Smart Cities, Volume 9, Issue 7 (July 2026) – 15 articles

Urban traffic anomaly detection is essential for intelligent transportation systems, particularly in smart city environments where fast identification of abnormal events can improve road safety and traffic management. This work proposes a novel ULSTM-driven architecture that explicitly models temporal dependencies across consecutive traffic frames to achieve more stable and temporally coherent reconstructions. The proposed framework leverages sequential spatio-temporal representations to improve the distinction between normal traffic patterns and anomalous events. To further enhance reliability, we introduce a Hybrid Weighted Fusion strategy that synergistically combines structural, perceptual and pixel-wise metrics. The framework’s parameters are optimized using a Discrete Dirichlet Sampling approach, achieving a peak F1 Score of 70.28%. Evaluations were conducted on a manually curated traffic anomaly dataset with frame-level annotations. Experimental results demonstrate that the ULSTM framework significantly outperforms frame-independent generative models by suppressing high-frequency reconstruction noise, providing a robust solution for real-world smart city deployments. While highly effective in complex scenarios, the proposed framework is strictly applicable to highly dynamic traffic environments with active motion, as static background ensembles can degrade performance. Full article

Background: Despite a growing awareness of the obvious disadvantages of car travel for drivers (e.g., cost and health) and society (e.g., external costs and infrastructure maintenance), commuting by car to work is the prevailing mode of transport in the UK. Methods: A digital model of work and home locations in England and Wales using OSRM was created to compare the effective accessibility of e-bikes and cars for those working in an office five days a week. This accessibility metric is extended by the effective speed concept. The latter accounts for time spent travelling alongside the time spent working to offset commuting costs. Results: s-pedelecs offer, in various settings, the highest effective accessibility scores. Commuting by car is only advisable for individuals with a higher wage and time availability. If only the variable cost of the car commute is considered, then driving becomes the most expedient choice for many. Conclusions: Commuting by car is undoubtedly the fastest option for wealthy individuals. Whereas those less affluent in terms of time and money may opt for an e-bike, as commuting by car may not yield the commonly anticipated savings. Full article

Firefighters operate in high-risk, rapidly evolving environments where exposure to extreme heat, toxic gases, and physiological stress significantly increases the likelihood of injury and fatality. This study systematically maps the emerging research landscape of real-time artificial intelligence (AI)-driven digital twins for environmental and physiological risk prediction in firefighting contexts. A combined bibliometric and qualitative content analysis was conducted using peer-reviewed literature retrieved from the Web of Science database (2010–2025). Bibliometric techniques were used to identify publication trends and thematic clusters, while content analysis examined the integration of sensing technologies, AI models, and digital twin architectures. The results reveal four dominant technological domains shaping the field: AI-enabled fire risk modeling, sensor data acquisition systems, IoT-based digital infrastructures, and predictive analytics for disaster simulation. Sensing technologies such as temperature, gas, particulate matter, thermal imaging, heart rate, and blood oxygen monitoring form the foundational data layer, while machine learning and deep learning models enable real-time hazard prediction and situational awareness. Digital twin architectures serve as the integration layer, fusing multi-source data and supporting simulation-based decision-making. Despite rapid advancements, key gaps persist, including limited integration of environmental and physiological data, insufficient predictive capabilities, a lack of standardized architectures, and minimal development of human-centered decision-support systems. This study provides a structured synthesis of current technologies and identifies future research directions toward integrated, explainable, and real-time digital twin systems to enhance firefighter safety and operational resilience. Full article

The transition from traditional siloed to intelligent cities allows for the deployment and management of information and communication technologies in the urban context to be driven by holistic sustainability requirements rather than technical ones such as feasibility and fragmented, siloed operational patterns. This work proposes a multi-dimensional decision-making framework to manage a smart city as an urban cognitive Cyber–Physical System (CPS) across environmental, economic, and social sustainability pillars, metrics and their trade-offs. A methodology based on Deep Reinforcement Learning (DRL), specifically adopting Deep Q-Networks (DQNs), is proposed to represent and assess sustainability pillar dependencies and their interplay. A case study on Low-Power Wide-Area Network planning, deployment and management in a Sicilian municipality has been developed to demonstrate the effectiveness of the proposed approach in dealing with the dynamics and non-linear dependencies of the sustainability pillars. Full article

