Narrow Results

Due to the rapid advancement of computational power and the Internet of Things (IoT) together with recent developments in digital-twin and cyber-physical systems, the integration of big data analytics techniques (BDAT) (e.g., data mining, machine learning (ML), deep learning, data farming, etc.) into traditional simulation methodologies, along with the enhancement of past simulation optimization techniques, has given rise to an emerging field known as simulation learning and optimization (SLO). Unlike simulation optimization, SLO is a data-driven fusion approach that integrates conventional simulation modeling methodologies, simulation optimization techniques, and learning-based big data analytics (BDA) to enhance the ability to address stochastic and dynamic decision-making problems in the real-world complex system and quickly find the best outcomes for the decision support in both real-time and nonreal-time analyses to achieve the data-driven digital twin capability. Although some literature in the past has mentioned similar applications and concepts, no paper provides a structural explanation and comprehensive review of relevant literature on SLO from both methodological and applied perspectives. Consequently, in the first part of this paper, we conduct a literature review on a novel SLO methodology emerging from the fusion of traditional simulation methodology, simulation optimization algorithms, and BDAT. In the second part of this paper, we review the applications of SLO in various contexts, with detailed discussions on manufacturing, maintenance, redundancy allocation, hybrid energy systems, humanitarian logistics, and healthcare systems. Lastly, we investigate potential research directions for SLO in this new era of big data and artificial intelligence (AI).

The current pension financial system faces multiple risks, including market risk, credit risk, and liquidity risk. Traditional risk assessment methods are difficult to capture these risks comprehensively and dynamically. Therefore, through literature review and expert consultation, this study systematically established a set of early warning index system covering macroeconomic environment, financial market conditions, operation conditions of pension financial institutions and policy environment. The system aims to comprehensively reflect the risk factors faced by the pension financial system and provide a solid data basis for subsequent risk early warning. This paper introduces fuzzy neural network (FNN) as the core algorithm, and uses its powerful nonlinear mapping ability and fuzzy information processing ability to build a risk warning model of pension financial system. In this paper, the model is trained and verified by combining historical data with simulation data. The results show that the risk early warning model of the pension financial system based on FNN can accurately identify the potential risks in the pension financial system, and the model has better stability.

Events featuring high energy jets and a large amount of missing transverse energy constitute a key signature for a wide spectrum of new physics models. In this review, the results of two searches with such signatures are presented. The benefits of performing these searches in a model-independent way are discussed and data-driven techniques used to estimate Standard Model backgrounds are described in detail. These data-driven techniques will be an important part of searches for new physics at the LHC, especially in the early data-taking period.

This study explores the implementation of the nonlinear autoregressive Volterra (NARV) model using a field programmable gate arrays (FPGAs)-based hardware simulation platform and accomplishes the identification process of the Hodgkin–Huxley (HH) model. First, a physiological detailed single-compartment HH model is applied to generate experiment data sets and the electrical behavior of neurons are described by the membrane potential. Then, based on the injected input current and the output membrane potential, a second-order NARV model is constructed and implemented on FPGA-based simulation platforms. The NARV modeling method is data-driven, requiring no accurate physiological information and the FPGA-based hardware simulation can provide a real time and high-performance platform to deal with the drawbacks of software simulation. Therefore, the proposed method in this paper is capable of handling the nonlinearities and uncertainties in nonlinear neural systems and may help promote the development of clinical treatment devices.

The recently emerged data-driven dynamic mode decomposition (DMD) method was employed to investigate the free surface sloshing dynamics of a partially filled rigid tank excited by horizontal harmonic motions. The volume of fluid algorithm was adopted for liquid–gas free surface tracking, and DMD was utilized for decomposition with physical interpretations of the DMD modes and the eigenvalues. Our results demonstrate that DMD works well for both data reconstruction and future-state prediction in terms of either free surface profiles or the sloshing pressure exerted on the rigid wall. DMD presents an efficient and versatile approach for accelerated reduced-order modeling and future-state forecasting. Our efforts provide the first reference on use of DMD for free surface sloshing problems to the best knowledge of the authors. We publicly share our data and codes for all the implementation.

