Abstract Objectives: Computational pathology has emerged as an attractive option for improving risk stratification in prostate cancer (PCa), but current approaches either lack interpretability or focus solely on tumor morphology, potentially limiting their utility. We aimed to identify an interpretable, immune microenvironment-derived computational pathology biomarker for PCa. Methods: We retrospectively identified two independent cohorts (Discovery and Validation) with localized PCa who underwent radical prostatectomy (RP) and had digitized H&E-stained whole-slides images (WSIs) and longitudinal outcomes data. We identified a third cohort from The Cancer Genome Atlas (TCGA) with localized PCa which was treated with RP and had WSIs, bulk RNA sequencing, and whole-exome sequencing. Immune cells were identified from WSIs using a publicly available deep learning model (CellViT), and spatially dense immune clusters were quantified using density-based spatial clustering of applications with noise (DBSCAN). CIBERSORTx was utilized for immune cell deconvolution and TRUST4 for immune receptor repertoire reconstruction from bulk RNA sequencing. Cox proportional hazard regression was used to examine associations between clinicopathologic features and the primary outcome of time to distant metastasis (DM), as well as secondary outcomes of biochemical recurrence (BCR) and overall survival (OS). Results: Median follow-up periods for the Discovery (n=272) and Validation (n=218) Cohorts were 12.6 and 8.1 years, respectively. In the Discovery Cohort, median age was 63, 14% had Gleason 8-10 disease, 94% had pT2-T3a disease, and median prostate-specific antigen level at diagnosis was 6.2 ng/mL. Median immune cell proportion was 4.3% (interquartile range 3.0-5.9%), and median immune cluster density was 2.4 per 400 mm2 of tissue (interquartile range 0-7.1). Similar values were observed in the Validation Cohort. In both cohorts, immune cell proportion was not associated with BCR, DM, or OS (P>=0.09). In the Discovery Cohort, while increasing immune cluster was not associated with BCR (P>=0.10), it was independently associated with a decreased risk of DM for Gleason 8-10 (adjusted hazard ratio [AHR] 0.42, 95% confidence interval [CI] 0.19-0.93) but not Gleason 6-7 patients (AHR 1.26, 95% CI 0.77-2.05; Pint=0.020). Similar results were observed in the Validation Cohort, where increasing immune cluster was not associated with BCR (P>=0.10) but was associated with a lower risk of DM in Gleason 8-10 disease (AHR 0.60, 95% CI 0.37-0.98), though not Gleason 6-7 (AHR 1.19, 95% CI 0.74-1.91; Pint=0.043). In TCGA Cohort (n=326), immune cluster was not associated with somatic alterations. For Gleason 8-10 but not Gleason 6-7 disease, high-cluster samples were enriched for CD8+ T cells, activated memory CD4+ T cells, and Tregs (P<=0.037), as well as clonal T cell populations (P<=0.039). Conclusions: Our findings nominate immune spatial clustering as a novel, interpretable computational pathology biomarker and provide insights into the unique immune features of high-grade PCa. Citation Format: David D. Yang, Aya Abdelnaser, Alexander J. Haas, Jeremiah Wala, Alfred A. Barney, Eddy Saad, Jett P. Crowdis, Cora A. Ricker, Seifeldin Awad, Bora Gurel, Jihye Park, Martin T. King, Paul L. Nguyen, Toni K. Choueiri, David J. Einstein, Steven P. Balk, Alok K. Tewari, Johann S. de Bono6, Keyan Salari, Mary-Ellen Taplin, Chin-Lee Wu, Eliezer M. Van Allen. . Immune spatial organization predicts metastasis risk in aggressive localized prostate cancer [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Innovations in Prostate Cancer Research and Treatment; 2026 Jan 20-22; Philadelphia PA. Philadelphia (PA): AACR; Cancer Res 2026;86(2_Suppl):Abstract nr PR001.

