Organizing Map Research Articles

Olfactory Atlases with an Array of Porphyrinoids Coated ZnO Nanoparticle

Olfactory Atlases with an Array of Porphyrinoids Coated ZnO Nanoparticle

Detection of Brain Tumor Using Self Organizing Map With K-mean Algorithm

Detection of Brain Tumor Using Self Organizing Map With K-mean Algorithm

A Study of Self- Organizing Maps(SOM) Neural Network Using Matlab

Kohonen's Self-Organizing Map ( SOM ) is one of the most popular artificial neural network algorithms. Bing unsupervised neural network , Self Organizing Maps( SOM ) have applications in different fields such as speech recognition, image processing and so on . This project includes a study of Self Organizing Maps neural network using MATLAB The structure, characteristics, implementation, applications and testing of this neural network for styles of one dimension and two dimensions have been considered It includes finding out the functions used for topology, and then finding out the distance function for this network throughout illustrative examples. Neural network implementation consists of three stages: Initialization (creation), Training, and Simulating. Explanation of the neighborhood concept is done. MATLAB software is used to perform how creating, training and simulating of a Self Organizing Map. Creation process consists of choosing a network parameters, plotting the results, then illustrating and identifying all functions used to create a Self Organizing Map. Training consists of weight initialization and weight vector creation. Simulating means testing the neural network using the initialization parameters and training vector created in the past two stages. The Study includes also four tests: The first test is used manual calculation procedure of the network mathematically. The other three tests are procedures for different applications using MATLAB language. It becomes evident from the graphs of the results that it’s essential to have the weight vectors for the coordination field greater than the density of input vectors in the case of employing the network to seclude the training styles in output cells. Keywords: Neural Network, Simulating, Self- Organizing Maps, Competitive layer, training DOI: 10.7176/RHSS/10-6-01 Publication date: March 31 st 2020

Adaptive multi-resolution graph-based clustering algorithm for electrofacies analysis

Logging facies analysis is a significant aspect of reservoir description. In particular, as a commonly used method for logging facies identification, Multi-Resolution Graph-based Clustering (MRGC) can perform depth analysis on multidimensional logging curves to predict logging facies. However, this method is very time-consuming and highly dependent on the initial parameters in the propagation process, which limits the practical application effect of the method. In this paper, an Adaptive Multi-Resolution Graph-based Clustering (AMRGC) is proposed, which is capable of both improving the efficiency of calculation process and achieving a stable propagation result. More specifically, the proposed method, 1) presents a light kernel representative index (LKRI) algorithm which is proved to need less calculation resource than those kernel selection methods in the literature by exclusively considering those “free attractor” points; 2) builds a Multi-Layer Perceptron (MLP) network with back propagation algorithm (BP) so as to avoid the uncertain results brought by uncertain parameter initializations which often happened by only using the K nearest neighbors (KNN) method. Compared with those clustering methods often used in image-based sedimentary phase analysis, such as Self Organizing Map (SOM), Dynamic Clustering (DYN) and Ascendant Hierarchical Clustering (AHC), etc., the AMRGC performs much better without the prior knowledge of data structure. Eventually, the experimental results illustrate that the proposed method also outperformed the original MRGC method on the task of clustering and propagation prediction, with a higher efficiency and stability.

Proposing a model for dynamical computing the risk of knowledge domains in the organizational knowledge map

PurposeThis paper aims to present a specific model and method for analyzing the knowledge domains and organization knowledge map. One of the functions of the organizational knowledge map is the possibility of extracting the risk of the organization's knowledge domains and thus the ability to define knowledge-based strategies in the organization. So far, various software tools have been designed to support the process of creating, analyzing knowledge domains and structure knowledge map. However, software companies have less detail and methodology of their software analysis and less research has been addressed.Design/methodology/approachThis model calculates the risk of knowledge domains using the recursive algorithm approach, assuming there is one-way communication between the knowledge domains and using specific factors.FindingsThe prominence of this model is to calculate knowledge domains risk, dynamic updating of knowledge domains risk after any changes in knowledge domain risk in the organization's knowledge map. The model can also be used as a simulation model and prioritize corrective actions.Originality/valueThis is a recursive model that by assuming one-way relations among knowledge domain computes the risk of each domain knowledge by considering the risk of its related domains, relations among different domains and pre-requisites and post-requisites. This model has no limitation in determining the number of knots and communications. Despite of simplicity, it is too efficient and any organization can localize it based on its own needs.

