Error Index Research Articles

Computational study of associations between the synaptic conductance of STN and GPe and the development of Parkinson's disease.

There is evidence that the subthalamic nucleus (STN) and globus pallidus pars externa (GPe) involve in the development of Parkinson's disease, a neurodegenerative disorder characterized by motor and non-motor symptoms and loss of dopaminergic neurons in which the error index (EI) in firing patterns is widely used to address the related issues. Whether and how this interaction mechanism of STN and GPe affects EI in Parkinson's disease is uncertain. To account for this, we propose a kind of basal ganglia-thalamic network model associated with Parkinson's disease coupled with neurons, and investigate the effect of synaptic conductance of STN and GPe on EI in this network, as well as their internal relationship under EI as an index. The results show a relationship like a piecewise function between the error index and the slope of the state transition function of synaptic conductance from STN to GPe ( ) and from GPe to STN ( ). And there is an approximate negative correlation between EI and . Increasing and decreasing can improve the fidelity of thalamus information transmission and alleviate Parkinson's disease effectively. These obtained results can give some theoretical evidence that the abnormal synaptic releases of STN and GPe may be the symptoms of the development of Parkinson's disease, and further enrich the understanding of the pathogenesis and treatment mechanism of Parkinson's disease.

Employee mental health risk prediction and coping management based on neural network

Abstract In this paper, after dissecting the neural network model, the initial weights and thresholds of the BP neural network are optimized through selection, crossover, mutation and other operations by using the global optimization-seeking ability of the genetic algorithm. The model for predicting employee mental health risks is initially constructed by selecting structural design, structural parameters, and genetic operators. The feasibility of the model in mental health risk prediction was explored based on the indicators of training time, model error and prediction accuracy, and the prediction model was utilized to predict the mental health risk of the employees in Company A and the coping plan for the employees’ mental health risk was established. The results show that the accuracy of the neural network model is 90% and 85%, respectively, during the training and testing processes. The sensitivity and specificity of the training set are 90.00% and 75.06%, respectively, the Yoden index is 0.78, and the Kappa coefficient is 0.69, and the sensitivity and specificity of the test set are 92.00% and 78.05%, which is a good performance, based on which the study is able to predict the risk of mental health of the employees and to guarantee the mental health of the employees in real-time.

A unified hp-HDG framework for Friedrichs' PDE systems

This work proposes a unified hp-adaptivity framework for hybridized discontinuous Galerkin (HDG) method for a large class of partial differential equations (PDEs) of Friedrichs' type. In particular, we present unified hp-HDG formulations for abstract one-field and two-field structures and prove their well-posedness. In order to handle non-conforming interfaces we simply take advantage of HDG built-in mortar structures. With split-type mortars and the approximation space of trace, a numerical flux can be derived via Godunov approach and be naturally employed without any additional treatment. As a consequence, the proposed formulations are parameter-free. We perform several numerical experiments for time-independent and linear PDEs including elliptic, hyperbolic, and mixed-type to verify the proposed unified hp-formulations and demonstrate the effectiveness of hp-adaptation. Two adaptivity criteria are considered: one is based on a simple and fast error indicator, while the other is rigorous but more expensive using an adjoint-based error estimate. The numerical results show that these two approaches are comparable in terms of convergence rate even for problems with strong gradients, discontinuities, and singularities.

Passenger flow forecast of tourist attraction based on MACBL in LBS big data environment

Abstract The existing scenic spot passenger flow prediction models have poor prediction accuracy and inadequate feature extraction ability. To address these issues, a multi-attentional convolutional bidirectional long short-term memory (MACBL)-based method for predicting tourist flow in tourist scenic locations in a location-based services big data environment is proposed in this study. First, a convolutional neural network is employed to identify local features and reduce the dimension of the input data. Then, a bidirectional long short-term memory network is utilized to extract time-series information. Second, the multi-head attention mechanism is employed to parallelize the input data and assign weights to the feature data, which deepens the extraction of important feature information. Next, the dropout layer is used to avoid the overfitting of the model. Finally, three layers of the above network are stacked to form a deep conformity network and output the passenger flow prediction sequence. In contrast to the state-of-the-art models, the MACBL model has enhanced the root mean square error index by at least 2.049, 2.926, and 1.338 for prediction steps of 24, 32, and 60 h, respectively. Moreover, it has also enhanced the mean absolute error index by at least 1.352, 1.489, and 0.938, and the mean absolute percentage error index by at least 0.0447, 0.0345, and 0.0379% for the same prediction steps. The experimental results indicate that the MACBL is better than the existing models in evaluating indexes of different granularities, and it is effective in enhancing the forecasting precision of tourist attractions.

