Search results

The Grey System Theory (GST) is an emerging area of research within artificial intelligence. Since its founding in 1982, it has seen a lot of multidisciplinary applications. In just a short period, it has garnered some considerable strengths. Based on the 1987–2021 data collected from the Web of Science (WoS), the current study reports the advancement of the GST.

Research papers utilizing the GST in the fields of economics and education were retrieved from the Web of Science (WoS) platform using a set of predetermined keywords. In the final stage of the process, the papers that underwent analysis were manually chosen, with selection criteria based on the information presented in the titles and abstracts.

The study identifies prominent authors, institutions, publications and journals closely associated with the subject. In terms of authors, two major clusters are identified around Liu SF and Wang ZX, while the institution with the highest number of publications is Nanjing University of Aeronautics and Astronautics. Moreover, significant keywords, trends and research directions have been extracted and analyzed. Additionally, the study highlights the regions where the theory holds substantial influence.

The study is subject to certain limitations stemming from factors such as the language employed in the chosen literature, the papers included within the Web of Science (WoS) database, the designation of works categorized as “articles” in the database, the specific selection of keywords and keyword combinations, and the meticulous manual process employed for paper selection. While the manual selection process itself is not inherently limiting, it demands a greater investment of time and meticulous attention, contributing to the overall limitations of the study.

The significance of the study extends not only to scholars and practitioners but also to readers who observe the development of emerging scientific disciplines.

The analysis of trends revealed a growing emphasis on the application of GST in diverse domains, including supply chain management, manufacturing and economic development. Notably, the emergence of COVID-19 as a new research focal point among GST scholars is evident. The heightened interest in COVID-19 can be attributed to its global impact across various academic disciplines. However, it is improbable that this interest will persist in the long term, as the pandemic is gradually brought under control.

A newly developed frequency-independent lumped parameter model (LPM) is the purpose of the present paper. This new model’s direct outcome ensures high efficiency and a straightforward calculation of foundations’ vertical vibrations. A rigid circular foundation shape resting on a nonhomogeneous half-space subjected to a vertical time-harmonic excitation is considered.

A simple model representing the soil–foundation system consists of a single degree of freedom (SDOF) system incorporating a lumped mass linked to a frequency-independent spring and dashpot. Besides that, an additional fictitious mass is incorporated into the SDOF system. Several numerical methods and mathematical techniques are used to identify each SDOF’s parameter: (1) the vertical component of the static and dynamic foundation impedance function is calculated. This dynamic interaction problem is solved by using a formulation combining the boundary element method and the thin layer method, which allows the simulation of any complex nonhomogeneous half-space configuration. After, one determines the static stiffness’s expression of the circular foundation resting on a nonhomogeneous half-space. (2) The system’s parameters (dashpot coefficient and fictitious mass) are calculated at the resonance frequency; and (3) using a curve fitting technique, the general formulas of the frequency-independent dashpot coefficients and additional fictitious mass are established.

Comparisons with other results from a rigorous formulation were made to verify the developed model’s accuracy; these are exceptional cases of the more general problems that can be addressed (problems like shallow or embedded foundations of arbitrary shape, other vibration modes, etc.).

In this new LPM, the impedance functions will no longer be needed. The engineer only needs a limited number of input parameters (geometrical and mechanical characteristics of the foundation and the soil). Moreover, a simple calculator is required (i.e. we do not need any sophisticated software).

This study establishes a method for predicting ground vibrations caused by railway tunnels in unsaturated soils with spatial variability.

First, an improved 2.5D finite-element-method-perfect-matching-layer (FEM-PML) model is proposed. The Galerkin method is used to derive the finite element expression in the ub-pl-pg format for unsaturated soil. Unlike the ub-v-w format, which has nine degrees of freedom per node, the ub-pl-pg format has only five degrees of freedom per node; this significantly enhances the calculation efficiency. The stretching function of the PML is adopted to handle the unlimited boundary domain. Additionally, the 2.5D FEM-PML model couples the tunnel, vehicle and track structures. Next, the spatial variability of the soil parameters is simulated by random fields using the Monte Carlo method. By incorporating random fields of soil parameters into the 2.5D FEM-PML model, the effect of soil spatial variability on ground vibrations is demonstrated using a case study.

