Test Inputs Research Articles

STTA: enhanced text classification via selective test-time augmentation.

Test-time augmentation (TTA) is a well-established technique that involves aggregating transformed examples of test inputs during the inference stage. The goal is to enhance model performance and reduce the uncertainty of predictions. Despite its advantages of not requiring additional training or hyperparameter tuning, and being applicable to any existing model, TTA is still in its early stages in the field of NLP. This is partly due to the difficulty of discerning the contribution of different transformed samples, which can negatively impact predictions. In order to address these issues, we propose Selective Test-Time Augmentation, called STTA, which aims to select the most beneficial transformed samples for aggregation by identifying reliable samples. Furthermore, we analyze and empirically verify why TTA is sensitive to some text data augmentation methods and reveal why some data augmentation methods lead to erroneous predictions. Through extensive experiments, we demonstrate that STTA is a simple and effective method that can produce promising results in various text classification tasks.

Improved Test Input Prioritization Using Verification Monitors with False Prediction Cluster Centroids

Deep learning (DL) systems have been remarkably successful in various applications, but they could have critical misbehaviors. To identify the weakness of a trained model and overcome it with new data collection(s), one needs to figure out the corner cases of a trained model. Constructing new datasets to retrain a DL model requires extra budget and time. Test input prioritization (TIP) techniques have been proposed to identify corner cases more effectively. The state-of-the-art TIP approach adopts a monitoring method to TIP and prioritizes based on Gini impurity; one estimates the similarity between a DL prediction probability and uniform distribution. This letter proposes a new TIP method that uses a distance between false prediction cluster (FPC) centroids in a training set and a test instance in the last-layer feature space to prioritize error-inducing instances among an unlabeled test set. We refer to the proposed method as DeepFPC. Our numerical experiments show that the proposed DeepFPC method achieves significantly improved TIP performance in several image classification and active learning tasks.

Microcontroller Based Smart Energy Meter with Data Logger System

Recent advancements in power system ensure that energy being generated is efficiently delivered to meet the growing demand for electricity in many countries. However, determining the proper energy usage by the consumers has become a major challenge to utility companies. Metering is an important aspect of electricity distribution, it helps to accurately measure and bill customers for their electricity consumption. In this project, a prototype for an electricity monitoring system using ATMEGA328P as the microcontroller was proposed and developed. The display parameter values are voltage, current, power factor, active and apparent power. A ZMPT101B voltage sensor is used to measure the AC voltage, while an SCT-013 100A current sensor is used to measure the AC current flowing through meter. In addition, a rotary encoder is used to converts the rotational motion into an electrical signal which is used to measure and control various parameters in a system. Real time clock module is based on an internal clock that generates pulses at a fixed frequency. variety of tests to verify that the system can handle the expected volume of data, can communicate reliably and that can secure data were performed such as logging the energy data to memory card, testing input sensors, The voltage and current errors for the energy meter are ±0.1% and ±0.3%, respectively while the power value error of ±0.04%, which is acceptable for most metering devices, The use of smart metering system lead to a more sustainable and efficient energy system for achieving a more sustainable future.

LMdist: Local Manifold distance accurately measures beta diversity in ecological gradients.

Differentiating ecosystems poses a complex, high-dimensional problem constrained by capturing relevant variation across species profiles. Researchers use pairwise distances and subsequent dimensionality reduction to highlight variation in a few dimensions. Despite popularity in analysis of ecological data, these low-dimensional visualizations can contain geometric abnormalities such as "arch" and "horseshoe" effects, potentially obscuring the impact of environmental gradients. These abnormalities appear in ordination but are in fact a product of oversaturated large pairwise distances. We present Local Manifold distance (LMdist), an unsupervised algorithm which adjusts pairwise beta diversity measures to better represent true ecological distances between samples. Beta diversity measures can have a bounded dynamic range in depicting long environmental gradients with high species turnover. Using a graph structure, LMdist projects pairwise distances onto a manifold and traverses the manifold surface to adjust pairwise distances at the upper end of the beta diversity measure's dynamic range. This allows for values beyond the range of the original measure. Not all datasets will have oversaturated pairwise distances, nor will capture variation that resembles a manifold, so LMdist adjusts only those pairwise values which may be undervalued in the presence of a sampled gradient. The adjusted distances serve as input for ordination and statistical testing. We demonstrate on real and simulated data that LMdist effectively recovers distances along known gradients and along complex manifolds such as the Swiss roll dataset. LMdist enables more powerful statistical tests for gradient effects and reveals variation orthogonal to the gradient. Available on GitHub at https://github.com/knights-lab/LMdist.