Genetic Variation in Type 1 Diabetes Reconfigures the 3D Chromatin Organization of T Cells and Alters Gene Expression

Genetics is a major determinant of susceptibility to autoimmune disorders. Here, we examined whether genome organization provides resilience or susceptibility to sequence variations, and how this would contribute to the molecular etiology of an autoimmune disease. We generated high-resolution maps of linear and 3D genome organization in thymocytes of NOD mice, a model of type 1 diabetes (T1D), and the diabetes-resistant C57BL/6 mice. Multi-enhancer interactions formed at genomic regions harboring genes with prominent roles in Tcell development in both strains. However, diabetes risk-conferring loci coalesced enhancers and promoters in NOD, but not C57BL/6 thymocytes. 3D genome mapping of NODxC57BL/6 F1 thymocytes revealed that genomic misfolding in NOD mice is mediated in cis. Moreover, immune cells infiltrating the pancreas of humans with T1D exhibited increased expression of genes located on misfolded loci in mice. Thus, genetic variation leads to altered 3D chromatin architecture and associated changes in gene expression that may underlie autoimmune pathology.

Assessment of Hamming Distance and Self Organization Map in Solving Cell Formation Problem

The cell formation (CF) problem is considered the most essential issue in cellular manufacturing systems (CMS). CF deals with the arrangement of similar parts into groups known as part families (PFs) and organizes machines also into groups, called machine cells (MCs). In the literature, numerous methods, models and algorithms have been proposed and developed to handle CF problems. However, very few studies have dealt with the assessment and comparison of these methods, to identify the most effective. This has provided strong motivation for the study presented here. The present paper focuses on two methods that are used infrequently to form MCs and PFs, and applies them in three strategies: the first is based on the use of a hamming distance only, while the second uses only a self-organization map (SOM). However, the third method applies a hybrid approach based on SOM and hamming distance. The outputs of the selected methods were compared, to select the best one. A set of five benchmark datasets and three performance measures was used for comparison and evaluation. These performance measures are: percent of the exceptional elements (PE), grouping efficiency (GE), and machine utilization (MU). The results refer to the outperforms of the hamming distance in terms of PE, GE and MU for most of the selected benchmark problems.

Improved Self-Organizing Map Clustering of Power Transformer Dissolved Gas Analysis Using Inputs Pre-Processing

Ability to organize data spatially while conserving the topological relation between data features makes the Self Organizing Map (SOM) a very useful tool for analysis and visualization of high dimensional data such as a power transformer's Dissolved Gas Analysis (DGA). Past SOM application required large historical data for its training and has limited fault detection sensitivity. In this paper, the effects of input features and data normalization are studied to enhance SOM's clustering. SOM is trained using DGA results extracted from actual faulted transformers. Combination of input features and data normalization methods are tested on SOM before the best SOM is identified. Validation is conducted using several datasets i.e. the IEC Technical Committee 10 database. Compared with past SOM applications, the proposed SOM required lesser training data, improved SOM's sensitivity in incipient fault detection and has good diagnosis accuracy. The proposed SOM is also compared with other AI-based DGA interpretation method i.e. Support Vector Machine (SVM) for benchmarking.

The Taxonomy of Living Organisms Using Self-organizing Map

The Self Organizing Map (SOM) is an unsupervised network algorithm that projects high dimensional data into low dimensional maps. The projection preserves the topology of the data so that similar data items are mapped to nearby locations on the map. The algorithm has been so popular because of its application in Computer Science and other areas; it has been applied in speech recognition, pattern identification, control engineering, earthquake detection et al. This research aimed to apply the SOM in the taxonomy of living organisms using 46 attributes. 68 animals from 6 phyla were considered and 46 attributes were used detailing their physical features, physiological features, evolution, adaptation, habitat et al. The features extracted were converted to 0s and 1s for the SOM algorithm to process. The result shows 96.569% accuracy of the SOM’s classification but better accuracy can be obtained if the SOM had processed the data for about 1000 iterations. This research revealed that SOM is a veritable tool or algorithm that can be used to classify living organisms. This research will help taxonomists, biologists and students who spend much time in classifying living organism and it will be of help to researchers who want to explore the SOM algorithm as a solution to taxonomy of living organisms. The SOM will ease taxonomy and will help to minimize the stress and time involved in classifying thousands of living organisms.

