Search Results (686)

Identifying noise sources in exceedance-triggered audio is essential for targeted source tracing and sustainable urban social noise governance. While accurate models require massive labeled data, the acoustic complexity, high redundancy, and imbalanced class distributions of real-world recordings incur prohibitive manual annotation costs, hindering their widespread application in IoT networks. To tackle this bottleneck, we present a label-efficient active learning framework designed to minimize annotation costs by dynamically selecting the most valuable audio samples. Specifically, rather than treating uncertainty, class balance, and diversity as separate query criteria, it encodes uncertainty and dynamic class-aware learning needs into a weighted acoustic feature space, so that diversity-based selection can be performed in a unified manner. Experiments on the UrbanSound8K benchmark and a realistic exceedance-triggered monitoring dataset demonstrate consistent label-efficiency advantages over mainstream methods. Notably, our approach reaches 98% of the fully supervised upper bound on the real-world dataset while reducing the training annotation workload by 85.0% compared to random sampling. On the real-world dataset, the proposed framework yields higher F1-scores for several challenging under-represented categories and reduces the misclassification of dominant sound events relevant to social noise source tracing. Furthermore, cross-site generalization experiments reveal rapid localized adaptation to new monitoring environments, reaching the fully supervised upper bound with only 13% of the target-domain training data. Overall, this study provides a scalable and cost-effective classification framework for urban noise monitoring, offering practical support for noise regulatory authorities and city managers in more targeted noise source tracing and governance. Full article

Smart cities are increasingly dependent on interconnected transportation systems; however, this connectivity exposes smart mobility networks to significant cybersecurity risks. Traditional Intrusion Detection Systems are ill-equipped for this environment, as they are designed for isolated systems or fixed network boundaries. Thus, they struggle to secure the complex and heterogeneous smart mobility networks, where various protocols and resource-constrained edge devices require more adaptive solutions. To address this limitation, we propose a novel hybrid deep learning framework that combines convolutional neural networks for spatial feature extraction, long short-term memory networks for temporal pattern recognition, and an attention mechanism for adaptive feature weighting, together forming a context-aware Intrusion Detection System. Our approach is evaluated across six benchmark datasets spanning vehicular networks, IoT ecosystems, cloud computing, and 5G environments—VeReMi Extension, CICIoV2024, Edge-IIoTset, UNSW-NB15, Car Hacking, and 5G-NIDD—a deliberately diverse selection that represents the heterogeneous nature of real-world smart mobility networks. Empirical evaluation using three different random seeds reveals the proposed framework achieves detection accuracy exceeding 98% on each dataset, a mean F1 score of 98.94%, and an inference latency of just 4.96 ms per sample. Our results show that the proposed model achieves consistently high detection performance across six heterogeneous benchmark datasets, making it a potentially robust candidate for real-time intrusion detection in smart mobility systems. Full article

This study presents a novel hybrid Bat-Artificial Bee Colony (BA-ABC) algorithm for energy-efficient optimization in Wireless Sensor Networks (WSNs), addressing the critical challenge of limited node energy and network lifetime degradation. The proposed framework integrates the rapid local convergence of the Bat Algorithm with the robust global exploration of the Artificial Bee Colony to achieve unified optimization of clustering and routing processes. An adaptive multi-objective fitness function is developed to balance energy consumption, network lifetime, and communication efficiency, enabling dynamic, efficient resource utilization across varying network conditions. Comprehensive simulations conducted in MATLAB R2024a demonstrate that the proposed BA-ABC algorithm significantly outperforms conventional and recent optimization approaches. The results show a reduction in total energy consumption of approximately 22-30%, an improvement in network lifetime of 18-25%, and a latency reduction of nearly 24% compared to baseline methods such as Ant Colony Optimization (ACO). Statistical validation, including confidence intervals and hypothesis testing, confirms the robustness, stability, and consistency of the proposed framework across multiple simulation runs. Unlike existing hybrid and machine-learning-based approaches, the BA-ABC algorithm achieves high optimization performance without introducing excessive computational overhead or complex training requirements, making it suitable for resource-constrained WSN environments. Furthermore, the proposed method demonstrates strong scalability and adaptability, positioning it as a practical solution for real-world applications, including smart cities, environmental monitoring, and healthcare systems. This work contributes to the advancement of intelligent WSN optimization by providing a scalable, adaptive, and computationally efficient hybrid framework aligned with emerging trends in next-generation IoT-enabled networks. Full article