Divergence-conforming methods for transient double-diffusive flows: a priori and a posteriori error analysis

Abstract The analysis of an $\textbf {H}(\textrm {div})$-conforming method for a model of double-diffusive flow in porous media introduced in Bürger, Méndez & Ruiz-Baier (2019, On H(div)-conforming methods for double-diffusion equations in porous media. SIAM J. Numer. Anal., 57,1318–1343) is extended to the time-dependent case. In addition, the efficiency and reliability of residual-based a posteriori error estimators for the steady, semidiscrete and fully discrete problems are established. The resulting methods are applied to simulate the sedimentation of small particles in salinity-driven flows. The method consists of Brezzi–Douglas–Marini approximations for velocity and compatible piecewise discontinuous pressures, whereas Lagrangian elements are used for concentration and salinity distribution. Numerical tests confirm the properties of the proposed family of schemes and of the adaptive strategy guided by the a posteriori error indicators.

Turbofan Engine Health Assessment Based on Spatial-Temporal Similarity Calculation.

Aiming at the problem of the remaining useful life prediction accuracy being too low due to the complex operating conditions of the aviation turbofan engine data set and the original noise of the sensor, a residual useful life prediction method based on spatial-temporal similarity calculation is proposed. The first stage is adaptive sequence matching, which uses the constructed spatial-temporal trajectory sequence to match the sequence to find the optimal matching sample and calculate the similarity between the two spatial-temporal trajectory sequences. In the second stage, the weights of each part are assigned by the two weight allocation algorithms of the weight training module, and then the final similarity is calculated by the similarity calculation formula of the life prediction module, and the final predicted remaining useful life is determined according to the size of the similarity and the corresponding remaining life. Compared with a single model, the proposed method emphasizes the consistency of the test set and the training set, increases the similarity between samples by sequence matching with other spatial-temporal trajectories, and further calculates the final similarity and predicts the remaining use through the weight allocation module and the life prediction module. The experimental results show that compared with other methods, the root mean square error (RMSE) index and the remaining useful life health score (Score) index are reduced by 12.6% and 14.8%, respectively, on the FD004 dataset, and the RMSE index is similar to that in other datasets; the Score index is reduced by about 10%, which improves the prediction accuracy of the remaining useful life and can provide favorable support for the operation and maintenance decision of turbofan engines.

Super-Resolution Reconstruction of CT Images Based on Multi-scale Information Fused Generative Adversarial Networks.

The popularization and widespread use of computed tomography (CT) in the field of medicine evocated public attention to the potential radiation exposure endured by patients. Reducing the radiation dose may lead to scattering noise and low resolution, which can adversely affect the radiologists' judgment. Hence, this paper introduces a new network called PANet-UP-ESRGAN (PAUP-ESRGAN), specifically designed to obtain low-dose CT (LDCT) images with high peak signal-to-noise ratio (PSNR) and high resolution (HR). The model was trained on synthetic medical image data based on a Generative Adversarial Network (GAN). A degradation modeling process was introduced to accurately represent realistic degradation complexities. To reconstruct image edge textures, a pyramidal attention model call PANet was added before the middle of the multiple residual dense blocks (MRDB) in the generator to focus on high-frequency image information. The U-Net discriminator with spectral normalization was also designed to improve its efficiency and stabilize the training dynamics. The proposed PAUP-ESRGAN model was evaluated on the abdomen and lung image datasets, which demonstrated a significant improvement in terms of robustness of model and LDCT image detail reconstruction, compared to the latest real-esrgan network. Results showed that the mean PSNR increated by 19.1%, 25.05%, and 21.25%, the mean SSIM increated by 0.4%, 0.4%, and 0.4%, and the mean NRMSE decreated by 0.25%, 0.25%, and 0.35% at 2[Formula: see text], 4[Formula: see text], and 8[Formula: see text] super-resolution scales, respectively. Experimental results demonstrate that our method outperforms the state-of-the-art super-resolution methods on restoring CT images with respect to peak signal-to-noise ratio (PSNR), structural similarity (SSIM) and normalized root-mean-square error (NRMSE) indices.

