Search Results (54)

Given the urgent demand for flexible peak-shaving in power systems and underutilized distributed photovoltaic (PV) regulation potential, this paper proposes a distributed PV peak-shaving control strategy based on the temporal coupling self-organizing map (TC-SOM) neural network and a bi-level model. First, the SOM algorithm is improved for efficient feature extraction and accurate clustering of distributed PV data, realizing rational PV cluster division. On this basis, a bi-level peak-shaving model for distributed PV is constructed, forming a hierarchical peak-shaving mechanism from node demand to PV clusters to individual PVs to ensure inter- and intra-cluster coordination. This hierarchical structure embodies symmetric response logic, enabling balanced interaction between upper-layer node demand guidance and lower-layer PV execution, as well as inter-cluster coordination. Simulations on the IEEE-33 node system confirm its effectiveness: it significantly smooths the load curve, reduces peak–valley differences, and optimizes the flexible utilization of distributed PV through coordinated control, aggregation management, and curtailment regulation, providing strong support for precise PV cluster regulation and stable operation of high-proportion PV-integrated power grids. Full article

In the financial sector, machine learning has become essential for credit risk assessment, often outperforming traditional statistical approaches, such as linear regression, discriminant analysis, or model-based expert judgment. Although machine learning technologies are increasingly being used, further research is needed to understand how they can be effectively combined and how different models interact during credit evaluation. This study proposes a technique that integrates hierarchical clustering, namely Agglomerative clustering and Balanced Iterative Reducing and Clustering using Hierarchies, along with individual supervised models and a self organizing map-based consensus model. This approach helps to better understand how different clustering algorithms influence model performance. To support this approach, we performed a detailed unsupervised component analysis using metrics such as the silhouette score and Adjusted Rand Index to assess cluster quality and its relationship with the classification results. The study was applied to multiple datasets, including a Taiwanese credit dataset. It was also extended to a multiclass classification scenario to evaluate its generalization ability. The results show that the quality metrics of the cluster correlate with the performance, highlighting the importance of combining unsupervised clustering and self organizing map consensus methods for improving credit evaluation. Full article

In the absence of system-wide planning and coordination, emerging mobility services have been integrated into urban transportation systems as independent network layers. Meanwhile, their interactions with traditional public transit give rise to complex self-organizing patterns in population mobility, manifested as coopetitive dynamics. To systematically analyze this phenomenon, this study constructs a four-layer temporal network—consisting of ride-hailing, metro, combined, and potential layers—based on a vectorized multilayer network model and inter-layer mapping relationships. An analytical framework is then developed using node strength, cosine similarity, and rich-club coefficients, along with two newly proposed indicators: the intermodal index and the node importance coefficient. The results reveal, for the first time, a spontaneously emergent intermodal phenomenon between ride-hailing and metro networks, manifested through both cross-day modal substitution and intra-day intermodal chains. The analysis further demonstrates that when sufficiently large and homogeneous demand cohorts are present, the phenomena can emerge even on non-working days. Based on the characteristics of this phenomenon, a method has been developed to identify intermodal nodes across different transport networks. Furthermore, the study uncovers a time-varying multicentric hierarchical structure within the metro network, characterized by small-scale core rich nodes and larger-scale secondary rich-node clusters. Overall, this study provides novel insights into the formation, coordination, and optimization of intermodal urban transport networks. Full article

Settlements and settlement systems are key arenas of human–environment interaction, and reconstructing their spatial patterns is essential for understanding historical socio-environmental dynamics. Using the Complete Map of the Great Qing Empire (1905), this study employs digital extraction and spatial-statistical analysis to examine the nationwide settlement system of late Qing China. The results reveal that: (1) The system features dispersed high-level settlements and highly clustered low-level ones; provincial and prefectural cities follow administrative divisions, while counties, towns, and villages display strong spatial self-organization. (2) Mid-to high-level systems exhibit hierarchical fractures, whereas low-level settlements conform to Zipf’s law, highlighting the regularity and universality of grassroots networks. (3) Road accessibility, slope, and elevation significantly influence settlement hierarchy, whereas river proximity plays a limited role—indicating greater dependence on transportation and terrain adaptability. Overall, the study elucidates the spatial structure and formative mechanisms of the Qing settlement system and provides empirical insights into the evolution of surface patterns and regional resilience since the modern era. Full article

