Multilayer Network Model Research Articles

Estimation of monthly sunshine duration using satellite derived cloud data

Sunshine duration (SD) is one of the critical meteorological parameters used in different fields of application such as climate, renewable energy and agriculture. In this respect, determination and/or estimation of the temporal and spatial variability of SD is critical. Meteorological satellite data/products can be used for estimating SD and in constructing their maps due to their frequent observation of large areas at once. In this study, a multilayer perceptron type artificial neural network model was built to estimate the monthly mean SD for Türkiye using the EUMETSAT CM SAF (Satellite Application Facility on Climate Monitoring) CFC (Cloud Fractional Coverage) and CTY (Cloud Type) data, GMTED2010 (Global Multi-resolution Terrain Elevation Data) data, month number and daylength. The datasets of 45 stations, spanning nine years (2005–2013), were used for training the model and 12 stations for testing and validating the simulated values. We have compared the results of our model with the ground-measured values for the whole period under consideration and the root mean square error (RMSE), mean absolute error (MAE), mean bias error (MBE) and the coefficient of determination (R2) were found as 0.7803 h, 0.6206 h, 0.1751 h and 0.9387, respectively. It has been shown that using the new generation cloud products such as CFC and CTY, elevation data such as GMTED2010 and daylength, it is possible to predict the SD for regions under the coverage of the satellite, in case no measurement is possible or may be unreliable, without needing any measured meteorological data.

Investigating the rheological characteristics of alkali-activated concrete using contemporary artificial intelligence approaches

Abstract Using artificial intelligence-based tools, this research aims to establish a direct correlation between the alkali-activated concrete (AAC) mix design factors and their performances. More specifically, the machine learning system was fed new property data obtained from AAC mixes used in laboratory experiments. The rheological parameters (yield stress [static/dynamic] and plastic viscosity) of AAC were predicted using the multilayer perceptron neural network (MLPNN) and bagging ensemble (BE) models. In addition, the R 2 values, k-fold analyses, statistical checks, and the dissimilarity between the experimental and predicted compressive strength were employed to assess the performance of the created models. Also, the SHapley additive exPlanation (SHAP) approach was used for examining the relevance of influencing parameters. The BE approach was found to be significantly accurate in all prediction models, with R 2 greater than 0.90, and MLPNN models were found to be moderately precise, with R 2 slightly below 0.90. However, the error assessment through statistical checks and k-fold analysis also validated the higher precision of BE models over the MLPNN models. Building models that can calculate rheological properties of AAC for different values of input parameters could save a lot of time and money compared to doing the tests in a laboratory. In order to ascertain the required amounts of raw materials of AAC, investigators, as well as businesses, may find the SHAP study helpful.

Emerging Vanadium-Doped Cobalt Chloride Carbonate Hydroxide for Flexible Electrochromic Micro-Supercapacitor: Charged-State Prediction from RGB Input by ANN Model.

Multifunctional devices integrated with electrochromic and supercapacitance properties are fascinating because of their extensive usage in modern electronic applications. In this work, vanadium-doped cobalt chloride carbonate hydroxide hydrate nanostructures (V-C3H NSs) are successfully synthesized and show unique electrochromic and supercapacitor properties. The V-C3H NSs material exhibits a high specific capacitance of 1219.9Fg-1 at 1mVs-1 with a capacitance retention of 100% over 30000 CV cycles. The electrochromic performance of the V-C3H NSs material is confirmed through in situ spectroelectrochemical measurements, where the switching time, coloration efficiency (CE), and optical modulation (∆T) are found to be 15.7 and 18.8s, 65.85cm2C-1 and 69%, respectively. A coupled multilayer artificial neural network (ANN) model is framed to predict potential and current from red (R), green (G), and blue (B) color values. The optimized V-C3H NSs are used as the active materials in the fabrication of flexible/wearable electrochromic micro-supercapacitor devices (FEMSDs) through a cost-effective mask-assisted vacuum filtration method. The fabricated FEMSD exhibits an areal capacitance of 47.15mFcm-2 at 1mVs-1 and offers a maximum areal energy and power density of 104.78Whcm-2 and 0.04mWcm-2, respectively. This material's interesting energy storage and electrochromic properties are promising in multifunctional electrochromic energy storage applications.

