Autoregressive Prediction Research Articles

Automated measurement of teleseismic P-, SH-, and SV-wave arrival times using autoregressive prediction and the instantaneous phase of multicomponent waveforms

Automated measurement of teleseismic P-, SH-, and SV-wave arrival times using autoregressive prediction and the instantaneous phase of multicomponent waveforms

Energy-efficient neural network training through runtime layer freezing, model quantization, and early stopping

Background:In the last years, neural networks have been massively adopted by industry and research in a wide variety of contexts. Neural network milestones are generally reached by scaling up computation, completely disregarding the carbon footprint required for the associated computations. This trend has become unsustainable given the ever-growing use of deep learning, and could cause irreversible damage to the environment of our planet if it is not addressed soon. Objective:In this study, we aim to analyze not only the effects of different energy saving methods for neural networks but also the effects of the moment of intervention, and what makes certain moments optimal. Method:We developed a novel dataset by training convolutional neural networks in 12 different computer vision datasets and applying runtime decisions regarding layer freezing, model quantization and early stopping at different epochs in each run. We then fit an auto-regressive prediction model on the data collected capable to predict the accuracy and energy consumption achieved on future epochs for different methods. The predictions on accuracy and energy are used to estimate the optimal training path. Results:Following the predictions of the model can save 56.5% of energy consumed while also increasing validation accuracy by 2.38% by avoiding overfitting.The prediction model developed can predict the validation accuracy with a 8.4% of error, the energy consumed with a 14.3% of error and the trade-off between both with a 8.9% of error. Conclusions:This prediction model could potentially be used by the training algorithm to decide which methods apply to the model and at what moment in order to maximize the accuracy-energy trade-off.

1D -FNO - Residual convolutional neural network autoregressive prediction model for deep water wave train evolution based on high-order spectral (HOS) data

Accurate prediction of deep-water wave dynamics is essential for ocean engineering, meteorology, and maritime safety. Traditional physical models, though effective, face significant computational and time challenges with complex nonlinear dynamics. This study introduces an autoregressive prediction model using a one-dimensional adaptive Fourier Neural Operator-Residual Convolutional Neural Network (1D-FNO-ResNet) to enhance prediction accuracy. We developed a high-precision single-step prediction model capable of capturing wave characteristics such as height and fluid particle velocity. A fine-tuning training strategy based on multi-step prediction errors was proposed for autoregressive evolution. Performance comparisons between the ResNet and FNO-ResNet models were made under various fine-tuning steps. A correction model was also introduced to control error accumulation, improving autoregressive prediction steps. The model's generalization performance was validated with modulated and random wave trains under different conditions, optimizing predictive stability and accuracy. This approach demonstrates efficient 1D deep-water wave evolution prediction, offering a novel deep learning solution for wave dynamics prediction in ocean engineering, supporting wave energy conversion device design and optimization.

Interpretable and explainable hybrid model for daily streamflow prediction based on multi-factor drivers.

Streamflow time series data typically exhibit nonlinear and nonstationary characteristics that complicate precise estimation. Recently, multifactorial machine learning (ML) models have been developed to enhance the performance of streamflow predictions. However, the lack of interpretability within these ML models raises concerns about their inner workings and reliability. This paper introduces an innovative hybrid architecture, the TCN-LSTM-Multihead-Attention model, which combines two layers of temporal convolutional networks (TCN) followed by one layer of long short-term memory (LSTM) units, integrated with a Multihead-Attention mechanism for predicting streamflow with streamflow causation-driven prediction samples (RCDP), employing local and global interpretability studies through Shapley values and partial dependency analysis. The find_peaks method was used to identify peak flow events in the test dataset, validating the model's generality and uncovering the physical causative patterns of streamflow. The results show that (1) compared to the LSTM model with the same hyperparameter settings, the proposed TCN-LSTM-Multihead-Attention hybrid model increased the R2 by 52.9%, 2.5%, 43.1%, and 10.7% respectively at four stations in the test set predictions using RCDP samples. Moreover, comparing the prediction results of the hybrid model under different samples in Hengshan station, the R2 for RCDP increased by 5.06% and 1.22% compared to streamflow autoregressive prediction samples (RAP) and meteorological-soil volumetric water content coupled autoregressive prediction samples (MCSAP) respectively. (2) Historical streamflow data from the preceding 3days predominantly influences predictions due to strong autocorrelation, with flow quantity (Q) typically emerging as the most significant feature alongside precipitation (P), surface soil moisture (SSM), and adjacent station flow data. (3) During periods of low and normal flow, historical data remains the most crucial factor; however, during flood periods, the roles of upstream inflow and precipitation become significantly more pronounced. This model facilitates the identification and quantification of various hydrodynamic impacts on flow predictions, including upstream flood propagation, precipitation, and soil moisture conditions. It also elucidates the model's nonlinear relationships and threshold responses, thereby enhancing the interpretability and reliability of streamflow predictions.

