Search Results (648)

While classical clustering methods, particularly k-means, produce powerful and practical solutions based on metric distances between data points, they can be limited in complex, nonlinear, and structurally disordered datasets. This study proposes a hybrid topological–metric clustering framework, referred to as Hybrid-NHTSI, that integrates persistent homology-based structural information into the clustering update process. The method is based on the Topological Cluster Separation Index (TCSI), a persistent homology (PH)-based metric for topological separation. In addition to TCSI, the proposed framework uses the Normalized Topological Cluster Separation Index (NTCSI), the Hybrid Topological Clustering Index (HTCI), and the Normalized Hybrid Topological Separation Index (NHTSI) to evaluate clustering performance from both geometric and topological perspectives. In the proposed approach, while the topological separation between clusters is increased, intra-cluster geometric scattering is controlled by a regularization term. This formulation enables the extraction of clusters that are consistent not only topologically but also geometrically. The performance of the method was evaluated on synthetic circles-and-moons benchmark datasets under different noise and overlap levels, and on the UCI Human Activity Recognition real sensor dataset. The experimental results showed that DBSCAN achieved the strongest overall performance on the density-favorable synthetic benchmark, which is consistent with the nonconvex and density-separable structure of the data. However, Hybrid-NHTSI produced higher NTCSI, HTCI, and NHTSI values than classical metric/geometric baselines such as k-means, Spectral Clustering, and Agglomerative Clustering. Pairwise statistical comparisons based on NHTSI confirmed that these improvements were significant against several competing methods. In the real-data experiment, although Spectral Clustering achieved the highest ARI value, Hybrid-NHTSI obtained the highest NTCSI, HTCI, and NHTSI values and significantly outperformed all competing methods in terms of NHTSI. The findings demonstrate that considering both metric and topological information together, rather than relying solely on metric or topological information, provides a more structurally informed evaluation and optimization mechanism for complex clustering problems. Accordingly, the proposed method should not be interpreted as a universally superior clustering algorithm across all metrics, but rather as a topology-aware hybrid refinement framework that enriches metric-based clustering with persistent homology. Full article

Although Random Forest (RF) is a widely adopted ensemble method for classification, preserving diversity among decision trees and reducing the negative impact of underperforming trees remain major challenges. This paper proposes DWRF-MVC, a novel RF optimization framework that integrates DBSCAN clustering with a multi-metric performance-weighted voting mechanism. Using a dissimilarity metric derived from classic RF outcomes, the framework applies DBSCAN to cluster decision trees, selects top-performing representatives from each cluster, and retains noise points to maintain diversity. A weighted voting mechanism is then introduced to further improve model performance. Experimental results on 14 benchmark datasets show that DWRF-MVC achieves an average accuracy improvement of 7.45% over classical RF with a 91.79% reduction in the number of trees. Moreover, DWRF-MVC surpasses two cutting-edge methods by 1.82% and 3.83% in average accuracy, respectively. Full article

The launch of sixth-generation (6G) mobile networks is expected to introduce significant variability in Quality of Service (QoS), driven by environmental conditions, traffic heterogeneity, device diversity, and network slicing policies. Existing clustering-based QoS analysis methods rely primarily on using only KPI variables, such as latency, throughput, jitter and packet loss datasets, and classical geometric validity metrics, providing limited insight into the stability, predictive capability, and operational relevance of discovered clusters. To address these limitations, this study proposes a context-aware QoS modelling framework and a unified network-centric cluster evaluation protocol. A dataset comprising 2345 observations is constructed by integrating QoS indicators with contextual and operational variables, including weather conditions, time of day, geographic region, traffic type, device class, and slice identity. Four clustering paradigms, k-means, DBSCAN, spectral clustering, and Deep Embedded Clustering (DEC), are evaluated using both classical metrics and three proposed evaluation measures: Contextual Cluster Stability (CCS), QoS-Regime Predictive Consistency (QPC), and Slice-Level Reliability Separation (SLRS). The results demonstrate that classical clustering metrics alone are insufficient for assessing QoS regime quality. While DEC achieves strong structural performance in latent space, all methods exhibit near-zero predictive consistency and weak reliability separation. These findings reveal a consistent divergence between structural clustering quality and operational usefulness, indicating that unsupervised clustering alone is insufficient for QoS prediction and reliability-aware decision-making. The proposed framework provides a foundation for evaluating clustering methods in context-sensitive network environments and highlights the need for integrating temporal modelling and reliability-aware learning in future 6G network optimisation systems. Full article

