Combination Of Kernels Research Articles

Research on Detection of Icing Cover Transmission Lines Under Different Weather Conditions Based on Wide-Field Dynamic Convolutional Network LDKA-NET

The safety of transmission lines is a crucial guarantee for the operation of the power grid. To address the issue of low detection accuracy for icing transmission line defects with existing models, this paper proposes a defect detection algorithm for icing transmission line defects under different weather conditions based on a Large Dynamic Kernel Aggregation Net (LDKA-NET). First, a wide field of view convolutional network (WFVC Net) is introduced to enhance the network’s perception and generalization capabilities, enabling better adaptation to complex scene targets. Secondly, a full-dimensional dynamic convolutional feature fusion network is proposed, which strengthens the model’s feature extraction ability by learning linear combinations of multiple convolution kernels and their weighted input-related attention. Finally, an Expectation Maximization Dynamic Convolutional Attention (EM-DCA) mechanism is introduced, which focuses on and utilizes important information in the input data to help the model better allocate attention, thereby improving its generalization and robustness. Experimental results show that on the dataset proposed in this paper, the average accuracy of the improved algorithm (mAP@0.5) reaches 99.01%. The model parameters decreased by 47.7 M compared with the baseline model and 91.26 M compared with the Faster region with CNN feature (Faster R-CNN) model. The accuracy is 4.81% and 3.11% higher than the SSD model and YOLOv5-L model, respectively. Compared with the existing models, our model is smaller and has higher detection accuracy. It can accurately detect ice-covered wires and complete the task of the ice-covered detection of transmission lines.

FOSSIL FUEL EMISSION PREDICTION SYSTEM USING MULTIPLE KERNEL GAUSSIAN PROCESS

<p>According to the United States Environmental Protection Agency, 81% of greenhouse gas emission is due to Carbon-dioxide. When fossil fuels, solid waste, trees, and wood products are burnt, Carbon-dioxide emission occurs. The concentration of Carbon-dioxide in the atmosphere is reduced when it is absorbed by plants as a part of the biological carbon cycle. The major sources of CO2 emission are from fossil fuel such as coal, natural gas, oil, cement production, gas flares used in industrial plants and bunker fuels used in ships. Increase in CO2 emission leads to the increase in global warming. Climate change, change in seasonal events and decrease in agricultural productivity are the major impacts of global warming. Hence it is important to study and analyse CO2 emission based on the recorded data across the globe. Further the major source of emission must be detected and alert messages must be sent to the pollution control boards in various countries to take necessary remedial actions. This work focuses on predicting the CO2 emission in the near future in various countries based upon the “Fossil-Fuel CO2 Emissions by Nation” dataset recorded by Carbon Dioxide Information Analysis Center (CDIAC), Oak Ridge National Laboratory. This system comprises of data cleaning, data normalization, optimization, and model building. The model built using Multiple Kernel Gaussian Process (MKGP) will predict the concentration of CO2 that may be present in the atmosphere in upcoming years. Based on the prediction the major source of CO2 emission is identified. We have studied the effects of Radial Basis Function kernel, Rational Quadratic, Periodic kernel and combinations of the kernels on India USA and China dataset. We have proposed a Multi-Kernel Gaussian Process for predicting the fossil fuel emission (MKGP - FFE). It has been inferred that combination of kernels performed well when compared to individual kernels in most of the cases.</p>

Regularized Simple Multiple Kernel k -Means With Kernel Average Alignment.

Multiple kernel clustering (MKC) aims to learn an optimal kernel to better serve for clustering from several precomputed basic kernels. Most MKC algorithms adhere to a common assumption that an optimal kernel is linearly combined by basic kernels. Based on a min-max framework, a newly proposed MKC method termed simple multiple kernel k -means (SimpleMKKM) can acquire a high-quality unified kernel. Although SimpleMKKM has achieved promising clustering performance, we observe that it cannot benefit from any prior knowledge. This would cause the learned partition matrix may seriously deviate from the expected one, especially in clustering tasks where the ground truth is absent during the learning course. To tackle this issue, we propose a novel algorithm termed regularized simple multiple kernel k -means with kernel average alignment (R-SMKKM-KAA). According to the experimental results of existing MKC algorithms, the average partition is a strong baseline to reflect true clustering. To gain knowledge from the average partition, we add the average alignment as a regularization term to prevent the learned unified partition from being far from the average partition. After that, we have designed an efficient solving algorithm to optimize the new resulting problem. In this way, both the incorporated prior knowledge and the combination of basic kernels are helpful to learn better unified partition. Consequently, the clustering performance can be significantly improved. Extensive experiments on nine common datasets have sufficiently demonstrated the effectiveness of incorporation of prior knowledge into SimpleMKKM.