Circulation type classification (CTC) is an important method in atmospheric sciences, which reveals the relationship between atmospheric circulation and regional weather and climate. Accurate circulation classification helps to improve weather forecasting accuracy and supports climate change research. China has complex topography and significant spatiotemporal variability in its circulation patterns, making the study of circulation type classification in this region highly significant. This study aims to evaluate the applicability of several mainstream objective CTC methods in the China region. We applied methods including T-mode principal component analysis (PCT), Ward linkage, K-means, and Self-Organizing Maps (SOM) to classify the sea-level pressure daily mean fields from 1993 to 2023 in the study area, and compared the classification results in terms of internal metrics, continuity, seasonal variation, separability of related meteorological variables (e.g., temperature, precipitation), and stability to spatiotemporal resolution. The results show that each method has its advantages in different contexts, with the K-means method showing the best overall performance. Additionally, an optimized approach combining PCT and K-means is proposed. Full article

Understanding how complex biological forms emerge and evolve remains a central question in evolutionary and developmental biology. To explore this complexity, we introduce a minimal two-dimensional, cellular automaton (CA)-based model that captures key features of biological development—such as spatial growth, self-organization, and differentiation—while remaining computationally tractable and evolvable. Unlike most abstract genotype–phenotype mapping models, our approach generates emergent morphological complexity through spatially explicit rule-based interactions governed by a simple genetic vector, resulting in self-organized patterns reminiscent of biological morphogenesis. Using simulations, we show that, as observed in empirical studies, the resulting phenotypic distribution is highly skewed: simple forms are common, while complex ones are rare. The model exhibits a strongly non-linear genotype-to-phenotype mapping in such a way that small genetic changes can lead to disproportionately large morphological shifts. Notably, transitions toward complexity are less frequent than regressions to simplicity, reflecting evolutionary asymmetries observed in natural systems. We further demonstrate that, by allowing for mutations in the generative rules, our model is capable of adaptive evolution and even reproducing generic features of tumoral growth. These findings suggest that even minimal developmental rules can give rise to rich, hierarchical patterns and complex evolutionary dynamics, positioning our CA-based model as a powerful tool for investigating how developmental constraints and biases shape morphological evolution. Full article

This study introduces SOMTreeNet, a novel hybrid neural model that integrates Self-Organizing Maps (SOMs) with BIRCH-inspired clustering features to address structured learning in a scalable and interpretable manner. Unlike conventional deep learning models, SOMTreeNet is designed with a recursive and modular topology that supports both supervised and unsupervised learning, enabling tasks such as classification, regression, clustering, anomaly detection, and time-series analysis. Extensive experiments were conducted using various publicly available datasets across five analytical domains: classification, regression, clustering, time-series forecasting, and image classification. These datasets cover heterogeneous structures including tabular, temporal, and visual data, allowing for a robust evaluation of the model’s generalizability. Experimental results demonstrate that SOMTreeNet consistently achieves competitive or superior performance compared to traditional machine learning and deep learning methods while maintaining a high degree of interpretability and adaptability. Its biologically inspired hierarchical structure facilitates transparent decision-making and dynamic model growth, making it particularly suitable for real-world applications that demand both accuracy and explainability. Overall, SOMTreeNet offers a versatile framework for learning from complex data while preserving the transparency and modularity often lacking in black-box models. Full article

The widespread application of organoids in disease modeling and drug development is significantly constrained by challenges in automated quantitative analysis. In bright-field microscopy images, organoids exhibit complex characteristics, including irregular morphology, blurred boundaries, and substantial scale variations, largely stemming from their dynamic self-organization that mimics in vivo tissue development. Existing convolutional neural network-based methods are limited by fixed receptive fields and insufficient modeling of inter-channel relationships, making them inadequate for detecting such evolving biological structures. To address these challenges, we propose a novel detection head, termed Interactive Dual-Perception Head (IDP-Head), inspired by hierarchical perception mechanisms in the biological visual cortex. Integrated into the RTMDet framework, IDP-Head comprises two bio-inspired components: a Large-Kernel Global Perception Module (LGPM) to capture global morphological dependencies, analogous to the wide receptive fields of cortical neurons, and a Progressive Channel Synergy Module (PCSM) that models inter-channel semantic collaboration, echoing the integrative processing of multi-channel stimuli in neural systems. Additionally, we construct a new organoid detection dataset to mitigate the scarcity of annotated data. Extensive experiments on both our dataset and public benchmarks demonstrate that IDP-Head achieves a 5-percentage-point improvement in mean Average Precision (mAP) over the baseline model, offering a biologically inspired and effective solution for high-fidelity organoid detection. Full article

