Use Of Simulated Data Research Articles

Pricing Chinese Convertible Bonds with Learning-Based Monte Carlo Simulation Model

In this paper, we explore a novel model for pricing Chinese convertible bonds that seamlessly integrates machine learning techniques with traditional models. The least squares Monte Carlo (LSM) method is effective in handling multiple state variables and complex path dependencies through simple regression analysis. In our approach, we incorporate machine learning techniques, specifically support vector regression (SVR) and random forest (RF). By employing Bayesian optimization to fine-tune the random forest, we achieve improved predictive performance. This integration is designed to enhance the precision and predictive capabilities of convertible bond pricing. Through the use of simulated data and real data from the Chinese convertible bond market, the results demonstrate the superiority of our proposed model over the classic LSM, confirming its effectiveness. The development of a pricing model incorporating machine learning techniques proves particularly effective in addressing the complex pricing system of Chinese convertible bonds. Our study contributes to the body of knowledge on convertible bond pricing and further deepens the application of machine learning in the field in an integrated and supportive manner.

Use of simulated data to explore the application of optical coherence tomography for classifying middle-ear pathologies.

Optical coherence tomography (OCT) vibrometry is a non-invasive tool for functional imaging of the middle ear. It provides spatially resolved vibrational responses and also anatomical images of the same ear. Our objective here was to explore the potential of OCT vibration measurements at the incus, as well as at the umbo, to distinguish among middle-ear disorders. Our approach was to build finite-element models of normal and pathological ears, generate large amounts of synthetic data, and then classify the simulated data into normal and pathological groups using a decision tree based on features extracted from simulated vibration magnitudes. We could distinguish between normal ears and ears with incudomallear joint (IMJ) disarticulation or stapes fixation, with the sensitivity and specificity both being 1.0; distinguish between stapes fixation and IMJ disarticulation with a sensitivity of 0.900 and a specificity of 0.889; and distinguish ears with ISJ disarticulation from normal ears with a sensitivity of 0.784 and a specificity of 0.872. Less extreme pathologies were also simulated. The results suggest that the vibration measurements within the middle ear that can be provided by OCT (e.g., at the incus) may be very valuable for diagnosis.

Robustness of ad hoc microphone clustering using speaker embeddings: evaluation under realistic and challenging scenarios

Speaker embeddings, from the ECAPA-TDNN speaker verification network, were recently introduced as features for the task of clustering microphones in ad hoc arrays. Our previous work demonstrated that, in comparison to signal-based Mod-MFCC features, using speaker embeddings yielded a more robust and logical clustering of the microphones around the sources of interest. This work aims to further establish speaker embeddings as a robust feature for ad hoc microphone clustering by addressing open and additional questions of practical interest, arising from our prior work. Specifically, whereas our initial work made use of simulated data based on shoe-box acoustics models, we now present a more thorough analysis in more realistic settings. Furthermore, we investigate additional important considerations such as the choice of the distance metric used in the fuzzy C-means clustering; the minimal time range across which data need to be aggregated to obtain robust clusters; and the performance of the features in increasingly more challenging situations, and with multiple speakers. We also contrast the results on the basis of several metrics for quantifying the quality of such ad hoc clusters. Results indicate that the speaker embeddings are robust to short inference times, and deliver logical and useful clusters, even when the sources are very close to each other.

Assessing Weak Adhesion in Single Lap Joints Using Lamb Waves and Machine Learning Methods for Structural Health Monitoring

