Change Point Detection Research Articles

Anomaly detection for atomic clocks using unsupervised machine learning algorithms

Atomic clocks are the most accurate timekeeping instruments in the world and play a crucial role in numerous applications, notably in satellite navigation. Nonetheless, the accuracy of these clock signals is subject to anomalies, highlighting the importance of anomaly characterization and detection. In our study, we identify three types of anomalies in the phase data of atomic clocks—outliers, phase jumps and inflection points, and also frequency jumps in the frequency data, which corresponds to the inflection points. The novelty of our work lies in the application of machine learning methods for atomic clock anomaly detection (AD), as opposed to traditional algorithms. We introduce a variety of unsupervised AD and change point detection (CPD) algorithms from the realms of statistics and machine learning, propose a customized thresholding function for AD, and evaluate AD and CPD algorithms on both synthetic and real-world atomic clock data. Our experiments reveal that the subsequence local outlier factor algorithm achieves excellent performance in detecting outliers and phase jumps, but struggles with inflection points. Crucially, we found that the application of a CPD algorithm specifically for detecting the frequency jumps in frequency data substantially improves performance. Our study adopts unsupervised machine learning methods for AD provides robust detection strategies, thereby contributing an expanded understanding of the use of machine learning for clock data monitoring.

Unraveling climate trends in the mediterranean: a hybrid machine learning and statistical approach

This study presents a comprehensive spatiotemporal analysis of sea surface temperatures (SST) and surface air temperatures (TAS) across 15 Mediterranean coastal stations, leveraging centennial-scale data to analyze regional climate dynamics. The modeling framework integrates three sequential phases: data preprocessing, statistical analysis, and advanced machine learning techniques, creating a robust analytical pipeline. The data preprocessing phase harmonizes diverse datasets, addresses missing values, and applies transformations to ensure analytical consistency. The statistical modeling employs the Pettitt test for change point detection and linear trend analysis to unveil underlying patterns. The machine learning phase utilizes K-means clustering for climate regime classification and implements tailored Convolutional Neural Networks (CNNs) for cluster-specific future climate anomaly projections. Results unveil a marked anthropogenic climate signal, with contemporary observations consistently surpassing historical baselines. Breakpoint analyses and linear trend assessments reveal heterogeneous climatic shifts, with pronounced warming in the northern Mediterranean. Notably, Nice and Ajaccio exhibit the highest SST increases (0.0119 and 0.0113 °C/decade, respectively), contrasting with more modest trends in Alexandria (0.0052 °C/decade) and Antalya (0.0047 °C/decade) in the eastern Mediterranean. The application of clustering and CNN projections provides granular insights into differential warming trajectories. By 2050, cooler northwestern Mediterranean zones are projected to experience dramatic SST anomalies of approximately 3 °C above the average, with corresponding TAS increases of 2.5 °C. In contrast, warmer eastern and southern regions display more subdued warming patterns, with projected SST and TAS increases of 1.5–2.5 °C by mid-century. This research’s importance is highlighted by its potential to inform tailored adaptation strategies and contribute to the theoretical understanding of climate dynamics, advancing climate modeling and analysis efforts.

Generalized fiducial inference for the GEV change-point model

Generalized extreme value (GEV) distribution is used to analyse the maximum from a block of data. It is very useful to describe the unusual event rather than the usual event. In this paper, we propose a change-point detection procedure for GEV distribution based on generalized fiducial inference. The fiducial distribution of the change-point location is constructed. Meanwhile, Markov Chain Monte Carlo method combined with Gibbs sampling and the Metropolis–Hastings algorithm is utilised to estimate the location of the change point and its confidence interval. In addition, the generalized fiducial factor is used to test whether there is a change point. Simulation results show that the proposed generalized fiducial method performs better in accuracy, robustness and the length of confidence intervals. Finally, we apply the proposed method to the annual maximum rainfall data in Beijing.