This study investigates the essential competencies for engineers in the context of digital transformation, with the aim of proposing a refined framework to guide professional development across career levels. A mixed-methods, sequential approach was adopted: (1) a systematic literature review, conducted between 2014 and 2024, which identified 46 competencies organized into seven dimensions; (2) a quantitative survey with 392 engineers who self-assessed their level of mastery for each competency; (3) semi-structured interviews with 20 company representatives, who validated and contextualized the essential competencies according to hierarchical levels (junior, mid-level, and senior); (4) data triangulation, resulting in a final competency model by career level. The findings reveal a widespread deficit in digital competencies, regardless of hierarchical level. In total, 33 competencies assessed by career level showed statistically significant differences in employer perceptions and were identified as progressive throughout the career trajectory. Analysis of self-assessments and interviews indicates that for early-career engineers, there is a strong emphasis on personal and basic cognitive competencies. For mid-level engineers, the data show a significant valuation of social competencies. Senior engineers are perceived as having accumulated experience across all seven mapped dimensions. This study offers a practical model that can be used by educational institutions, companies, and professionals to align education, market demands, and career planning. Full article

To address the challenges in current research on spatial clustering algorithms for buildings in topographic maps—namely, their limited ability to effectively accommodate diverse application scenarios, including dense and regular urban environments, sparsely and irregularly distributed rural areas, and urban villages with complex structures—this paper introduces an innovative progressive clustering algorithm framework. The proposed framework operates in a hierarchical manner, progressing from macro to micro levels, thereby enhancing its adaptability and practical versatility. Specifically, it employs the minimum spanning tree (MST) technique for macro-level clustering analysis. Subsequently, a self-organizing map (SOM) neural network is utilized to perform micro-level clustering, enabling a more refined and detailed classification. Within this framework, the minimum spanning tree effectively captures the macroscopic distribution patterns of the building population. The macroscopic clustering results are then utilized as the initial weight configurations for the SOM neural network. This approach ensures that the overall spatial structural integrity is preserved during the subsequent micro-level clustering process. Moreover, the SOM neural network achieves refined optimization of micro-clustering details by incorporating building feature factors. To validate the effectiveness of the proposed algorithm, this study conducts an empirical analysis and comparative testing using building data from Futian District, Shenzhen City. The results indicate that the proposed algorithm exhibits superior recognition capabilities when applied to complex and variable spatial distribution patterns of buildings. Furthermore, the clustering outcomes align closely with the principles of Gestalt visual perception and outperform the comparison algorithms in overall performance. Full article

The evaluation of air pollution is a critical concern due to its potential severe impacts on human health. Currently, vast quantities of data are collected at high frequencies, and researchers must navigate multiannual, multisite datasets trying to identify possible pollutant sources while addressing the presence of noise and sparse missing data. To address this challenge, multivariate data analysis is widely used with an increasing interest in neural networks and deep learning networks along with well-established chemometrics methods and receptor models. Here, we report a combined approach involving the Self-Organizing Map (SOM) algorithm, Hierarchical Clustering Analysis (HCA), and Positive Matrix Factorization (PMF) to disentangle multiannual, multisite data in a single elaboration without previously separating the sites and years. The approach proved to be valid, allowing us to detect the site peculiarities in terms of pollutant sources, the variation in pollutant profiles during years and the outliers, affording a reliable interpretation. Full article

Smart meter data provide an in-depth perspective on household energy usage. This research leverages on such data to enhance demand response (DR) programs through a novel application of ensemble clustering. Despite its promising capabilities, our literature review identified a notable under-utilization of ensemble clustering in this domain. To address this shortcoming, we applied an advanced ensemble clustering method and compared its performance with traditional algorithms, namely, K-Means++, fuzzy K-Means, Hierarchical Agglomerative Clustering, Spectral Clustering, Gaussian Mixture Models (GMMs), BIRCH, and Self-Organizing Maps (SOMs), across a dataset of 5567 households for a range of cluster counts from three to nine. The performance of these algorithms was assessed using an extensive set of evaluation metrics, including the Silhouette Score, the Davies–Bouldin Score, the Calinski–Harabasz Score, and the Dunn Index. Notably, while ensemble clustering often ranked among the top performers, it did not consistently surpass all individual algorithms, indicating its potential for further optimization. Unlike approaches that seek the algorithmically optimal number of clusters, our method proposes a practical six-cluster solution designed to meet the operational needs of utility providers. For this case, the best performing algorithm according to the evaluation metrics was ensemble clustering. This study is further enhanced by integrating Explainable AI (xAI) techniques, which improve the interpretability and transparency of our clustering results. Full article

