Time Series Processing Methods Research Articles

Retracted: Research on Nonlinear Time Series Processing Method for Automatic Building Construction Management

Retracted: Research on Nonlinear Time Series Processing Method for Automatic Building Construction Management

Hydraulic simulation of an urban river affected by treated effluent based on signal processing theory and physically based models

Study regionThe Tonghui River–a treated effluent-affected urban river located in Beijing, China. Study focusInspired by the signal processing theory, this study presented a simulation scheme for the treated effluent-affected river based on hydrologic monitoring, pattern recognization, pattern extraction, and hydrologic/hydraulic modelling. It aimed to precisely depict the river flow patterns when detailed wastewater treatment plant effluent data was absent and to fill in the gap of the application of signal-based hydrological time series processing methods in physically based hydraulic simulation. New hydrological insights for the regionDiurnal and semidiurnal patterns caused by the wastewater treatment plant (WWTP) effluent were recognized from the water level series using the continuous wavelet transform. Due to their small amplitudes, they were masked during flood events but dominated the flow regime in dry seasons. Based on the discrete wavelet decomposition and Fourier series fitting, these periodical patterns were extracted and fitted. With a preliminarily calibrated hydraulic model and a linear signal amplifier, a simulated WWTP effluent was retrieved. Dry seasons simulation utilizing the simulated effluent obtained significantly better performance than using the average effluent data from the aspects of conventional evaluation metrics, cross-wavelet transform, and wavelet coherence.

Synthesizing magnetotelluric time series based on forward modeling

The validity of magnetotelluric time-series processing methods has been lacking reasonable testing criteria. Since the time series synthesized by existing techniques are not fully derived from a given model, they are not reliable. In this paper, we present a novel approach to synthesize magnetotelluric time series based on forward modeling and the correspondence between frequency and time domain electromagnetic fields. In this approach, we obtain the electromagnetic response of two orthogonal polarization sources for a given model by magnetotelluric forward modeling, and simulate the randomness of the polarization of the natural field source by a linear combination of the two polarization sources. Based on the correspondence between the frequency and time domain electromagnetic fields, the electromagnetic fields obtained by forward modeling in the frequency domain are transformed into the time domain, and finally the time series are synthesized. The test results on 1D and 3D models validate the effectiveness of the proposed method and the correctness of the procedure. After adding noise to the synthesized time series, we can test the performance of each method by comparing the results of the time series processing methods with the response of the given model. Therefore, the method presented in this paper can be used to construct standard magnetotelluric time series, which can be used as a carrier to construct synthetic data satisfying various noise distributions, and for the study of related methods. This method can also be used to synthesize time series of other frequency-domain electromagnetic methods.

Identification of Potential Landslide Hazards Using Time-Series InSAR in Xiji County, Ningxia

Potential landslide identification and monitoring are essential to prevent geological disasters. However, in mountainous areas where the surface gradient changes significantly, the leveling effect is not completely removed, affecting the deformation results. In this paper, the SBAS-InSAR and PS-InSAR time-series processing methods were combined to interfere with the SAR image data of the ascending orbit in the southern mountainous area of Ningxia and its surrounding regions. Based on the obtained surface deformation monitoring results and optical images, landslide hazard identification was successfully carried out within the coverage area of 3130 km2 in Xiji County. The results show that the whole study area presented a relatively stable state, most of the deformation rates were concentrated in the range of 0 mm/a to −10 mm/a, and the deformation in the southwest area was larger. A total of 11 large potential landslides (which were already registered potential danger points of geological disasters) were identified in the study area, including three historical collapses. The landslide identification results were highly consistent with the field survey results after verification. The timing analysis of the typical landslide point of the Jiaowan landslide was further carried out, which showed that the Jiaowan landslide produced new deformation during the monitoring time, but it was still in a basically stable state. It can do a good job in disaster prevention and reduction while strengthening monitoring. The results of this study have a guiding effect on landslide prevention and mitigation in the mountainous areas of southern Ningxia.