KAYIP DEĞERLİ VERİ SETLERİNDE KÜMELEME UYGULAMALARI

Missing data is when one or more values cannot be obtained in the data sets. The purpose of cluster analysis is to provide summary information to the researcher by classifying the data according to their similarities and to reduce the number of data that is too much to less. In this study, the performances of the three clustering methods are compared using different missing data rates in eleven separate data sets consisting of numerical and nominal data. The correct clustering rates of the data were examined by decreasing the data at five percent, ten percent, fifteen percent, twenty percent, twenty five percent and thirty percent of the data sets completely and randomly. The methods whose working performance were tested using missing data are k-means, one of partitioned clustering methods and self-organizing maps, one of artificial neural network-based clustering methods - Self Organization Map (SOM) and linear vector segmentation model - Learning Vector Quantization (LVQ). According to the results of the analysis; it is observed that as the missing data rate increases, the correct cluster rate decreases. It was observed that the LVQ method performed better in four data sets with two sets of nominal and numerical data, while the SOM method performed better clustering in the other seven data sets consisting of numerical data.

Data Mining Techniques For Prediction Of Concrete Compressive Strength (CCS)

The main aim of this research is to use data mining techniques to explore the main factors affecting the strength of concrete mix. In this research, we are interested in finding some of the factors that influence the high performance of concrete to increase the Concrete Compressive Strength (CCS) mix. We used Waikato’s Knowledge Analysis Environment (WEKA) tool and algorithms such as K-Means, Kohonen’s Self Organizing Map (KSOM) and EM to identify the most influential factors that increase the strength of the concrete mix. The results of this research showed that EM is highly capable of determining the main components that affect the compressive strength of high performance concrete mix. The other two algorithms, K-Means and KSOM, were noted to be an advanced predictive model for predicting the strength of the concrete mix.

New Learning Approach for Unsupervised Neural Networks Model with Application to Agriculture Field

An accurate and lower cost hybrid machine learning algorithm based on a combination of Kohonen-Self Organizing Map (SOM) and Gram-Schmidt (GSHM) algorithm was proposed, to enhance the crop yield prediction and to increase the agricultural production. The combination of GSHM and SOM allows to withdraw the most informative components about our data, by overcoming correlation issues between input data prior to the training process. The improved hybrid algorithm was trained firstly on data that have a correlation problem, and it was compared with another hybrid model based on SOM and Principal Component Analysis (PCA), secondly, it was trained using selected soil parameters related to the atmosphere (e.g. pH, nitrogen, phosphate, potassium, depth, temperature, and rainfall). A comparative study with the standard SOM was conducted. The improved Kohonen-Self Organizing Map when applied to correlated data, demonstrated better results in terms of classification accuracy (8/8), and rapidity = 0.015s compared to a classification accuracy (7/8) and a rapidity = 97,828 s using SOM combined with PCA. Moreover, the proposed algorithm resulted in better results for crop prediction in terms of maximum iteration number of 675, mean error ≤0.00022, and rapidity = 18.422s versus an iteration number of 729, mean error ≤ 0.000916 and rapidity= 23.707s with the standard SOM. The proposed algorithm allowed us to overcome correlation issues, and to improve the classification, learning process, and rapidity, with the potential to apply for predicting crop yield in the agricultural field.

Automatic condition monitoring of electromechanical system based on MCSA, spectral kurtosis and SOM neural network

Condition monitoring and fault diagnosis play the most important role in industrial applications. The gearbox system is an essential component of mechanical system in fault identification and classification domains. In this paper, we propose a new technique which is based on the Fast-Kurtogram method and Self Organizing Map (SOM) neural network to automatically diagnose two localized gear tooth faults: a pitting and a crack. These faults could have very different diagnostics; however, the existing diagnostic techniques only indicate the presence of local tooth faults without being able to differentiate between a pitting and a crack. With the aim to automatically diagnose these two faults, a dynamic model of an electromechanical system which is a simple stage gearbox with and without defect driven by a three phase induction machine is proposed, which makes it possible to simulate the effect of pitting and crack faults on the induction stator current signal. The simulated motor current signal is then analyzed by using a Fast-Kurtogram method. Self-organizing map (SOM) neural network is subsequently used to develop an automatic diagnostic system. This method is suitable for differentiating between a pitting and a crack fault.

