Model Structure Research Articles

Multi-source sparse broad transfer learning for parkinson's disease diagnosis via speech.

Diagnosing Parkinson's disease (PD) via speech is crucial for its non-invasive and convenient data collection. However, the small sample size of PD speech data impedes accurate recognition of PD speech. Therefore, we propose a novel multi-source sparse broad transfer learning (SBTL) method, inspired by incremental broad learning, which balances model learning capability and the overfitting associated with limited sample size of PD speech data. Specifically, SBTL initially leverages a sparse network to preprocess highly overlapping PD speech data, facilitating the identification of intrinsic invariant features between the multi-source auxiliary domain and the target data, which contributes to reducing model complexity. Subsequently, SBTL evaluate transfer effectiveness by virtue of the incremental learning mechanism, adaptively adjusting model structure to ensure the positive transfer of knowledge from the multi-source auxiliary domains to the target domain. Numerous experimental results show that, compared to transfer learning methods for PD diagnosis via speech, SBTL consistently demonstrates significant advantages with a smaller standard deviation, particularly leading by at least 2.58%, 5.71%, 12%, and 14.81% in accuracy, precision, sensitivity, and F1-score, respectively. Even when compared to some well-known transfer learning methods, SBTL still exhibits significant advantages in most cases while maintaining comparable sensitivity. These demonstrate that SBTL is an effective, efficient, and stable multi-source transfer learning method for PD speech recognition, giving more accurate assistance information for clinicians on decision-making for PD in practice.

Fault analysis and fault degree evaluation via an improved ResNet method for aircraft hydraulic system

The hydraulic system is crucial for the safety of the aircraft, which is the key to ensuring the safety of both the aircraft and passengers. It is necessary to study and analyze the normal and fault mode of the system to provide a way for evaluating the fault degree of the hydraulic system. Therefore an improved ResNet based fault degree evaluation method was proposed to evaluate the fault degree of the aircraft hydraulic system. First, the aircraft hydraulic system is constructed by the AMESim, one normal and five fault modes are simulated. Then the effects of the parametric variations for the five fault models are studied, in which pump oil leakage is chosen for analysis. After the analysis of the 5 kinds of faults, each of them is divided to 3 different fault degree, then 16 kinds of states are definition. Second, using the SE-ResNet based method to evaluate the system fault degree. The structure of the two improved ResNet blocks are designed, after that the whole structure of the SE-ResNet fault degree evaluation model is given. Then the parameters of the SE-ResNet are optimization by simulation. After that the evaluate results are given and analyzed, moreover the comparison between the SE-ResNet method with the other machine learning methods are given. The results show that the method in this paper has the best accuracy and shortest test time, therefore the method proposed in this paper has effective measures to improve the reliability of the aircraft hydraulic system.

Correction to: Modelling the Covariance Structure in Marginal Multivariate Count Models: Hunting in Bioko Island

Correction to: Modelling the Covariance Structure in Marginal Multivariate Count Models: Hunting in Bioko Island

Small unmanned helicopter system identification based on the weighted least square method and improved grey wolf optimisation algorithm

Abstract Aiming to address the issue of low accuracy in model predictions obtained from fitting frequency domain response curves for small unmanned helicopters during the process of modeling their flight dynamics, this study proposes a system identification algorithm based on the combination of weighted least squares and improved grey wolf optimisation algorithm. The algorithm utilises the weighted least squares method to obtain the initial model structure, optimises the initial model parameters using the improved grey wolf optimisation algorithm, and enhances the local search and global optimisation ability of the grey wolf optimisation algorithm by introducing an improved grey wolf subgrouping rule, nonlinear convergence factor and dynamic cooperative rule. Ultimately, this approach establishes a dynamic model for small, unmanned helicopters. The identified model is validated using flight test data, with findings demonstrating that this method achieves higher accuracy in model identification and better fits to frequency domain response curves, thus providing a more accurate reflection of the flight dynamics of small unmanned helicopters.

Enhancing meteorological data reliability: An explainable deep learning method for anomaly detection.

