Reliable Performance Prediction Research Articles

A comparative study of the performance of ten metaheuristic algorithms for parameter estimation of solar photovoltaic models

This study conducts a comparative analysis of the performance of ten novel and well-performing metaheuristic algorithms for parameter estimation of solar photovoltaic models. This optimization problem involves accurately identifying parameters that reflect the complex and nonlinear behaviours of photovoltaic cells affected by changing environmental conditions and material inconsistencies. This estimation is challenging due to computational complexity and the risk of optimization errors, which can hinder reliable performance predictions. The algorithms evaluated include the Crayfish Optimization Algorithm, the Golf Optimization Algorithm, the Coati Optimization Algorithm, the Crested Porcupine Optimizer, the Growth Optimizer, the Artificial Protozoa Optimizer, the Secretary Bird Optimization Algorithm, the Mother Optimization Algorithm, the Election Optimizer Algorithm, and the Technical and Vocational Education and Training-Based Optimizer. These algorithms are applied to solve four well-established photovoltaic models: the single-diode model, the double-diode model, the triple-diode model, and different photovoltaic module models. The study focuses on key performance metrics such as execution time, number of function evaluations, and solution optimality. The results reveal significant differences in the efficiency and accuracy of the algorithms, with some algorithms demonstrating superior performance in specific models. The Friedman test was utilized to rank the performance of the various algorithms, revealing the Growth Optimizer as the top performer across all the considered models. This optimizer achieved a root mean square error of 9.8602187789E−04 for the single-diode model, 9.8248487610E−04 for both the double-diode and triple-diode models and 1.2307306856E−02 for the photovoltaic module model. This consistent success indicates that the Growth Optimizer is a strong contender for future enhancements aimed at further boosting its efficiency and effectiveness. Its current performance suggests significant potential for improvement, making it a promising focus for ongoing development efforts. The findings contribute to the understanding of the applicability and performance of metaheuristic algorithms in renewable energy systems, providing valuable insights for optimizing photovoltaic models.

Strain Decay Monitoring and Analytical Prediction of RC Columns Using Brillouin Optical Technology and Time-Dependent Deterioration Factor

This study presents a novel approach to the design and assessment of slender reinforced concrete (RC) columns by integrating Brillouin Optical Time Domain Analysis (BOTDA) for real-time, distributed strain monitoring and introducing a “time-dependent deterioration factor” strain decay (ηdecay). Experimental tests on 200 mm × 200 mm RC columns with lengths of 1800 mm and slenderness ratios of 29.4, reinforced with four 12 mm bars, captured strain variations up to 400 microstrain under an axial load of 1200 kN, demonstrate BOTDA’s sensitivity and precision. Unlike conventional strain gauges, BOTDA provided a continuous strain profile along the column height, accurately capturing strain decay with a resolution exceeding 95%, enabling the detection of localized strain reductions often missed by traditional methods. The integration of ηdecay into ACI 318 and Eurocode 2 models conservatively improved predictions, particularly for specimens tested with long-term testing (720 days), with experimental-to-predicted (E/P) ratios of 1.42 and 1.29, respectively, compared to higher discrepancies in the original codes. The ηdecay factor accounts for strain reduction along the column height caused by time-dependent effects such as creep, shrinkage, and material degradation, significantly improving the accuracy of axial load capacity predictions. Finite element analysis (FEA) validated these improvements, showing good agreement with experimental data up to the yield load. Post-yield, the modified equations effectively addressed underestimations caused by microcracking, highlighting the necessity of ηdecay for reliable long-term performance predictions. This research combines advanced BOTDA technology with an innovative ηdecay framework, addressing long-term structural deterioration and refining design codes. It establishes a robust foundation for integrating time-dependent effects into predictive models, enhancing the resilience, safety, and sustainability of RC structures under real-world conditions.