Development of a multi-layer network model for characterizing energy cascade behavior on turbulent mixing

Eddies of various sizes are visible to the naked eye in turbulent flow. Each eddy scale corresponds to a fraction of the total energy released by the turbulence cascade. Understanding the dynamic mechanism of the energy cascade is crucial to the study of turbulent mixing. In this paper, an energy cascade multi-layer network (ECMN) based on the complex network algorithm is proposed to investigate the spatio-temporal evolution of the energy cascade, covering both the inertial and dispersive ranges. The dynamic process of energy cascade is transformed into a topological structure based on the node definition and edge determination. The topological structure allows for the exploration of eddies interaction and chaotic energy transfer across scales. The model results show the intermittent and non-uniform nature of the energy cascade. Meanwhile, the scale gap found in the model verifies the fractal property of the energy evolution. We also found that scales of the generated eddies in energy cascade process are stochastic, and a synchronous energy cascade pattern is demonstrated according to the constructed framework. Furthermore, it provides a topological way to evaluate the contribution of large and small scale eddies. In addition, a network structure coefficient κ is proposed to evaluate the energy transfer strength. It agrees very well with the fluctuation of dissipation rates. All of this shows that the network model can effectively reveal the inhomogeneous properties of the energy cascade and quantify the turbulent mixing intensity based on the intermittent scale interaction. This also provides new insights into the study of fractal scales of nonlinear complex systems and the bridging of chaotic dynamics with topological frameworks.

Spatial Air Quality Assessment in Peninsular Malaysia: Insights from Environmetric Analyses and Artificial Neural Networks

The research investigated the spatial distribution of air quality in Peninsular Malaysia to offer crucial insights for mitigating air quality degradation. Utilizing historical data obtained from the Malaysian Department of Environment, eleven years' worth (2011-2021) of daily readings of PM10, O3 , SO2 , NO2 , and CO from thirty-four monitoring stations were subjected to environmetric techniques and Artificial Neural Network analysis. HACA successfully classified seven stations into the High Pollution Cluster (HPC), seven stations into the Moderate Pollution Cluster (MPC), and twenty stations into the Low Pollution Cluster (LPC). The discriminant analysis demonstrated a correct assignment rate of 91.87%, suggesting that all five parameters were able to discriminate with a significance level of p<0.0001. Principal Component Analysis (PCA) revealed two Variance Factors (VFs) across all clusters, with cumulative variances of 69.43% (HPC), 82.32% (MPC), and 62.16% (LPC) respectively. Furthermore, employing a Multi-Layer Perceptron Feed-Forward Artificial Neural Network (MLP-FF-ANN) model to predict API readings yielded a significant and strong correlation, as indicated by R2 =0.7774 and RMSE=9.9048. These findings hold significant potential in informing the adoption of effective preventative and management strategies.

Research on a Critical Link Discovery Method for Network Security Situational Awareness.

Network security situational awareness (NSSA) aims to capture, understand, and display security elements in large-scale network environments in order to predict security trends in the relevant network environment. With the internet's increasingly large scale, increasingly complex structure, and gradual diversification of components, the traditional single-layer network topology model can no longer meet the needs of network security analysis. Therefore, we conduct research based on a multi-layer network model for network security situational awareness, which is characterized by the three-layer network structure of a physical device network, a business application network, and a user role network. Its network characteristics require new assessment methods, so we propose a multi-layer network link importance assessment metric: the multi-layer-dependent link entropy (MDLE). On the one hand, the MDLE comprehensively evaluates the connectivity importance of links by fitting the link-local betweenness centrality and mapping entropy. On the other hand, it relies on the link-dependent mechanism to better aggregate the link importance contributions in each network layer. The experimental results show that the MDLE has better ordering monotonicity during critical link discovery and a higher destruction efficacy in destruction simulations compared to classical link importance metrics, thus better adapting to the critical link discovery requirements of a multi-layer network topology.

