Search

The interpretation of ligand–target interactions at atomistic resolution is central to most efforts in computational drug discovery and optimization. However, the highly dynamic nature of protein targets, as well as possible induced fit effects, makes difficult to sample many interactions effectively with docking studies or even with large-scale molecular dynamics (MD) simulations. We propose a novel application of Self-Organizing Maps (SOMs) to address the sampling and dynamic mapping tasks, particularly in cases involving ligand flexibility and induced fit. The SOM approach offers a data-driven strategy to create a map of the interaction process and pathways based on unbiased MD. Furthermore, we show how the preliminary SOM mapping is complementary to kinetic analysis, with the employment of both network-based approaches and Markov state models. We demonstrate the method by comprehensively mapping a large dataset of 640 μs of unbiased trajectories sampling the recognition process between the phosphorylated YEEI peptide and its high-specificity target lck-SH2. The integration of SOM into unbiased simulation protocols significantly advances our understanding of the ligand binding mechanism. This approach serves as a potent tool for mapping intricate ligand–target interactions with unprecedented detail, thereby enhancing the characterization of kinetic properties crucial to drug design. [ABSTRACT FROM AUTHOR]

The identification of new white dwarfs (WDs) polluted with heavy elements is important since they provide a valuable tool for inferring the chemical properties of putative planetary systems accreting material on their surfaces. The Gaia space mission has provided us with an unprecedented amount of astrometric, photometric, and low-resolution (XP) spectroscopic data for millions of newly discovered stellar sources, among them thousands of WDs. In order to find WDs among these data and to identify which ones have metals in their atmospheres, we propose a methodology based on an unsupervised artificial intelligence technique called self-organizing maps. In our approach, a nonlinear high-dimensional data set is projected on a 2D grid map where similar elements fall into the same neuron. By applying this method, we obtained a clean sample of 66,337 WDs. We performed an automatic spectral classification analysis on them, obtaining 143 bona fide polluted WD candidates not previously classified in the literature. The majority of them are cool WDs and we identify in their XP spectra several metallic lines such as Ca, Mg, Na, Li, and K. The fact that we obtain similar precision metrics to those achieved with recent supervised techniques highlights the power of our unsupervised approach to mine the Gaia archives for hidden treasures to follow up spectroscopically with higher resolution. [ABSTRACT FROM AUTHOR]

The Ouislane sub-watershed is currently experiencing severe water shortages and is highly dependent on its water supply. The sub-watershed spans two communes: Meknes to the north and El Hajeb to the south. It serves as the primary water source for irrigation and drinking purposes for the local population. Consequently, it is crucial to assess the spatio-temporal variations of water quality to identify and address potential gaps; these focused on effective monitoring systems to detect contaminants, pollutants and health risks. This research project aims on the application of self-organizing map (SOM) techniques combined with cluster analysis to classify water quality in springs for drinking and irrigation purposes. The present study evaluates the water quality variations using physicochemical parameters of twelve water springs, collected during the wet and dry seasons of 2022. For this purpose, the water quality index (WQI), self-organizing map (SOM), hierarchical cluster analysis (HCA), and principal component analysis (PCA) are used as evaluation and classification methods. As a result, the SOM algorithm with a size of 5 × 5 units identified as the most suitable, based on the minimum quantization error (QE) and topographic error (TE), yielding a QE of 0.379 and a TE of 0.000. It grouped the water quality data into five distinct clusters, Cluster I represented 37.5% of the total samples, while cluster II represented 25%. Cluster III and IV each accounted for 8.33% of the samples, while 20.83% of the sampling water are classified in cluster V. Clusters I, II, and IV indicate good water suitable for drinking. However, cluster V had the highest WQI, suggesting very high contamination due to increased levels of the 10 studied physicochemical parameters. The water quality in this region (cluster V) is influenced by natural processes, such as precipitation intensity, weathering and vegetation cover, as well as anthropogenic factors like agriculture and urban concentration. PCA confirmed the clustering results obtained by SOM. However, SOM provides a more detailed classification and additional insights into the dominant variables influencing the classification processes. The results of this study suggest that SOM was an effective tool for gaining a better understanding of the patterns and processes driving water quality in the Ouislane sub-watershed and provides valuable avenues for further research to establish and monitor water quality for effective management of water resources. [ABSTRACT FROM AUTHOR]

• A procedure combined SOM was developed to identify new refrigeration system faults. • Defrosting fault was due to abnormal action of gas-powered suction stop valve. • The diagnostic accuracy for DLL, DML, and DHL were 93.8 %, 91.2 % and 88.6 %, respectively. • Resolution of defrosting issues resulted in up to 18.3 % energy consumption reduction. Refrigeration systems in large cold stores frequently operate suboptimally due to component faults, leading to significant energy wastage and high carbon emissions. This study introduces a novel procedure that leverages data mining to automatically analyze and identify faults, thereby enhancing the intelligence of refrigeration equipment. The research focused on abnormal suction temperatures of compressors during the defrosting of air coolers in a large cold store. Through theoretical analysis and key data acquisition, the root cause of defrosting issues was traced to the abnormal operation of gas-powered suction stop valves, causing leakage of high-pressure hot gas. Clustering methods, Self-Organizing Maps (SOM), were utilized to classify system states and achieved high accuracy rates of 88.6 % to 93.8 % for the three fault modes during the defrosting process, respectively. The resolution of defrosting faults resulted in an energy consumption reduction of up to 18.3 %, aligning with global sustainability initiatives. The study also evaluated the carbon emission reduction, providing a comprehensive approach to improving the efficiency and environmental impact of cold store operations. [ABSTRACT FROM AUTHOR]

The paper is devoted to testing Kohonen self‐organising maps, with elliptic Fourier coefficients as quantitative variables, for the task of morphological classification of fragmented and non‐standardised ceramics. The advantage of the methodology used is its ability to account for the systematic statistical relationships inherent in the dataset, build models of varying degrees of generalisation and visualise multivariate data. The approbation of the method was carried out on materials from the Hlyboke Ozero‐2 settlement in Eastern Ukraine. The results are compared with the results obtained using principal component analysis + k‐means clustering. [ABSTRACT FROM AUTHOR]

Laser scanning data are increasingly used to segment forests into homogeneous units, called segments or stand compartments. Region growing and region merging have been traditionally employed for this purpose. Recently, alternative methods such as cellular automata (CA), self-organizing maps (SOM), and combinatorial optimization have emerged, promising more homogeneous stand delineations. However, these newer methods often require fine-tuning due to rugged stand boundaries. To address this, we propose and assess a novel hybrid approach that combines two segmentation algorithms, resulting in smoother boundaries and homogeneous stands. Our hybrid method outperforms traditional fine-tuning techniques, particularly using CA or SOM for initial segmentation and then refining it with another cellular automaton (CA'), adjusted to produce smooth boundaries. The new two-step hybrid method resulted in better segmentation results than the one-step algorithm combined with previously suggested fine-tuning methods. SOM-CA' showed the highest degree of explained variance (R2) of the LiDAR metrics used in the segmentation. CA-CA' reached almost the same R2 values with a larger average segment area. When the R2 of the LiDAR metrics was used as the criterion, the segments produced by the hybrid method outperformed the stand delineations of the current Spanish forest map with a clear margin. [ABSTRACT FROM AUTHOR]

