Nonlinear Neural Network Research Articles

Target location method of intelligent deicing robot based on nonlinear auto disturbance rejection neural network

A visual navigation scheme for intermittent walking deicing robots was designed to address the issues of multiple iterations, long computation time, and poor real-time performance in the nonlinear optimization of the original SLAM system. A computer image acquisition unit, a computer image processing module, and a visual navigation parameter extraction algorithm were also designed. Implemented a visual navigation system for deicing robots based on image processing. It can meet the navigation requirements of the deicing robot. Simulation and experiments have shown that the method proposed in this paper can quickly and accurately identify abnormal point clouds. The visual servo control scheme constructed in this paper is aimed at robot task operations with unknown system calibration and target depth information. By calibrating the robot vision system, the conversion between camera pixel coordinates and robot base coordinates is achieved, with a transmission frame rate of 53.65 per second; The maximum error in positioning accuracy in space is 10.6 mm. The feature trajectory of visual space is smooth and stable within the camera's field of view, and the end movement of Cartesian space robots is stable without rebound, resulting in high grasping and positioning accuracy.

Application of Neural Network in Seismic Risk Survey

The accuracy of inversion data is determined by the reliability of linear inversion method. Therefore, the study of nonlinear seismic inversion method is a meaningful work. This paper mainly aims at the application of nonlinear neural network inversion method in Fujian Risk Survey, the following work has been accomplished: (1) The theory and algorithm of the conventional multilayer feedforward neural network and some problems in the design of the model are analyzed and summarized. Aiming at the gradient descent function search algorithm in the BP algorithm, a method for global optimization is proposed by combining simulated annealing (global search algorithm) with Conjugate gradient method (local search algorithm) , the principle and implementation of simulated annealing and conjugate gradient algorithm are analyzed in detail. (2) Based on the analysis of conventional multilayer feedforward neural networks, the model structure and basic principle of probabilistic neural networks are studied. The object function search algorithm and its realization are analyzed. The method is applied to the risk elimination prediction for the first time, and the results are satisfactory. (3) The method and principle of inversion of reservoir parameters by using various seismic attribute information and neural network technology are discussed. In order to make full use of the effective information contained in seismic signal, the method of seismic attribute extraction and optimization is studied, the principle and implementation method of attribute optimal ranking by stepwise recursive method and selecting the most important attribute combination by interactive verification method are presented.

Using nonlinear auto-regressive with exogenous input neural network (NNARX) in blood glucose prediction

BackgroundPredicting of future blood glucose (BG) concentration is important for diabetes control. Many automatic BG monitoring or controlling systems use BG predictors. The accuracy of the prediction for long prediction time is a major factor affecting the performance of the control system. The predicted BG can be used for glycemia management in the form of early hypoglycemic/hyperglycemic alarms or adjusting insulin injections. Recent developments in continuous glucose monitoring (CGM) devices open new opportunities for glycemia management of diabetic patients. Many of those systems need prediction for long prediction horizons to avoid going through hypo or hyperglycemia.MethodsIn this article a nonlinear autoregressive exogenous input neural network (NNARX) is proposed to predict the glucose concentration for longer prediction horizons (PHs) than that was obtained previously with an established recurrent neural network (RNN). The proposed NNARX is a modified version from our previously published RNN with different initialization and building technique but has the same architecture. The modification is based on starting with building nonlinear autoregressive exogenous input model using MATLAB and train it, then close the loop to get NNARX network.ResultsThe results of using the proposed NNARX indicate that the proposed NNARX is better in prediction and stability than unmodified RNN as PH becomes higher than 45 minutes.ConclusionsModification in RNN building extends the ability of the prediction till 100 minutes. It performs statistically significant improvements in the FIT and RMSE values for 100 minutes prediction. It also decreases root mean squared error (RMSE) for both 45 and 60 minutes of prediction.