ECTFormer: An efficient Conv-Transformer model design for image recognition

Since the success of Vision Transformers (ViTs), there has been growing interest in combining ConvNets and Transformers in the computer vision community. While the hybrid models have demonstrated state-of-the-art performance, many of these models are too large and complex to be applied to edge devices for real-world applications. To address this challenge, we propose an efficient hybrid network called ECTFormer that leverages the strengths of ConvNets and Transformers while considering both model performance and inference speed. Specifically, our approach involves: (1) optimizing the combination of convolution kernels by dynamically adjusting kernel sizes based on the scale of feature tensors; (2) revisiting existing overlapping patchify to not only reduce the model size but also propagate fine-grained patches for the performance enhancement; and (3) introducing an efficient single-head self-attention mechanism, rather than multi-head self-attention in the base Transformer, to minimize the increase in model size and boost inference speed, overcoming bottlenecks of ViTs. In experimental results on ImageNet-1K, ECTFormer not only demonstrates comparable or higher top-1 accuracy but also faster inference speed on both GPUs and edge devices compared to other efficient networks.

A novel data-driven state evaluation approach for photovoltaic arrays in uncertain shading scenarios

Accurately determining the operating state of photovoltaic (PV) power-generation equipment and providing accurate support for maintenance management requires evaluation of the states of PV arrays under partial shading conditions. Results of such evaluation enable the optimization of maintenance measures to reduce maintenance costs and extend the lifespan of PV modules, thereby increasing the overall revenue of the PV power station. Therefore, this study proposes a novel state-evaluation approach based on current-voltage (I-V) curves under partial shading conditions. Based on the size of the pixel values in this curve, the proposed novel state-evaluation was performed using the proportion of the values of the normal and shaded curves under the same environmental conditions. Specifically, the feature variables (open-circuit voltage, short-circuit current) and pixel values within the I-V curve were analyzed and calculated using a sensitivity algorithm and computer vision algorithms (Canny edge-detection algorithm and Green's theorem). Based on the mapping relationship between feature variables and pixels, an improved Gaussian-process regression method with a combined kernel function (dot product and Matérn function) was proposed to predict the pixel values under the corresponding normal curve. This combined kernel function effectively captured causal relationships and handled outliers in the test dataset to improve the robustness of the model. Finally, the ratios of the pixel values were calculated using the predicted pixels within the normal curve and the calculated pixels within the shading curve. Experiments demonstrated that the root mean square error (RMSE), mean absolute error (MAE), R squared (R2) and log likelihood of the improved Gaussian-process regression method reached 0.011, 0.0086, 0.9996, and 24.7096, respectively.

Optimizing wheat crop performance: Genomic and phenomic insights into yield and days to maturity prediction using multi‐temporal UAV imagery

AbstractThis study assesses strategies for utilizing multispectral imaging data (from flowering to maturity) to predict late‐season traits in the Norwegian wheat breeding program, comparing them with genomic prediction (GP). In the phenomic prediction (PP) approach, spectral bands, their multispectral relationship matrix (M‐matrix), and vegetation indices (VIs) were considered. GP involved the genomic relationship matrix (G), extended to multi‐kernel predictors by incorporating environmental and genotype–environment interaction effects, complemented with multispectral reflectance data. Two different models including PLSR (partial least square regression) and Bayesian genomic best linear unbiased prediction regressor were applied. The phenological stage of spectral data collection impacted the trait prediction accuracy correlating with the relationship between multispectral data and measured traits. Higher correlations resulted in higher PP prediction accuracy. The results revealed that spectral bands and M‐matrix outperformed VIs by 10%–40% across different timepoints and all timepoints together for grain yield (GY) prediction. The single‐kernel GP model (G) outperformed PP by 28% (using Bayesian) and 29% (using PLSR). The integration of multi‐kernel GP models with spectral data improved GY prediction by up to 4%. In terms of days to maturity (DM) prediction, phenomic methods excelled, surpassing the single‐kernel GP (G: r = 0.63) model by 11% (Bayesian). In conclusion, this study underscores the effectiveness of phenomics prediction for traits like DM and its potential to enhance predictions for complex traits such as GY while highlighting the importance of correlation between measured traits and spectral data, kernel combinations, and model selection for prediction accuracy.

