Defect Detection Model Using Time Series Data Augmentation and Transformation

Time-series data provide important information in many fields,and their processing and analysis have been the focus of much research.However,detecting anomalies is very difficult due to data imbalance,temporal dependence,and noise.Therefore,methodologies for data augmentation and conversion of time series data into images for analysis have been studied.This paper proposes a fault detection model that uses time series data augmentation and transformation to address the problems of data imbalance,temporal dependence,and robustness to noise.The method of data augmentation is set as the addition of noise.It involves adding Gaussian noise,with the noise level set to 0.002,to maximize the generalization performance of the model.In addition,we use the Markov Transition Field(MTF)method to effectively visualize the dynamic transitions of the data while converting the time series data into images.It enables the identification of patterns in time series data and assists in capturing the sequential dependencies of the data.For anomaly detection,the PatchCore model is applied to show excellent performance,and the detected anomaly areas are represented as heat maps.It allows for the detection of anomalies,and by applying an anomaly map to the original image,it is possible to capture the areas where anomalies occur.The performance evaluation shows that both F1-score and Accuracy are high when time series data is converted to images.Additionally,when processed as images rather than as time series data,there was a significant reduction in both the size of the data and the training time.The proposed method can provide an important springboard for research in the field of anomaly detection using time series data.Besides,it helps solve problems such as analyzing complex patterns in data lightweight.

An Innovative Deep Architecture for Flight Safety Risk Assessment Based on Time Series Data

With the development of the integration of aviation safety and artificial intelligence,research on the combination of risk assessment and artificial intelligence is particularly important in the field of risk management,but searching for an efficient and accurate risk assessment algorithm has become a challenge for the civil aviation industry.Therefore,an improved risk assessment algorithm(PS-AE-LSTM)based on long short-term memory network(LSTM)with autoencoder(AE)is proposed for the various supervised deep learning algorithms in flight safety that cannot adequately address the problem of the quality on risk level labels.Firstly,based on the normal distribution characteristics of flight data,a probability severity(PS)model is established to enhance the quality of risk assessment labels.Secondly,autoencoder is introduced to reconstruct the flight parameter data to improve the data quality.Finally,utilizing the time-series nature of flight data,a long and short-termmemory network is used to classify the risk level and improve the accuracy of risk assessment.Thus,a risk assessment experimentwas conducted to analyze a fleet landing phase dataset using the PS-AE-LSTMalgorithm to assess the risk level associated with aircraft hard landing events.The results show that the proposed algorithm achieves an accuracy of 86.45%compared with seven baseline models and has excellent risk assessment capability.

Prediction of three-dimensional ocean temperature in the South China Sea based on time series gridded data and a dynamic spatiotemporal graph neural network

Ocean temperature is an important physical variable in marine ecosystems,and ocean temperature prediction is an important research objective in ocean-related fields.Currently,one of the commonly used methods for ocean temperature prediction is based on data-driven,but research on this method is mostly limited to the sea surface,with few studies on the prediction of internal ocean temperature.Existing graph neural network-based methods usually use predefined graphs or learned static graphs,which cannot capture the dynamic associations among data.In this study,we propose a novel dynamic spatiotemporal graph neural network(DSTGN)to predict threedimensional ocean temperature(3D-OT),which combines static graph learning and dynamic graph learning to automatically mine two unknown dependencies between sequences based on the original 3D-OT data without prior knowledge.Temporal and spatial dependencies in the time series were then captured using temporal and graph convolutions.We also integrated dynamic graph learning,static graph learning,graph convolution,and temporal convolution into an end-to-end framework for 3D-OT prediction using time-series grid data.In this study,we conducted prediction experiments using high-resolution 3D-OT from the Copernicus global ocean physical reanalysis,with data covering the vertical variation of temperature from the sea surface to 1000 m below the sea surface.We compared five mainstream models that are commonly used for ocean temperature prediction,and the results showed that the method achieved the best prediction results at all prediction scales.

Clustering Structure Analysis in Time-Series Data With Density-Based Clusterability Measure

Clustering is used to gain an intuition of the struc tures in the data.Most of the current clustering algorithms pro duce a clustering structure even on data that do not possess such structure.In these cases,the algorithms force a structure in the data instead of discovering one.To avoid false structures in the relations of data,a novel clusterability assessment method called density-based clusterability measure is proposed in this paper.I measures the prominence of clustering structure in the data to evaluate whether a cluster analysis could produce a meaningfu insight to the relationships in the data.This is especially useful in time-series data since visualizing the structure in time-series data is hard.The performance of the clusterability measure is evalu ated against several synthetic data sets and time-series data sets which illustrate that the density-based clusterability measure can successfully indicate clustering structure of time-series data.

