Self-organizing Feature Map Algorithm Research Articles

Quantitative characterization of fatigue damage in plate structures based on FSOM

For the problem of fatigue damage detection and damage degree assessment of plate structures, a quantitative damage assessment method based on the fast self-organizing feature mapping (FSOM) algorithm is proposed in this paper. The damage detection problem is transformed into a binary classification problem by extracting multidimensional damage features of the Lamb wave signal in plate to be detected and selecting damage sensitive features. Then, the FSOM network is used to identify the health state of the plate to be inspected, and the damage index is obtained by fusing the damage sensitive features using FSOM to quantitatively evaluate the damage level of the plate to be inspected. Simulation and experimental results show this method has a good dynamic tracking capability for the fatigue damage evolution of aluminum and composite plates, and can achieve quantitative assessment of fatigue damage of plate structures.

NeuroSOFM: A Neuromorphic Self-Organizing Feature Map Heterogeneously Integrating RRAM and FeFET

Many currently available hardware implementations of the unsupervised self-organizing feature map (SOFM) algorithm utilize complementary metal–oxide–semiconductor (CMOS)-only circuits that often compromise key behaviors of the SOFM algorithm due to complexity. We propose a neuromorphic architecture harnessing the unique properties of ferroelectric field-effect transistors (FeFETs) and gated-resistive random access memory (RRAM) for in-memory computing to implement the SOFM algorithm. The FeFET-based synapse, organized in a novel circuit, is able to compute the input-weight Euclidean error in memory via the saturation drain current. The self-decaying states of the gated-RRAM allow for a self-decaying neighborhood and learning rate implementation to allow for convergence and lifelong learning. This novel architecture is able to successfully cluster benchmarks (RGB colors and MNIST handwritten digits) and real-life datasets, such as COVID-19 patient chest X-rays completely unsupervised. The architecture also demonstrates a significant amount of robustness to device variability and damaged neurons. In addition, the proposed architecture is completely parallelized and provides a power-efficient platform for implementing the SOFM algorithm.

Feasibility study on identifying seed viability of Sophora japonica with optimized deep neural network and hyperspectral imaging

Aiming at the rapid identification of seed viability of Sophora japonica, different aging grades and imbibition states were proposed as the research focus. The hyperspectral data of the four viability grade seeds in the state of swelling at 0 h and 10 h were collected. The effects of swelling and aging on the content of water, protein, starch, fat and total sugar were compared, and then correlation analysis was established. Among them, fat was the most sensitive to changes in spectrum and viability. In the machine learning scale, naive bayes (NB), self-organizing feature mapping algorithm (SOFM), and support vector machine (SVM) were used. On the scale of deep learning, convolutional neural networks (CNN) and long short-term memory (LSTM) were applied to model on the one-dimensional spectral and two-dimensional image. The image-based deep learning model performed best among the three models, and the recognition accuracy was above 90%. A particle swarm optimization algorithm (PSO) was proposed to optimize the hyperparameters. It can increase the recognition rate, up to 99.73%, and increase the convergence speed. This study proved that deep learning combined with spectral or image has great potential in identifying the seed viability.

A Multi-Swarm ABC Algorithm for Parameters Optimization of SOFM Neural Network in Dynamic Environment

Self-organizing feature map (SOFM) neural network is a kind of competitive unsupervised learning neural network, which has strong self-organizing and self-learning capabilities. It has been widely used in the fields of data classification and data clustering. A crucial step for SOFM neural network is to set its weight parameters correctly because the output accuracy and efficiency of the network depend much on these parameters. Most of current methods for parameter setting are based on static data. However, in a dynamic environment, the statistical characteristics of the generated data will change unpredictably over time. If the SOFM network cannot react to the changes of the environment, its performance will degrade. To deal with this problem, a more powerful multi-swarm artificial bee colony algorithm (MABC) is proposed. In the algorithm, the classic ABC algorithm is improved with multi-swarm and exclusive operation strategies to make it suitable for tracking optimal parameter settings of the SOFM network, so that the SOFM network can be applied to a dynamic environment. Two real data streams, which are regarded as coming from dynamic environments, are used to evaluate the effectiveness of the algorithm. Results show that the proposed algorithm is superior to the classic SOFM algorithm in terms of clustering purity and effectiveness. It is a promising method for the classification of data streams from dynamic environments.