Accurate meteorological observation data is of great importance to human production activities. Meteorological observation systems have been advancing toward automation, intelligence, and informatization. Yet, instrumental malfunctions and unstable sensor node resources could cause significant deviations of data from the actual characteristics it should reflect. To achieve greater data accuracy, early detections of data anomalies, continuous collections and timely transmissions of data are essential. While obvious anomalies can be readily identified, the detection of systematic and gradually emerging anomalies requires further analyses. This study develops an interpretable deep learning method based on an autoencoder (AE), SHapley Additive exPlanations (SHAP) and Bayesian optimization (BO), in order to facilitate prompt and accurate anomaly detections of meteorological observational data. The proposed method can be unfolded into four parts. Firstly, the AE performs anomaly detections based on multidimensional meteorological datasets by marking the data that shows significant reconstruction errors. Secondly, the model evaluates the importance of each meteorological element of the flagged data via SHapley Additive exPlanation (SHAP). Thirdly, a K-sigma based threshold automatic delineation method is employed to obtain reasonable anomaly thresholds that are subject to the data characteristics of different observation sites. Finally, the BO algorithm is adopted to fine-tune difficult hyperparameters, enhancing the model's structure and thus the accuracy of anomaly detection. The practical implication of the proposed model is to inform agricultural production, climate observation, and disaster prevention.

The Impact of Health Consciousness and Environmental Awareness on Sports Enthusiasts’ Purchase Intentions for Sustainable Sports Products

(1) Background: With the growing severity of global environmental issues and increasing consumer health consciousness, green consumption has become a prominent focus in both research and practice. However, studies on the mechanisms of health consciousness and environmental awareness influencing the purchase intentions of sports enthusiasts toward sustainable sports products remain relatively limited. This study investigates how health consciousness and environmental awareness impact the green consumption behavior of sports enthusiasts through psychological pathways, including attitude, subjective norm, and perceived behavioral control, aiming to reveal their underlying mechanisms. (2) Methods: Based on the extended Theory of Planned Behavior (TPB), this study developed a theoretical model incorporating health consciousness and environmental awareness. Data were collected via a questionnaire survey, yielding 407 valid responses. The sample was gender-balanced (52.8% male, 47.2% female), predominantly consisting of young individuals aged 26–35 (44.7%) and 18–25 (28.0%), with primary occupations being company employees/managers (46.2%) and students/teachers (25.3%). The collected data were analyzed using SPSS and AMOS software to systematically evaluate the research hypotheses and the model’s applicability. (3) Results: The model exhibited excellent fit indices, with a χ2/df value of 2.129, an RMSEA value of 0.053, an RMR value of 0.029, and GFI, CFI, NFI, and NNFI values all exceeding 0.90, indicating that the model structure adequately explained the relationships among latent variables. All research hypotheses were significantly supported (p < 0.01), demonstrating that health consciousness and environmental awareness not only directly influence purchase intentions but also exert significant indirect effects through attitude, subjective norm, and perceived behavioral control. (4) Conclusions: Health consciousness and environmental awareness are critical drivers of sports enthusiasts’ purchasing behavior for sustainable sports products. This study deepens the understanding of the mechanisms underlying green consumption behavior and offers practical implications for related businesses. Companies should enhance product healthiness and environmental friendliness while optimizing consumer psychological perceptions to increase purchase intentions.

Small-data-trained model for predicting nitrate accumulation in one-stage partial nitritation-anammox processes controlled by oxygen supply rate.

Nitrate (NO3--N) accumulation is the biggest obstacle for wastewater treatment via partial nitritation-anammox process. Dissolved oxygen (DO) control is the most used strategy to prevent NO3--N accumulation, but the performance is usually unstable. This study proposes a novel strategy for controlling NO3--N accumulation based on oxygen supply rate (OSR). In comparison, limiting the OSR is more effective than limiting DO in controlling NO3--N accumulation through mathematical simulation. A laboratory-scale one-stage partial nitritation-anammox system was continuously operated for 135 days, which was divided into five stages with different OSRs. A novel deep learning model integrating Gated Recurrent Unit and Multilayer Perceptron was developed to predict NO3--N accumulation load. To tackle with the general obstacle of limited environmental samples, a generic evaluation was proposed to optimise the model structure by leveraging predictive performance and overfitting risk. The developed model successfully predicted the NO3--N accumulation in the system ten days in advance, showcasing its potential contribution to system design and performance enhancement.