Urban low-altitude unmanned aerial vehicle (UAV) logistics networks face critical operational bottlenecks due to complex three-dimensional spatial blockages, continuous communication diffraction, and severe vulnerability to information-layer threats such as Automatic Dependent Surveillance—Broadcast (ADS-B) signal anomalies. To address these interconnected challenges, this paper proposes an event-driven, cloud–edge collaborative digital twin framework to guarantee continuous multi-link communication and flight safety. The architecture operates through a dual-tier “Teacher–Student” paradigm. Under secure conditions, a cloud digital twin acts as a high-capacity “Teacher,” employing Density-Based Spatial Clustering of Applications with Noise (DBSCAN) to partition heterogeneous user topologies. It then utilizes an energy-guided stochastic diffusion sampling (EGSDS) method to refine initial macroscopic routing, generating precise, outage-free global trajectories by systematically minimizing non-line-of-sight (NLoS) observation penalties and kinematic regularization costs. To counteract signal anomalies, a distributed Time Difference of Arrival (TDOA) anchor network continuously validates UAV coordinate integrity. If a threshold is breached, control authority is instantly transferred to the UAV’s edge digital twin. This resource-constrained edge tier relies on a localized “Student” network trained via progressive distillation. By compressing the computationally heavy iterative diffusion process into a rapid one-step inference model, the UAV autonomously generates a secure, short-range emergency path that strictly adheres to minimum communication thresholds. Once interference clears, the cloud seamlessly regains control to complete the logistics mission. Experimental results demonstrate that the proposed scheme significantly outperforms conventional heuristic routing methods in cloud-based scenarios. Furthermore, the edge-based distillation mechanism substantially improves the overall trajectory survival rate under signal anomalies, ensuring resilient and continuous logistics operations. Full article

The rapid development of Internet of Things technologies has accelerated the deployment of smart home systems. However, perception solutions based on visual sensors remain constrained by illumination sensitivity, occlusion, and privacy concerns. Frequency-modulated continuous-wave (FMCW) millimeter-wave radar provides a promising alternative because it operates independently of lighting conditions, is robust to environmental changes, and preserves user privacy. To address multiple-extended-target tracking in cluttered indoor environments, this paper proposes a high-accuracy tracking algorithm that combines an improved Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm, an optimized Nearest-Neighbor Data Association (NNDA) scheme, and an Extended Kalman Filter (EKF). The improved DBSCAN algorithm introduces spatial-extent constraints, velocity-consistency checks, and candidate-cluster validation to cluster raw radar point clouds and convert extended targets into representative point targets with little additional computational cost. The optimized NNDA scheme then integrates clustering information into the association process, improving the matching accuracy between existing tracks and current measurements. Finally, the EKF estimates the state of each target from the associated measurements. Real-world experiments show that the proposed algorithm achieves tracking errors below 0.4 m in typical motion scenarios, maintains continuous tracking in two-person crossing scenarios, and reaches 93.3% counting accuracy in five-person scenarios. These results outperform the tracking system based on the commercial Texas Instruments (TI) IWR6843ISK millimeter-wave radar evaluation board. The proposed method offers a reliable and privacy-preserving sensing solution for smart homes, elderly care, and intelligent building applications. Full article

