Reduction In Mean Square Error Research Articles

Improving the experience of machine learning in compressive strength prediction of industrial concrete considering mixing proportions, engineered ratios and atmospheric features

In previous literature on predicting compressive strength (CS) using machine learning (ML), the focus has primarily been on algorithm-specific improvements, with less emphasis on improving the data perspective of CS prediction. Departing from these conventional investigations, this study presents data-centric enhancements. A systematic and comprehensive methodology is adopted, involving series of steps. Firstly, a large dataset (> 24,214 datapoints) comprising 26 input features relating to mixture proportions, engineered ratios and atmospheric parameters is prepared and processed. Feature engineering is then performed for selection and processing of data features. Subsequently, six scenarios are designed and investigated for CS prediction, focusing on distinct combinations of input features. Finally, CS predictions for all six scenarios are compared using five well-known ML model, and results are validated using statistical hypothesis testing. The results show significance improvements in CS prediction, with a 12.8 % increase in coefficient of determination (R2) and a 61 % reduction in root mean square error (RMSE) achieved by incorporating engineered and atmospheric parameters in conjunction with mixture proportion as inputs in CS prediction. Based on CS prediction in six scenarios, the study presents useful discussions focusing on concrete data perspective, role of engineering ratio and atmospheric features, and interaction and influence of input features in CS prediction. In conclusion, this work emphasizes the importance of enhancing data management practices for concrete performance assessment to have a more efficient, realistic, and sustainable outcomes in the concrete industry.

Enhancing physically-based flood forecasts through fusion of long short-term memory neural network with unscented Kalman filter

Accurate flood forecasts are vital for reservoir operation and flood prevention. The unscented Kalman filter (UKF) excels in improving physically-based models flood forecasting but depends on precise noise estimation, posing challenges in complex uncertainty quantification. In this study, we propose a novel approach, the deep fusion of a long short-term memory (LSTM) neural network and unscented Kalman filter (LSTM-UKF), to enhance flood forecasts by adaptively updating hydrological model states. The LSTM efficiently learns noise-related information from the estimation of Kalman Gain, obviating the need for intricate uncertainty recognition and approximation. For comparative analysis, the LSTM-UKF and UKF filters are constructed to correct Xinanjiang (XAJ) hydrological model states. Both filters utilize streamflow observations to update the XAJ model states and facilitate its flood forecasting performance. Comprehensive evaluations were conducted using 3-hourly meteor-hydrological sequences from the Jianxi and Tianyi basins in China, focusing on the accuracy, stability, and reliability of multi-step-ahead flood forecasts. Results indicate that the LSTM-UKF performs superior to the UKF, with maximal advancements in Nash-Sutcliffe efficiency coefficient (NSE) by 9.1%, maximal reduction in root mean square error (RMSE) by 18.7%, and maximal decrease in mean absolute error (MAE) by 22.6%. Additionally, the LSTM-UKF exhibits better robustness and stability in non-stationary flood events. The proposed LSTM-UKF mitigates the over-reliance on noise estimates, reducing systematic biases and error accumulation in state estimates and enhancing hydrological model generalizability in operational flood prevention platforms and systems.

Ultra-short-term photovoltaic power prediction based on similar day clustering and temporal convolutional network with bidirectional long short-term memory model: A case study using DKASC data

Due to its strong dependence on weather conditions, photovoltaic (PV) power is highly intermittent in nature. In light of this, this paper introduces a PV power prediction model based on similar-day clustering and temporal convolutional network (TCN) with bidirectional long short-term memory (BiLSTM) model. Firstly, in the data preprocessing stage, improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) method is used to decompose and denoise the original PV power data to obtain subsequences of different frequencies. Subsequently, the sample entropy (SE) method is incorporated to reconstruct the subsequences and generate low-frequency and high-frequency subsequences with more pronounced temporal features. In addition, a self-organizing map (SOM) with the K-means algorithm is used to categorize historical days into four weather types: sunny, cloudy, rainy, and intermittent. Through grey relational analysis (GRA), meteorological factors significantly affecting PV power prediction are identified to construct a multidimensional feature set. During the model prediction phase, historical PV power data and related meteorological impact factors are input into the TCN-BiLSTM model to perform multi-data-driven PV power prediction. Finally, the predicted results of each subsequence are linearly combined to obtain the ultimate PV power prediction. The proposed model is compared with convolutional neural network (CNN)-LSTM, LSTM, and TCN models, achieving a reduction in the root mean square error (RMSE) of 0.129 kW, 0.238 kW, and 0.257 kW, respectively. This demonstrates that the proposed model exhibits superior overall performance in time series modeling and information capture, enhancing the understanding of seasonal, periodic, and irregular patterns in PV power generation data.

