Self-organizing Map Neural Network Research Articles

Retracted: Difference Analysis of Regional Economic Development Based on the SOM Neural Network with the Hybrid Genetic Algorithm.

[This retracts the article DOI: 10.1155/2021/6734345.].

Retracted: Analysis of Enterprise Human Resources Demand Forecast Model Based on SOM Neural Network.

[This retracts the article DOI: 10.1155/2021/6596548.].

Retraction Note: Visualization model of big data based on self-organizing feature map neural network and graphic theory for smart cities

Retraction Note: Visualization model of big data based on self-organizing feature map neural network and graphic theory for smart cities

A data-driven spatially-specific vaccine allocation framework for COVID-19.

Although coronavirus disease 2019 (COVID-19) vaccines have been introduced, their allocation is a challenging problem. We propose a data-driven, spatially-specific vaccine allocation framework that aims to minimize the number of COVID-19-related deaths or infections. The framework combines a regional risk-level classification model solved by a self-organizing map neural network, a spatially-specific disease progression model, and a vaccine allocation model that considers vaccine production capacity. We use data obtained from Wuhan and 35 other cities in China from January 26 to February 11, 2020, to avoid the effects of intervention. Our results suggest that, in region-wise distribution of vaccines, they should be allocated first to the source region of the outbreak and then to the other regions in order of decreasing risk whether the outcome measure is the number of deaths or infections. This spatially-specific vaccine allocation policy significantly outperforms some current allocation policies.

Approximate optimal energy management with a high-precision vehicle speed prediction algorithm

A predictive energy management strategy is proposed for plug-in hybrid electric vehicles, which adopts a new high-precision vehicle speed prediction algorithm and a real-time reference state of charge (SOC) trajectory planning method. The speed prediction algorithm includes a modified Markov model based on vehicle speed features recognized by the self-organizing map neural network method, Fourier approximation, and moving average filtering. The prediction accuracy of the algorithm, measured by the root mean square error, is improved by 32.28% and 23.33%, respectively, over that of the standard Markov model when the prediction time is 5 and 10 s. To approach the optimal management strategy for improved vehicle fuel economy, the radial basis function neural network method is utilized to correlate the 10 s predicted vehicle speed with the trajectory slope of the suboptimal SOC for obtaining the reference SOC trajectory, which is applied to the adaptive equivalent consumption minimization strategy based on SOC feedback. The simulation indicates that the fuel consumption by using the proposed energy management strategy is very close to that by the theoretical suboptimal strategy with the shooting method, which leads to a superior fuel economy among the strategies studied.

Clustering and assessing carbon peak statuses of typical cities in underdeveloped Western China

As the main source of carbon emissions, cities are vital for achieving China's carbon peak goal by 2030. However, few studies have focused on China’s city-level carbon emissions peak, particularly in the underdeveloped western region of China. Therefore, this study explores the peak carbon statuses and trends of cities in less-developed western China. We applied a self-organising map neural network to perform cluster analysis within 76 cities, combined with the decoupling coefficient method and Mann-Kendall test to evaluate the peak carbon trend of cities. The results showed that cities in western China can be divided into resource-dependent cities, low-carbon buffer cities, economic priority cities, and low-carbon transition cities. We also discussed the unbalanced and asynchronous characteristics of paths to achieve carbon peaks in these cities, which should be addressed in China’s strategy of achieving carbon peaks.

An Integrated Condition Monitoring Method for Rotating Machinery Based on Optimum Healthy State

The degradation of a machine is nonlinear, which brings challenges to its performance assessment during condition monitoring, especially when there is a run-in period. Technically, the quantification of mechanical degradation is to define a distance metric from a health baseline. This paper develops an integrated condition monitoring scheme, where the degradation evaluation and fault diagnosis are combined by using one technical framework. Specifically, an optimum healthy state (OHS) is determined based on the clustering center of the self-organizing map (SOM) neural network instead of the commonly used initial working state. Then, the distance metric deviating from the OHS is defined as a health index, where the perceptual vibration hashing is improved to make it more sensitive to degradation. Visualized fault diagnosis is carried out by the SOM when the health index exceeds the preset threshold. Two cases with experiments are conducted to demonstrate the accuracy and robustness of the proposed method.

