Unsupervised Time Series Segmentation: A Survey on Recent Advances

Time series segmentation has attracted more interests in recent years,which aims to segment time series into different segments,each reflects a state of the monitored objects.Although there have been many surveys on time series segmentation,most of them focus more on change point detection(CPD)methods and overlook the advances in boundary detection(BD)and state detection(SD)methods.In this paper,we categorize time series segmentation methods into CPD,BD,and SD methods,with a specific focus on recent advances in BD and SD methods.Within the scope of BD and SD,we subdivide the methods based on their underlying models/techniques and focus on the milestones that have shaped the development trajectory of each category.As a conclusion,we found that:(1)Existing methods failed to provide sufficient support for online working,with only a few methods supporting online deployment;(2)Most existing methods require the specification of parameters,which hinders their ability to work adaptively;(3)Existing SD methods do not attach importance to accurate detection of boundary points in evaluation,which may lead to limitations in boundary point detection.We highlight the ability to working online and adaptively as important attributes of segmentation methods,the boundary detection accuracy as a neglected metrics for SD methods.

Determination of the Series Resistance of a Series Vertical-Junction Silicon (N+/P/P+) Solar Cell under Polychromatic Illumination and Magnetic Field: Effect of Optimum Thickness

By solving the magneto-transport equation for excess minority charge carriers in the base of the series vertical-junction silicon cell, the phenomenological parameters of the cell can be determined from the boundary conditions. Photocurrent density and photovoltage are determined for each value of applied magnetic field and corresponding optimum thickness, to establish the current-voltage characteristic (Jph(Sf, Sb, z, B, Hop)-Vph(Sf, Sb, z, B, Hop) of the silicon cell under polychromatic illumination. This study will make it possible to reduce the material used (by reducing the optimum thickness), which will help to lower prices. It will also enable us to reduce betting effects (lower series resistance), thereby boosting solar cell efficiency.

Analysis of the causes of primary revision after unicompartmental knee arthroplasty: A case series

BACKGROUND Unicompartmental knee arthroplasty(UKA)has great advantages in the treatment of unicompartmental knee osteoarthritis,but its revision rate is higher than that of total knee arthroplasty.AIM To summarize and analyse the causes of revision after UKA.METHODS This is a retrospective case series study in which the reasons for the first revision after UKA are summarized.We analysed the clinical symptoms,medical histories,laboratory test results,imaging examination results and treatment processes of the patients who underwent revision and summarized the reasons for primary revision after UKA.RESULTS A total of 13 patients,including 3 males and 10 females,underwent revision surgery after UKA.The average age of the included patients was 67.62 years.The prosthesis was used for 3 d to 72 months.The main reasons for revision after UKA were improper suturing of the surgical opening(1 patient),osteophytes(2 patients),intra-articular loose bodies(2 patients),tibial prosthesis loosening(2 patients),rheumatoid arthritis(1 patient),gasket dislocation(3 patients),anterior cruciate ligament injury(1 patient),and medial collateral ligament injury with residual bone cement(1 patient).CONCLUSION The causes of primary revision after UKA were gasket dislocation,osteophytes,intra-articular loose bodies and tibial prosthesis loosening.Avoidance of these factors may greatly reduce the rate of revision after UKA,improve patient satisfaction and reduce medical burden.

Reservoir characteristics and formation model of Upper Carboniferous bauxite series in eastern Ordos Basin,NW China