Raster‐to‐Graph: Floorplan Recognition via Autoregressive Graph Prediction with an Attention Transformer

AbstractRecognizing the detailed information embedded in rasterized floorplans is at the research forefront in the community of computer graphics and vision. With the advent of deep neural networks, automatic floorplan recognition has made tremendous breakthroughs. However, co‐recognizing both the structures and semantics of floorplans through one neural network remains a significant challenge. In this paper, we introduce a novel framework Raster‐to‐Graph, which automatically achieves structural and semantic recognition of floorplans. We represent vectorized floorplans as structural graphs embedded with floorplan semantics, thus transforming the floorplan recognition task into a structural graph prediction problem. We design an autoregressive prediction framework using the neural network architecture of the visual attention Transformer, iteratively predicting the wall junctions and wall segments of floorplans in the order of graph traversal. Additionally, we propose a large‐scale floorplan dataset containing over 10,000 real‐world residential floorplans. Our autoregressive framework can automatically recognize the structures and semantics of floorplans. Extensive experiments demonstrate the effectiveness of our framework, showing significant improvements on all metrics. Qualitative and quantitative evaluations indicate that our framework outperforms existing state‐of‐the‐art methods. Code and dataset for this paper are available at: https://github.com/HSZVIS/Raster-to-Graph.

Advancing blast fragmentation simulation of RC slabs: A graph neural network approach

Accurate prediction of blast-induced fragmentation in reinforced concrete (RC) structures is pivotal for structural debris hazard assessment in an explosion event. This assessment is essential for designing effective measures for protection of people and structure in the vicinity. While conventional computational techniques are proficient, they are computationally very demanding and may not be readily adaptable in practical applications. This study proposes a novel approach, the Fragment Graph Network (FGN), a specialized variant of graph neural networks (GNNs), to simulate complex interactions between macro-level particles of RC structures subjected to close-in blast loads. The RC structure is discretised into particles, with the model predicting structural responses and fragmentation based on states of these particles. Utilizing an autoregressive prediction mechanism, our model can accurately simulate spatiotemporal responses of RC slabs against blast loads. The efficacy of the model was tested on a dataset consisting of 149 simulated cases, encompassing around 180,000 states each, covering a wide range of blasting scenarios and structural design parameters including TNT charge weight, standoff distance, slab dimension, concrete strength, and reinforcement ratio and layout. Notably, the proposed model delivered accurate predictions, achieving relative errors under 10% and R2 values exceeding 0.93 for both standard and extrapolated test scenarios as compared to the SPH simulations. Remarkably, our model dramatically outpaced traditional numerical approaches, reducing simulation times from hours to minutes on CPUs and seconds on GPUs. This pioneering effort paves the way for efficient and accurate simulations of RC blast fragmentations, offering a rapid alternative to standard numerical approaches.

Multi-layer CNN-LSTM network with self-attention mechanism for robust estimation of nonlinear uncertain systems.