S-wave log construction through semi-supervised regression clustering using machine learning: A case study of North Sea fields

Accurate prediction of S-wave velocity from well logs is essential for understanding subsurface geological formations and hydrocarbon reservoirs. Machine learning techniques, including clustering and regression, have emerged as effective methods for indirectly estimating S-wave logs and other rock properties. In this study, we employed clustering algorithms to identify similarities among well log datasets, encompassing depth, sonic, porosity, neutron, and apparent density, facilitating the discovery of correlations among various wells. These identified correlations served as a foundation for predicting S-wave values using a novel semi-supervised approach. Our approach combined clustering, specifically k-means clustering, with different types of regressors, including Least Squares Regression (LSR), Support Vector Regression (SVR), and Multi-Layer Perceptron (MLP). Our results demonstrate the superior performance of this integrated approach compared to traditional regression methods. We validated our methodology using various parametric and non-parametric regression techniques, showcasing its effectiveness not only on wells within the training region but also on wells outside the study area. We achieved a significant improvement in the R2 score metric, ranging from 2.22% to 6.51%, and a reduction in Mean Square Error (MSE) of at least 31% when compared to predictions made without clustering. This study underscores the potential of machine learning techniques for accurate prediction of S-wave velocity and other rock properties, thereby enhancing our comprehension of subsurface geology and hydrocarbon reservoirs.

Prediction and analysis of relative error in electric vehicle charging stations based on an improved ConvFormer model

In order to address the issue of metering inaccuracies in charging stations that directly affect the development of electric vehicles, a prediction method for the relative error of charging stations based on the ConvFormer model is proposed. The model combines Convolutional Neural Networks (CNN) with Transformer models in parallel, significantly improving the prediction accuracy. First, charging station data is preprocessed using forward interpolation and normalization methods, and the dataset is transformed into a dataset of input relative errors. Then, a neural network with an improved unidirectional convolutional and attention combination for time-series forecasting is constructed, and common regression performance evaluation metrics, MAE (Mean Absolute Error) and MSE (Mean Squared Error), are selected for evaluation. Finally, based on seven days of charging station data, the relative error of charging stations for the next 24 h is predicted, and compared to traditional Transformer and LSTM (Long Short-Term Memory) time-series models. The results show that the improved model yields the lowest values for both MAE and MSE, with a 47.30 % reduction in MAE compared to the Transformer model and a 38.06 % reduction compared to LSTM, and a 66.94 % reduction in MSE compared to the Transformer model and approximately 62.32 % reduction compared to LSTM.

Ground visibility prediction using tree-based and random-forest machine learning algorithm: Comparative study based on atmospheric pollution and atmospheric boundary layer data

To mitigate haze impacts, three visibility simulation schemes were designed using decision tree and random forest algorithms, leveraging atmospheric boundary layer meteorological data, pollutant concentrations, and ground observations. The optimal approach was identified to investigate the boundary layer's effect on simulations. The results showed that the simulation effect of the random forest algorithm for two haze processes was better than that of the decision tree algorithm. In the first haze process, the random forest algorithm had a more significant reduction in root mean square error than the decision tree algorithm in the same visibility range (Scheme 3, visibility<200 m, mean absolute error reduced by 5.9%, root mean square error reduced by 19.1%). Simulation models significantly improved the accuracy of the models by adding atmospheric boundary layer observation data to the two fog-hazes process visibility. However, the addition of atmospheric boundary layer meteorological data in the first haze process had a better improvement effect (random forest: visibility<200 m, mean absolute errors of 25.0 (relative error<12.5%) and 25.5 m (relative error<12.8%) in Scheme 2 and 3, respectively). The addition of atmospheric boundary-layer pollutant concentrations data was more effective in the second haze process (random forest: visibility<200 m, scheme 2 and scheme 3 had mean absolute errors of 25.6 (relative error<12.8%) and 11.1 m (relative error<5.6%), respectively). The influence of atmospheric boundary layer meteorological data and pollutant data on the two fog processes is affected by the cause of the fog process.