Through core observation,thin section identification,X-ray diffraction analysis,scanning electron microscopy,and low-temperature nitrogen adsorption and isothermal adsorption experiments,the lithology and pore characteristics of the Upper Carboniferous bauxite series in eastern Ordos Basin were analyzed to reveal the formation and evolution process of the bauxite reservoirs.A petrological nomenclature and classification scheme for bauxitic rocks based on three units(aluminum hydroxides,iron minerals and clay minerals)is proposed.It is found that bauxitic mudstone is in the form of dense massive and clastic structures,while the(clayey)bauxite is of dense massive,pisolite,oolite,porous soil and clastic structures.Both bauxitic mudstone and bauxite reservoirs develop dissolution pores,intercrystalline pores,and microfractures as the dominant gas storage space,with the porosity less than 10% and mesopores in dominance.The bauxite series in the North China Craton can be divided into five sections,i.e.,ferrilite(Shanxi-style iron ore,section A),bauxitic mudstone(section B),bauxite(section C),bauxite mudstone(debris-containing,section D)and dark mudstone-coal section(section E).The burrow/funnel filling,lenticular,layered/massive bauxite deposits occur separately in the karst platforms,gentle slopes and low-lying areas.The karst platforms and gentle slopes are conducive to surface water leaching,with strong karstification,well-developed pores,large reservoir thickness and good physical properties,but poor strata continuity.The low-lying areas have poor physical properties but relatively continuous and stable reservoirs.The gas enrichment in bauxites is jointly controlled by source rock,reservoir rock and fractures.This recognition provides geological basis for the exploration and development of natural gas in the Upper Carboniferous in the study area and similar bauxite systems.

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.

Improved Responses with Multitaper Spectral Analysis for Magnetotelluric Time Series Data Processing:Examples from Field Data

In order to attain good quality transfer function estimates from magnetotelluric field data(i.e.,smooth behavior and small uncertainties across all frequencies),we compare time series data processing with and without a multitaper approach for spectral estimation.There are several common ways to increase the reliability of the Fourier spectral estimation from experimental(noisy)data;for example to subdivide the experimental time series into segments,taper these segments(using single taper),perform the Fourier transform of the individual segments,and average the resulting spectra.

Periodic signal extraction of GNSS height time series based on adaptive singular spectrum analysis

Singular spectrum analysis is widely used in geodetic time series analysis.However,when extracting time-varying periodic signals from a large number of Global Navigation Satellite System(GNSS)time series,the selection of appropriate embedding window size and principal components makes this method cumbersome and inefficient.To improve the efficiency and accuracy of singular spectrum analysis,this paper proposes an adaptive singular spectrum analysis method by combining spectrum analysis with a new trace matrix.The running time and correlation analysis indicate that the proposed method can adaptively set the embedding window size to extract the time-varying periodic signals from GNSS time series,and the extraction efficiency of a single time series is six times that of singular spectrum analysis.The method is also accurate and more suitable for time-varying periodic signal analysis of global GNSS sites.

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.

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.

The changes in soil organic carbon stock and quality across a subalpine forest successional series

Soil organic carbon(SOC)affects the function of terrestrial ecosystem and plays a vital role in global carbon cycle.Yet,large uncertainty still existed regarding the changes in SOC stock and quality with forest succession.Here,the stock and quality of SOC at 1-m soil profile were investigated across a subalpine forest series,including shrub,deciduous broad-leaved forest,broadleaf-conifer mixed forest,middle-age coniferous forest and mature coniferous forest,which located at southeast of Tibetan Plateau.The results showed that SOC stock ranged from 9.8 to29.9 kg·m^(-2),and exhibited a hump-shaped response pattern across the forest successional series.The highest and lowest SOC stock was observed in the mixed forest and shrub forest,respectively.The SOC stock had no significant relationships with soil temperature and litter stock,but was positively correlated with wood debris stock.Meanwhile,the average percentages of polysaccharides,lignins,aromatics and aliphatics based on FTIR spectroscopy were 79.89%,0.94%,18.87%and 0.29%,respectively.Furthermore,the percentage of polysaccharides exhibited an increasing pattern across the forest successional series except for the sudden decreasing in the mixed forest,while the proportions of lignins,aromatics and aliphatics exhibited a decreasing pattern across the forest successional series except for the sudden increasing in the mixed forest.Consequently,the humification indices(HIs)were highest in the mixed forest compared to the other four successional stages,which means that the SOC quality in mixed forest was worse than other successional stages.In addition,the SOC stock,recalcitrant fractions and HIs decreased with increasing soil depth,while the polysaccharides exhibited an increasing pattern.These findings demonstrate that the mixed forest had higher SOC stock and worse SOC quality than other successional stages.The high proportion of SOC stock(66%at depth of 20-100 cm)and better SOC quality(lower HIs)indicate that deep soil have tremendous potential to store SOC and needs more attention under global chan ge.