A financial time series data mining method with different time granularity based on trend Division

Stock research is an important field of Finance and time series research. Stock data research is also a typical financial time series problem. In the research of financial time series, there are many methods, such as model building, data mining, heuristic algorithm, machine learning, deep learning, and so on. VAR, ARIMA and other methods are widely used in practice. ARIMA and its combination methods have good processing effect on small data sets, but there are over fitting problems, which are difficult to process large data sets and data with different time granularity. At present, this paper takes the decision table transformation method of financial time series data as the research object, and puts forward the trend division method of financial time series based on different time granularity through the trend division of financial time series. On this basis, it puts forward the trend extreme point extraction method, and constructs the stock time series decision table according to the extreme point information and combined with the stock technical indicators, The decision table is verified by support vector machine based on the decision table. The research shows that the trend division method under different time granularity can transform the extreme point information into a decision table, which will not produce over fitting problem in practical application. It is an effective time series processing method, and provides a new research method for the future time series research with different granularity.

Research on PM2.5 Pollution Prediction Method in Hefei City Based on CNN-LSTM Hybrid Model

The air quality data has the characteristics of large scale and high time sequence. In the deep learning model, CNN has good feature extraction and expression ability through convolution operation. LSTM has strong time series data processing ability, which effectively solves the long-term dependence problem in the time series data that CNN cannot process. However, a single feature extraction or time series processing method will affect the accuracy of the model. This paper proposes a PM2.5 pollution prediction method based on the CNN-LSTM hybrid model, which can fuse the time series and nonlinear features of the data. By selecting the air quality and meteorological data of Hefei City in Anhui Province from 2018 to 2021 for prediction research, the experimental results show that the CNN-LSTM hybrid model is better than the LSTM model in terms of RMSE, MAE, and R2 evaluation indexes, which reflects higher prediction accuracy. It can not only be used for real-time prediction of PM2.5 pollution, but also for the prediction of other pollutants in the atmosphere. It also provides a reference for the application of CNN-LSTM model in solving other time series big data.

A Deep Learning Application for Deformation Prediction from Ground-Based InSAR

Ground-based synthetic aperture radar interferometry (GB-InSAR) has the characteristics of high precision, high temporal resolution, and high spatial resolution, and is widely used in highwall deformation monitoring. The traditional GB-InSAR real-time processing method is to process the whole data set or group in time sequence. This type of method takes up a lot of computer memory, has low efficiency, cannot meet the timeliness of slope monitoring, and cannot perform deformation prediction and disaster warning forecasting. In response to this problem, this paper proposes a GB-InSAR time series processing method based on the LSTM (long short-term memory) model. First, according to the early monitoring data of GBSAR equipment, the time series InSAR method (PS-InSAR, SBAS, etc.) is used to obtain the initial deformation information. According to the deformation calculated in the previous stage and the atmospheric environmental parameters monitored, the LSTM model is used to predict the deformation and atmospheric delay at the next time. The phase is removed from the interference phase, and finally the residual phase is unwrapped using the spatial domain unwrapping algorithm to solve the residual deformation. The predicted deformation and the residual deformation are added to obtain the deformation amount at the current moment. This method only needs to process the difference map at the current moment, which greatly saves time series processing time and can realize the prediction of deformation variables. The reliability of the proposed method is verified by ground-based SAR monitoring data of the Guangyuan landslide in Sichuan Province.

Investigating causal relationships between grassland deterioration and climate and socioeconomic changes through time-series computational learning

The paper investigates how climate changes and socioeconomic transformations affected grassland productivity from 2000 to 2017 in counties in Inner Mongolia of China. The grassland productivity and climatic change variables included 162 readings (9 periods in the growing season × 18 years), while ten socioeconomic variables contained 18 yearly readings. The mismatch between the environmental observations and socioeconomic data compounds quantitative analysis of causal relations between them. We applied several time-series processing methods to generate five datasets. We fit them with conventional, dependent-lagged, and dynamic-lagged panel regression models to investigate which combinations augment causal relationships between grassland productivity, climate, and socioeconomic changes.The results confirmed that the conventional model with the original data failed to reveal causal relationships between these factors. The panel regression models with the original data tended to intensify the causal effects of climate factors on grassland productivity. The models with the transformed datasets disclosed more socioeconomic variables showing causal relationships with grassland productivity. The dependent-lagged model with the empirical mode decomposition transformed data produced the highest R-squared value and lowest prediction error. GDP, state fixed asset investment, highway construction, grain plantation, and livestock density were primary factors affecting grassland productivity. In brief, the integration of time-series data mining and time-lagged panel analysis effectively unveiled the causes of grassland deterioration under climate and socioeconomic changes.

