Visual Data Mining Research Articles

GLAD: GLycan Array Dashboard, a visual analytics tool for glycan microarrays.

Traditional glycan microarray data is typically presented as excel files with limited visualization and interactivity. Thus, comparisons and analysis of glycan array data have been difficult, and there is need for a tool to facilitate data mining of glycan array data. GLAD (GLycan Array Dashboard) is a web-based tool to visualize, analyze, present and mine glycan microarray data. GLAD allows users to input multiple data files to create comparisons. GLAD extends the capability of the microarray data to produce more comparative visualizations in the form of grouped bar charts, heatmaps, calendar heatmaps, force graphs and correlation maps in order to analyze broad sets of samples. Additionally, it allows users to filter, sort and normalize the data and view glycan structures in an interactive manner, to facilitate faster visual data mining. GLAD is freely available for use on the Web at https://glycotoolkit.com/Tools/GLAD/ with all major modern browsers (Edge, Firefox, Chrome, Safari). Full documentation and video tutorials for GLAD can be found on https://glycotoolkit.com/GLAD.

Analysis of computer user behavior, security incidents and fraud using Self-Organizing Maps

This paper addresses several topics of great interest in computer security in recent years: computer users’ behavior, security incidents and fraud exposure on the Internet, due to their high economic and social cost. Traditional research has been based mainly on gathering information about security incidents and fraud through surveys. The novelty of the present study is given by the use of Self-Organizing Maps (SOMs), a visual data mining technique. SOMs are applied to two data sets acquired using two different methodologies for collecting data about computer security. First, a traditional online survey about fraud exposure, security and user behavior was used. Second, in addition to surveys, real data obtained from some of the users’ computers were also considered. In this way, the answers of the users can be benchmarked with the true situation of their computers. The surveys and the scanning of the computers were conducted in Spain from December 2013 to June 2014 by the National Observatory of Telecommunications and Information Society of the Spanish Ministry of Industry, performing 9181 surveys and 6350 computer scans in total. SOMs were applied to the datasets in their entirety first, and then a local analysis of the most interesting zones was carried out by zooming in on them. This approach allows for more detailed knowledge extraction. We conclude that SOMs enhance insight and interpretability about both data sets by untangling hidden relationships between variables, and could be helpful for similar future studies.

The affordance of virtual reality to enable the sensory representation of multi-dimensional data for immersive analytics: from experience to insight

Using the theory of affordance from perceptual psychology and through discussion of literature within visual data mining and immersive analytics, a position for the multi-sensory representation of big data using virtual reality (VR) is developed. While it would seem counter intuitive, information-dense virtual environments are theoretically easier to process than simplified graphic encoding—if there is alignment with human ecological perception of natural environments. Potentially, VR affords insight into patterns and anomalies through dynamic experience of data representations within interactive, kinaesthetic audio-visual virtual environments. To this end we articulate principles that can inform the development of VR applications for immersive analytics: a mimetic approach to data mapping that aligns spatial, aural and kinaesthetic attributes with abstractions of natural environments; layered with constructed features that complement natural structures; the use of cross-modal sensory mapping; a focus on intermediate levels of contrast; and the adaptation of naturally occurring distribution patterns for the granularity and distribution of data. While it appears problematic to directly translate visual data mining techniques to VR, the ecological approach to human perception discussed in this article provides a new framework for big data visualization researchers to consider.

Interactive Machine Learning by Visualization: A Small Data Solution.

Machine learning algorithms and traditional data mining process usually require a large volume of data to train the algorithm-specific models, with little or no user feedback during the model building process. Such a "big data" based automatic learning strategy is sometimes unrealistic for applications where data collection or processing is very expensive or difficult, such as in clinical trials. Furthermore, expert knowledge can be very valuable in the model building process in some fields such as biomedical sciences. In this paper, we propose a new visual analytics approach to interactive machine learning and visual data mining. In this approach, multi-dimensional data visualization techniques are employed to facilitate user interactions with the machine learning and mining process. This allows dynamic user feedback in different forms, such as data selection, data labeling, and data correction, to enhance the efficiency of model building. In particular, this approach can significantly reduce the amount of data required for training an accurate model, and therefore can be highly impactful for applications where large amount of data is hard to obtain. The proposed approach is tested on two application problems: the handwriting recognition (classification) problem and the human cognitive score prediction (regression) problem. Both experiments show that visualization supported interactive machine learning and data mining can achieve the same accuracy as an automatic process can with much smaller training data sets.