Abstract The search for extraterrestrial intelligence (SETI) commensal surveys aim to scan the sky to detect technosignatures from extraterrestrial life. A major challenge in SETI is the effective mitigation of radio frequency interference (RFI), a critical step that is particularly vital for the highly sensitive Five-hundred-meter Aperture Spherical radio Telescope (FAST). While initial RFI mitigation (e.g., removal of persistent and drifting narrowband RFI) are essential, residual RFI often persists, posing significant challenges due to its complex and various nature. In this paper, we propose and apply an improved machine learning approach, the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm, to identify and mitigate residual RFI in FAST–SETI commensal survey archival data from 2019 July. After initial RFI mitigation, we successfully identify and remove 36,977 residual RFIs (accounting for ∼77.87%) within approximately 1.678 s using the DBSCAN algorithm. This result shows that we have achieved a 7.44% higher removal rate than previous machine learning methods, along with a 24.85% reduction in execution time. We finally find interesting candidate signals consistent with previous studies, and retain one candidate signal following further analysis. Therefore, DBSCAN algorithm can mitigate more residual RFI with higher computational efficiency while preserving the candidate signals that we are interested in.

Acute lymphoblastic leukemia (ALL) is the most common childhood malignancy. While space-time clustering of ALL cases has been suggested, only one prior study has examined clustering by genetic subtype. We investigated space-time clustering of childhood ALL in Sweden, both overall and by genetic subtype. The cohort included 1,629 children age 0-18 years diagnosed with ALL between 1992 and 2017, comprising 1,446 B-cell precursor ALL (BCP-ALL) and 183 T-cell ALL (T-ALL) cases. Two BCP-ALL subgroups were analyzed: high hyperdiploidy (HeH, n = 466) and ETV6::RUNX1 (n = 225). The Unbiased Knox Test and Unbiased Combined Knox Test were used to assess space-time clustering at the municipality level, accounting for multiple testing and population shifts. The Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm was applied to identify significant clusters. Logistic regression was used to evaluate demographic differences between clusters, including age, sex, and birth order. Significant space-time clustering was observed in the HeH subgroup for both place and date of birth (p = 0.005) and place and date of diagnosis (p = 0.011), at space-time thresholds of 40km/18 months and 30km/24 months, respectively. No clustering was detected in the overall BCP-ALL group, T-ALL group, or the ETV6::RUNX1 subgroup. Space-time clustering at birth and diagnosis was observed in the HeH subgroup, suggesting potential etiologic heterogeneity in BCP-ALL. These findings support further investigation of environmental and infectious exposures across immunophenotypes and genetic subtypes in larger cohorts.

Changes in climate and ocean pollution has prioritized monitoring of ocean surface behavior. Ocean drifters, which are floating sensors that record position and velocity, help track ocean dynamics. However, environmental events such as oil spills can cause abnormal behavior, making anomaly detection critical. Unsupervised learning, combined with deep learning and advanced data handling, is used to detect unusual behavior more accurately on the NOAA Global Drifter Program dataset, focusing on regions of the West Coast and the Mexican Gulf, for time periods spanning 2010 and 2024. Using Density-Based Spatial Clustering of Applications with Noise (DBSCAN), pseudo-labels of anomalies are generated to train both a one-dimensional Convolutional Neural Network (CNN) and a Long Short-Term Memory (LSTM) network. The results of the two models are then compared with bootstrapping with block shuffling, as well as 10 trials with bar chart summaries. The results show nuance, with models outperforming the other in different contexts. Between the four spatiotemporal domains, a difference in the increasing rate of anomalies is found, showing the relevance of the suggested pipeline. Beyond detection, data reliability and efficiency are addressed: a RAID-inspired recovery method reconstructs missing data, while delta encoding and gzip compression cut storage and transmission costs. This framework enhances anomaly detection, ensures reliable recovery, and reduces energy consumption, thereby providing a sustainable system for timely environmental monitoring.

