Recursive Method Research Articles

Orientable sequences over non-binary alphabets

AbstractWe describe new, simple, recursive methods of construction for orientable sequences over an arbitrary finite alphabet, i.e. periodic sequences in which any sub-sequence of n consecutive elements occurs at most once in a period in either direction. In particular we establish how two variants of a generalised Lempel homomorphism can be used to recursively construct such sequences, generalising previous work on the binary case. We also derive an upper bound on the period of an orientable sequence.

Colored vertex models and Iwahori Whittaker functions

We give a recursive method for computing all values of a basis of Whittaker functions for unramified principal series invariant under an Iwahori or parahoric subgroup of a split reductive group G over a nonarchimedean local field F. Structures in the proof have surprising analogies to features of certain solvable lattice models. In the case G=GLr\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$G=\ extrm{GL}_r$$\\end{document} we show that there exist solvable lattice models whose partition functions give precisely all of these values. Here ‘solvable’ means that the models have a family of Yang–Baxter equations which imply, among other things, that their partition functions satisfy the same recursions as those for Iwahori or parahoric Whittaker functions. The R-matrices for these Yang–Baxter equations come from a Drinfeld twist of the quantum group Uq(gl^(r|1))\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$U_q(\\widehat{\\mathfrak {gl}}(r|1))$$\\end{document}, which we then connect to the standard intertwining operators on the unramified principal series. We use our results to connect Iwahori and parahoric Whittaker functions to variations of Macdonald polynomials.

Minimizing distance between distribution functions: discrete counterparts to continuous random variables with applications in non-life insurance and stochastic reliability

In this work, we propose a novel family of procedures for deriving a discrete counterpart to a continuous probability distribution. They are based on a class of distances between cumulative distribution functions, including the Cramér, the Cramér-von Mises, and the Anderson-Darling distances as particular cases. The discrete counterpart is defined and derived as the random variable which minimizes its distance to the assigned continuous probability distribution among all the discrete random variables supported on the set of integers (or positive integers). Applications are provided with reference to the exponential and the normal distributions, among others; the discrete counterparts are derived, and their main properties are discussed, also in comparison with the one obtained through an existing discretization technique based on the preservation of the cumulative distribution function at integer values. Parameter estimation for these discrete analogs is discussed, along with an analysis of two real datasets, where they are compared in terms of goodness-of-fit with some popular discrete distributions. Furthermore, in order to highlight the effectiveness and the benefits derived from the proposed discretization procedures, we illustrate two practical applications in actuarial science and in reliability engineering. In the former case, the problem of determining the distribution of the total claims amount for a non-life insurance portfolio is considered, where the claim sizes can be modelled as iid random variables, and the number of claims is random as well. Actuaries use a recursive calculation method based on Panjer's formula, which requires an appropriate discretization of the individual claim distribution, and therefore the proposed procedures can be used. Since we consider two simple cases where the distribution of the total claims amount is analytically acquirable, the efficacy of the discretization procedures in the final approximation can be easily assessed and turns out to be satisfactory, especially when compared to the existing discretization. The latter case considers the determination of the reliability parameter for a complex stress-strength model. Here, the approximation by discretization is compared to Monte Carlo simulation and shown to be relevant: with a comparable if not smaller computational effort, discretization leads to similar results as simulation. Such discretizations can also naturally be applied to more complex problems such as scenario generation in stochastic programming. R code for this article is provided as supplementary material.

Lithium battery state of charge estimation based on improved variable forgetting factor recursive least squares method and adaptive Kalman filter joint algorithm

As one of the core functions of the battery management system, battery state of charge (SOC) estimation is crucial to battery life and safety. As the traditional recursive least squares method cannot adapt well to complex variable current conditions, this paper proposes a SOC estimation method that combines the improved variable forgetting factor recursive least squares (IVFFRLS) and the adaptive extended Kalman filter (AEKF). First, IVFFRLS removes the rounding operation of the original algorithm to improve the sensitivity to errors and uses a genetic algorithm to optimize the upper and lower bounds of the variable forgetting factor and the sensitivity coefficient to improve the accuracy of the VFFRLS algorithm. Meanwhile, AEKF introduces a noise covariance adaptive update link based on the covariance matching method to correct the system's process noise Q and measurement noise R in real time to improve the SOC estimation accuracy. Based on the second-order RC equivalent circuit model, the method proposed in this paper has good accuracy and robustness under four different working conditions. The experimental results show that compared with traditional methods, the proposed IVFFRLS-AEKF algorithm has higher SOC estimation accuracy and better robustness.