Detection of spatiotemporal changepoints: a generalised additive model approach

The detection of changepoints in spatio-temporal datasets has been receiving increased focus in recent years and is utilised in a wide range of fields. With temporal data observed at different spatial locations, the current approach is typically to use univariate changepoint methods in a marginal sense with the detected changepoint being representative of a single location only. We present a spatio-temporal changepoint method that utilises a generalised additive model (GAM) dependent on the 2D spatial location and the observation time to account for the underlying spatio-temporal process. We use the full likelihood of the GAM in conjunction with the pruned linear exact time (PELT) changepoint search algorithm to detect multiple changepoints across spatial locations in a computationally efficient manner. When compared to a univariate marginal approach our method is shown to perform more efficiently in simulation studies at detecting true changepoints and demonstrates less evidence of overfitting. Furthermore, as the approach explicitly models spatio-temporal dependencies between spatial locations, any changepoints detected are common across the locations. We demonstrate an application of the method to an air quality dataset covering the COVID-19 lockdown in the United Kingdom.

Robust change point detection for high‐dimensional linear models with tolerance for outliers and heavy tails

Robust change point detection for high‐dimensional linear models with tolerance for outliers and heavy tails

Change point detection in length-biased lognormal distribution

In this paper, we develop two procedures for identifying the dynamic trends in the parameters of length-biased lognormal distribution based on likelihood ratio and modified information criterion. These methods mainly consider the test of the existence of the change point and provide the maximum likelihood estimation of the change point when the change point exists. In addition, the asymptotic distribution of test statistic based on likelihood ratio is derived as an extreme value distribution, while the asymptotic distribution of test statistic based on modified information criterion is derived as a chi-square distribution. And the consistency of parameter estimation is proved. Simulations are conducted to study the performance of the proposed method in terms of power, coverage probabilities and average sizes of confidence sets. The proposed methods are applied to a real data to illustrate the detecting procedures.

Phase unwrapping error identification and suppression method in φ-OTDR systems based on PELT-VMD-ARIMA

In phase-sensitive optical time-domain reflectometer (φ-OTDR) systems, phase unwrapping errors can distort vibration information. To address this issue, a phase unwrapping error identification and suppression method combining pruned exact linear time (PELT) changepoint detection, variational mode decomposition (VMD), and autoregressive integrated moving average (ARIMA) models, termed PELT-VMD-ARIMA, is proposed. Firstly, the principle of the proposed method is introduced, and its effectiveness is verified through a series of numerical simulation experiments. Next, piezoelectric transducers (PZTs) are employed as seismic sources in experiments involving single-frequency and chirp signals. Compared to the mean-shift method, the proposed method reduces the average root mean square error (RMSE) by 70.36% within 2δ range around the changepoints. Finally, the proposed method was validated through an active source seismic application. The results demonstrate the efficacy of the proposed method in identifying and suppressing phase unwrapping errors, thereby enhancing signal quality. This method enhances the vibration recognition capability of φ-OTDR systems, which facilitates precise distributed acoustic sensing applications.

A method for assessing the operational status of a microseismic monitoring system using energy distribution changes of observed data

Abstract The operational status of geophones plays a pivotal role in ensuring the accuracy and reliability of microseismic monitoring systems. However, conventional techniques used to evaluate the operational status of geophones require human intervention or significant time delays. To address this issue, we propose a method for online monitoring of geophone status using observed data obtained from a microseismic system. Firstly, the energy features of the preprocessed observation data are extracted via wavelet packet decomposition. Subsequently, the distribution parameters of energy features are obtained through loglogistic distribution fitting. These parameters are then applied to a change-point detection model, enabling the online monitoring of seismic geophones. In addition, we selected long short-term memory (LSTM) network to classify the operational status of the geophones, which is trained using the obtained energy distribution data and the time-frequency characteristics of the observed data. The experimental results indicate that the model achieves an accuracy of 98.33%, surpassing the 89.58% accuracy of the support vector machine (SVM). The proposed method not only contributes to online monitoring and precise determination of the operating status of detectors, but also has enormous application potential in other fields that require monitoring and evaluating the operating status of instruments.

