Organizing Map Research Articles

Customer Segmentation of Credit Card Default by Self Organizing Map

In this paper we applied the technique of Self Organizing Map (SOM) to segment individuals based on their credit information. SOM is an unsupervised machine learning method that reduces data complexity and dimensionality while keeping sits original topology, which is superior to other dimension reduction methods especially when features in data have unclear nonlinear relations. Through this method we provide more clear and intuitive segmentation that other traditional methods cannot achieve.

Diffusion Tensor Imaging of Tendons and Ligaments at Ultra-High Magnetic Fields.

Injuries to tendons and ligaments are a common problem limiting daily activities and athletic participation across all age groups. Conventional magnetic resonance imaging (MRI) is reliable for detecting complete tears in tendons and ligaments, but it has difficulty identifying low-grade injuries due to poor contrast and low intensity signal. We describe recent MRI advances using ultra-high magnetic fields and very short time echoes which overcome many of the limitations of the low signal and the short T2 of connective tissues. Using diffusion and relaxometry measurements at 11.7 T, we measured the high field relaxation times, mean diffusivity, and the fractional anisotropy of rabbit semitendinosus tendons and medial collateral ligaments. We found that ultra-high field diffusion tensor imaging and tractography provide repeatable and quantitative maps of fiber organization, which could improve injury diagnosis and therapeutic treatments and assist in presurgical planning.

A Methodological Approach to Development of Circular Economy Options in Businesses

Three types of re-design processes are described in the development of circular economy options in businesses: 1) Re-design of the provided services considering changes in the roles of products, users, service, infrastructure, etc.; 2) Re-design of the value chain relations up-stream to suppliers and down-stream to customers and users; 3) Redesign of internal business organization considering necessary changes in tasks, competences, structures and technologies. These redesign processes have been developed as methodology within a research project based on cooperation with businesses in Denmark about analyses of potentials and barriers to circular economy as part of their business strategies. Circular economy is understood as slowing, narrowing and closing resource flows in order to increase resource effectiveness.Before the re-design considerations, initial mappings are done of material relations of the business based on an environmental mapping in life cycle perspective and an organizational analysis mapping of value chain relations, competitive position, innovation practices, user practices and relations to regulation and civil society. The article shows that circular economy can be relevant to businesses within many product and service areas, to both start-ups and existing businesses and to businesses with different roles in value chains, including manufacturing, retail and service. The article develops the concept of ‘circular economy journey’, understood as the activities carried out as part of development and analyses of potentials and barriers to circular economy through slowing down, narrowing and closing resource flows in a specific business and its value chains.

Segmentation Method for Pathological Brain Tumor and Accurate Detection using MRI

Image segmentation is challenging task in field of medical image processing. Magnetic resonance imaging is helpful to doctor for detection of human brain tumor within three sources of images (axil, corneal, sagittal). MR images are nosier and detection of brain tumor location as feature is more complicated. Level set methods have been applied but due to human interaction they are affected so appropriate contour has been generated in discontinuous regions and pathological human brain tumor portion highlighted after applying binarization, removing unessential objects; therefore contour has been generated. Then to classify tumor for segmentation hybrid Fuzzy K Mean-Self Organization Mapping (FKM-SOM) for variation of intensities is used. For improved segmented accuracy, classification has been performed, mainly features are extracted using Discrete Wavelet Transformation (DWT) then reduced using Principal Component Analysis (PCA). Thirteen features from every image of dataset have been classified for accuracy using Support Vector Machine (SVM) kernel classification (RBF, linear, polygon) so results have been achieved using evaluation parameters like Fscore, Precision, accuracy, specificity and recall.

Do organisations have a mission for mapping processes?