A feasible method for the division of ecological vulnerability and its driving forces in Southern Shaanxi

Southern Shaanxi is located in one of the water sources of the China's South-to-North Water Diversion Project. Evaluating ecological vulnerability can effectively supervise environmental changes and master evolving driving forces so as to guide the rational use and protection of ecological environment in regional water sources. Based on meteorological data, remote sensing images and statistical data, this study established an evaluation index system for ecological vulnerability in this special area. Taking advantage of visual expression and data mining capacity of geographical information system and remote sensing, a spatial principal component analysis method was introduced to evaluate the geospatial and temporal features of ecological vulnerability. This study established a feasible method to comprehensively assess the level of ecological vulnerability, and quantitatively analyze the driving forces that affected the ecological vulnerability in study area. The results indicated high levels of ecological vulnerability grade in the urban areas and the adjacent counties. With the accelerated urbanization, the ecological vulnerability index of the three major urban areas and their surrounding areas had gradually increasing ecological vulnerability index. The proportion of III vulnerable areas was always the largest area, which also led to an increase in the instability of the ecological environment. Over time, the most important driving force for ecological vulnerability of evaluation units in different regions was socio-economic factors, and environmental topographic factors were also important secondary factors for ecological vulnerability in Southern Shaanxi.

Artificial Neural Network-Based Decision Support System for Development of an Energy-Efficient Built Environment

Implementing energy-efficient solutions in a built environment is important for reaching international energy reduction targets. For advanced energy efficiency-related solutions, computer-based decision support systems are proposed and rapidly used in a variety of spheres relevant to a built environment. Present research proposes a novel artificial neural network-based decision support system for development of an energy-efficient built environment. The system was developed by integrating methods of the multiple criteria evaluation and multivariant design, determination of project utility and market value, and visual data mining by artificial neural networks. It enables a user to compose up to 100,000,000 combinations of the energy-efficient solutions, analyze strengths and weaknesses of a built environment projects, provide advice for stakeholders, and calculate market value and utility degree of the projects. For visual data mining, self-organizing maps (type neural networks) are used, which may influence the choosing of the final set of alternatives and criteria in the decision-making problem, taking into account the discovered similarities of alternatives or criteria. A system was validated by the real case study on the design of an energy-efficient individual house.

Combining Linear Pixel Unmixing and STARFM for Spatiotemporal Fusion of Gaofen-1 Wide Field of View Imagery and MODIS Imagery

Spatiotemporal fusion of remote sensing data is essential for generating high spatial and temporal resolution data by taking advantage of high spatial resolution and high temporal resolution imageries. At present, the Spatial and Temporal Adaptive Reflectance Fusion Model (STARFM) is one of the most widely used spatiotemporal fusion technologies of remote sensing data. However, the quality of data acquired by STARFM depends on temporal information from homogeneous land cover patches at the MODIS (Moderate Resolution Imaging Spectroradiometer) imagery, and the estimation accuracy of STARFM degrades in highly fragmentated and heterogeneous patches. To address this problem, we developed an innovative method to improve fusion accuracy, especially in areas of high heterogeneity, by combining linear pixel unmixing and STARFM. This method derived the input data of STARFM by downscaling the MODIS data with a linear spectral mixture model. Through this fusion method, the complement effect of the advantages of remote sensing information can be realized, and the multi-source remote sensing data can be realized for visual data mining. The developed fusion method was applied in Bosten Lake, the largest freshwater lake in China, and our analysis of results suggests that (1) after introducing the linear spectral mixture model, the fusion images illustrated improved spatial details to a certain extent and can be employed to identify small objects, as well as their texture distribution information; (2) for fragmented and highly heterogeneous areas, a stronger correlation between the predicted results and the real images was observed when compared to STARFM with small bias; and (3) the predicted red band and near infrared band can generate high-precision 16-m NDVI (Normalized Difference Vegetation Index) data with advantages in both spatial resolution and temporal resolution. The results are generally consistent with the Gaofen-1 wide field of view cameras (GF-1 WFV) NDVI in the same period and therefore can reflect the spatial distribution of NDVI in detail.