A novel approach for the fractional SLS material model experimental identification

A multi-step, iterative technique for the local non-parametric identification of the standard linear solid (SLS) material model employing fractional order time differential operators is presented. Test input data consists of a set of identified material complex modulus values estimated at different frequency values, obtained from input–output experimental measurements made on a material specimen by means of forced harmonic excitation and from experimental measurements made on the same specimen in quasi-static relaxation conditions. The proposed technique is mainly based on an algebraic procedure leading to the solution of an overdetermined system of linear equations, in order to get the optimal value of the model unknown parameters. The procedure is non-parametric, since the SLS model order is initially unknown. The optimal model size can be found by evaluating the stability properties of the solution associated to any model size and by automatically discarding computational, non-physical contributions. The identification procedure is first validated by means of numerically simulated test data from within known model examples, and then it is applied to some experimentally obtained test data associated to different materials.

Gene Expression Machine Learning Models Classify Pediatric AML Subtypes with High Performance

Pediatric acute myeloid leukemia (pAML) encompasses over 20 molecular subtypes driven by unique genetic alterations, including hallmark chromosomal rearrangements and less frequently, point mutations or tandem duplications. Collectively, many of these pAML molecular categories are enriched in pediatric populations and are not represented by current classification systems, including the recently updated WHO or ICC. While fusion detection from RNA-Seq-based approaches is robust, many fusion negative subtypes would need to be defined by expression-based approaches as mutation calling from RNA-Seq data is less developed. Nevertheless, this could be challenging for subtypes with similar transcriptional profiles, such as those with shared HOX expression patterns, including NPM1, NUP98r, UBTF, DEK::NUP214, and KMT2A-PTD. To aid in the appropriate molecular classification of pAML, which is crucial for prognosis, we developed and compared three gene expression-based classifiers. A total of 1707 pAML gene expression profiles were mapped and analyzed from three distinct sources (St. Jude = 659; TARGET = 168; AAML1031 = 880). Raw read count data was normalized and scaled to obtain a relative expression value in transcripts per million (TPM), which served as input for feature selection, model training, and testing. Ground truth labels for all 1707 samples were obtained through multi-omics analysis, including whole genome sequencing, to identify fusions and mutations. For validation purposes, the data was stratified by subtypes and split 70/30 into training (n=1187) and testing (n=520). Three machine learning models were selected: random forest, XGboost, and linear support vector machine (SVM). Each sample had gene expression TPM data for 60,754 transcripts, out of which 20,004 transcripts related to protein-coding genes were incorporated for feature selection. Feature selection was performed using a median absolute deviation (MAD) algorithm to select the 3000 transcripts with the highest variability. Top variable 3000 genes were selected to allow for adequate tuning of the number of predictors. Each model was independently trained using stratified cross-validation and Monte-Carlo search for hyperparameter tuning. The best model was selected based on the Matthews Correlation Coefficient (MCC). Each model was tested on the hold-out TPM set with z-score normalization. On the hold-out testing set (n=520), the linear SVM model outperformed the random forest and XGboost models on five performance metrics across all subtypes (sensitivity=0.9577; precision=0.9577; specificity=0.9978; F1=0.96; accuracy=0.9958). The random forest (sensitivity=0.9154; precision=0.9154; specificity=0.9955; F1=0.92; accuracy=0.9915) and XGboost models (sensitivity=0.9231; precision=0.9231; specificity=0.9960; F1=0.92; accuracy=0.9923) also performed well across all subtypes. Although feature selection was shared across all three models, performance within each subtype varied between models. The linear SVM model demonstrated strong performance overall, driven by high specificity in classifying the KMT2Ar subgroup (n=127) and equal sensitivity across the GLIS-rearranged (n=14), GATA1 (n=10), BCL11B (n=7), CBFB::MYH11 (n=60), CEBPA (n=33), and RUNX1::RUNX1T1 (n=78) subtypes. The primary difference in performance between models is the high false positive rate for KMT2Ar and NPM1 (n=55) in the random forest and XGboost models. A preliminary hypothesis for this might be due to the large representation of KMT2Ar and NPM1 in the training data (24.85% and 10.78%, respectively). Synthetic upsampling (SMOTE) for the training dataset (n=1369) counteracts bias towards the majority classes and increases performance for the random forest (sensitivity=0.9327; precision=0.9327; specificity=0.9965; F1=0.93; accuracy=0.9933), XGboost (sensitivity=0.9404; precision=0.9404; specificity=0.9969; F1=0.94; accuracy=0.9940) and linear SVM (sensitivity=0.9615; precision=0.9615; specificity=0.9980; F1=0.96; accuracy=0.9962) models. Conjointly, these models demonstrate the utility and effectiveness of a machine learning approach for classifying pAML samples from transcriptome sequencing data, which may have broad clinical and research utility, especially for fusion negative subtypes.