Exploring multi-pollution variability in the urban environment: geospatial AI-driven modeling of air and noise

ABSTRACT This study addresses the critical need for comprehensive multi-pollution modeling in urban environments by employing Geospatial Artificial Intelligence (GeoAI) techniques. Specifically, it aims to elucidate the variability of air and noise pollution levels in Tehran, Iran, and develop precise multi-pollution susceptibility maps. A spatial database was compiled, encompassing annual average data (2019–2022) of the Air Quality Index (AQI) and Equivalent Continuous Sound Level (Leq), along with 19 influential factors related to both pollutants. The study utilized the CatBoost machine learning algorithm, enhanced with Grey Wolf Optimizer (GWO) and Harris Hawks Optimization (HHO) algorithms, to model and predict pollution patterns. Key quantitative achievements include a remarkable 15% reduction in Root Mean Square Error (RMSE) for air pollution and a 12% reduction in noise pollution when using the CatBoost-HHO configuration compared to the standalone CatBoost algorithm. Validation of the multi-pollution maps utilizing the Area Under the Curve (AUC) analysis showed high accuracy, with the CatBoost-HHO achieving AUC values of 0.943 for air pollution and 0.936 for noise pollution, outperforming CatBoost-GWO and standalone CatBoost models. These results underscore the efficacy of our approach in accurately identifying and mapping multi-pollution hotspots, contributing valuable insights for urban environmental management and public health preservation.

An Adjustable Parameter-Based Robust Distributed Fault Diagnosis for One-Sided Lipschitz Formation of Clustered Multi-Agent Systems

This paper addresses the challenge of distributed fault diagnosis in the context of the one-sided Lipschitz formation of agents. Each agent integrates an observer to detect and estimate both linear and non-linear faults in its attitude control subsystem. A robust design configuration is also developed to account for external perturbations. The robust observer utilized in this study is an unknown input observer (UIO), designed to mitigate the impact of disturbances on fault and state estimation errors. The observer’s parameters are determined using linear matrix inequalities (LMIs). Furthermore, a UIO incorporating an adjustable parameter (AP) is introduced to enhance fault diagnosis accuracy. Simulation results for two satellite clusters, consisting of five satellites with varying dynamics due to external disturbances, are presented to validate the approach. Instead of equipping every agent with an observer, specific agents can be equipped with observers to detect faults throughout the constellation, thereby reducing computational demands in configurations with numerous agents. Finally, a comparison is made between the proposed AP-based UIO and a standard UIO. The comparison findings reveal a noteworthy average of a substantial 56.61% reduction in root mean square error (RMSE) employing AP-based UIO compared to the utilization of standard robust UIO.

A Lightweight Neural Network for the Real-Time Dehazing of Tidal Flat UAV Images Using a Contrastive Learning Strategy

In the maritime environment, particularly within tidal flats, the frequent occurrence of sea fog significantly impairs the quality of images captured by unmanned aerial vehicles (UAVs). This degradation manifests as a loss of detail, diminished contrast, and altered color profiles, which directly impact the accuracy and effectiveness of the monitoring data and result in delays in the execution and response speed of monitoring tasks. Traditional physics-based dehazing algorithms have limitations in terms of detail recovery and color restoration, while neural network algorithms are limited in their real-time application on devices with constrained resources due to their model size. To address the above challenges, in the following study, an advanced dehazing algorithm specifically designed for images captured by UAVs over tidal flats is introduced. The algorithm integrates dense convolutional blocks to enhance feature propagation while significantly reducing the number of network parameters, thereby improving the timeliness of the dehazing process. Additionally, an attention mechanism is introduced to assign variable weights to individual channels and pixels, enhancing the network’s ability to perform detail processing. Furthermore, inspired by contrastive learning, the algorithm employs a hybrid loss function that combines mean squared error loss with contrastive regularization. This function plays a crucial role in enhancing the contrast and color saturation of the dehazed images. Our experimental results indicate that, compared to existing methods, the proposed algorithm has a model parameter size of only 0.005 M and a latency of 0.523 ms. When applied to the real tidal flat image dataset, the algorithm achieved a peak signal-to-noise ratio (PSNR) improvement of 2.75 and a mean squared error (MSE) reduction of 9.72. During qualitative analysis, the algorithm generated high-quality dehazing results, characterized by a natural enhancement in color saturation and contrast. These findings confirm that the algorithm performs exceptionally well in real-time fog removal from UAV-captured tidal flat images, enabling the effective and timely monitoring of these environments.

