Change-point Model Research Articles

A recent surge in global warming is not detectable yet

The global mean surface temperature is widely studied to monitor climate change. A current debate centers around whether there has been a recent (post-1970s) surge/acceleration in the warming rate. Here we investigate whether an acceleration in the warming rate is detectable from a statistical perspective. We use changepoint models, which are statistical techniques specifically designed for identifying structural changes in time series. Four global mean surface temperature records over 1850–2023 are scrutinized within. Our results show limited evidence for a warming surge; in most surface temperature time series, no change in the warming rate beyond the 1970s is detected despite the breaking record temperatures observed in 2023. As such, we estimate the minimum changes in the warming trend required for a surge to be detectable. Across all datasets, an increase of at least 55% is needed for a warming surge to be detectable at the present time.

UBEM calibration method by energy consumption disaggregation using a change-point model

Urban Building Energy Modeling (UBEM) is valuable for analyzing urban energy demand, but uncertainties can create gaps between predictions and actual usage. Calibration often uses utility bill data due to its urban-scale accessibility. However, comparing this data with simulation results for specific energy uses like cooling and heating is challenging. This study introduces a UBEM calibration method using a change-point model to disaggregate energy into heating, cooling, and base load. Applied to 222 office buildings in Seoul, this method provided more appropriate calibration results by considering individual energy consumption characteristics rather than just total consumption. The CVRMSE for base load, heating, and cooling energy decreased compared to uncalibrated simulations. This research highlights the importance of energy disaggregation when calibrating UBEM with utility bill data, offering a more nuanced approach to urban energy modeling.

Stepwise updating of probabilities is neither universal nor fully explained by motor costs.

Often our expectations are set by sampling many times from the same distribution. When that distribution changes, so should our expectations. If we want to decide whether to take our umbrella today we need to have tracked, and updated, our estimate of the probability of rain by reference to recent temperatures and precipitation. Under debate is whether we update our mental estimates of probabilities given each new incoming piece of evidence or whether we stick with a current estimate until it becomes clearly in need of change. Previous research has suggested that participant estimates of running probabilities are not updated on every trial, but only intermittently. This has been used to support change-point models of probability updating. However, such a pattern could also be explained by the way common laboratory procedures impose a motor cost to update the probability report. This study was designed to remove the motor confound. Our procedure required similar motor actions for both changing and maintaining one's probability estimate. At a group level, motor cost did affect updating frequency and removing the default response option encouraged more frequent updating. However, intermittent updating response patterns did not disappear completely. Despite this equivalence in response effort, some participants, even when forced to make a new estimate on every trial, continued to update rarely while other participants meticulously updated every trial. We conclude deliberate updating frequency is heterogenous but intermittent updating is not simply an artifact of motor cost.

Perpetual step-like restructuring of hippocampal circuit dynamics

Representation of the environment by hippocampal populations is known to drift even within a familiar environment, which could reflect gradual changes in single-cell activity or result from averaging across discrete switches of single neurons. Disambiguating these possibilities is crucial, as they each imply distinct mechanisms. Leveraging change point detection and model comparison, we find that CA1 population vectors decorrelate gradually within a session. In contrast, individual neurons exhibit predominantly step-like emergence and disappearance of place fields or sustained changes in within-field firing. The changes are not restricted to particular parts of the maze or trials and do not require apparent behavioral changes. The same place fields emerge, disappear, and reappear across days, suggesting that the hippocampus reuses pre-existing assemblies, rather than forming new fields de novo. Our results suggest an internally driven perpetual step-like reorganization of the neuronal assemblies.

Data-driven analysis of heating and cooling base temperatures for buildings: Case studies in South Korea