ABSTRACT Impact damage in carbon-fibre-reinforced polymer (CFRP) laminates threatens the safety of their structures, making it necessary to perform non-destructive testing (NDT) to avoid catastrophic accidents. In this study, a TOF-based fuzzy C-means (FCM) clustering method was developed for the tomographic evaluation of impact damage in CFRP laminates. Ultrasound water immersion experiments were conducted to obtain the time-of-flight (TOF) features of the CFRP laminates with different impact energies. To avoid the limitations of common FCM clustering methods, such as easily falling into local optimal solutions, the initial clustering centres were determined based on the most frequently occurring TOF values across all spatial points. The feasibility of the proposed TOF-based FCM was further validated using X-ray computed tomography (CT) experiments. Moreover, its applicability was demonstrated in CFRP laminates with more complex stacking sequences. The clustering performance of the proposed method was compared with that of Multi-Otsu, K-means, and Density-Based Spatial Clustering of Applications with Noise (DBSCAN). Among these approaches, FCM with the most frequent initialisation achieved a relatively high clustering accuracy while maintaining a low computation time, suggesting a favourable balance between precision and efficiency.

Indonesia is a country with high seismic activity due to its location at the convergence of three major tectonic plates. This condition creates a strong need for earthquake pattern analysis and magnitude prediction to support disaster mitigation. This study aims to cluster earthquake data using the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm and to predict earthquake magnitude using the Random Forest algorithm optimized through hyperparameter tuning. The Indonesian earthquake dataset was obtained from Kaggle with a total of 92,887 valid entries. The DBSCAN clustering results revealed several active seismic zones, particularly in Sumatra, Java, Sulawesi, and Papua. The comparison of R² between the Baseline Random Forest and the Tuned Random Forest shows a significant improvement after the parameter tuning process. The Tuned Random Forest model achieves an R² value of 0.478, which is higher than the Baseline Random Forest's 0.442. This indicates that the tuned model is better able to explain the variance in the data and provides more accurate predictions.

Copy-move forgery is a common form of digital image manipulation when a section of a picture is cut and placed within another image to hide or reproduce specified content. Common postprocessing processes like scaling, blurring, or compression might make traditional methods, including active and passive detection techniques, inaccurate when it comes to localising forgeries. In this research, we provide a new method that combines the deep learning architecture of VGG16 with Density-Based Spatial Clustering of Applications with Noise (DBSCAN) to intelligently segment images and classify them. By grouping nearby pixels according to similarity, the DBSCAN algorithm divides the picture into superpixels, which improves the identification of small areas that are replicated. These segmented regions are fed into the VGG16 network, which has been trained on the MICCF220 dataset to distinguish between authentic and tampered segments. A pattern matching algorithm is then applied to highlight anomalies and confirm the presence of forgery. Experimental results demonstrate that the proposed method achieves a detection accuracy of 93%, outperforming existing techniques in terms of precision, recall, and F1-score. The system is robust, efficient, and suitable for real-world forensic applications where detecting tampered evidence is critical.

Accurate extrinsic calibration between radar and camera sensors is essential for reliable multi-modal perception in robotics and autonomous navigation. Traditional calibration methods often rely on artificial targets such as checkerboards or corner reflectors, which can be impractical in dynamic or large-scale environments. This study presents a fully targetless calibration framework that estimates the rigid spatial transformation between radar and camera coordinate frames by aligning their observed trajectories of a moving object. The proposed method integrates You Only Look Once version 5 (YOLOv5)-based 3D object localization for the camera stream with Density-Based Spatial Clustering of Applications with Noise (DBSCAN) and Random Sample Consensus (RANSAC) filtering for sparse and noisy radar measurements. A passive temporal synchronization technique, based on Root Mean Square Error (RMSE) minimization, corrects timestamp offsets without requiring hardware triggers. Rigid transformation parameters are computed using Kabsch and Umeyama algorithms, ensuring robust alignment even under millimeter-wave (mmWave) radar sparsity and measurement bias. The framework is experimentally validated in an indoor OptiTrack-equipped laboratory using a Skydio 2 drone as the dynamic target. Results demonstrate sub-degree rotational accuracy and decimeter-level translational error (approximately 0.12–0.27 m depending on the metric), with successful generalization to unseen motion trajectories. The findings highlight the method’s applicability for real-world autonomous systems requiring practical, markerless multi-sensor calibration.