Joint buffetings suppression and trajectory tracking by fuzzy-based super-twist sliding mode control: Application to a fast parallel robot for PnP operations

This paper deals with the suppression of robotic joint buffetings for enhanced precision of trajectory tracking by means of fuzzy-based super-twist sliding mode control, which is illustrated with a fast pick-and-place parallel robot for material handling. Prior to control design, the joint motions and torques are measure to identify the dynamic parameters of the robot with recursive least square method, which is experimentally validated for the further model-based control design. In order to suppress the joint buffetings and to improve the tracking accuracy, the control law by integrating fuzzy algorithm and second-order sliding mode control is designed, where the control performance is evaluated by observing the joint dynamics, compared to the classical computed torque control and fuzzy sliding mode variable structure control. The experimental results and comparative study show the effectiveness of the developed control scheme, regarding the joint buffetings suppression and trajectory tracking precision. The main contribution lies in the integrated fuzzy algorithm and second-order sliding mode control for the model-based control design, with acceptable computational cost and trajectory tracking accuracy, from the perspective of actual engineering application.

Determination of Possible Biomarkers for Predicting Well-Differentiated Thyroid Cancer Recurrence by Different Ensemble Machine Learning Methods

Objective: Well-differentiated thyroid cancer (WDTC) is the most common thyroid malignancy and although it is curable, the risk of recurrence is high. In this study, classification algorithms based on clinicopathologic features of WDTC patients were used to determine the possible of recurrence in WDTC and to evaluate potential predictive factors, and possible biomarkers based on the optimal model were identified. Method: In this study, open access data on 383 patients with WDTC, 108 with recurrence and 275 without recurrence, were used. In order to predict recurrence in WDTC patients, features were selected using recursive feature elimination variable selection method among features and classification was performed with two ensemble learning methods (Random Forest, Adaboost). Results: Two different ensemble learning models used to classify recurrence in WDTC were Random Forest with an accuracy of 0.957, sensitivity of 0.889, specificity of 0.978, positive predictive value of 0.923, negative predictive value of 0.967, Matthews correlation coefficient of 0.878, G-mean of 0.945, F1-score of 0.906, and accuracy of 0.940, sensitivity of 0.889, specificity of 0.955, positive predictive value of 0.857, negative predictive value of 0.966, Matthews correlation coefficient of 0.833, G-mean of 0.910, F1-score of 0.873. Conclusion: According to variable importance based on the Random Forest, the 5 possible clinical biomarkers for predicting WDTC recurrence are Response, Risk, Node, Tumor, and age. In the light of these findings, patient management and treatment planning can be organized.

Neural learning control for sampled‐data nonlinear systems based on Euler approximation and first‐order filter

AbstractThe primary focus of this research paper is to explore the realm of dynamic learning in sampled‐data strict‐feedback nonlinear systems (SFNSs) by leveraging the capabilities of radial basis function (RBF) neural networks (NNs) under the framework of adaptive control. First, the exact discrete‐time model of the continuous‐time system is expressed as an Euler strict‐feedback model with a sampling approximation error. We provide the consistency condition that establishes the relationship between the exact model and the Euler model with meticulous detail. Meanwhile, a novel lemma is derived to show the stability condition of a digital first‐order filter. To address the non‐causality issues of SFNSs with sampling approximation error and the input data dimension explosion of NNs, the auxiliary digital first‐order filter and backstepping technology are combined to propose an adaptive neural dynamic surface control (ANDSC) scheme. Such a scheme avoids the ‐step time delays associated with the existing NN updating laws derived by the common ‐step predictor technology. A rigorous recursion method is employed to provide a comprehensive verification of the stability, guaranteeing its overall performance and dependability. Following that, the NN weight error systems are systematically decomposed into a sequence of linear time‐varying subsystems, allowing for a more detailed analysis and understanding. In order to ensure the recurrent nature of the input variables, a recursive design is employed, thereby satisfying the partial persistent excitation condition specifically designed for the RBF NNs. Meanwhile, it can verify that the NN estimated weights converge to their ideal values. Compared with the common ‐step predictor technology, there is no need to redesign the learning rules due to the designed NN weight updating laws without time delays. Subsequently, after capturing and storing the convergence weights, a novel neural learning dynamic surface control (NLDSC) scheme is specifically formulated by leveraging the acquired knowledge. The introduced methodology reduces computational complexity and facilitates practical implementation. Finally, empirical evidence obtained from simulation experiments validates the efficacy and viability of the proposed methodology.