With the help of robot technology, intelligent rehabilitation of patients with lower limb motor dysfunction caused by stroke can be realized. A key factor constraining the clinical application of rehabilitation robots is how to realize pattern recognition of human movement intentions by using the surface electromyography (sEMG) sensors to ensure unhindered human-robot interaction. A multilayer CNN-LSTM prediction network incorporating the self-attention mechanism (SAM) is proposed, in this paper, which can extract and learn the periodic and trend characteristics of the sEMG signals, and realize the accurate autoregressive prediction of the human motion information. Firstly, the multilayer CNN-LSTM network utilizes the CNN layer for initial feature extraction of data, and the LSTM network is used to improve the enhancement of the historical time-series features. Then, the SAM is used to improve the global feature extraction performance and parallel computation speed of the network. In comparison with existing test is carried out using actual data from five healthy subjects as well as a clinical hemiplegic patient to verify the superiority and practicality of the proposed algorithm. The results show that most of the model's prediction R > 0.9 for different motion states of healthy subjects; in the experiments oriented to the motion characteristics of patient subjects, the angle prediction results of R > 0.99 for the untrained data on the affected side, which proves that our proposed model also has a better effect on the angle prediction of the affected side. The main contribution of this paper is to realize continuous motion estimation of ankle joint for healthy and hemiplegic individuals under non-ideal conditions (weak sEMG signals, muscle fatigue, high muscle tension, etc.), which improves the pattern recognition accuracy and robustness of the sEMG sensor-based system.

Direct prediction for oceanic mesoscale eddy geospatial distribution through prior statistical deep learning

Mesoscale Eddy (ME) is a widely recognized and significant oceanic phenomenon characterized by extensive energy exchange. Accurate predictions of the future geospatial distribution of ME are crucial for maritime activities. Deep learning (DL) methods for ME prediction have consistently outperformed classical mathematical models and numerical modeling approaches. However, current DL methods based on two-dimensional gridded data suffer from error accumulation issues due to their indirect prediction approach, which involves first predicting the future environmental field and then identifying the ME patterns within it. Additionally, these models ignore the potential influence of prior knowledge related to ME on prediction outcomes. To address these issues, this paper proposes a direct prediction DL network called ES-ConvGRU, which incorporates historical prior statistics. First, we conduct an analysis of ME data from the Northwest Pacific region, extracting prior statistical knowledge such as interannual variations and seasonal characteristics. Second, mining patterns for the spatiotemporal features of both ME sequence and sea surface environmental field sequence are established. Furthermore, a nonlinear approach for mapping prior statistical knowledge and a multi-step autoregressive prediction model are designed, facilitating the integration of prior knowledge with multidimensional spatiotemporal features for ME prediction. Finally, the performance and effectiveness of ES-ConvGRU are evaluated. It achieves an average pixel accuracy of 93.21%, a mean intersection over union of 81.48%, and a frequency-weighted intersection over union of 87.55% for the 7-day distribution prediction. The results show that ES-ConvGRU exhibits notable advantages compared to the existing indirect and direct prediction methods.

Analysis and Modeling of Geodetic Data Based on Machine Learning

Abstract This paper underscores the significance of earth deformation observation in analyzing earth tide curves and predicting earthquakes, positioning it as a cornerstone of Earth observation technology. We delve into the critical task of detecting and diagnosing anomalies in geodetic data. Utilizing Python for data preprocessing, our approach identifies missing values, categorizes them by their spatial occurrence, and employs spline interpolation and autoregressive prediction methods for data imputation. This process ensures the integrity of the dataset for subsequent analysis and modeling, reinforcing the precision and reliability of geodetic data analysis in Earth science research. For problem I To expand the data set, we propose three models. Model I: Adding gaussian noise to the data. Model II: Resample the data. Model III: Using machine learning methods to learn the internal laws of the data and predict itself to generate new data. For each model, we discuss its advantages and disadvantages. Finally, we structurally fuse the three models to complete data enhancement. For problem II To extract the noise, we use DB4 wavelet transform to denoise the data set and extract the noise. Then we make descriptive statistics on the noise distribution, and use Laplace distribution to fit the probability distribution of noise, and finally get the accurate noise distribution. For problem III We start from the time domain and frequency domain to extract the features of the data. First, 17 features are extracted in the time domain, then the discrete fourier transform algorithm is used to transform the data into frequency domain data, and 13 are extracted. Therefore, we encode each data as a feature vector with a length of 30. We first use the decision tree as the baseline model to establish the recognition model to select the features. Logistic Regression, KNN, Naive Bayes and SVM are used to establish the recognition model. Finally, we use the Voting ensemble learning method to fuse the model, achieving an accuracy of 86% on the test set.

