Self-Organizing Map Based Approach for Assessment of Control Room Operator Training

We have been working on the application of Machining Learning in Metabolomics, Drug-Drug Interaction Discovery and Human Gait Recognition [1-5], profiling large data sets. Extraction of vital information about 1) plant metabolomics that can improve the environment and food quality, 2) in vitro neuronal network behavior patterns for various drugs that can be used to characterize drugs for brain deceases and 3) human gait patterns that can reveal various diseases were among these applications. We have demonstrated with considerable success in using unsupervised clustering techniques to analyze genetic and metabolomic data. This includes analysis of drought resistance in wheat [4] and microbial metagenomes [5].We introduced two methods: Near Unsupervised Learning (NUL) and Sub-sample Error Graphs (SEGs) [5] to analyze large amount of data. Self Organizing Map (SOM), which is one of the widely used Unsupervised Neural Networks, has been used as a data-mining tool due to its ability to map high dimensional data into a two dimensional feature map, which is expected to be topology preserving allowing users to visually identify clusters by their topological relationships in terms of their proximity on the map. The Growing Self Organizing Maps (GSOM) further allows the map size to be determined by the algorithm, which relies upon a user set parameter called Spread Factor (SF) [6]. The wide availability of GPUs for affordable prices allows faster comparison of various SOMs with different maps sizes taking away some of the advantages GSOM claimed. Further development of GSOM into a Dynamic SOM Tree exploits the possibility of varying SF to obtain multiple GSOMs from a small number of compact clusters to a large number of sparse clusters [7]. NUL methods can be applied on GSOM using a small number of labels that should be available for every class. This is however not realistic in some applications where the number of classes cannot be explicitly known. We propose a new method call Deep Near Unsupervised Learning (D-NUL), where Dynamic SOM tree is used instead of GSOM and the number of classes are not assumed to be known. The implementation of Dynamic SOM tree methods with varying SF on GPUs will make the computation with D-NUL possible for many problems in big data analytics.

Extending the Kohonen self-organizing map networks for clustering analysis

Background: A Liver tumor is a dangerous disease that may leads to death, the chances of survival will increase when it is detected in early time. Materials and Methods: In this study, clustering Fuzzy c-mean and ''Self-Organization Feature Map'', HSOFM, which is an unsupervised artificial neural network, based on the histogram of the image, are presented for segmenting, isolating, and then extracting tumors and other abnormal regions in liver images of MRI and CT imaging. In an additional processing, morphological operations were used to achieve the complete final extraction of the isolated regions without any extra pixels that do not belong to the abnormal regions. These two methods were applied on five MRI and four CT scan images. The extracted regions surface areas were calculated and compared with the groundtruth, manually extracted mass regions, to check the goodness adequacy of the adopted methods. The work was achieved by Mat Lab programing environment. Results: The percent relative differences of the extracted abnormal regions by implementing the adopted methods with the groundtruth were ranged from 1.108 % to 3.861 % for the images of MRI, while for CT scan images, the percent relative differences were in the range from 0.732 % to 3.456%. By implementing FCM clustering, the percent relative difference ranged from 0.724% to 4.370 % for three MRI images, while for CT scan images, the percent relative difference was 4.327 % for one of the adopted CT images. Results of implementing HSOFM indicate the high-quality performance of this method with 95 % accuracy. Conclusion: From the results we can conclude that there is an appropriate number of nodes and clusters that is a more adequate choice than others depending on the properties’ intensity variance in each processed image. The comparison between the two implemented methods figures out the superiority of the HSOFM method over FCM. There are some limitations, such as the small size of the abnormal regions as well as the interference of the abnormal regions with the normal regions of the similar intensity that require applying advanced enhancement methods as an additional preprocessing step.

The K-means (KM) and Self-Organizing Map (SOM) are two popular and very different techniques for clustering data. Both techniques require a set of training data which are used in an iterative process to find clusters in this set. For the KM, the number of clusters must be preassigned before a training session begins, whereas, the number of SOM clusters is determined after a single training is completed. In this paper we compare the clustering performance of these two methods using data from three mineral spectral libraries whose samples have been hierarchically labeled with Class, Subclass, and Group names. These names are used to determine the overall mineralogical purity of the clusterings as a function of cluster number. The degree of cluster overlap is also determined as a function of cluster number using the Davies-Bouldin (DB) index. We show that, in general, the purity and overlap of KM and SOM derived clusters differ significantly for cluster numbers small compared to the number of training samples. The KM clusters are less pure and overlap more than SOM clusters. The ramifications of these results on the accuracy of classification of spectra not used for training is discussed.