Impact of Fe-impurity centers on phonon subsystem of wurtzite-type ZnO

The paper addresses the question of the structural and vibrational properties of Fe-doped ZnO in the wurtzite structure with a lattice without an inversion center. The ZnO crystals containing Fe impurities in different charged states are studied by means of density functional theory (DFT) and potential-based methods. A first-principles simulation is performed to determine the local atomic configurations near the considered defects. The DFT results are compared with those obtained using the shell model. Both approaches give a similar pattern of lattice distortion around the Fe-impurity centers occupying cation sites in the isoelectronic charge state Fe2＋ and single-positive-charge state Fe3＋. The phonon local symmetrized densities of states projected onto the displacement of ions surrounding the defects are calculated by a well-established recursion method. The frequencies of defect vibrations of various symmetry types induced by Fe impurities are determined. The calculations made it possible to interpret the structure of the phonon sideband accompanying the zero-phonon line in polarized emission spectra attributed to the Fe3＋ intracenter transitions, as well as to estimate the role of Fe ions in the formation of observed peaks.

Estimation of equilibration time scales from nested fraction approximations.

We consider an autocorrelation function of a quantum mechanical system through the lens of the so-called recursive method, by iteratively evaluating Lanczos coefficients or solving a system of coupled differential equationsin the Mori formalism. We first show that both methods are mathematically equivalent, each offering certain practical advantages. We then propose an approximation scheme to evaluate the autocorrelation function and use it to estimate the equilibration time τ for the observable in question. With only a handful of Lanczos coefficients as the input, this scheme yields an accurate order of magnitude estimate of τ, matching state-of-the-art numerical approaches. We develop a simple numerical scheme to estimate the precision of our method. We test our approach using several numerical examples exhibiting different relaxation dynamics. Our findings provide a practical way to quantify the equilibration time of isolated quantum systems, a question which is both crucial and notoriously difficult.

Article Review: Relationship between Toxoplasmosis and other Diseases

Water provision is sensitive to climate change, and agricultural production and food supply are sensitive to water availability. Water scarcity affects food security and agricultural economic development through changes in agricultural production and changes in the composition of produced goods. Recent droughts also led to a decrease in the volume of water allocated to agriculture, which led to a decrease in total agricultural production and exports, and this has subsequent impacts on food security and economic development. The research aimed to measure the impact of water scarcity on agricultural economic development for the period 1990-2022. The research included three behavioral equations with three endogenous variables: the cultivated area, the value of agricultural output, and the value of gross domestic product, and four exogenous variables: the amount of available water, agricultural labor, and the value of agricultural investments and the income of other sectors, the studied model is called the sequential model, which was estimated using the Recursive method, using the ordinary least squares (OLS) method. The results indicated that increasing the amount of available water will lead to an increase in the cultivated areas by 141,129.2 dunums, and that increasing one thousand dunums of the cultivated area will increase agricultural output by 0.00821, and that agricultural labor is inversely proportional to agricultural output. It became clear that if the income of the rest of the sectors increased by one unit, the domestic product would increase by 0.1873. Water scarcity will reduce cultivated areas, which in turn will decrease agricultural output, causing the value of agricultural output to decrease and its contribution to the gross domestic product to decrease. In turn, it will have serious repercussions on agricultural economic development. Therefore, the research recommends the necessity of integrated water management and improving the efficiency of its use, as well as the application of modern technologies in agriculture, such as sprinkler irrigation, hydroponics, and redrawing crop compositions to ensure maximizing the net return per unit of water.

Association of hemoglobin-to-red cell distribution width ratio with the three-month outcomes in patients with acute ischemic stroke.

