ICMSEM 2020

Dr. Anil Dube

Mechanical Engineering, Sandip Institue of Engineering and Management Nashik, India

Research Area: Supply Chain Management, Renewable energy and Green Supply chain Management

Title : Impact of Supply Chain Practices on the Performance of Organization.

Abstract：

A supply chain (SC) includes all the activities, functions and facilities involved in the flow and transformation of goods and services from the material stage to the end-user. Supply chain management (SCM) aims to coordinate the flow of raw material, semi finish and finish goods, and services and the flow of information necessary to provide the worth that customers demand. Globalisation has driven many organisations to widen their resources and capability to a greater height. It is also true that competition among organisations is becoming keen and no longer between organisation and organisation, but SC to SC. To be competitive locally and across the borders, attention is increasingly shifting towards successful SCM implementation in the organisations. SCM includes external collaboration and networking outside the boundaries of the organisation and linked it to the internal activities.

Prof. Yao, Hsiu-Hsen

Department of Computer Science Yuan-Ze University, Taiwan, China

Research Area: Data Science, Artificial Intelligence

Title: Based on Data Engineering Technique to Support Urban Traffic Management

Abstract：

Intelligent traffic data analysis can help urban transportation planning and management. In this talk, five traffic data engineering process are discussed, including data collection, data warehousing, data analysis, data visualization, and data mining. First, IOV(Internet on Vehicle) and CV(Connected Vehicle) may get 3d G-sensors, eCompass, Gyro, OBDII, and GPS/Beidou satellite position data, which can be used to recognize driving behavior(braking, stepping on the accelerator, and L/R/U turn). This kind of data analysis can help traffic accident appraisal, analysis, and prevention for public driving safety management. Secondly, one 'big' transport data warehouse, including taxi/bus GPS data and passenger ride/transfer data, will be shown as a running example to explain how to use the time series data engineering, driving data recognition, discrete data smoothing/difference/integral, spatial-temporal data processing, and data visualization techniques to support public traffic management, will be shown in the talk. As an AI engineering application on traffic data, based on regression analysis and neural network approach, driving fuel consumption may be forecast/estimated from driving features extracted from these driving data. Finally, the talk will show how to cut and transform these driving data into a traffic situation data set by each road segment for urban transportation planning and management.