In this paper, we proposed VGASOM, a neural network approach for community detection. Community detection refers to discovering similar nodes in a graph that form a community having similar features or attributes as opposed to nodes from other communities. The proposed approach combines the capabilities of auto-encoder neural networks, specifically a Variational graph auto-encoder (VGAE) with self-organizing maps (SOM) clustering. VGAEs have achieved great success in learning the latent representation of graphs and therefore encoding them into lower-dimensional embeddings. The self-organizing map based on competitive learning is used to find communities in the graphs' embeddings obtained by the VGAE model which further reduces its dimensionality and divides the input space into clusters that correspond to the communities in the graph. We conducted experiments to evaluate our model compared to several baseline models, our model shows promising results for the community detection task. It outperforms the state-of-the-art methods by 3.29% in terms of the accuracy and 9% in terms of F1 metric. [ABSTRACT FROM AUTHOR]

Recently, machine learning (ML) has been considered a powerful technological element of different society areas. To transform the computer into a decision maker, several sophisticated methods and algorithms are constantly created and analyzed. In geophysics, both supervised and unsupervised ML methods have dramatically contributed to the development of seismic and well-log data interpretation. In well-logging, ML algorithms are well-suited for lithologic reconstruction problems, once there is no analytical expressions for computing well-log data produced by a particular rock unit. Additionally, supervised ML methods are strongly dependent on a accurate-labeled training data-set, which is not a simple task to achieve, due to data absences or corruption. Once an adequate supervision is performed, the classification outputs tend to be more accurate than unsupervised methods. This work presents a supervised version of a Self-Organizing Map, named as SSOM, to solve a lithologic reconstruction problem from well-log data. Firstly, we go for a more controlled problem and simulate well-log data directly from an interpreted geologic cross-section. We then define two specific training data-sets composed by density (RHOB), sonic (DT), spontaneous potential (SP) and gamma-ray (GR) logs, all simulated through a Gaussian distribution function per lithology. Once the training data-set is created, we simulate a particular pseudo-well, referred to as classification well, for defining controlled tests. First one comprises a training data-set with no labeled log data of the simulated fault zone. In the second test, we intentionally improve the training data-set with the fault. To bespeak the obtained results for each test, we analyze confusion matrices, logplots, accuracy and precision. Apart from very thin layer misclassifications, the SSOM provides reasonable lithologic reconstructions, especially when the improved training data-set is considered for supervision. The set of numerical experiments shows that our SSOM is extremely well-suited for a supervised lithologic reconstruction, especially to recover lithotypes that are weakly-sampled in the training log-data. On the other hand, some misclassifications are also observed when the cortex could not group the slightly different lithologies. [ABSTRACT FROM AUTHOR]

Vehicular ad hoc network (VANET) is a promising technology for controlling traffic on roads. Nowadays, heavy traffic is a major issue, and the presence of attackers exacerbates the situation. The most important challenge in VANET is its security from malicious vehicles. In order to defend against distributed denial of service DDoS attacks, we propose a comprehensive verification header format bandwidth detection (CVHB) in VANET. The behavior of a DDoS attack is unknown for all the other normal nodes in network. The header format of packer contains all the information of nodes that are actively participating in routing. The attacker infection probability measured by and or (10> 0.9). If both the parameters are high means attacker presence confirm in network. The CVHB scheme checks the packet header format of the attacker node, and only the attacker is one of the nodes whose sequence number is frequently changing. So, CVHB blocks the flooding of unwanted packets that consume the limited bandwidth of a wireless link and identify packets that contain no useful information. To measure the performance of the network, the basic performance metrics that are used are dropping percentage, packet delivery ratio (PDR), throughput and delay. The result of CVHB is showing improvement as compared to multilayer distributed self-organizing maps (MSOM) in VANET. [ABSTRACT FROM AUTHOR]

The majority of the KP-based copy-move forgery (CMF) detection techniques have a high computational cost due to their large feature descriptor sets and numerous KPs. Furthermore, the accuracy of the results may be impacted by the identified KPs not spreading over all regions of the image and the classical clustering approaches not efficiently classifying the feature space into cluster space. This article therefore attempts to employ both KAZE & fast hessian matrix (FHM) techniques for identifying KPs that spread over the entire image region, SURF for evaluating feature descriptors, Network based Dimensionality Reduction (NDR) for reducing the dimension of each feature descriptor and Self-Organizing Map (SOM) for clustering the feature vectors for avoiding sub-optimal clusters. It portrays the superior performances of the proposed forgery detection scheme on a standard image database “MICC-F220” and medical records like fundas images. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

The Growing Neural Gas (GNG) algorithm constitutes an incremental neural network model based on the idea of a Self-Organizing Map (SOM), that is, unsupervised learning algorithms that reduce the dimensionality of datasets by locating similar samples close to each other. The design of an electric vehicle charging network is an essential aspect in the transition towards more sustainable and environmentally friendly mobility. The need to design and implement an efficient network that meets the needs of all users motivates us to propose the use of a model based on GNG-type neural networks for the design of the network in a specific geographical area. In this paper, a variant of this iterative neural network algorithm is used with the objective that, from an initial dataset of points in the plane, it calculates a new simplified dataset with the main characteristic that the final set of points maintains the geometric shape and topology of the original set. To demonstrate the capabilities of the algorithm, it is exemplified in a real case, in which the design of an electric vehicle charging network is proposed. This network is built by applying the algorithm, taking as the original set of points the ones formed by the nodes of the gas station network in the geographical area studied. Several tests of running the algorithm for different sizes of the final dataset are performed, showing the differences between the original network and the computationally generated one. [ABSTRACT FROM AUTHOR]

There are currently many clinical issues plaguing digestive oncologists, including the impact of dietary habits on the occurrence of early gastrointestinal cancer, the association between irritable bowel syndrome, ulcerative colitis, and early gastrointestinal cancer, the expected changes in gastrointestinal cancer after IBS, IBD, and susceptibility gene mutations, and the mechanisms by which susceptibility gene mutations in gastrointestinal cancer lead to different diseases. Meanwhile, as a carcinogen, betel nut is also prone to cancer and emotional disorders, and there are also many doctor-patient conflicts in the current clinical treatment of digestive tract tumors. To address the aforementioned issues, the research team analyzed dietary habits data using SOM clustering algorithm and isolated forest algorithm. Based on bioinformatics, new therapies have been developed for the pathogenesis and immune pathways of various cancers in the digestive system. Using network pharmacology methods, explore the toxicological mechanism of betel nut and its mechanism in mediating emotional disorders. Molecular docking is used to elucidate drug prediction. Based on four AI algorithms, the occurrence of gastrointestinal cancer was predicted through dietary habits. Using computer vision technology to address the deficiencies in early clinical reporting of cancer. This article provides clinical doctors with new treatment tools. [ABSTRACT FROM AUTHOR]

In 2011, Korea installed artificial structures on four rivers to secure water resources and reduce flood damage; however, these structures have altered ecosystems and aquatic communities. This study analyzed fish communities and environmental variables at 72 sites in the Geumgang River. Fish communities and environmental variables before weir installation were examined using site data from 2008 to 2009. The results showed that Cyprinidae dominated the 70 observed species. A self-organizing map categorized the 72 sites into four groups based on fish communities. Sensitive and insectivorous species decreased, whereas tolerant and omnivorous species increased from Groups I to IV. Twenty-one indicator species were identified, with fewer and less distinct distribution patterns in Groups II and III than in Groups I and IV. The fish assessment index (FAI) showed a decline in grades A and B and an increase in grades C and D from Groups I to IV. Correlation analysis between the FAI and environmental variables indicated that fish communities in the Geumgang River were mainly influenced by water quality, reflecting altitude gradients and pollution levels. This study's findings are anticipated to significantly inform water management strategies for the Geumgang, Yeongsangang, Nakdonggang, and Hangang Rivers. [ABSTRACT FROM AUTHOR]

