Error Learning Research Articles

ANALISIS KESALAHAN NOLTING PADA SISWA DALAM MENGERJAKAN SOAL PERBANDINGAN TINGKAT SMP

Error is a mistake about something that was said to be correct in a previous agreement. Comparison is material that students still find difficult to understand in learning and many errors still occur. Even though the concept of comparative material is applied in everyday life, quite a lot of students have difficulty and do not understand comparative material. This research is descriptive research with a qualitative approach. Purposive sampling technique was used in this research to select samples with certain considerations. This research uses indicators of the types of Nolting errors, namely errors due to carelessness, errors in understanding concepts, errors in application, and errors in final results. The purpose of this research is to describe what errors experienced by students using the Nolting error type. Based on the results of the analysis carried out by researchers on careless mistakes, students were not careful enough to make mistakes that had an impact on the final results. In conceptual errors, students do not understand the formula so they cannot find a way to solve the problem. In application errors, students can know the formula but cannot apply it to the answer. Meanwhile, the final result is an error where the student is correct in the steps but does not answer what was asked in the question

Quadrature Based Neural Network Learning of Stochastic Hamiltonian Systems

Hamiltonian Neural Networks (HNNs) provide structure-preserving learning of Hamiltonian systems. In this paper, we extend HNNs to structure-preserving inversion of stochastic Hamiltonian systems (SHSs) from observational data. We propose the quadrature-based models according to the integral form of the SHSs’ solutions, where we denoise the loss-by-moment calculations of the solutions. The integral pattern of the models transforms the source of the essential learning error from the discrepancy between the modified Hamiltonian and the true Hamiltonian in the classical HNN models into that between the integrals and their quadrature approximations. This transforms the challenging task of deriving the relation between the modified and the true Hamiltonians from the (stochastic) Hamilton–Jacobi PDEs, into the one that only requires invoking results from the numerical quadrature theory. Meanwhile, denoising via moments calculations gives a simpler data fitting method than, e.g., via probability density fitting, which may imply better generalization ability in certain circumstances. Numerical experiments validate the proposed learning strategy on several concrete Hamiltonian systems. The experimental results show that both the learned Hamiltonian function and the predicted solution of our quadrature-based model are more accurate than that of the corrected symplectic HNN method on a harmonic oscillator, and the three-point Gaussian quadrature-based model produces higher accuracy in long-time prediction than the Kramers–Moyal method and the numerics-informed likelihood method on the stochastic Kubo oscillator as well as other two stochastic systems with non-polynomial Hamiltonian functions. Moreover, the Hamiltonian learning error εH arising from the Gaussian quadrature-based model is lower than that from Simpson’s quadrature-based model. These demonstrate the superiority of our approach in learning accuracy and long-time prediction ability compared to certain existing methods and exhibit its potential to improve learning accuracy via applying precise quadrature formulae.

State Observer-Based Iterative Learning Control Design for Discrete Systems Using the Heavy Ball Method

The paper considers a state observer-based iterative learning control design problem for discrete linear systems. To accelerate the convergence of the learning error, a combination of the heavy ball method from optimization theory and the vector Lyapunov function method for a class of two-dimensional systems known as repetitive processes is used to develop a new design. A supporting numerical example is given, including a comparison with an existing design.

Feature learning and generalization error analysis of two-layer linear neural networks for high-dimensional inputs

AbstractIt is well known that a model can generalize even when it completely interpolates the training data, which is known as the benign overfitting. Indeed, several work have theoretically revealed that the minimum-norm interpolator can exhibit the benign overfitting. On the other hand, deep learning models such as two-layer neural networks have been reported to outperform “shallow” learning models such as kernel methods under appropriate model sizes by adaptively learning the basis functions to the data. This mechanism is called feature learning, and it is known empirically to be beneficial even when the model size is large. However, it is generally difficult to show that benign overfitting occurs in learning models with feature learning especially for regression problems. In this study, we then analyze the predictive error of the estimator after one step feature learning in a two-layer linear neural network optimized by gradient descent methods and study the effect of feature learning on benign overfitting. The results show that feature learning reduces bias compared to a one-layer linear regression model without feature learning, especially when the eigenvalues of the covariance of input decay slowly. On the other hand, we clarify that the variance is hardly changed by feature learning. This differs significantly from the results for benign overfitting in the situation without feature learning and indicates the usefulness of feature learning.

