Big Data Analytics for Proactively Optimizing Rolling Stock Maintenance

2019 ◽  
Author(s):  
Naji Albakay ◽  
Michael Hempel ◽  
Hamid Sharif
Keyword(s):  
Big Data ◽  
Data Analytics ◽  
Big Data Analytics ◽  
Maintenance Scheduling ◽  
Traditional Scheduling ◽  
Rolling Stock ◽  
Data Set ◽  
Wear And Tear ◽  
Maintenance Schedules ◽  
Train Safety

Rolling stock, particularly of freight railroads, is currently maintained using regular preventative and corrective maintenance schedules. This maintenance approach recommends sets of inspections and maintenance procedures based on the average expected wear and tear across their inventory. In practice, however, this approach to scheduling preventative maintenance is not always effective. When scheduled too soon, it results in a loss of operating revenue, whereas when it is scheduled too late, equipment failure could lead to costly and disastrous derailments. Instead, proactive maintenance scheduling based on Big Data Analytics (BDA) could be utilized to replace traditional scheduling, resulting in optimized maintenance cycles for higher train safety, availability, and reliability. BDA could also be used to discover patterns and relationships that lead to train failures, identify manufacturer reliability concerns, and help validate the effectiveness of operational improvements. In this work, we introduce a train inventory simulation platform that enables the modelling of different train components such as wheels, brakes, axles, and bearings. The simulator accounts for the wear and tear in each component and generates a comprehensive data set suitable for BDA that can be used to evaluate the effectiveness of different BDA approaches in discerning patterns and extracting knowledge from the data. It provides the basis for showing that BDA algorithms such as Random Forest [9] and Linear Regression can be utilized to create models for proactive train maintenance scheduling. We also show the capability of BDA to detect hidden patterns and to predict failure of train components with high accuracy.

An Effective Model for Consumer Need Prediction Using Big Data Analytics

2021 ◽  
Author(s):  
Yihao Tian
Keyword(s):  
Big Data ◽  
Consumer Behavior ◽  
Data Analytics ◽  
Big Data Analytics ◽  
Customer Behavior ◽  
Data Set ◽  
Customer Data ◽  
Demand Prediction ◽  
Management Ratio ◽  
The Veil

Big data is an unstructured data set with a considerable volume, coming from various sources such as the internet, business organizations, etc., in various formats. Predicting consumer behavior is a core responsibility for most dealers. Market research can show consumer intentions; it can be a big order for a best-designed research project to penetrate the veil, protecting real customer motivations from closer scrutiny. Customer behavior usually focuses on customer data mining, and each model is structured at one stage to answer one query. Customer behavior prediction is a complex and unpredictable challenge. In this paper, advanced mathematical and big data analytical (BDA) methods to predict customer behavior. Predictive behavior analytics can provide modern marketers with multiple insights to optimize efforts in their strategies. This model goes beyond analyzing historical evidence and making the most knowledgeable assumptions about what will happen in the future using mathematical. Because the method is complex, it is quite straightforward for most customers. As a result, most consumer behavior models, so many variables that produce predictions that are usually quite accurate using big data. This paper attempts to develop a model of association rule mining to predict customers’ behavior, improve accuracy, and derive major consumer data patterns. The finding recommended BDA method improves Big data analytics usability in the organization (98.2%), risk management ratio (96.2%), operational cost (97.1%), customer feedback ratio (98.5%), and demand prediction ratio (95.2%).

scholarly journals Predicting Travel Behaviour of International and Domestic Tourists using Big Data

2019 ◽  
Vol 8 (3) ◽  
pp. 1572-1580
Keyword(s):  
Machine Learning ◽  
Big Data ◽  
San Francisco ◽  
Data Analytics ◽  
Demand Forecasting ◽  
Big Data Analytics ◽  
Travel Behaviour ◽  
Tourism Industry ◽  
Machine Learning Algorithms ◽  
Data Set

Tourism is one of the most important sectors contributing towards the economic growth of India. Big data analytics in the recent times is being applied in the tourism sector for the activities like tourism demand forecasting, prediction of interests of tourists’, identification of tourist attraction elements and behavioural patterns. The major objective of this study is to demonstrate how big data analytics could be applied in predicting the travel behaviour of International and Domestic tourists. The significance of machine learning algorithms and techniques in processing the big data is also important. Thus, the combination of machine learning and big data is the state-of-art method which has been acclaimed internationally. While big data analytics and its application with respect to the tourism industry has attracted few researchers interest in the present times, there have been not much researches on this area of study particularly with respect to the scenario of India. This study intends to describe how big data analytics could be used in forecasting Indian tourists travel behaviour. To add much value to the research this study intends to categorize on what grounds the tourists chose domestic tourism and on what grounds they chose international tourism. The online datasets on places reviews from cities namely Chicago, Beijing, New York, Dubai, San Francisco, London, New Delhi and Shanghai have been gathered and an associative rule mining based algorithm has been applied on the data set in order to attain the objectives of the study

scholarly journals A Survey on Big Data Analytics Using HADOOP

2019 ◽  
Vol 8 (S3) ◽  
pp. 35-40
Author(s):  
S. Mamatha ◽  
T. Sudha
Keyword(s):  
Big Data ◽  
Social Networking Sites ◽  
Data Analytics ◽  
Business Processes ◽  
Big Data Analytics ◽  
Large Data ◽  
Structured Data ◽  
Map Reduce ◽  
Data Set ◽  
Digital World