Determining the structure of data without prior knowledge of the number of clusters or any information about their composition is a problem of interest in many fields, such as image analysis, astrophysics, biology, etc. Partitioning a set of n patterns in a p-dimensional feature space must be done such that those in a given cluster are more similar to each other than the rest. As there are approximately Kn/K! possible ways of partitioning the patterns among K clusters, finding the best solution is very hard when n is large. The search space is increased when we have no a priori number of partitions. Although the self-organizing feature map (SOM) can be used to visualize clusters, the automation of knowledge discovery by SOM is a difficult task. This paper proposes region-based image processing methods to post-processing the U-matrix obtained after the unsupervised learning performed by SOM. Mathematical morphology is applied to identify regions of neurons that are similar. The number of regions and their labels are automatically found and they are related to the number of clusters in a multivariate data set. New data can be classified by labeling it according to the best match neuron. Simulations using data sets drawn from finite mixtures of p-variate normal densities are presented as well as related advantages and drawbacks of the method.

This paper proposes a clustering ensemble method that introduces cascade structure into the self-organizing map (SOM) to solve the problem of the poor performance of a single clusterer. Cascaded SOM is an extension of classical SOM combined with the cascaded structure. The method combines the outputs of multiple SOM networks in a cascaded manner using them as an input to another SOM network. It also utilizes the characteristic of high-dimensional data insensitivity to changes in the values of a small number of dimensions to achieve the effect of ignoring part of the SOM network error output. Since the initial parameters of the SOM network and the sample training order are randomly generated, the model does not need to provide different training samples for each SOM network to generate a differentiated SOM clusterer. After testing on several classical datasets, the experimental results show that the model can effectively improve the accuracy of pattern recognition by 4%∼10%.

A fuzzy self-organizing map (SOM) network is proposed in this paper for visual motor control of a 7 degrees of freedom (DOF) robot manipulator. The inverse kinematic map from the image plane to joint angle space of a redundant manipulator is highly nonlinear and ill-posed in the sense that a typical end-effector position is associated with several joint angle vectors. In the proposed approach, the robot workspace in image plane is discretized into a number of fuzzy regions whose center locations and fuzzy membership values are determined using a Fuzzy C-Mean (FCM) clustering algorithm. SOM network then learns the inverse kinematics by on-line by associating a local linear map for each cluster. A novel learning algorithm has been proposed to make the robot manipulator to reach a target position. Any arbitrary level of accuracy can be achieved with a number of fine movements of the manipulator tip. These fine movements depend on the error between the target position and the current manipulator position. In particular, the fuzzy model is found to be better as compared to Kohonen self-organizing map (KSOM) based learning scheme proposed for visual motor control. Like existing KSOM learning schemes, the proposed scheme leads to a unique inverse kinematic solution even for a redundant manipulator. The proposed algorithms have been successfully implemented in real-time on a 7 DOF PowerCube robot manipulator, and results are found to concur with the theoretical findings.

There is a growing need for a method to analyze massive gene expression data obtained from DNA microarrays. We introduce a method of combining a self-organizing map (SOM) and a k-means clustering for analyzing and categorizing the gene expression data. The SOM is an unsupervised neural network learning algorithm and forms a mapping the high-dimensional data to two-dimensional space. However, it is difficult to find clustering boundaries from results of the SOM. On the other hand, the k-means clustering can partition the data into the clusters under the assumption of the known number of clusters. In order to understand easily the results of SOM, we apply the k-means clustering to finding the clustering boundaries from results of SOM. We have applied the proposed method to the published data of yeast gene expression and show that the method is effective for categorizing the data.

Since we can accumulate a huge amount of data including useless information in these years, it is important to investigate various extraction method of clusters from data including a lot of noises. The self-organizing map (SOM) attracts attentions for clustering in these years. In our past study, we have proposed a method of using simultaneously two kinds of SOMs whose features are different (nSOM), namely, one self-organizes the area on which input data are concentrated, and the other self-organizes the whole of the input space. Further, we have applied this method to clustering of data including a lot of noises and have confirmed the efficiency. However, in order to obtain an efficient clustering performance using this method, we must determine the appropriate number of the SOMs used in the method. This problem has been remedied by proposing the Peace SOM (PSOM) method, however, PSOM algorithm must be used after executing the nSOM method. In this study, we propose a method of using plural SOMs (TSOM: Tentacled SOM) for effective data extraction, which possesses both abilities of nSOM and PSOM. Each SOM of TSOM can catch the information of other SOMs existing in its neighborhood and self-organizes with the competing and accommodating behaviors. The behavior of TSOM is investigated with applications to data extraction from input data including a lot of noises. We can confirm that TSOM successfully extracts clusters even in the case that we do not know the number of clusters in advance.

Permeability, the ability of rocks to flow hydrocarbons, is directly determined from core. Due to high cost associated with coring, many techniques have been suggested to predict permeability from the easy-to-obtain and frequent properties of reservoirs such as log derived porosity. This study was carried out to put clustering methods (dynamic clustering (DC), ascending hierarchical clustering (AHC) self organizing map (SOM) and multi-resolution graph-based clustering (MRGC)) into practice in order to predict the permeability of a heterogeneous carbonate reservoir in southwest of Iran. In addition, the results are compared with three conventional approaches, empirical models, regression analysis, and ANN. The performance of all the examined methods was compared in order to choose the best approach for predicting permeability in un-cored wells of the studied field. For all clustering methods, selecting the optimal number of clusters is the most important task. The optimal values for the number of clusters are selected by iteration. The optimal number of clusters for MRGC, SOM, DC, and AHC are 7, 9, 9, and 8 respectively. Empirical equations and regression analysis weakly predict permeability and the value of R² parameters of both approaches are around 0.6. Generally the performance of clustering techniques is acceptable in Fahliyan formation. These techniques predict permeability between 1 and 1000 mD very well and just overestimate permeability values less than 1 mD. SOM performed the best among all examined techniques (R²=0.7911). The constructed and validated SOM model with 9 clusters was selected to predict permeability in one of un-cored wells of the studied field. In this well, the predicted permeability was in good agreement with MDT derived permeability.

