Open Data Based Machine Learning Applications in Smart Cities: A Systematic Literature Review

Abstract

Machine learning (ML) has already gained the attention of the researchers involved in smart city (SC) initiatives, along with other advanced technologies such as IoT, big data, cloud computing, or analytics. In this context, researchers also realized that data can help in making the SC happen but also, the open data movement has encouraged more research works using machine learning. Based on this line of reasoning, the aim of this paper is to conduct a systematic literature review to investigate open data-based machine learning applications in the six different areas of smart cities. The results of this research reveal that: (a) machine learning applications using open data came out in all the SC areas and specific ML techniques are discovered for each area, with deep learning and supervised learning being the first choices. (b) Open data platforms represent the most frequently used source of data. (c) The challenges associated with open data utilization vary from quality of data, to frequency of data collection, to consistency of data, and data format. Overall, the data synopsis as well as the in-depth analysis may be a valuable support and inspiration for the future smart city projects.

Overcoming the Barriers of Using Linked Open Data in Smart City Applications

“…However, it is less frequent because companies refuse to freely share their data and to assume the costs related to the publication process [7]. The research conducted by Hurbean et al [8] proposes the Internet of Things (IOT), and Machine Learning (ML) in combination with LOD platforms as the key elements for building smart city applications.…”

“…In the introduction, we mentioned that LOD supports the digital transformation of cities by providing a mechanism to publish a consume source of information in a free and understandable way [2], [9], [8]. In the LOD ecosystem, there are two main stakeholders: data publishers (providers) and data users (consumers).…”

“…OD portals act as an intermediary between consumers and providers, helping providers with the maintenance and publication process. OD portals have to deal with heterogeneous data sources, and as they aggregate more data sources, more difficulties appear, and a higher level of automation is required [8]. Considering that interoperability is one of the main pillars on which any LOD initiative should be built, the World Wide Web Consortium (https://www.w3.org/) published the Data Catalog Vocabulary (DCAT [https://www.w3.org/TR/ vocab-dcat/]) to facilitate the exchange of data catalogs between different organizations.…”

The Impacts of Open Data and eXplainable AI on Real Estate Price Predictions in Smart Cities

“…The availability of open data has led to increased research using artificial intelligence for various applications. Furthermore, open data has been recognized as a catalyst for machine learning (ML), particularly in air pollution prediction, traffic forecasting, urban design, and transport features analysis [12]. It has facilitated knowledge discovery by making data findable, accessible, interoperable, and reusable, as per the FAIR Data Principles [13].…”

“…On the other hand, the housing supply in smart cities is influenced by a complex interplay of various factors, including financing costs, construction costs, vacancy rates, and regulatory constraints [26]. Studies have shown that financing costs, such as interest rates, have a negative effect on housing starts-a crucial economic indicator, as it reflects the health and direction of the housing market and, by extension, provides insights into broader economic conditions [12]. Similarly, construction costs, including material and wage costs, can also affect the housing supply, although the results are inconclusive in some cases [19].…”