Monitoring of meat quality and change-point detection by a sensor array and profiling of bacterial communities

BackgroundReal-time monitoring of food consumer quality remains challenging due to diverse bio-chemical processes taking place in the food matrices, and hence it requires accurate analytical methods. Thresholds to determine spoiled food are often difficult to set. The existing analytical methods are too complicated for rapid in situ screening of foodstuff. ResultsWe have studied the dynamics of meat spoilage by electronic nose (e-nose) for digitizing the smell associated with volatile spoilage markers of meat, comparing the results with changes in the microbiome composition of the spoiling meat samples. We apply the time series analysis to follow dynamic changes in the gas profile extracted from the e-nose responses and to identify the change-point window of the meat state. The obtained e-nose features correlate with changes in the microbiome composition such as increase in the proportion of Brochothrix and Pseudomonas spp. and disappearance of Mycoplasma spp., and with representative gas sensors towards hydrogen, ammonia, and alcohol vapors with R2 values of 0.98, 0.93, and 0.91, respectively. Integration of e-nose and computer vision into a single analytical panel improved the meat state identification accuracy up to 0.85, allowing for more reliable meat state assessment. SignificanceAccurate identification of the change-point in the meat state achieved by digitalizing volatile spoilage markers from the e-nose unit holds promises for application of smart miniaturized devices in food industry.

Research on Dynamic Subsidy Based on Deep Reinforcement Learning for Non-Stationary Stochastic Demand in Ride-Hailing

The ride-hailing market often experiences significant fluctuations in traffic demand, resulting in supply-demand imbalances. In this regard, the dynamic subsidy strategy is frequently employed by ride-hailing platforms to incentivize drivers to relocate to zones with high demand. However, determining the appropriate amount of subsidy at the appropriate time remains challenging. First, traffic demand exhibits high non-stationarity, characterized by multi-context patterns with time-varying statistical features. Second, high-dimensional state/action spaces contain multiple spatiotemporal dimensions and context patterns. Third, decision-making should satisfy real-time requirements. To address the above challenges, we first construct a Non-Stationary Markov Decision Process (NSMDP) based on the assumption of ride-hailing service systems dynamics. Then, we develop a solution framework for the NSMDP. A change point detection method based on feature-enhanced LSTM within the framework can identify the changepoints and time-varying context patterns of stochastic demand. Moreover, the framework also includes a deterministic policy deep reinforcement learning algorithm to optimize. Finally, through simulated experiments with real-world historical data, we demonstrate the effectiveness of the proposed approach. It performs well in improving the platform’s profits and alleviating supply-demand imbalances under the dynamic subsidy strategy. The results also prove that a scientific dynamic subsidy strategy is particularly effective in the high-demand context pattern with more drastic fluctuations. Additionally, the profitability of dynamic subsidy strategy will increase with the increase of the non-stationary level.

Noise-Adaptive State Estimators with Change-Point Detection.

Aiming at tracking sharply maneuvering targets, this paper develops novel variational adaptive state estimators for joint target state and process noise parameter estimation for a class of linear state-space models with abruptly changing parameters. By combining variational inference with change-point detection in an online Bayesian fashion, two adaptive estimators-a change-point-based adaptive Kalman filter (CPAKF) and a change-point-based adaptive Kalman smoother (CPAKS)-are proposed in a recursive detection and estimation process. In each iteration, the run-length probability of the current maneuver mode is first calculated, and then the joint posterior of the target state and process noise parameter conditioned on the run length is approximated by variational inference. Compared with existing variational noise-adaptive Kalman filters, the proposed methods are robust to initial iterative value settings, improving their capability of tracking sharply maneuvering targets. Meanwhile, the change-point detection divides the non-stationary time sequence into several stationary segments, allowing for an adaptive sliding length in the CPAKS method. The tracking performance of the proposed methods is investigated using both synthetic and real-world datasets of maneuvering targets.

Drift versus Shift: Decoupling Trends and Changepoint Analysis

We introduce a new approach for decoupling trends (drift) and changepoints (shifts) in time series. Our locally adaptive model-based approach for robustly decoupling combines Bayesian trend filtering and machine learning based regularization. An over-parameterized Bayesian dynamic linear model (DLM) is first applied to characterize drift. Then a weighted penalized likelihood estimator is paired with the estimated DLM posterior distribution to identify shifts. We show how Bayesian DLMs specified with so-called shrinkage priors can provide smooth estimates of underlying trends in the presence of complex noise components. However, their inability to shrink exactly to zero inhibits direct changepoint detection. In contrast, penalized likelihood methods are highly effective in locating changepoints. However, they require data with simple patterns in both signal and noise. The proposed decoupling approach combines the strengths of both, that is, the flexibility of Bayesian DLMs with the hard thresholding property of penalized likelihood estimators, to provide changepoint analysis in complex, modern settings. The proposed framework is outlier robust and can identify a variety of changes, including in mean and slope. It is also easily extended for analysis of parameter shifts in time-varying parameter models like dynamic regressions. We illustrate the flexibility and contrast the performance and robustness of our approach with several alternative methods across a wide range of simulations and application examples.