The use of adhesive joints has become increasingly popular in various industries due to their many benefits, such as low weight and good mechanical performance. However, adhesive joints can suffer from defects, one of them being weak adhesion. This defect poses a significant risk to structural integrity and can lead to premature failure, but is hard to detect using existing nondestructive testing methods. Therefore, there is a need for an effective technique that can detect weak adhesion in single-lap joints (SLJ) to prevent failure and assist in maintenance, namely in the framework of structural health monitoring. This paper presents a novel approach utilizing machine learning and Lamb Waves (LW) to determine the level of weak adhesion. Firstly, a numerical model of SLJs with different levels of weak adhesion is created and an original approach is proposed for its validation with data from real samples so that reliable LW data can further be easily generated to train and test any other data-driven algorithm for tackling damage. Secondly, a damage detection method is proposed, based on artificial neural networks and fed with simulated data, to determine the level of damage in SLJs, independent of their location. The results show that the simulation model can be validated with a small set of experimental data, being capable of replicating real damage in SLJs. Additionally, the use of simulated data in the training algorithm can increase the accuracy of the simulation model up to 26% when compared to only considering experimental data. The adopted artificial neural network for detecting weak adhesion emerges as a promising approach, yielding a precision of over 95%. Thus, machine learning and LW data can be used to improve the reliability and accuracy of adhesive bonding quality control, as well function as a technique for structural health monitoring, which can enhance the safety and durability of bonded structures.

Classification and Recognition Method of Non-Cooperative Object Based on Transfer Learning

Classifying and identifying non-cooperative targets plays an important role in space missions in the present age. A micro-Doppler characteristic signal is an effective means to identify the target. In order to better extract the micro-Doppler features of the target in the case of very little experimental data, a pose recognition network based on the theory of transfer learning is proposed. The source domain dataset is constructed of the time–frequency spectrums obtained by short-time Fourier transform of the simulated echo signals. The time–frequency spectrums from experiment are made as target domain. Pre-training and domain adaptation is applied in this work. Finally, the test results demonstrate that the classification accuracy of our pose recognition network based on transfer learning is improved due to the good use of simulation data and the small amount of experimental data.

Dynamics simulation-based deep residual neural networks to detect flexible shafting faults

Use of simulation data is necessary for training fault diagnostic models because there is an insufficient amount of fault data available for intricate supercritical flexible shafting. A hybrid dynamic modelling approach combining finite element and lumped mass techniques was used to construct dynamic models of the system in both normal and fault states. The simulation signals corresponding to each state were obtained through numerical calculations and subsequently compared with the existing literature to ensure the accuracy and validity of the dynamic model. By establishing this foundation, dependable training data can be acquired for fault diagnosis within a system. A deep residual neural network with a multi-scale convolution kernel (MSResNet) was used to conduct fault diagnosis of the flexible shafting. The efficacy of the suggested approach was substantiated through an experimental analysis. The outcomes of this research establish a theoretical foundation for fault diagnosis of flexible shafting in scenarios with an insufficient number of fault samples.

Aeroacoustic Liner Impedance Metamodel from Simulation and Experimental Data Using Probabilistic Learning

To be able to calculate a parameterized aeroacoustic liner impedance, a robust statistical metamodel is constructed as a function of the frequency and of the control parameters that are the percentage of open area and the sound pressure level. This construction is based on the use of simulated data generated with a computationally expensive aeroacoustic model, which translates to a very small training dataset. This means that the learning process has to be used and the probabilistic learning on manifolds algorithm is chosen. Although the aeroacoustic simulation is conducted on a large aeroacoustic computational model, some approximations are introduced, generating model errors that are taken into account by a probability model in the constructed training dataset. This probability model is calibrated using dimensionless experiments available from the open literature. Despite the fact that only a small amount of data is available, a novel statistical metamodel is successfully developed for which the predictions are consistent. This statistical framework allows for exhibiting a confidence region of the parameterized aeroacoustic liner impedance, which gives an information about the level of uncertainties as a function of the frequency and the control parameters.