Effective Permittivity of Compacted Granular Materials: Effects of Interfacial Polarization and Pore-filling Fluids

Interfacial polarization dominates the permittivity spectra of heterogeneous granular materials for the intermediate frequency range (i.e., from kHz to MHz). In this study, we examine the corresponding dielectric responses of compacted glass sphere packings saturated with pore-filling fluids under various compressive stresses. The effective permittivity spectra are observed to exhibit consistently a plateau-to-plateau drop, described by low-frequency permittivity, characteristic frequency, and high-frequency permittivity. The permittivity spectra under different compressive levels are found to be influenced by the packing structure, compressive stress, and electrical property contrasts between solid and fluid (specifically permittivity and conductivity). For considered measurement conditions, the variation of packing structure and its associated porosity is found to be more significant than the stress evolution in controlling the interfacial polarization, thus the permittivity spectra, as supported by analytical and numerical results for unit cells. Furthermore, to gain a general rule for dielectric responses for saturated granular materials, we train multi-layer artificial neural network (ANN) models based on a series of simulations for unit cells with various structures, stresses, and electrical and dielectric properties. The predictions with two-layer ANN agree well with experimental measurements, presenting errors smaller than 5% for both low-frequency and high-frequency permittivity. This study offers an effective predicting approach for the dielectric behaviour of heterogeneous and multiphase materials.

A multilayer network model of interaction between rumor propagation and media influence.

Rumors spread among the crowd have an impact on media influence, while media influence also has an impact on rumor dissemination. This article constructs a two-layer rumor media interaction network model, in which the rumors spread in the crowd are described using the susceptibility-apathy-propagation-recovery model, and the media influence is described using the corresponding flow model. The rationality of the model is studied, and then a detailed analysis of the model is conducted. In the simulation section, we undertake a sensitivity analysis of the crucial parameters within our model, focusing particularly on their impact on the basic reproduction number. According to data simulation analysis, the following conclusion can be drawn: First, when the media unilaterally influences the crowd and does not accept feedback from the crowd, the influence of the media will decrease to zero over time, which has a negative effect on the spread of rumors among the crowd (the degree of rumor dissemination decreases). Second, when the media does not affect the audience and accepts feedback from the audience, this state is similar to the media collecting information stage, which is to accept rumors from the audience but temporarily not disclose their thoughts. At this time, both the media influence and the spread of rumors in the audience will decrease. Finally, the model is validated using an actual dataset of rumors. The simulation results show an R-squared value of 0.9606, indicating that the proposed model can accurately simulate rumor propagation in real social networks.

Epidemic process on partially overlapped multi-layer networks

The phenomenon of epidemic spread has received continuous attention due to its profound applications in a wide range of social and economic activities. In this paper we propose a partially overlapped multi-layer network model and illustrate the influence of multi-layer structure on outbreaks. Combined with the classic SIS model, we propose a set of discrete Markov equations and make first-order approximation on the threshold of epidemic outbreak. In comparison with independent simplex networks, we find that a multi-layer structure promotes epidemic spread and leads to a smaller critical threshold. In addition, we also find that the epidemic process on partially overlapped multi-layer networks is dominated by the layer with the largest main eigenvalue. Through Monte Carlo simulations, we find that the role of the dominant layer is irrelevant with its size, which means a small set of nodes can exhibit a disproportionate impact on the epidemics of a large network. Our research sheds light on the epidemic process on partially overlapped multi-layer complex systems, and provides a theoretical explanation of unexpected real-world outbreaks.