Precise three-diode photovoltaic model for photovoltaic modules based on Puma optimizer

The modeling accuracy of photovoltaic (PV) modules is essential nowadays due to the spread of PV power plant installation. Thus, precise PV modeling is vital as it ensures the optimal design, reliable performance prediction, and efficient energy management in solar power systems. The three-diode PV modeling is thus a suitable solution due to its precision and accuracy. However, it is complicated and includes nine unidentified parameters. The Puma optimization algorithm is presented in this paper for utilization in extraction and the optimization of nine unknown PV module parameters. The suggested methodology is applied to two commercial PV modules: the Kyocera KC200GT multi-crystalline and the Canadian PV monocrystalline modules CS6K280M. To ensure the superiority of the Puma algorithm, its results are compared with others resulting from more than four optimization algorithms, which include Artificial Electric Field Algorithm, Northern Goshawk Optimization, Grey Wolf Optimization, Coati Optimization Algorithm, and Particle Swarm Optimization algorithms. The Puma’s parameter extraction precision is further approved by the close agreement between the measured and estimated characteristics curves, extending its validation to variable temperature and irradiance level variations scenarios. The study establishes the Puma algorithm as a robust tool for parameter determination in the three-diode PV model. It opens new avenues for application in other complex optimization problems in renewable energy systems.

Physics-based and data-driven modelling and simulation of Solid Oxide Fuel Cells

This paper presents a comprehensive approach to multiscale and multiphysics modelling of Solid Oxide Fuel Cells (SOFCs) by combining physics-based simulations with data-driven techniques. The modelling approach is tailored to specific end-use scenarios, ensuring that parameter selection aligns with operational requirements for accurate and efficient SOFC design. The study begins by constructing Representative Volume Elements (RVEs) from reconstructed microstructures, applying first-order homogenisation to upscale material properties, which are then incorporated into a macroscopic SOFC model. A major contribution is the structured model definition based on physical process entities, using a graphical representation of model topology. This approach simplifies complex system interactions by representing capacities (such as reservoirs, distributed systems, and interfaces) and transport processes (e.g., diffusion, convection, thermal diffusion), thereby enhancing clarity and improving the accuracy of SOFC performance simulations.A machine learning framework complements the physics-based modelling by training Artificial Neural Networks (ANNs) on simulation-generated datasets, delivering fast and reliable performance predictions. The study compares two optimisation techniques — Levenberg–Marquardt (LM) and Adam optimiser — demonstrating that LM is more effective for sparse datasets and smaller networks, whereas Adam performs better with large datasets and higher learning capacities. This hybrid modelling approach not only boosts predictive accuracy for SOFC performance but also lowers computational costs. By integrating physics-based simulations, machine learning, and a knowledge-driven simulation platform, this work advances SOFC design and optimisation, contributing to more efficient and cost-effective clean energy solutions.Additionally, the paper introduces a knowledge-driven simulation platform to enhance data management and integrate multiscale, multiphysics models. The platform leverages structured data models and ontological mappings to improve semantic interoperability, allowing for dataset reuse and validation across different simulation stages. This ensures a robust, reusable, and well-organised workflow, facilitating large-scale simulations and improving overall modelling accuracy.

Scaled Sensitivity of Pavement–Mechanistic-Empirical Transfer Function Coefficients for Flexible and Rigid Pavements

The American Association of State Highway and Transportation Officials (AASHTO)Ware Pavement–Mechanistic-Empirical (ME) transfer functions need local calibration for reliable performance predictions. It is often not viable to calibrate all coefficients at the same time. Therefore, it is crucial to identify the most sensitive transfer function coefficients. Moreover, the sensitivity also indicates the impact of each coefficient on the performance prediction. Several studies have shown the sensitivity of the Pavement-ME design inputs, but limited research is available on the sensitivity of transfer function coefficients. Typically, the sensitivity is obtained using a normalized sensitivity index (NSI). This paper estimated the sensitivity of the Pavement-ME transfer function coefficients using scaled sensitivity coefficients (SSCs). NSI values are compared with the SSCs. Ten sections, each from flexible and rigid pavements, were used to calculate the NSI values. These are existing pavement sections from the Michigan Department of Transportation (MDOT) pavement management system (PMS) database, designed using the 1993 AASHTO design guide. Results show that SSCs provide a more reliable sensitivity on a range of independent variables rather than a point estimate, unlike NSI. NSI values showed variability among different sections and magnitudes of predicted performance. Calculation of SSCs is a forward problem and does not require any input data. A mathematical model (transfer function) is needed; therefore, SSCs can be calculated on any range of independent variables. It also shows the potential correlation between different coefficients and accuracy in estimation.

