Narrow Results

Unmanned aerial vehicles (UAVs) can monitor traffic in different scenarios like surveillance, control, and security. The object detection method depends on UAVs equipped with vision sensors, which have received significant attention in domains such as intelligent transportation systems (ITSs) and UAVs, which can monitor road traffic across some distance and offer vital data for following intelligent traffic supervision tasks, namely traffic situational awareness, detecting sudden accidents, and calculating traffic flow. Nevertheless, most vehicle targets exhibit specific features and lesser sizes that challenge accurate vehicle recognition in UAV overhead view. Employing innovative computer vision (CV) models, vehicle recognition and tracking in UAV images contains detecting and following vehicles in aerial footage taken by UAVs. This procedure leverages deep learning (DL) approaches for perfectly detecting vehicles and a robust tracking method for monitoring their actions through the frames, offering vital information for traffic management, surveillance, and urban planning. Therefore, this study designs an Advanced DL-based Vehicle Detection and Tracking on UAV Imagery (ADLVDT-UAVI) approach. The drive of the ADLVDT-UAVI technique is to detect and classify distinct vehicles in the UAV images correctly as Brain-Like Computing technique for Traffic Flow Optimization in Smart Cities. In this approach, Gaussian filtering (GF) primarily eliminates the noise. Besides, the ADLVDT-UAVI technique utilizes a squeeze-and-excitation capsule network (SE-CapsNet) for feature vector derivation. Meanwhile, the hyperparameter selection process involves using the Fractals coati optimization algorithm (COA). Finally, the self-attention bi-directional long short-term memory (SA-BiLSTM) approach is utilized to classify detected vehicles. To validate the improved results of the ADLVDT-UAVI approach, a wide range of experiments is performed under VEDAI and ISPRS Postdam datasets. The experimental validation of the ADLVDT-UAVI approach portrayed the superior accuracy outcome of 98.35% and 98.96% compared to recent models.

Real-time detection of possible deforestation of urban landscapes is an essential task for many urban forest monitoring services. Computational methods emerge as a rapid and efficient solution to evaluate bird’s-eye-view images taken by satellites, drones, or even street-view photos captured at the ground level of the urban scenery. Identifying unhealthy trees requires detecting the tree itself and its constituent parts to evaluate certain aspects that may indicate unhealthiness, being street-level images a cost-effective and feasible resource to support the fieldwork survey. This paper proposes detecting trees and their specific parts on street-view images through a Convolutional Neural Network model based on the well-known You Only Look Once network with a MobileNet as the backbone for feature extraction. Essentially, from a photo taken from the ground, the proposed method identifies trees, isolates them through their bounding boxes, identifies the crown and stem, and then estimates the height of the trees by using a specific handheld object as a reference in the images. Experiment results demonstrate the effectiveness of the proposed method.

With the development of emerging information technology, the traditional management methods of marine fishes are slowly replaced by new methods due to high cost, time-consumption and inaccurate management. The update of marine fishes management technology is also a great help for the creation of smart cities. However, some new methods have been studied that are too specific, which are not applicable for the other marine fishes, and the accuracy of identification is generally low. Therefore, this paper proposes an ecological Internet of Things (IoT) framework, in which a lightweight Deep Neural Networks model is implemented as a image recognition model for marine fishes, which is recorded as Fish-CNN. In this study, multi-training and evaluation of Fish-CNN is accomplished, and the accuracy of the final classification can be fixed to 89.89%–99.83%. Moreover, the final evaluation compared with Rem-CNN, Linear Regression and Multilayer Perceptron also verify the stability and advantage of our method.

Intelligent forecasting of economic indexes has been an important demand for sustainable management of smart cities. Existing methods for this purpose were mostly established upon the basis of economic mechanism. Econometric models are the most general technical means in this area. However, in era of digital economy, increasing amount of big data has brought great change to traditional production. It is becoming more difficult for conventional technological forecasting methods to deal with multi-dimensional economic indexes. To deal with such challenge, this paper introduces the artificial intelligence algorithms to implement automatic information processing, and proposes a deep neural network-based intelligent forecasting method for multi-dimensional economic indexes in smart cities. Specifically, a deep neural network with three-layer structure is developed as the backbone methodology. For empirical analysis, the real-world data from “Chengdu–Chongqing Economic Circle” in China from 2012 to 2022 are selected as the main simulation scenario. Four major indexes are selected as the main research object: gross product (GDP), per capita GDP, GDP growth rate and the proportion of tertiary industry in GDP. The experimental results show that the proposal can well deal with such forecasting problem from a data-driven perspective, with a proper forecasting effect on historical data.