Problems on the theme "Maximum non-decreasing subsequence"

In the article, using the example of solving few problems, the methodology for studying the theme "Maximum non-decreasing subsequence" is illustrated in preparing schoolchildren for Olympiads in informatics. The study is based on the sequential solution of increasingly complex problems. For each problem, the following materials are given: the formulation of the problem, the idea of a solution, the solution in the Pascal programming language. Distance learning system (http://dl.gsu.by) is the technical base for teaching. The system allows to offer for a student a formulation of the problem; to submit the solution for review; to get a verdict from the system — a correct or incorrect solution; for incorrect solution, the number of the test on which the solution did not pass is indicated. A student can take a test (input and output data), on which his solution did not pass, figure out what the error is in his program, correct it and send the solution again. In addition, for each problem there is a link on it to the topic in the forum at site, where you can ask a question on solving this problem and / or read the answer if the questions have already been asked before.

GraphPrior: Mutation-based Test Input Prioritization for Graph Neural Networks

Graph Neural Networks (GNNs) have achieved promising performance in a variety of practical applications. Similar to traditional DNNs, GNNs could exhibit incorrect behavior that may lead to severe consequences, and thus testing is necessary and crucial. However, labeling all the test inputs for GNNs can be costly and time-consuming, especially when dealing with large and complex graphs, which seriously affects the efficiency of GNN testing. Existing studies have focused on test prioritization for DNNs, which aims to identify and prioritize fault-revealing tests (i.e., test inputs that are more likely to be misclassified) to detect system bugs earlier in a limited time. Although some DNN prioritization approaches have been demonstrated effective, there is a significant problem when applying them to GNNs: They do not take into account the connections (edges) between GNN test inputs (nodes), which play a significant role in GNN inference. In general, DNN test inputs are independent of each other, while GNN test inputs are usually represented as a graph with complex relationships between each test. In this article, we propose GraphPrior ( GNN -oriented Test Prior itization), a set of approaches to prioritize test inputs specifically for GNNs via mutation analysis. Inspired by mutation testing in traditional software engineering, in which test suites are evaluated based on the mutants they kill, GraphPrior generates mutated models for GNNs and regards test inputs that kill many mutated models as more likely to be misclassified. Then, GraphPrior leverages the mutation results in two ways, killing-based and feature-based methods. When scoring a test input, the killing-based method considers each mutated model equally important, while feature-based methods learn different importance for each mutated model through ranking models. Finally, GraphPrior ranks all the test inputs based on their scores. We conducted an extensive study based on 604 subjects to evaluate GraphPrior on both natural and adversarial test inputs. The results demonstrate that KMGP, the killing-based GraphPrior approach, outperforms the compared approaches in a majority of cases, with an average improvement of 4.76% ~49.60% in terms of APFD. Furthermore, the feature-based GraphPrior approach, RFGP, performs the best among all the GraphPrior approaches. On adversarial test inputs, RFGP outperforms the compared approaches across different adversarial attacks, with the average improvement of 2.95% ~46.69%.