Compression of Monochromatic and Multicolored Image with Neural Network

Nowadays we have so much images provided by different types of machines, while we need to store them or transfer to other devices or via internet, we need to compress them because the images usually have large amount of size. Compressing them reduces time for transferring files. The compression can be done with different methods and software in order to reduce their capacity expressed in megabytes as much as tens of hundreds of gigabytes for more files. It is well known that the speed of information transmission depends mainly on its quantity or the capacity of the information package. Image compression is a very important task for data transfer and data storage, especially nowadays because of the development of many image acquisition devices. If there is no compression technique used on these data, they may occupy immense space of memory, or render difficult data transmission. Artificial Neural Networks (ANN) have demonstrated good capacities for lossy image compression. The ANN algorithm we investigate is BEP-SOFM, which uses a Backward Error Propagation algorithm to quickly obtain the initial weights, and then these weights are used to speed up the training time required by the Self-Organizing Feature Map algorithm. In order to obtain these initial weights with the BEP algorithm, we analyze the hierarchical approach, which consists in preparing the image to compress using the quadtree data structure by segmenting the image into blocks of different sizes. Small blocks are used to represent image areas with large-scale details, while the larger ones represent the areas that have a small number of observed details. Tests demonstrate that the approach of quadtree segmentation quickly leads to the initial weights using the BEP algorithm.

The Analysis of Plants Image Recognition Based on Deep Learning and Artificial Neural Network

Classification and identification of plants are helpful for people to effectively understand and protect plants. The leaves of plants are the most important recognition organs. With the development of artificial intelligence and machine vision technology, plant leaf recognition technology based on image analysis is used to improve the knowledge of plant classification and protection. Deep learning is the abbreviation of deep neural network learning method and belongs to neural network structure. It can automatically learn features from big data and use artificial neural network based on back propagation algorithm to train and classify plant leaf samples. The main content of this paper is to extract plant leaf features and identify plant species based on image analysis. Firstly, plant leaf images are segmented by various methods, and then feature extraction algorithm is used to extract leaf shape and texture features from leaf sample images. Then the comprehensive characteristic information of plant leaves is formed according to the comprehensive characteristic information. In this paper, 50 plant leaf databases are tested and compared with KNN-based neighborhood classification, Kohonen network based on self-organizing feature mapping algorithm and SVM-based support vector machine. At the same time, the leaves of 7 different plants were compared and it was found that ginkgo leaves were easier to identify. For leaf images under complex background, good recognition effect has been achieved. Image samples of the test set are input into the learning model to obtain reconstruction errors. The class label of the test set can be obtained by reconstructing the deep learning model with the smallest error set. The results show that this method has the shortest recognition time and the highest correct recognition rate.

Heuristic Search Based Feature Selection and Discretive Self-Organized Map Clustering for Spatio-Temporal Pattern Discovery

Spatio-temporal pattern discovery is an essential one in data mining for predictive analytics. Since it manages both space and time information depending on their characteristics and the preferred applications performances. The predictive analytics uses the Spatio-temporal features to discover future outcomes. The several works have been done in the Spatio-temporal pattern discovery. But the accurate pattern discovery is the major challenges. In order to improve the accurate pattern discovery, Heuristic Best-First Search based Discretized Self-Organizing Feature Map (HBFS-DSOFM) Model is introduced. The HBFS-DSOFM model comprises two processes namely, Spatio-temporal feature selection and clustering. Initially, the Heuristic Best-First Search Algorithm is used for selecting the relevant Spatio-temporal features from the large dataset for pattern discovery. Best-first search explores a decision tree for selecting the relevant Spatio-temporal features through the maximum information gain value. After that, the Spatio-temporal data are clustered with the selected features by using Discretized Self-Organizing Feature Mapping Algorithm for Spatio-temporal pattern discovery. In Discretized Self-Organizing Feature Mapping, input spatio-temporal data is connected to the prototype neurons through the synaptic weight. For the clustering process, weights of the neurons (i.e. cluster) are initialized with random values. After that, the Manhattan distance is used to compute the distance between the input vector and cluster weight value. The gradient descent is applied to discover closest distance. The cluster whose weight is closest to the input data is grouped into the particular cluster. Then the weight of the cluster is updated with the previous weight value for grouping the entire data. This clustering process gets iterated until it satisfies termination condition. Finally, the outputs of Spatio-temporal data are combined to form a spatio-temporal pattern for efficient predictive analytics. Experimental evaluation is carried out for El Nino Dataset and taxi trajectory dataset using the factors such as time complexity, clustering accuracy, and false positive rate. The results confirm that the proposed HBFS-DSOFM model increases the Spatio-temporal pattern discovery in terms of high clustering accuracy with a less false positive rate as well as minimum time complexity. Based on the clarification, HBFS-DSOFM model is more efficient than the state-of-the-art methods.

