An Integrated Framework for Mixed Data Clustering Using Growing Hierarchical Self-Organizing Map (GHSOM)

A novel approach for image segmentation is proposed in this paper. This approach is based on the growing hierarchical self-organizing map (GHSOM), which consists of a hierarchical architecture composed of growing self-organizing maps (SOMs). The SOMs have shown to be successful for the analysis of high-dimensional input data as in data mining applications. The hierarchical architecture of the GHSOM is more flexible than a single SOM in the adaptation process to input data, mirroring inherent hierarchical relations among input data. Image hierarchical segmentation can be achieved by using this neural network model, where the hierarchical structure of segmented regions is captured. In order to evaluate the performance of this segmentation method, an application for hierarchical background modeling in video sequences is provided. Therefore, foreground detection is achieved. Experimental results show that the proposed approach is promising for applications where hierarchical segmentation is required.

This paper describes a focused literature survey of self-organizing maps (SOM) in support of intrusion detection. Specifically, the SOM architecture can be divided into two categories, i.e., static-layered architectures and dynamic-layered architectures. The former one, Hierarchical Self-Organizing Maps (HSOM), can effectively reduce the computational overheads and efficiently represent the hierarchy of data. The latter one, Growing Hierarchical Self-Organizing Maps (GHSOM), is quite effective for online intrusion detection with low computing latency, dynamic self-adaptability, and self-learning. The ultimate goal of SOM architecture is to accurately represent the topological relationship of data to identify any anomalous attack. The overall goal of this survey is to comprehensively compare the primitive components and properties of SOM-based intrusion detection. By comparing with the two SOM-based intrusion detection systems, we can clearly understand the existing challenges of SOM-based intrusion detection systems and indicate the future research directions.

Clustering is an unsupervised classification method that divides a data set in groups, where the elements of a group have similar characteristics to each other. A well-known clustering method is the Growing Hierarchical Self-Organizing Map (GH-SOM), that improves the results of an ordinary SOM by controlling the number of neurons generated. In this paper it is proposed a optimization of the typical GH-SOM, using a cluster validation index to verify the quality of partitioning.

Data mining and knowledge discovery aim at finding useful information from typically massive collections of data, and then extracting useful knowledge from the information. To date a large number of approaches have been proposed to find useful information and discover useful knowledge; for example, decision trees, Bayesian belief networks, evidence theory, rough set theory, fuzzy set theory, kNN (k-nearest-neighborhood) classifier, neural networks, and support vector machines. However, these approaches are based on a specific data type. In the real world, an intelligent system often encounters mixed data types, incomplete information (missing values), and imprecise information (fuzzy conditions). In the UCI (University of California – Irvine) Machine Learning Repository, it can be seen that there are many real world data sets with missing values and mixed data types. It is a challenge to enable machine learning or data mining approaches to deal with mixed data types (Ching, 1995; Coppock, 2003) because there are difficulties in finding a measure of similarity between objects with mixed data type attributes. The problem with mixed data types is a long-standing issue faced in data mining. The emerging techniques targeted at this issue can be classified into three classes as follows: (1) Symbolic data mining approaches plus different discretizers (e.g., Dougherty et al., 1995; Wu, 1996; Kurgan et al., 2004; Diday, 2004; Darmont et al., 2006; Wu et al., 2007) for transformation from continuous data to symbolic data; (2) Numerical data mining approaches plus transformation from symbolic data to numerical data (e.g.,, Kasabov, 2003; Darmont et al., 2006; Hadzic et al., 2007); (3) Hybrid of symbolic data mining approaches and numerical data mining approaches (e.g.,, Tung, 2002; Kasabov, 2003; Leng et al., 2005; Wu et al., 2006). Since hybrid approaches have the potential to exploit the advantages from both symbolic data mining and numerical data mining approaches, this chapter, after discassing the merits and shortcomings of current approaches, focuses on applying Self-Organizing Computing Network Model to construct a hybrid system to solve the problems of knowledge discovery from databases with a diversity of data types. Future trends for data mining on mixed type data are then discussed. Finally a conclusion is presented.

A Network Intrusion Detection System (NIDS) is an alarm system for networks. NIDS monitors all network actions and generates alarms when it detects suspicious or malicious attempts. A false positive alarm is generated when the NIDS misclassifies a normal action in the network as an attack. We present a data mining technique to assist network administrators to analyze and reduce false positive alarms that are produced by a NIDS. Our data mining technique is based on a Growing Hierarchical Self-Organizing Map (GHSOM) that adjusts its architecture during an unsupervised training process according to the characteristics of the input alarm data. GHSOM clusters these alarms in a way that supports network administrators in making decisions about true and false alarms. Our empirical results show that our technique is effective for real-world intrusion data.

