Mean Square Error Values Research Articles

Hybrid Encoding Schemes in Image Steganography Combined with Scrambling for Safeguarding Legal Asset Documents

Objective: The main objective of the study is to provide security to legal asset documents by including the details of ownership of the asset. Methods: This paper aims to improve security of legal asset documents using hybrid encoding schemes in Image Steganography combined with Image Scrambling. The proposed work uses images were gathered from various online sources grouped into a dataset of 40 images along with their 40 text files respectively. The techniques that were applied in the research are pre-processing for the noise removal, Steganography to embed data into image and Scrambling to introduce blur to the image. Finally, the objective metrics like Mean-Square Error (MSE), Peak Signal - Noise Ratio (PSNR) and Signal to Noise Ratio (SNR) values were calculated from them and compared with the acceptable values of the respective metrics. Findings: In the existing study, Steganography and Scrambling has been used separately for data and image security but in the proposed technique, Steganography has been applied with the land ownership data being hidden in the document image and the image being scrambled using different masks. The objective metrics gave the results such as the MSE value ranged between 0.0 and 10.0; the SNR value ranged between 14 dB to 80 dB; the PSNR value lies between 27 dB to 100 dB. The outcome of these values was mostly within the acceptable value range for all the measures here. Novelty: The proposed output dataset contains land asset documents that have details of ownership embedded in itself. Also, the hybrid encoding schemes of both the steganography and scrambling used here gives us data and image security together as proved in the outcome. Keywords: Image Steganography, Scrambling, Text Hiding, Legal Documents, Data Security

Generation of synthetic PET/MR fusion images from MR images using a combination of generative adversarial networks and conditional denoising diffusion probabilistic models based on simultaneous 18F-FDG PET/MR image data of pyogenic spondylodiscitis

BACKGROUND CONTEXTCross-modality image generation from magnetic resonance (MR) to positron emission tomography (PET) using the generative model can be expected to have complementary effects by addressing the limitations and maximizing the advantages inherent in each modality. PURPOSEThis study aims to generate synthetic PET/MR fusion images from MR images using a combination of generative adversarial networks (GANs) and conditional denoising diffusion probabilistic models (cDDPMs) based on simultaneous 18F-fluorodeoxyglucose (18F-FDG) PET/MR image data. STUDY DESIGNRetrospective study with prospectively collected clinical and radiological data. PATIENT SAMPLEThis study included 94 patients (60 men and 34 women) with thoraco-lumbar pyogenic spondylodiscitis (PSD) from February 2017 to January 2020 in a single tertiary institution. OUTCOME MEASURESQuantitative and qualitative image similarity were analyzed between the real and synthetic PET/ T2-weighted fat saturation MR (T2FS) fusion images on the test data set. METHODSWe used paired spinal sagittal T2FS and PET/T2FS fusion images of simultaneous 18F-FDG PET/MR imaging examination in patients with PSD, which were employed to generate synthetic PET/T2FS fusion images from T2FS images using a combination of Pix2Pix (U-Net generator + Least Squares GANs discriminator) and cDDPMs algorithms. In the analyses of image similarity between the real and synthetic PET/T2FS fusion images, we adopted the values of mean peak signal to noise ratio (PSNR), mean structural similarity measurement (SSIM), mean absolute error (MAE), and mean squared error (MSE) for quantitative analysis, while the discrimination accuracy by three spine surgeons was applied for qualitative analysis. RESULTSTotal of 2,082 pairs of T2FS and PET/T2FS fusion images were obtained from 172 examinations on 94 patients, which were randomly assigned to training, validation, and test data sets in 8:1:1 ratio (1664, 209, and 209 pairs). The quantitative analysis revealed PSNR of 30.634 ± 3.437, SSIM of 0.910 ± 0.067, MAE of 0.017 ± 0.008, and MSE of 0.001 ± 0.001, respectively. The values of PSNR, MAE, and MSE significantly decreased as FDG uptake increased in real PET/T2FS fusion image, with no significant correlation on SSIM. In the qualitative analysis, the overall discrimination accuracy between real and synthetic PET/T2FS fusion images was 47.4%. CONCLUSIONSThe combination of Pix2Pix and cDDPMs demonstrated the potential for cross-modal image generation from MR to PET images, with reliable quantitative and qualitative image similarities.