Short-term load forecasting plays a pivotal role in modern power system operations yet it remains challenging due to the complex spatiotemporal dependencies in load data. This paper proposes a dual-head attention residual network (DARNet) that significantly advances STLF through three key innovations: (1) a hybrid encoder combining 1D-CNN and GRU architectures to simultaneously capture the local load patterns and long-term temporal dependencies, achieving a 28% better locality awareness than that of conventional approaches; (2) a novel dual-head attention mechanism that dynamically models both the inter-temporal relationships and cross-variable dependencies, reducing the feature engineering requirements; and (3) an autocorrelation-adjusted recursive forecasting framework that cuts the multi-step prediction error accumulation by 33% compared to that with standard seq2seq models. Extensive experiments on real-world datasets from three Chinese cities demonstrate DARNet’s superior performance, outperforming six state-of-the-art benchmarks by 21–35% across all of the evaluation metrics (MAPE, SMAPE, MAE, and RRSE) while maintaining robust generalization across different geographical regions and prediction horizons. Full article

Deep learning has emerged as an effective tool for automatic waste classification, supporting cleaner cities and more sustainable recycling systems. Because environmental protection is central to the United Nations Sustainable Development Goals (SDGs), improving the sorting and processing of everyday waste is a practical step toward this broader objective. In many real-world settings, however, waste is still sorted manually, which is slow, labor-intensive, and prone to human error. Although convolutional neural networks (CNNs) can automate this task with high accuracy, many state-of-the-art models remain too large and computationally demanding for low-cost edge devices intended for deployment in homes, schools, and small recycling facilities. In this work, we investigate lightweight waste-classification models suitable for TinyML deployment while preserving competitive accuracy. We first benchmark multiple CNN architectures to establish a strong baseline, then apply complementary compression strategies including quantization, pruning, singular value decomposition (SVD) low-rank approximation, and knowledge distillation. In addition, we evaluate an RL-guided multi-teacher selection benchmark that adaptively chooses one teacher per minibatch during distillation to improve student training stability, achieving up to 85% accuracy with only 0.496 M parameters (FP32 ≈ 1.89 MB; INT8 ≈ 0.47 MB). Across all experiments, the best accuracy–size trade-off is obtained by combining knowledge distillation with post-training quantization, reducing the model footprint from approximately 16 MB to 281 KB while maintaining 82% accuracy. The resulting model is feasible for deployment on mobile applications and resource-constrained embedded devices based on model size and TensorFlow Lite Micro compatibility. Full article

We propose and experimentally validate an automatic urban water leakage detection architecture that leverages dark fiber links already deployed in telecommunication networks in underground conduits in the vicinity of water pipelines. The sensing stage relies on a differential-phase coherent optical time-domain reflectometry interrogator enhanced with optical pulse compression to improve sensitivity. Building on this vibration acquisition stage, automatic leakage detection algorithms are implemented by searching for leak-induced activity in the frequency domain, which is well suited to revealing leakage-related features. After acquiring a baseline calibration to characterize normal-condition vibrations at each sensing position, leakage candidates are identified by comparing distribution-based metrics computed over multiple measurements against the corresponding baseline statistics. Two automatic leakage detection strategies are developed. First, low-complexity feature-based metrics are implemented, enabling continuous monitoring with minimal computational requirements. Second, an autoencoder-based anomaly detection technique is introduced, which also relies on location-specific normal-condition calibration but reduces the dependence on prior knowledge of the expected leakage vibration signatures. A real-world field trial on an urban network demonstrates reliable detection and localization using controlled leak events generated in the field, with measurements performed over a 17 km sensing fiber and an effective spatial resolution of 2.6 m. Benchmarking against a commercial punctual electro-acoustic leak detector yields consistent trends. Overall, the proposed system could complement existing technologies by enabling automated, continuous city-scale monitoring over already deployed dark fiber infrastructure. Full article