Research on Nonlinear Time Series Processing Method for Automatic Building Construction Management

Aiming at the nonlinear time series of automatic building construction management, a neural network prediction model is proposed to analyze and process the nonlinear sequence of deformation monitoring number cutter. The specific content of this method is as follows: for the noise problems existing in deformation monitoring data, a wavelet is used to denoise the preprocessing; for the BP network and RBF network commonly used in neural networks, the performance of the two networks is compared and demonstrated by MATLAB program, which proves that RBF neural network can significantly improve the accuracy of deformation prediction. By comparing the results, the maximum relative error of BP network prediction is 18.59%, while the maximum relative error of RBF network prediction is 29.16%, and the average relative error of 13P network prediction is 7.02%, while the average relative error of RBF network prediction value is 10.5%. The comprehensive error of network prediction is 6.1%, RBF network prediction is 8.52%, the standard deviation RMSE of BP network prediction error is 15.347, and that of RBF network prediction error is 21.401, and it shows that the prediction accuracy of BP network is higher than that of RBF network.

GNSS-corrected InSAR displacement time-series spanning the 2019 Ridgecrest, CA earthquakes

SUMMARYInSAR displacement time-series are emerging as a valuable product to study a number of Earth processes. One challenge to current time-series processing methods, however, is that when large earthquakes occur, they can leave sharp coseismic steps in the time-series. These discontinuities can cause current atmospheric correction and noise smoothing algorithms to break down, as these algorithms commonly assume that deformation is steady through time. Here, we aim to remedy this by exploring two methods for correcting earthquake offsets in InSAR time-series: a simple difference offset estimate (SDOE) process and a multiparameter offset estimate (MPOE) parametric time-series inversion technique. We apply these methods to a 2-yr time-series of Sentinel-1 interferograms spanning the 2019 Ridgecrest, CA earthquake sequence. Descending track results indicate that the SDOE method precisely corrects for only 20 per cent of the coseismic offsets at 62 study locations included in our scene and only partially corrects or sometimes overcorrects for the rest of our study sites. On the other hand, the MPOE estimate method successfully corrects the coseismic offset for the majority of sites in our analysis. This MPOE method allows us to produce InSAR time-series and data-derived estimates of deformation during each phase of the earthquake cycle. In order to better isolate and estimate the signal of post-seismic lithospheric deformation in the InSAR time-series, we apply a GNSS-based correction to our interferograms. This correction ties the interferograms to median-filtered weekly GNSS displacements and removes additional atmospheric artefacts. We present InSAR-based estimates of post-seismic deformation for the area around the Ridgecrest rupture, as well as a 2-yr coseismic-corrected, GNSS-corrected InSAR time-series data set. This GNSS-corrected InSAR time-series will enable future modelling of post-seismic processes such as afterslip in the near field of the rupture, poroelastic deformation at intermediate distances and viscoelastic deformation at longer timescales in the far field.

Temporal Registration of Cardiac Multimodal Images Using Locally Linear Embedding Algorithm

Purpose: Multimodal Cardiac Image (MCI) registration is one of the evolving fields in the diagnostic methods of Cardiovascular Diseases (CVDs). Since the heart has nonlinear and dynamic behavior, Temporal Registration (TR) is the fundamental step for the spatial registration and fusion of MCIs to integrate the heart's anatomical and functional information into a single and more informative display. Therefore, in this study, a TR framework is proposed to align MCIs in the same cardiac phase. Materials and Methods: A manifold learning-based method is proposed for the TR of MCIs. The Euclidean distance among consecutive samples lying on the Locally Linear Embedding (LLE) of MCIs is computed. By considering cardiac volume pattern concepts from distance plots of LLEs, six cardiac phases (end-diastole, rapid-ejection, end-systole, rapid-filling, reduced-filling, and atrial-contraction) are temporally registered. Results: The validation of the proposed method proceeds by collecting the data of Computed Tomography Coronary Angiography (CTCA) and Transthoracic Echocardiography (TTE) from ten patients in four acquisition views. The Correlation Coefficient (CC) between the frame number resulted from the proposed method and manually selected by an expert is analyzed. Results show that the average CC between two resulted frame numbers is about 0.82±0.08 for six cardiac phases. Moreover, the maximum Mean Absolute Error (MAE) value of two slice extraction methods is about 0.17 for four acquisition views. Conclusion: By extracting the intrinsic parameters of MCIs, and finding the relationship among them in a lower-dimensional space, a fast, fully automatic, and user-independent framework for TR of MCIs is presented. The proposed method is more accurate compared to Electrocardiogram (ECG) signal labeling or time-series processing methods which can be helpful in different MCI fusion methods.