An Outlier Detection Approach Based on Improved Self-Organizing Feature Map Clustering Algorithm

Local Outlier Factor (LOF) outlier detecting algorithm has good accuracy in detecting global and local outliers. However, the algorithm needs to traverse the entire dataset when calculating the local outlier factor of each data point, which adds extra time overhead and makes the algorithm execution inefficient. In addition, if the K-distance neighborhood of an outlier point P contains some outliers that are incorrectly judged by the algorithm as normal points, then P may be misidentified as normal point. To solve the above problems, this paper proposes a Neighbor Entropy Local Outlier Factor (NELOF) outlier detecting algorithm. Firstly, we improve the Self-Organizing Feature Map (SOFM) algorithm and use the optimized SOFM clustering algorithm to cluster the dataset. Therefore, the calculation of each data point's local outlier factor only needs to be performed inside the small cluster. Secondly, this paper replaces the K-distance neighborhood with relative K-distance neighborhood and utilizes the entropy of relative K neighborhood to redefine the local outlier factor, which improves the accuracy of outlier detection. Experiments results confirm that our optimized SOFM algorithm can avoid the random selection of neurons, and improve clustering effect of traditional SOFM algorithm. In addition, the proposed NELOF algorithm outperforms LOF algorithm in both accuracy and execution time of outlier detection.

Self-Organizing Feature Map and K-Means Algorithm with Automatically Splitting and Merging Clusters based Image Segmentation

Self-Organizing Feature Map and K-Means Algorithm with Automatically Splitting and Merging Clusters based Image Segmentation

Absorption Spectra Analysis using Modified Self-Organizing Feature Maps

This research demonstrates an application of a modified self-organizing feature map (SOFM) algorithm to analyze and discover the quality of chemical absorption spectrum data. By forming an NxN neural array from input features and varying the essential parameters of the algorithm, map recognition quality is increased at the expense of more computation. The features of this SOFM are based on absorption intensity variations with excitation wavelength. SOFMs are used to discern pattern similarities and differences between spectral data. A context tree allows individual features, or key numbers in the data, to be input and classifies the vector to the type of data that is most similar. This research also use the self-organizing map to enhance as well as visualize resultant classification efficiency through the use of watershed transformation.

An Improved Self-Organizing Feature Maps Algorithm and its Application in Arts Course Teaching Evaluation

An Improved Self-Organizing Feature Maps Algorithm and its Application in Arts Course Teaching Evaluation

Selection of Suitable Window Size for Speckle Reduction and Deblurring using SOFM in Polarimetric SAR Images

Classification performance of PolSAR data, when used without speckle reduction is insufficient for most applications. Thus, speckle filtering becomes an essential preprocessing step. In this study we evaluate the effectiveness of different popular speckle filters and analyse their effects on the classification accuracy. We have used L-band and C-band fully polarimetric dataset acquired over Mumbai, India. The Wishart supervised classifier algorithm is used for classification of the filtered and unfiltered data. Boxcar, Refined Lee, Lopez, IDAN, Improved Sigma and sequential filters are analysed for the improvement in classification accuracy. Further we also evaluate the effect of window size on classification accuracy in order to be able to select appropriate window for speckle suppression. Boxcar and Refined Lee filters are used to test the effect of speckle filtering on classification with varying moving window size. Boxcar filter is widely used in the SAR application domain owing to it’s simplicity. However, the indiscriminate averaging of the Boxcar filter causes a resolution loss in the vicinity of sharp edges and point targets in the image. To overcome this, we have applied Kohonens Self-Organizing Feature Map (SOFM) algorithm to deblurr the image and improve edge and target preservation performance.