In this digital world, as organizations are evolving rapidly with data centric asset the explosion of data and size of the databases have been growing exponentially. Data is generated from different sources like business processes, transactions, social networking sites, web servers, etc. and remains in structured as well as unstructured form. The term ― Big data is used for large data sets whose size is beyond the ability of commonly used software tools to capture, manage, and process the data within a tolerable elapsed time. Big data varies in size ranging from a few dozen terabytes to many petabytes of data in a single data set. Difficulties include capture, storage, search, sharing, analytics and visualizing. Big data is available in structured, unstructured and semi-structured data format. Relational database fails to store this multi-structured data. Apache Hadoop is efficient, robust, reliable and scalable framework to store, process, transforms and extracts big data. Hadoop framework is open source and fee software which is available at Apache Software Foundation. In this paper we will present Hadoop, HDFS, Map Reduce and c-means big data algorithm to minimize efforts of big data analysis using Map Reduce code. The objective of this paper is to summarize the state-of-the-art efforts in clinical big data analytics and highlight what might be needed to enhance the outcomes of clinical big data analytics tools and related fields.

scholarly journals An end-to-end Novel Forecasting Model for Crime Prediction based on Big Data

2020 ◽  
Vol 8 (6) ◽  
pp. 3704-3708
Keyword(s):  
Time Series ◽  
Big Data ◽  
Data Analytics ◽  
Linear Time ◽  
Big Data Analytics ◽  
Series Data ◽  
Data Sets ◽  
Data Set ◽  
Main Category ◽  
Crime Prediction

Big data analytics is a field in which we analyse and process information from large or convoluted data sets to be managed by methods of data-processing. Big data analytics is used in analysing the data and helps in predicting the best outcome from the data sets. Big data analytics can be very useful in predicting crime and also gives the best possible solution to solve that crime. In this system we will be using the past crime data set to find out the pattern and through that pattern we will be predicting the range of the incident. The range of the incident will be determined by the decision model and according to the range the prediction will be made. The data sets will be nonlinear and in the form of time series so in this system we will be using the prophet model algorithm which is used to analyse the non-linear time series data. The prophet model categories in three main category and i.e. trends, seasonality, and holidays. This system will help crime cell to predict the possible incident according to the pattern which will be developed by the algorithm and it also helps to deploy right number of resources to the highly marked area where there is a high chance of incidents to occur. The system will enhance the crime prediction system and will help the crime department to use their resources more efficiently.

scholarly journals Big Data Analytics on Matrimonial Data Set

2020 ◽  
Vol 4 (4) ◽  
pp. 722-728
Author(s):  
Anurag Sinha ◽  
Arinjay Biswas ◽  
Tushar Raj ◽  
Aditya Misra
Keyword(s):  
Big Data ◽  
Data Analytics ◽  
Big Data Analytics ◽  
Data Set

scholarly journals Big Data Analytics using Swarm Intelligence based Framework for Prediction on Datasets

2019 ◽  
Vol 8 (4) ◽  
pp. 7356-7360
Keyword(s):  
Machine Learning ◽  
Big Data ◽  
Data Analytics ◽  
Information Source ◽  
Research Work ◽  
Big Data Analytics ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Data Set ◽  
Raw Data

Data Analytics is a scientific as well as an engineering tool used to investigate the raw data to revamp the information to achieve knowledge. This is normally connected with obtaining knowledge from reliable information source and rapidity in information processing, and future prediction of the data analysis. Big Data analytics is strongly evolving with different features of volume, velocity and Vectors. Most of the organizations are now concentrating on analyzing information or raw data that are fascinated in deploying analytics to survive forthcoming issues and challenges. The prediction model or intelligent model is proposed in this research to apply machine learning algorithms in the data set. Then it is interpreted and to analyze the better forecast value of the study. The major objective of this research work is to find the optimum prediction from the medical data set using the machine learning techniques.

Big Data Analytics Maximizes Value from Smart Well Completions

2021 ◽  
Author(s):  
Nasser M. Al-Hajri ◽  
Muhammad Imran Javed ◽  
Akram R. Barghouti ◽  
Hisham I. Al-Shuwaikhat
Keyword(s):  
Big Data ◽  
Economic Analysis ◽  
Asset Management ◽  
Data Analytics ◽  
Big Data Analytics ◽  
Distribution Functions ◽  
Cumulative Probability ◽  
Data Set ◽  
Valve Opening ◽  
Day To Day Operations