Multi-criteria comprehensive study on predictive algorithm of heating energy consumption of district heating station based on timeseries processing

Refined control of district heating station relies on reasonable and accurate prediction of heating energy consumption. Due to the influence of building thermal inertia and time-delay of the district heating system, certain research work is necessary to thoroughly illustrate and analyze the impact of data timeseries processing on various prediction models. Four kinds of prediction algorithms were investigated and compared in this paper. Results showed that all of three timeseries processing methods, namely time feature construction, sliding window and building thermal inertia coefficient (CBTI), can improve the prediction accuracy of all four models and CBTI had the greatest impact on model accuracy improvement. Moreover, timeseries processing method has no limitation on the types of prediction model and it is a general method to improve the model accuracy. Time feature construction and sliding window had greater influence on the non-neural network models while CBTI was the opposite. In terms of model robustness, the robustness had been significantly improved after introducing timeseries processing except random forest, and the comprehensive robustness coefficient for the other three models had been reduced by about 95%. Recurrent neural network had extremely excellent robustness under different temporal granularity.

Land subsidence modelling using a long short-term memory algorithm based on time-series datasets

Abstract. With the rapid growth of data volume and the development of artificial intelligence technology, deep-learning methods are a new way to model land subsidence. We utilized a long short-term memory (LSTM) model, a deep-learning-based time-series processing method to model the land subsidence under multiple influencing factors. Land subsidence has non-linear and time dependency characteristics, which the LSTM model takes into account. This paper modelled the time variation in land subsidence for 38 months from 2011 to 2015. The input variables included the change in land subsidence detected by InSAR technology, the change in confined groundwater level, the thickness of the compressible layer and the permeability coefficient. The results show that the LSTM model performed well in areas where the subsidence is slight but poorly in places with severe subsidence.

An end-to-end functional spiking model for sequential feature learning

Spiking Neural Network (SNN) has recently gained significant momentum in the neuromorphic low-power systems. However, the existing SNN models have limited use in time-sequential feature learning, and the exhausting spike encoding and decoding make the SNNs not straightforward to use. Inspired by the functional organization in the primate visual system, we propose an end-to-end functional spiking model in this paper to address these issues. Specifically, we propose the functional spike response to make each neuron special, and the dynamic synaptic efficiency to make the transmission of each input signal controllable. We represent inputs by a simple two-tuple set instead of conventional complex encoding, which achieves end-to-end learning. Experiments on synthetic datasets demonstrate that employing the two-tuple encoding strategy, our method improves the accuracy of the traditional SNN model significantly. In addition, we apply our method to seven real-world datasets and one human motion prediction dataset to investigate its performance. Experimental results show that the proposed functional spike response organization saves the running time of our model compared with the LSTM, GRU and one of the state-of-the-art time series processing methods.