Time series prediction of reservoir bank landslide failure probability considering the spatial variability of soil properties

Historically,landslides have been the primary type of geological disaster worldwide.Generally,the stability of reservoir banks is primarily affected by rainfall and reservoir water level fluctuations.Moreover,the stability of reservoir banks changes with the long-term dynamics of external disastercausing factors.Thus,assessing the time-varying reliability of reservoir landslides remains a challenge.In this paper,a machine learning(ML)based approach is proposed to analyze the long-term reliability of reservoir bank landslides in spatially variable soils through time series prediction.This study systematically investigated the prediction performances of three ML algorithms,i.e.multilayer perceptron(MLP),convolutional neural network(CNN),and long short-term memory(LSTM).Additionally,the effects of the data quantity and data ratio on the predictive power of deep learning models are considered.The results show that all three ML models can accurately depict the changes in the time-varying failure probability of reservoir landslides.The CNN model outperforms both the MLP and LSTM models in predicting the failure probability.Furthermore,selecting the right data ratio can improve the prediction accuracy of the failure probability obtained by ML models.

Deep Learning for Financial Time Series Prediction:A State-of-the-Art Review of Standalone and HybridModels

Financial time series prediction,whether for classification or regression,has been a heated research topic over the last decade.While traditional machine learning algorithms have experienced mediocre results,deep learning has largely contributed to the elevation of the prediction performance.Currently,the most up-to-date review of advanced machine learning techniques for financial time series prediction is still lacking,making it challenging for finance domain experts and relevant practitioners to determine which model potentially performs better,what techniques and components are involved,and how themodel can be designed and implemented.This review article provides an overview of techniques,components and frameworks for financial time series prediction,with an emphasis on state-of-the-art deep learning models in the literature from2015 to 2023,including standalonemodels like convolutional neural networks(CNN)that are capable of extracting spatial dependencies within data,and long short-term memory(LSTM)that is designed for handling temporal dependencies;and hybrid models integrating CNN,LSTM,attention mechanism(AM)and other techniques.For illustration and comparison purposes,models proposed in recent studies are mapped to relevant elements of a generalized framework comprised of input,output,feature extraction,prediction,and related processes.Among the state-of-the-artmodels,hybrid models like CNNLSTMand CNN-LSTM-AM in general have been reported superior in performance to stand-alone models like the CNN-only model.Some remaining challenges have been discussed,including non-friendliness for finance domain experts,delayed prediction,domain knowledge negligence,lack of standards,and inability of real-time and highfrequency predictions.The principal contributions of this paper are to provide a one-stop guide for both academia and industry to review,compare and summarize technologies and recent advances in this area,to facilitate smooth and informed implementation,and to highlight future research directions.

A Time Series Short-Term Prediction Method Based on Multi-Granularity Event Matching and Alignment