Optimization of 2024-T3 Aluminum Alloy Friction Stir Welding Using Random Forest, XGBoost, and MLP Machine Learning Techniques.

This study optimized friction stir welding (FSW) parameters for 1.6 mm thick 2024T3 aluminum alloy sheets. A 3 × 3 factorial design was employed to explore tool rotation speeds (1100 to 1300 rpm) and welding speeds (140 to 180 mm/min). Static tensile tests revealed the joints' maximum strength at 87% relative to the base material. Hyperparameter optimization was conducted for machine learning (ML) models, including random forest and XGBoost, and multilayer perceptron artificial neural network (MLP-ANN) models, using grid search. Welding parameter optimization and extrapolation were then carried out, with final strength predictions analyzed using response surface methodology (RSM). The ML models achieved over 98% accuracy in parameter regression, demonstrating significant effectiveness in FSW process enhancement. Experimentally validated, optimized parameters resulted in an FSW joint efficiency of 93% relative to the base material. This outcome highlights the critical role of advanced analytical techniques in improving welding quality and efficiency.

Application of Machine Learning and Optimization of Oil Recovery and CO2 Sequestration in the Tight Oil Reservoir

Summary In recent years, shale and tight reservoirs have become an essential source of hydrocarbon production since advanced multistage and horizontal drilling techniques were developed. Tight oil reservoirs contain huge oil reserves but suffer from low recovery factors. For tight oil reservoirs, CO2-water alternating gas (CO2-WAG) is one of the preferred tertiary methods to enhance the overall cumulative oil production while also sequestering significant amounts of injected CO2. However, the evaluation of CO2-WAG is strongly dependent on the injection parameters, which renders numerical simulations computationally expensive. In this study, a novel approach has been developed that utilized machine learning (ML)-assisted computational workflow in optimizing a CO2-WAG project for a low-permeability oil reservoir considering both hydrocarbon recovery and CO2 storage efficacies. To make the predictive model more robust, two distinct proxy models—multilayered neural network (MLNN) models coupled with particle swarm optimization (PSO) and genetic algorithms (GAs)—were trained and optimized to forecast the cumulative oil production and CO2 storage. Later, the optimized results from the two algorithms were compared. The optimized workflow was used to maximize the predefined objective function. For this purpose, a field-scaled numerical simulation model of the Changqing Huang 3 tight oil reservoir was constructed. By December 2060, the base case predicts a cumulative oil production of 0.368 million barrels (MMbbl) of oil, while the MLNN-PSO and MLNN-GA forecast 0.389 MMbbl and 0.385 MMbbl, respectively. As compared with the base case (USD 150.5 million), MLNN-PSO and MLNN-GA predicted a further increase in the oil recovery factor by USD 159.2 million and USD 157.6 million, respectively. In addition, the base case predicts a CO2 storage amount of 1.09×105 tons, whereas the estimates from MLNN-PSO and MLNN-GA are 1.26×105 tons and 1.21×105 tons, respectively. Compared with the base case, CO2 storage for the MLNN-PSO and MLNN-GA increased by 15.5% and 11%, respectively. In terms of the performance analysis of the two algorithms, both showed remarkable performance. PSO-developed proxies were 16 times faster and GA proxies were 10 times faster as compared with the reservoir simulation in finding the optimal solution. The developed optimization workflow is extremely efficient and computationally robust. The experiences and lessons will provide valuable insights into the decision-making process and in optimizing the Changqing Huang 3 low-permeability oil reservoir.