The human body will show very complex and diversified posture changes in the process of falling, including body posture, limb position, angle and movement trajectory, etc. The coordinates of the key points of the model are mapped to the three-dimensional space to form a three-dimensional model and obtain the three-dimensional coordinates of the key points; The construction decomposition method is used to calculate the rotation matrix of each key point, and the rotation matrix is solved to obtain the angular displacement data of the key points on different degrees of freedom. The method of curve fitting combined with the weight distribution kernel function based on self-organizing mapping theory is used to obtain the motion trajectory prediction equation of the human body falling in different degrees of freedom at random positions in three-dimensional space, determine the key point trajectory of human random fall behaviour. The experimental results show that the mapped 3D model is consistent with the real human body structure. This method can accurately determine whether the human body falls or squats randomly, and the prediction results of the key points of the human fall are consistent with the actions of the human body after the fall. [ABSTRACT FROM AUTHOR]

In the rapidly evolving technological landscape, the advent of collaborative Unmanned Aerial Vehicle (UAV) inspections represents a revolutionary leap forward in the monitoring and maintenance of power distribution networks. This innovative approach harnesses the synergy of UAVs working together, marking a significant milestone in enhancing the reliability and efficiency of infrastructure management. Despite its promise, current research in this domain frequently grapples with challenges related to efficient coordination, data processing, and adaptive decision-making under complex and dynamic conditions. Intelligent self-organizing algorithms emerge as pivotal in addressing these gaps, offering sophisticated methods to enhance the autonomy, efficiency, and reliability of UAV collaborative inspections. In response to these challenges, we propose the MARL-SOM-GNNs network model, an innovative integration of Multi-Agent Reinforcement Learning, Self-Organizing Maps, and Graph Neural Networks, designed to optimize UAV cooperative behavior, data interpretation, and network analysis. Experimental results demonstrate that our model significantly outperforms existing approaches in terms of inspection accuracy, operational efficiency, and adaptability to environmental changes. The significance of our research lies in its potential to revolutionize the way power distribution networks are inspected and maintained, paving the way for more resilient and intelligent infrastructure systems. By leveraging the capabilities of MARL for dynamic decision-making, SOM for efficient data clustering, and GNNs for intricate network topology understanding, our model not only addresses current shortcomings in UAV collaborative inspection strategies but also sets a new benchmark for future developments in autonomous infrastructure monitoring, highlighting the crucial role of intelligent algorithms in advancing UAV technologies. [ABSTRACT FROM AUTHOR]

Context. Hot subdwarf stars are compact blue evolved objects, burning helium in their cores surrounded by a tiny hydrogen envelope. In the Hertzsprung-Russell Diagram they are located by the blue end of the Horizontal Branch. Most models agree on a quite probable common envelope binary evolution scenario in the Red Giant phase. However, the current binarity rate for these objects is yet unsolved, but key, question in this field. Aims. This study aims to develop a novel classification method for identifying hot subdwarf binaries within large datasets using Artificial Intelligence techniques and data from the third Gaia data release (GDR3). The results will be compared with those obtained previously using Virtual Observatory techniques on coincident samples. Methods. The methods used for hot subdwarf binary classification include supervised and unsupervised machine learning techniques. Specifically, we have used Support Vector Machines (SVM) to classify 3084 hot subdwarf stars based on their colour-magnitude properties. Among these, 2815 objects have Gaia DR3 BP/RP spectra, which were classified using Self-Organizing Maps (SOM) and Convolutional Neural Networks (CNN). In order to ensure spectral quality, previously to SOM and CNN classification, our 2815 BP/RP set were pre-analysed with two different approaches: the cosine similarity technique and the Uniform Manifold Approximation and Projection (UMAP) technique. Additional analysis onto a golden sample of 88 well-defined objects, is also presented. Results. The findings demonstrate a high agreement level (∼70–90%) with the classifications from the Virtual Observatory Sed Analyzer (VOSA) tool. This shows that the SVM, SOM, and CNN methods effectively classify sources with an accuracy comparable to human inspection or non-AI techniques. Notably, SVM in a radial basis function achieves 70.97% reproducibility for binary targets using photometry, and CNN reaches 84.94% for binary detection using spectroscopy. We also found that the single–binary differences are especially observable on the infrared flux in our Gaia DR3 BP/BR spectra, at wavelengths larger than ∼700 nm. Conclusions. We find that all the methods used are in fairly good agreement and are particularly effective to discern between single and binary systems. The agreement is also consistent with the results previously obtained with VOSA. In global terms, considering all quality metrics, CNN is the method that provides the best accuracy. The methods also appear effective for detecting peculiarities in the spectra. While promising, challenges in dealing with uncertain compositions highlight the need for caution, suggesting further research is needed to refine techniques and enhance automated classification reliability, particularly for large-scale surveys. [ABSTRACT FROM AUTHOR]

Aimed at the information loss problem of using discrete indicators in wind power output characteristics analysis, a self-organizing map neural network-based clustering method is proposed in this study. By identifying the appropriate representativeness and topological structure of the competition layer, cluster analysis of the wind power output process in four seasons is realized. The output characteristics are evaluated through multiple evaluation indicators. Taking the wind power output of the Hunan power grid as a case study, the results underscore that the 1 × 3-dimensional competition layer structure had the highest representativeness (72.9%), and the wind power output processes of each season were divided into three categories, with a robust and stable topology structure. Summer and winter were the most representative seasons. Summer had strong volatility and small wind power outputs, which required the utilization of other power sources to balance power supply and load demand. Winter featured low volatility and large wind power outputs, necessitating cooperation with peak-shaving power sources to enhance the power grid's absorbability to wind power. The seasonal clustering analysis of wind power outputs will be helpful to analyze the seasonality of wind power outputs and can provide scientific and technical support for guiding the power grid's operation and management. [ABSTRACT FROM AUTHOR]

Understanding precipitation over complex terrain, such as southwestern China, requires the consideration of both multiscale circulation and topography. First, the dominant synoptic system must be clarified, as it determines how multiscale topography affects precipitation. Here, based on a self-organizing map, large-scale winds are categorized into anomalous-westerly types, anomalous-easterly types, and transitional types. Four synoptic-scale systems (vortex type, cold-front type, tropical-depression type, and weak-synoptic-forcing type) dominate the summer precipitation. The vortex type occurs with strengthened large-scale westerlies, and its precipitation is distributed within the moisture convergence region. The cold-front type, tropical-depression type, and weak-synoptic-forcing type exhibit large-scale easterly anomalies. For the cold-front type, a low-level northeasterly blocked by topography shapes the northwest–southeast-oriented front zone at the upper highland slope. The precipitation frequency and intensity are high within the frontal zone, while the intensity is weak on both sides. For the tropical-depression type, moist low-level easterlies uplifted by westward-rising topography anchor precipitation at the lower slope. Large precipitation for the tropical-depression type is attributed to a high frequency. Large-scale horizontal winds are the weakest for the weak-synoptic-forcing type, and the local topography influences the scattered precipitation distribution. Both the frequency and intensity are high for the weak-synoptic-forcing type. Overall, long-lasting nocturnal events dominate the precipitation of the four synoptic types, while large-scale easterlies favor precipitation events with shorter durations and earlier peaks. For obvious synoptic systems, large-scale topography influences precipitation via a dynamic blocking effect, while the thermodynamic role of local topography is important with a weak-synoptic-forcing. Significance Statement: Clarifying dominant synoptic systems is highly important for understanding precipitation over complex terrain, as the effect of topography on precipitation varies with different synoptic backgrounds. Taking southwestern China as a representative of complex terrain, this study objectively identified the dominant synoptic systems associated with summer precipitation. The distribution and fine-scale characteristics of precipitation have been further analyzed considering the combined influence of multiscale circulation and topography. In addition to advancing our understanding of precipitation in southwestern China, this study provides a reference for analyzing precipitation in other regions with complex terrains. [ABSTRACT FROM AUTHOR]