The combination of self-organizing feature maps and support vector regression for solving the inverse ECG problem

Noninvasive electrical imaging of the heart aims to quantitatively reconstruct transmembrane potentials (TMPs) from body surface potentials (BSPs), which is a typical inverse problem. Classically, electrocardiography (ECG) inverse problem is solved by regularization techniques. In this study, it is treated as a regression problem with multi-inputs (BSPs) and multi-outputs (TMPs). Then the resultant regression problem is solved by a hybrid method, which combines the support vector regression (SVR) method with self-organizing feature map (SOFM) techniques. The hybrid SOFM–SVR method conducts a two-step process: SOFM algorithm is used to cluster the training samples and the individual SVR method is employed to construct the regression model. For each testing sample, the cluster operation can effectively improve the efficiency of the regression algorithm, and also helps the setup of the corresponding SVR model for the TMPs reconstruction. The performance of the developed SOFM–SVR model is tested using our previously developed realistic heart-torso model. The experiment results show that, compared with traditional single SVR method in solving the inverse ECG problem, the proposed method can reduce the cost of training time and improve the reconstruction accuracy in solving the inverse ECG problem.

An edge preserving requantization model for color image coding with orthogonal polynomials

In this paper, an edge preserving fast requantization algorithm is proposed for color image coding. In this work, a block classifier in the orthogonal polynomials based transform domain is proposed to classify the color image region as containing either smooth or edge. The smooth regions are clustered by finding the central tendency adjacent smooth regions separated by edge block. The reduced training vectors are obtained from both edge blocks and clustered smooth blocks for quantization process. The quantization codebook Q 1 is then constructed from the reduced training vectors and so reduces the codebook training process. In this proposed work, the edge block training vectors and the quantization codebook Q 1 are utilized to construct the requantization codebook Q 2 so as to eliminate the edge degradation problem present in existing requantization techniques. The self-organizing feature map algorithm is employed in both quantization and requantization stage for codebook generation process. The computation time of color image encoding is further reduced in this proposed work by constructing a single codebook for all the R, G and B color components utilizing the inter-correlation property of the proposed transform. The experimental results demonstrate that the proposed work gives superior results compared with existing techniques.

Fractal Mechanism Analysis and Simulation of Information System

To find the best design and development model for the information system, this paper discusses the structural formation of the information system and the kinetics of the evolution of information system from the perspective of non-equilibrium statistical mechanics and generalized entropy in the system. Based on this view, physical laws for the evolution dynamics of information system are expressed as the maximum generalized entropy principle (MGEP). Combining with self-organizing feature map algorithm, we have analyzed the effect on the system structure from the exchange between information flows. That is to say, an information system has fractal characteristics. Except for these theories, we have done some numerous simulation on information systems of 10 major cities in China's to verify the fractal characteristics, which has great significant to the guidance of achieving full use of resources, accelerating the process of information society and constructing information systems.

A variant of the SOM algorithm and its interpretation in the viewpoint of social influence and learning

The conventional self-organizing feature map (SOM) algorithm is usually interpreted as a computational model, which can capture main features of computational maps in the brain. In this paper, we present a variant of the SOM algorithm called the SOM-based optimization (SOMO) algorithm. The development of the SOMO algorithm was motivated by exploring the possibility of applying the SOM algorithm in continuous optimization problems. Through the self-organizing process, good solutions to an optimization problem can be simultaneously explored and exploited by the SOMO algorithm. In our opinion, the SOMO algorithm not only can be regarded as a biologically inspired computational model but also may be regarded as a new approach to a model of social influence and social learning. Several simulations are used to illustrate the effectiveness of the proposed optimization algorithm.

A computational framework for topographies of cortical areas.

