Journal of Smart Cities and Society

Distributed Machine Learning (DML) has emerged as a disruptive technology that enables the execution of Machine Learning (ML) and Deep Learning (DL) algorithms in proximity to data generation, facilitating predictive analytics services in Smart City environments. However, the real-time analysis of data generated by Smart City Edge Devices (EDs) poses significant challenges. Concept drift, where the statistical properties of data streams change over time, leads to degraded prediction performance. Moreover, the reliability of each computing node directly impacts the availability of DML systems, making them vulnerable to node failures. To address these challenges, we propose a resilience framework comprising computationally lightweight maintenance strategies that ensure continuous quality of service and availability in DML applications. We conducted a comprehensive experimental evaluation using real datasets, assessing the effectiveness and efficiency of our resilience maintenance strategies across three different scenarios. Our findings demonstrate the significance and practicality of our framework in sustaining predictive performance in smart city edge learning environments. Specifically, our enhanced model exhibited increased generalizability when confronted with concept drift. Furthermore, we achieved a substantial reduction in the amount of data transmitted over the network during the maintenance of the enhanced models, while balancing the trade-off between the quality of analytics and inter-node data communication cost.

The 1990s marked the end of Yugoslavia and the height of conflict and urban destruction (Dubrovnik, Mostar, Sarajevo and later Belgrade). Bogdanovic (1993), an architect and former mayor of Belgrade, coined the neologism ‘urbicide’ to designate an enterprise of urban destruction which goes beyond the simple strategic objective of the physical destruction of the city, but that of the annihilation of memories, identities, and cultures associated with the city in question and its urbanity, that is to say, of the ‘ritualized murder of the city’. At the end of these multiple conflicts, the cities and the related tourism had to be rebuilt. Over the last twenty years, information technologies, the creation of peer-to-peer digital platforms (Booking, Airbnb, Expedia) and virtual reality for museum and heritage visits have boosted the attractiveness of the destination and tourism projects. The emergence of tourism projects based on digital and new technologies is booming in the Balkans, particularly the capitals like Belgrade or Sarajevo. By looking at different technological and digital projects for tourism purposes, we will see how local, private, transnational and citizen actors have taken up this project and if this projects contribute to the touristic destination.

As cities around the globe strive towards becoming “smart” and sustainable, the integration of green facades into smart building design has emerged as a viable solution to address several environmental challenges. This paper conducts a comprehensive review of current research and applications in green facades, analyzing their role in enhancing energy efficiency, improving indoor air quality, and contributing to overall building sustainability. The impact of green facades on reducing energy consumption, through natural insulation and shading, is explored in-depth, alongside their role in air purification and enhancing the aesthetic appeal of urban environments. Despite the potential of green facades, several gaps between theory and practice exist, including challenges in implementation, maintenance, and cost-effectiveness. This paper identifies these barriers and provides a robust discussion of potential solutions, which include technological innovations, policy support, and public awareness initiatives. Ultimately, the integration of green facades in smart buildings presents a significant step forward in creating sustainable urban environments, necessitating further research and action in this realm.