Use of the self-organising map network (SOMNet) as a decision support system for regional mental health planning

BackgroundDecision-making in mental health systems should be supported by the evidence-informed knowledge transfer of data. Since mental health systems are inherently complex, involving interactions between its structures, processes and outcomes, decision support systems (DSS) need to be developed using advanced computational methods and visual tools to allow full system analysis, whilst incorporating domain experts in the analysis process. In this study, we use a DSS model developed for interactive data mining and domain expert collaboration in the analysis of complex mental health systems to improve system knowledge and evidence-informed policy planning.MethodsWe combine an interactive visual data mining approach, the self-organising map network (SOMNet), with an operational expert knowledge approach, expert-based collaborative analysis (EbCA), to develop a DSS model. The SOMNet was applied to the analysis of healthcare patterns and indicators of three different regional mental health systems in Spain, comprising 106 small catchment areas and providing healthcare for over 9 million inhabitants. Based on the EbCA, the domain experts in the development team guided and evaluated the analytical processes and results. Another group of 13 domain experts in mental health systems planning and research evaluated the model based on the analytical information of the SOMNet approach for processing information and discovering knowledge in a real-world context. Through the evaluation, the domain experts assessed the feasibility and technology readiness level (TRL) of the DSS model.ResultsThe SOMNet, combined with the EbCA, effectively processed evidence-based information when analysing system outliers, explaining global and local patterns, and refining key performance indicators with their analytical interpretations. The evaluation results showed that the DSS model was feasible by the domain experts and reached level 7 of the TRL (system prototype demonstration in operational environment).ConclusionsThis study supports the benefits of combining health systems engineering (SOMNet) and expert knowledge (EbCA) to analyse the complexity of health systems research. The use of the SOMNet approach contributes to the demonstration of DSS for mental health planning in practice.

Data Visualization Indicator Disease (Malaria, Dengue Fever, and Measles) in The Year 2012-2015

The aim of this paper are: to create a data visualization that can assist the Government in evaluating the return on the development of health facilities in the region and province area in term of human resources for medical personnel, to help community knowing the amount of distribution of hospitals with medical personnel in the regional area and to map disease indicator in Indonesia. The issue of tackling health is still a major problem that is not resolved by the Government of Indonesia. There are three big things that become problems in the health sector in Indonesia: infrastructure has not been evenly distributed and less adequate, the lack of human resources professional health workforce, there is still a high number of deaths in the outbreak of infectious diseases. Data for the research are taken from BPS, in total 10,600 records after the Extract, Transform and Loading process. Time needed to convert several publications from PDF, to convert to CSV and then to MS Excel 3 weeks. The method used is Eight-step Data Visualization and Data Mining methodology. Tableau is chosen as a tool to create the data visualization because it can combine each dasboard inside a story interactive, easier for the user to analyze the data. The result is a story with 3 dashboards that can fulfill the requirement from BPS staff and has been tested with a satisfied result in the UAT (User Acceptance Test).
 Index Terms—Dashboard, data visualization, disease, malaria, Tableau
 REFERENCES
 [1] S. Arianto, Understanding of learning and others, 2008.
 [2] Rainer; Turban, Introduction to Information Systems, Danvers: John Wiley & Sons, Inc, 2007.
 [3] V. Friedman, Data Visualization Infographics, Monday Inspirition, 2008.
 [4] D. A. Keim, "Information Visualization and Visual Data Mining," IEEE Transactions on Visualization and Computer Graphics 8.1, pp. 1-8, 2002.
 [5] Connolly and Begg, Database Systems, Boston: Pearson Education, Inc, 2010.
 [6] E. Hariyanti, "Pengembangan Metodologi Pembangunan Information Dashboard Untuk Monitoring kinerja Organisasi," Konferensi dan Temu Nasional Teknologi Informasi dan Komunikasi untuk Indonesia, p. 1, 2008.
 [7] S. Darudiato, "Perancangan Data Warehouse Penjualan Untuk Mendukung Kebutuhan Informasi Eksekutif Cemerlang Skin Care," Seminar Nasional Informatika 2010, pp. E-353, 2010.