Enabling Multi-Step Forecasting with Structured State Space Learning Module

Data-driven soft sensor incorporated with the model predictive control (MPC) algorithms facilitating product quality and cost control are of imperative importance in industrial processes. However, the widely used one-step forecasting method can not incorporate with MPC and therefore restricts the practical usage of soft sensor. Multi-step forecasting introduces long-term dependencies problems yet has not been effectively resolved within traditional model structure. To address this problem, this paper proposes the deep learning network architecture named Extended State Space Learning Module (ESSLM). ESSLM extends the nonlinear mapping architecture of deep learning based on state space and retains state transfer matrices to characterize the dynamics of the system. ESSLM distinguishes itself from explicit network architectures such as gated RNNs by addressing the long-term dependencies problems through an implicit initialization method, and the MLP and RNN algorithms can be regarded as the manifestation of ESSLM in special cases. ESSLM characterizes the latent space as the coefficients of the orthogonal basis functions so that the input data can be encoded into a high-dimensional feature space with minimal information loss which efficiently achieves multi-step forecasting and give greater utility and practical significance.

Heterologous expression of calcium-independent mesophilic α-amylase from Priestia megaterium: Immobilization on genipin-modified multi-walled carbon nanotubes and silica supports to enhance thermostability and catalytic activity.

α-Amylases, constituting a significant share of the enzyme market, are mainly synthesized by the genus Bacillus. Enzymes tailored for specific industrial applications are needed to meet the growing demand across a range of industries, and thus finding new amylases and optimizing the ones that already exist are extremely important. This study reports the successful expression, characterization and immobilization of P. megaterium α-amylase (PmAmy) in E. coli protein expression systems. The recombinant PmAmy has a molecular weight of 56kDa and its in silico predicted model structure presents a monomer composed of three domains, like most amylases. Regarding long-term storage, PmAmy remained 60% active after 6weeks of storage at -20 and -80°C indicating its stable storage at low temperatures. PmAmy was found to be Ca2+ ion-independent for both catalytic activity and thermostability while Mn2+ enhanced activity in a concentration-dependent manner. The optimum characteristic working conditions of PmAmy were measured as pH 7.0 and 40°C. Immobilizing PmAmy significantly improved its thermal stability, increasing its resistance to thermal denaturation by at least 4.1-fold. Kinetic analyses revealed that the KM and Vmax values of free PmAmy were 0.1mg mL-1 and 556 U mg-1, respectively while immobilization resulted in an increase for both the KM and Vmax values. Kinetic analysis revealed enhanced activity for the Ca2+-independent immobilized enzyme, making it suitable for industrial applications particularly starch processing requiring moderate thermostability without the need for Ca2+ ions.

Fault diagnosis for ion mill etching machine cooling system based on omni-dimensional dynamic convolution and dynamic spatial pyramid pooling

ABSTRACT Ion mill etching machine is a critical equipment in semiconductor manufacturing for wafer etching processes. The cooling system, as an integral part of the Ion mill etching machine, is prone to malfunctions during operation, which can result in the scrapping of subsequent wafers processed by the equipment. Therefore, early detection of cooling system faults is crucial to prevent wafer wastage. Due to the high flexibility of the processing process in ion beam etching machines, the length of time-series signals collected by sensors varies significantly, which poses a challenge for accurate fault diagnosis of the cooling system in ion mill etching machines. To address these issues, we propose a novel end-to-end hybrid model called ODCNN-DSPP. The main contributions are as follows: (1) Enhancing the convolutional neural network (CNN) model structure by introducing an omni-dimensional dynamic convolutional layer to improve feature extraction capabilities; and (2) Utilising a dynamic spatial pyramid pooling method to mitigate the impact of irrelevant features on the CNN. Using publicly available ion mill etching machine datasets for experiments, the results indicate that the method proposed in this paper outperforms current mainstream fault diagnosis methods, achieving an average fault diagnosis accuracy of 96.55% on the test set.

Construction of tetrahedral mesh phantom for Chinese women of childbearing age.

Although the Boundary Representation (BREP) method creates detailed surface phantoms of Chinese women of childbearing age, these phantoms cannot be directly used in Monte Carlo simulations. They must first be converted into voxel phantoms, a process that may diminish some of the inherent advantages of the surface phantoms. Therefore, the aim of this study is to construct a tetrahedral mesh (TM) phantom of Chinese women of childbearing age based on the BREP phantom, incorporating micron-level structural refinements to certain organ tissues while maintaining the original model's structure. This TM phantom can be directly implemented into Monte Carlo codes to calculate the absorbed dose at different photon energies, demonstrating that both the structure and position of organ tissues affect the radiation dose. By achieving more accurate dose assessments, we can optimize radiation protection measures and reduce the potential risks to women of childbearing age.&#xD.