The VISTA Variables in the Vía Láctea (VVV) and its eXtension (VVVX) are near-infrared surveys mapping the Galactic bulge and adjacent disk. These datasets have enabled the discovery of numerous star clusters obscured by high and spatially variable extinction. However, most previous searches relied on visual inspection of individual tiles, which is inefficient and biased against faint or low-density systems. We aim to develop an automated, homogeneous algorithm for systematic cluster detection across different surveys. Here, we aim to apply our method to VVVX data covering low-latitude regions of the Galactic bulge and disk, affected by extinction and crowding. We introduce the Consensus-based Algorithm for Nonparametric Detection of Star Clusters ( ), which integrates kernel-density estimation (KDE), Density-Based Spatial Clustering of Applications with Noise (DBSCAN), and nearest-neighbor density estimation (NNDE) within a consensus framework. A stellar overdensity is classified as a candidate if identified by at least two of these methods. We applied to 680 tiles in the VVVX PSF photometric catalogue, covering ≈ 1100, ^2. CANDiSC CANDiSC deg We detect 163 stellar overdensities, of which 118 are known clusters. Cross-matching with recent catalogues yields five additional matches, leaving 40 likely new candidates absent from existing compilations. The estimated false-positive rate is below 5%. CANDiSC offers a robust and scalable approach for detecting stellar clusters in deep, near-infrared surveys, successfully recovering known systems and revealing new candidates in the obscured and crowded regions of the Galactic plane.

Smart farming relies heavily on IoT automation and data-driven decision making, but this growing connectivity also increases exposure to cyberattacks. Flow-based unsupervised intrusion detection is a privacy-preserving alternative to signature and payload inspection, yet it still faces three challenges: loss of subtle anomaly cues during Autoencoder (AE) compression, instability of fixed reconstruction-error thresholds, and performance degradation of clustering in noisy high-dimensional spaces. To address these issues, we propose a fog-aware two-stage hierarchical AE with latent-space gating, followed by Density-Based Spatial Clustering of Applications with Noise (DBSCAN) for attack categorization. A shallow AE compresses the input into a compact 21-dimensional latent space, reducing computational demand for fog-node deployment. A deep AE then computes reconstruction-error scores to isolate malicious behavior while denoising latent features. Only high-error latent vectors are forwarded to DBSCAN, which improves cluster separability, reduces noise sensitivity, and avoids predefined cluster counts or labels. The framework is evaluated on two benchmark datasets. On CIC IoT-DIAD 2024, it achieves 98.99% accuracy, 0.9897 F1-score, 0.895 Adjusted Rand Index (ARI), and 0.019 Davies–Bouldin Index (DBI). To examine generalizability beyond smart farming traffic, we also evaluate the framework on the CSE-CIC-IDS2018 benchmark, where it achieves 99.33% accuracy, 0.9928 F1-score, 0.9013 ARI, and 0.0174 DBI. These results confirm that the proposed model can reliably detect and categorize major cyberattack families across distinct IoT threat landscapes while remaining compatible with resource-constrained fog computing environments.