Predicting stock market crashes in MENA regions: study based on the irrationality of investor behavior and the NARX model

PurposeThis study aims to predict stock market crises in the Middle East North Africa (MENA) regions by leveraging the nonlinear autoregressive neural network with exogenous inputs (NARX) model with two measures of investor sentiment: the ARMS indicator and Google Trends' search volume of positive and negative words.Design/methodology/approachEmploying a novel approach, this study utilizes the NARX model with ten neurons in the hidden layer and the Levenberg–Marquardt training algorithm. It evaluates model performance through learning, validation and test errors, as well as correlation analysis between predicted and actual crises.FindingsThe NARX model, incorporating investor sentiment, has proven to be a reliable tool for forecasting crises, helping market participants understand data complexity and avoid crisis consequences. The divergence in how investors interpret market news, with some focusing solely on negative developments and others valuing positive outcomes, highlights the predictive nature of the optimistic and pessimistic sentiments captured by the model.Research limitations/implicationsThis study advocates for integrating behavioral approaches into stock market crisis prediction, highlighting the significance of investor sentiment and deep learning. It advances crisis mechanism understanding and opens avenues in behavioral finance. Integration of these findings into finance and economics education could enhance students' risk understanding and mitigation strategies.Practical implicationsThe adoption of NARX models, incorporating investor sentiment, empowers market participants to proactively manage crises, adjust strategies, enhance asset protection and make informed decisions. These models enable them to minimize losses, maximize returns and diversify portfolios effectively in response to market fluctuations. These insights also guide policymakers such as governments, regulatory institutions and financial organizations in formulating crisis prevention and mitigation policies, bolstering economic and financial stability.Social implicationsThis research reduces economic uncertainty, safeguards individuals' savings and investments and promotes a stable financial climate.Originality/valueThis study is one of the first attempts to demonstrate the detection and prediction of stock market crises, specifically in the MENA stock market, using the NARX model. It offers a robust forecasting model using machine learning and investor sentiment, providing decision-making support for investment strategies and policy development aimed at enhancing financial and economic stability.

The marriage of operations research and reinforcement learning: Integration of NEH into Q-learning algorithm for the permutation flowshop scheduling problem

The permutation flowshop scheduling problem (PFSP) attracted much interest from the operations research (OR) community, resulting in various heuristic and metaheuristic methods over the past half-century. However, given the hard nature of the PFSP, efficient algorithms rely on the configuration of initial solutions and sophisticated heuristics. Combining OR and artificial intelligence (AI), this paper investigates the marriage of OR and reinforcement learning for the PFSP. A novel method integrating NEH into the Q-learning algorithm is proposed for solving the PFSP with makespan criterion. With the refinement of action selection by strengthening good actions and weakening bad actions, the proposed Q-NEH algorithm shows a better learning and convergence rate, and outperforms the Q-learning algorithm for all 120 instances in Taillard’s benchmark dataset, with a significantly decreased average relative learning error (RLE) from 13.05 % to 1.73 %. Furthermore, by comparing the performances of the Q-NEH algorithm with related state-of-art benchmark algorithms in a wide range set of instances, it further confirms the superiority and stability of the Q-NEH algorithm in statistics. With a total of 2570 independent tests in two phases of experimental evaluations, the superiority of the Q-NEH algorithm for the PFSP suggests that the integration of OR and AI is a promising research direction for solving complex scheduling problems.