Research on Load Decomposition and Optimization of Intelligent Elderly Care Service Based on Heuristic and Event Detection Algorithm

Against the backdrop of the digital age, the openness, equality and interaction of the Internet economy have injected new vitality into China’s traditional industries. The application of big data technology, especially in information integration and analysis, has become a key force in promoting the sustainable and healthy development of the national economy. This study focuses on the “Internet +” environment, discusses the impact of the aging problem of community workers on home care services, and proposes an optimization scheme based on a heuristic algorithm. The heuristic algorithm, inspired by the foraging behavior of ants in nature, optimizes the route selection problem by simulating an ant colony to choose the path with a high concentration of pheromones and shows outstanding application potential in the field of home care. The accuracy of the event detection algorithm is directly related to the performance of the load decomposition algorithm, and the change point detection algorithm can effectively identify the change point of the probability distribution in the time series data, which provides important input data for unsupervised clustering. Advanced computer theory, including the Hidden Markov model (HMM) and swarm intelligence optimization algorithm, is used in this research. By comparing different swarm intelligence algorithms, we find that the standard Gray Wolf optimization (SGWO) model is better than the basic Gray Wolf optimization (BGWO) algorithm and the improved Gray Wolf optimization (DGWO) algorithm in terms of stability and output results. The SGWO model significantly improves the efficiency of the load decomposition algorithm, which has been verified in the application of the smart elderly care service platform. The platform not only supports the operation of related technologies and information products but also realizes the seamless integration of information among various subjects of elderly care services. In addition, the factor hidden in the Markov model that can be selectively activated effectively monitors equipment status in the Internet of Things environment, provides real-time monitoring of user consumption behavior and fault information and further enhances the quality and efficiency of smart elderly care services.

Empirical likelihood change point detection in quantile regression models

Empirical likelihood change point detection in quantile regression models

Trajectories and revolutions in popular melody based on U.S. charts from 1950 to 2023

In the past century, the history of popular music has been analyzed from many different perspectives, with sociologists, musicologists and philosophers all offering distinct narratives characterizing the evolution of popular music. However, quantitative studies on this subject began only in the last decade and focused on features extracted from raw audio, which limits the scope to low-level components of music. The present study investigates the evolution of a more abstract dimension of popular music, specifically melody, using a new dataset of popular melodies spanning from 1950 to 2023. To identify "melodic revolutions", changepoint detection was applied to a multivariate time series comprising features related to the pitch and rhythmic structure of the melodies. Two major revolutions in 1975 and 2000 and one smaller revolution in 1996, characterized by significant decreases in complexity, were located. The revolutions divided the time series into three eras, which were modeled separately with autoregression, linear regression and vector autoregression. Linear regression of autoregression residuals underscored inter-feature relationships, which become stronger in post-2000 melodies. The overriding pattern emerging from these analyses shows decreasing complexity and increasing note density in popular melodies over time, especially since 2000.

A novel control chart scheme for online social network monitoring using multivariate nonparametric profile techniques

Online social networks have become indispensable in modern life, facilitating knowledge sharing, social communication, and business marketing. To gain a deeper understanding of individuals' behavior within social networks, researchers have undertaken essential analytical tasks such as change point detection. Recently, nonparametric change point detection methods have attracted researchers' attention due to their generality and flexibility. However, existing methods exhibit limitations, including overlooking network structure, reliance on case-based network attributes, and neglecting the dynamic nature of data, which may have correlations in evolving social networks. In this study, we propose a novel multivariate mixed-effects nonparametric profile control (MENPC) algorithm to address these limitations. The advantage of MENPC relies on its unique point of view in approaching network data, where it incorporates the dynamic nature of data into the monitoring process without assuming internal independence of networks over time. Additionally, it takes into account the network structure by considering both nodal and network-level attributes. Furthermore, by introducing an updating trick formula, the proposed algorithm simplifies computations, effectively balancing memory and speed for online monitoring. We evaluate the effectiveness of MENPC through comprehensive numerical experiments using the degree correlated stochastic block model to simulate interactions in evolving online social networks. The results demonstrate MENPC's superior performance in terms of expected detection delay, showcasing its accuracy and efficiency in comparison to competing approaches including Wilson, and eigenvalue methods. Applying MENPC to the Enron email network dataset further confirms its significant progress in social network monitoring, expanding its potential for various applications.

