Kohonen's Self-organizing Feature Research Articles

Socio-geographical aspects of formation of the general educational complex of regions of Ukraine

The article considers spatial differences in the development of the general educational complex. The main indicators that characterize the level of development of the general educational complex are the coefficient of concentration, the coefficient of localization, social density, the quality of students' knowledge, the number of teachers, and others. Based on these indicators, 5 groups of regions were identified according to the level of development of the general educational complex using Kohonen's self-organizing feature map. As of January 1, 2020, there were 14,815 general secondary education institutions inUkraine, with 437,981 teachers and more than 4 million students. In general, inUkraine, there is significant spatial differentiation in the level of development of general secondary education, which contradicts the principles of equality and access to quality educational services.

Classification of power system voltage stability conditions using Kohonen's self-organising feature map and learning vector quantisation

SUMMARY This paper presents an artificial neural network–based approach, in which Kohonen's self-organising feature map technique in association with learning vector quantisation has been applied to classify the power system operating states on the basis of their degree of static voltage stability. The proposed scheme can seamlessly integrate itself within the energy management systems in the smart grid scenario. A self-organising feature map has been considered to be an ideal choice because the state classification problem is a typical multiclass pattern classification problem, which can be efficiently handled by a self-organising feature map with much shorter training time compared with other neural networks. The self-organising feature map provided information about the operating states of the power system and classified them into three categories, namely, normal state, intermediate state and emergency (or alert) state. To augment the classification accuracy of self-organising feature map, a learning vector quantisation–based supervised classification was also adopted. The proposed method was tested on a real 203-bus system of an Indian power utility, and the results obtained has been compared with standard voltage stability indicator–based classical voltage stability assessment results. Copyright © 2011 John Wiley & Sons, Ltd.

Cascading SOFM and RBF Networks for Categorization and Indexing of Fly Ashes

The objective of this work is to categorize the available fly ashes in different parts of the world into distinct groups based on its compositional attributes. Kohonen's self-organizing feature map and radial basis function networks are applied in a cascading fashion for the classification of fly ashes in terms of its chemical parameters. The basic procedure of the methodology consists of three stages: (1) apply self-organizing neural net to ascertain possible number of groups, delineate them and identify the group sensitive attributes; (2) find mean values of sensitive attributes of the elicited groups and augment them as start-up prototypes in k -means algorithm and find the refined centroids of these groups; (3) incorporate the centroids in a two layer radial basis function network and fine-tune the delineated groups and develop an indexing equation using the weights of the stabilized network. Further, to demonstrate the utility of this classification scheme, the so formed groups were correlated with their performance in High Volume Fly Ash Concrete System [HVFAC]. The categorization was found to be excellent and compares well with Canadian Standard Association's [CSA A 3000] classification scheme.

Representing and evaluating ultrasonic maps using active snake contours and Kohonen’s self-organizing feature maps

Active snake contours and Kohonen's self-organizing feature maps (SOMs) are employed for representing and evaluating discrete point maps of indoor environments efficiently and compactly. A generic error criterion is developed for comparing two different sets of points based on the Euclidean distance measure. The point sets can be chosen as (i) two different sets of map points acquired with different mapping techniques or different sensing modalities, (ii) two sets of fitted curve points to maps extracted by different mapping techniques or sensing modalities, or (iii) a set of extracted map points and a set of fitted curve points. The error criterion makes it possible to compare the accuracy of maps obtained with different techniques among themselves, as well as with an absolute reference. Guidelines for selecting and optimizing the parameters of active snake contours and SOMs are provided using uniform sampling of the parameter space and particle swarm optimization (PSO). A demonstrative example from ultrasonic mapping is given based on experimental data and compared with a very accurate laser map, considered an absolute reference. Both techniques can fill the erroneous gaps in discrete point maps. Snake curve fitting results in more accurate maps than SOMs because it is more robust to outliers. The two methods and the error criterion are sufficiently general that they can also be applied to discrete point maps acquired with other mapping techniques and other sensing modalities.