Stability control of adsorption robot considering external disturbance and parameter uncertainty using RMPC

This paper mainly studies the stability of a sea cucumber adsorption robot (SCAR) under external disturbances and parameter uncertainty. As a fishing robot with a suction effect, a dynamic model of its vertical operation is established, taking into account the mechanical structure of its suction port and the surrounding flow conditions. Specifically, robust model predictive control (RMPC) is adopted to ensure that the device maintains excellent stability in complex underwater environments. Considering the simplification of the model structure and real-time control, a discrete nominal model with the introduction of a feedback correction mechanism is designed to be close to the actual system. In the process of control design, the upper bound of robot speed and propeller saturation have been taken into account, and the optimization functions to reduce input consumption of the propellers are also provided at the same time. Furthermore, the feasibility of the recursive structure and the stability of the closed-loop structure are proved. Importantly, the external factors including disturbance sources obtained from pool experiments are subjected to our consideration. In total, the simulation results and comparative analysis are evidenced by the practicality of the designed vehicle and the effectiveness of the established methodology.

Abstract B019: Mathematical modeling-based optimization of gamma knife surgery after checkpoint blockade in melanoma brain metastases

Abstract Gamma knife radiotherapy (RT) treatment is often used as a salvage therapy after progression of melanoma brain metastasis (MBM) lesions under immune checkpoint inhibitor (ICI) blockade therapy; however, waiting until progression of nonresponsive lesions can result in significant symptomatic progression, and the toxicity of RT is greater for larger lesions as it is directly proportional to lesion volume. Robust and reliable standards for consistently maximizing the benefit of combination ICI + RT therapy remain elusive, likely in part due to the complexity of mechanistic interactions between each therapy. Addressing this clinical need will require optimizing the effects of their reported synergistic interactions such as tumor microenvironment modulation and immune activation while mitigating inhibitory effects such as immunosuppressive radiation effects. The ability to identify lesions unlikely to respond to ICI shortly after start of treatment would offer immediate clinical benefit by enabling earlier RT delivery, reduce the volume-dependent toxicities of RT, and reduce symptoms from lesion progression. To address the unmet clinical need for methods to optimize outcomes of combination ICI and RT therapy, we have developed a mechanistic mathematical model based on the biological and physical underpinnings of these complex therapies, and their interactions, which is able to describe and quantify interactions between ICI and RT and their interactions on the tumor. This builds upon our previous ICI modeling work by expanding the model based on the assumption that therapeutic outcome is not only a result of direct interaction between the treatment and disease, but is also a result of complex interplay between heterogeneous tumor populations that may be sensitive or resistant to treatment and their unique interactions with the immune system that serve to maintain or disrupt the tumor-immune equilibrium. RT further modulates this tumor-immune dynamic both by killing T cells in the tumor interior and by stimulating release of T cell activating antigens which can alter T cell activation exterior to the tumor, thereby affecting T cell recruitment into the tumor. By capturing how the complex time-dependent dynamics of tumor-immune interaction and recruitment influences – and is influenced by – transient shifts in treatment sensitive and resistant populations, our model aims to describe and quantify long-term tumor dynamics after ICI + RT therapy. This platform provides a consistent framework for systematically evaluating various proposed mechanisms underlying treatment interactions and how these may determine treatment failure or success. By applying the model to a retrospective, in-house generated melanoma brain metastasis data set, we are examining and refining our model structure with a goal of capturing a wide range of observed tumor dynamics using only clinically available data. This may lead to robust, quantitative methods to maximize treatment outcomes based on the unique characteristics of individual tumors. Citation Format: Alexander R. J. Silalahi, Caroline Chung, James W. Welsh, Zhihui Wang, Joseph D. Butner. Mathematical modeling-based optimization of gamma knife surgery after checkpoint blockade in melanoma brain metastases. [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Translating Targeted Therapies in Combination with Radiotherapy; 2025 Jan 26-29; San Diego, CA. Philadelphia (PA): AACR; Clin Cancer Res 2025;31(2_Suppl):Abstract nr B019.