Predicting the dynamic behavior of a magnetocaloric cooling prototype via artificial neural networks

Although magnetocaloric cooling is considered a promising long-term alternative to vapor compression, recent prototype developments have not yet made this technology commercially competitive, primarily due to its high energy consumption and lack of cost-effective, long-term mechanically-chemically stable materials. To address the first issue and understand how the efficiency of magnetocaloric systems can be improved, dynamic models can offer valuable insights into their transient operation. This work focuses on the development of an artificial neural network with experimental data to model the dynamic operation of a magnetic refrigeration system. Through a design of experiments approach, we propose excitation signals for the identification experiment, involving five manipulated variables and one selected disturbance as inputs, with the output temperature of the cold manifold and power consumption as the target parameters. We chose a nonlinear autoregressive artificial neural network with exogenous inputs to model the transient operation of the system. The temperature model achieved R2 values of 0.995 and 0.955 for the 1-step and 90-step ahead predictions, respectively. Similarly, the power consumption model achieved R2 values of 0.988 and 0.949 for the 1-step and 90-step ahead predictions, respectively. These performance metrics were evaluated on the test sets that were not used for training the models, highlighting the robustness and accuracy of the models in both short-term and long-term predictions.

Advertisement design in dynamic interactive scenarios using DeepFM and long short-term memory (LSTM).

This article addresses the evolving landscape of data advertising within network-based new media, seeking to mitigate the accuracy limitations prevalent in traditional film and television advertising evaluations. To overcome these challenges, a novel data-driven nonlinear dynamic neural network planning approach is proposed. Its primary objective is to augment the real-time evaluation precision and accuracy of film and television advertising in the dynamic interactive realm of network media. The methodology primarily revolves around formulating a design model for visual advertising in film and television, customized for the dynamic interactive milieu of network media. Leveraging DeepFM+long short-term memory (LSTM) modules in deep learning neural networks, the article embarks on constructing a comprehensive information statistics and data interest model derived from two public datasets. It further engages in feature engineering for visual advertising, crafting self-learning association rules that guide the data-driven design process and system flow. The article concludes by benchmarking the proposed visual neural network model against other models, using F1 and root mean square error (RMSE) metrics for evaluation. The findings affirm that the proposed model, capable of handling dynamic interactions among images, visual text, and more, excels in capturing nonlinear and feature-mining aspects. It exhibits commendable robustness and generalization capabilities within various contexts.

Predictive modelling of flow dynamics in micropolar hybrid nanofluids subjected to magnetic dipole influence using nonlinear autoregressive artificial neural networks with exogenous input

In the present research article, we explore the intelligence-based numerical computation of a nonlinear autoregressive artificial neural network with exogenous input using the Levenberg-Marquardt algorithm (ANN-LMA) trained to analyze the unsteady two-dimensional micro-polar flow of an incompressible hybrid nanofluid (Al 2 O 3−Fe 3 O 4/Ethylene Glycol) under the impact of the magnetic field introduced by the magnetic dipole on a nonlinear stretched sheet. In the first step of the research, partial differential equations are converted into nonlinear ordinary differential equations using appropriate transmission and then solved numerically via the Successive Over Relaxation method after applying the finite difference method. The impact of numerous emerging parameters on the solutions is displayed graphically, and the physical significance is discussed. The results show that the concentration profile displays a dwindling trend for the Brownian motion parameter, and the opposite trend is witnessed for the thermophoretic parameter. Moreover, for increasing values of the dimensionless distance parameter and ferromagnetic interaction parameter, the temperature and velocity profiles exhibit the opposite tendency. In the second step of the study, we validated the Successive Over Relaxation outcomes with an ANN-LMA. For this purpose, the suggested ANN-LMA is trained for six different scenarios of the reference dataset points of the given flow model. The analysis shows that Successive Over Relaxation and LM-SNNs yield similar results, with a decreasing trend for the Brownian motion parameter and an opposite trend for the thermophoretic parameter.

Coupling effects of multiple strengthening mechanisms in spheroidal microstructure eutectic high-entropy alloys

The yield strength of metallic materials is commonly estimated using linear superposition methods, but this method has limited adaptability to new materials. The mapping relationship between input and output in machine learning methods is difficult to quantify. This study employs a rapid screening method to identify the key strengthening mechanisms that influence the yield strength of typical homogeneous and heterogeneous metallic materials. A non-linear physical neural information network model is developed to describe the yield strength of heterogeneous structures, capturing the main parameters contributing to yield strength from selected physical quantity data. By considering the non-linear strengthening mechanisms arising from interactions among multiple strengthening mechanisms in heterogeneous metal structures, the microstructure and mechanical properties of eutectic high-entropy alloys are optimized through warm rolling and short-time annealing. By inducing microstructural spheroidization and introducing nanoscale precipitates, significant coupling effects of multiple strengthening mechanisms are achieved for eutectic high-entropy alloys. As a result, the yield strength increases by approximately 2.5 times, while plasticity remains nearly unchanged. Transmission electron microscopy, scanning electron microscopy, and electron backscatter diffraction observations provide evidence for the sources of these coupling effects. This study offers guidance for accelerating material design and exploring the physical relationship between microstructure and mechanical properties.