Addressing Data Scarcity in Solar Energy Prediction with Machine Learning and Augmentation Techniques

The accurate prediction of global horizontal irradiance (GHI) is crucial for optimizing solar power generation systems, particularly in mountainous areas with complex topography and unique microclimates. These regions face significant challenges due to limited reliable data and the dynamic nature of local weather conditions, which complicate accurate GHI measurement. The scarcity of precise data impedes the development of reliable solar energy prediction models, impacting both economic and environmental outcomes. To address these data scarcity challenges in solar energy prediction, this paper focuses on various locations in Europe and Asia Minor, predominantly in mountainous regions. Advanced machine learning techniques, including random forest (RF) and extreme gradient boosting (XGBoost) regressors, are employed to effectively predict GHI. Additionally, optimizing training data distribution based on cloud opacity values and integrating synthetic data significantly enhance predictive accuracy, with R2 scores ranging from 0.91 to 0.97 across multiple locations. Furthermore, substantial reductions in root mean square error (RMSE), mean absolute error (MAE), and mean bias error (MBE) underscore the improved reliability of the predictions. Future research should refine synthetic data generation, optimize additional meteorological and environmental parameter integration, extend methodology to new regions, and test for predicting global tilted irradiance (GTI). The studies should expand training data considerations beyond cloud opacity, incorporating sky cover and sunshine duration to enhance prediction accuracy and reliability.

Within-well patterns in bigeye tuna catch composition and implications for purse-seine port-sampling and catch estimation for the Eastern Pacific Ocean

In response to concerns about the stock status of bigeye tuna (BET) in the Eastern Pacific Ocean, the Inter-American Tropical Tuna Commission adopted additional management measures for BET in 2021, including an individual-vessel catch threshold system for the purse-seine fishery. Development of an enhanced port-sampling program for estimation of trip-level BET catch was also mandated to support member countries and their purse-seine vessels in their conservation efforts. To this end, a pilot study was conducted in the ports of Manta and Posorja, Ecuador, in 2022. In these ports, well unloading often takes place with small containers, which are used to transport fish from inside the well to the vessel’s wet deck. Using a high-frequency systematic sampling protocol, 63 wells of 37 trips with catch exclusively from floating-object (OBJ) sets were sampled from the start to the end of unloading, at a fixed interval from a random starting point, sampling about 10 % of all the containers of fish unloaded from each well. Notable large-scale pattern in the proportion of BET per container was found for 38 of the 56 wells that had BET catch. The proportion of BET per container, which could be high at the beginning, middle or end of the well unloading, sometimes varied by 0.40 or more. The magnitude of this large-scale within-well pattern had a significant increasing relationship with the number of OBJ sets associated with the well catch, consistent with variability in species composition among OBJ sets being an important factor in determining variability in species composition during catch unloading. Simulation studies demonstrated that such large-scale within-well pattern has potential implications for OBJ-set well-level sampling design, where, as expected from sampling theory, a systematic sampling protocol for containers of fish generally resulted in lower mean squared error (MSE) on the proportion of BET in the well, compared to simple random sampling of containers of fish. The reduction in MSE was largely due to a reduction in variance. Simulations also showed that the within-well variance component of the trip-level estimator for the proportion of BET can be larger than the among-well variance component, unless the within-well sampling coverage is relatively high. To minimize the negative impact of within-well variability on the precision of the estimator, results indicate that for a sampling protocol with one systematic sample per well, the within-well coverage should be at least 2 % of containers of fish unloaded from the well, and preferably more than 3 %. Finally, simulation studies were conducted with observer well plan data from 2013 to 2022 to put the well-level results in a larger context. Results indicated that the level of within-well sampling coverage may affect the variance on fleet-level estimates of the proportion of BET in the catch, with potentially substantially higher variance when the within-well sampling coverage is low. Taken together, these results suggest that both the type of within-well sampling and the level of within-well sampling coverage have important implications for the variance on BET catch estimates, from the well level to the fleet level.