Binary tree time adaptive self-organizing map

The traditional K-means clustering algorithm is difficult to determine the cluster number, which is sensitive to the initialization of the clustering center and easy to fall into local optimum. This paper proposes a clustering algorithm based on self-organizing mapping network and weight particle swarm optimization SOM&WPSO (Self-Organization Map and Weight Particle Swarm Optimization). Firstly, the algorithm takes the competitive learning mechanism of a self-organizing mapping network to divide the data samples into coarse clusters and obtain the clustering center. Then, the obtained clustering center is used as the initialization parameter of the weight particle swarm optimization algorithm. The particle position of the WPSO algorithm is determined by the traditional clustering center is improved to the sample weight, and the cluster center is the “food” of the particle group. Each particle moves toward the nearest cluster center. Each iteration optimizes the particle position and velocity and uses K-means and K-medoids recalculates cluster centers and cluster partitions until the end of the algorithm convergence iteration. After a lot of experimental analysis on the commonly used UCI data set, this paper not only solves the shortcomings of K-means clustering algorithm, the problem of dependence of the initial clustering center, and improves the accuracy of clustering, but also avoids falling into the local optimum. The algorithm has good global convergence.

A Bayesian deep restricted Boltzmann-Kohonen architecture for data clustering termed deep restricted Boltzmann machine (DRBM)-ClustNet is proposed. This core-clustering engine consists of a DRBM for processing unlabeled data by creating new features that are uncorrelated and have large variance with each other. Next, the number of clusters is predicted using the Bayesian information criterion (BIC), followed by a Kohonen network (KN)-based clustering layer. The processing of unlabeled data is done in three stages for efficient clustering of the nonlinearly separable datasets. In the first stage, DRBM performs nonlinear feature extraction by capturing the highly complex data representation by projecting the feature vectors of d dimensions into n dimensions. Most clustering algorithms require the number of clusters to be decided a priori; hence, here, to automate the number of clusters in the second stage, we use BIC. In the third stage, the number of clusters derived from BIC forms the input for the KN, which performs clustering of the feature-extracted data obtained from the DRBM. This method overcomes the general disadvantages of clustering algorithms, such as the prior specification of the number of clusters, convergence to local optima, and poor clustering accuracy on nonlinear datasets. In this research, we use two synthetic datasets, 15 benchmark datasets from the UCI Machine Learning repository, and four image datasets to analyze the DRBM-ClustNet. The proposed framework is evaluated based on clustering accuracy and ranked against other state-of-the-art clustering methods. The obtained results demonstrate that the DRBM-ClustNet outperforms state-of-the-art clustering algorithms.

The best known and most widely utilized pattern finding algorithm in data mining applications is association rule mining (ARM). Extraction of frequent patterns is an indispensable step in ARM. Most studies in the literature have been implemented on the concept of support and confidence framework utilization. Here, we investigated an efficient and robust ARM scheme based on a self-organizing map (SOM) and an optimized genetic algorithm (OGA). A SOM is an unsupervised neural network that efficaciously produces spatially coordinated internal feature representations and detected abstractions in the input space and is the most efficient clustering technique that reveals conventional similarities in the input space by performing a topology maintaining mapping. Hence, a SOM is utilized to generate accurate clustered frequency patterns and an OGA is used to generate positive and negative association rules with multiple consequences by studying all possible patterns. Experimental analysis on various datasets has shown the robustness of our proposed ARM in comparison to traditional rule mining approaches by proving that a greater number of positive and negative association rules is generated by the proposed methodology resulting in a better performance when compared to conventional rule mining schemes.

This paper looks at the use of a Self Organizing Map (SOM), to link of records of crimes of serious sexual attacks. Once linked a profile can be derived of the offender(s) responsible.The data was drawn from the major crimes database at the National Crime Faculty of the National Police Staff College Bramshill UK. The data was encoded from text by a small team of specialists working to a well-defined protocol. The encoded data was analyzed using SOMs. Two exercises were conducted. These resulted in the linking of several offences in to clusters each of which were sufficiently similar to have possibly been committed by the same offender(s). A number of clusters were used to form profiles of offenders. Some of these profiles were confirmed by independent analysts as either belonging to known offenders or appeared sufficiently interesting to warrant further investigation.The prototype was developed over 10 weeks. This contrasts with an in-house study using a conventional approach, which took 2 years to reach similar results. As a consequence of this study the NCF intends to pursue an in-depth follow up study.