Enhanced dynamic modeling of regenerative CO2 transcritical power cycles: Comparative analysis of Pham-corrected and conventional turbine models

Turbine modeling plays a critical role in assessing system power output and performance in CO₂ transcritical power cycle (CTPC) systems, particularly under dynamic operating conditions. Conventional turbine models often fail to provide accurate predictions when inlet parameters deviate from the design point, leading to discrepancies in system behavior. This paper introduces a novel methodology by integrating a Pham-based corrected turbine performance map into a regenerative CTPC dynamic system. This approach enhances turbine modeling accuracy compared to traditional models, such as the uncorrected turbine performance map, nozzle model, and empirical model. The proposed Pham-corrected model method improves system response stability, particularly in terms of inlet pressure and CO₂ mass flow rate under heat source temperature reductions, offering more reliable performance predictions. In contrast, the empirical model shows substantial deviations in net power output (32 kW or 4.0 %) and thermal efficiency (1.36 %), leading to longer system stabilization times. The Pham-corrected and uncorrected turbine performance map models exhibit similar responses under cooling water mass flow rate reductions but diverge in turbine inlet pressure trends compared to the nozzle and empirical models. Additionally, the uncorrected turbine performance map model shows significant deviations in net power (25.6 kW or 3.17 %) and thermal efficiency (0.5 %) under a 10 % reduction in pump speed. This study highlights the importance of correcting turbine inlet parameters and addressing prediction deviations in conventional models. The Pham-corrected turbine model improves reliability, performance prediction, and design optimization, especially under fluctuating heat sources. With its potential to enhance system stability and efficiency, this methodology offers significant prospects for future CTPC applications, including waste heat recovery and renewable energy integration.

Analysis and Prediction of Nonlinear Hysteretic Behaviors of Graphite Magnetorheological Grease at Different Temperatures.

Magnetorheological grease (MRG) is considered a promising alternative to magnetorheological fluids as a smart material because of its higher stability and less leakage. To enhance yield stresses in various applications, graphite is incorporated as an additive, resulting in graphite magnetorheological grease (GMRG). However, the nonlinear hysteresis properties of this new material and its prediction methods have not been investigated. Therefore, in this work, the nonlinear hysteretic properties of GMRG at different temperatures, magnetic fields, and frequencies are systematically investigated and compared with those of MRG. The results of rheological experiments show that graphite enhances the shear stress of GMRG in the hysteresis curve through its reinforcing effect on the magnetic chains. The strain hardening, elasticity, and viscosity of GMRG are enhanced, but an increase in temperature decreases this efficacy. A prediction model based on the particle swarm optimization neural network algorithm (PSO-BP) is also proposed to efficiently and accurately control the nonlinear behavior of GMRG in engineering. The hysteresis curves of GMRG under different external excitations are characterized and predicted by the particle swarm optimization neural network approach. The statistical results show that the PSO-BP-based hysteresis characteristic estimates have satisfactory accuracy. In the test data, the PSO-BP model demonstrates improvements in RMSE, MAE, and SMAPE by 19.5%, 20.6%, and 21.0%, respectively, compared to the conventional BP network, which maintains an R2 value exceeding 0.95. This method provides an efficient solution for researchers to carry out reliable performance prediction in work such as genetic engineering of materials and related engineering applications.

Machine learning­based approaches for enhancing human resource management using automated employee performance prediction systems

Purpose This study focuses on enhancing the accuracy and efficiency of employee performance prediction to enhance decision making and improve organisational productivity. By introducing advance machine learning (ML) techniques, this study aims to create a more reliable and data-driven approach to evaluate employee performance. Design/methodology/approach In this study, nine machine learning (ML) models were used for forecasting employee performance: Random Forest, AdaBoost, CatBoost, LGB Classifier, SVM, KNN, XGBoost, Decision Tree and one Hybrid model (SVM + XGBoost). Each ML model is trained on an HR data set covering various features such as employee demographics, job-related factors and past performance records, ensuring reliable performance predictions. Feature scaling techniques, namely, min-max scaling, Standard Scaler and PCA, have been used to enhance the effectiveness of employee performance prediction. The models are trained to classify data, predicting whether an employee’s performance meets expectations or needs improvement. Findings All proposed models used in the study can correctly categorize data with an average accuracy of 94%. Notably, the Random Forest model demonstrates the highest accuracy across all three scaling techniques, achieving optimise accuracy, respectively. The results presented have significant implications for HR procedures, providing businesses with the opportunity to make data-driven decisions, improve personnel management and foster a more effective and productive workforce. Research limitations/implications The scope of the used data set limits the study, despite our models delivering high accuracy. Further research could extend to different data sets or more diverse organisational settings to validate the model’s effectiveness across various contexts. Practical implications The proposed ML models in the study provide essential tools for HR departments, enabling them to make more informed data driven decisions with regard to employee performance. This approach can enhance personnel management, improve workforce productivity and fostering a more effective organisational environment. Social implications Although AI models have shown promising outcomes, it is crucial to recognise the constraints and difficulties involved in their use. To ensure the fair and responsible use of AI in employee performance prediction, ethical considerations, privacy problems and any biases in the data should be properly addressed. Future work will be required to improve and broaden the capabilities of AI models in predicting employee performance. Originality/value This study introduces an exclusive combination of ML models for accurately predicting employee performance. By employing these advanced techniques, the study offers novel insight into how organisations might transition from a conventional evaluation method to a more advanced and objective, data-backed approach.

