ABSTRACT
With the introduction of Industry 4.0, advancements in IT tools such as Internet of things (IOT), cloud computing, cyber-physical systems, artificial intelligence and virtual reality have popped up a new dimension in industries that incorporates intelligent human-to-machine and machine-to-machine systems. Machine learning (ML) proved to be an effective means to mimic various complex situations and processes involved in product manufacturing, manufacturer–supplier relation and manufacturer–consumer relations and to incorporate them into complicated decision-making algorithms. These incorporations, in turn, help industries in building energy- and time-efficient systems for a better utilization of resources, less involvement of humans and higher revenue creation. In ML, the machines are made to self-learn through experiences without being programmed explicitly. However, implementing ML techniques without having a structured project roadmap, methodologies and knowledge of their strengths and limitations can sometimes result in catastrophic failures and financial loss. In this chapter, a detailed review has been presented for the implementation of ML in various industrial scenarios such as in healthcare industries, agricultural supply chain systems and enterprises. In agriculture, various decision-making and sustainable challenges in agricultural supply chain and the concepts of smart farming and precision agriculture have been discussed. In healthcare industries, various limitations involving inadequate expertise of the medical practitioners in ML-related modelling algorithms and task optimization and implementation of the automated ML to improve and ease their utilization performance have been discussed. Lastly, in enterprise section, various types of ML usage, cases of ML development in financial services contributing towards better customer experience, ease in business processes and reduction in product lifecycle cost have been discussed.