As urbanization has accelerated, the coverage area of water distribution networks (WDNs) has been significantly increasing, making the management of large WDNs more difficult. To manage WDNs more accurately, water utilities split them into district metered areas (DMAs) of different sizes. However, the design of static DMAs has limitations in hydraulic performance during abnormal conditions in a WDN. To address this issue, first, this paper proposes a method for optimal DMA layout based on the combination of the self-organizing map (SOM) algorithm and the Leiden algorithm, achieving the optimal multilevel DMA layout and obtaining boundary pipes between DMAs. Then, the nondominated sorting genetic algorithm III (NSGAIII) method is employed to select the optimal arrangement of valves and flowmeters on boundary pipes from multiple perspectives, controlling the opening and closing of valves to achieve dynamic DMA partition. In the case of L-TOWN, the results show that the employed method reduces the average pressure variance by 15.6% compared with Louvain algorithms in the optimal multilevel DMA, which also effectively reduces bad connections between DMAs. Additionally, the obtained dynamic DMA layout exhibits excellent hydraulic performance. Under the two abnormal conditions, including fire events and increased water demand, the resilience index increased by 42% and 16%, respectively. [ABSTRACT FROM AUTHOR]

In this paper, we introduce a novel approach to enhance the accuracy and convergence behavior of Self-Organizing Maps (SOM) by incorporating a reweighted zero-attracting term into the loss function. We evaluated two SOM versions: conventional SOM and robust adaptive SOM (RASOM). The enhanced versions, reweighted zero-attracting SOM (RZA-SOM) and reweighted zero-attracting RASOM (RZA-RASOM), include an l 1 norm in the error function to add a zero-attractor term, which improves weight coefficient adjustments while preserving topology. The models were assessed for convergence speed and misadjustment under sparsity assumptions of the true coefficient matrix, and their robustness was tested under conditions of increased non-zero taps. Using six different datasets, we compared the performance of RZA-SOM and RZA-RASOM against conventional SOM and RA-SOM in terms of accuracy, quantization error, and topology preservation. Experimental results consistently demonstrated that RZA-SOM and RZA-RASOM surpassed the performance of conventional SOM and RA-SOM. • Introduction of novel reweighted zero-attractor term in loss function for heightened SOM algorithmic precision. • Heightened convergence rates and improved behavior, marked by earlier error steady-state attainment during training. • Enhanced robustness against outliers and superior handling of imbalanced data in multiclass clustering scenarios. • Rigorous experimental evaluations across six distinct datasets effectively underpin proposed algorithmic enhancements. [ABSTRACT FROM AUTHOR]

In an age where digital connectivity is increasingly shaping entertainment content, personalized movie recommendations play a pivotal role in enhancing user satisfaction and engagement. This research introduces an innovative approach utilizing Enhanced Self-Organizing Maps (SOM) to streamline movie selection processes. Self-Organizing Maps (SOMs), a type of unsupervised neural network architecture, are particularly adept at discerning intricate data patterns, making them valuable assets in recommendation systems. The methodology outlined in this paper commences with gathering usermovie interaction data, including user feedback and movie characteristics, which is standardized to ensure consistency before model training. Leveraging its adaptable learning rate and neighborhood function, the Enhanced SOM effectively identifies subtle data nuances. Personalized movie suggestions are then generated by exploiting the Enhanced SOM's capacity to identify similar users and films. Integration of hybrid filtering techniques enriches recommendation quality, blending collaborative filtering algorithms, which leverage user-item interactions, with content-based filtering, which utilizes movie attributes such as genres and descriptions. This amalgamation results in suggestions that harmoniously combine diverse filtering methodologies. The proposed solution's efficacy is rigorously evaluated by comparing suggestion accuracy and user satisfaction against predefined benchmarks. Extensive real-world dataset testing corroborates the effectiveness of the Enhanced SOM-based movie recommendation approach. Furthermore, the system offers flexibility through options for parameter adjustment, grid size variations, and neighborhood function modifications to further refine recommendation accuracy. Collectively, these elements underscore the efficacy of the proposed method in furnishing tailored movie recommendations. When coupled with hybrid filtering techniques, the implementation of Enhanced SOMs emerges as a reliable model for content platforms seeking to enhance user experiences by delivering precise movie recommendations, coupled with scalability and adaptability. [ABSTRACT FROM AUTHOR]

The automatic analysis of histology images is an open research field where machine learning techniques and neural networks, especially deep architectures, are considered successful tools due to their abilities in image classification. This paper proposes a granular computing methodology for histopathological image classification. It is based on embedding tiles of histopathology images using deep metric learning, where a self-organizing map is adopted to generate the granular structure in this learned embedding space. The SOM enables the implementation of an explainable mechanism by visualizing a knowledge space that the experts can use to analyze and classify the new images. Additionally, it provides confidence in the classification results while highlighting each important image fragment, with the benefit of reducing the number of false negatives. An exemplary case is when an image detail is indicated, with small confidence, as malignant in an image globally classified as benign. Another implemented feature is the proposal of additional labelled image tiles sharing the same characteristics to specify the context of the output decision. The proposed system was tested using three histopathology image datasets, obtaining the accuracy of the state-of-the-art black-box methods based on deep learning neural networks. Differently from the methodologies proposed so far for the same purpose, this paper introduces a novel explainable method for medical image analysis where the advantages of the deep learning neural networks used to build the embedding space for the image tiles are combined with the intrinsic explainability of the granular process obtained using the clustering property of a self-organizing map. [ABSTRACT FROM AUTHOR]

The purpose of this study is to investigate the effects of toolpath patterns, geometry types, and layering effects on the mechanical properties of parts manufactured by direct energy deposition (DED) additive manufacturing using data analysis and machine learning methods. A total of twelve case studies were conducted, involving four distinct geometries, each paired with three different toolpath patterns based on finite element method (FEM) simulations. These simulations focused on residual stresses, strains, and maximum principal stresses at various nodes. A comprehensive analysis was performed using a linear mixed-effects (LME) model, principal component analysis (PCA), and self-organizing map (SOM) clustering. The LME model quantified the contributions of geometry, toolpath, and layer number to mechanical properties, while PCA identified key variables with high variance. SOM clustering was used to classify the data, revealing patterns related to stress and strain distributions across different geometries and toolpaths. In conclusion, LME, PCA, and SOM offer valuable insights into the final mechanical properties of DED-fabricated parts. [ABSTRACT FROM AUTHOR]