A viewpoint on the impact of fundamental attribution error in organizational learning

PurposeTo explore the Fundamental Attribution Error (FAE) bias as a potential impediment to organizational learning and to develop a conceptual model for practitioners and scholars to consider.Design/methodology/approachOur methodology includes a review and adoption of concepts from social cognition, organizational psychology, and learning theory to examine the role of FAE bias in organizational learning.FindingsFAE bias is characterized by providing implicit support for fostering employee cynicism and resistance behaviors and facilitates ongoing cognitive cycles that hinder collaborative learning and knowledge sharing.Practical implicationsBy understanding the role of FAE bias in organizational learning, leaders can develop strategies to mitigate the negative impact of FAE bias on organizational learning dynamics and enhance a social cycle that can improve the organization's learning culture.Social implicationsThis viewpoint highlights that FAE bias in the workplace can lead to a breakdown in how individuals process emotions (affect), actions (behavior) and thoughts (cognition) in social scenarios, exacerbating employee cynicism and resistance, which in turn undermines effective collaboration, communication and the overall social fabric essential for organizational learning.Originality/valueThis viewpoint presents a novel perspective by linking FAE bias directly to cognitive cycles that can impede organizational learning processes through cynicism and resistance behavior, which we propose should be proactively considered by organizations leveraging learning as a key management strategy.

Dual optimization approach in discrete Hopfield neural network

Having effective learning and retrieval phases of satisfiability logic in Discrete Hopfield Neural Network models ensures optimal synaptic weight management, which consequently leads to the production of optimal final neuron states. However, the problem with this model is that different initial states can affect the biasedness of the retrieval phase since the model memorizes final states without generating new ones and produces suboptimal final neuron states. To date, there is no recent research that solves this issue by improving both phases in the Discrete Hopfield Neural Network that involves first-order satisfiability logic. Therefore, this research contributes to the improvement of the learning and retrieval phases by integrating the Hybrid Differential Evolution Algorithm and Swarm Mutation respectively. This research utilizes Y-Type Random 2 Satisfiability, which combines first and second-order clauses to expand the storage capacity of DHNN models, facilitating the retrieval of optimal final neuron states. To evaluate the effectiveness of the Hybrid Differential Evolution Algorithm and Swarm Mutation in the learning and retrieval phases, several performance metrics are employed in terms of synaptic weight management, learning errors, testing errors, energy profiles, solution variations, and similarity for 10 different cases. Quantitative evaluations show that the proposed model successfully enhances the optimization of both phases, ranking first compared to 10 recent algorithms for all metrics. In terms of convergence analysis, the proposed model progressed fast towards the optimal solution with only one iteration for all cases. Additionally, the proposed model can generate a 100 % global minima ratio when dealing with a high number of neurons for Case 5.

Study on the design method of multi-component industrial solid waste low carbon cementitious material with cement as the activator

The relationship between microstructure and mechanical properties of multi-component solid waste low-carbon cementitious materials has been widely pay attention to. However, industrial solid waste is a complex multi-component system with many variable factors, which makes it difficult to design the formulation of cementitious materials. This paper pioneered the application of machine learning (ML) models, algorithms and error rates to analyze the compressive and flexural strength of fly ash-based pastes. Coefficient of determination (R2), mean squared error (MSE), root mean square error (RMSE), mean absolute error (MAE) and a20-index were used to evaluate robustness. X-ray diffraction (XRD), scanning electron microscope (SEM) and Brunauer-Emmett-Taylor (BET) were carried out to analyze evolution of cementitious materials. The evaluation results of ML models exhibited that the Gradient boosting regression (GBR) model had the best determination parameters and a steep normal distribution fitting curve with an a20-index of 0.861. GBR model exhibited the best robustness. The key factors of fly ash-based cementitious materials were identified by Pearson's coefficient, which was benefit to determine the formulation of multi-component solid waste low-carbon cementitious materials. Furthermore, experiments also demonstrated that the optimum ratio of multi-component solid waste low carbon cementitious material was 10 % gypsum, 10 % metakaolin, 45 % fly ash, 15 % slag and 20 % cement, respectively. It was worth noting that the compressive strength of this kind of multi-component solid waste low-carbon cementitious materials reached 35 MPa, which was superior to the mechanical properties of P·O 32.5 cement. The results of phase, SEM images and pore structure distribution showed that the synergistic effect of the multi-component solid waste materials effectively filled the material voids and also facilitated the formation of a variety of gelatinous materials through gelling reactions in the late stage (14–28 d). This work will promote the resource utilization of industrial solid waste, contribute to carbon reduction, and can accelerate the green revolution of concrete.

