Big Data Analytics for Predictive Maintenance Strategies

Maintenance aims to reduce and eliminate the number of failures occurred during production as any breakdown of machine or equipment may lead to disruption for the supply chain. Maintenance policy is set to provide the guidance for selecting the most cost-effective maintenance approach and system to achieve operational safety. For example, predictive maintenance is most recommended for crucial components whose failure will cause severe function loss and safety risk. Recent utilization of big data and related techniques in predictive maintenance greatly improves the transparency for system health condition and boosts the speed and accuracy in the maintenance decision making. In this chapter, a Maintenance Policies Management framework under Big Data Platform is designed and the process of maintenance decision support system is simulated for a sensor-monitored semiconductor manufacturing plant. Artificial Intelligence is applied to classify the likely failure patterns and estimate the machine condition for the faulty component.

Applying Big Data with Fuzzy DEMATEL to Discover the Critical Factors for Employee Engagement in Developing Sustainability for the Hospitality Industry under Uncertainty

The hospitality industry is one of the fastest-growing industries in the world. The growth of this industry has been accompanied by issues of sustainability development. Employees expect firms to have the ability to address their negative impacts on the environment and society. However, firms are generally unable to reach such expectations due to an inability to acquire feedback from employees, which leads to employee dissatisfaction. In addition, there has been a lack in the theoretical linkage between employee engagement and sustainability development. Thus, this study determines the critical factors of employee engagement based on big data (using social media and quantitative and qualitative data) and integrates such data by using decision-making tests and laboratory evaluation methods to identify these interrelationships. The findings reveal that sustainability development can be enhanced through aggressive employee engagement, which also can generate a positive influence on economic performance. A detailed discussion is also presented.

Supply Chain Coordination Based on Web Service

The importance of integrating and coordinating supply chain business partners have been appreciated in many industries. In the global manufacturing industry, supply chain business partners' information integration is technically a daunting task due to highly disconnected infrastructures and operations. Information, software applications, and services are loosely distributed among participant business partners with heterogeneous operating infrastructures. A secure, and flexible information exchange architecture that can interconnect distributed information and share that information across global service provision applications is, therefore, immensely advantageous. This chapter describes the main features of an ontology-based web service framework for integrating distributed business processes in a global supply chain. A Scalable Web Service Discovery Framework (SWSDF) for material procurement systems of a manufacturing supply chain is described. Description Logic (DL) is used to represent and explain SWSDF. The framework uses a hybrid knowledge-based system, which consists of Case-Based Reasoning (CBR) and Rule-Based Reasoning (RBR). SWSDF includes: (1) a collection of web service descriptions in Ontology Web Language-Based Service (OWL-S), (2) service advertisement using complex concepts, and (3) a service concept similarity assessment algorithm. Finally, a business scenario is used to demonstrate functionalities of the described system.

Big Data Analytics

In this chapter, we will introduce practical issues and implementation challenges from the industry perspective. In particular, we explain three aspects based on the panel discussions from the set of representatives participated in a big data conference from three dominant industries such as e-commerce, health care and computer hardware, which are sought of big data for their growth and development. We introduce overall challenges and explain typical industry based practical issues, how they visualize the big picture for their strategic development and how industries are gearing towards converting the challenges to big opportunities through the partnership of universities. Finally, based on the content analysis we offer potential trends and future research directions.

How Smart Operations Help Better Planning and Replenishment?

This chapter discusses various roles of smart information in Supply Chains (SC) of digital age and tries to answer an important question - What types of collaborative arrangements facilitate smart operations to improve planning, production and timely replenishment? We have conducted longitudinal case studies with firms practicing SC collaborations and also using smart information for operations. Based on the case analysis, the companies are further classified as ‘smart planning' and ‘traditional planning'. Research findings show the importance of aligning SC partnerships based on smart information requirements. These findings are based on case studies of Indian firms with global SC collaboration. We also discuss the role of Big Data for the companies using smart planning.

Developing an Integration Framework for Crowdsourcing and Internet of Things with Applications for Disaster Response

The crowdsourcing and Internet of Things (IoT) have played a significant role in revolutionizing the information age. In response to pressing need, we have attempted to develop a theoretical framework which can help disaster relief workers to improve their coordination using valuable information derived using comprehensive crowdsourcing framework. In this study we have used two-prong research strategies. First we have conducted extensive review of articles published in reputable journals, magazines and blogs by eminent practitioners and policy makers followed by case studies: stampede in Godavari River at Rajahmundry (2015), earthquake in Nepal (2015), flood in Uttarakhand (2013). Finally we have concluded our research findings with further research directions.

Big Data and RFID in Supply Chain and Logistics Management

Big Data refers to complex and unstructured data that is difficult to analyse and utilize with traditional applications and analyses. Big Data comes from a variety of sources, including tracking and sensor devices which are widely used in logistics and supply chain management, and relate to Radio Frequency Identification (RFID) technology. Thus, this chapter reviews the literature on RFID adoption in supply chain/logistics management from 1995-2015. We identify current trends in the literature, drawing on the three levels of decision making, that is, strategic, tactical, and operational. We suggest that more research needs to be conducted with regards to the intangible benefits of RFID, the use of RFID big data for achieving higher performance, and to shift the focus from the ‘what' and the impacts on performance to the ‘how' and the ways RFID is adopted and assimilated in organizations and supply chains. Finally, the managerial implications of our review as well as the limitations and future research directions are outlined.

Exploring the Hidden Pattern from Tweets

Social media has recently emerged as a key tool to manage customer relations in industry. This chapter aims to contribute a step-by-step Twitter Analytic framework for analysing the tweets in a fiscal crisis. The proposed framework includes three major sections – demographic analytic, content analytic and integrated method analytic. This chapter provides useful insights to develop this framework through the lens of the recent Volkswagen emission scandal. A sizable dataset of #volkswagescandal tweets (8,274) was extracted as the research sample. Research findings based upon this sample include the following: Consumer sentiments are overall negative toward the scandal; some clustered groups are identified; male users expressed more interest on social media in the topic than female users; the popularity of tweets was closely related with the timing of news coverage, which indicates the traditional media is still playing a critical role in public opinion formation. The limitations and practical contribution of the current study are also discussed.

Role of Operations Strategy and Big Data

It has been observed that the less than truck load (LTL) industry is going through significant transformation. After the last few years of decline in revenue, due to weak economy, the profitability of the LTL is on the rise. A strategy based on improving freight flow and density, and tightening terminal capacity is finally producing results for many LTL's, at the same time other LTL's are investing on expanding terminal network's while making bigger gains in the revenue. The availability of big data has revolutionised the way the LTL industry operates. The data assists in planning, efficient routing, safety control, fuel conservation, driving habits, etc. Analysts believe that big data still has a bigger role to play and it will have significant impact on the LTL industry in the coming days. This chapter discusses the challenges and opportunities for LTL carriers as it arises due to the emergence of big data.

Data-Driven Inventory Management in the Healthcare Supply Chain

From 21st century, enterprises combine supply chain management with big data to improve their products and services level. In China healthcare industry, supply chain decisions are made based on experience, due to the environment complexities, such as changing policies and license delay. A flexible and dynamic big data driven analysis approach for supply chain decisions is urgently required. This report demonstrates a case study on CRT forecasting model of inventory data to predict the market demand based on pervious transaction data. First a basic statistic approach has been applied to represent the superficial patterns and suggest some decisions. After that a CRT model has been built based on the several independent variables. And there is also a comparison between CRT and CHAID models to choose a better one to further build an improved model. Finally some limitations and future work have been proposed.