A Hybrid Forecasting Model for Option Price Prediction using Machine Learning Technique

A hybrid model is presented in this paper that is aiming to forecast the option prices that are analyzed in the data set of different banks. A new move is proposed by this paper that is forecasting the option price with the use of ANN model which is optimizing the hybrid swarm optimization. The data set of the NSE India banking sector has been utilized for the calculation of an effective algorithm for forecasting the option price with the help of this ANN model. For forecasting the option price, the methods which are used in this paper are SOM (self organization map), RBF (Radial Basis Function) and the Hybrid Swarm Optimization system. The hybrid swarm intelligence algorithm reduces the variation of prices and proceeds the data for the prediction and used cascaded neural network-based classifier for the purification of data. Two results are combined so that the option price prediction can be achieved. A comprehensive description of the option price is offered with a combined forecasting model that is developing the accuracy of the option price forecasting, also the reflection of the stock market trends are seen in this investigation and the model also has the capacity to offer advices to the investors that are connected with the productive speculation.

Optimising the use of caesarean section: a generic formative research protocol for implementation preparation

BackgroundCaesarean section rates are rising across all geographical regions. Very high rates for some groups of women co-occur with very low rates for others. Both extremes are associated with short and longer term harms. This is a major public health concern. Making the most effective use of caesarean section is a critical component of good quality, sustainable maternity care. In 2018, the World Health Organization published evidence-based recommendations on non-clinical interventions to reduce unnecessary caesarean section. The guideline identified critical research gaps and called for formative research to be conducted ahead of any interventional research to define locally relevant determinants of caesarean birth and factors that may affect implementation of multifaceted optimisation strategies. This generic formative research protocol is designed as a guide for contextual assessment and understanding for anyone planning to take action to optimise the use of caesarean section.MethodsThis formative protocol has three main components: (1) document review; (2) readiness assessment; and (3) primary qualitative research with women, healthcare providers and administrators. The document review and readiness assessment include tools for local mapping of policies, protocols, practices and organisation of care to describe and assess the service context ahead of implementation. The qualitative research is organized according to twelve identified interventions that may optimise use of caesarean section. Each intervention is designed as a “module” and includes a description of the intervention, supporting evidence, theory of change, and in-depth interview/focus group discussion guides. All study instruments are included in this protocol.DiscussionThis generic protocol is designed to underpin the formative stage of implementation research relating to optimal use of caesarean section. We encourage researchers, policy-makers and ministries of health to adapt and adopt this design to their context, and share their findings as a catalyst for rapid uptake of what works.

Assessment of the Average Level of TOEFL Score by using SOM (Self Organizing Map) and K-Mean Clustering Techniques

Economic growth as measured by GDP growth rates and economic growth set as an increase in GDP strongly helps government predictions about the economic situation and the formation of economic development strategies. This measurement is done by combining mathematical and computer technology to make qualitative and quantitative predictions scientifically and appropriately for economic growth trends. It is a good practical sense to use scientific and proven methods to predict future GDP development trends of a particular economy. In some cases, machine learning methods have proven to be better forecasting results than statistical methods. A Deep Neural Network (DNN) is one type of ANN (Artificial Neural network) architecture based on deep MLP (Multi Layer Perceptron), which uses Deep Learning training techniques. This study proposes the use of DNN to predict the percentage of GDP distribution at current prices by industry sector. In this case, the DNN used will have multiple outputs as many industry sectors. The aim of this study is how to predict for the next period with the smallest possible prediction errors by using DNN.