Phase-space density control based on configuration invariant of spacecraft swarm

This paper investigates a phase-space density control based on configuration invariant for large-scale spacecraft swarms. By introducing Jordan-reduced dynamics and the configuration invariant to characterize relative orbits, the macroscopic swarm dynamics is presented with respect to the temporal evolution of phase space density. The density migration of the spacecraft swarm in phase space is modeled as a specific convection–diffusion process, where the diffusion term promotes swarm spreading and the convection term guides the swarm towards a designated region for uniform distribution. Through local density estimation and defining the convection and diffusion terms, the feedback control’s specific form is proposed and its exponential stability is proved. Particularly, the formulation of the convection term outside the target region and the combined kernel function for local density estimation help in avoiding sporadic isolated spacecraft. Numerical results of spacecraft swarm deployment validate the effectiveness and superiority of phase-space density control.

Optimization design of composite cap-shape pillar structure based on gaussian process of combined kernel function

Abstract To quickly realize the optimal design of the cap-shaped structure, an optimization design method of composite cap-shaped pillar structure based on combined kernel function Gaussian process was proposed. First, the shortcomings of two kernel functions representing different linear characteristics of data in model construction were analyzed, on which a new combined kernel function was constructed. Based on the finite element numerical simulation results, a database with the web thickness, web height, fiber volume, and ultimate bearing capacity of the cap-shaped structure was constructed. Then, a Gaussian process model based on the combined kernel function was established and the model parameters were trained by the maximum likelihood method. Finally, taking the ultimate bearing capacity per unit volume as the optimization objective, the artificial fish swarm algorithm was used to quickly obtain the structure design parameters under the optimal objective function, and the simulation results were compared with the initial design parameters. The results showed that the method proposed in this paper can optimize the structure performance, improve the design efficiency, and meet the engineering design requirements.

The equivalent conditions for norm of a Hilbert-type integral operator with a combination kernel and its applications

Introducing adaptation parameters σ,σ1, formal parameters λi(i=1,2,3,4),κ,τ, and type parameters μ,ν, the integration operator is defined as T:Lpp(1−μσˆ)−1(R+)→Lppνσˆ−1(R+), Tf(y)=∫R+eλ1xμyν+κe−λ2xμyνeλ3xμyν+τe−λ4xμyνf(x)dx,y∈R+. Using the weight function method, a general Hilbert-type integral inequality is obtained, thereby proving the boundedness of the operator. The constant factor of the general Hilbert-type inequality is the best possible if and only if the adaptation parameters satisfy σ=σ1. From this, the formula for calculating the operator norm is obtained. In terms of application, some results from the references have been consolidated by discussing the combination of formal parameters and type parameters, and many new operator inequalities of different types and forms have been derived.

Physics-constrained adaptive kernel interpolation for region-to-region acoustic transfer function: a Bayesian approach

A kernel interpolation method for the acoustic transfer function (ATF) between regions constrained by the physics of sound while being adaptive to the data is proposed. Most ATF interpolation methods aim to model the ATF for fixed source by using techniques that fit the estimation to the measurements while not taking the physics of the problem into consideration. We aim to interpolate the ATF for a region-to-region estimation, meaning we account for variation of both source and receiver positions. By using a very general formulation for the reproducing kernel function, we have created a kernel function that considers both directed and residual fields as two separate kernel functions. The directed field kernel considers a sparse selection of reflective field components with large amplitudes and is formulated as a combination of directional kernels. The residual field is composed of the remaining densely distributed components with lower amplitudes. Its kernel weight is represented by a universal approximator, a neural network, in order to learn patterns from the data freely. These kernel parameters are learned using Bayesian inference both under the assumption of Gaussian priors and by using a Markov chain Monte Carlo simulation method to perform inference in a more directed manner. We compare all established kernel formulations with each other in numerical simulations, showing that the proposed kernel model is capable of properly representing the complexities of the ATF.