Asymptotic generalization errors in the online learning of random feature models

Deep neural networks are widely used prediction algorithms whose performance often improves as the number of weights increases, leading to over-parametrization. We consider a two-layered neural network whose first layer is frozen while the last layer is trainable, known as the random feature model. We study over-parametrization in the context of a student-teacher framework by deriving a set of differential equations for the learning dynamics. For any finite ratio of hidden layer size and input dimension, the student cannot generalize perfectly, and we compute the non-zero asymptotic generalization error. Only when the student's hidden layer size is exponentially larger than the input dimension, an approach to perfect generalization is possible. Published by the American Physical Society 2024

Design and analysis of a lower limb assistive exoskeleton robot.

In recent years, exoskeleton robot technology has developed rapidly. Exoskeleton robots that can be worn on a human body and provide additional strength, speed or other abilities. Exoskeleton robots have a wide range of applications, such as medical rehabilitation, logistics and disaster relief and other fields. The study goal is to propose a lower limb assistive exoskeleton robot to provide extra power for wearers. The mechanical structure of the exoskeleton robot was designed by using bionics principle to imitate human body shape, so as to satisfy the coordination of man-machine movement and the comfort of wearing. Then a gait prediction method based on neural network was designed. In addition, a control strategy according to iterative learning control was designed. The experiment results showed that the proposed exoskeleton robot can produce effective assistance and reduce the wearer's muscle force output. A lower limb assistive exoskeleton robot was introduced in this paper. The kinematics model and dynamic model of the exoskeleton robot were established. Tracking effects of joint angle displacement and velocity were analyzed to verify feasibility of the control strategy. The learning error of joint angle can be improved with increase of the number of iterations. The error of trajectory tracking is acceptable.

Differences in Perceived Stress During the COVID-19 Pandemic Among Military Dental Postgraduate Residents.

In military training settings, stress can improve focus and motivation fostering effective learning. However, high perceived stress can be debilitating resulting in poor learning and clinical errors. Multiple studies have focused on medical residency stress; but there has been minimal focus on dental residents and even less on the impact of the unique stressors from the COVID-19 pandemic. The objectives of this study were to determine the impact of the COVID-19 pandemic on perceived stress of residents in a military dental residency training program and explore the association among perceived stress and anxiety, depression, sleep quality, and social support. Dental residents (N = 20) at the Naval Postgraduate Dental School participated in this study. Residents were assessed via self-report measures quarterly from March 2020 through June 2021. The assessment included measures of anxiety (GAD-7), depression (PHQ-9), perceived stress (PSS), fatigue (FSI), and social support (DUKE-SSQ). Before the pandemic shutdown, 60% of participants reported high perceived stress. These residents reported an initial decrease in symptoms of anxiety, depression, and fatigue compared to residents reporting low pre-pandemic perceived stress but returned to baseline levels post-shutdown. Additionally, the high stress participants reported lower social support. Based on pre-pandemic perceived stress, participants responded differently to the impact of the pandemic shutdown. The low baseline stress participants may have a more robust sense of grit and resilience. These findings suggest that postgraduate dental training programs should integrate coping skills training opportunities, especially for residents reporting high perceived stress before residency.

Controlling estimation error in reinforcement learning via Reinforced Operation

In Value-based and Actor-Critic reinforcement learning (RL) methods, both inaccuracy and instability of value estimation will detrimentally affect their performance. Some typical RL methods, such as Maxmin Q-learning and QMD3, are plagued by the underestimation problem while failing to trade off the estimation bias and variance jointly. We propose the Reinforced Operation (RO) to address these shortcomings, which selects the closest median among multiple Q-function. RO is applicable to any model-free RL method. Theoretically, we introduce the Mean Square Error (MSE) to jointly analyze the estimation bias and variance of value estimation methods. We also demonstrate the superiority of RO in MSE reduction and give an upper bound for the estimation bias of value estimation methods with arbitrary distribution to guide the calculation of the estimation bias of value estimation methods. Based on RO, we propose the variants of Q-learning and TD3, Reinforced Q-learning (RQ) and Reinforced Delayed Deep Deterministic policy gradient (RD3), respectively, to tackle different tasks. We empirically demonstrate that our method can reduce estimation error and achieve superior performance on discrete and continuous benchmark tasks.