Tracking the Connection Between Brazilian Agricultural Diversity and Native Vegetation Change by a Machine Learning Approach

In Brazil, agribusiness has a considerable role in the country's GDP. Because of this, the State needs territorial planning to minimize the impacts on natural resources, especially in the Pantanal and Amazon biomes, where agribusiness has expanded. The lower the agricultural diversification, the lower the pattern of land use homogeneity, generally associated with agribusiness, especially when it occupies large areas with more technological productive units. This paper investigates the relationship between spatial diversification patterns and the dynamics of native vegetation in Brazil. We propose a feature engineering and clustering approach for 5570 Brazilian municipalities between 1999 and 2018. It was based on the unsupervised artificial neural network Self-Organizing Map (SOM) to divide the municipalities into homogeneous groups of agricultural products diversity trends. The results were compared with the change in vegetation area using data from the national land use-mapping project called Mapbiomas. The analysis allowed the identification of three different regimes of modification in native vegetation, particularly related to municipalities in Brazil's Midwest and North regions, indicating substantial changes in the Cerrado and Amazon biomes.

Visualization Method of Key Knowledge Points of Nursing Teaching Management System Based on SOM Algorithm and Biomedical Diagnosis.

The traditional nursing teaching knowledge point recommendation algorithm based on collaborative filtering is difficult to deal with the problem of data sparsity, while the traditional recommendation algorithm based on matrix decomposition has poor scalability in dealing with high-dimensional data, and their recommendation results are only determined according to the prediction score, resulting in low recommendation accuracy. In view of this, a nursing teaching knowledge point recommendation method based on a SOM neural network and ranking factor decomposition machine is proposed. Firstly, the SOM neural network is used to cluster users based on users' academic background information, then the partial order relationship of nursing teaching knowledge points is constructed by using users' explicit and implicit web access behavior, and finally, the factor decomposition machine is used as the ranking function to classify users' academic background web access behavior, borrowing nursing teaching introduction text, and other characteristic information were modeled, and the peer-to-peer ranking learning algorithm was used to accurately recommend nursing teaching knowledge points. Experimental results show that the proposed method can effectively alleviate the problem of data sparsity and improve the accuracy and efficiency of recommendations.

Self-Organizing Maps to Multidimensionally Characterize Physical Profiles in Older Adults.

The aim of this study is to automatically analyze, characterize and classify physical performance and body composition data of a cohort of Mexican community-dwelling older adults. Self-organizing maps (SOM) were used to identify similar profiles in 562 older adults living in Mexico City that participated in this study. Data regarding demographics, geriatric syndromes, comorbidities, physical performance, and body composition were obtained. The sample was divided by sex, and the multidimensional analysis included age, gait speed over height, grip strength over body mass index, one-legged stance, lean appendicular mass percentage, and fat percentage. Using the SOM neural network, seven profile types for older men and women were identified. This analysis provided maps depicting a set of clusters qualitatively characterizing groups of older adults that share similar profiles of body composition and physical performance. The SOM neural network proved to be a useful tool for analyzing multidimensional health care data and facilitating its interpretability. It provided a visual representation of the non-linear relationship between physical performance and body composition variables, as well as the identification of seven characteristic profiles in this cohort.

Supervised and Unsupervised Machine Learning Algorithms for Forecasting the Fracture Location in Dissimilar Friction-Stir-Welded Joints

Artificial-intelligence-based algorithms are used in manufacturing to automate difficult activities and discover workflow or process patterns that had never been noticed before. Recent studies deal with the forecasting of the fracture location in dissimilar friction-stir-welded AA5754–C11000 alloys. Four types of supervised machine-learning-based classification algorithms i.e., decision tree, logistic classification, random forest, and AdaBoost were implemented. Additionally, in the present work, for the first time, a neurobiological-based unsupervised machine learning algorithm, i.e., self-organizing map (SOM) neural network, is implemented for determining the fracture location in dissimilar friction-stir-welded AA5754–C11000 alloys. Tool shoulder diameter (mm), tool rotational speed (RPM), and tool traverse speed (mm/min) are input parameters, while the fracture location, i.e., whether the specimen’s fracture is in the thermo-mechanically affected zone (TMAZ) of copper, or if it fractures in the TMAZ of aluminium. The results show that out of all implemented algorithms, the SOM algorithm is able to predict the fracture location with the highest accuracy of 96.92%.

Classification of Shrinking Cities in China Based on Self-Organizing Feature Map

Since the 1980s, China has been experiencing shrinking cities as part of a massive urbanization process. In recent years, the Matthew effect of factor accumulation has led to an increasingly substantial divergence in population concentration and sparseness in China. The pattern of shrinking Chinese cities has become increasingly severe. Accurate classification of shrinking cities is important for formulating policies and achieving the rational development of shrinking cities. In this study, the data of the 6th and 7th population censuses are used to investigate the shrinking Chinese cities, and prefecture-level cities are utilized as the scale of administrative units. The resident population in 130 cities decreased during the last decade. The population, economy, society, and space indicators are selected to cluster the shrinking cities through the self-organizing feature map neural network. Results show that China’s shrinking cities can be divided into four categories: (1) Sixty-two cities are characterized by a high degree of transfer dependence on the economy due to a chronic lack of population. (2) Twenty-eight cities are characterized by high urban expansion but with population loss. (3) Fourteen cities are characterized by obvious transportation and location advantages and with relatively slight population loss. (4) Twenty-six cities have good industrial development prospects but with serious urban pollution and “siphoning” effects from other cities. The shrinking cities are mainly concentrated in the western, central, and northeastern regions of China, which are represented by the old industrial and resource-depleted cities. The shrinking cities in the eastern region are fewer and less severe, which is mainly related to the high population concentration and developed economy in the region. This study provides solutions from different perspectives for four types of shrinking cities and serves as an empirical reference for policymakers and urban planners.