Structure of GroEL in Complex with an Early Folding Intermediate of Alanine Glyoxylate Aminotransferase

Primary hyperoxaluria type 1 is a rare autosomal recessive disease caused by mutations in the alanine glyoxylate aminotransferase gene (AGXT). We have previously shown that P11L and I340M polymorphisms together with I244T mutation (AGXT-LTM) represent a conformational disease that could be amenable to pharmacological intervention. Thus, the study of the folding mechanism of AGXT is crucial to understand the molecular basis of the disease. Here, we provide biochemical and structural data showing that AGXT-LTM is able to form non-native folding intermediates. The three-dimensional structure of a complex between the bacterial chaperonin GroEL and a folding intermediate of AGXT-LTM mutant has been solved by cryoelectron microscopy. The electron density map shows the protein substrate in a non-native extended conformation that crosses the GroEL central cavity. Addition of ATP to the complex induces conformational changes on the chaperonin and the internalization of the protein substrate into the folding cavity. The structure provides a three-dimensional picture of an in vivo early ATP-dependent step of the folding reaction cycle of the chaperonin and supports a GroEL functional model in which the chaperonin promotes folding of the AGXT-LTM mutant protein through forced unfolding mechanism.

A modified training scheme for SOFM to cluster multispectral images

In this paper, we propose modifications to Kohonen's Self-Organising Feature Map (SOFM) to achieve faster convergence specifically with respect to multispectral images. First, the raw image is pre-processed using data reduction technique to obtain reduced data set and then Condensed Nearest Neighbour (CNN) rule is applied to yield standard subset of samples. The samples in the standard subset are used to find the Best Matching Unit (BMU) and the samples in the reduced data set are used to update BMU and its neighbouring neurons. The SOFM is tested on: synthetic image data set and Harangi 1991, 1992 image data sets. Results are compared with conventional SOFM.

Extracting knowledge on the links between the water body stressors and biotic integrity

Multi-metric indices of biological integrity (IBIs) are most frequently created by examining single biological metrics along gradients of environmental degradation, and then combining multiple metrics using “best professional judgment” to characterize and calibrate stressor–response relationships. We aim to provide an efficient data analysis and visualization tool to assess the simultaneous effects of anthropogenic stressors on the fish population through the fish metrics and the associated Index of Biotic Integrity (IBI). Kohonen's self-organizing feature maps (SOM), unsupervised neural networks, are employed to pattern the sampling sites in the state of Ohio based on similar metrics characteristics. Canonical correspondence analysis (CCA) allows us then to draw conclusions about the role of the environmental variables in maintaining the perfect abode for fishes. Different visualizations superimposed with SOM clustering are realized to explore the complex interrelationships in the aquatic system and aid watershed managers to comprehend the effects of the environment on the fish.

Visual–Motor Coordination Using a Quantum Clustering Based Neural Control Scheme

Visual–Motor Coordination is a problem considered analogous to the hand-eye coordination in biological systems. In this work we propose a novel approach to this problem using Quantum Clustering and an extended Kohonen's Self-Organizing Feature Map (K-SOFM). This facilities the use of the method in varying workspaces by considering the joint angles of the robot arm. Unlike previous work, where a fixed topology for the input space is considered, the proposed approach determines a topology as the workspace varies. Quantum Clustering is a method which constructs a scale-space probability function and uses the Schroedinger equation and its lowest eigenstate to obtain a potential whose minimum gives the cluster centers. It transforms the input space into a Hilbert space, where it searches for its minimum. The motivation of this work is to identify the implicit relationship existing between the end-effector positions and the joint angles through Quantum Clustering and Neural Network methods to fine-tune the system to correctly identify the mapping.

Blood Vessel Segmentation via Neural Network in Histological Images

In this paper we utilize the Kohonen's self-organizing feature map to segment blood vessels from biopsies in tumor tissue. The ability of this kind of neural network to recognize very complex patterns makes it an effective computational tool for the segmentation. We propose a strategy of blood vessels segmentation using a neural network, taking into account the quality of our images and its features: complexity in shape and variability in size. Segmentation results are contingently manually corrected. The proposed segmentation strategy is tested on manual segmentation, where segmentation errors of less than 3.5% are observed. This work is a part of a global image analysis process and these images will be subject to a further morphometrical analysis in order to diagnose and prognosticate automatically malignant tumours.

Comparative analysis of different approaches to target differentiation and localization with sonar

This study compares the performances of different methods for the differentiation and localization of commonly encountered features in indoor environments. Differentiation of such features is of interest for intelligent systems in a variety of applications such as system control based on acoustic signal detection and identification, map building, navigation, obstacle avoidance, and target tracking. Different representations of amplitude and time-of-flight measurement patterns experimentally acquired from a real sonar system are processed. The approaches compared in this study include the target differentiation algorithm, Dempster–Shafer evidential reasoning, different kinds of voting schemes, statistical pattern recognition techniques ( k-nearest neighbor classifier, kernel estimator, parameterized density estimator, linear discriminant analysis, and fuzzy c-means clustering algorithm), and artificial neural networks. The neural networks are trained with different input signal representations obtained using pre-processing techniques such as discrete ordinary and fractional Fourier, Hartley and wavelet transforms, and Kohonen's self-organizing feature map. The use of neural networks trained with the back-propagation algorithm, usually with fractional Fourier transform or wavelet pre-processing results in near perfect differentiation, around 85% correct range estimation and around 95% correct azimuth estimation, which would be satisfactory in a wide range of applications.

