Search results

This research navigates the confluence of data analytics, machine learning, and artificial intelligence to revolutionize the management of urban services in smart cities. The study thoroughly investigated with advanced tools to scrutinize key performance indicators integral to the functioning of smart cities, thereby enhancing leadership and decision-making strategies. Our work involves the implementation of various machine learning models such as Logistic Regression, Support Vector Machine, Decision Tree, Naive Bayes, and Artificial Neural Networks (ANN), to the data. Notably, the Support Vector Machine and Bernoulli Naive Bayes models exhibit robust performance with an accuracy rate of 70% precision score. In particular, the study underscores the employment of an ANN model on our existing dataset, optimized using the Adam optimizer. Although the model yields an overall accuracy of 61% and a precision score of 58%, implying correct predictions for the positive class 58% of the time, a comprehensive performance assessment using the Area Under the Receiver Operating Characteristic Curve (AUC-ROC) metrics was necessary. This evaluation results in a score of 0.475 at a threshold of 0.5, indicating that there's room for model enhancement. These models and their performance metrics serve as a key cog in our data analytics pipeline, providing decision-makers and city leaders with actionable insights that can steer urban service management decisions. Through real-time data availability and intuitive visualization dashboards, these leaders can promptly comprehend the current state of their services, pinpoint areas requiring improvement, and make informed decisions to bolster these services. This research illuminates the potential for data analytics, machine learning, and AI to significantly upgrade urban service management in smart cities, fostering sustainable and livable communities. Moreover, our findings contribute valuable knowledge to other cities aiming to adopt similar strategies, thus aiding the continued development of smart cities globally.

Integration of city systems is needed to provide flexibility, agility and access to real-time information for the creation and delivery of efficient services in a smart and sustainable city. Consequently, City Process Modelling (CPMo) becomes an essential element of connecting various city sectors. However, to date, there has been limited research on the requirements of an ideal CPMo approach and the usefulness of available Business Process Modelling (BPMo) approaches. This research develops a framework for CPMo to guide smart city developers when modelling city processes.

Data from literature analysis was gathered to derive capabilities of existing BPMo techniques. Then, semi-structured interviews were conducted to thematically and qualitatively explore the requirements, challenges and success factors of CPMo.

The interview findings offered 17 requirements to be addressed by a CPMo approach, along with several challenges and success factors to be considered when implementing CPMo approaches. Then, the paper presents the results of mapping these requirements against 12 existing BPMo capabilities, identified from the literature, concluding that a significant number of requirements (which are mainly related to inputs and visualisation) have been left unfulfilled by existing BPMo approaches. Hence, developing an innovative CPMo approach is necessary to address the components of unfulfilled requirements.

The innovative framework presented in this paper justifies the CPMo requirements, which are unexplored in existing SCD frameworks. Moreover, it will act as a guide for smart city developers, to model cross-sectoral city processes, helping them progress their SCD road map and make their cities smart.

The purpose of this paper is to set up a growth model for a world city, in order to determine the roles of government and enterprises. With the model, the authors of this paper want to test the efficiencies between governmental and enterprise investment for the experience of Beijing.

The paper proves the contributions of enterprise and governmental investment for a world city by three assumptions. It then sets up a growth model for a world city by taking the variable of governmental investment instead of the labor variable in the Solow Growth Model. With C‐D function, the paper sets up an empirical growth model of the world city of Beijing by ordinary least squares (OLS) regression.

Results of OLS show that the elasticity of enterprises operating surplus to world city growth is bigger than the one of governmental expenditure to world city growth, which indicates that the investment ability of the private sector has more efficient effectiveness on a world city than governmental investment. Meanwhile, technological progress also has weak effectiveness for world city growth from the regression of C‐D function.

When the public and private sectors were taken into account for world city growth, the role of government investment is constructing a fair environment for enterprises' competition and encouraging innovation in the private sector, as well as enhancing efficient policy for innovation application in the private sector.

The paper sets up a growth model with the variables of private and public factors taking the place of the variable of labor in the Solow Growth Model with government investment. The model can be adopted to explain the dynamics of world city growth in a transition economy.

This paper critically analysed 195 articles with the objectives of providing a clear understanding of the current City Information Modelling (CIM) implementations, identifying the main challenges hampering the uptake of CIM and providing recommendations for the future development of CIM.

This paper adopts the PRISMA method in order to perform the systematic literature review.

The results identified nine domains of CIM implementation including (1) natural disaster management, (2) urban building energy modelling, (3) urban facility management, (4) urban infrastructure management, (5) land administration systems, (6) improvement of urban microclimates, (7) development of digital twin and smart cities, (8) improvement of social engagement and (9) urban landscaping design. Further, eight challenges were identified that hinder the widespread employment of CIM including (1) reluctance towards CIM application, (2) data quality, (3) computing resources and storage inefficiency, (4) data integration between BIM and GIS and interoperability, (5) establishing a standardised workflow for CIM implementation, (6) synergy between all parties involved, (7) cybersecurity and intellectual property and (8) data management.