Parameter sensitivity analysis of a sea ice melt pond parametrisation and its emulation using neural networks

Accurate simulation of sea ice is critical for predictions of future Arctic sea ice loss, looming climate change impacts, and more. A key feature in Arctic sea ice is the formation of melt ponds. Each year melt ponds develop on the surface of the ice and primarily via affecting the albedo, they have an enormous effect on the energy budget and climate of the Arctic. As melt ponds are subgrid scale and their evolution occurs due to a number of competing, poorly understood factors, their representation in models is parametrised.Sobol sensitivity analysis, a form of variance based global sensitivity analysis is performed on an advanced melt pond parametrisation (MPP), in Icepack, a state-of-the-art thermodynamic column sea ice model. Results show that the model is very sensitive to changing its uncertain MPP parameter values, and that these have varying influences over model predictions both spatially and temporally. Such extreme sensitivity to parameters makes MPPs a potential source of prediction error in sea-ice models, given that the (often many) parameters in MPPs are usually poorly known.Machine learning (ML) techniques have shown great potential in learning and replacing subgrid scale processes in models. Given the complexity of melt pond physics and the need for accurate parameter values in MPPs, we propose an alternative data-driven MPPs that would prioritise the accuracy of albedo predictions. In particular, we constructed MPPs based either on linear regression or on nonlinear neural networks, and investigate if they could substitute the original physics-based MPP in Icepack.Our results shown that linear regression are insufficient as emulators, whilst neural networks can learn and emulate the MPP in Icepack very reliably. Icepack with the MPPs based on neural networks only slightly deviates from the original Icepack and overall offers the same long term model behaviour.We then searched for the smallest possible emulator that achieves good performance by performing features selection based on mutual information. Results indicates that a smaller model, based only on a portion of the full set of input variables needed by the physical MPP, is also sufficient to approximate and replace the physical MPP. This smaller emulators are not only computationally faster but also easier to interpret on a physical ground.Several and diverse challenges still exist, yet this study is an encouraging first step, prior to using real data, towards the adoption of data-driven MPPs in sea-ice models.

A Deep Vision Sensing-Based Smart Control Method for Apple-Picking Robots Under the Context of Agricultural E-Commerce

The growing development of the agricultural e-commerce industry is promoting the Digital transformation of agricultural production and logistics. Aiming at the problem of labor shortage in apple picking, this paper proposes a performance control method for robot apple picking based on a nonlinear wide convolutional neural network (NLWCNN) and multi-objective cooperative distance transformation algorithm (MOCDTA). This method utilizes deep learning algorithms and visual sensing technology to enable robots to accurately recognize apples and perform autonomous picking operations based on their maturity and position. We have designed a machine learning-based algorithm that enables robots to accurately recognize and distinguish apples of different maturity levels through training on a large amount of sample data. At the same time, we also combined the motion control algorithm of the robot to enable efficient picking operations based on the position and maturity information of the apples. The experimental results indicate that the NLWCNN method can significantly improve the efficiency and accuracy of apple picking, ensure the safety and traceability of agricultural products, increase consumer trust, and promote agricultural product transactions.

Platinum and palladium price forecasting through neural networks

To many commodity market participants, forecasts of price series represent a critical task. In this work, nonlinear autoregressive neural network models’ potential is explored for forecasting daily prices series of platinum and palladium over about a fifty-year period. For this purpose, one hundred and twenty model settings are examined, including different training algorithms, numbers of hidden neurons and delays, and ratios used to segment the data. With the analysis, two models leading to stable and accurate forecast results are constructed for the prices of the two commodities. In particular, the models’ performance in terms of the relative root mean square error is 1.86% and 3.61% for platinum and palladium, respectively, for the overall sample. Results in this work could help technical forecasts and policy analysis. The forecast framework might be extended to other different commodities.