An intelligent system for monitoring the microgravity environment quality on-board the international space station

An intelligent system for monitoring the microgravity environment quality on-board the International Space Station is presented. The monitoring system uses a new approach combining Kohonen's self-organizing feature map, learning vector quantization, and a back propagation neural network to recognize and classify the known and unknown patterns. Finally, fuzzy logic is used to assess the level of confidence associated with each vibrating source activation detected by the system.

A neural network algorithm for the traveling salesman problem with backhauls

This paper introduces a new heuristic based on Kohonen's self-organizing feature map for the traveling salesman problem with backhauls (TSPB). The TSPB is an extension of the traveling salesman problem in which a set of customers is partitioned into a set of linehaul customers to be visited contiguously at the beginning of the route and a set of backhaul customers to be visited once all linehaul customers have been visited. The major innovation of the proposed heuristic is based on the design of a new network architecture, which consists of two separate chains of neurons. The network evolves into a feasible TSPB tour using four types of interactions: (1) the first chain interacts with the linehaul customers, (2) the second chain interacts with the backhaul customers, (3) the tails of the chains interacts together, and (4) the heads of the two chains interact with the depot. The generated tour is then improved using the 2-opt procedure. The new heuristic is compared to the best available TSPB heuristics in the literature on medium to large-sized instances up to 1000 customers. The computational results demonstrate that the proposed approach is comparable in terms of solution quality and computational requirements.

Recognition of impulse fault patterns in transformers using Kohonen's self-organizing feature map

Determination of exact nature and location of faults during impulse testing of transformers is of practical importance to the manufacturer as well as designers. The presently available diagnostic techniques more or less depend on expertized knowledge of the test personnel, and in many cases are not beyond ambiguity and controversy. This paper presents an artificial neural network (ANN) approach for detection and diagnosis of fault nature and fault location in oil-filled power transformers during impulse testing. This new approach relies on high discrimination power and excellent generalization ability of ANNs in a complex pattern classification problem, and overcomes the limitations of conventional expert or knowledge-based systems in this field. In the present work the "self-organizing feature map" (SOFM) algorithm with Kohonen's learning has been successfully applied to the problem with good diagnostic accuracy.

Recognition of Impulse Fault Patterns in Transformers Using Kohonen's Self-Organizing Feature Map

Determination of the exact nature and location of faults during impulse testing of transformers is of practical importance to the manufacturer as well as designers. The presently available diagnostic techniques more or less depend on expert knowledge of the test personnel, and in many cases are not beyond ambiguity and controversy. This paper presents an artificial neural network (ANN) approach for detection and diagnosis of fault nature and fault location in oil-filled power transformers during impulse testing. This new approach relies on high discrimination power and excellent generalization ability of ANNs in the complex pattern classification problem, and overcomes the limitations of conventional expert or knowledge-based systems in this field. In the present work, the self-organizing feature map (SOFM) algorithm with Kohonen's learning has been successfully applied to the problem with good diagnostic accuracy.

Novelty-dependent learning and topological mapping

Unsupervised topological ordering, similar to Kohonen's (1982, Biological Cybernetics, 43: 59-69) self-organizing feature map, was achieved in a connectionist module for competitive learning (a CALM Map) by internally regulating the learning rate and the size of the active neighbourhood on the basis of input novelty. In this module, winner-take-all competition and the 'activity bubble' are due tograded lateral inhibition between units. It tends to separate representations as far apart as possible, which leads to interpolation abilities and an absence of catastrophic interference when the interfering set of patterns forms an interpolated set of the initial data set. More than the Kohonen maps, these maps provide an opportunity for building psychologically and neurophysiologically motivated multimodular connectionist models. As an example, the dual pathway connectionist model for fear conditioning by Armony et al. (1997, Trends in Cognitive Science, 1: 28-34) was rebuilt and extended with CALM Maps. If the detection of novelty enhances memory encoding in a canonical circuit, such as the CALM Map, this could explain the finding of large distributed networks for novelty detection (e.g. Knight and Scabini, 1998, Journal of Clinical Neurophysiology, 15: 3-13) in the brain.