The primary objective of water supply systems is to ensure a reliable delivery of water in appropriate quantity, quality, and pressure. Designing water supply networks involves determining their geometric layout and capacity by selecting suitable pipe routes and sizes. Since the network layout influences pipe diameters, routing and sizing should be conducted simultaneously. This paper presents an application of the fractal-based method for designing water distribution networks (WDNs) in which the pipe routes and diameters are mathematically justified. The proposed approach takes into account the total pipe length, the total angular change in pipeline routing, construction costs, and water delivery priorities. Additionally, the method was tested under both quasi-real conditions (in the virtual city of Micropolis) and in real-world complex settlement. The results of the sizing process were also compared with those obtained using the genetic algorithm approach. Verification of the proposed method in both quasi-real and real-world scenarios showed a smaller total pipe length (by 9.53% and 12.17%), a lower maximum water age (11 and 87 h), and a comparable energy demand. The SRS method enables simultaneous determination of pipe diameters and layout routing, while ensuring proper hydraulic performance of the network due to the application of evolution theory rules which results in quasi-optimal solutions for WDN designing. Full article

With the widespread adoption of electric vehicles (EVs), the management and scheduling of charging and discharging play a crucial role in the performance of both the electricity grid and electric vehicles. Particularly in the context of peak shaving, valley filling, and the promotion of the energy internet infrastructure, efficient management of the EV charging and discharging process is vital. This study investigates the control and management issues surrounding EV charging and discharging, proposing a management strategy based on deep reinforcement learning. By constructing an intelligent decision-making model, it integrates factors such as the operating conditions of the electrical grid, user behavioral preferences, EV battery characteristics, and renewable energy outputs. The study collects real-world EV usage data from a city, establishing an experimental environment to simulate the interaction between the electricity grid and electric vehicles. Using techniques such as Deep Q-Network (DQN) and policy gradients, it constructs a decision network to explore charging and discharging strategies across different time scales and load situations. Experimental results show that this strategy, compared to traditional charging schedule methods, can effectively reduce energy loss during charging, enhance battery life, and balance the grid load, while suppressing demand peaks, thus achieving intelligent optimization and reliability enhancement of the charging and discharging process. Particularly, an adaptive charging power adjustment technique within the strategy can dynamically adjust the charging power according to the real-time status of the EV and grid load without affecting the user’s daily use, thereby achieving the dual objectives of efficient energy saving and economy. The research also quantitatively analyzes battery degradation characteristics and the continuity of charging to ensure the long-term sustainability of the charging strategy. The research findings are significant for understanding and guiding the practical management of EV charging and discharging. Full article

This study utilizes digital transformation and patent data from A-share listed companies on the Shanghai and Shenzhen stock exchanges in China between 2011 and 2021 to examine the influence of digital transformation on the quality of cross-regional collaborative innovation. The findings reveal that the cooperative innovation network exhibits pronounced small-world characteristics. In terms of spatio-temporal evolution, China’s urban collaborative innovation network demonstrates a notable quadrilateral spatial structure and has evolved toward a multicenter pattern. Moreover, the advancement of digital transformation positively contributes to both the quality and quantity of cross-regional cooperative innovation. By enhancing the relational embeddedness among cities, digital transformation facilitates improved outcomes in collaborative innovation. Furthermore, when the volume of digital patent applications surpasses a certain threshold, its positive effect on the quality of cross-regional collaborative innovation accelerates. These results provide empirical evidence from a major emerging economy, offering insights that can inform policies and strategies in other regions undergoing digital transition. The mechanisms identified, such as network structure evolution and relational embeddedness, contribute to a broader understanding of how digital transformation shapes innovation dynamics across geographical boundaries in a globalized knowledge economy. Full article