Using statistical and machine learning approaches to describe estuarine tidal dynamics

ABSTRACT Estuaries are ecologically valuable regions where tidal forces move large volumes of water. To understand the ongoing physical processes in such dynamic systems, a series of estuarine monitoring stations is required. Based on the measurements, estuarine dynamics can be described by key values, so-called tidal characteristics. The reconstruction and prediction of tidal characteristics by suitable approaches is essential to discover natural or anthropogenic changes. Therefore, it is of interest to inter- and extrapolate measured values in time and to investigate the spatial relationship between different stations. Normally, such system analyses are performed by deterministic numerical models. However, to facilitate long-term investigations also, statistical and machine learning approaches are good options. For a Weser estuary case study, we implemented three approaches (linear, non-linear, and artificial neural network regression) with the same database to enable the prediction of tidal extrema. Thereby we achieve an accuracy of 0.4–2.5% derivation (based on the RMSEs) while approximating measured values over 19 years. This proves that the approaches can be used for hindcast studies as well as for future analysis of system changes. Our work can be understood as a proof of concept for the practical potential of neural networks in estuarine system analysis.

Improving precipitation estimates for Turkey with multimodel ensemble: a comparison of nonlinear artificial neural network method with linear methods

AbstractEnsemble analysis is proven to provide advantages in climate change impact assessment based on outputs from climate models. Ensembled series are shown to outperform single-model assessments through increased consistency and stability. This study aims to test the improvement of precipitation estimates through the use of ensemble analysis for south and southwestern Turkey which is known to have complex climatic features due to varying topography and interacting climate forcings. The analysis covers an evaluation of the performance of eight regional climate models (RCMs) from the EUR-11 domain available from the CORDEX database. The historical outputs are evaluated for their representativeness of the current climate of the Mediterranean region and its surroundings in Turkey through a comparison with long-term monthly precipitation time series obtained from ground-based precipitation observations by the use of statistical performance indicators and Taylor diagrams. This is followed by a comparative evaluation of three ensemble methodologies, simple average of the models, multiple linear regression for superensemble, and artificial neural networks (ANN). The analysis results show that the overall performance of ensembled time series is better compared to individual RCMs. ANN generally provided the best performance when all RCMs are used as inputs. Improvement in the performance of ensembling due to the use of nonlinear models is further confirmed by fuzzy inference systems (FIS). Both ANN and FIS generated monthly precipitation time series with higher correlations with those of observations. However, extreme events are poorly represented in the ensembled time series, and this may result in inefficiency in the design of various water structures such as spillways and storm water drainage systems that are based on high return period events.

The role of cell-free DNA biomarkers and patient data in the early prediction of preeclampsia: an artificial intelligence model

ObjectiveAccurate individualized assessment of preeclampsia risk enables the identification of patients most likely to benefit from initiation of low-dose aspirin at 12-16 weeks’ gestation when there is evidence for its effectiveness, as well as guiding appropriate pregnancy care pathways and surveillance. The primary objective of this study was to evaluate the performance of artificial neural network models for the prediction of preterm preeclampsia (<37 weeks’ gestation) using patient characteristics available at the first antenatal visit and data from prenatal cell-free DNA (cfDNA) screening. Secondary outcomes were prediction of early onset preeclampsia (<34 weeks’ gestation) and term preeclampsia (≥37 weeks’ gestation). MethodsThis secondary analysis of a prospective, multicenter, observational prenatal cfDNA screening study (SMART) included singleton pregnancies with known pregnancy outcomes. Thirteen patient characteristics that are routinely collected at the first prenatal visit and two characteristics of cfDNA, total cfDNA and fetal fraction (FF), were used to develop predictive models for early-onset (<34 weeks), preterm (<37 weeks), and term (≥37 weeks) preeclampsia. For the models, the ‘reference’ classifier was a shallow logistic regression (LR) model. We also explored several feedforward (non-linear) neural network (NN) architectures with one or more hidden layers and compared their performance with the LR model. We selected a simple NN model built with one hidden layer and made up of 15 units. ResultsOf 17,520 participants included in the final analysis, 72 (0.4%) developed early onset, 251 (1.4%) preterm, and 420 (2.4%) term preeclampsia. Median gestational age at cfDNA measurement was 12.6 weeks and 2,155 (12.3%) had their cfDNA measurement at 16 weeks’ gestation or greater. Preeclampsia was associated with higher total cfDNA (median 362.3 versus 339.0 copies/ml cfDNA; p<0.001) and lower FF (median 7.5% versus 9.4%; p<0.001). The expected, cross-validated area under the curve (AUC) scores for early onset, preterm, and term preeclampsia were 0.782, 0.801, and 0.712, respectively for the LR model, and 0.797, 0.800, and 0.713, respectively for the NN model. At a screen-positive rate of 15%, sensitivity for preterm preeclampsia was 58.4% (95% CI 0.569, 0.599) for the LR model and 59.3% (95% CI 0.578, 0.608) for the NN model.The contribution of both total cfDNA and FF to the prediction of term and preterm preeclampsia was negligible. For early-onset preeclampsia, removal of the total cfDNA and FF features from the NN model was associated with a 6.9% decrease in sensitivity at a 15% screen positive rate, from 54.9% (95% CI 52.9-56.9) to 48.0% (95% CI 45.0-51.0). ConclusionRoutinely available patient characteristics and cfDNA markers can be used to predict preeclampsia with performance comparable to other patient characteristic models for the prediction of preterm preeclampsia. Both LR and NN models showed similar performance.