Variationally mimetic operator networks

In recent years operator networks have emerged as promising deep learning tools for approximating the solution to partial differential equations (PDEs). These networks map input functions that describe material properties, forcing functions, and boundary data to the solution of a PDE. This work describes a new architecture for operator networks, called the variationally mimetic operator network (VarMiON ), that mimics the form of the numerical solution obtained from an approximate variational or weak formulation of the problem. Like the conventional Deep Operator Network (DeepONet) the VarMiON is also composed of a sub-network that constructs the basis functions for the output and another that constructs the coefficients for these basis functions. However, in contrast to the DeepONet, the architecture of these sub-networks in the VarMiON is precisely determined. An analysis of the error in the VarMiON solution reveals that it contains contributions from the error in the training data, the training error, the quadrature error in sampling input and output functions, and a “covering error” that measures the distance between the test input functions and the nearest functions in the training dataset. It also depends on the stability constants for the exact solution operator and its VarMiON approximation. The application of the VarMiON to a canonical elliptic PDE and a nonlinear PDE reveals that for approximately the same number of network parameters, on average the VarMiON incurs smaller errors than a standard DeepONet and a recently proposed multiple-input operator network (MIONet). Further, its performance is more robust to variations in input functions, the techniques used to sample the input and output functions, the techniques used to construct the basis functions, and the number of input functions. Moreover, it consistently outperforms baseline methods at various dataset sizes. The data and code accompanying this manuscript are publicly available at https://github.com/dhruvpatel108/VarMiON.

ENN: Hierarchical Image Classification Ensemble Neural Network for Large-Scale Automated Detection of Potential Design Infringement

This paper presents a two-stage hierarchical neural network using image classification and object detection algorithms as key building blocks for a system that automatically detects a potential design right infringement. This neural network is trained to return the Top-N original design right records that highly resemble the input image of a counterfeit. This work proposes an ensemble neural network (ENN), an artificial neural network model that aims to deal with a large amount of counterfeit data and design right records that are frequently added and deleted. First, we performed image classification and objection detection learning per design right using acclaimed existing models with high accuracy. The distributed models form the backbone of the ENN and yield intermediate results aggregated at a master neural network. This master neural network is a deep residual network paired with a fully connected network. This ensemble layer is trained to determine the sub-models that return the best result for a given input image of a product. In the final stage, the ENN model multiplies the inferred similarity coefficients to the weighted input vectors produced by the individual sub-models to assess the similarity between the test input image and the existing product design rights to see any sign of violation. Given 84 design rights and the sample product images taken meticulously under various conditions, our ENN model achieved average Top-1 and Top-3 accuracies of 98.409% and 99.460%, respectively. Upon introducing new design rights data, a partial update of the inference model was performed an order of magnitude faster than the single model. The ENN maintained a high level of accuracy as it was scaled out to handle more design rights. Therefore, the ENN model is expected to offer practical help to the inspectors in the field, such as customs at the border that deal with a swarm of products.

Automated black-box boundary value detection

Software systems typically have an input domain that can be subdivided into sub-domains, each of which generates similar or related outputs. Testing it on the boundaries between these sub-domains is critical to ensure high-quality software. Therefore, boundary value analysis and testing have been a fundamental part of the software testing toolbox for a long time and are typically taught early to software engineering students. Despite its many argued benefits, boundary value analysis for a given software specification or application is typically described in abstract terms. This allows for variation in how testers apply it and in the benefits they see. Additionally, its adoption has been limited since it requires a specification or model to be analysed. We propose an automated black-box boundary value detection method to support software testers in performing systematic boundary value analysis. This dynamic method can be utilized even without a specification or model. The proposed method is based on a metric referred to as the program derivative, which quantifies the level of boundariness of test inputs. By combining this metric with search algorithms, we can identify and rank pairs of inputs as good boundary candidates, i.e., inputs that are in close proximity to each other but with outputs that are far apart. We have implemented the AutoBVA approach and evaluated it on a curated dataset of example programs. Furthermore, we have applied the approach broadly to a sample of 613 functions from the base library of the Julia programming language. The approach could identify boundary candidates that highlight diverse boundary behaviours in over 70% of investigated systems under test. The results demonstrate that even a simple variant of the program derivative, combined with broad sampling and search over the input space, can identify interesting boundary candidates for a significant portion of the functions under investigation. In conclusion, we also discuss the future extension of the approach to encompass more complex systems under test cases and datatypes.