Characterization of the function and clinical value of ERCC family genes in lung adenocarcinoma.

ERCC genes, responsible for encoding enzymes involved in base excision repair, have been implicated in various cancers, contributing to chemoresistance. However, a comprehensive analysis of the prognostic and therapeutic significance of this gene family in lung adenocarcinoma (LUAD) is lacking. This study conducted a multidimensional assessment of ERCC family genes in LUAD using bioinformatic approaches, including mRNA expression level, gene methylation, and copy number variation (CNV), as well as their correlations with clinical outcome, gene set variations, and tumor-infiltrating lymphocytes (TILs). In addition, We evaluated the anti-tumor effects of ERCC8 in cell lines, demonstrating its clinical potential on an experimental level. Overall, the expression of ERCC genes exhibited a negative correlation with good prognosis, with ERCC6L and ERCC8 demonstrating the most reliable predictive performance. Gene methylation level and CNV increases of ERCC genes generally displayed negative and positive associations with their expression levels, respectively. Additionally, GSVA analysis suggested that ERCC expression was positively correlated with cell cycle and apoptosis pathways but negatively correlated to the TSC/mTOR pathway. Furthermore, the expression of ERCC genes exhibited a complex relationship with TILs and the response to anti-tumor drugs. The results of in vitro cellular experiments show that inhibiting ERCC8 can alleviate the malignant phenotype of LUAD cells. Our study revealed the multifaceted biological and clinical significance of ERCC family members in LUAD. These findings provide new insights into the function of ERCC family genes in LUAD and their potential clinical applications.

A new nomogram for predicting extraurothelial recurrence in patients with upper urinary tract urothelial carcinoma following radical nephroureterectomy.

We sought to develop and validate a nomogram for predicting extra-urinary recurrence (EUR) following radical nephroureterectomy (RNU) in patients with upper urinary tract urothelial carcinoma (UTUC). Data from 556 UTUC patients post-RNU at the First Hospital of Jilin University were retrospectively analyzed. These patients were categorized into a training group (n=389) and a validation group (n=167). Variables significantly associated with prognosis were identified using univariate Cox regression and most minor absolute shrinkage and selection operator (LASSO) analysis. These independent predictors were incorporated into the nomogram to estimate extra-urinary recurrence-free survival (EURFS). Validation of the nomogram involved ROC curves, calibration plots, and decision curve analysis (DCA). Patients were stratified into two risk categories based on their nomogram scores to compare EURFS using the Kaplan-Meier method. Eight predictors were identified: T-stage, N-stage, tumor grade, local and nerve invasion, preoperative hemoglobin level, neutrophil-to-lymphocyte ratio (NLR), and creatinine, all proving to be independent predictors of EUR. A nomogram was created based on these eight factors, and using the ROC, calibration curves, and DCA, good prediction results were shown in both the training and validation groups. The training and validation groups also showed reliable predictive performance. In particular, there was a significant difference in survival between the high-risk and low-risk groups (P<0.0001). We have also built a network calculator that calculates patient survival time. The URL is https://haowu24.shinyapps.io/dynnomapp. A nomogram for predicting distant metastases in UTUC patients was successfully developed, and its accuracy, reliability, and clinical value were demonstrated. This new tool helps to improve the clinical management of UTUC cases.

Screening of Silver-Based Single-Atom Alloy Catalysts for NO Electroreduction to NH3 by DFT Calculations and Machine Learning.