To investigate statistical differences in the heating (Tbh) and cooling base temperatures (Tbc) across various building types, vintages, and sizes, we conducted case studies in Seoul, South Korea, based on data from more than 10,000 buildings. To assess the relative impacts of internal and external loads on Tbh and Tbc, we used a core-to-perimeter zone ratio approximated by the average floor area, defined as the floor area per building floor. Employing the energy signature method, change-point regression, and calendarization, we determined the best-fit change-point model and the corresponding Tbh and Tbc for each building. Our findings revealed statistically significant differences in Tbhs and Tbcs, with variations of up to 6 and 4 °C, respectively, across six building types. Notably, for most building types, Tbh and Tbc decreased as the average floor area increased, possibly influenced by a higher core zone to total area ratio. This highlights the predominant impact of internal loads over external loads. The influence of the average floor area on Tbh and Tbc outweighed that of building vintage, particularly for lodging, medical, and sales facilities, where Tbh and Tbc decreased in the more recent vintage buildings. However, this influence was less pronounced for facilities for senior citizens and children and education and research facilities, possibly due to factors such as diverse building shapes and the thermal preferences of occupants. Although this study focuses on South Korea, our data-driven approach provides statistical evidence for refining base temperature and improving traditional degree-day methods. Our findings suggest the need to establish base temperatures that consider various building types, vintages, and average floor areas, especially for large metropolitan cities where these factors vary widely.

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.

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.

The multivariate Bernoulli detector: change point estimation in discrete survival analysis.

Time-to-event data are often recorded on a discrete scale with multiple, competing risks as potential causes for the event. In this context, application of continuous survival analysis methods with a single risk suffers from biased estimation. Therefore, we propose the multivariate Bernoulli detector for competing risks with discrete times involving a multivariate change point model on the cause-specific baseline hazards. Through the prior on the number of change points and their location, we impose dependence between change points across risks, as well as allowing for data-driven learning of their number. Then, conditionally on these change points, a multivariate Bernoulli prior is used to infer which risks are involved. Focus of posterior inference is cause-specific hazard rates and dependence across risks. Such dependence is often present due to subject-specific changes across time that affect all risks. Full posterior inference is performed through a tailored local-global Markov chain Monte Carlo (MCMC) algorithm, which exploits a data augmentation trick and MCMC updates from nonconjugate Bayesian nonparametric methods. We illustrate our model in simulations and on ICU data, comparing its performance with existing approaches.

Random change point model with an application to the China Household Finance Survey

Random change point model with an application to the China Household Finance Survey

Using seasonal oscillations in fin ray microchemistry to chemically age Lake Sturgeon

AbstractObjectiveNonlethally sampled pectoral fin rays are commonly used as aging structures for Lake Sturgeon Acipenser fulvescens, but they tend to underestimate the true age in older, slow‐growing individuals (age > 14 years). Current aging practices involve counting bands along the structure, which are construed as annuli. Oscillations of certain trace elements corresponding with annuli have been seen across various fish species, with patterns continuing to the marginal edge of hard structures. This study explored the aging of fin rays by using microchemistry patterns in Lake Sturgeon of known age (n = 94; ages 5–21) to determine the potential use of this method as an alternative or supplementary aging technique.MethodsElements were chosen for age determination analysis by examining the relationship between profile minima/maxima and visually interpreted annuli. Fish were assigned ages using three different methods: (1) traditional interpretation (counting annuli along the structure), (2) chemical interpretation (examination of seasonal variations in elemental profiles with visually identified annuli), and (3) a statistical model (multivariate multiple changepoint analysis with finite differencing using raw elemental profiles).ResultMean absolute differences between age estimates and known age were significantly higher for the traditional interpretation method than for the chemical interpretation method. The mean coefficient of variation in estimated age was 11.14% for the traditional interpretation method and 4.04% for the chemical interpretation method. The changepoint model was able to correctly classify age for 100% of the samples within ±1 year in one population (ages 5–8) but could not classify samples from the second population (ages 12–21).ConclusionOur results suggest that chemical aging techniques could provide more reliable age estimates for juvenile and subadult Lake Sturgeon when fin rays are the only aging option. Further work is required to determine the applicability of the model for assigning ages to older fish and for use with different populations and structures.

The consistency for CUSUM estimator of mean change-point model based on association

The consistency for CUSUM estimator of mean change-point model based on association

A Bayesian Change Point Model for Dynamic Alternative Transcription Start Site Usage During Cellular Differentiation.