Purpose and goal pursuit as a self‐sustaining system: Evidence of daily within‐person reciprocity among adolescents in self‐driven learning

AbstractObjectiveDespite long‐standing assumptions that a sense of purpose in life and goal pursuit are mutually supportive, empirical evidence of their reciprocity remains deficient. In the context of a unique out‐of‐school time program that empowers youth to pursue passions through self‐driven learning, we examined whether purpose and one aspect of goal pursuit—perceptions of goal progress—work together to sustain themselves and each other over time.MethodAdolescents (N = 321) completed daily surveys throughout program enrollment (Menrollment = 69.09 days). Through dynamic structural equation modeling, we derived within‐person patterns of day‐to‐day prediction as well as individual differences in these patterns.ResultsWe found purpose and perceived goal progress exhibited significant daily inertia (i.e., autoregressive prediction) and reciprocity (i.e., cross‐lagged prediction) at the within‐person level. We also found initial evidence suggesting (a) tighter reciprocity was related to greater perceived goal progress overall and (b) people with greater purpose inertia may rely less on making goal progress to sustain momentum.ConclusionsWith evidence of daily purpose‐progress reciprocity, the field can look forward to replicating this work in other contexts, diving deeper into interesting patterns of within‐person dynamics, and developing interventions to support youth striving.

Refined self-attention mechanism based real-time structural response prediction method under seismic action

Accurate prediction of structural response under earthquake is of great significance for structural damage and performance evaluation. In order to improve the efficiency of structure time history response prediction, this paper proposes a novel SeisFormer model based on the self-attention mechanism and deep learning technology. Through autoregressive prediction, the SeisFormer can achieve real-time prediction of the response time histories of a large number of nodes in the structure under seismic action and can effectively solve the problem of data scarcity. Four case studies are performed to verify the accuracy and efficiency of the proposed methodology, including validation on datasets obtained from elastoplastic seismic analysis of a single-story structure, a three-story structure, and an eleven-story structure, and measured data of a shaking table test model. In addition, this paper further studies the prediction accuracy of the SeisFormer through ablation experiments and comparative experiments. The experimental results show that the SeisFormer can accurately predict the acceleration, velocity, and displacement time histories of numerous nodes in the structure. The prediction accuracy outperforms the LSTM model, and the prediction speed is 193–109,824 times faster than finite element method. Furthermore, with data augmentation through autoregressive prediction, the SeisFormer model can achieve efficient and accurate predictions when training data is exceptionally scarce, enabling engineering applications.

Phase-resolved wave prediction with linear wave theory and physics-informed neural networks

Deterministic wave elevation prediction is crucial for improving the power generation efficiency of offshore energy structures (OESs). Although phase-resolved wave models may predict deterministic wave information, a comprehensive understanding of wave theory and mathematics is necessary to guarantee their accuracy. Inspired by the capability of physics-informed neural networks (PINNs) in solving physical equations, we propose an irregular long-crested wave prediction model named LWT-PINN that combines the linear wave theory (LWT) with PINNs. To the best of our knowledge, this is the first time that PINNs are used to predict waves. Five sets of wave elevation time series with steepness ranging from 0.0174 to 0.0349 are generated in a wave basin to optimize and evaluate the LWT-PINN. The computing time for LWT-PINN is 0.13 s, close to real-time. When predicting downstream wave elevation, the LWT-PINN significantly outperforms the linear wave prediction (LWP) model in terms of accuracy and prediction length. Specifically, the LWT-PINN achieves satisfactory accuracy with only 100 s upstream wave elevation, whereas the LWP requires 175 s; LWT-PINN’s high-precision prediction duration is 13.7 s, which is 2.5 times longer than that of LWP (5.5 s). Moreover, LWT-PINN can provide wave autoregressive predictions of around 5 s without the aid of statistical methods, which offers a new direction for developing wave autoregressive prediction methods. The excellent performance of the proposed model can substantially assist the stable operation of OESs.