Integrative BNN-LHS Surrogate Modeling and Thermo-Mechanical-EM Analysis for Enhanced Characterization of High-Frequency Low-Pass Filters in COMSOL.

This paper pioneers a novel approach in electromagnetic (EM) system analysis by synergistically combining Bayesian Neural Networks (BNNs) informed by Latin Hypercube Sampling (LHS) with advanced thermal-mechanical surrogate modeling within COMSOL simulations for high-frequency low-pass filter modeling. Our methodology transcends traditional EM characterization by integrating physical dimension variability, thermal effects, mechanical deformation, and real-world operational conditions, thereby achieving a significant leap in predictive modeling fidelity. Through rigorous evaluation using Mean Squared Error (MSE), Maximum Learning Error (MLE), and Maximum Test Error (MTE) metrics, as well as comprehensive validation on unseen data, the model's robustness and generalization capability is demonstrated. This research challenges conventional methods, offering a nuanced understanding of multiphysical phenomena to enhance reliability and resilience in electronic component design and optimization. The integration of thermal variables alongside dimensional parameters marks a novel paradigm in filter performance analysis, significantly improving simulation accuracy. Our findings not only contribute to the body of knowledge in EM diagnostics and complex-environment analysis but also pave the way for future investigations into the fusion of machine learning with computational physics, promising transformative impacts across various applications, from telecommunications to medical devices.

Body Water Compartment and Sympathovagal Balance: Association with Visuomotor Retention in Young Adults

Cognitive functions are important for visuomotor learning and are associated with physiological factors such as body fluid compartment and cardiovascular reactivity. Previous studies found that body fluid compartment is associated with brain blood flow, which is regulated via sympathovagal balance. However, more evidence is needed to determine whether body fluid compartment and cardiovascular reactivity are associated with visuomotor learning. The purpose of this study was to explore the relationship of body fluid compartment and cardiovascular reactivity to visuomotor learning. We hypothesized that these physiological factors are associated with overall learning retention using upper extremity (including feedforward, volitional, and feedback conditions). Methods: Thirty young adults (12 males, 24.6 ± 3.9 years, right hand dominant) participated in this study. Participants tracked a sinusoidal wave with left arm at pre-test, learning, and post-test sessions on the first visit and at retention test session on the second visit seven days later. Participants performed one set of nine trials during each test and five sets of three trials during learning. Resistance and wave velocity were different in each trial. Learning error was calculated by the averaged absolute distance between the tracking line and the target line. Heart rate (HR), systolic blood pressure (SBP), and low to high frequency power ratio of heart rate variability (LF/HF) were continuously recorded during baseline before pre-test and during tests and learning. We analyzed participants’ extracellular to intracellular body water ratio (ECW/ICW) using an InBody body composition analyzer and tested their cognitive function with Picture Sequence Memory (PSMT), Pattern Comparison Processing Speed, Dimensional Change Card Sort, Flanker Inhibitory Control and Attention, and List Sorting Working Memory Tests from NIH Cognitive Toolbox. Data were statistically analyzed using linear regression analysis and quartile analysis. Results: ECW/ICW was associated with young adults’ ability to retain visuomotor learning after one week (R2 = 0.138, p = 0.043), whereas HR, SBP, and LF/HF at each session were not significantly associated with visuomotor retention. No differences were found in pre-test error among quartiles of five cognitive tests. Significant differences in retention error among quartiles were only found in PSMT, with participants scoring in the highest quartile of PSMT having lower SBP during the first visit and lower retention error compared to the lowest quartile. This finding suggests that young adults with better episodic memory were less stressed during learning and had better visuomotor retention. Conclusion: These findings support that ECW/ICW is associated with not only cognitive function but also visuomotor retention. In addition, cardiovascular reactivity during visuomotor learning may provide information for retention behavior. Relationship of body water compartment and sympathovagal balance to feedforward and feedback conditions in learning will be further discussed. Research Support: This study was funded by the Eunice Kennedy Shriver National Institute of Child Health and Human Development: R01HD084645, R01HD082109. This is the full abstract presented at the American Physiology Summit 2024 meeting and is only available in HTML format. There are no additional versions or additional content available for this abstract. Physiology was not involved in the peer review process.