Breast Cancer Classification using Nature-inspired Algorithm

Breast Cancer is one among the dangerous ailments that roots up of deaths among women worldwide. Lots of risk factors have been identified through research though the exact reasons of breast cancer are not yet fully understood The Artificial Immune Recognition System classifier helps to classify the type of breast cancer on Wisconsin dataset which provides accurate prediction of the classes of breast cancer. i.e, Benign and Malignant. This system focuses on supervised classification with the help of clonal selection algorithm, Hierarchical Learning Vector Quantization, Multipass Self Organizing Map. The goal of this system can implement the algorithm to classify the cancer accurately and to compare the error rate, f-measure with previous classification algorithms.

Variability of Major Aerosol Types in China Classified Using AERONET Measurements

Aerosol type is a critical piece of information in both aerosol forcing estimation and passive satellite remote sensing. However, the major aerosol types in China and their variability is still less understood. This work uses direct sun measurements and inversion derived parameters from 47 sites within the Aerosol Robotic Network (AERONET) in China, with more than 39,000 records obtained between April 1998 and January 2017, to identify dominant aerosol types using two independent methods, namely, K means and Self Organizing Map (SOM). In total, we define four aerosol types, namely, desert dust, scattering mixed, absorbing mixed and scattering fine, based on their optical and microphysical characteristics. Seasonally, dust aerosols mainly occur in the spring and over North and Northwest China; scattering mixed are more common in the spring and summer, whereas absorbing aerosols mostly occur in the autumn and winter during heating period, and scattering fine aerosols have their highest occurrence frequency in summer over East China. Based on their spatial and temporal distribution, we also generate seasonal aerosol type maps that can be used for passive satellite retrieval. Compared with the global models used in most satellite retrieval algorithms, the unique feature of East Asian aerosols is the curved single scattering albedo spectrum, which could be related to the mixing of black carbon with dust or organic aerosols.

EXPLORING SPATIO-TEMPORAL WAVE PATTERN USING UNSUPERVISED TECHNIQUE

Abstract. The sea waves are the up and down movements of water in the sea. The various heights of sea waves are known as significant wave heights. Each type of wave has their own characteristics based on their significant wave heights. The aim of this research is to explore spatio-temporal wave patterns and their effects on Tok Jembal coastal areas. For this study, the monthly wave data were obtained from the satellite altimeters that have been processed using Radar Altimeter Database System (RADS). The Self Organizing Map (SOM) method was used to extract the spatio-temporal wave height patterns from the monthly wave height data. From the clustering results, six number of clusters were extracted and then each of these clusters was categorized into specific type of wave heights. In addition, time series of Landsat satellite images were used to observe the coastal changes at Tok Jembal areas. Finally, we analyzed the effects of spatio-temporal wave patterns towards the occurrences of coastal erosion along the coastal areas. This study has discovered that the wave heights along the coastal areas fall in slight category and showed less effects on the erosion. From the visual interpretation of time- series images (10 years gap) also proved that the erosion can be considered as moderate. Overall, this study could benefit the coastal management especially for shoreline monitoring where early action can be taken when there are signs of erosion along the coast.

Development of the process map “research and development” for agricultural organizations

The quality management system is developing rapidly and dynamically in organizations of agriculture. The management of agricultural enterprises realizing the role of a leader in quality work is aimed at continuous improvement in all aspects of activity. The management of agricultural enterprises, realizing the role of a leader in quality work, is aimed at continuous improvement in all aspects of activity. The QMS in food production is implemented based on international standards such as ISO 22000, ISO 9001, where successive processes are described, which also include the principles of HACCP. This standard combines risk analysis and critical control points. Based on all these consistent measures, enterprises are striving to improve both the quality of the products and the work of the company as a whole. This is a necessary measure, it is obligatory in today’s time, because thanks to it, not only the product quality, but also the competitiveness of the production in the market increases. As a result, the enterprise opens an export opportunity. Without the introduction of a quality management system, the company cannot move on. This article discusses the QMS documentation, which allows controlling the processes and fruitfully developing the organizations of agriculture. Developing of the research engineering and development work process map for agricultural organizations. The input and output data of the process are determined, as well as the performance and risk indicators for the process. To improve the process management system, thresholds for process performance indicators are defined. The risks of the activities of the processes, to minimize the risks and prevent them in the future. The method of determining the effectiveness of the process is implemented. Indicators must be met in full size, without fail, of the number of non-compliances detected by the customer leads to a deterioration in the performance of the process by a percentage.