Understanding soil water in the saline-alkali lands is crucial for sustainable agriculture and ecological restoration. Existing studies have largely focused on macroscopic distribution and associated interpolation techniques, which complicates the precise identification of localized anomalous regions. To address this limitation, this study proposes a novel three-dimensional detection method for localized soil water anomalies (3D-SWLA). Utilizing soil water sampling data, a comprehensive three-dimensional soil water cube is constructed through 3D Empirical Bayesian Kriging (3D EBK). We introduce the Soil Water Local Anomaly Index (SWLAI) and apply a second-order difference method to effectively identify and filter anomalous voxels. Then, the 3D Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm is utilized to cluster Soil Water Anomalous Voxels (SWAVs), thereby delineating three-dimensional Local Anomalous Soil Water Areas (LASWAs) with precision and robustness. A series of experiments were conducted in Kenli to validate the proposed methodology. The results reveal that 3D-SWLA successfully identified a total of 8 Local Anomalous Soil Water Areas (LASWAs), four of which—classified as large-scale anomalies (area > 1.0 km2)—are predominantly concentrated in the northeastern coastal zone and the southern salt fields. The largest among them, LASWA-1, spans 1.8 km2 with a vertical depth ranging from 0 to 35 cm and an average soil water content of 0.36. Another significant anomaly, LASWA-8, covers 1.5 km2, extends to a depth of 0–60 cm, and exhibits a higher average water content of 0.42, reflecting distinct hydrological dynamics in these regions. Additionally, 4 smaller LASWAs (area < 1.0 km2) are spatially distributed along the northeastern irrigation channels, indicating localized moisture accumulation likely influenced by agricultural water management.

Cardiovascular diseases (CVDs) remain a significant global health concern, necessitating effective preventive measures and early diagnosis to reduce mortality rates. Leveraging machine learning models to identify risk factors holds great promise, especially in cardiology. This study introduces a robust methodology for prognosing cardiac illnesses based on patient-specific factors. By integrating five publicly available datasets from the UCI Repository and employing Feature Importance techniques for optimal risk factor selection, the proposed approach enhances prediction accuracy. Furthermore, the inclusion of the density-based spatial clustering of applications with noise (DBSCAN) algorithm assists in noise detection and removal, thereby improving model precision. The proposed Cardio MetaStack model, coupled with a stacking classifier ensemble, achieved an accuracy of 94.91%, surpassing that of traditional algorithms such as XGBoost 90.45%, demonstrating its efficacy in heart disease prediction.

Health is a fundamental right of every citizen. This right is realized in the form of health services. Good health services have an adequate ratio of health and medical personnel. However, in reality, there are still many provinces that have a shortage of health and medical personnel. Therefore, clustering is carried out to make it easier for the government to group provinces that have similarities in terms of the ratio of health and medical personnel in Indonesia in 2023. Density Based Spatial Clustering of Applications with Noise (DBSCAN) is one of the clustering methods used. Using the DBSCAN method, two clusters were obtained with a silhouette coefficient value of 0.49. Cluster 0 is called noise because the observation points in group 0 are outliers. Cluster 0 consists of provinces with a higher ratio of healthcare and medical personnel than cluster 1.

Abstract. We present a novel flexible bi-level spatiotemporal clustering algorithm to extract events based on their intensity and spatiotemporal structures. Our algorithm consists of using (i) a novel space-time k-means clustering to obtain spatiotemporally coherent intensity clusters, and (ii) a density-based spatial clustering of applications with noise (DBSCAN) to spatiotemporally section the intensity clusters into individual events. We discuss the development of the algorithm, the selection, tuning and meaning of the parameters within each step, as well as its validation. Finally, we apply the algorithm to a spatiotemporal drought index, standardized vapor pressure deficit drought index (SVDI), over the continental United States (US) from 1980–2021 and show that it captures historical drought events over the continental United States and their spatiotemporal extents.

