Big Data and Natural Language Processing for Analysing Railway Safety

Due to modern powerful computing and the explosion in data availability and advanced analytics, there should be opportunities to use a Big Data approach to proactively identify high risk scenarios on the railway. In this chapter, we comprehend the need for developing machine intelligence to identify heightened risk on the railway. In doing so, we have explained a potential for a new data driven approach in the railway, we then focus the rest of the chapter on Natural Language Processing (NLP) and its potential for analysing accident data. We review and analyse investigation reports of railway accidents in the UK, published by the Rail Accident Investigation Branch (RAIB), aiming to reveal the presence of entities which are informative of causes and failures such as human, technical and external. We give an overview of a framework based on NLP and machine learning to analyse the raw text from RAIB reports which would assist the risk and incident analysis experts to study causal relationship between causes and failures towards the overall safety in the rail industry.

Study and Analysis of Delay Factors of Delhi Metro Using Data Sciences and Social Media

Delhi Metro passengers had a difficult time mostly on Monday morning as trains on the busy corridors are delayed due to technical problems or track circuit failure. This study found different factors like power failure, weather, rider load, festive season, etc. which are responsible for the delay of Delhi Metro. Due to these factors, Metro got delayed and run at a reduced speed causing much inconvenience to the people, who are hoping to reach their offices on time. Delhi Metro data are received from different sources which may be structured (timings, speed, traffic), semi-structured (images and video) and unstructured (maintenance records) form. So, there is heterogeneity in data. Except for this data, the feedback or suggestion of a rider is vital to the system. Nowadays riders are using social media like Facebook and Twitter very frequently. Three-tier architecture is proposed for the delay analysis of Delhi Metro. Different implementation techniques are studied and proposed for the social media module and delay prediction modules for the proposed system.

Predicting Behavior of Passengers Using Data Collected Through Smart Cards

Many attempts have been made to derive insights and any useful information about the behavior of the passengers traveling using different data analytics approaches and techniques. The different ways the researchers have tried to model the travel behavior and also their attempt to measure the behavioral changes at an individual level will be discussed in this chapter. The insights derived using these methods can help policy makers and the authorities to make necessary and important changes to the railways. The transit systems of the Railways provide us with the data, which is analysed using different techniques and methodologies and derived insights from.

Big Data Analytics for Train Delay Prediction

Current Train Delay Prediction Systems (TDPSs) do not take advantage of state-of-the-art tools and techniques for extracting useful insights from large amounts of historical data collected by the railway information systems. Instead, these systems rely on static rules, based on classical univariate statistic, built by experts of the railway infrastructure. The purpose of this book chapter is to build a data-driven TDPS for large-scale railway networks, which exploits the most recent big data technologies, learning algorithms, and statistical tools. In particular, we propose a fast learning algorithm for Shallow and Deep Extreme Learning Machines that fully exploits the recent in-memory large-scale data processing technologies for predicting train delays. Proposal has been compared with the current state-of-the-art TDPSs. Results on real world data coming from the Italian railway network show that our proposal is able to improve over the current state-of-the-art TDPSs.

Application of Big Data Technologies for Quantifying the Key Factors Impacting Passenger Journey in a Multi-Modal Transportation Environment

Transportation systems are designed to run in normal conditions. The occurrence of planned works, unscheduled major events or disturbances can affect the transportation services that intended to provide and as a result, the disruptive nature may have a significant impact on the operation of the transport modes. This chapter focuses on the impact of disruptions in the multimodal transportation using the available open data. The enablers (key variables) of the datasets are taken into account to evaluate the service performance of each transport mode and its influence on other transport modes in case of disturbances. The high-volume, streaming data collected for a long time is a good potential use case for applying text mining techniques on big data. This chapter provides an insight into research being carried out for developing capabilities to store and analyze multi-modal data feeds for predictive analysis.