Training of a Neural Network System in the Task of Detecting Blue Stains in a Sawmill Wood Inspection System

This article presents the operation of an automatic pine sawn timber inspection system, which was developed at the Woodinspector company and is offered commercially. The vision inspection system is used to detect various wood defects, including knots, blue stain, and mechanical damage caused by worms. A blue stain is a defect that is difficult to detect based on the color of the wood, because it can be easily confused with wood defects or dirt that do not impair its strength properties. In particular, the issues of detecting blue stain in wood, the use of artificial neural networks, and improving the operation of the system in production conditions are discussed in this article. While training the network, 400 boards, 4 m long, and their cross-sections of 100 × 25 [mm] were used and photographed using special scanners with laser illuminators from four sides. The test stages were carried out during an 8-hour workday at a sawmill (8224 m of material was scanned) on material with an average of 10% blue stain (every 10th board has more than 30% of its length stained blue). The final learning error was assessed based on defective boards detected by humans after the automatic selection stage. The system error for 5387 boards, 550 m long, which had blue staining that was not detected by the scanner (clean) was 0.4% (25 pieces from 5387), and 0.1 % in the case of 3412 boards, 610 mm long, on which there were no blue stains, but were wrongly classified (blue stain). For 6491 finger-joint boards (180–400 mm), 48 pieces were classified as class 1 (clean), but had a blue stain (48/6491 = 0.7%), and 28 pieces did not have a blue stain, but were classified as class 2 (28/3561 = 0.7%).

Self-paced regularized adaptive multi-view unsupervised feature selection

Multi-view unsupervised feature selection (MUFS) is an efficient approach for dimensional reduction of heterogeneous data. However, existing MUFS approaches mostly assign the samples the same weight, thus the diversity of samples is not utilized efficiently. Additionally, due to the presence of various regularizations, the resulting MUFS problems are often non-convex, making it difficult to find the optimal solutions. To address this issue, a novel MUFS method named Self-paced Regularized Adaptive Multi-view Unsupervised Feature Selection (SPAMUFS) is proposed. Specifically, the proposed approach firstly trains the MUFS model with simple samples, and gradually learns complex samples by using self-paced regularizer. l2,p-norm (0<p≤1) is employed to measure the learning error and as the sparse regularization to accommodate various sparsity requirements across different datasets. Moreover, hypergraph Laplacian matrices are constructed for each view to better preserve the local manifold structure and encode high-order relationships within the data space. They are adaptively assigned weights to learn the underlying correlated and diverse information among different views. An iterative optimization algorithm is proposed to solve SPAMUFS and the convergence and computational complexity are also analyzed. The effectiveness of SPAMUFS is substantiated by comparing with eight state-of-the-art algorithms on nine public multi-view datasets.

Interlanguage Pragmatic Competence of University Students: An Error Analysis of Apology Speech Act Strategies in Japanese Learners

While acquiring a second language, learners may encounter challenges and difficulties in effectively carrying out verbal communication in the second language. Mastering the apology speech act is a challenge for L2 learners. The objective of this study is to identify the apology strategies utilized by individuals learning the Japanese language, as well as the specific types and underlying causes of errors produced during the execution of apologetic speech acts. The results of this study were gathered via the Discourse Completion Test (DCT), which encompassed a sample of 150 Japanese language learners. The gathered data were further classified using eight semantic formulas based on the research conducted by Haristiani and Sopiyanti (2019), while the various types and sources of error categorization were conducted based on the theories proposed by Corder (1981) and Richards (1975). The results of this study suggest that Japanese learners utilize the same primary strategies in apology speech acts. Furthermore, the study findings indicated that learners at the intermediate level displayed a higher frequency of errors in their speech compared to learners at the beginner levels and pre-intermediate levels, particularly in the strategy of taking responsibility. The main reason for this was primarily a lack of familiarity with the conventions of sentence structures, the proper use of language, and the appropriate use of expressions. The other sources of errors in language learning are likely to be ignoring language rule restrictions, incomplete application of rules, the learner’s false hypothesis, overgeneralization, and language transfer. This study is anticipated to function as a point of reference for research in interlanguage pragmatics, second-language acquisition, and error analysis. Gaining comprehension of the various problems and difficulties encountered when performing the speech act of apology in Japanese can assist both learners and educators in reducing these errors.