Generating and detecting true ambiguity: a forgotten danger in DNN supervision testing

Deep Neural Networks (DNNs) are becoming a crucial component of modern software systems, but they are prone to fail under conditions that are different from the ones observed during training (out-of-distribution inputs) or on inputs that are truly ambiguous, i.e., inputs that admit multiple classes with nonzero probability in their labels. Recent work proposed DNN supervisors to detect high-uncertainty inputs before their possible misclassification leads to any harm. To test and compare the capabilities of DNN supervisors, researchers proposed test generation techniques, to focus the testing effort on high-uncertainty inputs that should be recognized as anomalous by supervisors. However, existing test generators aim to produce out-of-distribution inputs. No existing model- and supervisor independent technique targets the generation of truly ambiguous test inputs, i.e., inputs that admit multiple classes according to expert human judgment. In this paper, we propose a novel way to generate ambiguous inputs to test DNN supervisors and used it to empirically compare several existing supervisor techniques. In particular, we propose AmbiGuess to generate ambiguous samples for image classification problems. AmbiGuess is based on gradient-guided sampling in the latent space of a regularized adversarial autoencoder. Moreover, we conducted what is {-} to the best of our knowledge {-} the most extensive comparative study of DNN supervisors, considering their capabilities to detect 4 distinct types of high-uncertainty inputs, including truly ambiguous ones. We find that the tested supervisors’ capabilities are complementary: Those best suited to detect true ambiguity perform worse on invalid, out-of-distribution and adversarial inputs and vice-versa.

Vehicle detection and classification using three variations of you only look once algorithm

<p><span>Vehicle detection and classification are essential for advanced driver assistance systems (ADAS) and even traffic camera surveillance. Yet, it is challenging due to complex backgrounds, varying illumination intensities, occlusions, vehicle size, and type variations. This paper aims to apply you only look once (YOLO) since it has been proven to produce high object detection and classification accuracy. There are various versions of YOLO, and their performances differ. An investigation on the detection and classification performance of YOLOv3, YOLOv4, and YOLOv5 has been conducted. The training images were from common objects in context (COCO) and open image, two publicly available datasets. The testing input images were captured on a few highways in two main cities in Malaysia, namely Shah Alam and Kuala Lumpur. These images were captured using a mobile phone camera with different backgrounds during the day and night, representing different illuminations and varying types and sizes of vehicles. The accuracy and speed of detecting and classifying cars, trucks, buses, motorcycles, and bicycles have been evaluated. The experimental results show that YOLOv5 detects vehicles more accurately but slower than its predecessors, namely YOLOv4 and YOLOv3. Future work includes experimenting with newer versions of YOLO.</span></p>

Automatic Test Sequence Generation and Functional Coverage Measurement From UML Sequence Diagrams

Sequence diagrams define functional requirements through use cases. However, their visual form limits their usability in the later stages of the development life cycle. This work proposes a method to transform sequence diagrams into graph-based event sequence graphs, allowing the application of graph analysis methods and defining graph-based coverage criteria. This work explores these newfound abilities in two directions. The first is to use coverage criteria along with existing tests to measure their coverage levels, providing a metric of how well they address the scenarios defined in sequence diagrams. The second is to use coverage criteria to automatically generate effective and efficient acceptance test cases based on the scenarios defined in sequence diagrams. The transformation method is validated with over eighty non-trivial projects. The complete method is validated through a non-trivial example. The results show that the test cases generated with the proposed method are more effective at exposing faults and more efficient in test input size than user-generated test cases.