Research on the chemical oxygen demand spectral inversion model in water based on IPLS-GAN-SVM hybrid algorithm.

Spectral collinearity and limited spectral datasets are the problems influencing Chemical Oxygen Demand (COD) modeling. To address the first problem and obtain optimal modeling range, the spectra are preprocessed using six methods including Standard Normal Variate, Savitzky-Golay Smoothing Filtering (SG) etc. Subsequently, the 190-350 nm spectral range is divided into 10 subintervals, and Interval Partial Least Squares (IPLS) is used to perform PLS modeling on each interval. The results indicate that it is best modeled in the 7th range (238~253 nm). The values of Mean Square Error (MSE), Mean Absolute Error (MAE) and R2score of the model without pretreatment are 1.6489, 1.0661, and 0.9942. After pretreatment, the SG is better than others, with MSE and MAE decreasing to 1.4727, 1.0318 and R2score improving to 0.9944. Using the optimal model, the predicted COD for three samples are 10.87 mg/L, 14.88 mg/L, and 19.29 mg/L. To address the problem of the small dataset, using Generative Adversarial Networks for data augmentation, three datasets are obtained for Support Vector Machine (SVM) modeling. The results indicate that, compared to the original dataset, the SVM's MSE and MAE have decreased, while its accuracy has improved by 2.88%, 11.53%, and 11.53%, and the R2score has improved by 18.07%, 17.40%, and 18.74%.

A Hybrid Neural Network‐Based Improved PSO Algorithm for Gas Turbine Emissions Prediction

AbstractIn gas‐fired power plants, emissions may reduce turbine blade rotation, thus decreasing power output. This study proposes a hybrid model integrating the Feed forward Neural Network (FFNN) model and Particle Swarm Optimization (PSO) algorithm to predict gas emissions from natural gas power plants. The FFNN predicts gas turbine nitrogen oxides (NOx) and carbon monoxide (CO) emissions, while the PSO optimizes FFNN weights, improving prediction accuracy. The PSO adopts a unique random number selection strategy, incorporating the K‐Nearest Neighbor (KNN) algorithm to reduce prediction errors. Neighbor Component Analysis (NCA) selects parameters most correlated with CO and NOx emissions. The hybrid model is constructed, trained, and testedusing publicly available datasets, evaluating performance with statistical metrics like Mean Square Error (MSE), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE). Results show significant improvement in FFNN training with the PSO algorithm, boosting CO and NOx prediction accuracy by 99.18% and 82.11%, respectively. The model achieves the lowest MSE, MAE, and RMSE values for CO and NOx emissions. Overall, the hybrid model achieves high prediction accuracy, particularly with optimized PSO parameter selection using seed random generators.

Short-Term Electrical Energy Demand Forecasting Using Fuzzy Logic Technique

Minimization of electrical energy wastage and provision of its regular supply make electrical load forecasting an important aspect of the power infrastructure. An accurate load forecasting is crucial for the reduction of the cost of electrical energy generation and spinning reserve capacity. Therefore, in this study, fuzzy logic (FL) technique was employed for the projection of electrical energy demand on short-term basis. The FL model was trained using the six months hourly load and temperature data respectively obtained from 132/33 kV Ikeja West Transmission Station, Ayobo and Nigerian Meteorological Agency, Oshodi, Lagos State, Nigeria. Triangular and trapezoidal membership functions (MFs) were used in the training of the model with Mamdani fuzzy inference system. The time, load and temperature inputs were fuzzified into six, four and three MFs respectively while the fuzzification process used 25 fuzzy rule bases. The centroid method of defuzzification was used to change the results into readable values. The adequacy of the FL model was determined using five metrics including mean square error (MSE), mean absolute error (MAE), mean absolute percentage error (MAPE), chi square (χ2) and F- test. The obtained results revealed that the FL model developed excelled in all the five tests of adequacy considered with MSE, MAE, MAPE, χ2 and F-test values of 4.17, 6.74, 11.51%, 7.93 and 1.27 respectively and hence, performed satisfactorily. This work established that the fuzzy logic approach is appropriate for electrical load projection on short-term basis.