The spatial variability of the soil parameters primarily affected the vibration acceleration amplitude but had a minor effect on its spatial distribution and attenuation over time. In addition, ground vibration acceleration was more affected by the spatial variability of the soil bulk modulus of compressibility than by that of saturation.

Using the 2.5D FEM-PML model in the ub-pl-pg format of unsaturated soil enhances the computational efficiency. On this basis, with the random fields established by Monte Carlo simulation, the model can calculate the reliability of soil dynamics, which was rarely considered by previous models.

Surface roughness has a serious impact on the fatigue strength, wear resistance and life of mechanical products. Realizing the evolution of surface quality through theoretical modeling takes a lot of effort. To predict the surface roughness of milling processing, this paper aims to construct a neural network based on deep learning and data augmentation.

This study proposes a method consisting of three steps. Firstly, the machine tool multisource data acquisition platform is established, which combines sensor monitoring with machine tool communication to collect processing signals. Secondly, the feature parameters are extracted to reduce the interference and improve the model generalization ability. Thirdly, for different expectations, the parameters of the deep belief network (DBN) model are optimized by the tent-SSA algorithm to achieve more accurate roughness classification and regression prediction.

The adaptive synthetic sampling (ADASYN) algorithm can improve the classification prediction accuracy of DBN from 80.67% to 94.23%. After the DBN parameters were optimized by Tent-SSA, the roughness prediction accuracy was significantly improved. For the classification model, the prediction accuracy is improved by 5.77% based on ADASYN optimization. For regression models, different objective functions can be set according to production requirements, such as root-mean-square error (RMSE) or MaxAE, and the error is reduced by more than 40% compared to the original model.

A roughness prediction model based on multiple monitoring signals is proposed, which reduces the dependence on the acquisition of environmental variables and enhances the model's applicability. Furthermore, with the ADASYN algorithm, the Tent-SSA intelligent optimization algorithm is introduced to optimize the hyperparameters of the DBN model and improve the optimization performance.

Identifying the flow regime is a prerequisite for accurately modeling two-phase flow. This paper aims to introduce a comprehensive data-driven workflow for flow regime identification.

A numerical two-phase flow model was validated against experimental data and was used to generate dynamic pressure signals for three different flow regimes. First, four distinct methods were used for feature extraction: discrete wavelet transform (DWT), empirical mode decomposition, power spectral density and the time series analysis method. Kernel Fisher discriminant analysis (KFDA) was used to simultaneously perform dimensionality reduction and machine learning (ML) classification for each set of features. Finally, the Shapley additive explanations (SHAP) method was applied to make the workflow explainable.

The results highlighted that the DWT + KFDA method exhibited the highest testing and training accuracy at 95.2% and 88.8%, respectively. Results also include a virtual flow regime map to facilitate the visualization of features in two dimension. Finally, SHAP analysis showed that minimum and maximum values extracted at the fourth and second signal decomposition levels of DWT are the best flow-distinguishing features.

This workflow can be applied to opaque pipes fitted with pressure sensors to achieve flow assurance and automatic monitoring of two-phase flow occurring in many process industries.

This paper presents a novel flow regime identification method by fusing dynamic pressure measurements with ML techniques. The authors’ novel DWT + KFDA method demonstrates superior performance for flow regime identification with explainability.

Automatic modulation recognition (AMR) is a challenging problem in intelligent communication systems and has wide application prospects. At present, although many AMR methods based on deep learning have been proposed, the methods proposed by these works cannot be directly applied to the actual wireless communication scenario, because there are usually two kinds of dilemmas when recognizing the real modulated signal, namely, long sequence and noise. This paper aims to effectively process in-phase quadrature (IQ) sequences of very long signals interfered by noise.