Exploring the effectiveness of a multilayer neural network model for gold price prediction

Exploring the effectiveness of a multilayer neural network model for gold price prediction

Research on the Interrelationship of Sustainable Development Goals Based on Multilayer Network Modeling

The Sustainable Development Goals are not just a call to action, but a vision of hope for a better world. To achieve sustainable development, it is critical to study relationship between SDGs and select the most effective priority goals. A multi-layer network approach was employed to establish a model for analyzing the interrelationships and impacts of SDGs.The ffnal model was derived by computing the Pearson correlation coefffcient matrix and network connections. The network models for 10 regions were visualized, revealing that in the WLD region, SDG8 had a positive impact on other SDGs, particularly on SDG4, while SDG17 had a negative impact on 14 SDGs.We have concluded that our model has strong robustness, high stability, and good interpretability. This provides scientiffc guidance and support for achieving the SDGs.

Novel hybrid intelligence predictive model based on successive variational mode decomposition algorithm for monthly runoff series

A high-accuracy estimation of the runoff has always been an extremely relevant and challenging subject in hydrology science.Therefore, in the current research, a novel hybrid decomposition-integration-optimization based model is developed to enhance the estimation precision of the runoff. The suggested predictive model is a combination of successive variational mode decomposition (SVMD) technique and Multi-Layer Perceptron neural network (MLP) model integrated with particle swarm optimization (PSO) meta-heuristic algorithm (i.e., hybrid SVMD-MLP-PSO model). To test its performance, the mean monthly runoff data recorded from Sep 1986-Aug 2017 in Dez River basin (MRDRm), southwest of Iran, are used. The performance of the recommended model is also matched with other different hybrid and single models including MLP-PSO, SVMD-MLP, and MLP as the benchmark model. In all models, the sequence-to-one regression module of forecasting (i.e., without using meteorological parameters recorded in the study region) is utilized. In the SVMD based hybrid models, the optimal value of compactness of mode (α) for the original MRDRm time series is achieved at 100. Then, the PACF(partial autocorrelation function) diagram related to the lag length from each decomposed intrinsic mode function (IMF) sub-signals sequence generated is operated to select the ideal input variables. Performance evaluation metrics prove that the hybrid SVMD-MLP-PSO model under the best predictor and meta-parameters, outperformed with an R2 of 0.89, modified 2012 version of Kling-Gupta efficiency (KGEʹ) of 0.83, volumetric efficiency (VE) of 0.91, Nash–Sutcliffe efficiency (NSE) of 0.88, and RMSE of 13.91 m3/s. Comparatively, the standalone MLP as the benchmark model results in an R2 of 0.24, VE of 0.33, KGEʹ of 0.2, NSE of 0.29, and RMSE of 153.39 m3/s.

Significant risk factors for intensive care unit-acquired weakness: A processing strategy based on repeated machine learning.

Intensive care unit-acquired weakness (ICU-AW) is a common complication that significantly impacts the patient's recovery process, even leading to adverse outcomes. Currently, there is a lack of effective preventive measures. To identify significant risk factors for ICU-AW through iterative machine learning techniques and offer recommendations for its prevention and treatment. Patients were categorized into ICU-AW and non-ICU-AW groups on the 14th day post-ICU admission. Relevant data from the initial 14 d of ICU stay, such as age, comorbidities, sedative dosage, vasopressor dosage, duration of mechanical ventilation, length of ICU stay, and rehabilitation therapy, were gathered. The relationships between these variables and ICU-AW were examined. Utilizing iterative machine learning techniques, a multilayer perceptron neural network model was developed, and its predictive performance for ICU-AW was assessed using the receiver operating characteristic curve. Within the ICU-AW group, age, duration of mechanical ventilation, lorazepam dosage, adrenaline dosage, and length of ICU stay were significantly higher than in the non-ICU-AW group. Additionally, sepsis, multiple organ dysfunction syndrome, hypoalbuminemia, acute heart failure, respiratory failure, acute kidney injury, anemia, stress-related gastrointestinal bleeding, shock, hypertension, coronary artery disease, malignant tumors, and rehabilitation therapy ratios were significantly higher in the ICU-AW group, demonstrating statistical significance. The most influential factors contributing to ICU-AW were identified as the length of ICU stay (100.0%) and the duration of mechanical ventilation (54.9%). The neural network model predicted ICU-AW with an area under the curve of 0.941, sensitivity of 92.2%, and specificity of 82.7%. The main factors influencing ICU-AW are the length of ICU stay and the duration of mechanical ventilation. A primary preventive strategy, when feasible, involves minimizing both ICU stay and mechanical ventilation duration.