Predicted evaporation in Basrah using artificial neural networks

Abstract Accurate evaporation estimation is crucial for managing hydrologic, hydraulic, and agricultural systems, among many other applications of water resources. Empirical formulae for estimating evaporation exist, but their performance is not always sufficient due to the intricacy of the process and its nonlinear connection with other elements of the hydrological cycle. For this reason, a model of artificial neural networks was developed to estimate the daily potential evaporation in the southern Iraqi city of Basrah. A feedforward backpropagation (BP) network with a single hidden layer has been used to construct the mode. Different networks with various neuron counts were assessed. The developed models have been trained, tested, and validated using daily observations of the average rainfall, wind speed, average temperature, average relative humidity, and evaporation. The final evaporation was predicted using an artificial neural network (ANN) model. The proposed model was found to be more suitable to describe evaporation in any region of the world based on the values of the error analysis and the coefficient of determination, according to the ANN model. The Levenberg–Marquardt algorithm (LMA) was determined to have the lowest mean-squared error (MSE) and highest value of the coefficient of correlation (R) of the six proposed BP algorithms. The LMA’s hidden layer’s ideal neuron count was 30 neurons, with an MSE of 0.00288 and R 2 = 99. As a result, ANN displayed excellent performance in terms of evaporation prediction value. The study’s findings highlight the significance of predicting evaporation as the main metric for evaluating the effects of climate change on water resources.

Modeling the adsorption of ibuprofen on the Zn-decorated S,P,B co-doped C2N nanosheet: Machine learning and central composite design approaches

The ibuprofen (IB) residuals in water resources are classified as toxic and non-biodegradable contaminants. In the previous study, the Zn-decorated S,P,B co-doped C2N (Zn-SPB@C2N) nanosheet exhibited significant effectiveness in adsorbing IB from aqueous solutions. However, the operating conditions were not optimized for the adsorption process. The current study modeled the adsorption of IB onto Zn-SPB@C2N nanosheets employing central composite design (CCD) and machine learning (ML) methods under various operating conditions. The operating conditions included adsorbent mass, initial IB concentration, and pH. The CCD model revealed a mean squared error (MSE) value of 36.56. The ML investigations showed MSE values of 28.12 for the artificial neural network (ANN), 10.12 for the decision tree (DT), 8.68 for the linear regression (LR), and 3.70 for the random forest (RF) models. The RF model demonstrated high reliability in predicting IB removal across various conditions compared to other methods. Using the RF model, a maximum removal efficiency of 98 % was achieved under the optimized operating conditions, containing a pH of 7, an initial concentration of 59 mg/L, and an adsorbent mass of 0.020 g.

Analysis of Ground Vibration Levels Due to the Blasting Process at PT. Bumi Suksesindo

Ground vibration is one of the effects of the blasting process; when the ground vibration reaches the highest level, it will disturb comfort and even cause damage to the surrounding building structure. This research aims to determine the magnitude of ground vibrations in Pit A and Pit C, as well as determine the relationship between Peak Particle Velocity (PPV) and scaled Distance, and determine the maximum explosive charge weight per delay based on the SNI 7571: 2010 reference. Actual ground vibration measurement data during research based on PPV theory and the actual PPV power regression relationship with scaled distance was used to obtain a ground vibration prediction formula to be a reference for determining the amount of explosive filling per delay. The ground vibration produced in the blasting process is hoped not to exceed the safe threshold. Prediction of the ground vibration formula at 100 m to 1500 m according to the US Bureau of Mines where the Mean Squared Error (MSE) value is 0.54, the MSE value from the Langefors-Kihlstrom equation is 1.85 while the MSE value from the Ambersays-Hendorn equation is 0.31 with the slightest deviation is very good to use as a reference for predicting ground vibrations with the predicted PPV formula. Hence, the maximum explosive charge with a PPV limit of 2 mm/s is 2.452 kg, a PPV limit of 3 mm/s is 11.332 kg, and a PPV limit of 5 mm/s is 23.040 kg. The factors that influence ground vibration are the Distance from the blasting location to the measurement location and the maximum number of explosives per delay, so the results taken from this research are that blasting in Pit A and Pit C is still categorized as safe for infrastructure and community housing.

