Optimization of order dispatch operations and delivery time prediction is a major concern in supply chains, mainly for e-commerce, which requires the implementation of advanced solutions to reduce delivery time, minimize costs and maximize customer satisfaction. In practice, they fail to warrant scalable and sustainable solutions as the numbers of orders become larger. For that, proper prediction and optimization for delivery operations are required for optimal logistics management. This paper presents an advanced logistics service, which warrants dynamic coordination among all the actors in the smart logistics environment. The proposed advanced shipping system consists of two main parts: the delivery prediction model to compute the expected arrival time, and a hybrid optimization model to tackle path issues. We demonstrate that the advanced system consistently outperforms conventional standard dispatching methods, which means that the proposed approach effectively contributes to optimizing the distribution chain and reducing costs.

No abstract

With growing evidence of advanced technologies-assisted smart processes, it is fundamental to comprehend whether manufacturing systems are adequate to manage flexibility and complexity to enhance the monitoring of smart factories. Smart manufacturing (SM) is evolving as a new version of traditional manufacturing, revealing the magnitude and power of smart technologies such as Artificial Intelligence (AI) and the Internet of Things (IoT). The wide applicability of these technologies is allowing important innovations across all industries. As the manufacturing industry has gained benefits, the current boosts of Smart Manufacturing are experiencing exceptional levels of interest. However, providing suitable SM systems and identifying the priority of requirements may vary according to different scenarios. To this end, this study presents a systematic survey of the current SM research trends. Furthermore, this paper aims to present a consistent and comprehensive vision of existing efforts in smart manufacturing and discussed the remaining open issues.

No abstract