The integration of forensic accounting and big data technology frameworks for internal fraud mitigation in the banking industry

The purpose of this study is to investigate the integration of forensic accounting and big data technology frameworks in relation to the mitigation of internal fraud risk in the banking industry. This study employed an explanatory research design involving the use of simulated data to mirror the situation in the banking industry. To this end, the big data analytical approach considered is machine learning that involves a neural network with two-layer feed forward, one hidden layer and five hidden neuron layers created to detect the presence of fraud and classify them into two, viz.: fraudulent and non-fraudulent activities. Both the input and output target samples are automatically divided into training, validation, and test datasets, while the confusion matrix is employed to visualise the percentages of correct and incorrect classifications. Furthermore, the clustering of the fraud indicators was also carried out to group them based on their similarities. The results obtained demonstrate the feasibility of neural networks in classifying internal fraud into three levels of risks and fraud detection. This is evidenced in the percentage of correct classification (95%) and misclassification (5%) obtained from the confusion matrix. The model also demonstrates the feasibility of clustering the potential red flags of internal fraud. This study provides an understanding into the attributes of internal fraud and a practical guided approach to implement an integrated forensic accounting and big data technology framework for internal fraud mitigation. The forensic accountant should ensure that the machine learning models are regularly updated with new datasets for automatic classification and clustering analysis. There is still scanty information regarding the integration of forensic accounting and big data technology for mitigation of internal fraud risk in the banking industry. Hence, it is envisaged that this study will contribute to the method, theory and practise of internal fraud mitigation.

Data Teams in Teacher Preparation: Improving Data-Based Instruction in Reading

Data-based instruction (DBI) is a process of collecting and using student progress data to guide decision-making related to intervention intensity and individualization for students with learning disabilities (LD). However, effective DBI requires that teachers have a range of knowledge and skills across multiple domains. Past research has shown that data teams can improve teachers’ use of data for instructional decision-making. This article describes the use of simulated data teams to build capacity for DBI among pre-service teachers in an undergraduate-level university course focused on intensive reading intervention. Three components are described for each weekly data team meeting: (a) mini professional development session (e.g., instruction led by course instructor focused on key DBI knowledge and skills), (b) data chat (e.g., review and discussion of student data), and (c) completion of a weekly team activity and submission. The structure and implementation of this 5-week, multi-component professional learning tool are detailed.

Alternative procedure to verify the H–V diagram after external installations on helicopters

Certification of external installations on helicopters, for modifications for which CS27/29.865 is not applicable, often requires the showing of compliance of paragraph CS XX.79—limiting height-speed envelope—which might imply, ultimately, a certain degree of H–V testing. Due to the implications on safety during the investigation of the H–V curve, a preliminary analytical investigation is advisable, to understand whether H–V test can be drastically reduced. Analytical investigation, though, is usually based on the extensive use of simulation data, based on validated dynamic mathematical models, which are usually not available to the applicant. The authors recently proposed an alternative method, based on the analysis of a set of flight tests, which is meant to assess quantitatively the different phases of the physical/mechanical phenomena related to the emergency maneuver performed by the pilot as a consequence of a power loss, within or in the proximity of the H–V curve. More in details, the analysis of the autorotation phenomenology reveals that the maneuver is made up by different phases and dedicated tests have been proposed to assess each of these phases. The whole test campaign is hence meant to gain a thorough insight of how, and specifically in which part of the maneuver, the external modification could affect the helicopter H–V characteristic. Depending on this substantiation, H–V testing can be avoided or drastically reduced, limiting the investigation to a few meaningful points. The proposed method has been recently assessed on an external basket installation, making use of purposely developed Flight Instrumentation and post-processing tools. More in details, results and conclusions are based on the analysis of static and dynamic flight parameters, acquired with a non-intrusive Flight Test Instrumentation, which monitors and correlates cockpit parameters and flight commands, following a back-to-back approach (i.e., pre- and post-modification). The method demonstrated was witnessed by EASA and found acceptable as an alternative method for showing of compliance to the applicable requirements.

Iterative Landmark-Based Umbrella Sampling (ILBUS) Protocol for Sampling of Conformational Space of Biomolecules.