Elucidation of interface interactions between a dehydratase domain and an acyl carrier protein in cremimycin polyketide synthase.

Modular polyketide synthases (PKSs) are multi-domain enzymes involved in the biosynthesis of polyketide natural products. The dehydratase (DH) domain catalyzes the dehydration of the β-hydroxyacyl unit attached to the acyl carrier protein (ACP) domain in modular PKS. Although the DH domain likely recognizes the cognate ACP domain during the dehydration reaction, the molecular basis of DH-ACP interactions remains elusive. In this study, we conducted cross-linking analysis using a pantetheine-type probe for investigating the ACP recognition of a fusion-DH protein generated from a split-DH domain of cremimycin PKS. Based on the AlphaFold 3-predicted model structure of the fusion-DH-ACP complex, DH-ACP interface residues were identified and validated by mutational analysis. Our findings provide the first detailed insights into domain-domain interactions between DH and ACP in modular PKSs.

Data Security and Privacy Protection in Artificial Intelligence Models: Challenges and Defense Mechanisms

Artificial intelligence (AI) and deep learning algorithms are advancing rapidly, with these emerging technologies being widely applied in areas such as audio-visual recognition and natural language processing. However, in recent years, researchers have identified several security risks in current mainstream AI models, which could hinder the further development of AI technologies. As a result, the issues of data security and privacy protection in AI models have become a focus of research. The data and privacy leakage problems are primarily studied from two perspectives: data leakage based on model outputs and data leakage based on model updates. In the context of model output-based data leakage, the study discusses the principles and research status of model theft attacks, model inversion attacks, and membership inference attacks. In the context of model update-based data leakage, the research focuses on how attackers can steal private data during the distributed training process. Regarding data and privacy protection, three common defense methods are primarily studied: model structure defenses, information obfuscation defenses, and query control defenses. This paper reviews the cutting-edge research achievements in the field of data security and privacy protection in AI deep learning models, focusing on the theoretical foundations, key findings, and related applications of data theft and defense technologies in AI deep learning models. Keywords: Artificial Intelligence, Data Security, Privacy Leakage, Privacy Protection

Impact of under-assisted ventilation on diaphragm function and structure in a porcine model.

Long-term controlled mechanical ventilation (CMV) in intensive care unit (ICU) induces ventilatory-induced-diaphragm-dysfunction (VIDD). The transition from CMV to assisted mechanical ventilation is a challenge that requires clinicians to balance over-assistance and under-assistance. While the effects of over-assistance on the diaphragm are well known, we aimed to assess the impact of under-assistance on diaphragm function and structure in piglet model with pre-existing VIDD (after long-term CMV) or without VIDD (short-term CMV). Twenty-two Large-White female piglets were anesthetized, ventilated, and separated into two groups: a VIDD group (n=10) with long-term 72-hour CMV, and a no-VIDD group (n=12) with short-term 2-hour CMV. After sedation reduction at the end of CMV period, each piglet was switched to under-assisted ventilation for 2 hours. Diaphragm function (supramaximal diaphragm pressure-generating capacity assessed by negative tracheal pressure after transvenous phrenic nerve stimulation) and diaphragm structure (mini-invasive in vivo biopsies) were assessed before and after under-assisted ventilation. In VIDD group, supramaximal diaphragm pressure-generating capacity decreased by 22% from 69.9±12.7 to 54.9±19.7 cmH2O (p=0.04) after 72 hours of CMV evidencing VIDD, then dropped by a further 29% from 54.9±19.7 to 38.9±15.5 cmH2O (p<0.01) after 2 hours of under-assisted ventilation. Diaphragm pressure-generating capacity remains stable from 55.3±22.7 to 58.2±24 cmH2O (p=0.24) in no-VIDD group. Diaphragm structure showed sarcomeric injuries increase from 13±10% to 24±19% (p<0.01) and lipid droplets decrease from 14±8% to 11±6% (p=0.03) of the total micrograph area after 2 hours of under-assisted ventilation in the VIDD group. Sarcomeric injuries and lipid droplets accounted respectively for 17±16% and 2±3% of the total micrograph area after under-assisted ventilation in the no-VIDD group. In this porcine model, a short two-hour exposure of under-assisted ventilation induces impairment of diaphragm function with damage to the diaphragm structure in ICU condition with pre-existing VIDD.