Mapping winter wheat using phenological feature of peak before winter on the North China Plain based on time-series MODIS data

By employing the unique phenological feature of winter wheat extracted from peak before winter （PBW） and the advantages of moderate resolution imaging spectroradiometer （MODIS） data with high temporal resolution and intermediate spatial resolution, a remote sensing-based model for mapping winter wheat on the North China Plain was built through integration with Landsat images and land-use data. First, a phenological window, PBW was drawn from time-series MODIS data. Next, feature extraction was performed for the PBW to reduce feature dimension and enhance its information. Finally, a regression model was built to model the relationship of the phenological feature and the sample data. The amount of information of the PBW was evaluated and compared with that of the main peak （MP）. The relative precision of the mapping reached up to 92% in comparison to the Landsat sample data, and ranged between 87 and 96% in comparison to the statistical data. These results were sufficient to satisfy the accuracy requirements for winter wheat mapping at a large scale. Moreover, the proposed method has the ability to obtain the distribution information for winter wheat in an earlier period than previous studies. This study could throw light on the monitoring of winter wheat in China by using unique phenological feature of winter wheat.

Spatio-temporal changes of underground coal fires during 2008-2016 in Khanh Hoa coal field(North-east of Viet Nam) using Landsat time-series data

Underground coal fires are one of the most common and serious geohazards in most coal producing countries in the world. Monitoring their spatio-temporal changes plays an important role in controlling and preventing the effects of coal fires, and their environmental impact. In this study, the spatio-temporal changes of underground coal fires in Khanh Hoa coal field(North-East of Viet Nam) were analyzed using Landsat time-series data during the 2008-2016 period. Based on land surface temperatures retrieved from Landsat thermal data, underground coal fires related to thermal anomalies were identified using the MEDIAN+1.5×IQR(IQR: Interquartile range) threshold technique. The locations of underground coal fires were validated using a coal fire map produced by the field survey data and cross-validated using the daytime ASTER thermal infrared imagery. Based on the fires extracted from seven Landsat thermal imageries, the spatiotemporal changes of underground coal fire areas were analyzed. The results showed that the thermalanomalous zones have been correlated with known coal fires. Cross-validation of coal fires using ASTER TIR data showed a high consistency of 79.3%. The largest coal fire area of 184.6 hectares was detected in 2010, followed by 2014(181.1 hectares) and 2016(178.5 hectares). The smaller coal fire areas were extracted with areas of 133.6 and 152.5 hectares in 2011 and 2009 respectively. Underground coal fires were mainly detected in the northern and southern part, and tend to spread to north-west of the coal field.

Time-Series Data and Analysis Software of Connected Vehicles

In this study,we developed software for vehicle big data analysis to analyze the time-series data of connected vehicles.We designed two software modules:The rst to derive the Pearson correlation coefcients to analyze the collected data and the second to conduct exploratory data analysis of the collected vehicle data.In particular,we analyzed the dangerous driving patterns of motorists based on the safety standards of the Korea Transportation Safety Authority.We also analyzed seasonal fuel efciency(four seasons)and mileage of vehicles,and identied rapid acceleration,rapid deceleration,sudden stopping(harsh braking),quick starting,sudden left turn,sudden right turn and sudden U-turn driving patterns of vehicles.We implemented the density-based spatial clustering of applications with a noise algorithm for trajectory analysis based on GPS(Global Positioning System)data and designed a long shortterm memory algorithm and an auto-regressive integrated moving average model for time-series data analysis.In this paper,we mainly describe the development environment of the analysis software,the structure and data ow of the overall analysis platform,the conguration of the collected vehicle data,and the various algorithms used in the analysis.Finally,we present illustrative results of our analysis,such as dangerous driving patterns that were detected.

Classification of Vegetation in North Tibet Plateau Based on MODIS Time-Series Data

Based on the 16d-composite MODIS （moderate resolution imaging spectroradiometer）-NDVI（normalized difference vegetation index） time-series data in 2004, vegetation in North Tibet Plateau was classified and seasonal variations on the pixels selected from different vegetation type were analyzed. The Savitzky-Golay filtering algorithm was applied to perform a filtration processing for MODIS-NDVI time-series data. The processed time-series curves can reflect a real variation trend of vegetation growth. The NDVI time-series curves of coniferous forest, high-cold meadow, high-cold meadow steppe and high-cold steppe all appear a mono-peak model during vegetation growth with the maximum peak occurring in August. A decision-tree classification model was established according to either NDVI time-series data or land surface temperature data. And then, both classifying and processing for vegetations were carried out through the model based on NDVI time-series curves. An accuracy test illustrates that classification results are of high accuracy and credibility and the model is conducive for studying a climate variation and estimating a vegetation production at regional even global scale.