EarlGAN: An enhanced actor–critic reinforcement learning agent-driven GAN for de novo drug design

Deep generative models, such as Generative Adversarial Networks (GANs), have attracted the attention of researchers in the denovo drug design field. However, traditional GANs are typically used for image processing. Therefore, they are unsuitable for Simplified Molecular-Input Line-Entry System (SMILES) strings due to their discrete nature. Previous studies addressed this problem by combining Reinforcement Learning (RL) approaches with Monte Carlo tree search. However, for large chemical datasets, the molecule generation process is time-consuming due to the lengthy atom-by-atom sampling process with cumulative reward, an essence of the Monte Carlo tree search-based RL approaches. To address this problem, we propose an enhanced actor–critic RL agent-driven GAN, called EarlGAN, for denovo drug design. Specifically, EarlGAN’s generator acts as an actor to generate SMILES strings, and the discriminator acts as a critic to perform discrimination. EarlGAN makes autoregressive predictions at the atomic level. While the generator is based on previously generated atoms, the discriminator discriminates using a bidirectional pass over the atoms, including the current atom that is being predicted. We integrate moment, global-level discrimination rewards, and information entropy maximization. The moment rewards reduce the computation time, and the global-level rewards ensure the consistency of the molecule, whereas the information entropy maximization leads to a more diverse sample generation. Experiments and ablation studies verify the effectiveness of EarlGAN for denovo drug design on the QM9 and ZINC datasets. In addition, the visualization analysis provides insight into EarlGAN and supports our conclusion.

Diformer: A dynamic self-differential transformer for new energy power autoregressive prediction

Power prediction is important as a technical support mechanism in the global carbon neutrality initiative. Existing artificial intelligence methodologies frequently grapple with the challenge of excessive dependence on numerical space mapping. This reliance often results in sacrificing the precision of power prediction trends to achieve smoother prediction outcomes. Therefore, to address this issue, we propose a dynamic self-differential transformer (Diformer) tailored explicitly for univariate power time series forecasting to address this issue. Diformer incorporates two unique constructions: (i) a novel self-differential attention mechanism that enhances the importance of sequence trends through bidirectional difference features, resolving the issue of excessive reliance on token mapping in the numerical space in the transformer-based model during extracting features. (ii) a loss function called trade-loss, intensifying error loss by dynamically adjusting weights when the sequence trend changes. This formula mode significantly improves the model’s ability to discern the direction of the sequence trend. Extensive experiments on six power time series datasets and publicly available power-related datasets demonstrate that Diformer significantly outperforms existing models and is better suited for power time series forecasting.

Real-time forecasting of COVID-19 spread according to protective behavior and vaccination: autoregressive integrated moving average models