This is the first paper of its kind that provides a holistic understanding of the current implementation of CIM. The outcomes will benefit multiple target groups. First, urban planners and designers will be supplied with a status-quo understanding of CIM implementations. Second, this research introduces possibilities of CIM deployment for the governance of cities; hence the outcomes can be useful for policymakers. Lastly, the scientific community can use the findings of this study as a reference point to gain a comprehensive understanding of the field and contribute to the future development of CIM.

This paper aims to create a new searchable 3D city model to help managers improve their decision-making.

This paper identifies data management basics and the key elements used in the new model design; it further analyzes five-city models, presents its findings and proposes analytical trends for the new model. It discusses the concepts underlying existing models, explains the benefit brought by the proposed model and demonstrates its robustness.

City systems can be interconnected, thanks to data digitization and the integration of new technologies into different management processes. Although there are several 3D city models available, none of those identified in this research can be queried for several sectors.

This model design can only be successfully realized in the presence of a public mandate. Potential limitations include information security risks and political non-acceptance.

The present work proposes a searchable and high performance model having the distinctive capacity to bring together city systems and perform real-time data analysis in order to extract important information needed to guide the city, and in the context of a global vision.

Taking as a case study the city of San Carlos de Bariloche – in northern Patagonia, Argentina – this paper aims to compare its urban structure with previous urbanization models and identify some characteristics of this tourist city that could inspire the construction of an adapted urban model for Latin American tourist cities, particularly those based on natural attractions.

Based on multivariate analysis of population census data and local economic statistics, this paper compares the residential location of different social groups and the location of main economic activities in Bariloche. First, principal component analysis (PCA) is combined with cluster analysis to classify Bariloche’s neighborhoods. Second, different maps are analyzed to study the location of economic activities, in comparison with previous clusters.

The results of this paper show that Bariloche partially adjusts to previous urbanization models, as the landscape and physical environment determine the characteristics of its urban growth, as well as the development of tourist activities. Therefore, this paper then proposes an adapted urban model for the case of Bariloche, which could be also contrasted with other Latin American tourist cities in the future.

Bearing in mind that there is no model of Latin American tourist cities so far, this paper tries to analyze to what extent the assumptions and patterns of previous urban models could be adapted to Latin American tourist cities, such as Bariloche, which base their attractiveness and economic dynamism on its natural physical environment.

The objective of this research work is to design a data-based solution for administering traffic organization in a smart city by using the machine learning algorithm.

A machine learning framework for managing traffic infrastructure and air pollution in urban centers relies on a predictive analytics model. The model makes use of transportation data to predict traffic patterns based on the information gathered from numerous sources within the city. It can be promoted for strategic planning determination. The data features volume and calendar variables, including hours of the day, week and month. These variables are leveraged to identify time series-based seasonal patterns in the data. To achieve accurate traffic volume forecasting, the long short-term memory (LSTM) method is recommended.

The study has produced a model that is appropriate for the transportation sector in the city and other innovative urban applications. The findings indicate that the implementation of smart transportation systems enhances transportation and has a positive impact on air quality. The study's results are explored and connected to practical applications in the areas of air pollution control and smart transportation.

The present paper has created the machine learning framework for the transportation sector of smart cities that achieves a reasonable level of accuracy. Additionally, the paper examines the effects of smart transportation on both the environment and supply chain.

We are interested in modeling the impact of spatial and interindustry dependence on firm-level innovation of Chinese firms The existence of network ties between cities imply that changes taking place in one city could influence innovation by firms in nearby cities (local spatial spillovers), or set in motion a series of spatial diffusion and feedback impacts across multiple cities (global spatial spillovers). We use the term local spatial spillovers to reflect a scenario where only immediately neighboring cities are impacted, whereas the term global spatial spillovers represent a situation where impacts fall on neighboring cities, as well as higher order neighbors (neighbors to the neighboring cities, neighbors to the neighbors of the neighbors, and so on). Global spatial spillovers also involve feedback impacts from neighboring cities, and imply the existence of a wider diffusion of impacts over space (higher order neighbors).

Similarly, the existence of national interindustry input-output ties implies that changes occurring in one industry could influence innovation by firms operating in directly related industries (local interindustry spillovers), or set in motion a series of in interindustry diffusion and feedback impacts across multiple industries (global interindustry spillovers).

Typical linear models of firm-level innovation based on knowledge production functions would rely on city- and industry-specific fixed effects to allow for differences in the level of innovation by firms located in different cities and operating in different industries. This approach however ignores the fact that, spatial dependence between cities and interindustry dependence arising from input-output relationships, may imply interaction, not simply heterogeneity across cities and industries.

We construct a Bayesian hierarchical model that allows for both city- and industry-level interaction (global spillovers) and subsumes other innovation scenarios such as: (1) heterogeneity that implies level differences (fixed effects) and (2) contextual effects that imply local spillovers as special cases.