To explore the association of Hemoglobin-to-Red Cell Distribution Width Ratio (HRR) with the risk of three-month unfavorable outcomes in acute ischemic stroke (AIS). A secondary analysis was conducted based on a prospective cohort study. A total of 1,889 patients with AIS treated in South Korea from January 2010 to December 2016 were enrolled. Multivariable logistic regression was conducted to investigated the independent relationship between HRR and risk of three-month unfavorable outcomes in AIS. Fitted smoothing curves were used to determine non-linear correlations. The recursive method was employed to explore the turning point and build a two-piece linear regression model. In addition, a set of subgroup analyses were carried out to evaluate the relationship between HRR and risk of three-month unfavorable outcomes. Multivariate analysis in which potential confounders were adjusted for indicated that the risk of unfavorable outcomes was reduced by 10% for each unit increased of HRR [OR = 0.90, 95% CI: 0.84-0.96, p = 0.0024]. In addition, a non-linear relationship was observed between HRR and risk of three-month unfavorable outcomes, which had an inflection point of HRR was 10.57. The effect sizes and the confidence intervals on the left side of the inflection point were 0.83 (0.75, 0.91), p = 0.0001. On the right side of the inflection point, no association was found between HRR and the risk of three-month unfavorable outcomes. This study demonstrates a negative association between HRR and risk of three-month unfavorable outcomes. The relationship between HRR and risk of three-month unfavorable outcomes is non-linear. The correlation is negative for HRR values less than 10.57. For, HRR higher than 10.57, HRR is not associated with the risk of three-month unfavorable outcomes.

Breast histopathological imaging using ultra-fast fluorescence confocal microscopy to identify cancer lesions at early stage.

Ultrafast fluorescent confocal microscopy is a hypothetical approach for breast cancer detection because of its potential to achieve instantaneous, high-resolution images of cellular-level tissue features. Traditional approaches such as mammography and biopsy are laborious, invasive, and inefficient; confocal microscopy offers many benefits over these approaches. However, confocal microscopy enables the exact differentiation of malignant cells, the expeditious examination of extensive tissue sections, and the optical sectioning of tissue samples into tiny slices. The primary goal should be to prevent cancer altogether, although detecting it early can help achieve that objective. This research presents a novel Breast Histopathology Convolutional Neural Network (BHCNN) for feature extraction and recursive feature elimination method for selecting the most significant features. The proposed approach utilizes full slide images to identify tissue in regions affected by invasive ductal carcinoma. In addition, a transfer learning approach is employed to enhance the performance and accuracy of the models in detecting breast cancer, while also reducing computation time by modifying the final layer of the proposed model. The results showed that the BHCNN model outperformed other models in terms of accuracy, achieving a testing accuracy of 98.42% and a training accuracy of 99.94%. The confusion matrix results show that the IDC positive (+) class achieved 97.44% accuracy and 2.56% inaccurate results, while the IDC negative (-) class achieved 98.73% accuracy and 1.27% inaccurate results. Furthermore, the model achieved less than 0.05 validation loss. RESEARCH HIGHLIGHTS: The objective is to develop an innovative framework using ultra-fast fluorescence confocal microscopy, particularly for the challenging problem of breast cancer diagnosis. This framework will extract essential features from microscopy and employ a gradient recurrent unit for detection. The proposed research offers significant potential in enhancing medical imaging through the provision of a reliable and resilient system for precise diagnosis of breast cancer, thereby propelling the progression of state-of-the-art medical technology. The most suitable feature was determined using BHRFE optimization techniques after retrieving the features by proposed model. Finally, the features chosen are integrated into a proposed methodology, which is then classified using a GRU deep model. The aforementioned research has significant potential to improve medical imaging by providing a complex and reliable system for precise evaluation of breast cancer, hence advancing the development of cutting-edge medical technology.

Improved rank-based recursive feature elimination method based ovarian cancer detection model via customized deep architecture

BackgroundOvarian cancer is often considered the most lethal gynecological cancer because it tends to be diagnosed at an advanced stage, leading to limited treatment options and poorer outcomes. Several factors contribute to the challenges in managing ovarian cancer, namely rapid metastasis, genetic factors, reproductive history, etc. This necessitates the prompt and precise diagnosis of ovarian cancer in order to carry out efficient treatment plans and give patients who are all impacted by OC the care and support they need. MethodsThis CCLSTM model is suggested under four essential stages including preprocessing, feature extraction, feature selection and detection. Initially, the input data is preprocessed using Improved Two-step Data Normalization. Subsequently, features such as statistical, modified entropy, raw features and mutual information are extracted from the normalized data. Next, obtained features undergo the Improved Rank-based Recursive Feature Elimination method (IR-RFE) to select the most suitable features. Finally, the proposed CCLSTM model takes the selected features as input and provides a final detection outcome. ResultsFurthermore, the performance of the proposed CCLSTM technique is examined through a thorough assessment using diverse analyses Additionally, the CCLSTM schemes show a sensitivity value of 0.948, whereas the sensitivity ratings for ALO-LSTM + ALOCNN, Bi-GRU, LSTM, RNN, KNN, CNN, and DCNN are 0.808, 0.893, 0.829, 0.851, 0.765, 0.872, and 0.893, respectively. ConclusionIn the end, the development of CNN and the addition of LSTM technique have produced an ovarian cancer detection technique that is more accurate and consistent compared to other existing strategies.