Deep Graph Learning-Based Surrogate Model for Inverse Modeling of Fractured Reservoirs

Inverse modeling can estimate uncertain parameters in subsurface reservoirs and provide reliable numerical models for reservoir development and management. The traditional simulation-based inversion method usually requires numerous numerical simulations, which is time-consuming. Recently, deep learning-based surrogate models have been widely studied as an alternative to numerical simulation, which can significantly improve the solving efficiency of inversion. However, for reservoirs with complex fracture distribution, constructing the surrogate model of numerical simulation presents a significant challenge. In this work, we present a deep graph learning-based surrogate model for inverse modeling of fractured reservoirs. Specifically, the proposed surrogate model integrates the graph attention mechanisms to extract features of fracture network in reservoirs. The graph learning can retain the discrete characteristics and structural information of the fracture network. The extracted features are subsequently integrated with a multi-layer recurrent neural network model to predict the production dynamics of wells. A surrogate-based inverse modeling workflow is then developed by combining the surrogate model with the differential evolutionary algorithm. Numerical studies performed on a synthetic naturally fractured reservoir model with multi-scale fractures illustrate the performance of the proposed methods. The results demonstrate that the proposed surrogate model exhibits promising generalization performance of production prediction. Compared with tens of thousands of numerical simulations required by the simulation-based inverse modeling method, the proposed surrogate-based method only requires 1000 to 1500 numerical simulations, and the solution efficiency can be improved by ten times.

Electroconvulsive Therapy Regulates Brain Connectome Dynamics in Patients With Major Depressive Disorder

BackgroundElectroconvulsive therapy (ECT) is an effective treatment for patients with major depressive disorder (MDD), but its underlying neural mechanisms remain largely unknown. The aim of this study was to identify changes in brain connectome dynamics after ECT in MDD and to explore their associations with treatment outcome. MethodsWe collected longitudinal resting-state functional magnetic resonance imaging data from 80 patients with MDD (50 with suicidal ideation [MDD-SI] and 30 without [MDD-NSI]) before and after ECT and 37 age- and sex-matched healthy control participants. A multilayer network model was used to assess modular switching over time in functional connectomes. Support vector regression was used to assess whether pre-ECT network dynamics could predict treatment response in terms of symptom severity. ResultsAt baseline, patients with MDD had lower global modularity and higher modular variability in functional connectomes than control participants. Network modularity increased and network variability decreased after ECT in patients with MDD, predominantly in the default mode and somatomotor networks. Moreover, ECT was associated with decreased modular variability in the left dorsal anterior cingulate cortex of MDD-SI but not MDD-NSI patients, and pre-ECT modular variability significantly predicted symptom improvement in the MDD-SI group but not in the MDD-NSI group. ConclusionsWe highlight ECT-induced changes in MDD brain network dynamics and their predictive value for treatment outcome, particularly in patients with SI. This study advances our understanding of the neural mechanisms of ECT from a dynamic brain network perspective and suggests potential prognostic biomarkers for predicting ECT efficacy in patients with MDD.