Comparison of machine learning and statistical approaches for Digital Elevation Model (DEM) correction: interim results

Abstract. The correction of digital elevation models (DEMs) can be achieved using a variety of techniques. Machine learning and statistical methods are broadly applicable to a variety of DEM correction case studies in different landscapes. However, a literature survey did not reveal any research that compared the effectiveness or performance of both methods. In this study, we comparatively evaluate three gradient boosted decision trees (XGBoost, LightGBM and CatBoost) and multiple linear regression for the correction of two publicly available global DEMs: Copernicus GLO-30 and ALOS World 3D (AW3D) in Cape Town, South Africa. The training datasets are comprised of eleven predictor variables including elevation, slope, aspect, surface roughness, topographic position index, terrain ruggedness index, terrain surface texture, vector ruggedness measure, percentage bare ground, urban footprints and percentage forest cover as an indicator of the overland forest distribution. The target variable (elevation error) was derived with respect to highly accurate airborne LiDAR. The results presented in this study represent urban/industrial and grassland/shrubland/dense bush landscapes. Although the accuracy of the original DEMs had been degraded by several anomalies, the corrections improved the vertical accuracy across vast areas of the landscape. In the urban/industrial and grassland/shrubland landscapes, the reduction in the root mean square error (RMSE) of the original AW3D DEM was greater than 70%, after correction. The corrections improved the accuracy of Copernicus DEM, e.g., &gt; 44% RMSE reduction in the urban area and &gt;32% RMSE reduction in the grassland/shrubland landscape. Generally, the gradient boosted decision trees outperformed multiple linear regression in most of the tests.

More Accurately Estimating Aboveground Biomass in Tropical Forests With Complex Forest Structures and Regions of High‐Aboveground Biomass

AbstractAccurately estimating aboveground biomass (AGB) in tropical forests is vital for managing the threats posed by deforestation, degradation, and climate change. However, challenges persist in accurately estimating AGB in high AGB regions. This study aims to accurately estimate the AGB of regions with high AGB by using spatial statistical analyses based on AGB estimates made by machine‐learning fusion of multisource data. We hypothesize that incorporating dominant auxiliary factors in the analysis increases the estimation accuracy. This study focuses on tropical forests located in Longyan, Fujian Province, China, covering an area of 19,028 km2. Multisource data are used, including airborne laser scanning, the Shuttle Radar Topography Mission digital elevation model, the Landsat Operational Land Imager, and the National Forest Inventory. Based on GeogDetector's spatial covariance matrix and the spatial similarity principle, we identify key auxiliary factors (dominant tree species, canopy closure, and herbaceous cover) and investigated how auxiliary variables can improve estimation accuracy. Empirical Bayesian kriging regression prediction introduces the main auxiliary factors to refine AGB estimates. These refinements significantly enhance the accuracy of AGB estimates, particularly for high AGB, resulting in a 0.1 increase in R2, a 7.0% reduction in root mean square error, a 13.5% reduction in mean square error, and a 6.6% reduction in mean absolute error when compared with the AGB estimates obtained by using machine learning to fuse multisource data. Thus, incorporating spatial statistical analysis into the integration of multisource data and machine learning for AGB estimation can enhance the accuracy of high‐AGB estimates in intricate forest structures, resulting in precise AGB maps.