Computer simulations of biomolecules such as molecular dynamics often suffer from insufficient sampling. Due to limited computational resources, insufficient sampling prevents obtaining proper equilibrium distributions of observed properties. To deal with this problem, we proposed a simulation protocol for efficient resampling of collected off-equilibrium trajectories. These trajectories are utilized for the initial mapping of the conformational space, which is later properly resampled by the introduced Iterative Landmark-Based Umbrella Sampling (ILBUS) method. Reconstruction of static equilibrium properties is achieved by the multistate Bennett acceptance ratio (MBAR) method, which enables efficient use of simulated data. The ILBUS protocol is geometry-based and does not demand any additional collective variable or a dimensional-reduction technique. The only requirement is a set of suitably spaced reference conformations, which serve as landmarks in the mapped conformational space. Additionally, the ILBUS protocol encompasses an iterative process that optimizes the force constant used in the umbrella sampling simulation. Such tuning is an inherent feature of the protocol and does not need to be performed by the user in advance. Furthermore, even the simulations with suboptimal force constants can be used in estimates by MBAR. We demonstrate the feasibility and the performance of this approach in the study of the conformational landscape of the alanine dipeptide, met-enkephalin, and adenylate kinase.

Hybrid Models That Combine Machine Learning and Simulations

Simulation experts are now well acquainted with machine learning (ML) techniques, using them to find patterns in data that can later be turned into rules of a simulation or enabling their simulated entities to adapt and learn. In the other direction, ML experts occasionally make use of simulated data to create controlled experiments in which learning algorithms can be evaluated. In this article, we go beyond these typical uses by focusing on current opportunities that have the potential to bring the two research communities together. These opportunities can be realized in areas where the potential of hybrid ML/simulation methods has not been fully attained yet. Such applications also motivate the development of innovative methods, for example, to combine the accuracy of ML with the interpretability of simulation models. Using select examples from our interdisciplinary team, this article reflects on opportunities in applications and techniques to promote productive conversations across research areas.

Assessing the Validity of Normalizing Aflatoxin B1-Lysine Albumin Adduct Biomarker Measurements to Total Serum Albumin Concentration across Multiple Human Population Studies.

The assessment of aflatoxin B1 (AFB1) exposure using isotope-dilution liquid chromatography-mass spectrometry (LCMS) of AFB1-lysine adducts in human serum albumin (HSA) has proven to be a highly productive strategy for the biomonitoring of AFB1 exposure. To compare samples across different individuals and settings, the conventional practice has involved the normalization of raw AFB1-lysine adduct concentrations (e.g., pg/mL serum or plasma) to the total circulating HSA concentration (e.g., pg/mg HSA). It is hypothesized that this practice corrects for technical error, between-person variance in HSA synthesis or AFB1 metabolism, and other factors. However, the validity of this hypothesis has been largely unexamined by empirical analysis. The objective of this work was to test the concept that HSA normalization of AFB1-lysine adduct concentrations effectively adjusts for biological and technical variance and improves AFB1 internal dose estimates. Using data from AFB1-lysine and HSA measurements in 763 subjects, in combination with regression and Monte Carlo simulation techniques, we found that HSA accounts for essentially none of the between-person variance in HSA-normalized (R2 = 0.04) or raw AFB1-lysine measurements (R2 = 0.0001), and that HSA normalization of AFB1-lysine levels with empirical HSA values does not reduce measurement error any better than does the use of simulated data (n = 20,000). These findings were robust across diverse populations (Guatemala, China, Chile), AFB1 exposures (105 range), HSA assays (dye-binding and immunoassay), and disease states (healthy, gallstones, and gallbladder cancer). HSA normalization results in arithmetic transformation with the addition of technical error from the measurement of HSA. Combined with the added analysis time, cost, and sample consumption, these results suggest that it may be prudent to abandon the practice of normalizing adducts to HSA concentration when measuring any HSA adducts—not only AFB1-lys adducts—when using LCMS in serum/plasma.