Boosting Fuzzer Efficiency: An Information Theoretic Perspective

In this paper, we take the fundamental perspective of fuzzing as a learning process. Suppose before fuzzing, we know nothing about the behaviors of a program P : What does it do? Executing the first test input, we learn how P behaves for this input. Executing the next input, we either observe the same or discover a new behavior. As such, each execution reveals "some amount" of information about P 's behaviors. A classic measure of information is Shannon's entropy. Measuring entropy allows us to quantify how much is learned from each generated test input about the behaviors of the program. Within a probabilistic model of fuzzing, we show how entropy also measures fuzzer efficiency. Specifically, it measures the general rate at which the fuzzer discovers new behaviors. Intuitively, efficient fuzzers maximize information. From this information theoretic perspective, we develop ENTROPIC, an entropy-based power schedule for greybox fuzzing that assigns more energy to seeds that maximize information. We implemented ENTROPIC into the popular greybox fuzzer LIBFUZZER. Our experiments with more than 250 open-source programs (60 million LoC) demonstrate a substantially improved efficiency and confirm our hypothesis that an efficient fuzzer maximizes information. ENTROPIC has been independently evaluated and integrated into the main-line LIBFUZZER as the default power schedule. ENTROPIC now runs on more than 25,000 machines fuzzing hundreds of security-critical software systems simultaneously and continuously.

Automated and Efficient Test-Generation for Grid-Based Multiagent Systems

Automatic generation of random test inputs is an approach that can alleviate the challenges of manual test case design. However, random test cases may be ineffective in fault detection and increase testing cost, especially in systems where test execution is resource- and time-consuming. To remedy this, the domain knowledge of test engineers can be exploited to select potentially effective test cases. To this end, test selection constraints suggested by domain experts can be utilized either for filtering randomly generated test inputs or for direct generation of inputs using constraint solvers. In this paper, we propose a domain specific language (DSL) for formalizing locality-based test selection constraints of autonomous agents and discuss the impact of test selection filters, specified in our DSL, on randomly generated test cases. We study and compare the performance of filtering and constraint solving approaches in generating selective test cases for different test scenario parameters and discuss the role of these parameters in test generation performance. Through our study, we provide criteria for suitability of the random data filtering approach versus the constraint solving one under the varying size and complexity of our testing problem. We formulate the corresponding research questions and answer them by designing and conducting experiments using QuickCheck for random test data generation with filtering and Z3 for constraint solving. Our observations and statistical analysis indicate that applying filters can significantly improve test efficiency of randomly generated test cases. Furthermore, we observe that test scenario parameters affect the performance of the filtering and constraint solving approaches differently. In particular, our results indicate that the two approaches have complementary strengths: random generation and filtering works best for large agent numbers and long paths, while its performance degrades in the larger grid sizes and more strict constraints. On the contrary, constraint solving has a robust performance for large grid sizes and strict constraints, while its performance degrades with more agents and long paths.

Fault localization in DSLTrans model transformations by combining symbolic execution and spectrum-based analysis

The verification of model transformations is important for realizing robust model-driven engineering technologies and quality-assured automation. Many approaches for checking properties of model transformations have been proposed. Most of them have focused on the effective and efficient detection of property violations by contract checking. However, there remains the fault localization step between identifying a failing contract for a transformation based on verification feedback and precisely identifying the faulty rules. While there exist fault localization approaches in the model transformation verification literature, these require the creation and maintenance of test cases, which imposes an additional burden on the developer. In this paper, we combine transformation verification based on symbolic execution with spectrum-based fault localization techniques for identifying the faulty rules in DSLTrans model transformations. This fault localization approach operates on the path condition output of symbolic transformation checkers instead of requiring a set of test input models. In particular, we introduce a workflow for running the symbolic execution of a model transformation, evaluating the defined contracts for satisfaction, and computing different measures for tracking the faulty rules. We evaluate the effectiveness of spectrum-based analysis techniques for tracking faulty rules and compare our approach to previous works. We evaluate our technique by introducing known mutations into five model transformations. Our results show that the best spectrum-based analysis techniques allow for effective fault localization, showing an average EXAM score below 0.30 (less than 30% of the transformation needs to be inspected). These techniques are also able to locate the faulty rule in the top-three ranked rules in 70% of all cases. The impact of the model transformation, the type of mutation and the type of contract on the results is discussed. Finally, we also investigate the cases where the technique does not work properly, including discussion of a potential pre-check to estimate the prospects of the technique for a certain transformation.