Tumor markers are substances, usually proteins that can be found in the blood, urine, stool, tumor tissue and more recently DNA changes, which are produced by the body in response to cancer growth. Thus far, more than 20 different tumor markers have been identified where some of them are specific for a particular type of cancer, while others are associated with several cancer types. The problem of tumor profiling has been extensively studied by the bioinformatics community. Although tumor classification has improved nowadays, there has been no general approach for identifying new cancer classes or for assigning tumors to known classes. In this paper we describe a novel strategy for tumor classification by using Growing Hierarchical Self-Organizing map (GHSOM) since it is able to weigh the contribution of each marker according to its relatedness with other tumor markers as well as handles highly skewed tumor marker expressions well. In the end, experiments are conducted to further demonstrate the feasibility and efficiency of tumor classification approach which provide valuable contribution in the field of oncology and cancer diseases and will be as a guide for the identification of these diseases.

Topological pattern discovery and feature extraction for fraudulent financial reporting

The paper approaches aspect based opinion mining, which uses an unsupervised neural network as the opinion classifier. The neural network is an extension of the Growing Hierarchical Self-organizing Maps (GHSOM). In the aspect based sentiment analysis, we exploit the fact that the binary relations of syntactic dependency, extracted from product reviews, very often express relations between an aspect of the reviewed product and an opinion towards that aspect. We use the Growing Hierarchical Self-organizing Maps to classify pairs built according to the dependency relations, more exactly to classify pairs of the form (aspect, opinion bearing word). With this classification, we discover whether the various text mentions of the aspects of the target entity (such as the aspects of a product) are opinionated with positive or negative sentiment in the text of a review. We classify these pairs against a domain specific taxonomy of aspects, which also includes (positive/ negative) opinions associated with the aspects. Since it is based on classification against an ontology, our approach is semantic oriented. We tested our system on a collection of reviews about photo cameras.

Since manufacturing industry has become specialized, socialized, service-oriented and collaborative, mass individualized demands on products and manufacturing services have driven prosumers clustering into various communities. Lots of professional and socialized small and medium-sized prosumers spring up to provide product-service for satisfying customers’ requirements. Under this trend, a new social business relationship organizational network has been proposed to aggregate these prosumers into communities for mass individualization manufacturing. Communities are established by two steps. First, the similar prosumers are clustered into one community by growing hierarchical self-organizing map (GHSOM) algorithm. Suitable communities are selected, and then the resources are mapped to the prosumers. Second, the order is allocated to the prosumers, and thereby different order allocation strategies lead to different forms of communities. Product cost and delivery time serve as the indicators for selecting the best community. A multi-objective algorithm is proposed to tackle the order allocation problem. A case from a machinery firm is analyzed to validate the proposed model. Several rules are revealed and used for guiding practical production.

Clustering algorithms play a pivotal role in data mining, offering powerful tools for uncovering hidden patterns and structures within datasets. These algorithms aim to divide data points into coherent groups based on similarities or dissimilarities, making it easier to explore and understand complex data. Clustering algorithms typically rely on similarity measures to assess the likeness between data points. Consequently, selecting a suitable similarity measure is crucial for achieving satisfactory clustering outcomes. However, this decision can pose significant challenges, especially for non-experts, given the plethora of similarity measures available in the literature and their performance which is closely linked to the specific dataset, clustering algorithm, and cluster validity index employed. This difficulty is even more important when considering mixed data clustering. Mixed data refers to heterogeneous data characterized by both numerical and categorical attributes. In such a context, the same similarity measure cannot be used for both types of attributes due to their different nature. Commonly, two similarity measures are combined, one for numerical attributes and one for categorical attributes. This adds a layer of complexity to the problem since it requires the selection of two similarity measures instead of just one. This paper introduces SIMREC, a similarity measure recommendation system for mixed data clustering. The system uses meta-learning to mine the relationship between dataset characteristics and similarity measures performances for different mixed data clustering algorithms and cluster validity indices. Therefore, given a mixed dataset, a mixed data clustering algorithm, and a cluster validity index, the system can recommend suitable pairs of numerical and categorical similarity measures based on the characteristics of the dataset. We implemented the proposed system using 130 pairs of similarity measures (10 numerical and 13 categorical), 4 commonly used mixed data clustering algorithms (K-Prototypes, LSH-K-Prototypes, K-Medoids, and Hierarchical Clustering), and three cluster validity indices (Silhouette, Clustering Accuracy, and Adjusted Rand Index). Our experiments on 185 publicly available mixed datasets show that the pairs of similarity measures recommended by SIMREC outperform the baseline pairs, including classically used pairs of similarity measures in the literature.

With an onset of social network amount of data is increasing day by day. In order to analyze the data and extract useful information, the data mining technology can be used. Clustering is one of the popular method of data mining. Clustering can be used for visualizing and analyzing of data. We are discussing Kohonen SOM. We are using neural networks, as a data mining tool which provides statistical observation and layout from big data-sets. We determine how Self-Organizing Kohonen Maps, can be efficiently used for data mining purposes. The Self Organizing Map (SOM) unsupervised learning is an effective computational tool in data mining processes. Self-Organizing Maps (SOMs) used to visualize social network dataset. We used Self-Organizing Map for clustering and analyzing high-dimensional and complex social network datasets. This paper also visualizes SOM neighbor connection, SOM neighbor weight distance, SOM weight position. We perform self organizing map algorithm for social network dataset in matlab.