Abstract This paper presents a workflow based on big data analytics to model the reliability of downhole Inflow Control Valves (ICVs) and predict their failures. The paper also offers economic analysis of optimum ICV stroking frequency to maintain valves functionality at the lowest possible cost to the oilfield operator. Installing an ICV in a petroleum well is a costly process and is done by a drilling or workover rig. As such, maintaining a fully functional ICV throughout the lifecycle of a well is important to ensure proper return on investment. ICVs are known to malfunction if not periodically stroked/cycled. The action of stroking ensures that each valve opening is free from obstructing material that would prevent the ICV from operating between one valve opening step to another. When an ICV malfunctions, a costly functionality restoration operation is sometime required without guaranteed results. In other cases, the valve is declared no longer useful and the asset cannot be further utilized due to malfunction. In this paper, an analytical decision making model to predict failures of ICVs is presented that is based on rigorous big data analytics. The model factors in the frequency of stroking before a valve fails. Then, an economic analysis accounting for the CAPEX & OPEX of an ICV is included to optimize the stroking frequency. The utilized techniques include ICV failure and stroking records and classifying the data into pre-defined criteria. Cumulative probability distribution functions are defined for each data set and used to generate failure probability functions. The probability equations are factored into an asset management cost scheme to minimize expected maintenance costs and probability of ICV failure. The results of applying this novel methodology to any smart well clearly showed maximized ICV service life and proper return of investment. The results demonstrate that ICVs lifecycle was prolonged with low maintenance cycling cost. Methodologies similar to the one presented in this paper are true manifestation of the fruitful impact IR4.0 technologies have on oilfields day-to-day operations.

Movie Analytics for Effective Recommendation System using Pig with Hadoop

2016 ◽  
Vol 3 (2) ◽  
pp. 82-100 ◽  
Author(s):  
Arushi Jain ◽  
Vishal Bhatnagar
Keyword(s):  
Big Data ◽  
Science Fiction ◽  
Data Analytics ◽  
Recommendation System ◽  
18Th Century ◽  
Big Data Analytics ◽  
Data Set ◽  
The People ◽  
Late 18Th Century

Movies have been a great source of entertainment for the people ever since their inception in the late 18th century. The term movie is very broad and its definition contains language and genres such as drama, comedy, science fiction and action. The data about movies over the years is very vast and to analyze it, there is a need to break away from the traditional analytics techniques and adopt big data analytics. In this paper the authors have taken the data set on movies and analyzed it against various queries to uncover real nuggets from the dataset for effective recommendation system and ratings for the upcoming movies.

Statistical Visualization of Big Data Through Hadoop Streaming in RStudio

2022 ◽  
pp. 758-787
Author(s):  
Chitresh Verma ◽  
Rajiv Pandey
Keyword(s):  
Big Data ◽  
Data Visualization ◽  
Data Analytics ◽  
Big Data Analytics ◽  
Data Streaming ◽  
Data Set ◽  
Graphical Modeling ◽  
Hadoop Mapreduce ◽  
R Packages ◽  
Case Based

Data Visualization enables visual representation of the data set for interpretation of data in a meaningful manner from human perspective. The Statistical visualization calls for various tools, algorithms and techniques that can support and render graphical modeling. This chapter shall explore on the detailed features R and RStudio. The combination of Hadoop and R for the Big Data Analytics and its data visualization shall be demonstrated through appropriate code snippets. The integration perspective of R and Hadoop is explained in detail with the help of a utility called Hadoop streaming jar. The various R packages and their integration with Hadoop operations in the R environment are explained through suitable examples. The process of data streaming is provided using different readers of Hadoop streaming package. A case based statistical project is considered in which the data set is visualized after dual execution using the Hadoop MapReduce and R script.

Big Data analytics for prediction: parallel processing of the big learning base with the possibility of improving the final result of the prediction

2018 ◽  
Vol 46 (3) ◽  
pp. 147-160 ◽  
Author(s):  
Laouni Djafri ◽  
Djamel Amar Bensaber ◽  
Reda Adjoudj
Keyword(s):  
Big Data ◽  
Data Analytics ◽  
Sampling Method ◽  
New Technologies ◽  
Predictive Analytics ◽  
Big Data Analytics ◽  
Sampling Strategy ◽  
Original Data ◽  
Data Set ◽  
Content Type

Purpose This paper aims to solve the problems of big data analytics for prediction including volume, veracity and velocity by improving the prediction result to an acceptable level and in the shortest possible time. Design/methodology/approach This paper is divided into two parts. The first one is to improve the result of the prediction. In this part, two ideas are proposed: the double pruning enhanced random forest algorithm and extracting a shared learning base from the stratified random sampling method to obtain a representative learning base of all original data. The second part proposes to design a distributed architecture supported by new technologies solutions, which in turn works in a coherent and efficient way with the sampling strategy under the supervision of the Map-Reduce algorithm. Findings The representative learning base obtained by the integration of two learning bases, the partial base and the shared base, presents an excellent representation of the original data set and gives very good results of the Big Data predictive analytics. Furthermore, these results were supported by the improved random forests supervised learning method, which played a key role in this context. Originality/value All companies are concerned, especially those with large amounts of information and want to screen them to improve their knowledge for the customer and optimize their campaigns.

Sign in / Sign up

Export Citation Format

Share Document