PurposeThe purpose of this paper is twofold: to identify and explore the reasons why organisations decide to use process mapping software (PMS) facilities in support of business process management (BPM); and to determine the objectives set by senior management for its introduction, and understand extent to which organisations achieve expected benefits.Design/methodology/approachThis paper uses an exploratory research design and investigates the elements of organisations’ objectives, implementation and evaluation of using PMS. The research data were collected through semi-structured interviews with business managers responsible for the implementation of PMS. The respondent organisations were selected from a range of industries who were using the same software.FindingsThe results of the research show that organisations do set objectives for using PMS, relevant to a wide range of business, operational and strategic objectives, dependant on the needs of the organisation. Additionally, the results show that some gain further advantages post-implementation, based on their PMS experience. Regarding explicit evaluation of their investment, organisations attempt this to a very limited extent; whilst recognising a broad a range of “softer” benefits.Research limitations/implicationsThis exploratory research has been conducted on a small range of organisations, all using the same software, therefore the results cannot be clearly generalizable. The research suggests organisations are making effective decisions regarding adopting PMS, further research on the evaluating its benefits could support better decision-making in the future.Practical implicationsThe practical implications of this research are for decision-makers in organisations recognising and understanding the strategic/operational benefits that could be achieved by implementing a software system for BPM.Originality/valueWhilst the use of process mapping of organisation’s operations is widespread the benefits achieved by organisations are only partially understood. Knowledge of the strategic impact of BPM is limited, as reported by numerous researchers. This research attempts to explore the context of organisations using such software, and point towards further approaches to its investigation.

Self Organizing Map of Artificial Neural Network for Groundwater Quality Classification in the F'kirina Plain : Oum El Bouaghi Province-NE of Algeria

Self Organizing Map of Artificial Neural Network for Groundwater Quality Classification in the F'kirina Plain : Oum El Bouaghi Province-NE of Algeria

Brain Tumor Segmentation using Watershed Technique and Self Organizing Maps

Objectives: To segment tumor with higher accuracy. Methods/Statistical Analysis: Noise removal is done with the help of Gabor filter as a preprocessing step. Skull stripping is done to remove non cerebral regions using thresholding and morphological operations. Segmentation using watershed algorithm is done, as it achieves exact location of outline. Unsupervised type of neural network i.e. self organizing maps is used for classification. Finding: It has been analyzed that by combining watershed and neural networks segmentation accuracy has been improved to 95.93%. The motive of the research is to segment the tumor with precision using computerized segmentation algorithm that can help physicians to analyze brain diseases and treatment can be started as soon as possible. Applications: The proposed technique can be used in image processing of brain tumor detection. Keywords: Brain Tumor Segmentation, Image Segmentation, Magnetic Resonance Imaging (MRI), Self Organizing Maps (SOM), Stationary Wavelet Transform (SWT)

Comparison between genetic algorithm and self organizing map to detect botnet network traffic

In Cyber Security world the botnet attacks are increasing. To detect botnet is a challenging task. Botnet is a group of computers connected in a coordinated fashion to do malicious activities. Many techniques have been developed and used to detect and prevent botnet traffic and the attacks. In this paper, a comparative study is done on Genetic Algorithm (GA) and Self Organizing Map (SOM) to detect the botnet network traffic. Both are soft computing techniques and used in this paper as data analytics system. GA is based on natural evolution process and SOM is an Artificial Neural Network type, uses unsupervised learning techniques. SOM uses neurons and classifies the data according to the neurons. Sample of KDD99 dataset is used as input to GA and SOM.

The Population health management as the road map of Italian Regional healthcare systems’ reforms for tackling chronic care

The Italian Health Ministry recently approved a national plan for tackling chronic care, which sets out the prevailing organisational models and the clinical governance guide lines for major conditions. On the top of these addresses, the plan identified the Population Health Management (PHM) approach as a road map for Regional Healthcare Services (RHS) and organizations. The PHM identifies five pillars: 1) demand analysis, segmentation and targeting; 2) set up of clinical pathways from early prevention to treatment and follow up; 3) identify models of care for chronic care management; 4) personalized care pathways; 5) Results, outcome evaluation and quality improvement.The paper aims to provide a national overview of the PHM development in different RHSs, starting from the five pillars as the key variables for analyzing regional patterns further reinforced by the institutional context analysis of reforms driven by the PHM attainments. For instance, the call for population-based system has accelerated yet the processes of merges and establishment of bigger LHAs as healthcare services commissioners serving population of almost 1 billion inhabitants, on average; yet the processes for centralizing the support management processes and programme planning within the regional governance. The paper analyses in depth five regional cases that firstly underwent the PHM model, detangling the policy and management strategies developed compared to the five pillars as well as the resources, tools, infrastructure and ICT technologies put in place and the models of care. The analysis provides insights from the lessons learnt by these RHSs and the challenges they are facing today, in order to understand the implementation matters with the national endowment of the PHM.