Exploring NO reduction reaction (NORR) electrocatalysts with high activity and selectivity toward NH3 is essential for both NO removal and NH3 synthesis. Due to their superior electrocatalytic activities, single-atom alloy (SAA) catalysts have attracted considerable attention. However, the exploration of SAAs is hindered by a lack of fast yet reliable prediction of catalytic performance. To address this problem, we comprehensively screened a series of transition-metal atom doped Ag-based SAAs. This screening process involves regression machine learning (ML) algorithms and a compressed-sensing data-analytics approach parameterized with density-functional inputs. The results demonstrate that Cu/Ag and Zn/Ag can efficiently activate and hydrogenate NO with small Φmax(η), a grand-canonical adaptation of the Gmax(η) descriptor, and exhibit higher affinity to NO over H adatoms to suppress the competing hydrogen evolution reaction. The NH3 selectivity is mainly determined by the s orbitals of the doped single-atom near the Fermi level. The catalytic activity of SAAs is highly correlated with the local environment of the active site. We further quantified the relationship between the intrinsic features of these active sites and Φmax(η). Our work clarifies the mechanism of NORR to NH3 and offers a design principle to guide the screen of highly active SAA catalysts.

Screening of Silver‐Based Single‐Atom Alloy Catalysts for NO Electroreduction to NH3 by DFT Calculations and Machine Learning

AbstractExploring NO reduction reaction (NORR) electrocatalysts with high activity and selectivity toward NH3 is essential for both NO removal and NH3 synthesis. Due to their superior electrocatalytic activities, single‐atom alloy (SAA) catalysts have attracted considerable attention. However, the exploration of SAAs is hindered by a lack of fast yet reliable prediction of catalytic performance. To address this problem, we comprehensively screened a series of transition‐metal atom doped Ag‐based SAAs. This screening process involves regression machine learning (ML) algorithms and a compressed‐sensing data‐analytics approach parameterized with density‐functional inputs. The results demonstrate that Cu/Ag and Zn/Ag can efficiently activate and hydrogenate NO with small Φmax(η), a grand‐canonical adaptation of the Gmax(η) descriptor, and exhibit higher affinity to NO over H adatoms to suppress the competing hydrogen evolution reaction. The NH3 selectivity is mainly determined by the s orbitals of the doped single‐atom near the Fermi level. The catalytic activity of SAAs is highly correlated with the local environment of the active site. We further quantified the relationship between the intrinsic features of these active sites and Φmax(η). Our work clarifies the mechanism of NORR to NH3 and offers a design principle to guide the screen of highly active SAA catalysts.

High-fidelity reconstruction of porous cathode microstructures from FIB-SEM data with deep learning

Accurate modeling of lithium-ion battery (LIB) electrode microstructures provides essential references for understanding degradation mechanisms and optimizing materials. Traditional segmentation methods often struggle to accurately capture the complex microstructures of porous LIB electrodes in focused ion beam scanning electron microscopy (FIB-SEM) data. In this work, we develop a deep learning model based on the Swin Transformer to segment FIB-SEM data of a lithium cobalt oxide electrode, utilizing fused secondary and backscattered electron images. The proposed approach outperforms other deep learning methods, enabling the acquirement of 3D microstructure with reduced particle elongated artifacts. Analyses of the segmented microstructures reveal improved electrode tortuosity and pore connectivity crucial for ion and electron transport, emphasizing the necessity of accurate 3D modeling for reliable battery performance predictions. These results suggest a path toward voxel-level degradation analysis through more sensible battery simulation on high-fidelity microstructure models directly twinned from real porous electrodes.

Interpretable multi-step hybrid deep learning model for karst spring discharge prediction: Integrating temporal fusion transformers with ensemble empirical mode decomposition