Visual data mining for crowd anomaly detection using artificial bacteria colony

This paper presents a novel method for global anomaly detection in crowded scenes. The optical flow of frames is used to extract the foreground of areas with people motions in the crowd in the form of layers. The optical flow between two frames generates one layer. The proposed method applies the metaheuristic of artificial bacteria colony as a robust algorithm to optimize the extracted layers. Artificial bacteria cover all regions of interest that have high movement between frames. The artificial bacteria colony adapts quickly to the most varied scenarios. Moreover, the algorithm has low sensibility to noise and to sudden changes in video lighting as captured by optical flow. The bacteria population of the colonies, its food storage and the colony’s centroid position regarding each optical flow layer, are used as input to train a Kohonen’s neural network. Once trained the network is able to detect specific events based on behavior patterns similarity, as produced by the bacteria colony during such events. Experiments are conducted on available public dataset. The achieved results show that the proposed method captures the dynamics of the crowd behavior successfully, revealing that the proposed scheme outperforms the available state-of-the-art algorithms for global anomaly detection.

Experience from Two Years of Visualizing Flash with SSDPlayer

Data visualization is a thriving field of computer science, with widespread impact on diverse scientific disciplines, from medicine and meteorology to visual data mining. Advances in large-scale storage systems, as well as low-level storage technology, played a significant role in accelerating the applicability and adoption of modern visualization techniques. Ironically, “the cobbler’s children have no shoes”: Researchers who wish to analyze storage systems and devices are usually limited to a variety of static histograms and basic displays. The dynamic nature of data movement on flash has motivated the introduction of SSDPlayer, a graphical tool for visualizing the various processes that cause data movement on solid-state drives (SSDs). In 2015, we used the initial version of SSDPlayer to demonstrate how visualization can assist researchers and developers in their understanding of modern, complex flash-based systems. While we continued to use SSDPlayer for analysis purposes, we found it extremely useful for education and presentation purposes as well. In this article, we describe our experience from two years of using, sharing, and extending SSDPlayer and how similar techniques can further advance storage systems research and education.

Strategic eco-design map of the complex products: toward visualisation of the design for environment

With growing sustainability and environmental concerns regarding the products, decision-makers and business managers need to integrate sustainability into business strategies and support it via systematic business processes and decision support tools. With the integration of the eco-efficiency attributes to the product development, more data should be analysed in engineering design. This integration also increases the complexity of the design process due to the large volume of data processing and diversity of the different attributes and features of the products. In this paper, we used the stock market metaphor to develop a visual data mining approach to the strategic eco-design assessment of the complex products. We presented a fresh framework using clustering and visualisation techniques to analyse the eco-efficiency profile of the different modules, components and parts of a complex product, and provide an efficient data exploration tool for decision-makers to facilitate processing of eco-design attributes, and strategic objectives at the same time. An illustrative example is provided to show the procedure of the application and the effectiveness of the proposed approach.

Multi-agent modelling of decision support systems based on visual data mining

Multi-agent modelling of decision support systems based on visual data mining

VdmR: Generating Web-Based Visual Data Mining Tools with R

The vdmR package generates web-based visual data mining tools by adding interactive functions to ggplot2 graphics. Brushing and linking between multiple plots is one of the main features of this package. Currently, scatter plots, histograms, parallel coordinate plots, and choropleth maps are supported in the vdmR package. In addition, identification on a plot is supported by linking the plot and the data table.

Visualisasi Perbandingan Anggaran Pendapatan Dan Belanja Daerah (APBD) Pemerintah Provinsi Kabupaten Dan Kota Di Indonesia Periode 2010-2014

Regional Income and Expenditure Budget (APBD) is a very important thing in the progress of a region. APBD is an indicator of public welfare level in a region. Data of APBD that is shared on the official website data.go.id is still hard to read and understood, and for that reason the author will compare the budget value of APBD in every province, district, and city by using visualization. The method the author used is Visual Data Mining by creating an APBD visualization dashboard according to provinces, districts, and cities. Tableau Software is used to create the dashboard because Tableau allows an interactive, easy-to-use dashboard for analyzing lots of data. Besides, Tableau is already supported by many platform such as web based, iPhone app, also Android app, and this application is one of the common for visualization so there are a lot of sources to get more information and to develop visualization. The result of this research could help the government in reevaluating the APBD financial budget in every region in Indonesia. This research can help the people to know the APBD budget applied in every region.
 Index Terms-Regional Income and Expenditure Budget (APBD), financial, visualization.

Web-igloo: a web based platform for multivariate data visualization.