NWP calibration applied to Aeolus Mie channel winds

AbstractAeolus is the first Doppler wind lidar (DWL) to measure wind profiles from space. Aeolus is an ESA (European Space Agency) explorer mission with the objective to retrieve winds from the collected atmospheric return signal which is the result of Mie and Rayleigh scattering of laser‐emitted light by atmospheric molecules and particulates. The focus of this paper is on winds retrieved from instrument Mie channel collected data, that is, originating from Mie scattering by atmospheric aerosols and clouds. The use of simulated data from numerical weather prediction (NWP) models is a widely accepted and proven concept for the monitoring of the performance of many meteorological instruments, including Aeolus. Continuous monitoring of Aeolus Mie channel winds against model winds from the European Centre for Medium‐Range Weather Forecasts (ECMWF) has revealed systematic errors in retrieved Mie winds. Following a reverse engineering approach, the systematic errors could be traced back to imperfections of the data in the calibration tables which serve as input for the on‐ground wind processing algorithms. A new algorithm, denoted NWP calibration, makes use of NWP model winds to generate an updated calibration table. It is shown that Mie winds retrieved by making use of the NWP‐based calibration tables show reduced systematic errors, not only when compared to NWP model winds but also when compared to an independent dataset of very‐high‐resolution aircraft wind data. The latter gives high confidence that the NWP‐based calibration algorithm does not introduce model‐related errors into retrieved Aeolus Mie winds. Based on the presented results in this paper, the NWP‐based calibration table, as part of the level‐2B wind processing, has become part of the operational processing chain since 01 July 2021.

Мультиагентная модель многономенклатурного мелкосерийного производства

Production planning is a key aspect when optimizing production activities. Simulation is one of the most effective methods available for assessing production problems. The principles of adaptive planning consist of making day-to-day operational decisions at the shop floor, predicting equipment availability, assessing performance, and eliminating bottlenecks. Existing research to eliminate bottlenecks has focused on analyzing data from the physical shop, or vice versa, only on the use of simulated data. Convergence between real and simulated data allows, on the one hand, to obtain more information to predict the availability of each workplace, on the other hand, it allows performance assessment for replanning using a simulation model. Aim. Development of optimization tools for production planning using simulation approaches. Materials and methods. This article presents a multi-agent simulation model for each workplace in the workshop, examines the workload of the workshop, and evaluates the productivity of workplaces. Optimization is proposed for optimal utilization of production facilities. As an example illustrating the efficiency and advantage of the proposed model, we took the production process of electronic equipment in the assembly shop. Results. A planning problem and an approach to optimization are formulated. A multi-agent model of multinomenclature small-scale production has been developed. The model provides for the integration of simulation tools with operational planning systems at the data level. Conclusion. The model proposed in the study allows small-scale production to plan the number of jobs and identify bottlenecks in production. The use of a combination of simulation and planning tools ensures enterprise resource management, taking into account dynamic changes in the system.

Parallel Mode Differential Phase Contrast in Transmission Electron Microscopy, II: K2CuF4 Phase Transition

AbstractIn Part I of this diptych, we outlined the theory and an analysis methodology for quantitative phase recovery from real-space distortions of Fresnel images acquired in the parallel mode of transmission electron microscopy (TEM). In that work, the properties of the method, termed TEM-differential phase contrast (TEM-DPC), were highlighted through the use of simulated data. In this work, we explore the use of the TEM-DPC technique with experimental cryo-TEM images of a thin lamella of a low-temperature two-dimensional (2D) ferromagnetic material, K2CuF4, to perform two tasks. First, using images recorded below the ordering temperature, we compare the TEM-DPC method with the transport of intensity one for phase recovery and discuss the relative advantages the former has for experimental data. Second, by tracking the induction of the sample as it is driven through a phase transition by heating, we extract estimates for the critical temperature and critical exponent of the order parameter. The value of the latter is consistent with the 2D XY class, raising the prospect that a Kosterlitz–Thoules transition may have occurred.