Leakage of water pipelines in urban underground utility tunnels poses a major threat to tunnel safety and operation; therefore, voiceprint recognition is adopted for real-time pipeline monitoring. Although utility tunnels are less affected by outdoor interference, multiple internal noises still degrade voiceprint recognition accuracy. To address this problem, this study proposes an enhanced StarGAN-based denoising method using a single network to handle multiple noise types. Unlike the original StarGAN-VC2 developed for voice conversion, the proposed model is specifically redesigned for leakage voiceprint denoising by integrating MFCC-based representation, a lightweight bottleneck, channel attention, residual feature preservation, and U-Net-style reconstruction. Experimental and engineering application results show that the denoised signals achieve improvements of 3–7 dB in SNR, 3–4 dB in PSNR, and 3–4 in SSR. The model also demonstrates strong generalization capability and plug-and-play applicability, enabling integration with conventional denoising and voiceprint recognition networks. These results indicate that the proposed method can effectively suppress diverse utility tunnel noises while preserving leakage-related voiceprint features. Full article

Intelligent transportation systems (ITSs) and traffic control promise substantial efficiency and safety improvements but frequently face public resistance and driver compliance issues. Many drivers perceive such control measures as unfair or unnecessary, despite measurable system-wide benefits. This study investigates how chronoception—the subjective perception of time—affects user acceptance of ITS control strategies and how signal design can be adapted to reduce perceived delays. We introduce a chronoceptive design framework that integrates insights from cognitive psychology into traffic-control design. Using ramp metering as a case study, we conduct virtual experience stated preference experiments with 101 participants, comparing standard and chronoceptive ramp metering designs featuring shorter signal cycles, three-phase lights, and countdown timers. The results show that chronoceptive signal designs significantly improve user acceptance (by up to 12%) and reduce perceived waiting times, despite identical or slightly longer objective travel times. These findings reveal a systematic bias between factual and perceived benefits and highlight the potential of chronoceptive design to enhance compliance and fairness perception. This study contributes a new human-centred design paradigm for traffic control that aligns objective performance with user perception and outlines how chronoception and perceived fairness can be operationalised in traffic control. The source code and survey data can be found open-source on GitHub. Full article

Modern construction sites generate large volumes of visual, spatial, and operational data that can support data-driven project delivery, improved monitoring, and reliable decision-making within the smart-city built environment. However, construction management still relies heavily on human observation and manual interpretation, limiting the transformation of field data into structured information for sustainable urban infrastructure delivery. Multimodal generative artificial intelligence (GenAI) offers a promising approach for interpreting construction-site data, yet its performance under real site conditions remains insufficiently examined, particularly across tasks requiring different levels of visual recognition, contextual reasoning, and professional judgment. This paper presents a field-based evaluation of multimodal GenAI models using 1186 images collected from 17 active construction sites. The evaluation considered three widely available general-purpose multimodal GenAI assistants: Gemini, ChatGPT, and Microsoft Copilot. Four major construction management tasks were assessed: construction activity identification, progress tracking, execution defect detection, and safety hazard identification. The GenAI outputs were compared against ground-truth evaluations established by human experts. The results suggest that GenAI performs more reliably in descriptive and visually explicit tasks than in judgment-intensive tasks requiring engineering interpretation. Activity identification achieved the strongest performance, whereas execution defect detection was the most challenging. The findings indicate that GenAI can support visual site interpretation and improve construction management efficiency, while highlighting the need for human oversight and verification in smart-city infrastructure delivery. Full article