Research on diagnosis of pre-ignition of hydrogen engine based on SOM-MAS

Abnormal combustion is an important factor in the development process of hydrogen engine and it mainly includes pre-ignition, backfire and knocking, among which pre-ignition has the most serious impact on hydrogen engine. In this paper, it is divided into four types: normal combustion, slight pre-ignition, moderate pre-ignition and severe pre-ignition according to different crankshaft rotation angles. In order to identify different combustion types, this paper proposes a fault diagnosis model based on the fusion of SOM neural network and Multi-Agent System (SOM-MAS). Firstly, different combustion types are identified by SOM. Secondly, the abnormal combustion is tracked and located mainly through the Multi-Agent System, and the location of the abnormality is identified. Finally, based on 44 sets of pressure data samples collected from the in-cylinder combustion of a hydrogen engine on the experimental bench, different combustion types were diagnosed and identified, and the location of abnormal combustion faults was tracked, which verifies the effectiveness of the proposed method shows that the method has certain feasibility and superiority for the diagnosis of hydrogen engine pre-ignition.

The Relationship between Social Entrepreneurship Capability of SOM Neural Network Algorithm and New Enterprise Performance

As an important factor in the creation and growth of new enterprises, social entrepreneurship and new enterprise performance have attracted more and more attention from scholars in recent years. This research analyzes the network relationship of new companies on the basis of existing entrepreneurial network research. This paper proposes social entrepreneurial capabilities and new company performance based on the SOM neural network algorithm to solve these problems and then establishes entrepreneurial networks, organizational learning, and new business performance models. The method of this paper is to study the SOM neural network algorithm and then establish the entrepreneurial ability and enterprise performance evaluation system. The function of these methods is to put forward the meaning and research of venture capital. It also defines the meaning and research of innovation capabilities based on innovation theory, ensuring the scientific nature of the evaluation indicators, evaluation standards, and evaluation processes of innovative enterprises. In this survey, this paper conducted a field survey in Shanxi Province, China, and analyzed the internal impact of the network of social entrepreneurship and new companies on corporate performance. The survey results show that the value of the correlation β between entrepreneurial orientation and entrepreneurial environment dynamics is 0.167 ( P < 0.05 ). This shows that improving the entrepreneurial environment and enhancing social entrepreneurial capabilities have a positive impact on corporate performance.

Gear Fault Diagnosis and Life Prediction of Petroleum Drilling Equipment Based on SOM Neural Network.

In order to solve the problem that variable working conditions and fault types cannot be diagnosed in gear fault diagnosis of petroleum drilling equipment, four kinds of faults, namely, gear broken tooth, gear crack, gear pitting, and gear wear, are studied in this paper. Based on the SOM neural network algorithm, an intelligent diagnosis model of gear fault is proposed, and the PCA method is used to reduce data dimension and fuse features. The state index of life prediction is determined, and the remaining service life prediction of gear transmission system is predicted based on exponential degradation model. The results show that the accuracy of the SOM model for fault diagnosis is high, and the bearing in gearbox can be replaced or repaired in advance according to the residual life curve, so as to achieve the purpose of predictive maintenance.

Research on Clustering Algorithm Based on Improved SOM Neural Network

Clustering algorithm is a statistical method to study sample classification. With the rapid development of science and technology, people have higher and higher requirements for data classification, so there are more and more researches on clustering in modern society. Various mathematical algorithms are introduced to further improve the accuracy of clustering. Therefore, this paper proposes an improved SOM neural network algorithm to evaluate the comprehensive quality of students. SOM neural network can automatically find the internal laws and essential attributes in the samples, self-organize and adaptively change the network parameters and structure, and realize the classification of samples. Factor analysis is introduced to reduce the dimension of input layer in SOM neural network analysis, better process high-dimensional data, and improve the speed and accuracy of the algorithm. The improved SOM neural network algorithm can be used for the cluster analysis of the comprehensive quality of college students. The algorithm simulation results show that the improved neural network algorithm can intuitively evaluate the comprehensive quality of students and reflect the overall characteristics of each type of student.