Optimizing the classification ability of CNN for SAR fully polarized radar data based on DCGAN

In recent years, the deep learning network is widely used. In the field of remote sensing images, due to the high cost of image acquisition, there are still too few training samples, which greatly limits the application of deep learning in SAR data classification. This paper proposes a method that is generating simulated SAR image by generative adversarial network, and uses the image as the training data of convolutional neural network. Aiming at the impact of the simulated images generated by DCGAN’s generator on the classification of convolutional neural networks. The results show that DCGAN can fully extract the main features of the image, and the convolution model based on DCGAN can make CNN have better classification ability and get rid of the dependence on the sample size. CNN can also make full use of simulation data. Whether it is test data set or random dataset, its F1 score can obviously surpass the classification ability without DCGAN’s simulated data. In experiments with different sample numbers, the highest F1 score is 93.6479 in the dataset with DCGAN’s simulated data. In another experiment, its F1 Score reached 87.32, higher than the dataset without DCGAN’s simulated data.

Assessment and Adjustment of Approximate Inference Algorithms Using the Law of Total Variance

A common method for assessing validity of Bayesian sampling or approximate inference methods makes use of simulated data replicates for parameters drawn from the prior. Under continuity assumptions, quantiles of functions of the simulated parameter values for corresponding posterior distributions are uniformly distributed. Checking for uniformity when a posterior density is approximated numerically provides a diagnostic for algorithm validity. Furthermore, adjustments to achieve uniformity can improve the quality of approximate inference methods. The present article develops a moment-based alternative to the conventional checking and adjustment methods using quantiles. The new approach relates prior and posterior expectations and covariances through the tower property of conditional expectation and the law of total variance. For adjustment, approximate inferences are modified so that the correct prior to posterior relationships hold. We illustrate the method in three examples. The first uses an auxiliary model in a likelihood-free inference problem. The second considers corrections for variational Bayes approximations in a deep neural network generalized linear mixed model. Our final application considers a deep neural network surrogate for approximating Gaussian process regression predictive inference. Supplementary files for this article are available online.

SomatoSim: precision simulation of somatic single nucleotide variants

BackgroundSomatic single nucleotide variants have gained increased attention because of their role in cancer development and the widespread use of high-throughput sequencing techniques. The necessity to accurately identify these variants in sequencing data has led to a proliferation of somatic variant calling tools. Additionally, the use of simulated data to assess the performance of these tools has become common practice, as there is no gold standard dataset for benchmarking performance. However, many existing somatic variant simulation tools are limited because they rely on generating entirely synthetic reads derived from a reference genome or because they do not allow for the precise customizability that would enable a more focused understanding of single nucleotide variant calling performance.ResultsSomatoSim is a tool that lets users simulate somatic single nucleotide variants in sequence alignment map (SAM/BAM) files with full control of the specific variant positions, number of variants, variant allele fractions, depth of coverage, read quality, and base quality, among other parameters. SomatoSim accomplishes this through a three-stage process: variant selection, where candidate positions are selected for simulation, variant simulation, where reads are selected and mutated, and variant evaluation, where SomatoSim summarizes the simulation results.ConclusionsSomatoSim is a user-friendly tool that offers a high level of customizability for simulating somatic single nucleotide variants. SomatoSim is available at https://github.com/BieseckerLab/SomatoSim.

A note on an extreme left skewed unit distribution: Theory, modelling and data fitting

Abstract In probability and statistics, unit distributions are used to model proportions, rates, and percentages, among other things. This paper is about a new one-parameter unit distribution, whose probability density function is defined by an original ratio of power and logarithmic functions. This function has a wide range of J shapes, some of which are more angular than others. In this sense, the proposed distribution can be thought of as an “extremely left skewed alternative” to the traditional power distribution. We discuss its main characteristics, including other features of the probability density function, some stochastic order results, the closed-form expression of the cumulative distribution function involving special integral functions, the quantile and hazard rate functions, simple expressions for the ordinary moments, skewness, kurtosis, moments generating function, incomplete moments, logarithmic moments and logarithmically weighted moments. Subsequently, a simple example of an application is given by the use of simulated data, with fair comparison to the power model supported by numerical and graphical illustrations. A new modelling strategy beyond the unit domain is also proposed and developed, with an application to a survival times data set.