Price forecasting through neural networks for crude oil, heating oil, and natural gas

Building price projections of various energy commodities has long been an important endeavor for a wide range of participants in the energy market. We study the forecast problem in this paper by concentrating on four significant energy commodities. Using nonlinear autoregressive neural network models, we investigate the daily prices of WTI and Brent crude oil as well as the monthly prices of Henry Hub natural gas and New York Harbor No. 2 heating oil. We investigate prediction performance resulting from various model configurations, including training techniques, hidden neurons, delays, and data segmentation. Based on the investigation, relatively straightforward models are built that yield quite accurate and reliable performance. Specifically, performance in terms of relative root mean square errors is 1.96%/1.81%/9.75%/21.76%, 1.96%/1.80%/8.76%/14.41%, and 1.87%/1.78%/9.10%/16.97% for model training, validation, and testing, respectively, and the overall relative root mean square error is 1.95%/1.80%/9.51%/20.35% for the whole sample for WTI crude oil/Brent crude oil/New York Harbor No. 2 heating oil/Henry Hub natural gas. The outcomes of this projection might be used in technical analysis or integrated with other fundamental forecasts for policy analysis.

Optimization of Nonlinear Convolutional Neural Networks based on Improved Chameleon Group Algorithm

In order to solve the most difficult problem of the architectural model established by CNN in solving specific problems, which results in parameter overflow and inefficient training, an optimization algorithm for nonlinear convolutional neural networks based on improved chameleon swarm algorithm is proposed. This article mainly introduces the use of Chameleon Swarm Optimization (PSO) algorithm to research the parameters of CNN architecture, solve them, and achieve the optimization of the optimization model.Although the number of parameters that need to be set up in CNN is very large, this method can find better testing space for Alexnet samples with 5 different images. In order to improve the performance of the improved pruning algorithms, two candidate pruning algorithms are also proposed. The experimental results show that compared with the traditional Alexnet model, the improved pruning method improves the image recognition ability of the Caffe primary parameter set from 1.3% to 5.7%. This method has wide applicability and can be applied to most neural networks which do not require any special functional modules of the Alexnet network model.

An interpretable neural network-based non-proportional odds model for ordinal regression

This study proposes an interpretable neural network-based non-proportional odds model (N3POM) for ordinal regression. N3POM is different from conventional approaches to ordinal regression with non-proportional models in several ways: (1) N3POM is defined for both continuous and discrete responses, whereas standard methods typically treat the continuous variables as if they were discrete, (2) instead of estimating response-dependent finite-dimensional coefficients of linear models from discrete responses as is done in conventional approaches, we train a non-linear neural network to serve as a coefficient function. Thanks to the neural network, N3POM offers flexibility while preserving the interpretability of conventional ordinal regression. We establish a sufficient condition under which the predicted conditional cumulative probability locally satisfies the monotonicity constraint over a user-specified region in the covariate space. Additionally, we provide a monotonicity-preserving stochastic (MPS) algorithm for effectively training the neural network. We apply N3POM to several real-world datasets.

Robust machine learning models: linear and nonlinear

AbstractArtificial Intelligence relies on the application of machine learning models which, while reaching high predictive accuracy, lack explainability and robustness. This is a problem in regulated industries, as authorities aimed at monitoring the risks arising from the application of Artificial Intelligence methods may not validate them. No measurement methodologies are yet available to jointly assess accuracy, explainability and robustness of machine learning models. We propose a methodology which fills the gap, extending the Forward Search approach, employed in robust statistical learning, to machine learning models. Doing so, we will be able to evaluate, by means of interpretable statistical tests, whether a specific Artificial Intelligence application is accurate, explainable and robust, through a unified methodology. We apply our proposal to the context of Bitcoin price prediction, comparing a linear regression model against a nonlinear neural network model.