Investigation of waste LDPE with Pongamia pinnata seed for sustainable resource recovery: Thermodynamics, Kinetics and artificial neural network modeling for co-pyrolysis potential

Pyrolysis conversion offers the advantages of significant waste reduction and potential energy recovery. This work examined the potential of combining plastic and agricultural wastes as pyrolysis feedstocks. The mixture of waste low-density polyethylene and Pongamia pinnata seeds was analysed using differential and thermogravimetric methods. In addition to the Coats-Redfern (CR) method, Kissinger-Akahira-Sunose (KAS), Flynn-Wall-Ozawa (FWO), Friedman (FRM), and Kissinger (KN) model-free methods were also applied to calculate the kinetic parameters. The apparent activation energy (Ea) calculation demonstrated that the co-pyrolysis conversion required Ea values of 125–154 kJ mol−1. The artificial neural network (ANN) model was considered to validate thermogravimetric data. The R2 values were near unity in training, validation, and testing conditions, with the minimum possible value for mean square error obtained for the considered heating rates. The Pongamia pinnata seeds and waste plastic mixture could surely be utilized to lessen environmental degradation, add value to leftover seeds and waste low-density polyethylene by extracting fuel for transportation and other commercial activities, and produce industrial chemicals, as found through the kinetic modelling, thermodynamic parameters, and ANN modelling.

Prediction of rock fragmentation in a fiery seam of an open-pit coal mine in India

Spontaneous combustion of coal increases the temperature in adjoining overburden strata of coal seams and poses a challenge when loading blastholes. This condition, known as hot-hole blasting, is dangerous due to the increased possibility of premature explosions in loaded blastholes. Thus, it is crucial to load the blastholes with an appropriate amount of explosives within a short period to avoid premature detonation caused by high temperatures of blastholes. Additionally, it will help achieve the desired fragment size. This study tried to ascertain the most influencial variables of mean fragment size and their optimum values adopted for blasting in a fiery seam. Data on blast design, rock mass, and fragmentation of 100 blasts in fiery seams of a coal mine were collected and used to develop mean fragmentation prediction models using soft computational techniques. The coefficient of determination (R2), root mean square error (RMSE), mean absolute error (MAE), mean square error (MSE), variance account for (VAF) and coefficient of efficiency in percentage (CE) were calculated to validate the results. It indicates that the random forest algorithm (RFA) outperforms the artificial neural network (ANN), response surface method (RSM), and decision tree (DT). The values of R2, RMSE, MAE, MSE, VAF, and CE for RFA are 0.94, 0.034, 0.027, 0.001, 93.58, and 93.01, respectively. Multiple parametric sensitivity analyses (MPSAs) of the input variables showed that the Schmidt hammer rebound number and spacing-to-burden ratio are the most influencial variables for the blast fragment size. The analysis was finally used to define the best blast design variables to achieve optimum fragment size from blasting. The optimum factor values for RFA of S/B, ld/B and ls/ld are 1.03, 1.85 and 0.7, respectively.

Agriculture crop yield prediction using inertia based cat swarm optimization

Crop yield prediction is among the most important and main sources of income in the Indian economy. In this paper, the improved cat swarm optimization (ICSO) based recurrent neural network (RNN) model is proposed for crop yield prediction using time series data. The inertia weight parameter is added to position equation that is selected randomly, and a new velocity equation is produced which enhances the searching ability in the best cat area. By using inertia weight, the ICSO enhances performance of feature selection and obtains better convergence in minimum iteration. The RNN is applied to produce direct graph using sequence of data and decides current layer output by involving all other existing calculations. The performance of the model is estimated using coefficient of determination (R2), root mean square error (RMSE), mean squared error (MSE), and mean absolute error (MAE) on the yield from the years 2011 to 2021 with an annual prediction for 120 records of approximately 8 million nuts. The evaluated result shows that the proposed ICSO-RNN model delivers metrics such as R2, MAE, MSE, and RMSE values of 0.99, 0.77, 0.68, and 0.82 correspondingly, which ensures accurate yield prediction when compared with the existing methods which are hybrid reinforcement learning-random forest (RL-RF) and machine learning (ML) methods.