A Novel Fractional Multi-Order High-Gain Observer Design to Estimate Temperature in a Heat Exchange Process

In the present manuscript, we design a fractional multi-order high-gain observer to estimate temperature in a double pipe heat exchange process. For comparison purposes and since we want to prove that when using our novel technique, the estimation is more robust than the classical approach, we design a non-fractional high-gain observer, and then we compare the performance of both observers. We consider three scenarios: The first one considers the estimation of the system states by measuring only one output with no noise added on it and under ideal conditions. Second, we add noise to the measured output and then reconstruct the system states, and, third, in addition to the noise, we increase the gain parameter in both observers (non-fractional and fractional) due to the fact that we want to prove that the robustness changes in this parameter. The results showed that, using our approach, the estimated states can be recovered under noise circumstances in the measured output and under parameter change in the observer, contrary to using classical (non-fractional) observers where the states cannot be recovered. In all our tests, we used the normalized root-mean-square, integral square error, and integral absolute error indices, resulting in a better performance for our approach than that obtained using the classical approach. We concluded that our fractional multi-order high-gain observer is more robust to input noise than the classical high-gain observer.

Evaluation Modeling of Electric Bus Interior Sound Quality Based on Two Improved XGBoost Algorithms Using GS and PSO

There is no doubt that traffic noise has become one of the main sources of urban noise, and the electric bus, as an important means of transport frequently used by people in daily life, has a direct impact on the psychological and auditory health of passengers due to its interior noise characteristics. Consequently, studying electric bus sound quality is an important way to improve vehicle performance and comfort. In this paper, eight electric buses were selected and 64 noise samples were measured. Acoustic comfort was taken as an evaluation index, professionals were organized to complete the subjective evaluation tests for all noise samples based on rank score comparison (RSC). And nine psycho-acoustic objective parameters such as loudness, sharpness and roughness were calculated using ArtemiS software to establish the sound quality database of electric buses. Aiming at the practical application requirements of high-precision modeling of acoustic comfort in vehicles, this paper presented two improved extreme gradient boosting (XGBoost) algorithms based on grid search (GS) method and particle swarm optimization (PSO), respectively, with objective parameters and acoustic comfort as input and output variables, and established three regression models of standard XGBoost, GS-XGBoost and PSO-XGBoost through data training. Finally, the calculation results of three indexes of average relative error, square root error and correlation coefficient indicate that the proposed PSO-XGBoost model is significantly better than GS-XGBoost and standard XGBoost, with its prediction accuracy as high as 97.6 %. This model is determined as the evaluation model of interior acoustic comfort for this case, providing a key technical support for future sound quality optimization of electric buses.

An examination of the impact of the selected error criterion on the ACO performance in BLDC drives

Brushless direct current (BLDC) motor drives are becoming increasingly popular in motion control applications. As a result, a low-cost but effective BLDC motor speed controller is required. They are used in industrial and home appliances with conventional motor drive technology, such as robots, refrigerators and air conditioning systems. Brushless direct current (BLDC) drives are well known for their high efficiency and low maintenance. This work aims to design a non-conventional PID controller via Ant Colony Optimisers (ACO) in order to obtain an efficient speed performance for a BLDC motor "namely, Maxon EC flat". Moreover, when ACO is used for tuning of PID control, the objective function is required. Therefore, in this work, four different objective functions which are MSE, ISE, IAE, and ITAE are applied and their performance was compared in terms of motor' speed stability. In a simulation environment, the PID controller is used to control the speed of BLDC motors under three testing conditions which are Small, medium, and high inertia loads. The simulation results demonstrate that MSE offers the best performance under low and high inertial loading cases. Whereas, IAE has been superior compared with other criterions when medium loads are applied. Moreover, this paper shows a stability speed- power consumption trade-off problem. In other words, achieving a fast stability via any type of error indices doesn’t guarantee a low amount of consuming energy.

A computational solution of relativistic Thomas-Fermi equation of an atom with exponential collocation genetic algorithm optimization

An Exponential Collocation Genetic Algorithm Optimization (ECGAO) is considered for solving the relativistic Thomas-Fermi equation of the statistical model of an atom. The governing model equation has been transformed into an optimization problem by collocation technique using exponential basis. Then, fitness function is formulated in terms of nonlinear coupled residual equations. The fitness values achieved remained of the order of10−4. The improvement in the ionization energy values for the heavier atoms from the ECGAO came with the small percentage error for Z=80,86and92 as 1.418630%, 0.301381% and 0.018417% respectively. The accuracy and stability of the proposed method were verified using Mean Absolute Deviation (MAD), Theil's Inequality Coefficient (TIC), and Mean Fitness Value (MFV). Approximately 74% of the trial runs have successfully achieved these low statistical error indices values (in the order of10−4to10−3) for the relativistic Thomas-Fermi model. After several experimentations, we have determined that the optimal values for crossover fraction, elite count, and migration fraction interval as 0.4, 16, 0.6, and 10, respectively. The proposed methodology is computationally consistent and more accurate for scientific investigations of the relativistic Thomas-Fermi equation.