ABSTRACT An alternative transcription start site (ATSS) is a major driving force for increasing the complexity of transcripts in human tissues. As a transcriptional regulatory mechanism, ATSS has biological significance. Many studies have confirmed that ATSS plays an important role in diseases and cell development and differentiation. However, exploration of its dynamic mechanisms remains insufficient. Identifying ATSS change points during cell differentiation is critical for elucidating potential dynamic mechanisms. For relative ATSS usage as percentage data, the existing methods lack sensitivity to detect the change point for ATSS longitudinal data. In addition, some methods have strict requirements for data distribution and cannot be applied to deal with this problem. In this study, the Bayesian change point detection model was first constructed using reparameterization techniques for two parameters of a beta distribution for the percentage data type, and the posterior distributions of parameters and change points were obtained using Markov Chain Monte Carlo (MCMC) sampling. With comprehensive simulation studies, the performance of the Bayesian change point detection model is found to be consistently powerful and robust across most scenarios with different sample sizes and beta distributions. Second, differential ATSS events in the real data, whose change points were identified using our method, were clustered according to their change points. Last, for each change point, pathway and transcription factor motif analyses were performed on its differential ATSS events. The results of our analyses demonstrated the effectiveness of the Bayesian change point detection model and provided biological insights into cell differentiation.

A Method of Reliability Assessment Based on Trend Analysis for Open Source Software

Software reliability growth model (SRGM) is used as one of the reliability assessment methods to assess the software reliability. In SRGM, the degree of reliability growth may fluctuate greatly according to change in the internal state of the software. It is called the change point (CP). Several researchers proposed the SRGM considering CP. In the open source software (OSS), there are many projects that continue development even after the software is released. Therefore, major updates with breaking changes may occur in it. The major updates can be a factor that causes a CP because it greatly changes the internal state of the OSS. This paper focuses on the relationship between CP and software updates. We collect OSS fault data from a bug tracking system. Moreover, we examine the behavior of SRGM before and after software updates. Furthermore, we discuss the applicability of SRGM for CP in OSS. Also, we compare the proposed model based on CP with the model without CP. As a result, we have confirmed that the SRGM can evaluate the reliability in the environment with major updates. Moreover, the proposed method performs better than without considering CP model. Especially, the exponential model’s mean value function is the suitable method to assess the OSS reliability for the proposed method.

Microalgal assemblages response to water quality remediation in coastal waters of Perth, Australia

Nutrient reduction is an essential environmental policy for water quality remediation, but climate change can offset the ecological benefits of nutrient reduction and lead to the difficulty of environmental evaluation. Here, based on the records of three lipid microalgal biomarkers and stable isotopes of carbon and nitrogen in two sediment cores from the embayment of Perth, Australia, we reconstructed the microalgal biomasses (diatoms, dinoflagellates and coccolithophores) over the past century and evaluated the ecological effects of nutrient reduction on them, using Change Point Modeling (CPM) and redundancy analysis (RDA). The CPM result showed that total microalgal biomarkers increased by 25% and 51% in deep and shallow areas, respectively, due to nutrient enrichment caused by industrial wastewater in the 1950s and the causeway construction in the 1970s, and dinoflagellates were beneficiaries of eutrophication. The nutrient reduction policy since the 1980s had not decreased total microalgal biomass, and diatoms were beneficiaries of this period. RDA based on time series of sediment cores and water monitoring data revealed that the increase of sea-surface temperature and the decrease of rainfall since the 1980s may be important factors sustaining the high total microalgal biomass and increasing the degree of diatom dominance. The result also indicated that the variations of microalgal assemblages may better explain the effect of nutrient reduction rather than total microalgal biomass.

The Bitemporal Lens Model-toward a holistic approach to chronic disease prevention with digital biomarkers.

We introduce the Bitemporal Lens Model, a comprehensive methodology for chronic disease prevention using digital biomarkers. The Bitemporal Lens Model integrates the change-point model, focusing on critical disease-specific parameters, and the recurrent-pattern model, emphasizing lifestyle and behavioral patterns, for early risk identification. By incorporating both the change-point and recurrent-pattern models, the Bitemporal Lens Model offers a comprehensive approach to preventive healthcare, enabling a more nuanced understanding of individual health trajectories, demonstrated through its application in cardiovascular disease prevention. We explore the benefits of the Bitemporal Lens Model, highlighting its capacity for personalized risk assessment through the integration of two distinct lenses. We also acknowledge challenges associated with handling intricate data across dual temporal dimensions, maintaining data integrity, and addressing ethical concerns pertaining to privacy and data protection. The Bitemporal Lens Model presents a novel approach to enhancing preventive healthcare effectiveness.