Variable heat fluxes over the Tibetan Plateau (TP) interact thermally with the atmosphere, affecting weather in surrounding areas, particularly in the Middle and Lower Yangtze River (MLYR). However, the circulation patterns and time-lag effects between TP heat fluxes and MLYR precipitation remain unclear. This study identified 577 large-scale daily heavy precipitation events (LSDHPEs) in the MLYR from 1980 to 2022. We analyzed the weather causation and spatiotemporal correlations between the TP surface heat fluxes and MLYR LSDHPEs using self-organizing map clustering, singular value decomposition, and harmonic analysis of time series. The results found two dominant synoptic patterns of LSDHPEs at 500 hPa: one, driven by anticyclonic and cyclonic circulations coinciding with shifts in the West Pacific subtropical high and South Asian high, increased from 2000 to 2022; the other, influenced by MLYR cyclonic circulation, showed a significant decrease. For the first time, we revealed lagged effects of the latent heat anomalies (with a lag time of 1–10 d and 130–200 d) and sensible heat anomalies (with a lag time of 2–4 months) over the TP during LSDHPEs in the MLYR. The results may enhance our understanding of TP heat flux anomalies as precursor signals for early warning of heavy rainfall and flooding in the MLYR. [ABSTRACT FROM AUTHOR]

Soil and water conservation is one of the most important parts of the national ecological civilization. The spatial control area of soil and water conservation can be divided to effectively manage the soil and water loss regions. However, it is still lacking in the spatial delineation in the regional division of soil and water conservation. Only a few studies have been focused on the spatial control of soil and water conservation, according to the small watershed. This study aims to explore the spatial control zoning for soil and water conservation, and then implement the differentiated protection and management measures. The universal soil loss equation (USLE) model was used to calculate the potential and actual soil erosion. The main influencing factors of soil erosion were determined by random forests. A self-organizing feature map (SOFM) was used to determine the spatial control zone of soil and water conservation in the Dabie Mountain area on a small catchment scale. The results showed that: 1) The average potential and actual soil erosion were 84415.7 t/(km²·a) and 210.25 t/(km²·a), respectively. The actual soil erosion was distributed mainly in 0-300 t/(km²·a) at the small watershed scale. There was the basically same distribution of spatial patterns under the potential and actual soil erosion. The high-value area was distributed mainly in the central and eastern mountain areas at the high elevation. 2) Vegetation coverage and slope were the main influencing factors of potential and actual soil erosion at the small watershed scale, indicating a significantly positive correlation with the potential soil erosion (P<0.01). The high vegetation cover area was concentrated in the hinterland of Dabie Mountain. The high slope area was extended from the west to the east along the ridgeline of Dabie Mountain. 3) The SOFM results showed that the spatial control zone of soil and water conservation was divided into three areas: key prevention, general prevention, and the rest area at the small watershed scale. Among them, the key prevention area involved 710 small watersheds with an area of 1 5287.4 km². There were 890 small watersheds in the general prevention area, covering an area of 18 874.4 km². Two prevention areas accounted for 61.2% of the study area. There was an outstanding difference between actual and potential soil erosion and slope among regions. The classification index can serve as the spatial control of soil and water conservation. The finding can provide theoretical support and decision-making on the spatial control regionalization for soil and water conservation. [ABSTRACT FROM AUTHOR]

Coastal moorings allow scientists to collect long-term datasets valuable in understanding shelf dynamics, detecting climate variability and changes, and evaluating their impacts on marine ecosystems. Continuous time series data from moorings is often disrupted due to mooring losses or instrument failures, which prevents us from obtaining complete and accurate information on the marine environment. Here, we present an updated version of the 14-year subsurface mooring dataset off the southwest coast of Western Australia during 2010–2023 (https://doi.org/10.25919/myac-yx60 , Bui and Feng, 2024). This updated dataset offers continuous daily temperature and current data with a 5-meter vertical resolution, collected from six coastal Integrated Marine Observing System (IMOS) moorings at depths between 48 m and 500 m. Self-Organizing Map (SOM) machine learning technique is applied to fill in the data gaps in the previous version. The usage of the in-filled data product is demonstrated by detecting sub-surface marine heatwaves on the Rottnest shelf. The data products can be used to characterise subsurface features of extreme events such as marine heatwaves, and marine cold-spells, influenced by the Leeuwin Current and the wind-driven Capes Current, and to detect long-term change signals along the coast. [ABSTRACT FROM AUTHOR]

Background: Anxiety is the most prevalent comorbidity among children and adolescents with autism spectrum disorder (ASD), yet little is known about the associated risk factors. Methods: In a heterogenous cohort of children aged 5–18 years old (n = 262, 42% ASD), participants and their parents completed standardized questionnaires to assess anxiety, ASD symptom severity, inattention/hyperactivity, emotional problems, depressive symptoms, parental styles and stress, and demographic factors. Results: An artificial neural network analysis using a self-organizing map, a statistical technique used to cluster large datasets, revealed 3 distinct anxiety profiles: low (n = 114, 5% ASD), moderate (n = 70, 64% ASD) and high (n = 78, 96% ASD) anxiety. A recursive feature elimination analysis revealed that depression and peer problems contributed the most to differences between the anxiety profiles. Difficulties with peers in individuals with ASD who experience anxiety may be related to challenges with social competence and this may heighten depressive symptoms. Conclusion: Findings highlight the importance of assessing depressive symptoms in children and adolescents with ASD who experience anxiety. Identifying anxiety profiles among children and adolescents with ASD may prove beneficial in clinical practice by facilitating the development of tailored interventions that aid in managing anxiety and depressive symptoms. Furthermore, strengthening social communication skills may improve peer relationships and could aid in managing depressive symptoms among children and adolescents with ASD who experience anxiety. [ABSTRACT FROM AUTHOR]

The increased occurrence of extreme weather events worldwide has changed the way power system reliability is determined. The effect of high intensity weather events has catastrophic effects on power system operation, and the determination of its effect is a very important and timely requirement. The conventional reliability evaluation methods used in power systems require knowledge of historical datasets, which may not be available in the case of an extreme event as these events have a low probability of occurrence. Hence, new methods to quantify power system resilience are needed. This paper uses a self-organizing map (SOM) to compute the resilience of any network using only system information, no historical data are required. The use of SOM makes the resilience quantification process very fast, and hence resilience can be evaluated in real-time during any catastrophic event, and correspondingly, action can be taken to improve the resilience of the system using available resources in the most suitable way so that the system can glide through the extreme event with the best possible performance. The paper first details the SOM-based resilience quantification method and then proposes a two-stage resilience improvement strategy using existing resources connected to the system based on the resilience value calculated in real-time during the progression of the event. The proposed quantification method and the resilience improvement strategy are tested on the IEEE 33 bus and 69 bus distribution systems. The results show that the resilience improved from 0.45 to 0.95 and 0.65 to 0.85 for the two systems, respectively, which proves the effectiveness of the proposed methodology. [ABSTRACT FROM AUTHOR]

To deal with the task assignment problem of multi-AUV systems under kinematic constraints, which means steering capability constraints for underactuated AUVs or other vehicles likely, an improved task assignment algorithm is proposed combining the Dubins Path algorithm with improved SOM neural network algorithm. At first, the aimed tasks are assigned to the AUVs by the improved SOM neural network method based on workload balance and neighborhood function. When there exists kinematic constraints or obstacles which may cause failure of trajectory planning, task re-assignment will be implemented by changing the weights of SOM neurals, until the AUVs can have paths to reach all the targets. Then, the Dubins paths are generated in several limited cases. The AUV's yaw angle is limited, which results in new assignments to the targets. Computation flow is designed so that the algorithm in MATLAB and Python can realize the path planning to multiple targets. Finally, simulation results prove that the proposed algorithm can effectively accomplish the task assignment task for a multi-AUV system. [ABSTRACT FROM AUTHOR]