Predicting dynamic compressive strength of frozen-thawed rocks by characteristic impedance and data-driven methods

In cold regions, the dynamic compressive strength (DCS) of rock damaged by freeze-thaw weathering significantly influences the stability of rock engineering. Nevertheless, testing the dynamic strength under freeze-thaw weathering conditions is often both time-consuming and expensive. Therefore, this study considers the effect of characteristic impedance on DCS and aims to quickly determine the DCS of frozen-thawed rocks through the application of machine-learning techniques. Initially, a database of DCS for frozen-thawed rocks, comprising 216 rock specimens, was compiled. Three external load parameters (freeze-thaw cycle number, confining pressure, and impact pressure) and two rock parameters (characteristic impedance and porosity) were selected as input variables, with DCS as the predicted target. This research optimized the kernel scale, penalty factor, and insensitive loss coefficient of the support vector regression (SVR) model using five swarm intelligent optimization algorithms, leading to the development of five hybrid models. In addition, a statistical DCS prediction equation using multiple linear regression techniques was developed. The performance of the prediction models was comprehensively evaluated using two error indexes and two trend indexes. A sensitivity analysis based on the cosine amplitude method has also been conducted. The results demonstrate that the proposed hybrid SVR-based models consistently provided accurate DCS predictions. Among these models, the SVR model optimized with the chameleon swarm algorithm exhibited the best performance, with metrics indicating its effectiveness, including root mean square error (RMSE) = 3.9675, mean absolute error (MAE) = 2.9673, coefficient of determination (R2) = 0.98631, and variance accounted for (VAF) = 98.634. This suggests that the chameleon swarm algorithm yielded the most optimal results for enhancing SVR models. Notably, impact pressure and characteristic impedance emerged as the two most influential parameters in DCS prediction. This research is anticipated to serve as a reliable reference for estimating the DCS of rocks subjected to freeze-thaw weathering.

The Influence of Steganographic Methods and QR Code Resolutions on Data Hiding in Cover Images

Abstract This work deals with digital image processing using the steganography technique in real life. Various steganography techniques face data authentication, data security, and copyright issues. Due to the fact that the problem of data security is currently very topical, these techniques are often sought after. This is related to the constant development of new algorithms that provide solutions that will safely hide the secret message in the image and at the same time will be resistant to various types of attacks. The motivation for writing this work lies in the technique of representing a secret message using a Quick Response code. Later in this work is comparison between our results and results of approach made by scientific community, which works with data hiding within steganographic principles. The secret message is written in the least significant bit plane of the cover image, which ensures that the modification of the image cannot be detected by the naked eye. The proposed solution is evaluated by mathematical quality assessment parameters Peak signal-to-noise ratio, Mean squared error, Normalized cross-correlation and Structural similarity index.

Two‐stage diffusion model deriving FDG‐PET from T1 Weighted Magnetic Resonance Images for diagnosis of Alzheimer’s disease

AbstractBackgroundAlzheimer’s Disease (AD) is a neurodegenerative disease which is characterized by cognitive and functional impairment, and defined by triad of Amyloid status, Tau pathology, and Neuroimaging marker of neurodegeneration or neuronal injury. An early diagnosis of AD can be challenging and it can be detected earlier in brain functional imaging than brain structural imaging.MethodWe develop a pipeline for synthesizing FDG‐PET/MRI from source MRI‐T1‐Weighted (MRI‐T1W) images based on denoising diffusion mechanism [1]. The pipeline includes a forward pass which encodes the source MRI‐T1WI images to gaussian noise space, and a backward pass which generates the corresponding FDG‐PET from the derived noises with repeated denoising steps. Furthermore, to validate the effectiveness of the synthesized FDG‐PET images, we also develop multiple types of classifiers and the experiments for both single input of MRI‐T1WI and joint input of MRI‐T1WI and synthesized FDG‐PET.ResultThe experiments are performed on 1036 of FDG‐PET/MRI pairs (286,474, 276 for Cognitive Normal, Mild Cognitive Impaiement and Alzheimer’s Disease each) are obtained from ADNI [2] datasets and display the promising results with low Mean Absolute Error (MAE) and high Structural Similarity Index Measure (SSIM) for the two stage diffusion denoising based FDG‐PET synthesis pipeline. The results for the additional classification experiments also show that in most cases the joint input enhances the classifiers' performance in accuracy and F1‐score. The results also indicate that the synthesized FDG‐PET images are not only visually similar to the ground truth images, but also improve the performance of machine learning based AD diagnosis.ConclusionThis work provides support for the notion that machine learning‐derived image analysis may be a useful approach to improving the diagnosis of AD.Reference:[1] Ho, J., Jain, A., & Abbeel, P. (2020). Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems, 33, 6840‐6851.[2] Petersen, R., Aisen, P. S., Beckett, L. A., Donohue, M. C., Gamst, A. C., Harvey, D. J., … & Toga, A. W. (2010). Alzheimer’s disease neuroimaging initiative (ADNI). Neurology, 74(3), 201‐209.

