Today, the automotive and transportation sector is undergoing a transformation process to meet the requirements of sustainable and efficient operations. This transformation mainly reveals itself by electric vehicles, hybrid electric vehicles, and electric vehicle sharing. One significant, and the most expensive, component in electric vehicles is the batteries, and the management of batteries is crucial. It is essential to perform constant monitoring of behavior changes for operational purposes and quickly adjust components and operations to these changes. Thus, to address these challenges, we propose a knowledge graph-based data integration framework for simplifying access and analysis of data accumulated through the operations of vehicles and related transportation systems. The proposed framework aims to enable the effortless analysis and navigation of integrated knowledge and the creation of additional data sets from this knowledge to use during the application of data analysis and machine learning. The knowledge graph serves as a significant component to simplify the extraction, enrichment, exploration, and generation of data in this framework. We have developed it according to the human-centered design, and various roles of the data science and machine learning life cycle can use it. Its main objective is to streamline the exploration and interaction with the integrated data to maximize human productivity. Finally, we present a battery use case to show the feasibility and benefits of the proposed framework. The use case illustrates the usage of the framework to extract knowledge from raw data, navigate and enrich it with additional knowledge, and generate data sets.

No abstract

Nowadays, machine learning methods are increasingly used in different parts of autonomous driving and driving assistance systems. Yet, data and computational requirements can be enormous with these methods. Thus, providing several datasets containing many and diverse cases for the target problem and sufficient hardware for training and application of ML methods are too critical for achieving accurate results when applying them. Hence, we present an object detection benchmark study implementing the knowledge graph-based data integration framework to meet the data requirements and run the implementation on a big data and high-performance computing (HPC) platform, namely the EVOLVE. We applied different object detection methods to widely known open datasets, and compared the results on three different hardware setups, including EVOLVE. We also performed a small-scale transfer learning experiment. The results show that EVOLVE allowed the exploitation of much bigger data leading to a more efficient application of the object detection models with the help of the knowledge graph-based data integration framework. EVOLVE significantly improved the execution times compared to running them on a local laptop and a virtual machine and provided the easy-to-use and ready-to-use means to store large datasets and apply different models with its hardware and software stack.