This work explores how graph theory and graph neural networks can support the strategic planning of rail network expansions using only publicly available city data, applied to the São Paulo Metropolitan Region. The methodology consolidates information from multiple public sources, develops a catchment-area formula to estimate potential passenger demand, applies Random Forest to identify the most relevant demographic features, and implements a GraphSAGE model that derives predictive capability from network topology together with socioeconomic features and origin–destination trips. The demand approximation was checked against observed station boardings, with predicted and observed rankings in agreement. The GraphSAGE model achieved an R² of 0.874 ± 0.042 when predicting the proxy demand indicator, with minimal overfitting, outperforming the Random Forest baseline and achieving accuracy comparable to an XGBoost baseline while overfitting substantially less; this performance remained stable under spatial cross-validation. The model is computationally efficient and requires no rail-system-specific information beyond topology, making it suitable for the fast, low-cost comparison of expansion proposals rather than as a replacement for detailed transport demand models. It was used to evaluate eleven real projects and proposals for the São Paulo Metropolitan Region. Employment, residences, and destinations where people go to eat together represent about 65% of the model’s predictive capacity. Full article

Artificial intelligence (AI), building information modeling (BIM), and digital twins are increasingly transforming construction sites into smart, data-driven environments that support safer, more efficient, and more sustainable building and urban infrastructure delivery. However, site-level spatial decision-making related to site layout optimization (SLO) remains constrained by fragmented data environments, limited interoperability, and weak integration between planning, monitoring, and adaptive decision-making. This study presents a systematic literature review of how AI, BIM, and enabling digital technologies are being applied to support smart construction site management, site-level spatial decision-making, and SLO-related applications. A Scopus-based search conducted in October 2025 identified 169 records, of which 63 studies were retained following PRISMA-guided screening. Because explicit SLO studies remain limited, the review synthesizes both directly relevant SLO studies and contextually relevant enabling studies with clear implications for smart and sustainable construction operations. The review combines bibliometric analysis, thematic content analysis, and cross-functional technology mapping to examine the intellectual structure of the field, the main operational domains addressed, and the dominant technological convergences supporting intelligent site decision-making. The findings show that the field is expanding rapidly but remains unevenly consolidated, with greater evidence concentration and practical readiness in real-time digital twin and spatial data management, automated monitoring, and proactive safety intelligence than in closed-loop logistics coordination and autonomous mobility. Across application domains, the dominant technology convergences combine machine learning and deep learning with multidimensional BIM, frequently extended through digital twins, sensors, cloud platforms, UAVs, simulation tools, and GIS-related infrastructures. The review further shows that the main barriers to deployment are not merely algorithmic, but also relate to interoperability, data quality, implementation complexity, human oversight, and limited field validation. Overall, this study provides a structured synthesis of evidence concentration, practical readiness, dominant patterns, and unresolved gaps of AI-BIM-enabled smart construction site management, and outlines directions for more interoperable, human-centered, and field-validated systems that support sustainable smart building and urban infrastructure delivery. Full article

Smart-port decarbonisation requires operations-research decision support under day-ahead uncertainty. We present a rolling-horizon Model Predictive Control Energy Management System, formulated as a Mixed-Integer Linear Program with five forecast streams, and benchmark it against a deterministic rule-based controller on an identical configuration. A full-year proof-of-concept at the Port of Ancona (8760 hourly steps over the 2024 Italian Day-Ahead Market, 6.5 MWp PV, 1.0 MWh BESS) combines realised 2024 market, photovoltaic and auxiliary-demand series with a post-AFIR projected cold-ironing demand—the dominant load—and is therefore an operational proof-of-concept rather than a fully metered baseline. The principal MPC outcome is structural: anticipatory dispatch raises the mean BESS state of charge from 13.6% to 46.0% and cuts residence at the minimum SoC from 81% to 6% of hours. The forecasting layer attains sub-7% sMAPE on cold-ironing-loaded demand and 9–18% on the remaining streams (seasonal MASE₂₄ ≤ 0.74 on demand and price streams). At the relay-constrained 0.08 C pilot, the realised savings is 0.44% (€14,463 yr⁻¹; 95% moving-block bootstrap CI [€12,842, €15,742]); benchmarked against an enhanced rule-based controller that is itself permitted price-threshold grid charging, the residual value of predictive optimisation is €5652 yr⁻¹ (0.17%), with the remainder of the gap being the value of enabling grid charging. A C-rate sweep shows the savings doubling to 0.93% at 0.5 C, and a direct 20 MWh/±10 MW simulation yields a €0.57 M yr⁻¹ gross arbitrage savings whose net value, after a realistic battery-degradation penalty, is substantially smaller. Controller-level operational CO₂ rises marginally (+6.2 t, +0.13%), an effect distinct from—and dwarfed by—the system-level cold-ironing decarbonisation. The framework is reproducible in open-source Python (PuLP/HiGHS) from the actual data and is portable to other single-node smart city energy hubs. Full article