This paper aims to recognize driving risks in individual vehicles online based on a data-driven methodology. Existing advanced driver assistance systems (ADAS) have difficulties in effectively processing multi-source heterogeneous driving data. Furthermore, parameters adopted for evaluating the driving risk are limited in these systems. The approach of data-driven modeling is investigated in this study for utilizing the accumulation of on-road driving data. A recognition model of driving risk based on belief rule-base (BRB) methodology is built, predicting driving safety as a function of driver characteristics, vehicle state and road environment conditions. The BRB model was calibrated and validated using on-road data from 30 drivers. The test results show that the recognition accuracy of our proposed model can reach about 90% in all situations with three levels (none, medium, large) of driving risks. Furthermore, the proposed simplified model, which provides real-time operation, is implemented in a vehicle driving simulator as a reference for future ADAS and belongs to research on artificial intelligence (AI) in the automotive field.

Accurate prediction of train delay recovery is critical for railway incident management and providing passengers with accurate journey time. In this paper, a two-stage prediction model is proposed to predict the recovery time of train primary-delay based on the real records from High-Speed Railway (HSR). In Stage 1, two models are built to study the influence of feature space and model framework on the prediction accuracy of buffer time in each section or station. It is found that explicitly inputting the attribute features of stations and sections to the model, instead of implicit simulation, will improve the prediction accuracy effectively. For validation purpose, the proposed model has been compared with several alternative models, namely, Logistic Regression (LR), Artificial Neutral Network (ANN), Support Vector Machine (SVM) and Gradient Boosting Tree (GBT). The results show that its remarkable performance is better than other schemes. Specifically, when the error is extended to 3min, the proposed model can achieve up to the accuracy of 94.63%. It proves that our method has high value in practical engineering application. Considering the delay propagation of trains is a complex process, our future study will focus on building delay propagation knowledge base and dispatcher experience knowledge base.

Traditional physics-based mathematical models of viscoelastic (VE) damper often exhibit different degrees of prediction errors under complex working conditions, whereas data-driven approaches have shown significant potential for overcoming such problems, and have not been introduced into any study to describe the dynamic mechanical properties of VE damper. In this paper, the architecture of microsphere model is adopted to represent the spatial distribution of molecular chain structure of VE damping material, which is categorized into free chains and elastic chains. Then, the physics-informed neural network surrogates are introduced to describe the statistical stress–strain behaviors of free chains and elastic chains. Finally, by constructing the physics-constrained loss function based on the combination of physics-based model and data-driven model, a physics-constrained data-driven model is proposed to characterize the dynamic mechanical behaviors of VE damper used for structure vibration control. Based on the existing experimental data, the prediction ability and robustness of the proposed model are comparatively verified, the results reveal that the proposed model can accurately reflect the stiffness and energy dissipation of VE damper under different ambient temperatures, excitation frequencies, and deformation conditions. This study proves the potential of physics-informed neural network theory in characterizing the complex mechanical behaviors of VE damper.

The construction of electronic government (e-government) systems is a process of continuous improvement. It is necessary to evaluate the performance of e-government systems regularly to improve the services provided by government agencies and enhance the exchange of information between governments and citizens. Evaluating e-government performance based on citizens’ experience is a multiple criterion decision making (MCDM) problem under uncertainty, where assessments are qualitative, and many e-government system users are involved. Deriving criterion weights from a large amount of evaluation data is rarely discussed in previous MCDM studies. This paper proposes a data-driven evidential reasoning (DDER) method for evaluating e-government performance. A criteria framework from the citizens’ experience perspective, including service guide clarity, site usability, information sharing, documentation, and the availability of e-services, is proposed. Belief structures are used to portray uncertain assessments from e-government system users. The criterion weights are learned from the data by minimizing the dissimilarity between the aggregation assessments of the alternatives on each criterion and citizens’ historical observations on a whole. A case study is conducted in 16 cities of Anhui province in China to evaluate the performance of e-government systems. The ranking results verified the applicability and effectiveness of the proposed method.