Toward a certified greedy Loewner framework with minimal sampling

We propose a strategy for greedy sampling in the context of non-intrusive interpolation-based surrogate modeling for frequency-domain problems. We rely on a non-intrusive and cheap error indicator to drive the adaptive selection of the high-fidelity samples on which the surrogate is based. We develop a theoretical framework to support our proposed indicator. We also present several practical approaches for the termination criterion that is used to end the greedy sampling iterations. To showcase our greedy strategy, we numerically test it in combination with the well-known Loewner framework. To this effect, we consider several benchmarks, highlighting the effectiveness of our adaptive approach in approximating the transfer function of complex systems from a few samples.

Distribution network power flow calculation based on the BPNN optimized by GA‐ADAM

AbstractPower system operation and control are based on power flow calculations. In order to solve the uncertainty of the increasing penetration of renewable energy, the voltage fluctuation at the load point increases in the distribution network, and the inaccuracy of the power flow calculation due to the insufficient power flow data collection capability of the traditional power system. In this paper, a data‐driven power flow analysis model is proposed, a back propagation neural network combined with genetic algorithm (GA) and adaptive moment estimation (ADAM) optimization algorithm model is constructed to analyze the power flow calculation method of distribution networks under stochasticity. Firstly, the power flow initial value information, topology characteristics, and power factor index are introduced to construct a training set, and the mapping relationship between bus voltage and power is fully explored by training the regression model. Second, the GA‐ADAM algorithm is used to optimize the initial values and weight parameters of the model. Finally, it is verified based on IEEE‐33 bus distribution model, and the model is used for power flow calculation, and compared with other methods through each relevant error evaluation indicators. The results show that the model constructed in this paper has small error indicators and high accuracy, which improves the efficiency and accuracy of power flow calculation.

A new hybrid model SARIMA-ETS-SVR for seasonal influenza incidence prediction in mainland China.

Seasonal influenza is a serious public health issue in China. This study aimed to develop a new hybrid model for seasonal influenza incidence prediction and provide reference information for early warning management before outbreaks. Data on the monthly incidence of seasonal influenza between 2004 and 2018 were obtained from the China Public Health Science Data Center website. A single seasonal autoregressive integrated moving average (SARIMA) model and a single error trend and seasonality (ETS) model were built. On this basis, we constructed SARIMA, ETS, and support vector regression (SARIMA-ETS-SVR) hybrid model. The prediction performance was determined by comparing mean absolute error (MAE), mean square error (MSE), mean absolute percentage error (MAPE), and root mean square error (RMSE) indices. The optimum SARIMA model was SARIMA (0,1,0) (0,0,1)12. Error trend and seasonality (ETS) (M,A,M) was the SARIMA optimal model. For the fitting performance, the SARIMA-ETS-SVR hybrid model achieved the lowest values of MAE, MSE, and RMSE, in addition to the MAPE. In terms of predictive performance, the SARIMA-ETS-SVR hybrid model had the lowest MAE, MSE, MAPE, and RMSE values among the three models. The study demonstrated that the SARIMA-ETS-SVR hybrid model provides better generalization ability than a single SARIMA model and a single ETS model, and the predictions will provide a useful tool for preventing this infectious disease.