Analysis and Comparison of Artifact Removal Techniques for Epilepsy EEG Signal

Objective: Accurate epilepsy diagnosis demands precise EEG analysis, hindered by non-neuronal artifacts. This study evaluates artifact removal methods, specifically Independent Component Analysis (ICA) and Empirical Mode Decomposition (EMD), aiming to enhance signal quality. We introduce a hybrid approach, combining ICA and EMD. Methods: ICA and EMD are applied to preprocess epilepsy EEG recordings. Quantitative evaluation metrics, including Signal-to-Noise Ratio (SNR), Peak Signal-to-Noise Ratio (PSNR), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Standard Deviation (SD), are calculated and compared for both methods. Findings: ICA outperforms EMD, showing higher SNR and PSNR, notably in BONN and CHB-MIT datasets. ICA achieves significant reductions in MSE, RMSE, and SD. The hybrid approach surpasses existing methods, supported by quantitative data. Novelty: Rigorous application of ICA and EMD to diverse datasets quantitatively establishes ICA's superiority. The hybrid approach, backed by quantitative evidence, proves effective beyond epilepsy EEG. Conclusion: This abstract provides clear, quantitative support for ICA's superiority and the hybrid approach's efficacy, offering valuable insights into artifact removal in EEG analysis. Keywords: Epilepsy, Artifact removal, EEG, ICA, DWT, EMD, Performance metrics

Site index curves using the generalized algebraic difference approach – Gada in planted forests of Pinus taeda L. in the midwest of Santa Catarina, Brazil

One of the most widely used tools for assessing the productive potential of planted Pinus taeda L. forests is to generate site index curves. Site index is a measure of the productive potential of forests and is influenced by various factors such as soil, water, light, among others, representing the relationship between the dominant height of trees and age at a specific location. This relationship produces a curve and can be used for site classification, consequently estimating the productivity of the forest stand. The objective of this study was to evaluate the performance of dynamic equations, the Algebraic Difference Approach (ADA), and its generalization (GADA). The data were obtained from permanent plots of Continuous Forest Inventory (CFI), collected in forest stands, through a sequence of annual remeasurements from 5 to 17 years of age. Dominant height was estimated as a function of age using nonlinear equations, and subsequently, the ADA and GADA methods were applied using the Chapman-Richards basic equation. The results of the GADA method provided a substantial reduction in the root mean square error (RMSE), less than half when compared to the traditional guide curve method, and an increase from 0.95 to 0.99 in R2adj. Therefore, the GADA methodology proved to be suitable and efficient for site index classification, with noticeable flexibility and reliability on its estimates.

Improving short-term forecasting of solar power generation by using an EEMD-BiGRU model: A comparative study based on seven standalone models and six hybrid models

ABSTRACT Accurate and timely forecasting is critical for grid-connected solar power safety and stability, achieved through machine learning (ML) for both common and real-time applications. To mitigate the impact of nonstationarity and volatility in solar power generation, we employed empirical mode decomposition (EMD), ensemble empirical mode decomposition (EEMD), variational mode decomposition (VMD), and complete EEMD with adaptive noise (CEEMDAN) to decompose time series into frequency components, reducing fluctuations and noise. A combination of four decomposition methods (EMD, EEMD, VMD, and CEEMDAN) and two ML models, bidirectional gated recurrent unit (BiGRU) and bidirectional long short-term memory (BiLSTM) were utilized to construct six hybrid forecasting models (EMD-BiLSTM, EMD-BiGRU, EEMD-BiLSTM, EEMD-BiGRU, VMD-BiGRU, and CEEMDAN-BiGRU), which were validated on a dataset from a 20 MW solar power station in Hebei, compared to the seven standalone ML models, backpropagation neural networks (BPNN), support vector machines (SVM), long short-term memory (LSTM), gated recurrent unit (GRU), convolutional neural networks (CNN), BiLSTM, and BiGRU, these six hybrid models demonstrated enhanced forecast accuracy. Of these, EEMD-BiGRU, VMD-BiGRU, and CEEMDAN-BiGRU significantly reduced prediction errors, with percentage reductions in root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) ranging from 44.18 ~ 49.43%, 43.67 ~ 48.59%, and 44.64% ~53.53%, respectively. The EEMD-BiGRU model outperformed all hybrid models, achieving an RMSE of 0.7662, MAE of 0.3990, MAPE of 7.982%, and R2 of 0.9865. The findings of this study can provide insights and support for applying a hybrid model based on decomposition methods for the short-term forecasting of solar power generation.