Wildfire Prediction in the United States Using Time Series Forecasting Models

Wildfires are a widespread phenomenon that affects every corner of the world with the warming climate. Wildfires burn tens of thousands of square kilometres of forests and vegetation every year in the United States alone with the past decade witnessing a dramatic increase in the number of wildfire incidents. This research aims to understand the regions of forests and vegetation across the US that are susceptible to wildfires using spatiotemporal kernel heat maps and, forecast these wildfires across the United States at country-wide and state levels on a weekly and monthly basis in an attempt to reduce the reaction time of the suppression operations and effectively design resource maps to mitigate wildfires. We employed the state-of-the-art Neural Basis Expansion Analysis for Time Series (N-BEATS) model to predict the total area burned by wildfires by several weeks and months into the future. The model was evaluated based on forecasting metrics including mean-squared error (MSE)., and mean average error (MAE). The N-BEATS model demonstrates improved performance compared to other state-of-the-art (SOTA) models, obtaining MSE values of 116.3, 38.2, and 19.0 for yearly, monthly, and weekly forecasting, respectively.

Comparative Analysis of Ensemble Learning Techniques and ANN for Prediction of Compressive Strength of Concrete Mix

Abstract: In this study, non-linear machine learning regressors and an artificial neural network (ANN) were modeled to predict the compressive strength of concrete mixes. A dataset of 1030 mix design data points with a wide range of compressive strength varying from M10 to M80 is taken into account. The data set comprised of 8 input parameters namely- cement, water, fine & coarse aggregate, flyash, slag, superplasticizer, and age. The paper also analyzes effects on the prediction of compressive strength due to waiving of the parameters with lesser importance factors. To improve the performances of models by reducing the variance, biases, and errors, K-fold cross-validation was examined. To examine the performances of the models, metrics such as coefficient of determination (R2) and mean square error (MSE) were employed. Most of the models can predict the compressive strength with good accuracy. Out of the 7-machine learning regressors and ANN models employed, Gradient Boosting Regressor yielded the best prediction accuracy of 0.9561 with the lowest MSE value of 0.0513.

LSB-2 Steganography with Brotli Compression and base64 Encoding for Improving Data Embedding Capacity

Steganography functions as a technique for embedding messages or data in various forms of media, such as images, audio, video, or text, with the aim of avoiding detection by unauthorized parties. Steganography techniques can be used as a solution to hide and protect data. In this research, steganography will be carried out using images as the transmission object. This research was conducted to offer a modification of the Least Significant Bit (LSB) steganography technique using the LSB-2 method with Brotli compression and base64 encoding. Modification and use of Brotli compression and base64 coding aims to increase the message capacity that can be embedded in a transmission object while maintaining the quality of the transmission object. Experiments using small data and big data. The experimental results will be presented in tabular form by comparing the original image with the steganographically processed image using metrics such as Mean Square Error (MSE), Peak Signal-to-Noise Ratio (PSNR), and Structural Similarity Index (SSIM) as a comparison. The experiments carried out resulted in an increase in image capacity by reducing capacity usage with an average of 47.13% for small data and an average of 71.34%. The big data experiment resulted in an increase in the PSNR value of around 3.49%, accompanied by a decrease in the average MSE value of 33.85%, and a constant SSIM value of 0.9999, thus proving that the proposed method was successful in increasing image capacity and improving stego-image quality. when embedding big data.