Estimating changepoints in extremal dependence, applied to aviation stock prices during COVID-19 pandemic

The dependence in the tails of the joint distribution of two random variables is generally assessed using χ-measure, the limiting conditional probability of one variable being extremely high given the other variable is also extremely high. This work is motivated by the structural changes in χ-measure between the daily rate of return (RoR) of the two Indian airlines, IndiGo and SpiceJet, during the COVID-19 pandemic. We model the daily maximum and minimum RoR vectors (potentially transformed) using the bivariate Hüsler-Reiss (BHR) distribution. To estimate the changepoint in the χ-measure of the BHR distribution, we explore two changepoint detection procedures based on the Likelihood Ratio Test (LRT) and Modified Information Criterion (MIC). We obtain critical values and power curves of the LRT and MIC test statistics for low through high values of χ-measure. We also explore the consistency of the estimators of the changepoint based on LRT and MIC numerically. In our data application, for RoR maxima and minima, the most prominent changepoints detected by LRT and MIC are close to the announcement of the first phases of lockdown and unlock, respectively, which are realistic; thus, our study would be beneficial for portfolio optimization in the case of future pandemic situations.

Assessing drought in Turkish basins through satellite observations

AbstractDrought occurs when there is a sustained decrease in rainfall over an extended period, impacting the socio‐cultural and environmental aspects of humans and other living beings. The geographic distribution and timing of droughts play a crucial role in drought management and mitigation strategies. Identifying and predicting the onset of droughts in specific regions, especially in watershed areas, is a primary concern in the field of hydrology. This study focuses on how the spatiotemporal patterns of drought are developing in Turkish Basins using detailed data on Terrestrial Water Storage (TWS), precipitation, and temperature at the pixel level. GRACE (Gravity Recovery and Climate Experiment), PERSIANN (Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks), and WorldClim (World Climate) data sets are employed to assess long‐term changes of drought on a basin‐scale. Spatial analyses are conducted in a Geographic Information System (GIS) environment for the derivation of basinal monthly mean, minimum, and maximum statistics of TWS, precipitation, and temperature anomalies within Turkish Basins. Time series analyses are implemented to investigate the temporal evolution of droughts in these basins, for the basinal monthly mean, minimum, and maximum statistics obtained. The Mann–Kendall trend test and Pettitt change point detection tests are used to assess the statistical significance of the calculated trends and to expose the existence of any change point therein, respectively. The findings of the study indicate that Turkiye faces a significant risk of drought development in nearly all its basins, particularly after 2016. The GRACE dataset provides realistic insights into the temporal behaviour of hydrological droughts. PERSIANN is effective in identifying years with extreme meteorological conditions, and the standardized precipitation index (SPI) shows similar effectiveness, while they are ineffective in exposing significant trends due to the nature of the precipitation data. WorldClim data proves insufficient for modelling the temporal behaviour of droughts in these basins.

Change Point Detection in Length-Biased Weibull Distribution for Random Censored Data Based on Modified Information Criterion

Change Point Detection in Length-Biased Weibull Distribution for Random Censored Data Based on Modified Information Criterion

Some clustering-based change-point detection methods applicable to high dimension, low sample size data

Detection of change-points in a sequence of high dimensional observations is a challenging problem, and this becomes even more challenging when the sample size (i.e., the sequence length) is small. In this article, we propose some change-point detection methods based on clustering, which can be conveniently used in such high dimension, low sample size situations. First, we consider the single change-point problem. Using k-means clustering based on a suitable dissimilarity measures, we propose some methods for testing the existence of a change-point and estimating its location. High dimensional behavior of these proposed methods are investigated under appropriate regularity conditions. Next, we extend our methods for detection of multiple change-points. We carry out extensive numerical studies and analyze a real data set to compare the performance of our proposed methods with some state-of-the-art methods.