Risk assessment analysis for investment decisions largely depends on expert judgment using traditional approaches and is lacking in considering investors’ different preferences and limitations. This paper proposes an adaptive personalized property investment risk analysis (APPIRA) method to identify the property investment determinants using a data-driven and personalized approach to weight the risk factors using the multicriteria decision model for optimal solutions. Result for predictive modeling using value prediction technique that measures the median house price depicts that the best method used was nonseasonal ARIMA. Furthermore, classification technique indicates that in each of the three selected suburbs, different property characteristics determined the rental properties desirable. As shown in result, for the investors who plan to invest in property for rental purposes, they need to choose townhouse type or property to make it rentable while for Vaucluse, terrace houses. These results can be applied into practice and will benefit the property industry directly.

The diverse nature of cerebral activity, as measured using neuroimaging techniques, has been recognised long ago. It seems obvious that using single modality recordings can be limited when it comes to capturing its complex nature. Thus, it has been argued that moving to a multimodal approach will allow neuroscientists to better understand the dynamics and structure of this activity. This means that integrating information from different techniques, such as electroencephalography (EEG) and the blood oxygenated level dependent (BOLD) signal recorded with functional magnetic resonance imaging (fMRI), represents an important methodological challenge. In this work, we review the work that has been done thus far to derive EEG/fMRI integration approaches. This leads us to inspect the conditions under which such an integration approach could work or fail, and to disclose the types of scientific questions one could (and could not) hope to answer with it.

A major goal of personalized anti-cancer therapy is to increase the drug effects while reducing the side effects as much as possible. A novel therapeutic strategy called synthetic lethality (SL) provides a great opportunity to achieve this goal. SL arises if mutations of both genes lead to cell death while mutation of either single gene does not. Hence, the SL partner of a gene mutated only in cancer cells could be a promising drug target, and the identification of SL pairs of genes is of great significance in pharmaceutical industry. In this paper, we propose a hybridized method to predict SL pairs of genes. We combine a data-driven model with knowledge of signalling pathways to simulate the influence of single gene knock-down and double genes knock-down to cell death. A pair of genes is considered as an SL candidate when double knock-down increases the probability of cell death significantly, but single knock-down does not. The single gene knock-down is confirmed according to the human essential genes database. Our validation against literatures shows that the predicted SL candidates agree well with wet-lab experiments. A few novel reliable SL candidates are also predicted by our model.

Inhomogeneous materials are characterized by uneven material properties with changing dimensions. Effective and precise identification of nonuniform material properties is essential for studying material inhomogeneity. In this study, we propose a hybrid physics-informed neural network (PINN) to identify the inhomogeneous thermal diffusivity only using temperature data collected in a transient heat conduction problem. A PINN and a fully connected neural network are combined in the proposed model. The PINN model is trained to learn the law of physics governed by the transient heat conduction equation. The identification network is trained to uncover the thermal diffusivity variation with changing dimensions. The proposed model successfully identifies two types of inhomogeneity: temperature-dependent and space-dependent thermal diffusivity, and both two-dimensional and three-dimensional heat conduction problems are investigated. The proposed model is examined to be robust to small datasets and noisy training data. In addition to heat conduction problems, the proposed model can be adopted to identify the material properties of various types of inhomogeneous materials.

Assembly simulations such as assembly process simulation and assembly tolerance simulation have become an effective means to evaluate and analyze product assembly design and assembly process planning. Being core aspect of simulation implementation, building an assembly simulation model is rather time-consuming because of its high complexity. Furthermore, modeling has a significant influence on the popularization and application of simulation technology. In this paper, data needed by assembly process and tolerance simulation are addressed to propose a data-driven approach for assembly simulation modeling. The application process and the architecture of modeling framework for assembly simulation are presented as well. An assembly sequence simulation example is given to illustrate the application of the framework. The framework provides a new idea for the realization of automatic modeling for assembly simulation.