Urban freight distribution is essential for supplying commercial activities, but it also increases pressure on curb space, vehicular circulation, pedestrian movement, and public space management, especially in medium-sized cities where dedicated loading and unloading infrastructure is often limited. Although recent literature emphasizes the need for data-driven urban logistics planning, empirical evidence from intermediate Latin American cities remains scarce. This study develops and applies a spatial-operational framework to characterize urban freight distribution, identify patterns of conflict and informality, estimate loading and unloading bay requirements, and prioritize intervention areas in a medium-sized city. A quantitative, observational, exploratory–descriptive, and correlational design was applied, based on 642 georeferenced loading and unloading operations recorded through a digital field survey. The analysis integrated data cleaning, descriptive and inferential statistics, logistic models, an operational sustainability risk/pressure index, DBSCAN spatial clustering, logistics pressure and sustainable transport priority indices, and a capacity model based on average daily operations. The results revealed spatial concentration of logistics activity, a predominance of light trucks, frequent use of paid parking areas and roadways, and a high presence of operational conflicts. The study provides a replicable and planning-oriented framework for prioritizing curbside management interventions for sustainable urban freight distribution in medium-sized Latin American cities. Full article

Vibration-based Structural Health Monitoring (SHM) exploits automated Operational Modal Analysis (OMA) to track changes in modal parameters over time for subsequent statistical pattern recognition and anomaly detection. However, weak excitation, measurement noise, non-stationarities, non-linearities, and model inaccuracies can jeopardize the reliability of automated OMA and pollute the modal parameter time series with a number of outliers or spurious estimates. These have an impact on statistical pattern recognition and consequently, the anomaly detection accuracy. Thus, a preliminary data cleansing to enhance the robustness of modal parameter tracking is imperative to ensure the reliability of SHM outcomes. Clustering techniques represent an attractive solution to automatically identify underlying data patterns and discriminate possible spurious results. However, the curse of dimensionality is often an issue in the application of such techniques to time series of experimentally identified modal parameters. To mitigate this issue and, at the same time, the computational efforts, the present study proposes an innovative approach leveraging clustering techniques coupled with mode-pairing constraints for robust and automatic tracking of modal parameters in the context of vibration-based SHM applications. Different clustering algorithms have been embedded in the proposed data processing strategy and applied to a real dataset collected on a full-scale structure under operational conditions. The comparative performance assessment demonstrated how DBSCAN outperforms other clustering methods in the context of the proposed approach, allowing the effective separation of the physical poles from the spurious ones even in the presence of closely spaced modes and highly polluted feature space. Full article

Underwater target detection via side-scan sonar is vital for defense and economy but hindered by sparse targets, high data costs, and feature extraction difficulties due to textureless acoustic data and limited samples. To overcome these limitations, particularly for few-shot, small-object detection, we propose a Spatial Distribution Probability-Guided Detection Framework to aid Unmanned Underwater Vehicles (UUVs) in precise localization and clustering. The framework features a novel module that leverages a pre-trained Vision Foundation Model (DINOv3) to generate spatial distribution probability maps, guiding a Transformer-based network for accurate detection with scarce data. Additionally, it incorporates a Target Position Calculation Module and a DBSCAN-based post-processing module to determine global geographic coordinates and cluster discrete points, respectively. Experiments were conducted on both a Public Mine Detection Dataset and a self-collected dataset containing simulated mines and buoys. Ablation studies and comparison experiments demonstrated that the proposed guidance mechanism significantly improves detection performance. Furthermore, two comb-search missions verified that the system could accurately locate and cluster targets, distinguishing real targets from false detections (noise). These results confirm the framework’s efficacy in enabling high-precision perception and autonomous operations for complex underwater inspection tasks. Full article