Seamless Micro-Electro-Mechanical System-Inertial Navigation System/Polarization Compass Navigation Method with Data and Model Dual-Driven Approach.

The integration of micro-electro-mechanical system-inertial navigation systems (MEMS-INSs) with other autonomous navigation sensors, such as polarization compasses (PCs) and geomagnetic compasses, has been widely used to improve the navigation accuracy and reliability of vehicles in Internet of Things (IoT) applications. However, a MEMS-INS/PC integrated navigation system suffers from cumulative errors and time-varying measurement noise covariance in unknown, complex occlusion, and dynamic environments. To overcome these problems and improve the integrated navigation system's performance, a dual data- and model-driven MEMS-INS/PC seamless navigation method is proposed. This system uses a nonlinear autoregressive neural network (NARX) based on the Gauss-Newton Bayesian regularization training algorithm to model the relationship between the MEMS-INS outputs composed of the specific force and angular velocity data and the PC heading's angular increment, and to fit the integrated navigation system's dynamic characteristics, thus realizing data-driven operation. In the model-driven part, a nonlinear MEMS-INS/PC loosely coupled navigation model is established, the variational Bayesian method is used to estimate the time-varying measurement noise covariance, and the cubature Kalman filter method is then used to solve the nonlinear problem in the model. The robustness and effectiveness of the proposed method are verified experimentally. The experimental results show that the proposed method can provide high-precision heading information stably in complex, occluded, and dynamic environments.

Multi-task learning using non-linear autoregressive models and recurrent neural networks for tide level forecasting

Tide level forecasting plays an important role in environmental management and development. Current tide level forecasting methods are usually implemented for solving single task problems, that is, a model built based on the tide level data at an individual location is only used to forecast tide level of the same location but is not used for tide forecasting at another location. This study proposes a new method for tide level prediction at multiple locations simultaneously. The method combines nonlinear autoregressive moving average with exogenous inputs (NARMAX) model and recurrent neural networks (RNNs), and incorporates them into a multi-task learning (MTL) framework. Experiments are designed and performed to compare single task learning (STL) and MTL with and without using non-linear autoregressive models. Three different RNN variants, namely, long short-term memory (LSTM), gated recurrent unit (GRU) and bidirectional LSTM (BiLSTM) are employed together with non-linear autoregressive models. A case study on tide level forecasting at many different geographical locations (5 to 11 locations) is conducted. Experimental results demonstrate that the proposed architectures outperform the classical single-task prediction methods.

A novel comparative study of NNAR approach with linear stochastic time series models in predicting tennis player's performance

BackgroundPrediction models have gained immense importance in various fields for decision-making purposes. In the context of tennis, relying solely on the probability of winning a single match may not be sufficient for predicting a player's future performance or ranking. The performance of a tennis player is influenced by the timing of their matches throughout the year, necessitating the incorporation of time as a crucial factor. This study aims to focus on prediction models for performance indicators that can assist both tennis players and sports analysts in forecasting player standings in future matches.MethodologyTo predict player performance, this study employs a dynamic technique that analyzes the structure of performance using both linear and nonlinear time series models. A novel approach has been taken, comparing the performance of the non-linear Neural Network Auto-Regressive (NNAR) model with conventional stochastic linear and nonlinear models such as Auto-Regressive Integrated Moving Average (ARIMA), Exponential Smoothing (ETS), and TBATS (Trigonometric Seasonal Decomposition Time Series).ResultsThe study finds that the NNAR model outperforms all other competing models based on lower values of Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE). This superiority in performance metrics suggests that the NNAR model is the most appropriate approach for predicting player performance in tennis. Additionally, the prediction results obtained from the NNAR model demonstrate narrow 95% Confidence Intervals, indicating higher accuracy and reliability in the forecasts.ConclusionIn conclusion, this study highlights the significance of incorporating time as a factor when predicting player performance in tennis. It emphasizes the potential benefits of using the NNAR model for forecasting future player standings in matches. The findings suggest that the NNAR model is a recommended approach compared to conventional models like ARIMA, ETS, and TBATS. By considering time as a crucial factor and employing the NNAR model, both tennis players and sports analysts can make more accurate predictions about player performance.