Automated Feature Identification and Classification Using Automated Feature Weighted Self Organizing Map (FWSOM)

This paper investigates the application of a novel method for classification called Feature Weighted Self Organizing Map (FWSOM) that analyses the topology information of a converged standard Self Organizing Map (SOM) to automatically guide the selection of important inputs during training for improved classification of data with redundant inputs, examined against two traditional approaches namely neural networks and Support Vector Machines (SVM) for the classification of EEG data as presented in previous work. In particular, the novel method looks to identify the features that are important for classification automatically, and in this way the important features can be used to improve the diagnostic ability of any of the above methods. The paper presents the results and shows how the automated identification of the important features successfully identified the important features in the dataset and how this results in an improvement of the classification results for all methods apart from linear discriminatory methods which cannot separate the underlying nonlinear relationship in the data. The FWSOM in addition to achieving higher classification accuracy has given insights into what features are important in the classification of each class (left and right-hand movements), and these are corroborated by already published work in this area.

Intelligent network assets supervision and control in Enedis

Recent years gave rise to major issues having an impact on the supervision and control domains for utilities, namely: (a) Automated metering, (b) Communication technologies based on IP, (c) Abandon of analogue communication networks by operators and manufacturers, (d) Digital control and supervision technologies in primary and secondary substations, (e) massive connection of distributed energy resources on medium and low voltage networks, (f) Smart grids and market flexibilities with a wider need of exchanges among actors, (g) Increase in the quantity of supervised equipment on the network with smart grids, (h) Need for strengthening cyber security for control systems. To efficiently address all these issues, Enedis launched a renovation project of supervision and control domains whose objectives tackle (i) design of equipment, including standardisation needs, (ii) implementation methodologies, (iii) assets management and maintenance, (iv) global configuration, (v) global supervision. Project organisation, priority issues, methodology (use case driven) and road map with major milestones are described in the study.

The Epstein-Barr Virus Regulome in Lymphoblastoid Cells

Epstein-Barr virus (EBV) transforms B cells to continuously proliferating lymphoblastoid cell lines (LCLs), which represent an experimental model for EBV-associated cancers. EBV nuclear antigens (EBNAs) and LMP1 are EBV transcriptional regulators that are essential for LCL establishment, proliferation, and survival. Starting with the 3D genome organization map of LCL, we constructed a comprehensive EBV regulome encompassing 1,992 viral/cellular genes and enhancers. Approximately 30% of genes essential for LCL growth were linked to EBV enhancers. Deleting EBNA2 sites significantly reduced their target gene expression. Additional EBV super-enhancer (ESE) targets included MCL1, IRF4, and EBF. MYC ESE looping to the transcriptional stat site of MYC was dependent on EBNAs. Deleting MYC ESEs greatly reduced MYC expression and LCL growth. EBNA3A/3C altered CDKN2A/B spatial organization to suppress senescence. EZH2 inhibition decreased the looping at the CDKN2A/B loci and reduced LCL growth. This study provides a comprehensive view of the spatial organization of chromatin during EBV-driven cellular transformation.

Mapping Patterns Achievement Based on CRISP-DM and Self Organizing Maps (SOM) Methods

Successful of regional development is a reflection of the good government policy. Many programs created by the local government every period but many programs stop without results. Therefore, we need to evaluation its government programs. Evaluation of government programs must do to prevent the failure of the programs. One way to evaluate the government programs is to collect the support data to see the data model and analyzed the data. In this research will conduct an evaluation on the achievement of RPJMD performance of Bali Province by using data mining. The process of data mining used the CRISP-DM method and Self Organizing Maps (SOM) for mapping the achievement patterns. The used data is RPJMD data in the 2013-2018 period. but the data used for data mining process only 3 years data that is 2014-2016 as a middle evaluation. That data clustered into five clusters. The final result of this research are 78% of assessment indicators in the RPJMD program are inconsistent position and 22% are in an inconsistent position. Moreover, there are 84 assessment indicators that have no reached the target. From that results of data, assessment mapping can use as the guidance of Bali Province to catch up the achievement of RPJMD programs and prepare the next strategies to support the success of the RPJMD program during the RPJMD period.