This study investigates the cluster approach to optimize strategies for agricultural enterprises in Ukraine, emphasizing geographical proximity as a key factor in cluster formation. The research applies Kohonen Self-Organizing Maps (SOMs) and Ward’s hierarchical clustering to classify enterprises based on storage capabilities, transport logistics, crop yields, and military risk exposure. By analyzing these factors, this study identifies distinct patterns of innovation adoption, strategic management, and economic resilience among the clusters. The findings highlight variations in competitiveness and resource efficiency, providing a detailed understanding of regional economic performance. Unlike previous research, this study offers a novel integration of conflict-related risks into the clustering methodology, revealing new insights into how military factors influence cluster dynamics. Comprehensive maps and diagrams illustrate the spatial and economic distribution of clusters, aiding in visual interpretation. The results propose strategic measures tailored to enhance agricultural productivity and competitiveness, particularly in Ukraine’s current military context. This approach offers a more adaptive framework for managing agricultural enterprises, promoting resilience and long-term sustainability in global markets. Full article

Grasping how scale influences the interactions among ecosystem services (ESs) is vital for the sustainable management of multiple ESs at the regional level. However, it is currently unclear whether the actual ES interactions and their driving mechanisms are consistent across different spatial and temporal scales. Therefore, using the Lishui River Basin of China as a case study, we analyzed the spatial and temporal distribution of five key ESs across three scales (grid, sub-watershed, and county) from 2010 to 2020. We also innovatively used Pearson correlation analysis, Self-organizing Mapping (SOM), and random forest analysis to assess the dynamic trends of trade-offs/synergies among ESs, ecosystem service bundles (ESBs), and their main socio-ecological drivers across different spatiotemporal scales. The findings showed that (1) the spatial distribution of ESs varied with land use types, with high-value areas mainly in the western and northern mountainous regions and lower values in the eastern part. Temporally, significant improvements were observed in soil conservation (SC, 3028.23–5023.75 t/hm²) and water yield (WY, 558.79–969.56 mm), while carbon sequestration (CS) and habitat quality (HQ) declined from 2010 to 2020. (2) The trade-offs and synergies among ESs exhibited enhanced at larger scales, with synergies being the predominant relationship. These relationships remained relatively stable over time, with trade-offs mainly observed in ES pairs related to nitrogen export (NE). (3) ESBs and their socio-ecological drivers varied with scales. At the grid scale, frequent ESB flows and transformations were observed, with land use/land cover (LULC) being the main drivers. At other scales, climate (especially temperature) and topography were dominant. Ecosystem management focused on city bundles or downstream city bundles in the east of the basin, aligning with urban expansion trends. These insights will offer valuable guidance for decision-making regarding hierarchical management strategies and resource allocation for regional ESs. Full article

Machine learning algorithms have revolutionized data analysis by uncovering hidden patterns and structures. Clustering algorithms play a crucial role in organizing data into coherent groups. We focused on K-Means, hierarchical, and Self-Organizing Map (SOM) clustering algorithms for analyzing homogeneous datasets based on archaeological finds from the middle phase of Pre-Pottery B Neolithic in Southern Levant (10,500–9500 cal B.P.). We aimed to assess the repeatability of these algorithms in identifying patterns using quantitative and qualitative evaluation criteria. Thorough experimentation and statistical analysis revealed the pros and cons of each algorithm, enabling us to determine their appropriateness for various clustering scenarios and data types. Preliminary results showed that traditional K-Means may not capture datasets’ intricate relationships and uncertainties. The hierarchical technique provided a more probabilistic approach, and SOM excelled at maintaining high-dimensional data structures. Our research provides valuable insights into balancing repeatability and interpretability for algorithm selection and allows professionals to identify ideal clustering solutions. Full article