crucial role of knowledge about occluded features. Training the CNN with such knowledge slightly reduces pixel precision, but enables the prediction of 3 times more features, including those that are not initially visible, resulting in an overall better performing 6D system. Notably, we reveal that the data augmentation technique ofscalecan interfere with pixel precision when used during training. These findings are crucial for the entire system, which leverages the Solve Perspective-N-Point (Solve-PnP) algorithm, achieving 6D pose accuracy within 1 $$^\circ$$ ∘ and 7 cm at distances ranging from 7.5 to 35 m from the camera. Moreover, this solution operates in real-time, achieving sub-10ms processing times on a desktop PC.

The US Air Force has multiple detection systems for specific applications that could be combined to work together to yield better accuracy than the individual systems. The amount of time and money used to design, build, simulate, test, validate and verify such combining can be long and expense. Also, there can be several ways to combine these multiple systems, thus, generating more time and cost to determine an optimal (or approximately optimal) combination rule. This paper considers a simple version of this greater problem posed as follows. Suppose we have two legacy detections system families that are designed to detect the same “target” and we conjecture that combining them would yield a new detection system with improved accuracy. Suppose we know the ROC functions of both detection system families, but do not know (or have access to) the data that produced them. Can we construct the ROC function of the combined systems from the individual ROC functions? Copula theory has been in existence since 1959. This theory produces the means to address the dependence between random variables. This paper takes copula and applies it to the fusion of detection systems. Examples will be given that demonstrate how the formulas are used.

This paper introduces a method for unsupervised tokenization of Controller Area Network (CAN) data payloads using bit level transition analysis and a greedy grouping strategy. The primary goal of this proposal is to extract individual time series which have been concatenated together before transmission onto a vehicle's CAN bus. This process is necessary because the documentation for how to properly extract data from a network may not always be available; passenger vehicle CAN configurations are protected as trade secrets. At least one major manufacturer has also been found to deliberately misconfigure their documented extraction methods. Thus, this proposal serves as a critical enabler for robust third-party security auditing and intrusion detection systems which do not rely on manufacturers sharing confidential information.

Using deeply recurrent neural networks to account for temporal dependence in electroencephalograph (EEG)-based workload estimation is shown to considerably improve day-to-day feature stationarity resulting in significantly higher accuracy (p < .0001) than classifiers which do not consider the temporal dependence encoded within the EEG time-series signal. This improvement is demonstrated by training several deep Recurrent Neural Network (RNN) models including Long Short-Term Memory (LSTM) architectures, a feedforward Artificial Neural Network (ANN), and Support Vector Machine (SVM) models on data from six participants who each perform several Multi-Attribute Task Battery (MATB) sessions on five separate days spread out over a month-long period. Each participant-specific classifier is trained on the first four days of data and tested using the fifth’s. Average classification accuracy of 93.0% is achieved using a deep LSTM architecture. These results represent a 59% decrease in error compared to the best previously published results for this dataset. This study additionally evaluates the significance of new features: all combinations of mean, variance, skewness, and kurtosis of EEG frequency-domain power distributions. Mean and variance are statistically significant features, while skewness and kurtosis are not. The overall performance of this approach is high enough to warrant evaluation for inclusion in operational systems.

A reasonable starting place for developing decision fusion rules of families of classification systems is using the logical AND and OR rules. These two rules, along with the unary rule NOT, can lead to a Boolean algebra when a number of properties are shown to exist. This paper examines how these rules for classification system families comprise a Boolean algebra of systems. This Boolean algebra of families is then shown under assumptions of independence to be isomorphic to a Boolean algebra of receiver operating characteristic (ROC) curves. These decision fusion rules produce ROC curves which become the bounds by which to test non-Boolean, possibly non-decision fusion rules for performance increases. We give an example to demonstrate the usefulness of this Boolean algebra of ROC curves.