Nanoscale architecture of the Schizosaccharomyces pombe contractile ring.

The contractile ring is a complex molecular apparatus which physically divides many eukaryotic cells. Despite knowledge of its protein composition, the molecular architecture of the ring is not known. Here we have applied super-resolution microscopy and FRET to determine the nanoscale spatial organization of Schizosaccharomyces pombe contractile ring components relative to the plasma membrane. Similar to other membrane-tethered actin structures, we find proteins localize in specific layers relative to the membrane. The most membrane-proximal layer (0-80 nm) is composed of membrane-binding scaffolds, formin, and the tail of the essential myosin-II. An intermediate layer (80-160 nm) consists of a network of cytokinesis accessory proteins as well as multiple signaling components which influence cell division. Farthest from the membrane (160-350 nm) we find F-actin, the motor domains of myosins, and a major F-actin crosslinker. Circumferentially within the ring, multiple proteins proximal to the membrane form clusters of different sizes, while components farther from the membrane are uniformly distributed. This comprehensive organizational map provides a framework for understanding contractile ring function.

Virtual screening and repositioning of inconclusive molecules of beta-lactamase Bioassays—A data mining approach

This study focuses on the best possible way forward in utilizing inconclusive molecules of PubChem bioassays AID 1332, AID 434987 and AID 434955, which are related to beta-lactamase inhibitors of Mycobacterium tuberculosis (Mtb). The inadequacy in the experimental methods that were observed during the invitro screening resulted in an inconclusive dataset. This could be due to certain moieties present within the molecules. In order to reconsider such molecules, insilico methods can be suggested in place of invitro methods For instance, datamining and medicinal chemistrymethods: have been adopted to prioritise the inconclusive dataset into active or inactive molecules. These include the Random Forest algorithm for dataminning, Lilly MedChem rules for virtually screening out the promiscuity, and Self Organizing Maps (SOM) for clustering the active molecules and enlisting them for repositioning through the use of artificial neural networks. These repositioned molecules could then be prioritized for downstream drug discovery analysis.

MODELO DE DETECCIÓN DE INTRUSIONES EN SISTEMAS COMPUTACIONALES, REALIZANDO SELECCIÓN DE CARACTERÍSTICAS CON CHI SQUARE, ENTRENAMIENTO Y CLASIFICACIÓN CON GHSOM

Dado que la información se ha constituido en uno de los activos más valiosos de las organizaciones, es necesario salvaguardarla a través de diferentes estrategias de protección, con el fin de evitar accesos intrusivos o cualquier tipo de incidente que cause el deterioro y mal uso de la misma. Precisamente por ello, en este artículo se evalúa la eficiencia de un modelo de detección de intrusiones de red, utilizando métricas de sensibilidad, especificidad, precisión y exactitud, mediante un proceso de simulación que utiliza el DATASET NSL-KDD DARPA, y en concreto las características más relevantes con CHI SQUARE. Esto último a partir de una red neuronal que hace uso de un algoritmo de aprendizaje no supervisado y que se basa en mapas auto organizativos jerárquicos. Con todo ello se clasificó el tráfico de la red BI-CLASE de forma automática. Como resultado se encontró que el clasificador GHSOM utilizado con la técnica CHI SQUARE genera su mejor resultado a 15 características con precisión, sensibilidad, especificidad y exactitud