Fatigue driving is one of the leading causes of traffic accidents, and the rapid and accurate detection of driver fatigue is of paramount importance for enhancing road safety. However, the application of deep learning models in fatigue driving detection has long been constrained by high computational costs and power consumption. To address this issue, this study proposes an approach that combines Self-Organizing Map (SOM) and Spiking Neural Networks (SNN) to develop a low-power model capable of accurately recognizing the driver's mental state. Initially, spatial features are extracted from electroencephalogram (EEG) signals using the SOM network. Subsequently, the extracted weight vectors are encoded and fed into the SNN for fatigue driving classification. The research results demonstrate that the proposed method effectively considers the spatiotemporal characteristics of EEG signals, achieving efficient fatigue detection. Simultaneously, this approach successfully reduces the model's power consumption. When compared to traditional artificial neural networks, our method reduces energy consumption by approximately 12.21–42.59%. [ABSTRACT FROM AUTHOR]

Cognitive diagnosis is a crucial element of intelligent education that aims to assess the proficiency of specific skills or traits in students at a refined level and provide insights into their strengths and weaknesses for personalized learning. Researchers have developed numerous cognitive diagnostic models. However, previous studies indicate that diagnostic accuracy can be significantly influenced by the appropriateness of the model and the sample size. Thus, designing a general model that can adapt to different assumptions and sample sizes remains a considerable challenge. Artificial neural networks have been proposed as a promising approach in some studies. In this paper, we propose a cognitive diagnosis model of a neural network constrained by a Q-matrix and named QNN. Specifically, we employ the Q-matrix to determine the connections between neurons and the width and depth of the neural network. Moreover, to reduce the human effort in the training algorithm, we designed a self-organizing map-based cognitive diagnosis training framework called SOM-NN, which enables the QNN to be trained unsupervised. Extensive experimental results on simulated and real datasets demonstrate that our approaches are effective in both accuracy and interpretability. Notably, under unsupervised conditions, our approach has significant advantages on small sample datasets with high levels of guessing and slipping, especially on the pattern-wise agreement rates. This work bridges the gap between psychometrics and machine learning and provides a realistic and implementable reference solution for classroom instructional assessment and the cold start of personalized and adaptive assessment systems. [ABSTRACT FROM AUTHOR]

There has been an increasing interest in multi-view approaches based on their ability to manage data from several sources. However, regarding unsupervised learning, most multi-view approaches are clustering algorithms suitable for analyzing vector data. Currently, only a relatively few SOM algorithms can manage multi-view dissimilarity data, despite their usefulness. This paper proposes two new families of batch SOM algorithms for multi-view dissimilarity data: multi-medoids SOM and relational SOM, both designed to give a crisp partition and learn the relevance weight for each dissimilarity matrix by optimizing an objective function, aiming to preserve the topological properties of the map data. In both families, the weight represents the relevance of each dissimilarity matrix for the learning task being computed, either locally, for each cluster, or globally, for the whole partition. The proposed algorithms were compared with already in the literature single-view SOM and set-medoids SOM for multi-view dissimilarity data. According to the experiments using 14 datasets for F-measure, NMI, Topographic Error, and Silhouette, the relevance weights of the dissimilarity matrices must be considered. In addition, the multi-medoids and relational SOM performed better than the set-medoids SOM. An application study was also carried out on a dermatology dataset, where the proposed methods have the best performance. [ABSTRACT FROM AUTHOR]

Groundwater is a dynamic component of the global water cycle with important social, economic, ecological, and Earth system functions. We present a new global classification and mapping of groundwater systems, which we call groundwaterscapes, that represent predominant configurations of large‐scale groundwater system functions. We identify and map 15 groundwaterscapes which offer a new lens to conceptualize, study, model, and manage groundwater. Groundwaterscapes are derived using a novel application of sequenced self‐organizing maps that capture patterns in groundwater system functions at the grid cell level (∼10 km), including groundwater‐dependent ecosystem type and density, storage capacity, irrigation, safe drinking water access, and national governance. All large aquifer systems of the world are characterized by multiple groundwaterscapes, highlighting the pitfalls of treating these groundwater bodies as lumped systems in global assessments. We evaluate the distribution of Global Groundwater Monitoring Network wells across groundwaterscapes and find that industrial agricultural regions are disproportionately monitored, while several groundwaterscapes have next to no monitoring wells. This disparity undermines the ability to understand system dynamics across the full range of settings that characterize groundwater systems globally. We argue that groundwaterscapes offer a conceptual and spatial tool to guide model development, hypothesis testing, and future data collection initiatives to better understand groundwater's embeddedness within social‐ecological systems at the global scale. Key Points: Groundwaterscapes are presented as landscape units representing configurations of groundwater's social‐ecological and Earth system functionsA two‐stage self‐organizing map clustering method is implemented to derive 15 groundwaterscapes at the global scaleAll large aquifer systems of the world contain multiple groundwaterscapes [ABSTRACT FROM AUTHOR]

The purpose of this research was to model areas prone to erosion in the Gol-Mehran catchment in southern Iran. For this purpose, the soil erosion map was determined using membership functions and analytic hierarchy process (AHP) determined the soil erosion map. Additionally, using the self-organizing map (SOM) and principal component analysis (PCA) methods, the most crucial parameters affecting gully erosion were extracted. Finally, soil erosion was predicted using a multilayer perceptron (MLP) and radial basis function. The results of the fuzzy AHP method with all data and the selected data with SOM and PCA demonstrated that areas located in the center of the region were prone to gully erosion. The results of this research also demonstrated that urban lands have expanded significantly, while vegetation has decreased from 1990 to 2019, which has had a significant impact on soil erosion. The results also showed that the MLP model, with R2 = 0.97, could accurately predict soil erosion. [ABSTRACT FROM AUTHOR]

Integrating ecosystem services (ESs) to delineate ecological functional zones (EFZs) is fundamental in terrestrial spatial planning and ecosystem management. However, existing studies have largely overlooked the refinement of EFZs at local scales, which hinders targeted and multi-scale ecosystem management. This study introduced a "two-step refinement zoning method" to address this gap, first using a self-organizing feature mapping method to delineate EFZs at a township scale, and then applying a hotspot overlay analysis to refine the resulting EFZs by designating them with different grades at the village scale. The proposed method was applied in Wuhan City, dividing it into five types of EFZs with different ES combinations and land use compositions. Furthermore, 5.23% of villages were identified as level I areas of EFZs, serving as advantageous areas of dominant ESs in the study area. On this basis, diversified management strategies and conservation priorities were proposed. This study provides a theoretical and methodological reference for terrestrial spatial planning and sustainable ecosystem management. [ABSTRACT FROM AUTHOR]

Background and objective: Systemic autoinflammatory diseases (SAIDs) are characterized by widespread inflammation, but for most of them there is a lack of specific biomarkers for accurate diagnosis. Although a number of machine learning algorithms have been used to analyze SAID datasets, aiding in the discovery of novel biomarkers, there is a growing recognition of the importance of SAID timeseries clustering, as it can capture the temporal dynamics of gene expression patterns. Methodology: This paper proposes a novel clustering methodology to efficiently associate three-dimensional data. The algorithm utilizes competitive learning to create a self-organizing neural network and adjust neuron positions in time-dependent and high dimensional feature space in order to assign them as clustering centers. The quantitative evaluation of the clustering was based on well-known clustering indices. Furthermore, a differential expression analysis and classification pipeline was employed to assess the capability of the proposed methodology to extract more accurate pathway-specific genes from its clusters. For that, a comparative analysis was also conducted against a heuristic timeseries clustering method. Results: The proposed methodology achieved better overall clustering indices scores and classification metrics using genes derived from its clusters. Notable cases include a threefold increase in the Calinski-Harabasz clustering index, a twofold improvement in the Davies–Bouldin clustering index and a ∼60% increase in the classification specificity score. Conclusion: A novel clustering methodology was developed and applied on several gene expression timeseries datasets from systemic autoinflammatory diseases, and its ability to efficiently produce well separated clusters compared to existing heuristic methods was demonstrated.