Polynomial kernel learning for interpolation kernel machines with application to graph classification

Since all training data is interpolated, interpolating classifiers have zero training error. However, recent work provides compelling reasons to investigate these classifiers, including their significance for ensemble methods. Interpolation kernel machines, which belong to the class of interpolating classifiers, are capable of good generalization and have proven to be an effective substitute for support vector machines, particularly for graph classification. In this work, we further enhance their performance by studying multiple kernel learning. To this end, we propose a general scheme of polynomial combined kernel functions, employing both quadratic and cubic kernel combinations in our experimental work. Our findings demonstrate that this approach improves performance compared to individual graph kernels. Our work supports the use of interpolation kernel machines as an alternative to support vector machines, thereby contributing to greater methodological diversity.

Improving the Accuracy of Agricultural Pest Identification: Application of AEC-YOLOv8n to Large-Scale Pest Datasets

Crop diseases and pests are important factors restricting agricultural production. Traditional pest detection methods are mainly targeted at a single pest species, which is difficult to meet the needs of multi-target identification and rapid response in real scenes. Therefore, this paper improves the YOLOv8n model for efficient multi-target pest detection. Two feature enhancement modules, EMSFEM and AFEM_SIE, are proposed in this paper. The EMSFEM module enriches the model’s receptive field through the combination of multi-scale asymmetric convolution kernel and different expansion rates and can better extract the width, height, texture, and edge information of the target. The AFEM_SIE module captures the similarities and differences between upper and lower features through spatial information exchange and enhances feature representation through inter-feature information exchange. In addition, an improved feature fusion operation, Concat_Weighting, is proposed on the basis of Concat. The module uses the learned weights to carry out channel weighting and feature graph weighting for input features, which realizes more flexible and effective feature fusion. The results of experiments conducted on the publicly available large-scale crop pest and disease dataset IP102 show that the performance of the AEC-YOLOv8n model is significantly improved compared with the original YOLOv8n model, with mAP50 increased by 8.9%, accuracy increased by 6.8%, and recall rate increased by 6.3%. The AEC-YOLOv8n model proposed in this study can effectively identify and deal with a variety of crop pests and has achieved the best detection accuracy on the IP102 dataset, which has high application value.

Improved mixture correntropy cubature Kalman filter for attitude estimation

Abstract This work proposes an algorithm based on improved mixture correntropy cubature Kalman filtering (IMC-CKF) to address the issues of low accuracy and susceptibility to complex noise and outlier interference in inertial navigation attitude estimation. First, a combination of Gaussian kernel and Cauchy kernel is suggested to construct mixture correntropy to tackle the problem of single kernel-based correntropy being insufficient to confronted with complex noise. Second, the model fitting loss based on mean square error and measurement fitting loss based on mixture correntropy are used to establish the objective function. The maximum correntropy criterion (MCC) replaces the minimum mean square error (MMSE) criterion, and the fixed-point iteration method is used to solve the objective function, deriving the mixture correntropy matrix to adjust the measurement noise variance. Finally, the semi-trapezoidal membership function is used to determine the mixture correntropy coefficient. Accordingly, the algorithm can adaptively select the proportions of each kernel function according to the respective noise interference situation. Simulations and dynamic–static experiments have been conducted, and the algorithm has been compared with single kernel-based correntropy algorithms and other robust algorithms to confirm its superior precision and stability under complex noise and outlier interference.

Association between rare pathogenic variants in established cancer risk genes and the diagnosis of single and multiple common cancers: A UK Biobank study.

10505 Background: Much of our understanding of cancer risk attributable to rare pathogenic variants (RPV) is derived from family-based and case-only cohort studies, which may be limited by ascertainment bias. We sought to identify associations between RPVs and cancer diagnoses in a large population-based study. Methods: We conducted a case-control study using the UK Biobank. We performed gene-based aggregate testing to examine the relationship between RPVs (defined as pathogenic or likely pathogenic variants) in 96 genes implicated in cancer risk and the diagnosis of 11 common cancers using the combined optimal unified sequence kernel association test (SKAT-O). Odds ratios (OR) and 95% confidence intervals (CI) were then calculated using Firth logistic regression. Results were adjusted for age, sex and genetic ancestry. Bonferroni-adjusted p-values were used to determine statistical significance. Variant pathogenicity was determined by American College of Medical Genetics criteria. Results: We identified 24 genes in which RPVs were statistically significantly associated with at least one of 11 common cancers among 183,626 individuals. The presence of an RPV in one of these 24 genes was associated with increased odds of one cancer (OR 1.8; 95% CI: 1.7-2.0), and multiple cancers (OR 2.5; 95% CI: 2.2-2.9). Conclusions: This large population-based study identified 24 established cancer risk genes in which RPVs were associated with common cancers. We identified both known and novel associations between cancer and RPVs. Some associations—i.e. renal/pancreas and MEN1—may be due to ascertainment and/or misclassification bias. We also show that individuals with RPVs in cancer risk genes not only have higher odds of one cancer diagnosis, but also multiple cancers.[Table: see text]