Enhancing lithium-ion battery lifespan early prediction using a multi-branch vision transformer model

Accurately predicting the lifespan of lithium-ion batteries is crucial for effective battery management systems, particularly for ensuring the safe operation and proactive maintenance of electric vehicles. However, existing methods encounter challenges due to the early weak capacity aging trend in batteries. This study a novel approach using a multibranch vision transformer model to address early stage lifespan prediction issues. The proposed model leverages a multi-input data structure by considering various battery parameters during the charging and discharging phases. By employing distinct branch structures for different inputs, the model can separately extract features from individual input variables. Each vision transformer network was meticulously designed to extract high-dimensional global hidden features from the inputs and integrated to predict the battery lifespan. Comparative analyses against advanced baseline models and existing methods consistently demonstrate the superior performance and robustness of the proposed model. Compared with traditional vision transformer, the proposed model demonstrated a notable reduction in root mean square errors of 13.17 % and 6.32 % on the two public datasets, respectively, indicating the efficacy and reliability of our approach for accurately predicting the lifespan of LIBs during the early stages of capacity decline.

Quantifying gas emissions through Vertical Radial Plume Mapping based on historical information

Vertical Radial Plume Mapping (VRPM) is a method for measuring fluxes of fugitive surface source gases, lacking sufficient temporal sequence information as it inversely calculates fluxes only based on the current cycle’s measurements. We propose an improved VRPM flux inversion model, incorporating Weighted Iterative Average (WIA) corrected Path-Integrated Concentration (PIC) and Adaptive Weighted Sum of Squared Errors (AWSSE). Compared to the original VRPM, our model introduces historical measurement PICs and reconstructed PICs. Using the Bayesian Optimization Gaussian Processes (BO-GP), we derive optimal weight factor for the hyperparameter of the WIA component in the model. Validation on simulated data highlights the superior flux inversion capability of the WIA-AWSSE-VRPM model across diverse surface sources, efficiently leveraging historical data. The improved VRPM method achieves a significant 9.65% reduction in root mean square error (RMSE) within consistent source sets and decreases RMSE from 1.6979 to 0.1513 across varied sources, underscoring its effectiveness in accurately measuring emissions from fugitive sources. Finally, we apply the model to characterize gas emissions in field experiments.

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.

Implementing intelligent‐based sparse channel estimation in Multi User‐Multiple Input Multiple Output‐Orthogonal Frequency Division Multiplexing system with hybridized optimization algorithm

SummaryThe channel plays a significant role as the multipath in Multiple Input Multiple Output‐Orthogonal Frequency Division Multiplexing (MIMO‐OFDM) systems. The precoding‐based channel estimation algorithms estimate the channel capacity at the receiver node and they provide efficient channel estimates under worst case channel scenarios. To estimate the channel capacity in the mobile node, semi‐blind scenario is a crucial task in Multi User (MU) MIMO systems. Therefore, a semi blind sparse channel estimation algorithm is demonstrated in the MU‐MIMO system to provide better performance. In the transmitter side, the signal modulation is performed with the help of Quadrature Phase Shift Keying (QPSK), and the modulated signal is given to Pulse Shaping Algorithm (PSA) to reduce the inter‐carrier interference as well as inter symbol interference. At each transmitter, the Inverse Fast Fourier Transforms (IFFT) technique is used for mapping the symbols and then the mapped signal is send to the receiver. In the receiver side, the FFT, pulse reshaping, and QPSK demodulation blocks are serially connected and perform inverse operations of the transmitter in the receiver. Then, the sparse channel is estimated at the receiver by using the semi blind sparse algorithm, where the parameters are optimized by using the Hybridized Drosophila with Virus Colony Search Optimization (HD‐VCSO). The objective function of the developed sparse channel estimation is the reduction of Minimum Mean Square Error (MMSE) in the channel. The performance of the developed sparse channel estimation algorithm is analyzed through different conventional algorithms to validate the effectiveness of the proposed algorithm.