Association rule mining is one of the most popular pattern discovery methods used in data mining. Frequent pattern extraction is an essential step in association rule mining. Most of the proposed algorithms for extracting frequent patterns are based on the downward closure lemma concept utilizing the support and confidence framework. In this chapter we investigate an alternative method for mining frequent patterns in a transactional database. Self-Organizing Map (SOM) is an unsupervised neural network that effectively creates spatially organized internal representations of the features and abstractions detected in the input space. It is one of the most popular clustering techniques, and it reveals existing similarities in the input space by performing a topology-preserving mapping. These promising properties indicate that such a clustering technique can be used to detect frequent patterns in a top-down manner as opposed to the traditional approach that employs a bottom-up lattice search. Issues that are frequently raised when using clustering technique for the purpose of finding association rules are: (i) the completeness of association rule set, (ii) the support level for the rules generated, and (iii) the confidence level for the rules generated. We present some case studies analyzing the relationships between the SOM approach and the traditional association rule framework, and propose a way to constrain the clustering technique so that the traditional support constraint can be approximated. Throughout our experiments, we have demonstrated how a clustering approach can be used for discovering frequent patterns.

The Umpire 2.0 R-package offers a streamlined, user-friendly workflow to simulate complex, heterogeneous, mixed-type data with known subgroup identities, dichotomous outcomes, and time-to-event data, while providing ample opportunities for fine-tuning and flexibility. Here, we describe how we have expanded the core Umpire 1.0 R-package, developed to simulate gene expression data, to generate clinically realistic, mixed-type data for use in evaluating unsupervised and supervised machine learning (ML) methods. As the availability of large-scale clinical data for ML has increased, clinical data has posed unique challenges, including widely variable size, individual biological heterogeneity, data collection and measurement noise, and mixed data types. Developing and validating ML methods for clinical data requires data sets with known ground truth, generated from simulation. Umpire 2.0 addresses challenges to simulating realistic clinical data by providing the user a series of modules to generate survival parameters and subgroups, apply meaningful additive noise, and discretize to single or mixed data types. Umpire 2.0 provides broad functionality across sample sizes, feature spaces, and data types, allowing the user to simulate correlated, heterogeneous, binary, continuous, categorical, or mixed type data from the scale of a small clinical trial to data on thousands of patients drawn from electronic health records. The user may generate elaborate simulations by varying parameters in order to compare algorithms or interrogate operating characteristics of an algorithm in both supervised and unsupervised ML.

Sales volume forecasting is becoming a crucial requirement for many sellers, enabling them to modify their advertising strategies and strike the ideal balance between sales volume and profit. A higher budget for promotion and a lower profit are the outcomes of overestimating the sales volume, which results in lower actual sales than predicted. Therefore, accurate sales volume forecasting is essential for sellers to choose the best methods of advertisement. The quantity of sales predicting approach in this case is one that predicts future sales based on historical data for the particular supplier, as well as the advertising techniques to be used on the relevant future days, sales volume from the past, dynamic influencing elements like past marketing strategies and weather data, and the static characteristics of the specific vendor are all examples of historical information. As a result, merchants use the expected forthcoming gross revenue under various stuff to choose the deal strategy to be employed. This work suggests a clustering-based forecasting methodology for predicting sales by fusing clustering and machine-learning techniques. The suggested method first divided the training data into groups using the clustering technique, which groups data with comparable features or patterns. The forecasting models for each group are then, using machine learning techniques, it was trained. Once, the cluster's trained forecasting model was chosen for sales forecasting. It was determined which cluster's data patterns matched the test data the most closely. Because sales data reflect similar data patterns or features over time, the presented clustering-based forecasting methodology can enhance forecast accuracy. Three machine learning techniques are used in this paper: Generalized Linear Regression, Decision Tree, and Gradient Boosted Tree, as well as two clustering techniques: Self Organizing Map (SOM) and K-mean clustering. A predictive model that is most suited for predicting the sales trend is presented based on a performance evaluation. Discussion of the data is done in terms of the precision and accuracy of good prediction systems. The best-fit model is chosen to be the Gradient Boosted Tree Algorithm and it has the highest level of forecasting and sales prediction accuracy. The sales forecast, or which product will be sold in the future and in what quantity, is carried out using Gradient Boosted Tree.

In general, visual clusters are preferred over large data sets; this is an attempt to take advantage of cluster techniques to reduce the mathematical complexity of small data sets. To identify the possibility of implementing the clustering technique in a small dataset, the wear observations of PLA/Cu composite samples printed using the Fused Deposition Model (FDM) is taken into consideration. In this study, the Self Organizing Map (SOM) tool as a non-supervised Neural Network (NN) is used to visualize the data. Here, SOM combinations with vector quantification and projection are used to identify or rank the wear machinability parameters on the new composite filament printed under different FDM conditions. The competitive layer in SOM will classify the given parameters of the wear machine (vectors) at any number of dimensions may be into several groups of layer neurons. The limitation of SOM is map size which cannot exceed 1000 units of training. However, for the small data set under consideration, the extent of these limits will not affect performance. The SOM algorithm developed for the study of wear provides the outlet within the acceptable range. In addition, the linear regression analysis is carried out for the output response to measure the wear characteristics of the machining observation.