Dimensional variation analysis in multistation manufacturing processes (MMPs) is a challenging research topic with great practical significance. Researchers have been focused on constructing various mathematical models to identify the correlations among the huge amounts of collected production data. However, current models have achieved insufficient insights into the variation correlation laws due to the complexity of the data’s mutual relations. In this study, a data-driven modeling method is developed for deep data-mining and dimensional variation analysis. The proposed initial mathematical expression originates from practical engineering knowledge. Through a mathematical treatment, the mathematical expression is transformed into a first-order AR(1) model format, which contains multiple dimensional variations’ interstation and temporal correlating information. To obtain this information, the estimation of the proposed model is discussed in detail. A simulation case involving two key product characteristics of a grinding process is used to demonstrate the effectiveness and accuracy of the proposed method for dimensional variation analysis in MMPs.

The factors that affect the performance of the equipment are numerous and complicated, which makes it difficult to establish a performance calculation model. This paper puts forward a data-driven modeling method with reverse process for this problem. Based on the partial least squares (PLS) algorithm and the gray relational analysis (GRA) method, the analysis method of the performance related factors, the extraction method of characteristic variables, and the performance modeling method are studied. The related factors of the energy consumption of an industrial steam turbine are analyzed, and an energy consumption calculation model is established, and the effectiveness of the above-mentioned modeling methods is verified with sample data, which provides a basis for the energy-saving optimization of the steam turbine.

The Fourth Industrial Revolution, marked by emerging/disruptive technologies like mobile internet, big data, robotics, artificial intelligence (AI), immersive media (VR/AR/MR), and the Internet of Things (IoT), is transforming cities and promoting urban development. This paper argues that these technologies foster urban studies and implementation in three pathways: methodology, epistemology, and practice. First, the new data environment offers a foundation for quantitative and objective urban studies, enabling researchers to treat cities as laboratories and conduct city experiments worldwide. Second, emerging technologies are reshaping contemporary urban life and space, promoting the update of urban theories. Third, these technologies are expected to be applied as new elements in the urban planning and design processes to create smart urban spatial forms that cater to contemporary needs. Overall, this paper highlights the potential significance of emerging technologies for urban research and development in terms of research methods and data support, theoretical updates and iterations, and practical urban planning and design.

Business model innovation is crucial for transforming Chinese smart manufacturing listed businesses in light of the local and global double-cycle economic model background. Numerous studies have shown that various factors affecting business model innovation are driven by each other to form multiple complex systems. In this paper, we analyze the driving mechanisms of business model innovation grouping in innovative manufacturing listed companies in a global context by exploring the internal and external factors from the perspective of internal and external drivers. At the same time, the fuzzy set qualitative comparative analysis (fsQCA) method is combined to find and found different abilities to the business model innovation mechanism of innovative manufacturing listed companies.

In the context of Industry 4.0, a large amount of industrial data is collected, which provides a good basis for soft sensing modeling. However, industrial data may have potentially multiple working conditions that make the data vary locally. Therefore, the prediction performance of the global model largely depends on the division of training data and test data. To illustrate this, Gaussian mixture model (GMM) is used for data partitioning, and then training data and test data are obtained proportionally in different partitions. Finally, support vector regression (SVR) and multilayer perceptron (MLP) are built under different training and test data to observe the changes of R², RMSE and MAPE. The results show that model’s performance is largely affected by partitioning, and in order to obtain stable and usable models, data partitioning needs to be reasonably considered.

Decision makers often face a problem to decide to maintain or terminate an existing program with only observational data available. Within the potential outcomes framework, we show the problem could be modelled as a causal inference problem to estimate the conditional average treatment effect of the treatment on the treated (CATT). In this paper, we propose a model with separate Gaussian processes to estimate average treatment effect for the treated group and the control group. We conduct experiments on an empirical case and show that our method could contribute to decision making in the kind of problem described above.