In maritime electronic support measures (ESMS), multipath-scattered pulses are often suppressed during pulse sorting, although their delay, amplitude, and angular differences may provide information for passive scatterer localization. This paper investigates a front-end path-classification task positioned after emitter-level clustering and before multipath-assisted passive localization. Pulses produced by the same non-cooperative emitter but received through different propagation paths are classified as direct-path or multipath-scattered pulses. The task is formulated as supervised binary classification over PDW sequences. Five representative solution families are evaluated under a common protocol: FCM, DBSCAN, temporal sequence analysis (TSA), Single-LSTM, and a residual two-layer unidirectional LSTM with residual fusion. The input features are RF, PA, PW, PRI, TOA, DOA, and ΔTOA; the recurrent models use class-weighted training to address the direct/scattered class imbalance. Across 36 coupled scenarios with pulse-loss rates from 0% to 50% and parameter-jitter levels from 0.0 to 1.0, the residual LSTM obtains the highest average macro-F1 score (0.8717), compared with Single-LSTM (0.7726), DBSCAN (0.7686), TSA (0.6511), and FCM (0.5917). Repeated training over four random seeds yields a validation macro-F1 of 0.9821 ± 0.0007 on the original validation set. The ablation results indicate that ΔTOA is the principal temporal cue in this setting, while LayerNorm, residual fusion, class weighting, and augmentation mainly contribute to optimization stability and perturbation robustness. Measured-data verification suggests that the learned temporal representation can provide usable inputs for subsequent scatterer localization. The current validation is limited to a one-emitter simulation and rule-assisted measured-data annotation; mixed-emitter validation and quantitatively calibrated localization evaluation remain subjects for future study. Full article

Berry thinning is a fundamental operation in modern vineyard management, and future robotic thinning systems have the potential to reduce labor intensity and improve operational consistency. However, automated berry thinning under field conditions is still constrained by insufficient berry-level segmentation accuracy, difficulty in recognizing occluded berries, and high missed-detection rates for small berries. These limitations mainly arise from dense berry arrangements, severe mutual occlusion, and the subtle visual features of small targets. To address these challenges, this study developed a lightweight grape berry instance segmentation and thinning decision-support method based on YOLOv8n-seg. A two-stage knowledge distillation strategy, using Mask R-CNN and YOLOv8l-seg as teacher models, was combined with 30% backbone pruning to improve the recognition of occluded and small berries while maintaining model efficiency. Subsequently, the DBSCAN clustering algorithm was used to analyze berry centroid coordinates and equivalent diameters extracted from instance segmentation masks, thereby generating preliminary thinning-target recommendations based on local berry density and berry size. The model was trained and evaluated on a self-constructed dataset containing 330 valid grape bunch images collected in 2025 from Yongming Vineyard, Lin’an District, Hangzhou, Zhejiang Province, China. The results showed that the optimized YOLOv8n-seg model achieved a box $mAP50\text{-}95$ of 0.8945 and a mask $mAP50\text{-}95$ of 0.7910, with an inference speed of 119.19 $FPS$ and 3.26 M parameters on an NVIDIA RTX 3060 Laptop GPU. Compared with the original YOLOv8n-seg model, the optimized model improved mask $mAP50\text{-}95$ by 1.20 percentage points, increased inference speed by 71.79 $FPS$, and reduced the number of parameters by 2.38 M. These results indicate that the proposed method improves grape berry instance segmentation performance while achieving a favorable balance among segmentation accuracy, lightweight characteristics, and inference efficiency. The proposed framework provides an offline RGB-based visual perception and preliminary thinning decision-support method for future grape berry thinning robots. However, because the current dataset was collected from Shine Muscat grape bunches at the berry enlargement stage in a single vineyard using the same imaging setup, the results should be interpreted as preliminary evidence under the specific cultivar, growth stage, vineyard, and imaging conditions of this study. Further validation across different grape cultivars, growth stages, vineyards, production seasons, camera systems, embedded platforms, and real robotic thinning operations is still required. Full article