Effects of Freezing Disaster on Green-up Date of Vegetation Using MODIS/EVI Time Series Data

In the field of global changes, the relationship between plant phenology and climate, which reflects the response of terrestrial ecosystem to global climate change, has become a key subject that is highly concerned. Using the moderate-resolution imaging spectroradiometer (MODIS)/enhanced vegetation index(EVI) collected every eight days during January- July from 2005 to 2008 and the corresponding remote sensing data as experimental materials, we constructed cloud-free images via the Harmonic analysis of time series (HANTS). The cloud-free images were then treated by dynamic threshold method for obtaining the vegetation phenology in green up period and its distribution pattern. And the distribution pattern between freezing disaster year and normal year were comparatively analyzed for revealing the effect of freezing disaster on vegetation phenology in experimental plot. The result showed that the treated EVI data performed well in monitoring the effect of freezing disaster on vegetation phenology, accurately reflecting the regions suffered from freezing disaster. This result suggests that processing of remote sensing data using HANTS method could well monitor the ecological characteristics of vegetation.

Effect of calibration data series length on performance and optimal parameters of hydrological model

In order to assess the effects of calibration data series length on the performance and optimal parameter values of a hydrological model in ungauged or data-limited catchments （data are non-continuous and fragmental in some catchments）, we used non-continuous calibration periods for more independent streamflow data for SIMHYD （simple hydrology） model calibration. Nash-Sutcliffe efficiency and percentage water balance error were used as performance measures. The particle swarm optimization （PSO） method was used to calibrate the rainfall-runoff models. Different lengths of data series ranging from one year to ten years, randomly sampled, were used to study the impact of calibration data series length. Fifty-five relatively unimpaired catchments located all over Australia with daily precipitation, potential evapotranspiration, and streamflow data were tested to obtain more general conclusions. The results show that longer calibration data series do not necessarily result in better model performance. In general, eight years of data are sufficient to obtain steady estimates of model performance and parameters for the SIMHYD model. It is also shown that most humid catchments require fewer calibration data to obtain a good performance and stable parameter values. The model performs better in humid and semi-humid catchments than in arid catchments. Our results may have useful and interesting implications for the efficiency of using limited observation data for hydrological model calibration in different climates.

Outliers Mining in Time Series Data Sets

In this paper, we present a cluster-based algorithm for time series outlier mining.We use discrete Fourier transformation (DFT) to transform time series from time domain to frequency domain. Time series thus can be mapped as the points in k -dimensional space.For these points, a cluster-based algorithm is developed to mine the outliers from these points.The algorithm first partitions the input points into disjoint clusters and then prunes the clusters,through judgment that can not contain outliers.Our algorithm has been run in the electrical load time series of one steel enterprise and proved to be effective.

TSCND:Temporal Subsequence-Based Convolutional Network with Difference for Time Series Forecasting

Time series forecasting plays an important role in various fields, such as energy, finance, transport, and weather. Temporal convolutional networks (TCNs) based on dilated causal convolution have been widely used in time series forecasting. However, two problems weaken the performance of TCNs. One is that in dilated casual convolution, causal convolution leads to the receptive fields of outputs being concentrated in the earlier part of the input sequence, whereas the recent input information will be severely lost. The other is that the distribution shift problem in time series has not been adequately solved. To address the first problem, we propose a subsequence-based dilated convolution method (SDC). By using multiple convolutional filters to convolve elements of neighboring subsequences, the method extracts temporal features from a growing receptive field via a growing subsequence rather than a single element. Ultimately, the receptive field of each output element can cover the whole input sequence. To address the second problem, we propose a difference and compensation method (DCM). The method reduces the discrepancies between and within the input sequences by difference operations and then compensates the outputs for the information lost due to difference operations. Based on SDC and DCM, we further construct a temporal subsequence-based convolutional network with difference (TSCND) for time series forecasting. The experimental results show that TSCND can reduce prediction mean squared error by 7.3% and save runtime, compared with state-of-the-art models and vanilla TCN.

Generalized unscented Kalman filtering based radial basis function neural network for the prediction of ground radioactivity time series with missing data

On the assumption that random interruptions in the observation process are modeled by a sequence of independent Bernoulli random variables, we firstly generalize two kinds of nonlinear filtering methods with random interruption failures in the observation based on the extended Kalman filtering （EKF） and the unscented Kalman filtering （UKF）, which were shortened as GEKF and CUKF in this paper, respectively. Then the nonlinear filtering model is established by using the radial basis function neural network （RBFNN） prototypes and the network weights as state equation and the output of RBFNN to present the observation equation. Finally, we take the filtering problem under missing observed data as a special case of nonlinear filtering with random intermittent failures by setting each missing data to be zero without needing to pre-estimate the missing data, and use the GEKF-based RBFNN and the GUKF-based RBFNN to predict the ground radioactivity time series with missing data. Experimental results demonstrate that the prediction results of GUKF-based RBFNN accord well with the real ground radioactivity time series while the prediction results of GEKF-based RBFNN are divergent.