Suitability analysis of human activities over Antarctic ice shelves: an integrated assessment of natural conditions based on machine learning algorithms

ABSTRACT Human activities increase significantly over Antarctic ice shelves. However, they are constantly faced with danger posed by the harsh environment. For decision-making, it is a prerequisite to have the macro-scale suitability information about human activity site selection. Here, we define a new index, the human activity suitability (HAS) index, to quantitatively analyze the locational suitability of human activity sites over Antarctic ice shelves. Two multi-criteria decision analysis methods (AHP + Entropy, TOPSIS) and three machine learning methods (support vector machine, random forest and logistic regression) are tested to develop HAS maps. Nine conditioning factors about ice surface features, ice shelf stability, meteorology and topography are generated as input parameters. The accuracy of the proposed models is evaluated using metrics such as the area under curve (AUC-ROC), root mean square error, overall accuracy and kappa index. The results indicate that the Random Forest performs best. The HAS map exhibits great heterogeneity driven by the synergistic influence of multiple factors. Areas in low HAS classes are concentrated at Crosson, Brunt, Thwaites and the edge of some ice shelves, implying the complex environment in these regions. The findings can provide a new insight for forecasting the potential human footprint and support sustainability research in Antarctica.

Construction of Transformer Fault Diagnosis and Prediction Model Based on Deep Learning

The current intelligent diagnosis and prediction methods for transformer faults are prone to low diagnostic accuracy and insufficient trend prediction ability when the fault categories are imbalanced. Therefore, a fault diagnosis and prediction model for transformers was constructed using a deep learning framework. The fault diagnosis model was constructed using a focus loss stack sparse noise reduction autoencoder on the deep learning framework. The prediction model was constructed by fusing long and short term memory networks on the basis of tree structure Parzen optimization, and the two models were validated. The results obtained through validation of the diagnostic model indicate that, when the actual hidden layer is set to 3 and the quantity of neurons is 58, the model accuracy during training and testing reaches 97.5% and 92.5% respectively. After adding 0.001 times the Gaussian white noise, the model accuracy was significantly lifted, so this study set the Gaussian noise coefficient to 0.001. In the comparison with baseline models, the actual classification ability of the research model samples is strong, significantly improving the fault diagnosis ability. In the validation of the prediction model, the three error index values of the research model in the single prediction step of CH4 concentration were 0.0699, 0.0540, and 0.8481%, respectively, and proved to be were lower than in the case of the baseline model. The three error values in the two-step prediction are 0.0194, 0.0161, and 0.6535%, which are also lower than in case of the baseline model. Overall, the diagnosis and prediction model proposed in this paper can provide real-time future numerical predictions of dissolved gas analysis and monitoring data in transformer oil. Furthermore, the research outilnes the future development trend of monitoring and measurement through application of tensor flow deep learning framework in transformer fault diagnosis. The attained prediction results are innovative, and could well complete the purpose of actual transformer fault diagnosis and early warning.

Efficient adsorption of Cr (VI) onto hematite nanoparticles: ANN, ANFIS modelling, isotherm, kinetic, thermodynamic studies and mechanistic insights

Hematite nanoparticles (AF–Fe2O3NPs) were prepared through a simple method utilizing Acacia falcata leaf extract in this investigation. The nanoparticles were extensively characterized to understand their specific properties. FESEM images revealed agglomerated surface morphology, while EDS confirmed the existence of elemental components, including Fe, O, and C. The mesoporous nature of AF–Fe2O3NPs with a pore diameter of 3.77 nm was determined through BET studies. XRD analysis indicated the crystallinity, with lattice parameters characteristic of hematite nanoparticles (a = 0.504 nm and c = 1.381 nm). Superparamagnetic property of the AF–Fe2O3NPs was affirmed from the saturation magnetization (2.98 emu/g) without any hysteresis. Subsequently, AF–Fe2O3NPs were used as adsorbent for the removal of Cr (VI) from aqueous solution. The experimental data were subjected to machine learning (ML) models, specifically ANN and ANFIS, to predict Cr (VI) removal. Both ML models exhibited excellent predictive capabilities, with high R2 values (>0.99) and low error indices such as MSE, RMSE, and MAE. Furthermore, comprehensive kinetic, isotherm, and thermodynamic studies were conducted to gain insights into the behavior and sorption mechanisms of Cr (VI). The Hill model, a statistical physics model, demonstrated an outstanding fit compared to conventional isotherms. It revealed a saturation adsorption potential of 12.91 mg/g at pH 2, 1.5 g/L dose, and a temperature of 30 °C, corroborating physisorption as the dominant mechanism. XPS results confirmed Cr (VI) reduction to Cr (III) through the appearance of specific peaks at 577.18 and 587.08 eV. Thermodynamic investigations established the endothermicity and spontaneity of the adsorption. In summary, the hematite nanoparticles synthesized in this study exhibit promising potential to remove Cr (VI) from aqueous streams, making them a viable option for water treatment applications.