Advanced Analytics for Train Delay Prediction Systems by Including Exogenous Weather Data

Oneto, Luca; Fumeo, Emanuele; Clerico, Giorgio; Canepa, Renzo; Papa, Federico; Dambra, Carlo; Mazzino, Nadia; Anguita, Davide

doi:10.1109/dsaa.2016.57

Cited by 32 publications

(18 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several analytical approaches, including correlation analysis, causal analysis (e.g., principal component), time series analysis, and ML techniques (e.g., SVM), are applied to learn rules automatically and build failure prediction models. Oneto et al [66] proposed a train delay prediction system (TDPS) using ML to predict delays, considering exogenous weather data. The model can be further improved by including data from exogenous sources, particularly on the weather information provided by national weather services.…”

Section: C: MLmentioning

confidence: 99%

“…Most recently, the shallow and deep extreme learning machine (DELM) was proposed, along with the rapid development of big data technologies. Oneto et al [20], [66] presented a data-driven TDPS for a large-scale railway network to provide useful information to RTC processes by using state-of-the-art tools and techniques; this system can extract information from a large amount of historical train movement data using the most recent big data technologies, learning algorithms, and statistical tools. The described approach and prediction system have been validated on the basis of real historical data in six months.…”

Section: B: Gmmentioning

confidence: 99%

See 1 more Smart Citation

Train Dispatching Management With Data- Driven Approaches: A Comprehensive Review and Appraisal

Wen

Huang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Train dispatching (TD) is at the forefront of all rail operations that transport passengers or goods. Recent technological advances and the explosion of digital data have introduced data-driven methods (DDMs) in rail operations. In this study, DDMs on the TD problem are briefly explored, focusing on relevant studies on delay distribution, delay propagation, and timetable rescheduling. Data-driven TD methods, including statistical methods (SM), graphical models (GM), and machine learning (ML) methods are reviewed. Then, key issues in establishing different data-driven models for the TD problem are addressed. Subsequently, ML methods are considered to be among the most promising DDMs that lead to innovative TD methods, relying on rich data obtained from train operations. This study emphasizes the potentials for designing new alternatives in the three key fields of interest and provides directions for further research on TD. Future research, including the ML-driven TD and intelligent TD, were discussed in this study. INDEX TERMS Data-driven, delay distribution, delay propagation, timetable rescheduling, train dispatching, machine learning.

show abstract

Section: C: MLmentioning

confidence: 99%

Section: B: Gmmentioning

confidence: 99%

Train Dispatching Management With Data- Driven Approaches: A Comprehensive Review and Appraisal

Wen

Huang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Network Rail has utilized Deloitte's suite of cloudbased analytics tools to provide real-time timetable information for timetable management [165]. The development of advanced analytics for train delay prediction using exogenous data is provided by Oneto et al [166] where multivariate statistical concepts are implemented using big data analytics tools, and improvements in train delay prediction using advanced data analytics including multivariate statistics over traditional delay prediction methods are discussed. Further work is suggested for inclusion of railway asset condition data to improve prediction accuracy.…”

Section: E Big Data Analytics Tool Selection and Challengesmentioning

confidence: 99%

Requirements for Big Data Adoption for Railway Asset Management

2020

View full text Add to dashboard Cite

Nowadays, huge amounts of data have been captured along with the day-today operation of assets including railway systems. Hence, we have come to the era of big data. The utilization of big data technologies for asset condition information management is becoming indispensable for improving asset management decision making. The vital information such as precursor information collected on failure modes and knowledge that may be available for analysis is hidden within the large extent of data. There are analysis tools incorporated with techniques such as multiple regression analysis and machine learning that are facilitated by the availability of big data. Therefore, the utilization of big data technologies for asset condition information management is becoming indispensable for improving asset management decision making. This paper provides a review of the requirements and challenges for big data analytics applications to railway asset management. The review focuses on railway asset data collection, data management, data applications with the implementation of Blockchain technology as well as big data analytics technologies. The need for, and the importance of big data analytics in railway asset management; and the requirement for the asset condition data collection in the railway industry are highlighted. Research challenges in railway asset management via application of big data analytics are identified and the future research directions are presented. INDEX TERMS Big data analytics, asset management, railway, data management, blockchain.

show abstract

“…The results of this process is the availability of a huge amount of historical and real-time data (Linoff & Berry, 2011). Recently, industries have realized that these data, despite their management costs, can be considered as an opportunity to improve their business since historical information can be adopted to create new services or improve the quality of their products (Linoff & Berry, 2011;Oneto et al, 2016b). In particular, they can leverage this huge amount of data thanks to the DMMs which can rapidly and effectively extract useful and actionable information (Witten et al, 2016).…”

Section: Introductionmentioning

confidence: 99%

Condition-Based Maintenance of Naval Propulsion Systems with supervised Data Analysis

et al. 2018

Self Cite

View full text Add to dashboard Cite

The behavior and interaction of the main components of Ship Propulsion Systems cannot be easily modeled with a priori physical knowledge, considering the large amount of variables influencing them. Data-Driven Models (DDMs), instead, exploit advanced statistical techniques to build models directly on the large amount of historical data collected by on-board automation systems, without requiring any a priori knowledge. DDMs are extremely useful when it comes to continuously monitoring the propulsion equipment and take decisions based on the actual condition of the propulsion plant. In this paper, the authors investigate the problem of performing Condition-Based Maintenance through the use of DDMs. In order to conceive this purpose, several state-of-the-art supervised learning techniques are adopted, which require labeled sensor data in order to be deployed. A naval vessel, characterized by a combined diesel-electric and gas propulsion plant, has been exploited to collect such data and show the effectiveness of the proposed approaches. Because of confidentiality constraints with the Navy the authors used a real-data validated simulator and the dataset has been published for free use through the UCI repository.

show abstract

Advanced Analytics for Train Delay Prediction Systems by Including Exogenous Weather Data

Cited by 32 publications

References 45 publications

Train Dispatching Management With Data- Driven Approaches: A Comprehensive Review and Appraisal

Train Dispatching Management With Data- Driven Approaches: A Comprehensive Review and Appraisal

Requirements for Big Data Adoption for Railway Asset Management

Condition-Based Maintenance of Naval Propulsion Systems with supervised Data Analysis

Contact Info

Product

Resources

About