Design and Motion Control of Master-Slave Control Endotracheal Intubation Robot.

Master-slave remote control technology allows patients to be treated promptly during transport and also reduces the risk of contagious infections. Endotracheal intubation, guided by endoscopy and a master-slave system, enables doctors to perform the procedure efficiently and accurately. In this paper, we present the development of a master-slave controlled endotracheal intubation robot (EIR). It is based on operation incremental mapping, a weighted recursive average filtering method to reduce vibration, and a virtual fixture designed to reduce mishandling in minimally invasive surgery. Simulation analysis of the master-slave control demonstrates that the weighted recursive average filtering method effectively reduces vibration, while the virtual fixture assists in confining the operator's movement within a delimited area. Experimental validation confirms the validity of the robot's structural design and control method. The developed robot successfully achieves the necessary motion for endotracheal intubation surgery through master-slave control.

An online payload identification method based on parameter difference for industrial robots

AbstractAccurate online estimation of the payload parameters benefits robot control. In the existing approaches, however, on the one hand, only the linear friction model was used for online payload identification, which reduced the online estimation accuracy. On the other hand, the estimation models contain much noise because of using actual joint trajectory signals. In this article, a new estimation algorithm based on parameter difference for the payload dynamics is proposed. This method uses a nonlinear friction model for the online payload estimation instead of the traditionally linear one. In addition, it considers the commanded joint trajectory signals as the computation input to reduce the model noise. The main contribution of this article is to derive a symbolic relationship between the parameter difference and the payload parameters and then apply it to the online payload estimation. The robot base parameters without payload were identified offline and regarded as the prior information. The one with payload can be solved online by the recursive least squares method. The dynamics of the payload can be then solved online based on the numerical difference of the two parameter sets. Finally, experimental comparisons and a manual guidance application experiment are shown. The results confirm that our algorithm can improve the online payload estimation accuracy (especially the payload mass) and the manual guidance comfort.

SOC and SOH state estimation of lithium battery based on ffrls and kalman filter

Abstract In the energy storage System, the Battery Management System (BMS) is responsible for the charge and discharge control and energy balance control of the lithium battery, and the accuracy of lithium battery state estimation is directly affected by the control effect of BMS. In order to ensure the normal operation of lithium batteries, this paper selects the State of Charge (SOC) and State of Health (SOH) of lithium batteries as the research object and accurately estimates the SOC and SOH of lithium batteries as the research goal. The equivalent circuit model based on lithium battery is established, and the identification model parameters are based on the recursive least squares method with forgetting factor. Based on the Thevenin equivalent circuit model, the Extended Kalman Filter (EKF) and Unscented Kalman Filter (UKF) are used to estimate the SOC of the battery, respectively. FFRLS and Double Extended Kalman Filter (DEKF) are used to estimate the ohm internal resistance in the equivalent model based on lithium battery, and then the SOH is estimated.

Clustering of primordial black holes from quantum diffusion during inflation

We study how large fluctuations are spatially correlated in the presence of quantum diffusion during inflation. This is done by computing real-space correlation functions in the stochastic-δ N formalism. We first derive an exact description of physical distances as measured by a local observer at the end of inflation, improving on previous works. Our approach is based on recursive algorithmic methods that consistently include volume-weighting effects. We then propose a “large-volume” approximation under which calculations can be done using first-passage time analysis only, and from which a new formula for the power spectrum in stochastic inflation is derived. We then study the full two-point statistics of the curvature perturbation. Due to the presence of exponential tails, we find that the joint distribution of large fluctuations is of the form P(ζ R 1, ζ R 2) = F(R 1,R 2, r) P(ζ R 1)P( ζ R 2), where ζ R 1 and ζ R 2 denote the curvature perturbation coarse-grained at radii R 1 and R 2, around two spatial points distant by r. This implies that, on the tail, the reduced correlation function, defined as P(ζ R 1 > ζc, ζ R 2 > ζc)/[P(ζ R 1 > ζc) P(ζ R 2 > ζc)]-1, is independent of the threshold value ζc. This contrasts with Gaussian statistics where the same quantity strongly decays with ζc, and shows the existence of a universal clustering profile for all structures forming in the exponential tails. Structures forming in the intermediate (i.e. not yet exponential) tails may feature different, model-dependent behaviours.