CLUSTERING OF HIGH RESOLUTION UAV IMAGERY TO IDENTIFY ESSENTIAL PLANTS USING SOM NEURAL NETWORK

The use of high-resolution remote sensing image data is necessary to distinguish essential plants with other plants. This study uses image data taken using Unmanned Aerial Vehicle (UAV) to identify essential plants especially citronella and kaffir lime. To distinguish the structure of essential plants with other objects used texture features extracted by wavelet daubechies method. The features that have been ekstract, then is grouped based on the proximity feature with the Self Organizing Map (SOM) Neural Network. Thus, objects that have similar features will clump together. The tests were conducted on two groups of data sets, where the first group data consisted of plants, buildings and vacant lots, while the second group data consisted only of plants. The results of testing of the first data group shows that the techniques can recognize the citronella plants among other objects, especially building objects and bare land with purity of 0.862745 and Silhouette Coeficient of 0.5520671. While in the second data group, the value of purity and Silhouette Coeficient decreased to 0.737705 and 0.161028. However, from the test of the second data group still shows that the method used can distinguish citronella crops to other plants.

Libraries, Archives, Museums

During the ancient period, Libraries, Archives and Museums had the same name, because they were the home of the Muses, but over the centuries, the three institutions have diversified. The museums display individual specimens; libraries and archives predominantly preserve and offer library objects and documents. While the manuscripts are kept, generally, in individual pieces, the books, after the invention of printing, exist in multiple copies, but there is no general bibliographic map to find specificity, duplication, or deficiencies. The digitization of works and editions of the past aggravates the problems of organization and bibliographic mapping, because it provides the sources of consultation and indexing, but ignores the imposing mass of written materials that represented the documentary basin of different ages, and who they are scattered in towns and historic European libraries.

Random forest and Self Organizing Maps application for analysis of pediatric fracture healing time of the lower limb

In this study, we examined the lower limb fracture healing time in children using random forest (RF) and Self Organizing feature Maps (SOM) methods. The study sample was obtained from the pediatric orthopedic unit in University Malaya Medical Centre. Radiographs of long bones of lower limb fractures involving the femur, tibia and fibula from children ages 0–12 years, with ages recorded from the date and time of initial injury. Inputs assessment extracted from radiographic images included the following features: type of fracture, angulation of the fracture, contact area percentage of the fracture, age, gender, bone type, type of fracture, and number of bone involved. RF is initially used to rank the most important variables that effecting bone healing time. Then, SOM was applied for analysis of the relationship between the selected variables with fracture healing time. Due to the limitation of available dataset, leave one out technique was applied to enhance the reliability of RF. Results showed that age and contact area percentage of fracture were identified as the most important variables in explaining the fracture healing time. RF and SOM applications have not been reported in the field of pediatric orthopedics. We concluded that the combination of RF and SOM techniques can be used to assist in the analysis of pediatric fracture healing time efficiently.

SOM-based partial labeling of imbalanced data stream

Data streams are found in many large-scale systems such as security, finance, and internet. In many of the data streams, the class distribution is imbalanced, and hence most of the traditional classification modeler fails to produce high accuracy for the samples from minority class. In addition, data streams are changing and the model should be updated to maintain the classification performance. However, obtaining the true class labels of the data samples is not an easy task since labeling process is extremely time-consuming and very often class labels are not available immediately after classification. The goal of this research is to reduce the labeling for an imbalanced data stream, and to produce high classification performance when compared to fully labeling setting. In an imbalanced data stream, the challenging part is to find and label minority class samples. In this paper, we propose RLS-SOM (Reduced labeled Samples-Self Organizing Map) framework for classification of the imbalanced data stream in a non-stationary environment. RLS-SOM locates the minority class samples in the feature space using SOM. It maintains an ensemble of the classifiers and builds a new model when the changes occur, using only partial labeled samples. In RLS-SOM, the classification results are obtained from the ensemble, as well as each individual model in the ensemble. An individual model classification results are selected over ensemble results, if its performance is higher than the ensemble's performance. This comparison is performed to improve the performance as there may be one model in the ensemble that produces higher performance than the ensemble. Our experimental results demonstrate that RLS-SOM obtains higher performance when it is compared with several partially labeling techniques over benchmark data sets. In addition, the experimental results with other state of the art fully labeling methods such as UCB, SERA, SEA, and Learn++.CDS shows RLS-SOM maintains equivalent classification performance by using 10–30% labeling, on average.