Smart-city advanced metering infrastructure enables utility-scale remote analytics, but some forms of under-registration closely resemble lawful changes in demand and are hard to model as anomalies. We study a narrow, physically motivated event family at the single-meter level, namely multiplicative under-registration with unknown onset (a shunt-like attack), in which recorded active energy is approximately scaled by a factor $\alpha <1$ after a change-point while the daily-profile structure and spectral shape remain invariant. We formalize the problem and develop a physics-guided detector family based on weighted daily-profile regression (GLS) and its robust variant (RGLS), with quality-control filters, spectral-consistency checks, and an optional reactive-channel gate, designed to stay selective under confounders such as rooftop photovoltaics, electric-vehicle charging, and heat-pump onsets. On a device-disjoint Low Carbon London benchmark (487 households) the preferred GLS detector attains precision $0.915$, recall $0.978$, and $F_1=0.945$ at $\alpha =0.10$ while keeping the non-theft suspected rate near $1\%$; a cross-dataset check on Open Power System Data with real EV/PV/heat-pump overlays yields zero false alarms on all 72 cases, and Mendeley and WPuQ benchmarks add a second large family and a reactive-channel test. We compare against external baselines (classical change-point detection, Isolation Forest, autoencoder, LSTM, gradient boosting, and a supervised statistical pipeline) on the same protocol: generic anomaly detectors fail on this shape-preserving attack, and supervised models match the detector only in-distribution while, unlike it, failing to transfer to real lawful confounders. All metrics carry bootstrap confidence intervals, and a full reproducibility bundle accompanies the submission. Full article

Urban mobility planning in smart cities requires sophisticated simulation tools, yet their complexity often creates a technical barrier for non-expert stakeholders. This paper presents a novel architecture that integrates generative artificial intelligence with digital twin technology to create an accessible and decision-support prototype. The framework employs a conversational AI agent based on Gemini 2.5 Flash Lite to interpret natural language intentions and translate them into validated simulation parameters. A critical safety layer, built using Pydantic, ensures that the agent’s stochastic outputs adhere to strict technical schemas and predefined logical bounds before execution. The underlying digital twin, developed with SimPy, NetworkX, and OSMnx, features a multi-source data integration strategy that includes demographic density (INE), tourism activity (ISTAC), and high-resolution traffic statistics (TomTom) to calibrate vehicle behavior. The architecture was technically demonstrated through a Technology Readiness Level (TRL) 4 proof-of-concept in Las Palmas de Gran Canaria, simulating multimodal scenarios including buses, the future MetroGuagua (BRT), and pedestrian flows. Results demonstrate a 96% success rate in intent recognition and configuration mapping, with end-to-end execution times under 20 min for a 19 h simulated day. This study demonstrates that LLM-driven orchestration, coupled with automated data pipelines and a decoupled microservice architecture, can lower technical barriers to urban simulation, which could support broader participation in future smart city deployments. Full article