Investigation of the Dynamical Analysis, Stability, and Bifurcation for a Connected Damped Oscillator with a Piezoelectric Harvester

PurposeThe present work investigates and analyzes the mathematical modeling of a dynamical system attached to a piezoelectric device. It is well-established that piezoelectric transducers are effective energy harvesting devices commonly utilized in practical applications with mechanical systems. The structure of the dynamical model contains a damped Duffing oscillator acting as the major component, which is connected to an un-stretched pendulum and at the same time, to the piezoelectric harvester.MethodLagrange's equations are employed to deduce the governing equations of motion (EOM) based on the overall generalized coordinates characterizing the system. This model has been solved analytically using a perturbation technique known multiple-scales (MS) up to the third approximation. This indicates a level of complexity and detail in the model’s analysis. Moreover, the obtained solutions are compared with the numerical ones for more transparency and to highlight the accuracy of the approximate solutions.ResultsDetailed graphical figures have been executed to study the nonlinear stability analysis of the equations of modulation. Phase portrait diagrams, bifurcation ones, and spectrums of Lyapunov are exhibited to illustrate various types of systems’ behavior, complemented by Poincaré maps for further insight. Additionally, the varied ranges of the stabilities are explored and discussed.ApplicationsThe mechanical vibrations are converted to electricity due to the existence of the piezoelectric transducer that is connected to the dynamic model, which has wide uses and applications like crystal oscillators, medical ultrasound applications, gas igniters, and displacement transducers.

Directed Acyclic Graphs in Decision-Analytic Modeling: Bridging Causal Inference and Effective Model Design in Medical Decision Making.

Our commentary proposes the application of directed acyclic graphs (DAGs) in the design of decision-analytic models, offering researchers a valuable and structured tool to enhance transparency and accuracy by bridging the gap between causal inference and model design in medical decision making.The practical examples in this article showcase the transformative effect DAGs can have on model structure, parameter selection, and the resulting conclusions on effectiveness and cost-effectiveness.This methodological article invites a broader conversation on decision-modeling choices grounded in causal assumptions.

Fractal Characteristics of the Relationship between Industrial Water Use Efficiency and Economic Development at Multiple Temporal and Spatial Scales

The fractal theory is introduced to explore the stable fractal characteristics of the correlation between industrial water use efficiency (IWUE) and economic development level (EDL) at different spatial and temporal scales. The research was carried out based on statistical data including the water consumption per 104 yuan of industrial added value (as IWUE) and per capita GDP (as EDL) of 336 cities in China from 1998 to 2017 and 142 countries across the world in 2017. The results show that during 1998-2017, the IWUE and the EDL of Chinese cities have improved gradually. Although the difference of IWUE and EDL among cities has gradually narrowed, the fractal dimension of the correlation between them has remained at around 1.45 in the past 20 years. The overall fractal characteristics is stable while the value of individual city is dynamic with time. Spatially, relationship between IWUE and EDL also maintains a stable fractal pattern for cities in different sub-regions and international countries. The stable fractal characteristics of EDL and IWUE at different spatial-temporal scales lays a theoretical foundation for further exploration of the structure of WUE regulation model and management target.

Modulating Electronic Spin State of Perovskite Fluoride by Ni─F─Mn Bond Activating the Dynamic Site of Oxygen Reduction Reaction.

Establishing the relationship between catalytic performance and material structure is crucial for developing design principles for highly active catalysts. Herein, a type of perovskite fluoride, NH4MnF3, which owns strong-field coordination including fluorine and ammonia, is in situ grown on carbon nanotubes (CNTs) and used as a model structure to study and improve the intrinsic catalytic activity through heteroatom doping strategies. This approach optimizes spin-dependent orbital interactions to alter the charge transfer between the catalyst and reactants. As a result, the oxygen reduction reaction (ORR) activity of NH4MnF3 on CNTs is significantly enhanced by partial substitution of Mn sites with Ni, such as a half-wave potential (E1/2) of 0.86V and a limiting current density of 5.26mA cm-2, which are comparable to those of the commercial Pt/C catalysts. Experimental and theoretical calculations reveal that the introduction of Ni promotes lattice distortion, adjusts the electronic states of the active Mn centers, facilitates the transition from low-spin to intermediate-spin states, and shifts the d-band center closer to the Fermi level. This study establishes a novel approach for designing high-performance perovskite-based fluoride electrocatalysts by modulating spin states.