Cluster analysis using a validated self‐organizing method: cases of problem identification

AbstractKohonen's self‐organizing feature maps (SOFM) are commonly used in cluster analysis for problem solving. However, given a set of sample data, the cluster analysis results obtained by using the standard SOFM method can vary depending on the setting of the parameters of the SOFM. To validate the cluster analysis results, information in addition to the data for the SOFM is required. This paper reports practical cases of cluster analysis using SOFM in conjunction with a measure of validation. In these cases, multivariate data of survey were used to identify problems through validated SOFM cluster analyses. Copyright © 2001 John Wiley & Sons, Ltd.

Fluorescent image classification by major color histograms and a neural network

Efficient image classification of microscopic fluorescent spheres is demonstrated with a supervised backpropagation neural network (NN) that uses as inputs the major color histogram representation of the fluorescent image to be classified. Two techniques are tested for the major color search: (1) cluster mean (CM) and (2) Kohonen's self-organizing feature map (SOFM). The method is shown to have higher recognition rates than Swain and Ballard's Color Indexing by histogram intersection. Classification with SOFM-generated histograms as inputs to the classifier NN achieved the best recognition rate (90%) for cases of normal, scaled, defocused, photobleached, and combined images of AMCA (7-Amino-4-Methylcoumarin- 3-Acetic Acid) and FITC (Fluorescein Isothiocynate)-stained microspheres.

Dynamic generation of prototypes with self-organizing feature maps for classifier design

We propose a new scheme for designing a nearest-prototype classifier using Kohonen's self-organizing feature map (SOFM). The net starts with the minimum number of prototypes which is equal to the number of classes. Then on the basis of the classification performance, new prototypes are generated dynamically. The algorithm merges similar prototypes and deletes less significant prototypes. If prototypes are deleted or new prototypes appear then they are fine tuned using Kohonen's SOFM algorithm with the winner-only update strategy. This adaptation continues until the system satisfies a termination condition. The classifier has been tested with several well-known data sets and the results obtained are quite satisfactory.

Feature extraction of chromosomes from 3-D confocal microscope images.

An investigation of local energy surface detection integrated with neural network techniques for image segmentation is presented, as applied in the feature extraction of chromosomes from image datasets obtained using an experimental confocal microscope. Use of the confocal microscope enables biologists to observe dividing cells (living or preserved) within a three-dimensional (3-D) volume, that can be visualised from multiple aspects, allowing for increased structural insight. The Nomarski differential interference contrast mode used for imaging translucent specimens, such as chromosomes, produces images not suitable for volume rendering. Segmentation of the chromosomes from this data is, thus, necessary. A neural network based on competitive learning, known as Kohonen's self-organizing feature map (SOFM) was used to perform segmentation, using a collection of statistics or features defining the image. Our past investigation showed that standard features such as the localized mean and variance of pixel intensities provided reasonable extraction of objects such as mitotic chromosomes, but surface detail was only moderately resolved. In this current work, a biologically inspired feature known as local energy is investigated as an alternative image statistic based on phase congruency in the image. This, along with different combinations of other image statistics, is applied in a SOFM, producing 3-D images exhibiting vast improvement in the level of detail and clearly isolating the chromosomes from the background. Index Terms-DIC, differential interference contrast, feature extraction, feature space, image segmentation, local energy, Morlet wavelet, phase congruency, self organizing feature map, SOFM.

Some novel classifiers designed using prototypes extracted by a new scheme based on self-organizing feature map

We propose two new comprehensive schemes for designing prototype-based classifiers. The scheme addresses all major issues (number of prototypes, generation of prototypes, and utilization of the prototypes) involved in the design of a prototype-based classifier. First we use Kohonen's self-organizing feature map (SOFM) algorithm to produce a minimum number (equal to the number of classes) of initial prototypes. Then we use a dynamic prototype generation and tuning algorithm (DYNAGEN) involving merging, splitting, deleting, and retraining of the prototypes to generate an adequate number of useful prototypes. These prototypes are used to design a "1 nearest multiple prototype (1-NMP)" classifier. Though the classifier performs quite well, it cannot reasonably deal with large variation of variance among the data from different classes. To overcome this deficiency we design a "1 most similar prototype (1-MSP)" classifier. We use the prototypes generated by the SOFM-based DYNAGEN algorithm and associate with each of them a zone of influence. A norm (Euclidean)-induced similarity measure is used for this. The prototypes and their zones of influence are fine-tuned by minimizing an error function. Both classifiers are trained and tested using several data sets, and a consistent improvement in performance of the latter over the former has been observed. We also compared our classifiers with some benchmark results available in the literature.