Accurate forecasting of time series is crucial across various domains.Many prediction tasks rely on effectively segmenting,matching,and time series data alignment.For instance,regardless of time series with the same granularity,segmenting them into different granularity events can effectively mitigate the impact of varying time scales on prediction accuracy.However,these events of varying granularity frequently intersect with each other,which may possess unequal durations.Even minor differences can result in significant errors when matching time series with future trends.Besides,directly using matched events but unaligned events as state vectors in machine learning-based prediction models can lead to insufficient prediction accuracy.Therefore,this paper proposes a short-term forecasting method for time series based on a multi-granularity event,MGE-SP(multi-granularity event-based short-termprediction).First,amethodological framework for MGE-SP established guides the implementation steps.The framework consists of three key steps,including multi-granularity event matching based on the LTF(latest time first)strategy,multi-granularity event alignment using a piecewise aggregate approximation based on the compression ratio,and a short-term prediction model based on XGBoost.The data from a nationwide online car-hailing service in China ensures the method’s reliability.The average RMSE(root mean square error)and MAE(mean absolute error)of the proposed method are 3.204 and 2.360,lower than the respective values of 4.056 and 3.101 obtained using theARIMA(autoregressive integratedmoving average)method,as well as the values of 4.278 and 2.994 obtained using k-means-SVR(support vector regression)method.The other experiment is conducted on stock data froma public data set.The proposed method achieved an average RMSE and MAE of 0.836 and 0.696,lower than the respective values of 1.019 and 0.844 obtained using the ARIMA method,as well as the values of 1.350 and 1.172 obtained using the k-means-SVR method.

On power series statistical convergence and new uniform integrability of double sequences

In the present paper,we mostly focus on P_(p)^(2)-statistical convergence.We will look into the uniform integrability via the power series method and its characterizations for double sequences.Also,the notions of P_(p)^(2)-statistically Cauchy sequence,P_(p)^(2)-statistical boundedness and core for double sequences will be described in addition to these findings.

AFSTGCN:Prediction for multivariate time series using an adaptive fused spatial-temporal graph convolutional network

The prediction for Multivariate Time Series(MTS)explores the interrelationships among variables at historical moments,extracts their relevant characteristics,and is widely used in finance,weather,complex industries and other fields.Furthermore,it is important to construct a digital twin system.However,existing methods do not take full advantage of the potential properties of variables,which results in poor predicted accuracy.In this paper,we propose the Adaptive Fused Spatial-Temporal Graph Convolutional Network(AFSTGCN).First,to address the problem of the unknown spatial-temporal structure,we construct the Adaptive Fused Spatial-Temporal Graph(AFSTG)layer.Specifically,we fuse the spatial-temporal graph based on the interrelationship of spatial graphs.Simultaneously,we construct the adaptive adjacency matrix of the spatial-temporal graph using node embedding methods.Subsequently,to overcome the insufficient extraction of disordered correlation features,we construct the Adaptive Fused Spatial-Temporal Graph Convolutional(AFSTGC)module.The module forces the reordering of disordered temporal,spatial and spatial-temporal dependencies into rule-like data.AFSTGCN dynamically and synchronously acquires potential temporal,spatial and spatial-temporal correlations,thereby fully extracting rich hierarchical feature information to enhance the predicted accuracy.Experiments on different types of MTS datasets demonstrate that the model achieves state-of-the-art single-step and multi-step performance compared with eight other deep learning models.

Advancing Autoencoder Architectures for Enhanced Anomaly Detection in Multivariate Industrial Time Series

In the context of rapid digitization in industrial environments,how effective are advanced unsupervised learning models,particularly hybrid autoencoder models,at detecting anomalies in industrial control system(ICS)datasets?This study is crucial because it addresses the challenge of identifying rare and complex anomalous patterns in the vast amounts of time series data generated by Internet of Things(IoT)devices,which can significantly improve the reliability and safety of these systems.In this paper,we propose a hybrid autoencoder model,called ConvBiLSTMAE,which combines convolutional neural network(CNN)and bidirectional long short-term memory(BiLSTM)to more effectively train complex temporal data patterns in anomaly detection.On the hardware-in-the-loopbased extended industrial control system dataset,the ConvBiLSTM-AE model demonstrated remarkable anomaly detection performance,achieving F1 scores of 0.78 and 0.41 for the first and second datasets,respectively.The results suggest that hybrid autoencoder models are not only viable,but potentially superior alternatives for unsupervised anomaly detection in complex industrial systems,offering a promising approach to improving their reliability and safety.