Social Media as a Tool to Understand Behaviour on the Railways

Social media plays an increasing role in how passengers communicate to, and about, train operators. In response, train operators and other rail stakeholders are adopting social media to contact their users. There are a number of opportunities for tapping this big data information stream through the overt use of technology to analyse, filter and present social media, including filtering for operational staff, or sentiment mapping for strategy. However, this analysis is predicated on a number of assumptions regarding the manner in which social media is currently being used within a railway context. In the following chapter, we present data from studies of rail social media that shed light on how big data analysis of social media exchange can support the passenger. These studies highlight important factors such as the broad range of issues covered by social media (not just disruption), the idiosyncrasies of individual train operators that need to be taken into account within social media analysis, and the time critical nature of information during disruption.

Blockchains

In recent years, the UK railway industry has struggled with the effects of poor integration of data across ICT systems, particularly when that data is being used across organizational boundaries. Technical progress is being made by the industry towards enabling data sharing, but an open issue remains around how the costs of gathering and maintaining pooled information can be fairly attributed across the stakeholders who draw on that shared resource. This issue is particularly significant in areas such as Remote Condition Monitoring, where the ability to analyse the network at a whole-systems level is being blocked by the business cases around the purchase of systems as silos. Blockchains are an emerging technology that have the potential to revolutionize the management of transactions in a number of industrial sectors. This chapter will address the outstanding issues around the fair attribution of costs and benefits of data sharing in the rail industry by proposing blockchains as a forth enabler of the rail data revolution, alongside ESB, ontology, and open data.

Scalable Software Framework for Real-Time Data Processing in the Railway Environment

To this day, railway actors obtain information by actively hunting for relevant data in various places. Despite the availability of a variety of travel-related data sources, accurate delivery of relevant, timely information to these railway actors is still inadequate. In this chapter, we present a solution in the form of a scalable software framework that can interface with almost any type of (open) data. The framework aggregates a variety of data sources to create tailor-made knowledge, personalised to the dynamic profiles of railway users. Core functionality, including predefined non-functional support, such as load balancing strategies, is implemented in the generic base layer, on top of which a use case specific layer – that can cope with the specifics of the railway environment – is built. Data entering the framework is intelligently processed and the results are made available to railway vehicles and personal mobile devices through REST endpoints.

Evolution of Indian Railways Through IoT

Indian Railways is the largest rail network in the world, can be plays an essential role in the development of infrastructure areas such as coal, electric power, steel, concrete and other critical industries. Indian government has started concentrating on the modernization of the railways through huge investment. Internet of Things(IoT) is vital attention to expansion and excellence. The chapter will commence with the past history of rail transport in India Further section will support the IoT which is another great trend in technology. The later section of the chapter will give attention to how Internet of things could expertise the railroad industry, introducing a remedy which will be made to modernize aging sites at railroads, improve basic safety. The railway can help the passenger to utilize fewer interruptions in the event that's what they need. There's a large number of things that require to be watched and the railway can run as a completely digital service, without having to have people walking the tracks, it brings cost benefits and increased safety for the workforce.

Intelligent Transport Systems Services in VANETs and Case Study in Urban Environment

The VANET (Vehicular Ad hoc Network) is a collection of mobile nodes forming a temporary network on variable topology, operating without base station and without centralized administration. Communication is possible between vehicles within each other's radio range as well as with fixed components on road side infrastructure. The characteristics of VANET network that distinguishes it from other ad hoc networks, such as high mobility and communication with the infrastructure to support security or comfort applications, have prompted researchers to develop models and mobility specific protocols. The main goal of this chapter is firstly to compare the performance of three Ad hoc routing protocols: OLSR, AODV and DSDV, and secondly to examine the impact of varying mobility, density and pause time on the functionality of these protocols. The results of this chapter demonstrate that AODV have better performance in terms of Throughput and Packets Delivery Rate (PDR), whereas OLSR have best performance in terms of Packet Delivery Time (Delay).