This study addresses a modified continuous multi-reservoir scheduling problem characterized by a high-dimensional continuous decision space, strong time-varying storage constraints, strict terminal storage closure requirements, and a highly nonconvex composite objective. To solve this challenging problem, a multi-stage collaborative memetic algorithm based on CVT-MAP-Elites and clustering gradient (MCMA-CCG) is proposed. The framework consists of three tightly coupled stages: an exploration stage based on CVT-MAP-Elites to preserve diverse high-potential elites, a clustering stage using DBSCAN with a customized noise-retention strategy, and a refinement stage that combines DE with gradient-enhanced SLSQP to perform accurate exploitation. Under a unified experimental setting, MCMA-CCG was evaluated against several representative optimization algorithms, including DE, GA, SAPHTLR, HBMO, MFA, and MBWOHHO, over 30 independent runs. The updated results show that MCMA-CCG consistently achieves the best overall performance in both the four-cycle and five-cycle reservoir scheduling scenarios while also exhibiting superior empirical runtime and feasibility behavior. In the four-cycle case, it attained a best value of 6.08 × 10³, an average of 5.97 × 10³, and a standard deviation of 4.62 × 10¹; meanwhile, it produced feasible solutions in 26 of 30 runs, achieved a mean feasibility distance of 1.20 × 10⁻³, and required only 54.91 s on average under the 30,000-function-evaluation budget. In the more challenging five-cycle case, it attained a best value of 7.60 × 10³, an average of 7.44 × 10³, and a standard deviation of 7.55 × 10¹; it still generated feasible solutions in 19 of 30 runs, with a mean feasibility distance of 4.84 × 10⁻³ and an average runtime of 93.80 s under the 50,000-function-evaluation budget. By contrast, all baseline algorithms produced no fully feasible runs under the same feasibility criterion and generally required longer wall-clock time. Ablation studies further demonstrate that the superior performance of MCMA-CCG does not arise from any single module, but from the effective synergy among quality-diversity exploration, cluster-guided seed extraction, and gradient-assisted local refinement. These results confirm both the numerical superiority and the physical interpretability of the proposed framework for complex continuous multi-reservoir scheduling problems. Full article

Forecasting urban traffic requires consideration of both general temporal patterns and local dynamics, which depend on specific sensors. In this paper, we develop and evaluate a cluster-based forecasting architecture for the PEMS04 and PEMS08 traffic datasets. First, sensors are clustered using the DBSCAN algorithm based on robust descriptors (mean, standard deviation, and upper quantile statistics regarding traffic intensity, lane occupancy, and speed). Second, forecasting models are trained and compared across three operational horizons: 15, 30, and 60 min (H = 3/6/12 with 5 min granularity). The comparison includes Historical Average (HA), Global LSTM, CNN-LSTM, and Cluster-Aware LSTM. The results show that Cluster-Aware LSTM provides the best MAE on short and medium horizons (H = 3, H = 6), while HA remains the strongest on the long horizon (H = 12), indicating strong seasonal stability that extends beyond a single hour. Cluster-level confidence matrices reveal a systematic concentration of difficulties in groups where congestion prevails. Explainability diagnostics (accuracy and stability) demonstrate very stable attributions and stronger accurate signals in the cases of the most challenging clusters. Overall, the study supports a hybrid operational strategy: deep, cluster-adaptive forecasting for short- to medium-term horizons and a robust seasonal buffer for forecasting longer-term horizons. Full article