Consumer electronics (CE) companies have the potential to significantly contribute to the advancement of autonomous vehicles and their accompanying technology by providing security, connectivity, and efficiency. The Consumer Autonomous Vehicles market is set for significant growth, driven by growing awareness and implementation of sustainable practices using computing technologies for traffic flow optimization in smart cities. Businesses are concentrating more on eco-friendly solutions, using AI, communication networks, and sensors for autonomous city navigation, giving safer and more efficient mobility solutions in response to growing environmental concerns. Object detection is a crucial element of autonomous vehicles and complex systems, which enables them to observe and react to their surroundings in real-time. Multiple autonomous vehicles employ deep learning (DL) for detection and deploy specific sensor arrays custom-made to their use case or environment. DL processes sensory data for autonomous vehicles, enabling data-driven decisions on environmental reactions and obstacle recognition. This paper projects a Galactical Swarm Fractals Optimizer with DL-Enabled Object Detection for Autonomous Vehicles (GSODL-OOAV) model in Smart Cities. The presented GSODL-OOAV model enables the object identification for autonomous vehicles properly. To accomplish this, the GSODL-OOAV model initially employs a RetinaNet object detector to detect the objects effectively. Besides, the long short-term memory ensemble (BLSTME) technique was exploited to allot proper classes to the detected objects. A hyperparameter tuning procedure utilizing the GSO model is employed to enhance the classification efficiency of the BLSTME approach. The experimentation validation of the GSODL-OOAV technique is verified using the BDD100K database. The comparative study of the GSODL-OOAV approach illustrated a superior accuracy outcome of 99.06% over present innovative approaches.

Energy is now seen as a significant resource that develops abundant on the world economy, with short supply and development. A study found that renewable energy systems are needed to prevent shortages. Hence, all the focus in this study to decrease electricity consumption and reduce the overall completion times for a regular console in green technology networks was an efficient and scalable production genomic solution. A Renewable green energy resources smart city (RGER-SC) framework is proposed that used a multi-target evolutionary algorithm was hybridized to be effective and calculated arithmetically in this study. This work deals with fostering renewable energy incorporation by adjusting federal charges to increase the energy accounting practitioners. Besides, this report analyses the timely generation of delay-tolerant demands and the maintenance of district heating at network infrastructure. In comparison, capacity differentials between consumers and information centres are considered and evaluated using the Renewable green energy resources smart city (RGER-SC) framework for energy conservation and controlled task management at an industrial level.

In many countries, energy-saving and emissions mitigation for urban travel and public transportation are important for smart city developments. It is essential to understand the impact of smart transportation (ST) in public transportation in the context of energy savings in smart cities. The general strategy and significant ideas in developing ST for smart cities, focusing on deep learning technologies, simulation experiments, and simultaneous formulation, are in progress. This study hence presents simultaneous transportation monitoring and management frameworks (STMF ). STMF has the potential to be extended to the next generation of smart transportation infrastructure. The proposed framework consists of community signal and community traffic, ST platforms and applications, agent-based traffic control, and transportation expertise augmentation. Experimental outcomes exhibit better quality metrics of the proposed STMF technique in energy saving and emissions mitigation for urban travel and public transportation than other conventional approaches. The deployed system improves the accuracy, consistency, and F-1 measure by 27.50%, 28.81%, and 31.12%. It minimizes the error rate by 75.35%.

There has been considerable research on smart cities and on adapting technology for businesses, governments, citizens and other stakeholders. However, scant attention has been paid to determine how disruptive technologies influence smart cities. Through a systemic literature review, this paper provides a point-by-point consideration of ‘nested’ disruptive technologies, namely, the Internet of Things (IoT), autonomous vehicles (AV), artificial general intelligence (AGI) and 5G networks (5G), and the factors affecting their deployment in the context of smart cities. This paper also discusses why these are important disruptive technologies for smart cities and how these technologies influence them. The main challenges of implementing these disruptive technologies have been identified in the literature and are discussed in this paper. This paper also offers suggestions on the implementation of these disruptive technologies for practitioners of smart cities, so that they can consider them while digitalizing smart cities. In addition to discussing research implications, the paper also throws light on theoretical contributions and recommends ways to leverage these disruptive technologies for smart cities.

Over the past decade, Open Innovation (OI) literature has extended its scope beyond strictly economical contexts to the context of societal value creation. This has given rise to the notion of distributed knowledge as a driver for sustainable innovation development. Over the past 15 years, the concept of Urban Living Labs (ULLs) has gained popularity to put social OI into practice. Hence, this concept is often applied in urban environments to support transition processes that try to tackle so-called wicked problems. However, a fuzzy understanding of this ULL concept still exists, due to an unclear understanding of its value creation mechanics. Therefore, this paper aims to both conceptualise and gain a better understanding of how ULLs are instrumentalised and create value. This is studied from the perspective of “ecosystem stakeholders” that participate in ULL projects. These insights are obtained through a case study with a multimethod qualitative research approach. The main data sources are a series of 20 semi-structured key-informant interviews, four focus groups, and participatory observation. The results show that the value creation for the participating stakeholders can be summarised in two main clusters: (1) the ULL as a way to build and strengthen the capacities of participating stakeholders; and (2) the ULL as a way to facilitate purpose driven fulfilment in urban transition processes.