NEM-GNN: DAC/ADC-less, Scalable, Reconfigurable, Graph and Sparsity-Aware Near-Memory Accelerator for Graph Neural Networks

Graph neural networks (GNNs) are of great interest in real-life applications such as citation networks and drug discovery owing to GNN’s ability to apply machine learning techniques on graphs. GNNs utilize a two-step approach to classify the nodes in a graph into pre-defined categories. The first step uses a combination kernel to perform data-intensive convolution operations with regular memory access patterns. The second step uses an aggregation kernel that operates on sparse data having irregular access patterns. These mixed data patterns render CPU/GPU-based compute energy-inefficient. Von Neumann based accelerators like AWB-GCN [ 7 ] suffer from increased data movement, as the data-intensive combination requires large data movement to/from memory to perform computations. ReFLIP [ 8 ] performs resistive random access memory based in-memory (PIM) compute to overcome data movement costs. However, ReFLIP suffers from increased area requirement due to dedicated accelerator arrangement, and reduced performance due to limited parallelism and energy due to fundamental issues in ReRAM-based compute. This article presents a scalable (non-exponential storage requirement), DAC/ADC-less PIM-based combination, with (i) early compute termination and (ii) pre-compute by reconfiguring SOC components. Graph and sparsity-aware near-memory aggregation using the proposed compute-as-soon-as-ready (CAR) broadcast approach improves performance and energy further. NEM-GNN achieves ∼80–230x, ∼80–300x, ∼850–1,134x, and ∼7–8x improvement over ReFLIP, in terms of performance, throughput, energy efficiency, and compute density.

Impact of deep learning image reconstruction on volumetric accuracy and image quality of pulmonary nodules with different morphologies in low-dose CT

BackgroundThis study systematically compares the impact of innovative deep learning image reconstruction (DLIR, TrueFidelity) to conventionally used iterative reconstruction (IR) on nodule volumetry and subjective image quality (IQ) at highly reduced radiation doses. This is essential in the context of low-dose CT lung cancer screening where accurate volumetry and characterization of pulmonary nodules in repeated CT scanning are indispensable.Materials and methodsA standardized CT dataset was established using an anthropomorphic chest phantom (Lungman, Kyoto Kaguku Inc., Kyoto, Japan) containing a set of 3D-printed lung nodules including six diameters (4 to 9 mm) and three morphology classes (lobular, spiculated, smooth), with an established ground truth. Images were acquired at varying radiation doses (6.04, 3.03, 1.54, 0.77, 0.41 and 0.20 mGy) and reconstructed with combinations of reconstruction kernels (soft and hard kernel) and reconstruction algorithms (ASIR-V and DLIR at low, medium and high strength). Semi-automatic volumetry measurements and subjective image quality scores recorded by five radiologists were analyzed with multiple linear regression and mixed-effect ordinal logistic regression models.ResultsVolumetric errors of nodules imaged with DLIR are up to 50% lower compared to ASIR-V, especially at radiation doses below 1 mGy and when reconstructed with a hard kernel. Also, across all nodule diameters and morphologies, volumetric errors are commonly lower with DLIR. Furthermore, DLIR renders higher subjective IQ, especially at the sub-mGy doses. Radiologists were up to nine times more likely to score the highest IQ-score to these images compared to those reconstructed with ASIR-V. Lung nodules with irregular margins and small diameters also had an increased likelihood (up to five times more likely) to be ascribed the best IQ scores when reconstructed with DLIR.ConclusionWe observed that DLIR performs as good as or even outperforms conventionally used reconstruction algorithms in terms of volumetric accuracy and subjective IQ of nodules in an anthropomorphic chest phantom. As such, DLIR potentially allows to lower the radiation dose to participants of lung cancer screening without compromising accurate measurement and characterization of lung nodules.