Multivariate form of Hermite sampling series

In this paper,we establish a new multivariate Hermite sampling series involving samples from the function itself and its mixed and non-mixed partial derivatives of arbitrary order.This multivariate form of Hermite sampling will be valid for some classes of multivariate entire functions,satisfying certain growth conditions.We will show that many known results included in Commun Korean Math Soc,2002,17:731-740,Turk J Math,2017,41:387-403 and Filomat,2020,34:3339-3347 are special cases of our results.Moreover,we estimate the truncation error of this sampling based on localized sampling without decay assumption.Illustrative examples are also presented.

Multivariate Time Series Anomaly Detection Based on Spatial-Temporal Network and Transformer in Industrial Internet of Things

In the Industrial Internet of Things(IIoT),sensors generate time series data to reflect the working state.When the systems are attacked,timely identification of outliers in time series is critical to ensure security.Although many anomaly detection methods have been proposed,the temporal correlation of the time series over the same sensor and the state(spatial)correlation between different sensors are rarely considered simultaneously in these methods.Owing to the superior capability of Transformer in learning time series features.This paper proposes a time series anomaly detection method based on a spatial-temporal network and an improved Transformer.Additionally,the methods based on graph neural networks typically include a graph structure learning module and an anomaly detection module,which are interdependent.However,in the initial phase of training,since neither of the modules has reached an optimal state,their performance may influence each other.This scenario makes the end-to-end training approach hard to effectively direct the learning trajectory of each module.This interdependence between the modules,coupled with the initial instability,may cause the model to find it hard to find the optimal solution during the training process,resulting in unsatisfactory results.We introduce an adaptive graph structure learning method to obtain the optimal model parameters and graph structure.Experiments on two publicly available datasets demonstrate that the proposed method attains higher anomaly detection results than other methods.

Main controlling factors and exploration enlightenment of aluminous rock series gas reservoirs in Ordos Basin,NW China

Based on the data of outcrop,core,logging,gas testing,and experiments,the natural gas accumulation and aluminous rock mineralization integrated research was adopted to analyze the controlling factors of aluminous rock series effective reservoirs in the Ordos Basin,NW China,as well as the configuration of coal-measure source rocks and aluminous rock series reservoirs.A natural gas accumulation model was constructed to evaluate the gas exploration potential of aluminous rock series under coal seam in the basin.The effective reservoirs of aluminous rock series in the Ordos Basin are composed of honeycomb-shaped bauxites with porous residual pisolitic and detrital structures,with the diasporite content of greater than 80%and dissolved pores as the main storage space.The bauxite reservoirs are formed under a model that planation controls the material supply,karst paleogeomorphology controls diagenesis,and land surface leaching improves reservoir quality.The hot humid climate and sea level changes in the Late Carboniferous–Early Permian dominated the development of a typical coal-aluminum-iron three-stage stratigraphic structure.The natural gas generated by the extensive hydrocarbon generation of coal-measure source rocks was accumulated in aluminous rock series under the coal seam,indicating a model of hydrocarbon accumulation under the source.During the Upper Carboniferous–Lower Permian,the relatively low-lying area on the edge of an ancient land or island in the North China landmass was developed.The gas reservoirs of aluminous rock series,which are clustered at multiple points in lenticular shape,are important new natural gas exploration fields with great potential in the Upper Paleozoic of North China Craton.

Electromagnetic Performance Analysis of Variable Flux Memory Machines with Series-magnetic-circuit and Different Rotor Topologies

In this paper,the electromagnetic performance of variable flux memory(VFM)machines with series-magnetic-circuit is investigated and compared for different rotor topologies.Based on a V-type VFM machine,five topologies with different interior permanent magnet(IPM)arrangements are evolved and optimized under same constrains.Based on two-dimensional(2-D)finite element(FE)method,their electromagnetic performance at magnetization and demagnetization states is evaluated.It reveals that the iron bridge and rotor lamination region between constant PM(CPM)and variable PM(VPM)play an important role in torque density and flux regulation(FR)capabilities.Besides,the global efficiency can be improved in VFM machines by adjusting magnetization state(MS)under different operating conditions.