Using Data Mining with Time Series Data in Short-Term Stocks Prediction: A Literature Review

Data Mining (DM) methods are being increasingly used in prediction with time series data, in addition to traditional statistical approaches. This paper presents a literature review of the use of DM with time series data, focusing on shorttime stocks prediction. This is an area that has been attracting a great deal of attention from researchers in the field. The main contribution of this paper is to provide an outline of the use of DM with time series data, using mainly examples related with short-term stocks prediction. This is important to a better understanding of the field. Some of the main trends and open issues will also be introduced.

The Information Protection in Automatic Reconstruction of Not Continuous Geophysical Data Series

We show a quantitative technique characterized by low numerical mediation for the reconstruction of temporal sequences of geophysical data of length L interrupted for a time ΔT where . The aim is to protect the information acquired before and after the interruption by means of a numerical protocol with the lowest possible calculation weight. The signal reconstruction process is based on the synthesis of the low frequency signal extracted for subsampling (subsampling &#8711Dirac = ΔT in phase with ΔT) with the high frequency signal recorded before the crash. The SYRec (SYnthetic REConstruction) method for simplicity and speed of calculation and for spectral response stability is particularly effective in the studies of high speed transient phenomena that develop in very perturbed fields. This operative condition is found a mental when almost immediate informational responses are required to the observation system. In this example we are dealing with geomagnetic data coming from an uw counter intrusion magnetic system. The system produces (on time) information about the transit of local magnetic singularities (magnetic perturbations with low spatial extension), originated by quasi-point form and kinematic sources (divers), in harbors magnetic underwater fields. The performances of stability of the SYRec system make it usable also in long and medium period of observation (activity of geomagnetic observatories).

Comparison of Missing Data Imputation Methods in Time Series Forecasting

Time series forecasting has become an important aspect of data analysis and has many real-world applications.However,undesirable missing values are often encountered,which may adversely affect many forecasting tasks.In this study,we evaluate and compare the effects of imputationmethods for estimating missing values in a time series.Our approach does not include a simulation to generate pseudo-missing data,but instead perform imputation on actual missing data and measure the performance of the forecasting model created therefrom.In an experiment,therefore,several time series forecasting models are trained using different training datasets prepared using each imputation method.Subsequently,the performance of the imputation methods is evaluated by comparing the accuracy of the forecasting models.The results obtained from a total of four experimental cases show that the k-nearest neighbor technique is the most effective in reconstructing missing data and contributes positively to time series forecasting compared with other imputation methods.

A Survey of Time Series Data Visualization Methods

In the era of big data,the general public is more likely to access big data,but they wouldn’t like to analyze the data.Therefore,the traditional data visualization with certain professionalism is not easy to be accepted by the general public living in the fast pace.Under this background,a new general visualization method for dynamic time series data emerges as the times require.Time series data visualization organizes abstract and hard-to-understand data into a form that is easily understood by the public.This method integrates data visualization into short videos,which is more in line with the way people get information in modern fast-paced lifestyles.The modular approach also facilitates public participation in production.This paper summarizes the dynamic visualization methods of time series data ranking,studies the relevant literature,shows its value and existing problems,and gives corresponding suggestions and future research prospects.

Orthogonal Series Estimation of Nonparametric Regression Measurement Error Models with Validation Data

In this article we study the estimation method of nonparametric regression measurement error model based on a validation data. The estimation procedures are based on orthogonal series estimation and truncated series approximation methods without specifying any structure equation and the distribution assumption. The convergence rates of the proposed estimator are derived. By example and through simulation, the method is robust against the misspecification of a measurement error model.

Non-Stationary Trend Change Point Pattern Using 24-Hourly Annual Maximum Series (AMS) Precipitation Data

This paper mainly investigated the basic information about non-stationary trend change point patterns. After performing the investigation, the corresponding results show the existence of a trend, its magnitude, and change points in 24-hourly annual maximum series (AMS) extracted from monthly maximum series (MMS) data for thirty years (1986-2015) rainfall data for Uyo metropolis. Trend analysis was performed using Mann-Kendall (MK) test and Sen’s slope estimator (SSE) used to obtain the trend magnitude, while the trend change point analysis was conducted using the distribution-free cumulative sum test (CUSUM) and the sequential Mann-Kendall test (SQMK). A free CUSUM plot date of change point of rainfall trend as 2002 at 90% confidence interval was obtained from where the increasing trend started and became more pronounced in the year 2011, another change point year from the SQMK plot with the trend intensifying. The SSE gave an average rate of change in rainfall as 2.1288 and 2.16 mm/year for AMS and MMS time series data respectively. Invariably, the condition for Non-stationary concept application is met for intensity-duration-frequency modeling.