Urban social life increasingly depends on a functioning social and technical infrastructure. Protecting infrastructures from natural disasters and extreme weather events, which are especially a result of climate change, has become an important topic in international research in the last years [Birkmann et al. (2016). Journal of Extreme Events, 03: 1650017]. In order to increase efficiency, the connections and interrelations between infrastructure components have been strengthened more and more, promoting the growth of large-scale interconnected systems. This in turn has resulted in uncontrollable potential risks as the functionality of each component now depends on an ever-increasing number of other infrastructure components. If one infrastructure component fails, this causes extensive cascades carrying the original failure over to successive components. This can, for example, cause large-scale failures in the rail network due to a shortage of fuel supply in large power plants resulting in impaired grid stability and thus a blackout, which in turn affects communications infrastructure, water supply, and other sectors. The growing complexity of connected infrastructures across multiple sectors and the use of continuously evolving technologies pose great challenges for researchers and providers regarding the prediction of cascading disruptions in the event of a component failure. Cascade modeling is an essential tool for improving the system’s resilience, since the security of the population’s supply is already disrupted when only parts of infrastructure systems are deactivated for test purposes. Accordingly, development and improvement of modeling approaches for the depiction of failure scenarios plays an essential role in planning and operating infrastructure systems. Against this background, we are developing an intersectoral graph-theoretical model framework for cascading failures in large-scale infrastructure systems in order to identify hotspots of high criticality. This work extends the study of criticality as a function of network centrality metrics. Network centrality metrics are applied to the electricity sector to examine and comprehend their correlation. The proposed criticality model for the graph model is then extended to a geographical dependence model. Predicting and analyzing criticality is important to support urban planners in setting up independently operational infrastructure systems and to accomplish the transformation of existing vulnerabilities into resilient adaptive structures.

This paper explains the potential implications of digital interventions for social accountability through the Smart Cities Mission (SCM) in India. The SCM represents India’s transition to a new political economy based on rapid urbanization and wide-scale application of digital technology to reform public service delivery while simultaneously creating new markets for urban transformation. Within this wider context, the paper considers the future of democratic practices in urban governance. We argue that while citizen-led accountability practices were trialed by civil society organizations since 1990s, the SCM presented unique opportunity and challenge to institutionalize these tools within the framework of multi-scalar governance — between central-, state- and local-level institutions and between communities, private vendors and public bodies. Zooming into the four smart city projects — Indore, Kakinada, Panaji and Ranchi — we explain how each city engaged with citizen groups, communities and civil society and what their experiences tell us about the prospects and challenges of democratizing digital urban futures.

In-vehicle human object identification plays an important role in vision-based automated vehicle driving systems while objects such as pedestrians and vehicles on roads or streets are the primary targets to protect from driverless vehicles. A challenge is the difficulty to detect objects in moving under the wild conditions, while illumination and image quality could drastically vary. In this work, to address this challenge, we exploit Deep Convolutional Generative Adversarial Networks (DCGANs) with Single Shot Detector (SSD) to handle with the wild conditions. In our work, a GAN was trained with low-quality images to handle with the challenges arising from the wild conditions in smart cities, while a cascaded SSD is employed as the object detector to perform with the GAN. We used tested our approach under wild conditions using taxi driver videos on London street in both daylight and night times, and the tests from in-vehicle videos demonstrate that this strategy can drastically achieve a better detection rate under the wild conditions.

Despite the diffuse, diverse, and controversial meaning of the “smart city” concept, its proponents assume that a smart city is capable of better addressing the challenges of urban resilience and sustainability. The evolution of “smart cities” toward a widespread use of artificial intelligence (AI) techniques, processes, and devices indicates that a new urban AI regime will expand in the coming years, and therefore it is necessary to analyze both the benefits and the risks of this strategy. This disruptive urban AI regime (which I describe as “destructive creation”) generates a critical mass of negative externalities in the development process of smart cities, derived initially from the contemporary hegemonic nature of technological innovation in urban socioeconomic processes. Such a disruptive thrust represents a risk for the centrality of public spaces and the civic friction between humans that should occur, according to Jane Jacobs, in the core of the urban as self-organized complexity. The intelligent disruption (destructive creation) produced by AI systems is no longer avoidable, although we can debate about what kind of sustainability we want for ourselves and for future generations. There should be analyses and discussions around the notion of “smart and just sustainability” as a normative horizon setting the framework to decide what technological innovations and what AI applications we need.