Abstract One method for estimating floods in areas lacking statistical data is the use of regional frequency analysis based on machine learning. In this study, statistical and clustering-based approaches were evaluated for flood estimation in the Karkheh watershed. The hydrological homogeneity of the obtained zones was then assessed using linear moments and heterogeneity adjustment methods proposed by Hosking and Wallis. Then, the ZDIST statistic was used to calculate the three-parameter distributions for stations within each hydrologically homogeneous cluster. These parameters were computed using linear moments, and floods with different return periods at each station were estimated using regional relationships. The results indicated the creation of two clusters in this area, with five stations in cluster one and 11 stations in cluster two. The statistical homogeneity values for clusters one and two were calculated as 0.33 and 0.17, respectively, indicating the homogeneity of each region. Generalized Pearson type III and generalized extreme value distributions were selected as the best regional distributions for clusters 1 and 2, respectively. The results also showed that floods could be estimated for return periods of 2, 5, 25 years, and more. The highest estimated flood is predicted at the Jelugir-e Majin station, where the flood with a 2-year return period reaches 1034 m3 s−1. This increases to 5360 m3 s−1 for a 100-year return period. The approach presented in this study is recommended for similar regions lacking complete information.

Objective weather classification methods have been extensively applied to identify dominant ozone-favorable synoptic weather patterns (SWPs), however, the consistency of different classification methods is rarely examined. In this study, we apply two widely-used objective methods, the self-organizing map (SOM) and K-means clustering analysis, to derive ozone-favorable SWPs at four Chinese megacities in 2015–2022. We find that the two algorithms are largely consistent in recognizing dominant ozone-favorable SWPs for four Chinese megacities. In the case of classifying six SWPs, the derived circulation fields are highly similar with a spatial correlation of 0.99 between the two methods, and the difference in the mean frequency of each SWP is less than 7%. The six dominant ozone-favorable SWPs in Guangzhou are all characterized by anomaly higher radiation and temperature, lower cloud cover, relative humidity, and wind speed, and stronger subsidence compared to climatology mean. We find that during 2015–2022, the occurrence of ozone-favorable SWPs days increases significantly at a rate of 3.2 day/year, faster than the increases in the ozone exceedance days (3.0 day/year). The interannual variability between the occurrence of ozone-favorable SWPs and ozone exceedance days are generally consistent with a temporal correlation coefficient of 0.6. In particular, the significant increase in ozone-favorable SWPs in 2022, especially the Subtropical High type which typically occurs in September, is consistent with a long-lasting ozone pollution episode in Guangzhou during September 2022. Our results thus reveal that enhanced frequency of ozone-favorable SWPs plays an important role in the observed 2015–2022 ozone increase in Guangzhou. [ABSTRACT FROM AUTHOR]

Customer data analysis helps companies to understand customer intentions and behaviors better. This study introduces an analysis of product reviews to help managers adopt a more efficient strategy to extract valuable knowledge and help detect segment of customers that need a special attention and products that need improvement or with the most impact. The used dataset is a set of Amazon reviews divided into multiple categories; each review has a target column called 'overall' that takes a value between 1 and 5 (customer's satisfaction). Based on the 'overall' column, multiple labeling methods have been used and compared to get a binary target variable, positive or negative, that affects a class to a review. This dataset contains more than one million reviews and can give companies great insight into products' quality and customers' retention. This work has materialized by using customer segmentation and competitive learning with self-organizing map (SOM) Model and adopting a new approach to explore the generated network/map, it is based on clustering and map nodes labelling using a majority voting process. The results show that the proposed dual approach combining the prior knowledge, related to supervised learning, and the competitive learning abilities enhances the SOM model's capabilities. [ABSTRACT FROM AUTHOR]

Mini-batch partitioning is a widely used technique in deep learning that involves dividing a dataset into smaller subsets. This method is crucial in training deep learning models such as deep neural networks and convolutional neural networks. It is favored for its ability to accelerate model convergence, reduce memory overhead, and minimize convergence errors. The primary advantage of mini-batch partitioning is that it allows the model to learn dataset features more evenly, thereby speeding up the convergence process. However, determining the optimal method and size for mini-batch partitioning remains a challenging problem. This paper proposes a novel mini-batch partitioning method focused on feature reorganization. By leveraging a Self-Organizing Map network for feature extraction, data with similar characteristics are initially grouped into the same batch. The purity index of each batch is then calculated based on the number of features and labels, allowing for a comprehensive evaluation of batch homogeneity. Batches with significant differences in purity are selectively reorganized to ensure that each batch contains a diverse set of features, reducing intra-batch feature correlation and ultimately enhancing data representation.Furthermore, through SOM network mapping, the dataset can be effectively partitioned into subsets that are well-suited for model training. Experimental comparisons of various batch partitioning methods on multiple UCI datasets demonstrate that our proposed method, termed MPBS (Mini-Batch Partitioning Algorithm based on Self-Organizing Map Network). Compared with other algorithms, the accuracy, loss and training time are improved by 14.06%, 24.31% and 31.22%. [ABSTRACT FROM AUTHOR]

Introduction: Degeneracy in the brain-behavior code refers to the brain's ability to utilize different neural configurations to support similar functions, reflecting its adaptability and robustness. This study aims to explore degeneracy by investigating the non-linear associations between psychometric profiles and resting-state functional connectivity (RSFC). Methods: The study analyzed RSFC data from 500 subjects to uncover the underlying neural configurations associated with various psychometric outcomes. Self-organized maps (SOM), a type of unsupervised machine learning algorithm, were employed to cluster the RSFC data. And identify distinct archetypal connectivity profiles characterized by unique within- and betweennetwork connectivity patterns. Results: The clustering analysis using SOM revealed several distinct archetypal connectivity profiles within the RSFC data. Each archetype exhibited unique connectivity patterns that correlated with various cognitive, physical, and socioemotional outcomes. Notably, the interaction between different SOM dimensions was significantly associated with specific psychometric profiles. Discussion: This study underscores the complexity of brain-behavior interactions and the brain's capacity for degeneracy, where different neural configurations can lead to similar behavioral outcomes. These findings highlight the existence of multiple brain architectures capable of producing similar behavioral outcomes, illustrating the concept of neural degeneracy, and advance our understanding of neural degeneracy and its implications for cognitive and emotional health. [ABSTRACT FROM AUTHOR]