A sequential feature selection approach to change point detection in mean-shift change point models

A sequential feature selection approach to change point detection in mean-shift change point models

Piecewise Linear Multiple Change Point Modelling for Under-Five Child Mortality

Using a piecewise linear multiple change-point model instead of more traditional survival techniques is more beneficial when dealing with mortality data. Utilizing this technique, the hazard model is estimated and the number of cut-point locations is found. Using various covariates, such as sociodemographic, biological, and proximate co-factors, this piecewise hazard model is fitted to the Infant Mortality Data of Bangladesh Demographic and Health Survey 2014. Finding the change point and the impact of covariates on the hazard rate is done using the maximum likelihood estimation process. The parameter's significance is subsequently supported by the Wald test statistic. It turns out that the mother's educational status, religion, mother's age in years, the number of children they have ever had, currently breastfeeding, the size of the child, desire for more children, cesarean delivery, ANC visits, and birth orders are all significant factors. It is also discovered that the detected change point of the hazard rate is extremely important for the child until they reach the age of five. Through the various time cut points, it is found that a piecewise linear multiple change-point model is very important for under-five child mortality. Public health specialists, researchers, and clinicians can all benefit from this piecewise hazard model. One of the most crucial elements in lowering child mortality is time.

Likelihood ratios for changepoints in categorical event data with applications in digital forensics.

We investigate likelihood ratio models motivated by digital forensics problems involving time-stamped user-generated event data from a device or account. Of specific interest are scenarios where the data may have been generated by a single individual (the device/account owner) or by two different individuals (the device/account owner and someone else), such as instances in which an account was hacked or a device was stolen before being associated with a crime. Existing likelihood ratio methods in this context require that a precise time is specified at which the device or account is purported to have changed hands (the changepoint)-this is the known changepoint likelihood ratio model. In this paper, we develop a likelihood ratio model that instead accommodates uncertainty in the changepoint using Bayesian techniques, that is, an unknown changepoint likelihood ratio model. We show that the likelihood ratio in this case can be calculated in closed form as an expression that is straightforward to compute. In experiments with simulated changepoints using real-world data sets, the results demonstrate that the unknown changepoint model attains comparable performance to the known changepoint model that uses a perfectly specified changepoint, and considerably outperforms the known changepoint model that uses a misspecified changepoint, illustrating the benefit of capturing uncertainty in the changepoint.

Bayesian and deep-learning models applied to the early detection of ovarian cancer using multiple longitudinal biomarkers.

Ovarian cancer is the most lethal of all gynecological cancers. Cancer Antigen 125 (CA125) is the best-performing ovarian cancer biomarker which however is still not effective as a screening test in the general population. Recent literature reports additional biomarkers with the potential to improve on CA125 for early detection when using longitudinal multimarker models. Our data comprised 180 controls and 44 cases with serum samples sourced from the multimodal arm of UK Collaborative Trial of Ovarian Cancer Screening (UKCTOCS). Our models were based on Bayesian change-point detection and recurrent neural networks. We obtained a significantly higher performance for CA125-HE4 model using both methodologies (AUC 0.971, sensitivity 96.7% and AUC 0.987, sensitivity 96.7%) with respect to CA125 (AUC 0.949, sensitivity 90.8% and AUC 0.953, sensitivity 92.1%) for Bayesian change-point model (BCP) and recurrent neural networks (RNN) approaches, respectively. One year before diagnosis, the CA125-HE4 model also ranked as the best, whereas at 2 years before diagnosis no multimarker model outperformed CA125. Our study identified and tested different combination of biomarkers using longitudinal multivariable models that outperformed CA125 alone. We showed the potential of multivariable models and candidate biomarkers to increase the detection rate of ovarian cancer.

Uncertainty Quantification for Data-Driven Change-Point Learning via Cross-Validation

Accurately detecting multiple change-points is critical for various applications, but determining the optimal number of change-points remains a challenge. Existing approaches based on information criteria attempt to balance goodness-of-fit and model complexity, but their performance varies depending on the model. Recently, data-driven selection criteria based on cross-validation has been proposed, but these methods can be prone to slight overfitting in finite samples. In this paper, we introduce a method that controls the probability of overestimation and provides uncertainty quantification for learning multiple change-points via cross-validation. We frame this problem as a sequence of model comparison problems and leverage high-dimensional inferential procedures. We demonstrate the effectiveness of our approach through experiments on finite-sample data, showing superior uncertainty quantification for overestimation compared to existing methods. Our approach has broad applicability and can be used in diverse change-point models.