Self-organizing feature maps (SOFMs) represent a dimensionality-reduction algorithm that has been used to replicate feature topographies observed experimentally in primary visual cortex (V1). We used the SOFM algorithm to model possible topographies of generic sensory cortical areas containing up to five arbitrary physiological features. This study explored the conditions under which these multi-feature SOFMs contained two features that were mapped monotonically and aligned orthogonally with one another (i.e., "globally orthogonal"), as well as the conditions under which the map of one feature aligned with the longest anatomical dimension of the modeled cortical area (i.e., "dominant"). In a single SOFM with more than two features, we never observed more than one dominant feature, nor did we observe two globally orthogonal features in the same map in which a dominant feature occurred. Whether dominance or global orthogonality occurred depended upon how heavily weighted the features were relative to one another. The most heavily weighted features are likely to correspond to those physical stimulus properties transduced directly by the sensory epithelium of a particular sensory modality. Our results imply, therefore, that in the primary cortical area of sensory modalities with a two-dimensional sensory epithelium, these two features are likely to be organized globally orthogonally to one another, and neither feature is likely to be dominant. In the primary cortical area of sensory modalities with a one-dimensional sensory epithelium, however, this feature is likely to be dominant, and no two features are likely to be organized globally orthogonally to one another. Because the auditory system transduces a single stimulus feature (i.e., frequency) along the entire length of the cochlea, these findings may have particular relevance for topographic maps of primary auditory cortex.

Image Denoising through Self-Organizing Feature Map Based on Wavelet-Domain HMMs

Although the Wavelet-domain hidden Markov Models (HMMs) can powerfully preserve the image edge information, it lacks local dependency information. According to the deficiency, a novel image denoising method based HMMs through the self-organizing feature map(SOFM) which exploits spatial local correlation among image neighbouring wavelet coefficients is proposed in this paper. SOFM algorithms is popular for unsupervised learning and data clustering and can capture persistence properties of wavelet coefficients. Experimental results show that the performance of the proposed method is more practicable and more effective to suppress additive white Gaussian noise and preserve the details of the image.

Automatic Inspection of Transmission Devices Using Acoustic Data

Most factories depend on skilled workers to test the quality of transmission devices by listening to the sound. In this paper, an intelligent inspection system is proposed to evaluate the quality of transmission devices in place of experts. Since the causes of faults of transmission devices are complex and a defective product might simultaneously have many types of faults, the discrimination process between defective and nondefective products and the classification process of defective products are treated separately in the proposed system. From the acoustic data of operating transmission devices, we extract the feature vectors based on time-frequency analysis and train a neuroclassifier by using the learning vector quantization (LVQ). Furthermore, the genetic algorithm (GA) with floating point (FP) is utilized to select some significant frequencies from the spectra of acoustic data of defective and nondefective products and to make a quality evaluation rule automatically. The defective products are picked up from the automatic production line according to the evaluation rule and the trained neuroclassifier. At last, the self-organizing feature map (SOM) algorithm is used to identify the kinds of defective products. The experimental results show that the proposed intelligent system is able to perform the quality evaluation of transmission devices successfully. This paper was motivated by the problem of developing an intelligent evaluation system in place of skilled workers to evaluate the quality of transmission devices automatically based on acoustic data. Most of the prior works in quality evaluation of transmission devices are based on processing vibrometer signals for system vibrations. Such vibrometers must be installed on the surface of vibrating part of transmission devices, which alter the physical integrity. In this paper, the acoustic data of operating transmission devices are recorded. We first compute the ASFTS and FVAVT, where ASFTS denotes the average of a serial of spectra calculated from time segments of an acoustic data and FVAVT denotes the feature vector of amplitude variation with time in a certain band. By using the different characteristics of the ASFTS and the FVAVT, we apply the LVQ and the FGA to the quality evaluation of transmission devices, respectively. Utilizing the advantages of the SOM, we classify the defective products successfully. In the industry production, the quality of each batch of products will change according to the situation of equipments. Similarly, the quality evaluation rule will be adjusted according to the yield and the request of customers. The proposed system can evaluate the quality of transmission devices correctly as demanded so long as we change the nondefective and defective samples.

A hybrid SOFM-SVR with a filter-based feature selection for stock market forecasting

Stock market price index prediction is regarded as a challenging task of the financial time series prediction process. Support vector regression (SVR) has successfully solved prediction problems in many domains, including the stock market. This paper hybridizes SVR with the self-organizing feature map (SOFM) technique and a filter-based feature selection to reduce the cost of training time and to improve prediction accuracies. The hybrid system conducts the following processes: filter-based feature selection to choose important input attributes; SOFM algorithm to cluster the training samples; and SVR to predict the stock market price index. The proposed model was demonstrated using a real future dataset – Taiwan index futures (FITX) to predict the next day’s price index. The experiment results show that the proposed SOFM-SVR is an improvement over the traditional single SVR in average prediction accuracy and training time.