Smart city mobility is increasingly governed by a techno-solutionist logic that prizes data, automation, and efficiency, often at the expense of public trust, social legitimacy, and lived experience. This article argues that the fate of a mobility transition appears to depend less on the sophistication of the technology than on the pace and posture of change. Building on the CalmMobility framework and on Weiser and Brown’s concept of calm technology, it develops the idea of calm smart mobility—a human-paced, options-first approach in which innovation enters everyday life gradually and with credible alternatives already in place, so that residents are not asked to continuously adapt. The framework’s three pillars (Comprehensiveness; Pacing–Sequencing–Inclusion; Future-Readiness) are mapped onto four recurring challenges of smart mobility (Policy Layering, Affective Mismatch, Governance Silos, and the Future-Readiness Gap) and then used as a descriptive analytical lens to characterize seven documented implementations across economic, spatial, mass-transit, service, and platform interventions and four world regions: the Stockholm congestion charge, the London ULEZ expansion, the Barcelona superblocks, Bogotá’s TransMilenio bus rapid transit and Ciclovía, Seoul’s Cheonggyecheon restoration and bus reform, Helsinki’s Whim Mobility-as-a-Service, and Sidewalk Toronto. Presented through a comparison table, a positioning map, and adoption trajectories rather than rankings, the characterization suggests that the provision of alternatives, the sequencing and pace of change, and the genuineness of co-creation are more closely associated with smooth adoption than the type of instrument deployed. The article is conceptual and framework-building. The cases illustrate and probe the framework instead of validating it, and a testable central hypothesis is specified for future empirical work. Calm smart mobility is offered as a transferable, citizen-centred logic for guiding smart city mobility transitions at a human pace. Full article

Urban land use intensity (U-LUI) is a widely used term for describing urban development processes, yet its conceptualisation and measurement remain inconsistent. Existing approaches focus on isolated dimensions, such as structural density, functional activity, and socio-economic indicators, resulting in limited comparability and weak integration across scales and data sources. This paper reviews and synthesises current approaches to U-LUI with a focus on remote sensing (RS), in situ data and emerging urban data sources. It analyses definitions, related concepts of urban intensity and existing monitoring frameworks at national, European and global levels, and compares methodological approaches for observing U-LUI. Based on this synthesis, U-LUI is defined as a continuous, multidimensional and spatio-temporally dynamic property of urban systems that reflects the intensity of anthropogenic use. To operationalise this concept, the paper develops an integrative, trait-based framework comprising six indicator families: traits, genesis, structure, taxonomy, function and socio-economics. The proposed framework is illustrated and supported through the synthesis of existing RS approaches, urban monitoring concepts and representative examples from the literature, demonstrating its potential for consistent and scalable U-LUI assessment. These dimensions link physically observable characteristics with functional and contextual aspects of urban systems and provide a basis for more consistent quantification and comparison. The results highlight key challenges for U-LUI monitoring, including limited conceptual harmonisation, incomplete integration of dimensions and the need for improved data integration. The proposed framework supports more coherent and scalable assessments of U-LUI in research, monitoring and planning contexts. Full article

Artificial intelligence is reshaping employment in smart cities, yet centralized hiring platforms can deepen exclusion for persons with disabilities through privacy risk, biased models, weak multilingual support, and limited accommodation awareness. Because disability-related records are highly sensitive, no single institution holds enough representative data to train fair models, and centralizing such data is rarely permissible across borders. We propose FedAgent-Chain, a framework that integrates federated learning, blockchain-based auditability, multilingual processing, rule-based agentic services, and human-in-the-loop governance, extended with an education-to-employment module that builds individualized, accessible job-readiness pathways. Institutions across Saudi Arabia, the United States, China, and Europe train shared models without exchanging raw data. In a prototype evaluation on synthetic records over five seeds, the framework reached a mean F1 of 0.7207 (95% CI: [0.6506, 0.7909]), comparable to a centralized logistic-regression baseline while preserving data locality, with a formal $(\epsilon =3.2,\delta ={10}^{-5})$ differential-privacy guarantee after 20 rounds. Multi-dimensional fairness regularization lowered disability-category and work-mode disparity by 32.3% and 40.3% relative to local-only training. We report the fairness behavior transparently, including a case where the penalty does not outperform standard FedAvg on disability-category disparity, and we position cross-institutional integration with accountable governance, rather than raw metric superiority, as the central contribution. Full article