Prognostic Modelling of Biomethane Production from Waste: Application of Extreme Gradient Boosting

The escalating fossil fuel prices and greenhouse gases need urgent attention for a sustainable solution. The present study explores as modern machine learning approaches can be employed to prognosticate the complex biomethane generation process from organic wastes, like biowaste or food waste. The research investigates the use of organic sludges and how intelligent approaches can be employed to comprehend the complex nonlinear processes involved in biomethane production. Linear regression and Extreme gradient boosting (XGBoost) based prediction-models were developed and assessed employing a diverse set of statistical parameters, including R, R2, Mean Squared Error (MSE), Mean Absolute Error (MAE), and Kling-Gupta Efficiency (KGE). The results show that the XGBoost model beat the classical Linear Regression (LR) model in both the training and testing phases. During training, the XGBoost had an impressive R2 value of 0.99994, indicating a perfect fit to the data. In contrast, LR achieved an R2 value of 0.65464. Similarly, during the test period, XGBoost outperformed LR with R2 values ​​of 0.9553 to 0.9902. Furthermore, XGBoost reduced prediction errors, with significantly lower MSE and MAE values ​​than LR. Taylor’s graph better illustrates the excellent performance of the XGBoost over LR in both training and testing. These data demonstrate the ability of XGBoost to predict biomethane production, as well as its ability to improve the biomethane production process.

Study on Landslide Displacement Prediction Considering Inducement under Composite Model Optimization

The precise extraction of displacement time series for complex landslides poses significant challenges, and conventional landslide prediction models often overlook the deformation impacts of displacement triggers. To address this, we introduce a novel composite model tailored for predicting landslide displacement. This model employs Variational Mode Decomposition (VMD) to isolate each displacement component, with optimization achieved through the groupwise coupling algorithm. Subsequently, Grey correlation analysis (GRA) is applied to quantitatively assess the dynamic correlations between various triggering factors and landslide displacement. This analysis informs the construction of a feature set predicated on these correlation factors. Integrating the time-series VMD module into the standard Transformer architecture facilitates the prediction of landslide displacement. This integration allows for the extraction of critical time-evolution features associated with the displacement components. Ultimately, the predicted displacements are aggregated and reconstructed. We validate our model using the Bazimen landslide case study, analyzing displacement monitoring data from 1 January 2007, to 31 December 2012. The values of the root mean square error and the mean absolute percentage error were 1.86 and 4.85, respectively. This model offers a more nuanced understanding of the multifaceted causes and evolutionary dynamics underpinning landslide displacement and deformation, thereby markedly enhancing prediction accuracy.

Estimation of soil erodibility in Peninsular Malaysia: A case study using multiple linear regression and artificial neural networks

Soil erodibility (K) is an essential component in estimating soil loss indicating the soil's susceptibility to detach and transport. Data Computing and processing methods, such as artificial neural networks (ANNs) and multiple linear regression (MLR), have proven to be helpful in the development of predictive models for natural hazards. The present case study aims to assess the efficiency of MLR and ANN models to forecast soil erodibility in Peninsular Malaysia. A total of 103 samples were collected from various sites and K values were calculated using the Tew equation developed for Malaysian soil. From several extracted parameters, the outcomes of correlation and principal component analysis (PCA) revealed the influencing factors to be used in the development of ANN and MLR models. Based on the correlation and PCA results, two sets of influencing factors were employed to develop predictive models. Two MLR (MLR-1 and MLR-2) models and four neural networks (NN-1, NN-2, NN-3, and NN-4) optimized using Levenberg-Marquardt (LM) and scaled conjugate gradient (SCG) were developed and evaluated. The model performance validation was conducted using the coefficient of determination (R2), mean squared error (MSE), root mean squared error (RMSE), and Nash-Sutcliffe efficiency coefficient (NSE). The analysis showed that ANN models outperformed MLR models. The R2 values of 0.446 (MLR-1), 0.430 (MLR-2), 0.894 (NN-1), 0.855 (NN-2), 0.940 (NN-3), and 0.826 (NN-4); MSE values of 0.0000306 (MLR-1), 0.0000315 (MLR-2), 0.0000158 (NN-1), 0.0000261 (NN-2), 0.0000318 (NN-3), and 0.0000216 (NN-4) suggested the higher accuracy and lower modelling error of ANN models as compared with MLR. This study could provide an empirical basis and methodological support for K factor estimation in the region.