This study proposes an integrated Fault Diagnosis (FDD) and Fault-Tolerant Control (FTC) framework aimed at enhancing the operational stability of Remotely Operated Vehicles (ROVs) by addressing thruster faults that compromise mission safety. The proposed methodology utilizes a data-driven FDD system, based on the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm, to identify propeller breakage and entanglement faults from thruster current and Revolutions Per Minute (RPM) data. Based on the diagnostic results, an adaptive FTC strategy is activated, applying a ‘Thrust Compensation’ model for breakage faults and an ‘Exclusion and Reallocation’ approach for entanglement faults. The performance of the framework was validated through experiments in an engineering water tank, where results demonstrated a significant improvement in the ROV’s hovering stability and control accuracy under fault conditions. The system successfully restored thrust balance during breakage scenarios and maintained a stable attitude after excluding an entangled thruster. Consequently, the proposed adaptive FDD-FTC framework provides an effective solution for enhancing the operational reliability and safety of ROVs.

Abstract Point cloud‐based construction quality assessment and quality control (QA/QC) are playing an increasingly important role in large‐scale complex building projects. However, this approach faces several challenges, such as the laborious and time‐intensive process of manual point cloud segmentation, the high cost of point cloud labeling, and the lack of sufficient training data for deep learning‐based automatic segmentation methods. To address these issues, this paper proposed a method for detecting construction deviations in large‐scale complex building structures by utilizing synthetic point clouds for segmentation. The method automatically generated labeled synthetic point clouds with Gaussian noise using BIM and a virtual engine, significantly augmenting the limited amount of real point cloud data to train the semantic segmentation model, enabling the achievement of 94.2% overall accuracy (OA) and 81.1% mean intersection over union (M_IoU). Furthermore, a point cloud instance segmentation method according to density‐based spatial clustering of applications with noise (DBSCAN) and voxel‐vs‐BIM was proposed to independently compare each instance object of different building components with its corresponding BIM model, assessing the construction accuracy of each component based on root mean square error metric and the level of accuracy specification. For components with an LOA3 accuracy level, further deviation analysis was conducted. Taking the structural construction deviation detection of beams, columns, and concrete thick shells in the core area of the Shanghai Grand Opera House as a case, the proposed method significantly improved the efficiency of QA/QC.

Accurately mapping crop distribution is important for environmental and food security applications. The success of machine learning algorithms (MLs) applied to mapping crops is partly dependent on the acquisition of sufficient training samples. However, since minor crops typically cover only few areas within agricultural landscapes, opportunities for collecting training data for those classes are often constrained. This problem is particularly acute in high-elevation regions, where fields tend to be small and heterogeneous in shape. This often leads to imbalanced training datasets, where the proportions of samples for each class differ greatly. To address this issue, a novel resampling algorithm, i.e., the adaptive synthetic and repeat oversampling technique (ASROT), was proposed by coupling two existed algorithms: adaptive synthetic sampling (ADASYN) and density-based spatial clustering of applications with noise (DBSCAN). Then, we explored the application of the proposed ASROT approach and compared it with six commonly used alternative algorithms, using 13 imbalanced datasets generated from GF-6 images of a high-elevation region. The imbalanced training datasets as well as balanced versions produced by ASROT and the comparison algorithms were used with two classifiers (i.e., random forest (RF) and a stacking classifier) to map crop types. The results showed a negative correlation between overall accuracy and the imbalance degree of datasets, illustrating the latter does affect the models in calibrating the crop classification. The balanced datasets produced higher accuracy for crop classification than the original imbalanced datasets for both the RF and stacking classifiers. The classification accuracy of almost all the crop classes and the overall classification accuracy (OA) increased. Most notably, the accuracy for minor crops (e.g., highland barley and broad beans) increased by approximately 30%. Overall, the proposed ASROT algorithm provides an effective method for balancing training datasets, simultaneously improving classification accuracy of both major and minor crops in high-elevation regions.