This paper combines self-organizing mapping (SOM) and a long short-term memory network (SOM-LSTM) to construct an audio-based motor-fault diagnosis system for identifying the operating states of a rotary motor. This paper first uses an audio signal collector to measure the motor sound signal data, uses fast Fourier transform (FFT) to convert the actual measured sound–time-domain signal into a frequency-domain signal, and normalizes and calibrates the frequency-domain signal to ensure the consistency and accuracy of the signal. Secondly, the SOM is used to further analyze the characterized frequency-domain waveforms in order to reveal the intrinsic structure and pattern of the data. The LSTM network is used to process the secondary data generated via SOM. Dimensional data aggregation and the prediction of sequence data in long-term dependencies accurately identify different operating states and possible abnormal patterns. This paper also uses the experimental design of the Taguchi method to optimize the parameters of SOM-LSTM in order to increase the execution efficiency of fault diagnosis. Finally, the fault diagnosis system is applied to the real-time monitoring of the motor operation, the work of identifying the motor-fault type is performed, and tests under different loads and environments are attempted to evaluate its feasibility. The completion of this paper provides a diagnostic strategy that can be followed when it comes to motor faults. Through this fault diagnosis system, abnormal conditions in motor equipment can be detected, which can help with preventive maintenance, make work more efficient and save a lot of time and costs, and improve the industry's ability to monitor motor operation information. [ABSTRACT FROM AUTHOR]

Federated Learning (FL) is an emerging privacy-preserving technology that enables training a global model beneficial to all participants without sharing their data. However, differences in data distributions among participants may undermine the stability and accuracy of the global model. To address this challenge, recent research proposes client clustering based on data distribution similarity, generating independent models for each cluster in order to enhance FL performance. Nevertheless, due to the uncertainty of participant identities, FL struggles to rapidly and accurately determine the clusters. Most of the existing algorithms distinguish clients by iterative clustering, which not only increases the computing cost of the server but also affects the convergence speed of the federation model. To address these shortcomings, in this paper, we propose a novel clustering-based FL method, SoFL. SoFL introduces SOM networks, improves the quality of cluster data, and eliminates redundant categories through secondary clustering, encouraging more similar clients to train together. Through this mechanism, SoFL completes the clustering task in one round of communication and speeds up the convergence of federated model training. Simulation results demonstrate that SoFL accurately and swiftly adapts to determine the clusters. In different non-IID settings, SoFL's model accuracy improvements ranged from 9 to 18% compared to FedAvg and FedProx. [ABSTRACT FROM AUTHOR]

To comprehensively explore flow control method of profiled end wall for turbine stage at low Reynolds numbers, a surrogate model optimization platform including non-uniform rational B-spline surface parameterization method, support vector regression, and improved chaos particle swarm optimization algorithm is integrated. Optimization designs have been carried out for stator profiled end walls, rotor profiled end wall, and combined end walls, respectively. The results indicate that under the constraint of the output power, the application of various profiled end wall design cases all can effectively improve the aerodynamic performance of the turbine stage. By organizing the flow field of downstream rotor, the profiled end wall of stator can significantly affect the stage efficiency. The flow control benefits of the profiled end wall of the rotor is from the obstruction of the cross migration of the pressure side leg of the horseshoe vortex. The application of profiled end wall on stator has the most practical engineering value. Self-organizing maps and Shapley methods are used to explore potential correlation information of aerodynamic parameters and summarize design experience. The sensitive design variables of profiled end walls are extracted. Based on the local controllability of NURBS surfaces, the regions that affect the stage efficiency are mainly concentrated in the middle of the stator passage, near the stator trailing edge and near the rotor leading edge. The regions with a significant impact on the output power of the turbine stage are near the trailing edge of the rotor and stator. The corresponding design rules of end walls modeling are summarized. [ABSTRACT FROM AUTHOR]

This article explores the efficiency of various clustering methods for image segmentation under different luminosity conditions. Image segmentation plays a crucial role in computer vision applications, and clustering algorithms are commonly used for this purpose. The search for an adaptive clustering mechanism aims to ensure the maximum symmetry of real objects with objects/segments in their digital representations. However, clustering method performances can fluctuate with varying lighting conditions during image capture. Therefore, we assess the performance of several clustering algorithms—including K-Means, K-Medoids, Fuzzy C-Means, Possibilistic C-Means, Gustafson–Kessel, Entropy-based Fuzzy, Ridler–Calvard, Kohonen Self-Organizing Maps and MeanShift—across images captured under different illumination conditions. Additionally, we develop an adaptive image segmentation system utilizing empirical data. Conducted experiments highlight varied performances among clustering methods under different luminosity conditions. This research enhances a better understanding of luminosity's impact on image segmentation and aids the method selection for diverse lighting scenarios. [ABSTRACT FROM AUTHOR]

The onset of the rainy season in Vietnam displays distinct characteristics compared to other Asian summer monsoon (ASM) regions due to its elongated shape running from south to north, coupled with its complex terrain and the influences of multiple weather systems. Determining the onset is challenging, although numerous empirical indices exist. Here, we proposed an alternative approach to determine the onset by examining the large-scale weather patterns associated with the abrupt increase in rainfall in the country. In this new approach, the evolutions of the ASM system were interpreted as consecutive occurrences of multiple weather patterns, detected by a clustering algorithm Self Organizing Maps (SOMs). Specifically, SOMs were applied on outgoing longwave radiation, 850 hPa wind, and geopotential height over the ASM regions from April to July. The primary features of these atmospheric variables were generalized to 16 patterns. A high-resolution Vietnam Gridded Precipitation (VnGP) dataset was employed to investigate the linkage between these large-scale patterns and local-scale rainfall. The large-scale patterns associated with the onset were distinguished, which are characterized by the development of westerly winds and large-scale convections. Then, the onset of summer rainfall in Vietnam is identified based on the initial appearance of wet-condition weather patterns. This approach offers several advantages: it is objective and does not require additional thresholds of rain or wind to determine the monsoon onset. It also more effectively captures the characteristics of large-scale circulation and deep convection compared to relying on predefined monsoon indices alone. Additionally, this approach helped to elucidate two types of weather patterns associated with the onset: those associated with the northeastward development of deep convection and westerly wind from the Indian Ocean to the Indochina Peninsula and activities of the Boreal Summer Intraseasonal Oscillation. [ABSTRACT FROM AUTHOR]

The objectives of this study were to examine the importance of variables such as perceived quality, low price, social interaction, consumer knowledge, and packaging on purchase intention for beer in the Brazilian market; and to identify consumer groups with a distinct profile based on their behavior concerning these important variables. We found that perceived quality, low price, and social interaction were predictors of the willingness to buy beer. We also found that consumer product knowledge and packaging moderated the effects of perceived quality and low price on purchase intention. Our findings showed that the more product knowledge a consumer possesses, the less perceived quality would impact a beer brand's purchase intention; and the greater the influence of packaging, the less impact a low price will have on the purchase intention of a beer brand. Our research also identified three distinct groups of beer consumers: Bohemians, Tasters, and NOBELs (NOt a BEer Lover). [ABSTRACT FROM AUTHOR]

This paper assesses the importance of incorporating care dimensions into activity-travel segmentation to understand daily life mobility strategies. The data came from six neighbourhoods in Concepción, Chile, and included detailed information on activity-travel time use and interaction and classification schemes to identify care purposes. The study uses self-organizing maps to build incremental behavioural segments from weekly mobility and time use variables, adding care activities to assess their role in this segmentation. The results identify groups with a higher burden on care than others, emphasizing the role of transport mode and time use patterns. The result remarks caregiving activities hidden within other categories, identifying groups of caregivers, including domestic workers and women who work and have intense accompanying activities with children. The results highlight the differences between mobility patterns between different segments to make more invisible care and other related activities disproportionately performed by groups of women. [ABSTRACT FROM AUTHOR]