Mexico City’s Metro Line 7 is a critical north–south artery within one of the world’s largest metro systems, yet it suffers from persistent operational inefficiencies, including chronic overcrowding and extended passenger travel times. This research employed a data-driven discrete-event simulation model built in SIMIO to analyze the passenger dynamics of Line 7. The model was grounded in a comprehensive dataset of approximately 280,000 daily passengers over one year. Key innovations included modeling station-specific passenger arrivals as non-stationary Poisson processes with time-varying rates calculated at 15-min intervals and incorporating empirically derived walking times within stations. The simulation framework replicated the system’s operational logic, including train movements, passenger boarding and alighting, and complex transfer behaviors at interchange stations, while accounting for the influence of the broader metro network on Line 7’s passenger flows. The simulation results, derived from 100 replications, quantified severe systemic inefficiencies. The average total travel time for a passenger using Line 7 was 81.17 min. However, the ideal in-motion travel time was calculated to be only 53 min, revealing that passengers spend a disproportionate amount of time waiting. This yielded a travel time efficiency of just 65.3%. The model identified specific bottlenecks at key transfer stations like Tacubaya and San Pedro de Los Pinos, where platform utilization reaches full capacity, directly causing the excessive queuing times that degrade the overall passenger experience. This study demonstrated that the primary issue is not the speed of trains but the systemic inability to manage passenger flow during peak demand, leading to critical capacity shortfalls at specific stations. The simulation provides a quantitative tool for diagnosing these inefficiencies and offers a robust platform for prototyping and evaluating strategic interventions, such as optimized timetables and resource allocation, before costly real-world implementation. Full article

Quantitative evaluation of public transit networks (PTNs) with complex-network models informs route optimization and operational adjustments. Prior studies emphasize large cities and pay limited attention to small-sized urban systems. This study examines the bus network of Cangzhou City, Hebei Province, China, to broaden the empirical scope and characterize PTNs in smaller cities. The dataset for this study comprises route and stop records, passenger boarding logs, and bus GPS traces. We develop a general workflow for bus data cleaning and completion. To characterize the dynamic bus network and compare it with the static network, we construct a static network and Directed Weighted Dynamic Network I (DWDN I) using the L-space method, and we construct Directed Weighted Dynamic Network II (DWDN II) using the P-space method. We calculated network metrics including degree, weighted degree, clustering coefficient, path length, network diameter, network efficiency, and small-world coefficient. The principal results show that: (1) at the macroscopic level, the dynamic PTN tracks passenger demand, as the average degree, weighted average degree, and clustering coefficient fluctuate in concert with passenger flows; (2) key stations concentrate in the urban core, and stations with high weighted degree display pronounced spatial autocorrelation; (3) the exponential form of the weighted-degree distribution indicates that the examined bus network is not scale-free, while the dynamic network’s small-world coefficient exceeds that of the static network across time periods, reflecting stronger small-world characteristics. This study integrates network and spatial attributes of the PTN to offer an exploratory case for investigating public transit networks in third-tier cities. The findings can inform comparable studies and offer practical guidance for bus operators. Full article

This study presents the results of an archaeometric investigation of white marble votive reliefs from the Roman city of Pautalia (modern Kyustendil, Bulgaria), with the aim of clarifying patterns of material selection, production, and connectivity within the eastern provinces of the Roman Empire. Although these votive monuments, primarily dated to the 2nd and 3rd centuries AD, have long been examined from stylistic, iconographic, and epigraphic perspectives, the provenance of the marble used in their manufacture has remained largely unexplored. A total of 27 votive reliefs from urban and extra-urban sanctuary contexts were analysed using a multi-method approach combining petrographic analysis, stable isotope ratios (δ¹³C and δ¹⁸O), and trace element analysis by ICP-MS, and compared against an extensive geological reference database of ancient marble quarries. The results indicate a clear predominance of local and regional marble sources, alongside a limited but meaningful presence of imported material. This distribution pattern supports the existence of local workshops operating in or near Pautalia, which relied primarily on nearby quarry sources while selectively incorporating imported marble, likely through the reuse of pre-existing blocks or workshop offcuts rather than through systematic long-distance supply. These findings underscore Pautalia’s role as a regional production centre and as a nodal point within wider networks connecting the Aegean world and the Balkan hinterland. Full article