Advanced method for short‐term wind power prediction with multiple observation points using extreme learning machines

This research paper presents an advanced approach to enhance the short-term wind power prediction based on artificial intelligence techniques. A high-quality wind power prediction is essential for power system planning, operation, and control. Thus, a new novel approach has been developed to improve the quality and reliability of the calculated results by integrating advanced time series processing method and the extreme learning machine technique. Moreover, historical records are utilised from numerical weather information and multiple observations points close to real wind farm sites within Australia regions. The wind speed is assessed by using the developed model in the first stage, and then the wind power and capacity factor is calculated using wind power–speed curve for each observation site. Artificial neural network, fuzzy logic (adaptive neuro-fuzzy inference system), and support vector machine models are used for model verifications, validations, and practical applications. The developed model is tested using real wind measurements by Bureau of Meteorology, 15 selected weather stations corresponded to the locations of nearby real wind farm sites in Australia. The demonstrated results and performance indicators, e.g. root mean square error and mean absolute error are compared with Khalid, persistence, and Grey predictor models for validations and verifications reasons. As the potential gains over other techniques, the proposed model has found more efficient and superior for wind power estimation and prediction than other developed conventional methods and models, which in turn improves the power system performance, and reduces the economic impacts.

Filtering and windowing mobile traffic time series for territorial land use classification

Analytics of mobile traffic information may take into account the time-series nature of the data itself. When employing mobile traffic data in a predictive setting to derive useful knowledge to characterize the city environment, the most suitable time series processing methods must be identified. In this paper, we propose an approach to process mobile traffic data using specific time series techniques – smoothing, decomposition, filtering, time-windowing – and to establish the best approach to exploit information extracted from those time series to classify land use, according to sensitivity/specificity metrics. We apply our methodology to a large-scale mobile traffic dataset, we assess its feasibility and we discuss the suitability of different methods for land use classification.

Assessing the Feasibility of Optical Probe in Phase Holdup Measurements and Flow Regime Identification

Abstract Despite the hydrodynamics of trickle beds experiencing pilot size, on the contrary, the possibility of measuring hydrodynamic parameters locally and for large scale and finding an indicator to pinpoint the flow regime from trickling to pulsing remains obscure, to assess the feasibility of getting such information the reactor bed was randomly packed with equal-sized spherical beads of 3 mm diameter. Gas and liquid holdup measurements and flow regime identification were achieved at various flow conditions from trickling to the pulsing regime by an optical probe method using time series processing method. This method is shown to be simple and efficient provides quantitative information about the gas and liquid holdup variation in different flow regime. The various experimental results were compared to available literature models and correlations for confrontation and recommendations. The trickle-to-pulse flow transition boundary shifted towards higher gas and liquid superficial velocities, aligning with the findings on a variation of holdup along the axial direction confirmed to broaden the trickle flow domain. [Correction added after online publication June 26, 2015: To unify the adjective everywhere in this manuscript, optic fiber probe was changed to optical probe.]

Wind Turbine Gearbox Fault Diagnosis Method Based on Riemannian Manifold

As multivariate time series problems widely exist in social production and life, fault diagnosis method has provided people with a lot of valuable information in the finance, hydrology, meteorology, earthquake, video surveillance, medical science, and other fields. In order to find faults in time sequence quickly and efficiently, this paper presents a multivariate time series processing method based on Riemannian manifold. This method is based on the sliding window and uses the covariance matrix as a descriptor of the time sequence. Riemannian distance is used as the similarity measure and the statistical process control diagram is applied to detect the abnormity of multivariate time series. And the visualization of the covariance matrix distribution is used to detect the abnormity of mechanical equipment, leading to realize the fault diagnosis. With wind turbine gearbox faults as the experiment object, the fault diagnosis method is verified and the results show that the method is reasonable and effective.

A Comparative Analysis of Short Time Series Processing Methods

This article analyzes the traditional time series processing methods that are used to perform the task of short time series analysis in demand forecasting. The main aim of this paper is to scrutinize the ability of these methods to be used when analyzing short time series. The analyzed methods include exponential smoothing, exponential smoothing with the development trend and moving average method. The paper gives the description of the structure and main operating principles. The experimental studies are conducted using real demand data. The obtained results are analyzed; and the recommendations are given about the use of these methods for short time series analysis.

Statistical analysis and mathematical models of the induced seismicity in the region of the large Charvak reservoir

The parameters system, which describes the time change of seismicity and characterizes the hydrodynamic and isostatic Earth crust state of the region (a possible genesis of the induced earthquakes), as well as the parameters of the reservoir operating conditions were selected. This paper is devoted to interpretation of some induced seismicity problems by means of statistical analysis and time series processing methods adapted to the study. The threshold values of the reservoir operating conditions were received.