Riveting quality inspection is critical for ensuring structural integrity and safety in aerospace, automotive, and civil engineering, as rivet defects during the riveting process may cause catastrophic failures in structural connections. This study focuses on the detection method for multi-type rivet head defects and aims to improve the performance of feature extraction and classification for various head defects. The research is carried out to develop a lightweight classification network with a Dynamic Screening Self-Attention (DSSA) mechanism for 3D point clouds. To achieve the rivet head dataset, we employ Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering to extract each target head data from the dataset of riveted plates. The head dataset can be further simplified using the Non-Maximum Eigenvalue Curvature Method (NMECM). In this way, redundant information can be reduced. The PointGhost network is then designed for the classification of head defects. It contains a sampling module with a Virtual Block Sampling (VBS) mechanism that reduces the computational complexity. In addition, there exists a feature extraction module with a Grouped Pointwise Convolution Ghost (GPC-Ghost) lightweight model that performs local and global feature learning, together with the DSSA mechanism to enhance the riveted head defects. Lastly, the severity levels of rivet protrusion and indentation are quantified using Principal Component Analysis (PCA) and the Total Least Squares (TLS) fitting algorithm. In terms of the experiment, six popular lightweight models are compared, wherein GPC-Ghost shows more significant performance, achieving a 4.31% higher mean accuracy than PointNet++, with less computational cost of 0.66 GFLOPs. Based on the comparative analysis of six attention mechanisms and seven classification networks, the PointGhost model possesses the highest mean accuracy of 99.49%, with an average misclassification rate of 1.19%. The method can balance the accuracy and efficiency effectively, demonstrating its potential for engineering inspection. Full article

Euler deconvolution is widely used to estimate the three-dimensional locations of geological sources from magnetic anomaly data. However, traditional Euler deconvolution is commonly performed on planar gridded data, whereas magnetic surveys in mountainous and hilly areas are often acquired over undulating terrain. Reducing such data to a horizontal plane before derivative calculation can introduce transformation errors, and derivative calculation by the conventional FFT-based (wavenumber-domain) method becomes less suitable under variable topographic conditions. To address these limitations, this study proposes an equivalent source method based on correlation imaging for calculating the spatial derivatives required by Euler deconvolution directly from magnetic anomaly data acquired over undulating terrain. An improved Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm is further introduced to suppress spurious Euler solutions and retain valid source location estimates. Synthetic model experiments show that the proposed equivalent source method yields more accurate derivatives than the conventional FFT-based method under undulating terrain conditions. The improved DBSCAN algorithm effectively removes spurious solutions while preserving clustered solutions associated with geological sources. The proposed workflow was further applied to magnetic data from a coal fire zone in Shenmu, Shaanxi Province, China, to estimate the 3D locations of underground magnetic sources related to underground coal fires. The interpreted source locations are consistent with surface validation evidence, demonstrating the applicability of the proposed method for magnetic anomaly interpretation in complex topographic settings. Full article

For enhancing the level of refinement of short-horizon wind-storage power prediction, this paper introduces an advanced BiLSTM prediction model integrating data preprocessing based on the density-based clustering technique known as DBSCAN, partial least squares regression (PLSR), and particle swarm optimization (PSO). In this paper, “wind-storage power” refers to the net power output of a wind farm integrated with a battery energy storage system (BESS), where the measured data already embed the effects of charge/discharge operations. First, outage and missing data are removed from the historical dataset. DBSCAN is then employed to identify abnormal samples in wind-storage power and meteorological variables, such as wind speed, wind direction, atmospheric pressure, temperature, and humidity, and linear regression is used to correct the detected noise points. Correlation analysis is further conducted to identify the most relevant meteorological inputs, namely wind speed, wind direction, and atmospheric pressure. Next, the PLSR model is applied to generate the preliminary prediction of wind-storage output. On this basis, the BiLSTM network is employed to predict the residual error, which mainly reflects the nonlinear characteristics not captured by the preliminary prediction. Meanwhile, PSO is implemented to determine the most suitable core hyperparameters for the BiLSTM architecture. Ultimately, the preliminary PLSR result is corrected by the predicted residual to obtain the final wind-storage power prediction. The DBSCAN parameters are systematically selected via a k-distance plot (ε = 0.9, MinPts = 2.5), and the PLSR number of components is set to A = 3 based on five-fold cross-validation. Case studies show that, for the 24 h prediction horizon, the proposed method improves prediction accuracy by 2.29%, 11.47%, and 5.54% compared with the BP, Wavelet-LSTM, and standard LSTM models, respectively. Furthermore, statistical significance is confirmed by Diebold–Mariano tests and 10-run confidence intervals. Full article