Clinical interpretation of cell-based non-invasive prenatal testing for monogenic disorders including repeat expansion disorders: potentials and pitfalls.

Introduction: Circulating fetal cells isolated from maternal blood can be used for prenatal testing, representing a safe alternative to invasive testing. The present study investigated the potential of cell-based noninvasive prenatal testing (NIPT) for diagnosing monogenic disorders dependent on the mode of inheritance. Methods: Maternal blood samples were collected from women opting for prenatal diagnostics for specific monogenic disorders (N = 7). Fetal trophoblasts were enriched and stained using magnetic activated cell sorting and isolated by fluorescens activated single-cell sorting. Individual cells were subject to whole genome amplification, and cells of fetal origin were identified by DNA-profiling using short tandem repeat markers. The amplified fetal DNA was input for genetic testing for autosomal dominant-, autosomal recessive-, X-linked and repeat expansion disorders by direct variant analysis and haplotyping. The cell-based NIPT results were compared with those of invasive testing. Results: In two cases at risk of skeletal dysplasia, caused by variants in the FGFR3 gene (autosomal dominant disorders), cell-based NIPT correctly stated an affected fetus, but allelic dropout of the normal alleles were observed in both cases. Cell-based NIPT gave an accurate result in two cases at risk of autosomal recessive disorders, where the parents carried either different diastrophic dysplasia causing variants in the SLC26A2 gene or the same cystic fibrosis disease-causing variant in the CFTR gene. Cell-based NIPT accurately identified an affected male fetus in a pregnancy at risk of Duchenne muscular dystrophy (DMD gene, X-linked recessive disorders). In two cases at risk of the myotonic dystrophy type 1 (DMPK gene, repeat expansion disorder), cell-based NIPT correctly detected an affected and an unaffected fetus, respectively. Discussion: Circulating fetal cells can be used to detect both maternally- and paternally inherited monogenic disorders irrespective of the type of variant, however, the risk of allelic dropout must be considered. We conclude that the clinical interpretation of the cell-based NIPT result thus varies depending on the disorders' mode of inheritance.

System Identification of Unmanned Air Systems at Texas A&M University

This paper presents a summary of system identification flight testing and results for a variety of large and small fixed-wing and multirotor unmanned air systems at Texas A&M University from 1999 to 2023. The six different types of vehicles range from a large powered parafoil, to a fixed-wing vehicle with synthetic jet-actuated roll control effectors, to a radially asymmetric multirotor, to large and small fixed-wing vehicles, and to a Steppe eagle. The observer/Kalman filter identification algorithm is used to generate linear time-invariant state-space models, and the results for both near-real-time online model generation and postflight offline model generation are presented. The use and efficacy of a variety of test input types and their sensitivity to exogenous inputs such as turbulence, in addition to identified model evaluation and selection criteria, are discussed. Several generations of low size, weight, power, and cost flight-test instrumentation including the Developmental Flight-Test Instrumentation data acquisition package are also presented. Challenges that arose from the flight-testing campaigns along with solutions are highlighted in the paper.

Physics-Guided Adversarial Machine Learning for Aircraft Systems Simulation

In the context of aircraft system performance assessment, deep learning technologies allow us to quickly infer models from experimental measurements, with less detailed system knowledge than usually required by physics-based modeling. However, this inexpensive model development also comes with new challenges regarding model trustworthiness. This article presents a novel approach, physics-guided adversarial machine learning (ML), which improves the confidence over the physics consistency of the model. The approach performs, first, a physics-guided adversarial testing phase to search for test inputs revealing behavioral system inconsistencies, while still falling within the range of foreseeable operational conditions. Then, it proceeds with a physics-informed adversarial training to teach the model the system-related physics domain foreknowledge through iteratively reducing the unwanted output deviations on the previously uncovered counterexamples. Empirical evaluation on two aircraft system performance models shows the effectiveness of our adversarial ML approach in exposing physical inconsistencies of both the models and in improving their propensity to be consistent with physics domain knowledge.