This paper proposes a general model for a modulation classifier based on a two-layer nested structure of long short-term memory (LSTM) networks, called a two-layer nested structure (TLN)-LSTM, which exploits the time sensitivity of LSTM and the ability of the nested network structure to extract more features, and can achieve effective processing of ultra-long signal IQ sequences collected from real wireless communication scenarios that are interfered by noise.

Experimental results show that our proposed model has higher recognition accuracy for five types of modulation signals, including amplitude modulation, frequency modulation, gaussian minimum shift keying, quadrature phase shift keying and differential quadrature phase shift keying, collected from real wireless communication scenarios. The overall classification accuracy of the proposed model for these signals can reach 73.11%, compared with 40.84% for the baseline model. Moreover, this model can also achieve high classification performance for analog signals with the same modulation method in the public data set HKDD_AMC36.

At present, although many AMR methods based on deep learning have been proposed, these works are based on the model’s classification results of various modulated signals in the AMR public data set to evaluate the signal recognition performance of the proposed method rather than collecting real modulated signals for identification in actual wireless communication scenarios. The methods proposed in these works cannot be directly applied to actual wireless communication scenarios. Therefore, this paper proposes a new AMR method, dedicated to the effective processing of the collected ultra-long signal IQ sequences that are interfered by noise.

Recognizing construction workers' activities is critical for on-site performance and safety management. Thus, this study presents the potential of automatically recognizing construction workers' actions from activations of the erector spinae muscles.

A lab study was conducted wherein the participants (n = 10) performed rebar task, which involved placing and tying subtasks, with and without a wearable robot (exoskeleton). Trunk muscle activations for both conditions were trained with nine well-established supervised machine learning algorithms. Hold-out validation was carried out, and the performance of the models was evaluated using accuracy, precision, recall and F1 score.

Results indicate that classification models performed well for both experimental conditions with support vector machine, achieving the highest accuracy of 83.8% for the “exoskeleton” condition and 74.1% for the “without exoskeleton” condition.

The study paves the way for the development of smart wearable robotic technology which can augment itself based on the tasks performed by the construction workers.

This study contributes to the research on construction workers' action recognition using trunk muscle activity. Most of the human actions are largely performed with hands, and the advancements in ergonomic research have provided evidence for relationship between trunk muscles and the movements of hands. This relationship has not been explored for action recognition of construction workers, which is a gap in literature that this study attempts to address.

Gas insulated systems, such as gas insulated lines (GIL), use insulating gas, mostly sulfur hexalfluoride (SF₆), to enable a higher dielectric strength compared to e.g. air. However, under high voltage direct current conditions, charge accumulation and electric field stress may occur, which may lead to partial discharge or system failure. Therefore, numerical simulations are used to design the system and determine the electric field and charge distribution. Although the gas conduction shows a more complex current–voltage characteristic compared to solid insulation, the electric conductivity of the SF₆ gas is set as constant in most works. The purpose of this study is to investigate different approaches to address the conduction in the gas properly for numerical simulations.

In this work, two approaches are investigated to address the conduction in the insulating gas and are compared to each other. One method is an ion-drift-diffusion model, where the conduction in the gas is described by the ion motion in the SF₆ gas. However, this method is computationally expensive. Alternatively, a less complex approach is an electro-thermal model with the application of an electric conductivity model for the SF₆ gas. Measurements show that the electric conductivity in the SF₆ gas has a nonlinear dependency on temperature, electric field and gas pressure. From these measurements, an electric conductivity model was developed. Both methods are compared by simulation results, where different parameters and conditions are considered, to investigate the potential of the electric conductivity model as a computationally less expensive alternative.

The simulation results of both simulation approaches show similar results, proving the electric conductivity for the SF₆ gas as a valid alternative. Using the electro-thermal model approach with the application of the electric conductivity model enables a solution time up to six times faster compared to the ion-drift-diffusion model. The application of the model allows to examine the influence of different parameters such as temperature and gas pressure on the electric field distribution in the GIL, whereas the ion-drift-diffusion model enables to investigate the distribution of homo- and heteropolar charges in the insulation gas.