The development of AI-driven automated driving functions requires vast amounts of diverse, high-quality data to ensure road safety and reliability. However, both the manual collection of real-world data and creation of 3D environments are costly, time-consuming, and hard to scale. Most automatic environment generation methods still rely heavily on manual effort, and only a few are tailored for Advanced Driver Assistance Systems (ADAS) and Automated Driving Systems (ADS) training and validation. We propose an automated generative framework that learns ground-truth features to reconstruct 3D environments from a road definition and two simple parameters for country and area type. Environment generation is structured into three modules—map-based data generation, semantic city generation, and final detailing. The overall framework is validated by training a perception network on a mixed set of real and synthetic data, validating it solely on real data, and comparing performance to assess the practical value of the environments we generated. By constructing a Pareto front over combinations of training set sizes and real-to-synthetic data ratios, we show that our synthetic data can replace up to $85\%$ of real data without significant quality degradation. Our results demonstrate how multi-layered environment generation frameworks enable flexible and scalable data generation for perception tasks while incorporating ground-truth 3D environment data. This reduces reliance on costly field data and supports automated rapid scenario exploration for finding safety-critical edge cases. Full article

Modern urban transport systems face the critical challenge of fully integrating regional and international hubs into local mobility strategies. This article addresses the role of airports in shaping sustainable urban mobility, with a specific focus on their inclusion in Sustainable Urban Mobility Plans (SUMPs). Despite airports being major generators of passenger and freight traffic, they are often treated as isolated “transport islands” in spatial planning. The primary objective of this research is to develop and validate an original method for assessing the integration and transport accessibility of airports using the AirportSustainIndex. The methodology is based on a mathematical Weighted Sum Model (WSM), integrating twelve technical, economic, and environmental criteria, including travel times and costs for public vs. private transport, frequency of rail and bus connections, availability of electric vehicle infrastructure, and tariff integration. The analysis is supported by Geographic Information Systems (GIS) tools and OpenStreetMap data, allowing for a precise reflection of real-world network accessibility. The study covers two significant aviation hubs in Poland: Katowice Airport in Pyrzowice and Poznań-Ławica Airport. The results reveal a paradox: Katowice Airport, despite its significant distance from the agglomeration center (approx. 36 km), achieved a markedly higher sustainability index (0.554) than Poznań-Ławica Airport (0.301), which is located close to the city center (approx. 7 km). Key factors determining this outcome include the high frequency of metropolitan bus lines (“M” lines), the implementation of new rail infrastructure, and a coherent parking policy for low-emission vehicles. The article demonstrates that physical distance from the center is not the primary barrier to building sustainable mobility, provided that high intermodality and integration within the SUMP framework are ensured. The presented research tool is universal and can be applied by policymakers and urban planners to optimize airport-city connectivity, a necessary condition for achieving EU climate goals in the transport sector. Full article

Dynamic Wireless Power Transfer (DWPT) is emerging as critical smart city infrastructure for sustainable urban mobility, enabling electric vehicle charging while driving. However, DWPT introduces complex fault scenarios requiring intelligent monitoring. Existing fault diagnosis approaches for wireless power transfer systems face three key complexities: (1) they are limited to static charging with only 2–4 fault categories, failing to address the time-varying coupling dynamics and segmented coil handover transients inherent in dynamic charging; (2) they lack integration with the host distribution grid, ignoring grid-side disturbances that propagate to charging stations; and (3) they offer only reactive detection without predictive capability for incipient fault management. This paper presents a deep neural network (DNN)-based fault diagnosis framework utilizing multi-station sensor fusion for DWPT systems integrated with the IEEE 13-bus distribution network to address these limitations. The system monitors 36 sensor features across three charging stations, employing feature-level concatenation with station-specific normalization for multi-station fusion, achieving 97.85% classification accuracy across eight fault types. Unlike static charging, the framework explicitly models time-varying coupling dynamics due to vehicle motion, including segmented coil handover effects. A digital twin provides dual-horizon prediction: long-term forecasting (24–72 h) for incipient faults and real-time detection under 50 ms for critical protection, with fault probability outputs and ranked fault lists enabling actionable maintenance decisions. The DNN outperforms SVM (92.45%), Random Forest (94.82%), and LSTM (96.54%) with statistical significance ($p<0.001$), while maintaining model inference latency of 4.2 ms, suitable for edge deployment. Circuit-based analysis provides analytical justification for fault signatures, and practical parameter acquisition methods enable real-world implementation. Five case studies validate robustness across highway, urban, and grid disturbance scenarios with detection accuracies exceeding 95%. Full article