Karst groundwater is a critical freshwater resource for numerous regions worldwide. Monitoring and predicting karst spring discharge is essential for effective groundwater management and the preservation of karst ecosystems. However, the high heterogeneity and karstification pose significant challenges to physics-based models in providing robust predictions of karst spring discharge. In this study, an interpretable multi-step hybrid deep learning model called selective EEMD-TFT is proposed, which adaptively integrates temporal fusion transformers (TFT) with ensemble empirical mode decomposition (EEMD) for predicting karst spring discharge. The selective EEMD-TFT hybrid model leverages the strengths of both EEMD and TFT techniques to learn inherent patterns and temporal dynamics from nonlinear and nonstationary signals, eliminate redundant components, and emphasize useful characteristics of input variables, leading to the improvement of prediction performance and efficiency. It consists of two stages: in the first stage, the daily precipitation data is decomposed into multiple intrinsic mode functions using EEMD to extract valuable information from nonlinear and nonstationary signals. All decomposed components, temperature and categorical date features are then fed into the TFT model, which is an attention-based deep learning model that combines high-performance multi-horizon prediction and interpretable insights into temporal dynamics. The importance of input variables will be quantified and ranked. In the second stage, the decomposed precipitation components with high importance are selected to serve as the TFT model’s input features along with temperature and categorical date variables for the final prediction. Results indicate that the selective EEMD-TFT model outperforms other sequence-to-sequence deep learning models, such as LSTM and single TFT models, delivering reliable and robust prediction performance. Notably, it maintains more consistent prediction performance at longer forecast horizons compared to other sequence-to-sequence models, highlighting its capacity to learn complex patterns from the input data and efficiently extract valuable information for karst spring prediction. An interpretable analysis of the selective EEMD-TFT model is conducted to gain insights into relationships among various hydrological processes and analyze temporal patterns.

Optimized Machine Learning Model for Predicting Compressive Strength of Alkali-Activated Concrete Through Multi-Faceted Comparative Analysis

Alkali-activated concrete (AAC), produced from industrial by-products like fly ash and slag, offers a promising alternative to traditional Portland cement concrete by significantly reducing carbon emissions. Yet, the inherent variability in AAC formulations presents a challenge for accurately predicting its compressive strength using conventional approaches. To address this, we leverage machine learning (ML) techniques, which enable more precise strength predictions based on a combination of material properties and cement mix design parameters. In this study, we curated an extensive dataset comprising 1756 unique AAC mixtures to support robust ML-based modeling. Four distinct input variable schemes were devised to identify the optimal predictor set, and a comparative analysis was performed to evaluate their effectiveness. After this, we investigated the performance of several popular ML algorithms, including random forest (RF), adaptive boosting (AdaBoost), gradient boosting regression trees (GBRTs), and extreme gradient boosting (XGBoost). Among these, the XGBoost model consistently outperformed its counterparts. To further enhance the predictive accuracy of the XGBoost model, we applied four state-of-the-art optimization techniques: the Gray Wolf Optimizer (GWO), Whale Optimization Algorithm (WOA), beetle antennae search (BAS), and Bayesian optimization (BO). The optimized XGBoost model delivered superior performance, achieving a remarkable coefficient of determination (R2) of 0.99 on the training set and 0.94 across the entire dataset. Finally, we employed SHapely Additive exPlanations (SHAP) to imbue the optimized model with interpretability, enabling deeper insights into the complex relationships governing AAC formulations. Through the lens of ML, we highlight the benefits of the multi-faceted synergistic approach for AAC strength prediction, which combines careful input parameter selection, optimal hyperparameter tuning, and enhanced model interpretability. This integrated strategy improves both the robustness and scalability of the model, offering a clear and reliable prediction of AAC performance.

A chaotic time series prediction model based on the improved dung beetle optimizer and echo state network

Echo state network (ESN) possesses advantages such as simple network structure, ease of training, and reliable prediction performance, making them widely applied in the field of time series prediction. Selecting the optimal reservoir parameters is a key issue in ESN research, as it determines the effectiveness of the network prediction, and it is crucial to design an efficient optimization method for parameter optimization. This paper introduces an improved version of the dung beetle optimizer (IDBO), which employs various strategies to enhance population initialization, algorithm optimization capability, and convergence speed. For theoretical function optimization problems, comparing IDBO with other commonly used optimization methods validated its effectiveness and feasibility. Subsequently, combining IDBO with ESN to construct a new model, IDBO-ESN, and conducting time series prediction experiments, the superior performance of this model is verified on two benchmark datasets and one real dataset.

Transferable Deep Learning Models for Accurate Ankle Joint Moment Estimation during Gait Using Electromyography

The joint moment is a key measurement in locomotion analysis. Transferable prediction across different subjects is advantageous for calibration-free, practical clinical applications. However, even for similar gait motions, intersubject variance presents a significant challenge in maintaining reliable prediction performance. The optimal deep learning models for ankle moment prediction during dynamic gait motions remain underexplored for both intrasubject and intersubject usage. This study evaluates the feasibility of different deep-learning models for estimating ankle moments using sEMG data to find an optimal intrasubject model against the inverse dynamic approach. We verified and compared the performance of 1302 intrasubject models per subject on 597 steps from seven subjects using various architectures and feature sets. The best-performing intrasubject models were recurrent convolutional neural networks trained using signal energy features. They were then transferred to realize intersubject ankle moment estimation.