Adaptive Constraint Penalty-Based Multiobjective Operation Optimization of an Industrial Dynamic System With Complex Multiconstraint.

Aiming at the operation optimization of the wastewater treatment process (WWTP) with nonstationary time-varying dynamics and complex multiconstraint, this article proposes a novel adaptive constraint penalty decomposed multiobjective evolutionary algorithm with synthetical distance (SD)-based cross-generation crossover. First, the concept of spatial SD is presented to comprehensively evaluate the similarity of individual solutions from two aspects of distance and angle, and the individual information between two adjacent generations is used to enhance the diversity of individuals and accelerate the convergence of the algorithm. Second, aiming at the complex multiconstraint during the operation optimization of WWTP, an adaptive penalty algorithm is further adopted to punish the individual solutions that violate the constraints, so as to improve the handling efficiency and success rate of constraints. Furthermore, in view of the time-varying dynamics of actual WWTP, a recursive bilinear subspace identification method based on sliding window is adopted to establish the optimization models as well as the constraint models with self-learning parameter, which provides accurate model guarantee for high-performance multiobjective operation optimization. Finally, the effectiveness, superiority, and practicability of the proposed method are verified through test function experiments as well as operation optimization control experiments of WWTP.

Hybrid six sigma based on recursive kalman filter and weibull distribution to estimate the lifespan of Bulb LEDs

The durability of LED bulbs ensures that the lights can operate for a long time without needing to be replaced or maintained too often. The brightness of high-power LED bulbs provides a strong and efficient light source, saves energy, and has a long lifespan. The traditional method of testing LED bulb life span has limitations such as long testing time, limited accuracy, high cost, inability to predict accurately, and failure to respond quickly. Therefore, the development of new and improved testing methods is necessary to effectively and accurately evaluate and ensure the durability of LED bulbs. This research paper proposes a hybrid Six Sigma method based on the recursive Kalman filter and Weibull distribution to estimate the lifespan of Bulb LEDs. The goal of the new method for evaluating LED bulb life is to provide accurate, reliable, and multi-dimensional information about the life of LED lamps, meeting the requirements of accuracy, diversity, time-saving, resources, credibility, and the ability to evaluate from a variety of perspectives. As a result of the research, the recursive Kalman filter method has strengths such as high accuracy, flexibility, saving computational resources, the ability to handle inaccurate data, and scalability. When applied to LED bulb life assessment, it provides an accurate and reliable estimate of LED lamp life. Research results on longevity testing were reduced from 1650 h to 710 h. The end-of-life test time is 710 h, and the aging time per life test cycle is 135 h. The cost of life testing is reduced from 2100.17 USD to 410.12 USD. This LED bulb lifespan testing method can be applied to similar types of LED products to improve the company's productivity and business efficiency.

A novel fatigue driving detection method based on whale optimization and Attention-enhanced GRU

Fatigue driving has emerged as the predominant causative factor for road traffic safety accidents. The fatigue driving detection method, derived from laboratory simulation data, faces challenges related to imbalanced data distribution and limited recognition accuracy in practical scenarios. In this study, we introduce a novel approach utilizing a gated recurrent neural network method, employing whale optimization algorithm for fatigue driving identification. Additionally, we incorporate an attention mechanism to enhance identification accuracy. Initially, this study focuses on the driver's operational behavior under authentic vehicular conditions. Subsequently, it employs wavelet energy entropy, scale entropy, and singular entropy analysis to extract the fatigue-related features from the driver's operational behavior. Subsequently, this study adopts the cross-validation recursive feature elimination method to derive the optimal fatigue feature index about operational behavior. To effectively capture long-range dependence relationships, this study employs the gated recurrent unit neural network method. Lastly, an attention mechanism is incorporated in this study to concentrate on pivotal features within the data sequence of driving behavior. It assigns greater weight to crucial information, mitigating information loss caused by the extended temporal sequence. Experimental results obtained from real vehicle data demonstrate that the proposed method achieves an accuracy of 89.84% in third-level fatigue driving detection, with an omission rate of 10.99%. These findings affirm the feasibility of the approach presented in this study.