This work presents numerical simulation models for high voltage direct current GIL, where the conduction in the SF₆ gas is described more precisely compared to a definition of a constant electric conductivity value for the insulation gas. The electric conductivity model for the SF₆ gas allows for consideration of the current–voltage characteristics of the gas, is computationally less expensive compared to an ion-drift diffusion model and needs considerably less solution time.

This paper investigates the impact of investor attention on the COVID-19 concept stocks in China's stock market from the perspectives of the macroeconomy, the stock market and the COVID-19 pandemic.

On the basis of controlling the time effects and individual fixed effects, this paper studies the impact of investor attention on the COVID-19 concept stocks in China's stock market through a set of fixed effect panel data models. Among them, investor attention focuses on macroeconomy, stock market and the COVID-19 pandemic, respectively, while stock indicators cover return, volatility and turnover. In addition, this paper also examines the heterogeneity influence of investor attention on the COVID-19 concept stocks from the perspective of time and stock classification.

Findings indicate that the attention to macroeconomy does not have a statistically significant effect on the return, unlike the attention to stock market and COVID-19 incident. Three types of investor attention have significant positive effects on the volatility and turnover rate. During the outbreak of the domestic epidemic, the impact of investor attention was significantly higher than that during the outbreak of the epidemic overseas. A finer-grained analysis shows that the attention to stock market has significantly increased the return of preventive type and treatment type stocks, while diagnostic-related stocks have been most affected by the attention to COVID-19 incident.

The major limitation of this work is the construction of investor attention. Although Baidu index is widely used, investor attention can be assessed more accurately based on more unstructured data. In addition, the effect of the COVID-19 can also be investigated in a longer time domain. Further research can be combined with the dynamics of the COVID-19 pandemic to more comprehensively evaluate its impact on the stock market.

The research proves that investor attention plays an important role in stock pricing and provides empirical evidence on the behavioral foundations of the conceptual sector of the stock market under uncertainty. It also has practical implications for regulators and investors interested in conducting accurate asset allocation and risk assessment.

Software defect prediction (SDP) is a critical aspect of software quality assurance, aiming to identify and manage potential defects in software systems. In this paper, we have proposed a novel hybrid approach that combines Gray Wolf Optimization with Feature Selection (GWOFS) and multilayer perceptron (MLP) for SDP. The GWOFS-MLP hybrid model is designed to optimize feature selection, ultimately enhancing the accuracy and efficiency of SDP. Gray Wolf Optimization, inspired by the social hierarchy and hunting behavior of gray wolves, is employed to select a subset of relevant features from an extensive pool of potential predictors. This study investigates the key challenges that traditional SDP approaches encounter and proposes promising solutions to overcome time complexity and the curse of the dimensionality reduction problem.

The integration of GWOFS and MLP results in a robust hybrid model that can adapt to diverse software datasets. This feature selection process harnesses the cooperative hunting behavior of wolves, allowing for the exploration of critical feature combinations. The selected features are then fed into an MLP, a powerful artificial neural network (ANN) known for its capability to learn intricate patterns within software metrics. MLP serves as the predictive engine, utilizing the curated feature set to model and classify software defects accurately.

The performance evaluation of the GWOFS-MLP hybrid model on a real-world software defect dataset demonstrates its effectiveness. The model achieves a remarkable training accuracy of 97.69% and a testing accuracy of 97.99%. Additionally, the receiver operating characteristic area under the curve (ROC-AUC) score of 0.89 highlights the model’s ability to discriminate between defective and defect-free software components.

Experimental implementations using machine learning-based techniques with feature reduction are conducted to validate the proposed solutions. The goal is to enhance SDP’s accuracy, relevance and efficiency, ultimately improving software quality assurance processes. The confusion matrix further illustrates the model’s performance, with only a small number of false positives and false negatives.