Accelerated prediction of stacking fault energy in FCC medium entropy alloys using multilayer perceptron neural networks: correlation and feature analysis

A multilayer perceptron neural networks (MLPNN) model is developed for robust and quick prediction of stacking fault energy (SFE) to overcome the challenges faced in the calculation of SFE via experimentation and atomistic calculations in FCC medium entropy alloys (MEA). The present investigation employs a three-step hybrid feature selection approach to obtain a comprehensive understanding of the prominent features that influence the SFE, as well as the interrelationships among these features. The feature space encompasses various features related to composition, lattice stability, and elemental properties, of MEAs. The findings indicate that the estimation of SFE relies on five crucial factors: temperature, lattice stability, specific heat, ionization energy, and Allen electronegativities. Furthermore, a mathematical relationship for the estimation of the SFE is derived, considering the various influencing and prominent factors. Consequently, the MLPNN model for robust SFE prediction in MEAs is developed and the performance is evaluated using R 2 scores, with values of 0.87 and 0.85 obtained for the training and testing datasets, respectively. This efficient strategy introduces a novel opportunity for the engineering of SFE in the extensive range of alloy chemistry of MEAs, enabling the quick prediction of SFE, and facilitating the systematic exploration of new alloys for the development of mechanisms that may accommodate deformation through octahedral/partial slip, twinning, and/or transformation.

Identification of breast cancer subtypes based on graph convolutional network

Identification of molecular subtypes of malignant tumors plays a vital role in individualized diagnosis, personalized treatment, and prognosis prediction of cancer patients. The continuous improvement of comprehensive tumor genomics database and the ongoing breakthroughs in deep learning technology have driven further advancements in computer-aided tumor classification. Although the existing classification methods based on gene expression omnibus database take the complexity of cancer molecular classification into account, they ignore the internal correlation and synergism of genes. To solve this problem, we propose a multi-layer graph convolutional network model for breast cancer subtype classification combined with hierarchical attention network. This model constructs the graph embedding datasets of patients' genes, and develops a new end-to-end multi-classification model, which can effectively recognize molecular subtypes of breast cancer. A large number of test data prove the good performance of this new model in the classification of breast cancer subtypes. Compared to the original graph convolutional neural networks and two mainstream graph neural network classification algorithms, the new model has remarkable advantages. The accuracy, weight-F1-score, weight-recall, and weight-precision of our model in seven-category classification has reached 0.851 7, 0.823 5, 0.851 7 and 0.793 6 respectively. In the four-category classification, the results are 0.928 5, 0.894 9, 0.928 5 and 0.865 0 respectively. In addition, compared with the latest breast cancer subtype classification algorithms, the method proposed in this paper also achieved the highest classification accuracy. In summary, the model proposed in this paper may serve as an auxiliary diagnostic technology, providing a reliable option for precise classification of breast cancer subtypes in the future and laying the theoretical foundation for computer-aided tumor classification.

Can Machine Learning Predict Running Kinematics Based on Upper Trunk GPS-Based IMU Acceleration? A Novel Method of Conducting Biomechanical Analysis in the Field Using Artificial Neural Networks

This study aimed to investigate whether running kinematics can be accurately estimated through an artificial neural network (ANN) model containing GPS-based accelerometer variables and anthropometric data. Thirteen male participants with extensive running experience completed treadmill running trials at several speeds. Participants wore a GPS device containing a triaxial accelerometer, and running kinematics were captured by an 18-camera motion capture system for each trial. Multiple multilayer perceptron neural network models were constructed to estimate participants’ 3D running kinematics. The models consisted of the following input variables: 3D peak accelerometer acceleration during foot stance (g), stance time (s), running speed (km/h), participant height (cm), leg length (cm), and mass (kg). Pearson’s correlation coefficient (r), root mean squared error (RMSE), and relative root mean squared error (rRMSE) showed that ANN models provide accurate estimations of joint/segment angles (mean rRMSE = 13.0 ± 4.3%) and peak segment velocities (mean rRMSE = 22.1 ± 14.7%) at key gait phases across foot stance. The highest accuracies were achieved for flexion/extension angles of the thorax, pelvis, and hip, and peak thigh flexion/extension and vertical velocities (rRMSE < 10%). The current findings offer sports science and medical practitioners working with this data a method of conducting field-based analyses of running kinematics using a single IMU.