Unsupervised Offline Changepoint Detection Ensembles

Katser, Iurii; Kozitsin, Viacheslav; Lobachev, Victor; Maksimov, Ivan

doi:10.3390/app11094280

Cited by 9 publications

(5 citation statements)

References 42 publications

(73 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The goal was to identify changes in the time series. Thus, to solve this changepoint detection problem, the standard deviation was used as a cost function (Katser et al, 2021). The content consumer behavior pattern has a cycle of a week, thus the standard deviation was calculated for 7 and 14 days.…”

Section: Engagement Windowmentioning

confidence: 99%

A data‐driven approach to improve online consumer subscriptions by combining data visualization and machine learning methods

Fernandes,

Moro,

Cortez

2024

Int J Consumer Studies

View full text Add to dashboard Cite

Effective online consumer research helps companies on defining a successful strategy to increase user loyalty and shape brand engagement. Digital innovation introduced a dramatic change in businesses, particularly in the online news industry. Content consumers have a wide offer across different channels which increase the digital challenge for online news media companies to retain their readers and convert them into online subscribers. Furthermore, digital news publishers often strive to balance revenue sources in online business models. Thus, this study fills a gap in the literature on media consumer research by proposing a data‐driven approach that combines two machine learning (ML) models to allow managers dynamically improve their marketing and editorial strategies. Firstly, the authors present an online user profiling to identify consumer segments based on the interplay between several engagement’ variables substantiated in the literature research. Second, as few studies have explored the factors influencing users' intention to pay for such services, the eXtreme Gradient Boosting ML algorithm identifies the predictors of consumer's willingness to pay. Third, a dashboard presents the key performance indicators across the audience funnel. Thus, practical implications and business suggestions are presented in a two‐fold strategy to maximize revenue from digital subscriptions and advertising. Findings provide new insights into an engagement approach and the relation to acquire a digital subscription in online content platforms. We believe that the provided recommendations are potentially useful to help marketing and editorial teams to manage their customer engagement process across the funnel in a more efficient way.

show abstract

Section: Engagement Windowmentioning

confidence: 99%

A data‐driven approach to improve online consumer subscriptions by combining data visualization and machine learning methods

Fernandes,

Moro,

Cortez

2024

Int J Consumer Studies

View full text Add to dashboard Cite

show abstract

“…Brunello et al [70] created syntax trees that utilized bounded signal temporal logic statement. The trees were altered using an evolutionary approach to predict failure in Blackblaze Hard Drive [105], Tennessee Eastman Process [123], and CMAPSS [69] datasets, commononly used datasets for PdM of hard drives, electrical processes and turbofans. This method led to great performance with rulebased explanations.…”

Section: ) Rule-based Explainersmentioning

confidence: 99%

Explainable Predictive Maintenance: A Survey of Current Methods, Challenges and Opportunities

Cummins,

Sommers,

Ramezani

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Predictive maintenance is a well studied collection of techniques that aims to prolong the life of a mechanical system by using artificial intelligence and machine learning to predict the optimal time to perform maintenance. The methods allow maintainers of systems and hardware to reduce financial and time costs of upkeep. As these methods are adopted for more serious and potentially life-threatening applications, the human operators need trust the predictive system. This attracts the field of Explainable AI (XAI) to introduce explainability and interpretability into the predictive system. XAI brings methods to the field of predictive maintenance that can amplify trust in the users while maintaining well-performing systems. This survey on explainable predictive maintenance (XPM) discusses and presents the current methods of XAI as applied to predictive maintenance while following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines. We categorize the different XPM methods into groups that follow the XAI literature. Additionally, we include current challenges and a discussion on future research directions in XPM.

show abstract

“…Considering that each algorithm produces different change points, we can benefit from them all by combining them using the union operator suggested by Ref. 44 to generate an unsupervised ensemble CPD method; however, these points must be checked before entering the union operator.…”

Section: Multi-temporal Sugar Beet Anomaly Detectionmentioning

confidence: 99%

Cercospora leaf spot detection in sugar beets using high spatio-temporal unmanned aerial vehicle imagery and unsupervised anomaly detection methods

Noroozi,

Shah-Hosseini

2024

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

Early disease detection is required, considering the impacts of diseases on crop yield. However, current methods involve labor-intensive data collection. Thus, unsupervised anomaly detection in time series imagery was proposed, requiring high-resolution unmanned aerial vehicle (UAV) imagery and sophisticated algorithms to identify unknown anomalies amidst complex data patterns to cope with within season crop monitoring and background challenges. The dataset used in this study was acquired by a Micasense Altum sensor on a DJI Matrice 210 UAV with a 4 mm resolution in Gottingen, Germany. The proposed methodology includes (1) date selection for finding the date sensitive to sugar beet changes, (2) vegetation index (VI) selection for finding the one sensitive to sugar beet and its temporal patterns by visual inspection, (3) sugar beet extraction using thresholding and morphological operator, and (4) an ensemble of bottom-up, Kernel, and quadratic discriminate analysis methods for unsupervised time series anomaly detection. The study highlighted the importance of the wide-dynamic-range VI and morphological filtering with time series trimming for accurate disease detection while reducing background errors, achieving a kappa of 76.57%, comparable to deep learning model accuracies, indicating the potential of this approach. Also, 81 days after sowing, image acquisition could begin for cost and time efficient disease detection.

show abstract

Unsupervised Offline Changepoint Detection Ensembles

Cited by 9 publications

References 42 publications

A data‐driven approach to improve online consumer subscriptions by combining data visualization and machine learning methods

A data‐driven approach to improve online consumer subscriptions by combining data visualization and machine learning methods

Explainable Predictive Maintenance: A Survey of Current Methods, Challenges and Opportunities

Cercospora leaf spot detection in sugar beets using high spatio-temporal unmanned aerial vehicle imagery and unsupervised anomaly detection methods

Contact Info

Product

Resources

About