Predicting Crime rate in Punjab: An Analysis of Artificial Intelligence based Models

This study aims at measuring and evaluating the accuracy rate or Mean Square Error (MSE) of different machine learning models to predict crime count (dependent variable) on the basis of a number of independent variables such as shift, day, month, police station, district and time of the day. It is a quantitative research study where primary data is collected from rescue 15 call record. The year 2022 has been chosen for the purpose of data under the crime head of theft across the Punjab province which is divided into three eight hourly shifts each in a day during any week of a month. The crime count indicates number of incidents of theft reported during these three shifts per day per month in a district in 2022. The data containing variables is then used for prediction through an appropriate machine learning model. The MSE value of Random Forest Regression (RFR) is greater than MSE value of Multi-Layer Perceptron Regression (MLPR). It is however lower than MSE score of Linear Regression (LR) model and greater than MSE value of Support Vector Regression (SVR). This shows that MLPR model is the most suitable one with least error as compared to other models which have higher MSE values while predicting the dependent variable (theft crime count). The study findings may assist the intelligence branches of police to efficiently utilize their material and human resources while applying the appropriate model of machine learning to predict the number of crime incidents in any geographical dispensation at sub national level.

Remaining useful life prediction of lithium-ion batteries combined with SVD-SDAE and support vector quantile regression

Lithium-ion batteries are important energy storage materials, and the prediction of their remaining useful life has practical importance. Since traditional feature extraction methods depend on parameter settings and have poor adaptability, singular value decomposition was used to extract 15 health indicators from the degradation data of lithium-ion batteries. To eliminate redundancy among the extracted health indicators, Spearman correlation analysis was subsequently used to determine the most appropriate health indicators. On this basis, the selected health indicators were processed by the denoising stack autoencoder, and a fusion health indicator was obtained. Finally, the support vector quantile regression model was used to predict the battery capacity interval by the fusion health indicator. The National Aeronautics and Space Administration battery dataset and Massachusetts Institute of Technology battery dataset were used to verify the validity and generalizability of our proposed model, and our proposed model was compared with the existing four classical prediction models. The experimental results showed that our proposed prediction model had higher prediction accuracy and better robustness than the other models and could effectively improve the prediction effect of the remaining useful life of batteries. The mean value of the root mean square error of the predicted results using our proposed model remained within 1.3%, and the mean value of the coefficient of determination was above 0.97.

A Comparative Study on the Performance of Covariance Functions in Gaussian Process Regression model: Application to Global Wheat Price

Gaussian Process Regression (GPR) is a nonparametric machine learning model that provides uncertainty quantification in making predictions. GPR utilizes several covariance functions (CFs) in the process of developing models to ensure high accuracy. There are five common CFs in GPR, which are the Radial Basis Function (RBF), Rational Quadratic (RQ), Periodic (Per), Matérn 3/2 (Mat 3/2), and Matérn 5/2 (Mat 5/2), where each covariance function (CF) has different characteristics and behaviors. This paper is to investigate the comparative performances of each CF when applied to the Global Wheat Prices dataset. Error metric measurement like Mean Square Error (MSE) and Root Mean Square Error (RMSE), while Coefficient of Variation (CV) for uncertainty quantification measurement is computed for each CF, and comparisons was made among the CFs to conclude the best CF for this application. The lowest values among them will be the best CF for the data. It should be noted that the CV for each model should be less than 5%, and the CF with the smallest value of CV is considered reliable. The five CFs were fit to the Global Wheat Prices dataset, and it was found that the Mat 3/2 produced the best performances with the lowest values of MSE, RMSE, and CV. Mat 3/2 is the most efficient CF for making predictions since it gives the lowest value of error metric measurement and the lowest value of CV under 5% among the other CFs, making it more reliable for modeling. Overall, the outcome shows that Mat 3/2 is the best CF to be used in developing a GPR model to predict Global Wheat Prices dataset.