BackgroundMathematical and statistical models are used to predict trends in epidemic spread and determine the effectiveness of control measures. Automatic regressive integrated moving average (ARIMA) models are used for time-series forecasting, but only few models of the 2019 coronavirus disease (COVID-19) pandemic have incorporated protective behaviors or vaccination, known to be effective for pandemic control.MethodsTo improve the accuracy of prediction, we applied newly developed ARIMA models with predictors (mask wearing, avoiding going out, and vaccination) to forecast weekly COVID-19 case growth rates in Canada, France, Italy, and Israel between January 2021 and March 2022. The open-source data was sourced from the YouGov survey and Our World in Data. Prediction performance was evaluated using the root mean square error (RMSE) and the corrected Akaike information criterion (AICc).ResultsA model with mask wearing and vaccination variables performed best for the pandemic period in which the Alpha and Delta viral variants were predominant (before November 2021). A model using only past case growth rates as autoregressive predictors performed best for the Omicron period (after December 2021). The models suggested that protective behaviors and vaccination are associated with the reduction of COVID-19 case growth rates, with booster vaccine coverage playing a particularly vital role during the Omicron period. For example, each unit increase in mask wearing and avoiding going out significantly reduced the case growth rate during the Alpha/Delta period in Canada (–0.81 and –0.54, respectively; both p < 0.05). In the Omicron period, each unit increase in the number of booster doses resulted in a significant reduction of the case growth rate in Canada (–0.03), Israel (–0.12), Italy (–0.02), and France (–0.03); all p < 0.05.ConclusionsThe key findings of this study are incorporating behavior and vaccination as predictors led to accurate predictions and highlighted their significant role in controlling the pandemic. These models are easily interpretable and can be embedded in a “real-time” schedule with weekly data updates. They can support timely decision making about policies to control dynamically changing epidemics.

On Training Targets and Activation Functions for Deep Representation Learning in Text-Dependent Speaker Verification

Deep representation learning has gained significant momentum in advancing text-dependent speaker verification (TD-SV) systems. When designing deep neural networks (DNN) for extracting bottleneck (BN) features, the key considerations include training targets, activation functions, and loss functions. In this paper, we systematically study the impact of these choices on the performance of TD-SV. For training targets, we consider speaker identity, time-contrastive learning (TCL), and auto-regressive prediction coding, with the first being supervised and the last two being self-supervised. Furthermore, we study a range of loss functions when speaker identity is used as the training target. With regard to activation functions, we study the widely used sigmoid function, rectified linear unit (ReLU), and Gaussian error linear unit (GELU). We experimentally show that GELU is able to reduce the error rates of TD-SV significantly compared to sigmoid, irrespective of the training target. Among the three training targets, TCL performs the best. Among the various loss functions, cross-entropy, joint-softmax, and focal loss functions outperform the others. Finally, the score-level fusion of different systems is also able to reduce the error rates. To evaluate the representation learning methods, experiments are conducted on the RedDots 2016 challenge database consisting of short utterances for TD-SV systems based on classic Gaussian mixture model-universal background model (GMM-UBM) and i-vector methods.

Automatized localization of induced geothermal seismicity using robust time-domain array processing

The surveillance of geothermal seismicity is typically conducted using seismic networks, deployed around the power plants and subject to noise conditions in often highly urbanized areas. In contrast, seismic arrays can be situated at greater distances and allow monitoring of different power plants from one central location, less affected by noise interference. However, the effectiveness of arrays to monitor geothermal reservoirs is not well investigated and the increased distance to the source coincides with a decreased accuracy of the earthquake localizations. It is therefore essential to establish robust data processing and to obtain precise estimates of the location uncertainties. Here, we use time-domain array data processing and solve for the full 3-D slowness vector using robust linear regression. The approach implements a Biweight M-estimator, which yields stable parameter estimates and is well suited for real-time applications. We compare its performance to conventional least squares regression and frequency wavenumber analysis. Additionally, we implement a statistical approach based on changepoint analysis to automatically identify P- and S-wave arrivals within the recorded waveforms. The method can be seen as a simplification of autoregressive prediction. The estimated onsets facilitate reliable calculations of epicentral distances. We assess the performance of our methodology by comparison to network localizations for 77 induced earthquakes from the Landau and Insheim deep-geothermal reservoirs, situated in Rhineland-Palatinate, Germany. Our results demonstrate that we can differentiate earthquakes originating from both reservoirs and successfully localize the majority of events within the magnitude range of ML -0.2 to ML 1.3. The discrepancy between the two localization methods is mostly less than 1 km, which falls within the statistical errors. However, a few localizations deviate significantly, which can be attributed to poor observations during the winter of 2021/2022.

