Mobility as a Service (MaaS) is a way to enable individuals a transportation method – for example, a bike, car or bus – depending on their needs. It is a shift from personally owned modes of transportation towards mobility provided as a service. OSMaaS is a Synergy project within the Halmstad University Knowledge and Competence Center. The intradisciplinary project aims to develop MaaS platforms using service design methods. Subprojects are within Business Model Innovation, Design Ethnography and Technical Design.
OSMaaS has different sub-projects, which include a technical design that develops the platform’s logic and the necessary optimizations. It includes search algorithms for complex combinations of different travel modalities and discovery and management of users’ preferences. Given the access to user mobility patterns via the product design, the project will provide tools to do a meaningful analysis of user data based on the actual use of the platform. The sub-project is motivated by the need for reliable and optimized handling of data to achieve a positive user experience, both in terms of efficiency and relevance and to provide input to the development of new services and businesses from big data, machine learning and AI technologies.
In the technicl design of OSMaaS, the following sub-projects and studies have been performed:
This study proposes a knowledge-based framework based on Artificial Intelligence (AI) to integrate various mobility data types and provide travellers with customized services. The proposed framework includes a knowledge acquisition process to extract and structure data from multiple sources of information (such as mobility experts and weather data). It also adds new information to a knowledge base and improves the quality of previously acquired knowledge. We discuss how AI can help discover knowledge from various data sources and recommend sustainable and personalized mobility services with explanations. The proposed knowledge-based AI framework uses a synthetic dataset as a proof of concept. Combining different information sources to generate valuable knowledge is identified as one of the challenges in this study. Finally, explanations of the proposed decisions provide a criterion for evaluating and understanding the proposed knowledge-based AI framework.
Link to the article: https://www.mdpi.com/2071-1050/15/3/2717
Link to the project code: https://github.com/caisr-hh/OSMaaS/tree/main/OSMaaS_knowledge_based_AI_framework#readme
The Point of Interest (POI) Android Automotive app is a powerful tool designed to enhance the navigation experience for vehicle users within the Android Automotive platform. This application leverages OpenStreetMap data to provide a curated selection of Points of Interest (POIs) based on the user's current location. By harnessing data from an open map library (OpenStreetMap), the app offers a carefully curated selection of POIs based on the user's current location. This app covers a wide range of categories, allowing users to effortlessly explore various points of interest, including dining options, electric vehicle charging stations, recreational facilities, scenic spots, as well as cultural and historical sites. Users can also mark their favorite places for quick and convenient access. The repository is focused on managing and displaying points of interest within the specific application. This could be useful in various contexts like travel, navigation, and tourism using OpenStreetMap. It allows users to filter and view different categories of points of interest, such as restaurants, landmarks, recreational facilities, etc. The repository could contribute to the broader OpenStreetMap ecosystem by creating tools, applications, or services that utilize OpenStreetMap data in innovative ways.
Link to the project code: https://github.com/caisr-hh/OSMaaS/tree/main/OSMaaS_Point_of_Interest
Artificial Intelligence (AI) allows the analysis of complex transportation domains from various perspectives. Sustainability is one of the important transportation factors vital for a robust, fair, and efficient living environment and a city's livability. This study leverages different feature engineering techniques on the New York City mobility dataset to identify the significant sustainability factors and employs the k-means clustering technique to cluster the commuters based on their transportation modes and demographics. The NYC mobility dataset has provided vast information to extract relevant patterns or features influencing New Yorkers' sustainable mode of transportation choice. Machine learning techniques and graph analysis can predict trip destinations or the purpose of commuters’ trips based on different features in the dataset and identify commuters’ patterns.
Link to the article: https://ieeexplore.ieee.org/document/9801569
Link to the project code: https://github.com/caisr-hh/OSMaaS/tree/main/OSMaaS_NYC_Mobility_Clustering
Identifying centrality measures using social network analytics techniques is an interesting topic that can help highlight various amenities around the city like hospitals, bus stops, parking spots, electric vehicle charging stations, bicycle rental places and bicycle parking spots. Street centrality refers to a set of metrics that measure the importance of each street segment within a street network. Street centrality can be used to identify the most important or central streets within a network, which can be useful for a variety of urban planning and transportation applications.
In this work, we used OSMnx, which is a Python package that allows users to analyze street networks and other infrastructure data from OpenStreetMap. It is a powerful tool for urban planners, geographers, and researchers who are interested in understanding and analyzing urban environments. We utilized OSMnx to calculate several different centrality measures that can be calculated for a street network, including Degree Centrality, Eigenvector Centrality, Closeness Centrality and Betweenness Centrality.
Link to the project code: https://github.com/caisr-hh/OSMaaS/tree/main/OSMaaS_Social_Network_analytics_Map