Efficient water-related failure detection in PEM fuel cells: Combining a PEMFCs fractional order impedance model with FFT-PWM techniques and artificial neural network classification

Water management and early detection of faults in proton exchange membrane fuel cells (PEMFCs) are among the most critical constraints that limit the optimal spread of this type of energy. Consequently, it is necessary to enhance the reliability and durability of PEMFCs by developing an approach to diagnose and identify water failure modes. This paper proposes an effective and simple method to detect, diagnose, and classify various water failure modes in PEMFCs using a hybrid diagnostic approach. This approach combines the PEMFC fractional order impedance model (FOIM) with fast Fourier transform pulse width modulation (FFT-PWM) techniques and artificial neural network pattern recognition (ANN-PR) classification. The results show an accurate match between the electrochemical impedance spectroscopy (EIS) experimental data, the Nyquist impedance spectra of FOIM, and the FFT-PWM algorithm as a proposed alternative technique to EIS measurements. Learning of ANN-PR was performed using the frequency spectrum amplitude (FSA) database of the voltage and current signals produced by the PEMFCs FOIM DC/DC boost converter, which was generated using the FFT-PWM algorithm. The ANN-PR achieved low values for error accuracy, with the Low Square Error and Learning Error reaching 6.676 × 10−19 and 1.888 × 10−16, respectively. The elements inside the confusion matrix and the rest of the matrices confirm that the proposed model's accuracy, precision, recall, and high F1 score reached 100%. Furthermore, all predictions made by the ANN-PR model were consistently accurate across all areas of failure detection. Overall, the proposed method helps in analyzing, diagnosing, and classifying fuel cell failure modes such as flooding and drying, which may simplify the health assessment of PEMFC.

Exploration on relation between vehicle oscillation type and platoon oscillation evolution based on multi-scenario field experiment

In order to explore the categorization of vehicle oscillation and the relationship between individual vehicle oscillation and platoon oscillation in traffic flow, this paper conducts field experiments with both human driving vehicles(HDVs) and autonomous vehicles(AVs). The objective is to utilize experimental data to categorize and quantify traffic oscillation, delve into the impact of different degrees of vehicle oscillation on platoon oscillation, identify patterns between vehicle oscillation types and platoon oscillation evolution, and study the influence of AVs on platoon oscillation. The paper commences with car-following experiments involving HDVs and AVs, sets the platoon into three scenarios of HDV’s platoon, AV’s platoon, and mixed platoon experimental datasets. Subsequently, nine oscillation features reflecting the oscillation characteristics of vehicle traveling, such as volatility and trend, etc., are extracted from the experimental datasets. Then the CLS deep clustering model is constructed, trained, and outputs high-dimensional features. The model's effectiveness is assessed using both clustering error and deep learning error simultaneously. Finally, the paper analyzes the classification results of the experimental dataset and explores the relationship between vehicle oscillation type and platoon oscillation. The research finding indicates that the oscillation classification effectiveness of the CLS model is significantly superior to other algorithms. Using the CLS model, vehicle oscillations are categorized into four most suitable types: I, II, III, and IV, representing slight oscillation, general oscillation, relatively serious oscillation, and severe oscillation respectively. In HDVs’ platoon, as the vehicle oscillation type increases, the following vehicle does not fully adhere to the front vehicle, the amplitude trend of the vehicle changes, leading to oscillation in the following vehicle platoon. In the AVs’ platoon, AVs suppress the backward propagation of oscillations in the platoon, and the oscillation types are all type I, indicating mild oscillation. In the mixed platoon, it is observed that AVs, through swift perception of the state of preceding vehicle, promptly respond to adjust their own driving condition to alleviate platoon oscillation. The higher the proportion of AVs in the platoon, the stronger the inhibitory effect on platoon oscillation.