The majority of data generated routinely from various experiments are essentially multivariate, often categorized with multiple experimental metadata. Analyzing such results with interactive visualizations often yields interesting and intuitive results which otherwise remains undisclosed. In this paper, we present Web-Igloo-a GUI based interactive 'feature decomposition independent' multivariate data visualization platform. Web-Igloo is likely to be a valuable contribution in the field of visual data mining, especially for researchers working with but not limited to multi-omics data. To demonstrate its utility, we have used a metagenomic dataset pertaining to the effect of multiple doses of antibiotic treatment on the human gut microbiome. http://metagenomics.atc.tcs.com/webigloo and http://121.241.184.233/webigloo [Freely available for academic use]. sharmila@atc.tcs.com. Supplementary data are available at Bioinformatics online.

Dimensionality Reduction for Visual Data Mining of Earth Observation Archives

Modern knowledge discovery systems, empowered by visual data exploration techniques, enable the user to discover and understand the data content. Considering patch-level processing, the visual exploration of Earth Observation archives aims to identify groups of items sharing similar semantic content. Each patch is further represented by certain descriptors, i.e., spectral signatures or Weber local descriptors, to capture structural signature. Later on, the content of the archive is illustrated by a 3-D projection of the high-dimensional space of the descriptors. Aspiring to prove the visual data mining potential, this letter intends to determine the capability of dimensionality reduction techniques to achieve a meaningful 3-D projection of the high-dimensional space. Several real-world data sets were used, i.e., University of California, Merced Land Use data set and a Landsat 7 Enhanced Thematic Mapper Plus image tiled into patches.

An analysis of wintertime navigational accidents in the Northern Baltic Sea

Navigational accidents in wintertime conditions occur relatively frequently, yet there is little systematic knowledge available about the circumstances under which these occur. This paper presents an analysis of navigational shipping accidents in the Northern Baltic Sea area which occurred in the period 2007–2013. The analysis is based on an integration of various data sources, aiming to reconstruct the accident conditions based on the best available data sources. Apart from basic accident information from the original accident databases, data from the Automatic Identification System is used to obtain insight in the operation type during which the accident occurred, as well as into other dynamic aspects of the accident scenario. Finally, atmospheric and sea ice data is used to reconstruct the navigational conditions under which the accidents occurred. The analysis aims to provide qualitative insights in patterns and outlier cases in the accidental conditions. Correspondingly, visual data mining is selected as analysis approach, because of its utility in obtaining qualitative knowledge from data sources through a combination of visualization techniques and human interaction with the data. Special attention is given to the strength of evidence of the identified accident patterns. The results are primarily useful for improving risk analyses focusing on oil spill risks in winter conditions and for developing realistic training scenarios for oil spill response operations.

Enhanced visual data mining process for dynamic decision-making

Data mining has great potential in extracting useful knowledge from large amount of temporal data for dynamic decision-making. Moreover, integrating visualization in data mining, known as visual data mining, allows combining the human ability of exploration with the analytical processing capacity of computers for effective problem solving. To design and develop visual data mining tools, an appropriate process must be followed. In this context, the goal of this paper is to enhance existing visualization processes by adapting it under the temporal dimension of data, the data mining tasks and the cognitive control aspects. The proposed process aims to model the visual data mining methods for supporting the dynamic decision-making. We illustrate the steps of our proposed process by considering the design of the visualization of the temporal association rules technique. This technique was developed to assist physicians to fight against nosocomial infections in the intensive care unit. Actually, an evaluation study in Situ was performed to assess the automatic prediction results as well as the visual representations. At the end, the test of the efficiency of our process using utility and usability evaluation shows satisfactory.

Volume-rendering on a 3D hyperwall: A molecular visualization platform for research, education and outreach

We present a unique platform for molecular visualization and design that uses novel subatomic feature detection software in tandem with 3D hyperwall visualization technology. We demonstrate the fleshing-out of pharmacophores in drug molecules, as well as reactive sites in catalysts, focusing on subatomic features. Topological analysis with picometer resolution, in conjunction with interactive volume-rendering of the Laplacian of the electronic charge density, leads to new insight into docking and catalysis. Visual data-mining is done efficiently and in parallel using a 4×4 3D hyperwall (a tiled array of 3D monitors driven independently by slave GPUs but displaying high-resolution, synchronized and functionally-related images). The visual texture of images for a wide variety of molecular systems are intuitive to experienced chemists but also appealing to neophytes, making the platform simultaneously useful as a tool for advanced research as well as for pedagogical and STEM education outreach purposes.