Infrared small target detection algorithm based on filter kernel combination optimization learning method

Infrared small target detection in complex backgrounds remains a big challenge due to its small size and weak energy, which makes it easy to be submerged in complex backgrounds. Common filtering algorithms are difficult to apply to various complex scenes and generate many false alarms and poor robustness. Therefore, this paper proposes an infrared small target detection algorithm based on filter kernel combination optimization learning method. For the sample image block use typical filter kernels and weight coefficients to calculate the combination of filtering results, and construct the loss function of the results and the true value. The optimal weight coefficients are learned using an optimization method, which effectively achieves the fusion of multiple features, then we build a sample library containing comprehensive priori information. In the implementation, an online inference method based on similarity measure is proposed to match test images with sample library image blocks to obtain optimal combination weights. By utilizing the comprehensive priori information to enhance the adaptive ability of the algorithm for various complex backgrounds. Finally, get the position of the infrared small target. The experimental results show that our algorithm has excellent detection performance for infrared small targets with complex background and low signal to clutter ratio, and the AUC value is 0.9980, which is more robust than other comparative algorithms.

A novel graph-based multiple kernel learning framework for hyperspectral image classification

ABSTRACT Multiple kernel learning (MKL) is an efficient way to improve hyperspectral image classification with few training samples by integrating spectral and spatial features. Nonetheless, presenting a MKL algorithm to capture significant information and eliminate redundancy is indispensable. In this paper, a novel graph-based MKL method (GMKL) is introduced to enhance the performance of the MKL algorithm and achieve high discriminative features, resulting in maximum separability. To do so, an informative low-rank graph is determined via a new algorithm called block diagonal representation that takes into account both local and global data structures. Then, in lieu of a time-consuming search for finding the optimal combination of the basic kernels, unlike the prior works, an optimal projective direction is acquired using graph theory. Various basic kernels generated from superpixels and attribute profiles are projected to produce a discriminative combination of kernels. Eventually, the optimum kernel is given to the support vector machine classifier. Experiments have been conducted on two popular hyperspectral datasets (Indian Pines and Pavia University). For the datasets, the proposed algorithm gained 90.43% and 99.28% overall accuracy, respectively, using only 1% training samples, which is much better than the state-of-the-art MKL algorithm and deep learning-based approaches with lower computational time.

Prediction of LncRNA-Protein Interactions Based on Kernel Combinations and Graph Convolutional Networks.

The complexes of long non-coding RNAs bound to proteins can be involved in regulating life activities at various stages of organisms. However, in the face of the growing number of lncRNAs and proteins, verifying LncRNA-Protein Interactions (LPI) based on traditional biological experiments is time-consuming and laborious. Therefore, with the improvement of computing power, predicting LPI has met new development opportunity. In virtue of the state-of-the-art works, a framework called LncRNA-Protein Interactions based on Kernel Combinations and Graph Convolutional Networks (LPI-KCGCN) has been proposed in this article. We first construct kernel matrices by taking advantage of extracting both the lncRNAs and protein concerning the sequence features, sequence similarity features, expression features, and gene ontology. Then reconstruct the existent kernel matrices as the input of the next step. Combined with known LPI interactions, the reconstructed similarity matrices, which can be used as features of the topology map of the LPI network, are exploited in extracting potential representations in the lncRNA and protein space using a two-layer Graph Convolutional Network. The predicted matrix can be finally obtained by training the network to produce scoring matrices w.r.t. lncRNAs and proteins. Different LPI-KCGCN variants are ensemble to derive the final prediction results and testify on balanced and unbalanced datasets. The 5-fold cross-validation shows that the optimal feature information combination on a dataset with 15.5% positive samples has an AUC value of 0.9714 and an AUPR value of 0.9216. On another highly unbalanced dataset with only 5% positive samples, LPI-KCGCN also has outperformed the state-of-the-art works, which achieved an AUC value of 0.9907 and an AUPR value of 0.9267.

Health prediction of lithium-ion batteries by combining with empirical mode decomposition and PF-GPR algorithm

A new model based on empirical mode decomposition (EMD) and particle filter-gaussian progress regression (PF-GPR) algorithm is developed for estimating state of health (SOH) and remaining useful life (RUL) of lithium-ion batteries (LIBs). The capacity degradation process of LIBs is investigated and reveals that the new model is convenient and accurate for estimating SOH and RUL of LIBs. The relative error of SOH prediction is less than 1.5%, while the maximum absolute error of RUL prediction is one cycle. Compared with other models reported in previous works, the present model shows smaller absolute error and root mean square error. In addition, the EMD-PF-GPR fusion model based on combined kernel function and mahalanobis distance possesses a good generalization ability and ability of learning from local variations. The work provides a new method to accurately predict health of LIBs.