A long-term dissolved oxygen prediction model in aquaculture using transformer with a dynamic adaptive mechanism

The prediction of Dissolved Oxygen (DO) in oceans is crucial for the survival of marine life and the management of marine farms. However, due to the inherent instability and uncertainty of DO, prediction models frequently necessitate parameter adjustments, posing challenges to maintaining reliable predictive performance and generalization capabilities. Based on this, a long-term dissolved oxygen prediction model in aquaculture using Transformer with a dynamic adaptive mechanism is proposed in the paper. A multi-scale latent correlation decomposition strategy was devised, merging both time and frequency domain decompositions. This approach proficiently untangles time series exhibiting intricate non-linear cycles, thereby delving deeper into and furnishing a more comprehensive array of feature data. Furthermore, an uncertainty-aware attention mechanism was posited, ensuring accurate pinpointing of pivotal data amidst a highly volatile data environment, thus cementing prediction accuracy. Finally, the incorporation of an adaptive hyperparameter adjustment mechanism enables the model to recalibrate in line with feature insights, bolstering its generalization potential across marine farms in diverse regions. Empirical results show that the model proposed in this study can effectively accomplish high-precision long-term forecasting. When juxtaposed with other models under comparable conditions, its mean squared error significantly diminished by 40.2%, the mean absolute error contracted by 55.4%, and concurrently, the R2 value ascended by 7%. This research proffers a fresh vantage point for long-term marine chemical data predictions and extends robust technical bolstering for refining and augmenting aquacultural strategies.

Evaluating the Efficacy of GARCH Models in Forecasting Volatility Dynamics Across Major Global Financial Indices: A Decade-long Analysis

This study investigates the volatility dynamics of five major global financial indices—FTSE 100, Hang Seng, NIKKEI 225, NSE 50, and S&amp;P 500—using a range of GARCH models over a ten-year period from January 1, 2014, to December 31, 2023. The analysis involves preprocessing the data to ensure stationarity, calculating log returns, and conducting stationarity and ARCH effect LM tests. Various GARCH models, including GARCH (0,1), GARCH (1,1), GARCH (1,2), and GARCH (2,2), are applied to capture and forecast volatility. The study aims to determine the most effective model for accurately reflecting volatility dynamics while accounting for significant market events such as the COVID-19 pandemic. The findings reveal that the GARCH (1,1) model generally provides a robust balance between model simplicity and statistical significance, effectively capturing the time-varying volatility of the indices. Despite some complex models offering better fit measures according to the Akaike Information Criterion (AIC) and Schwarz Criterion (SC), the GARCH (1,1) model consistently demonstrates significant parameter estimates and reliable predictive performance, as evidenced by consistent Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) values. This suggests that the GARCH (1,1) model is a preferred choice for volatility forecasting due to its effectiveness and parsimony, although future research might explore more advanced GARCH model variations for further refinement.

Building reliable AI for quantifying uncertainty in particulate matter predictions with deep learning

Predicting the concentrations of particulate matter (PM) has recently become crucial because of its significant impact on air pollution. As the adoption of artificial intelligence (AI) in this domain increases, ensuring the reliability of AI-driven predictions has become paramount. Although many previous studies have harnessed the power of AI for PM prediction, the inherent uncertainty in the results, which is influenced by spatial data imbalances and varying meteorological factors, poses a challenge. Addressing this uncertainty is central to building reliable AI systems. Therefore, we employed the Monte Carlo dropout (MCDO) approach, which is a technique that integrates dropout layers in neural networks during both the training and inference phases, to estimate the prediction uncertainty. Our objective was to address the challenge of prediction uncertainty in PM concentrations, with the ultimate aim of enhancing the reliability and trustworthiness of AI-driven predictions in air quality forecasting. By applying the MCDO approach to grids formed from multidimensional arrays of air quality and weather data, we obtained a 95% confidence interval for the prediction results, thereby demonstrating the trustworthiness of our model. Our evaluation revealed an R-square greater than 0.97 for PM10 and PM2.5, showcasing the robust and reliable predictive performance of the model. This study highlights not only the accuracy of this approach but also the critical role of quantifying uncertainty in building reliable AI systems. Our findings mark a significant step towards a holistic approach to predictive modeling in which reliability and uncertainty quantification are at the forefront.