Constructing a health indicator for bearing degradation assessment via an unsupervised and enhanced stacked autoencoder

To eliminate the noise from the extracted health indicator (HI) and reduce dependence on manual experience including knowledge for selecting the appropriate time–frequency domain indicators and conversions for data pre-processing, multiple-step processing, and multiple model combinations. An enhanced stacked autoencoder (ESAE) based on an exponent weight moving average (EWMA) in a deep learning model is proposed. This ESAE uses the vibration amplitude of an unlabeled original time-domain signal to construct the HI directly. To demonstrate our proposed method is better than other models, including the stacked autoencoder (SAE), stacked denoising autoencoder (SDAE), root mean square (RMS), kurtosis, K-medoids clustering, and self-organizing map (SOM) neural network models. The proposed model is simulated for multiple bearings in two case studies. The experiment result shows that the extracted HI curve is smoother than mentioned-above other models reduce the wrong judgment of bearing health caused by noise effectively. Moreover, high monotonicity is lay a good foundation for following reaming useful life prediction. An index, named Mon, is used to assess the monotonicity performance of all models, the experiment result also shows that the extracted HI by our proposed is superior to other models.

Using real-time manufacturing data to schedule a smart factory via reinforcement learning

Under the background of intelligent manufacturing, internet of things and other information technologies have accumulated a large amount of data for manufacturing system. However, the traditional scheduling methods often ignore the production law and knowledge hidden in the manufacturing data. Therefore, this paper proposes a cyber-physical architecture and a communication protocol for smart factory, and a multiagent-system-based dynamic scheduling mechanism is given using contract net protocol. In the dynamic scheduling mechanism, the problem formulation module and scheduling point module are designed first. Then, a genetic programming (GP) method is proposed to form sixteen high-quality rules, which constitute the scheduling rule library. Meanwhile, combining with autoencoder, self-organizing mapping neural network and k-means clustering algorithm, the state clustering module is designed to realize the efficient clustering of production attribute vector. Moreover, an improved Q-learning algorithm is used to train the GP rule selector, so that the decision-making agent can choose the appropriate GP rule according to the production state at each scheduling point. Finally, the experimental results show that the proposed method has feasibility and superiority compared with other methods in real-time scheduling, and can effectively deal with disturbance events in the manufacturing process.

Deep-learning-based short-term photovoltaic power generation forecasting using improved self-organization map neural network

As a vital function of an energy management system for distributed energy resources, optimal operation in distribution systems, and mitigating potentially adverse effects of photovoltaic (PV) systems, accurate forecasting of PV power generation is required. This article presents an alternative technique to improve the accuracy of deep-learning-based short-term PV power-generation forecasting models by clustering the input data using a self-organization map (SOM). To validate the proposed model, long short-term memory (LSTM), feedforward neural network (FNN), FNN with the proposed SOM clustering method (FNN-SOM), and LSTM with the proposed SOM clustering method (LSTM-SOM) were tested and compared with one-year hourly datasets (8760 samples). Root mean square error, mean absolute error, and mean absolute percentage error were used as validation factors in this work. The results show that the proposed method provides a more accurate solar power generation forecast than other methods. Moreover, the proposed method can work effectively even with a few inputs system.

Measurement of health evolution tendency for aircraft engine using a data-driven method based on multi-scale series reconstruction and adaptive hybrid model

With the improvement of structure complexity and the strict requirement for stable operation, maintenance pattern of aircraft engine has experienced the transformation from passive response to active prevention. Accurate result of health evolution trend measuring is the core part of conducting the prevention maintenance. In this paper, a data-driven method based on multi-scale series reconstruction and adaptive hybrid model is proposed to measure the health development tendency of aircraft engine. Firstly, to quantitatively characterize the health levels of engine, a comprehensive health state index (CHSI) is innovatively constructed by an improved ensemble auto-encoder (EnAE) and self-organizing map (SeOM) neural network, which realizes the feature-level fusion of multi-source sensory data. By designing novel network structure and training pattern in EnAE, original auto-encoder model is optimized and the more robust state features can be captured from raw signals. Secondly, considering the influence of series random fluctuations on forecasting results, a multi-scale intrinsic mode functions (IMFs) reconstruction strategy using the fast ensemble empirical mode decomposition based dispersion entropy (FEEMD-DE) theory is provided to efficiently extract the regular and irregular components from original CHSI series. Finally, an adaptive hybrid model, combining a recurrent reconstructed Grey Markov (RRGM) model and long short-term memory (LSTM) network, is developed to capture the complex characteristics of reconstruction components and then complete the measurement of health evolution trend. The feasibility and superiority of the proposed method is validated by using a multi-source sensory dataset collected from aircraft engines, and the experimental results indicate that the measuring accuracy of the proposed method is significantly higher than that of other existing methods.