Understanding driver behavior is critical for enhancing road safety and enabling proactive interventions. While prior studies have largely focused on driver-specific profiles (e.g., aggressive, cautious, safe), such approaches overlook the fact that crashes are often concentrated at specific crash hostspot and corridors. Hence, this study adopts a location-based perspective, analyzing how drivers behave at particular roadway segments to identify their driving patterns. The objectives are: (i) to develop a robust machine learning framework that classifies location-specific driving behavior according to its risk level, and (ii) to create a unified model capable of analyzing multiple vehicle classes together, eliminating the need for separate models for each type. Trajectory data from different vehicle classes, collected in Chennai, India, form the basis of this analysis. Initially, each vehicle type was examined independently to capture mode-specific behaviors at various locations. The datasets were then combined to investigate cross-modal behavior patterns. Principal Component Analysis (PCA) was applied to reduce dimensionality, and four clustering techniques: K-Means, Density-Based Spatial Clustering of Applications with Noise (DBSCAN), Mean Shift, and Deep Embedded Clustering (DEC) were employed to classify location-based behaviors into ‘Aggressive,’ ‘Cautious,’ and ‘Safe’ categories. The clustering outcomes were systematically evaluated using Silhouette Score, Davies–Bouldin Index (DBI), and Calinski–Harabasz Index (CHI). The findings show that DEC performs best, while DBSCAN yields the weakest clustering results. The unified location-based model demonstrates strong potential for large-scale deployment in real-world scenarios, offering valuable insights into risky driving hotspots and enabling targeted interventions to improve driver awareness and roadway safety.

As a vital support for sustainable energy power systems, shared energy storage has the potential to address challenges in energy storage within rural grids. Nevertheless, the comprehensive value of rural shared energy storage (RSES) exhibits scenario-dependent variations across operation models, and existing studies have neither revealed this sensitivity nor established a scientifically unified evaluation method. This study first identifies typical rural grid scenarios using the density-based spatial clustering of applications with noise (DBSCAN) algorithm and analyzes RSES operation models. Then, this paper creates a three-dimensional evaluation system of RSES based on environmental, social, and governance (ESG) concepts that support sustainable development goals. Furthermore, to reconcile conflicts between subjective and objective weights, this paper proposes a combination weighting method based on Nash negotiation, subsequently using an improved technique for order preference by similarity to an ideal solution (TOPSIS) for multi-attribute decision-making. Finally, this paper completes simulations and discussions by an improved IEEE 33 bus system. The decision-making trial and evaluation laboratory (DEMATEL) technique and sensitivity analysis validate the validity and feasibility of the method proposed from horizontal and vertical dimensions. Based on the results, preferred strategies of RSES currently are energy aggregation and service purchase, for which this study provides recommendations.

ABSTRACT Calibration is a crucial approach to enhancing the accuracy performance of six‐axis force/torque sensors. Although the least squares method is a widely used framework for six‐axis sensor calibration, it struggles to accurately capture the nonlinear relationship between analog and digital signals. Furthermore, traditional methods have difficulty in effectively addressing interaxis crosstalk in six‐axis force/torque sensors. This paper proposes an eXtreme Gradient Boosting (XGBoost) ensemble learning calibration algorithm, where the density‐based spatial clustering of applications with noise (DBSCAN) model is utilized to train sample weights and eliminate the interference of outliers. By leveraging the strong fitting and generalization capabilities of ensemble learning, the proposed method addresses both nonlinear relationships and crosstalk in calibration data. However, the inherent limitations of black‐box models have raised concerns about the appropriateness of machine learning and ensemble learning paradigms in the calibration process. To ensure the reliability and rationality of the calibration algorithm, this paper employs the shapley additive explanation (SHAP) model for interpretability analysis. Comparison with least squares method (LS), numerical and experimental results validate the effectiveness of the proposed calibration algorithm, demonstrating a significant improvement in the accuracy of the six‐axis force/torque sensor while reducing inter‐axis crosstalk. The Type I error of is reduced by [56.7%,65.6%,54.2%,27.5%,9%,99.9%] , while the Type II error is reduced by [68.3%,64%,2.1%,22.1%,7.6%,99.9%] .