Adaptive HDR Image Blind Watermarking Approach Based on Redundant Discrete Wavelet Transform

Remarkable success has been recorded in the usage of digital watermarking which is aimed at protecting the intellectual property of multimedia content. In this paper, a new tone mapping attack-resistant high dynamic range (HDR) image zero-watermarking algorithm is proposed. In this algorithm extraction of stable and invariant features are extracted for efficient zero-watermarking through the application of the redundant discrete wavelet transform (RDWT) to the HDR image. The first step involves transforming the HDR image to HVS color space, and RDWT is implemented using the V-channel so that the LL sub-band which contains the strong structure contents of the image is obtained. The second step involves dividing the LL sub-band into non-overlapping blocks, which are afterwards subjected to the process of transformation through the use of the singular value decomposition (SVD) so that the U matrix can be extracted. Third, the use of an Auto-Regressive (AR) prediction technique was employed in generating a local relationship model and comparison is done to facilitate the production of a binary feature mask. In the fourth process, hybrid chaotic mapping (HCM) is used to generate blended watermark so that the security of the watermark can be fortified. Lastly, the computation of an effective zero-watermark is achieved through the implementation of an exclusive-or operation on the blended watermark and the binary feature mask. Based on the results, the approach presented in this study demonstrated superior performance in terms of withstanding TM attacks and other attacks associated with image processing.

Cluster-Based Regression Transfer Learning for Dynamic Multi-Objective Optimization

Many multi-objective optimization problems in the real world have conflicting objectives, and these objectives change over time, known as dynamic multi-objective optimization problems (DMOPs). In recent years, transfer learning has attracted growing attention to solve DMOPs, since it is capable of leveraging historical information to guide the evolutionary search. However, there is still much room for improvement in the transfer effect and the computational efficiency. In this paper, we propose a cluster-based regression transfer learning-based dynamic multi-objective evolutionary algorithm named CRTL-DMOEA. It consists of two components, which are the cluster-based selection and cluster-based regression transfer. In particular, once a change occurs, we employ a cluster-based selection mechanism to partition the previous Pareto optimal solutions and find the clustering centroids, which are then fed into autoregression prediction model. Afterwards, to improve the prediction accuracy, we build a strong regression transfer model based on TrAdaboost.R2 by taking advantage of the clustering centroids. Finally, a high-quality initial population for the new environment is predicted with the regression transfer model. Through a comparison with some chosen state-of-the-art algorithms, the experimental results demonstrate that the proposed CRTL-DMOEA is capable of improving the performance of dynamic optimization on different test problems.

A Novel Cycle Slips Detection and Repair Method with AR Model of BDS-3 Dual-Frequency Signal in Severe Multipath Environments

High-level applications of geo-processing services generally lack accurate temporal and spatial information. BDS-3 provides high precision temporal and spatial reference for geoprocessing services, but their signal is prone to cycle slips in a severe multipath environment. Aiming at the problem of the reliable detection and repair of cycle slips in BDS-3 (B1c + B2a) dual-frequency positioning in a severe multipath environment, an AR (autoregressive) model-assisted MW + GF BDS dual-frequency combined detection method (AMG method) is proposed in this research. A sliding-window autoregressive prediction strategy is introduced to correct the pseudorange observations interfered by a multipath, then an AR + MW + GF cycle slips detection model is constructed, and a cycle slips statistical completeness test index is established to verify the effectiveness of the algorithm. Six groups of cycle slips are artificially added into the different constellations and dual-frequency point phase observations of BDS-3 (B1c and B2a) in a multipath environment to demonstrate the cycle slips’ detection performance. The experimental results show that the traditional MW + GF method fails, but the proposed AMG method still maintains accurate cycle slip detection and repair capabilities. The detection success rate and repair success rate obtained by using the new method are significantly improved by 63.4%, and the cycle slips’ false detection rate and missed detection rate are reduced by 64.5% and 42.0%, respectively, even in harsh environments.