Masahiro Takatsuka's research while affiliated with The University of Sydney and other places

Publications (98)

Preprint
Graph-based clustering methods like spectral clustering and SpectralNet are very efficient in detecting clusters of non-convex shapes. Unlike the popular $k$-means, graph-based clustering methods do not assume that each cluster has a single mean. However, these methods need a graph where vertices in the same cluster are connected by edges of large...
Preprint
SpectralNet is a graph clustering method that uses neural network to find an embedding that separates the data. So far it was only used with $k$-nn graphs, which are usually constructed using a distance metric (e.g., Euclidean distance). $k$-nn graphs restrict the points to have a fixed number of neighbors regardless of the local statistics around...
Preprint
Partitioning trees are efficient data structures for $k$-nearest neighbor search. Machine learning libraries commonly use a special type of partitioning trees called $k$d-trees to perform $k$-nn search. Unfortunately, $k$d-trees can be ineffective in high dimensions because they need more tree levels to decrease the vector quantization (VQ) error....
Preprint
The recently emerged spectral clustering surpasses conventional clustering methods by detecting clusters of any shape without the convexity assumption. Unfortunately, with a computational complexity of $O(n^3)$, it was infeasible for multiple real applications, where $n$ could be large. This stimulates researchers to propose the approximate spectra...
Preprint
Spectral clustering became a popular choice for data clustering for its ability of uncovering clusters of different shapes. However, it is not always preferable over other clustering methods due to its computational demands. One of the effective ways to bypass these computational demands is to perform spectral clustering on a subset of points (data...
Preprint
Graph Neural Networks (GNNs) are increasingly becoming the favorite method for graph learning. They exploit the semi-supervised nature of deep learning, and they bypass computational bottlenecks associated with traditional graph learning methods. In addition to the feature matrix $X$, GNNs need an adjacency matrix $A$ to perform feature propagation...
Preprint
Approximate spectral clustering (ASC) was developed to overcome heavy computational demands of spectral clustering (SC). It maintains SC ability in predicting non-convex clusters. Since it involves a preprocessing step, ASC defines new similarity measures to assign weights on graph edges. Connectivity matrix (CONN) is an efficient similarity measur...
Preprint
Graph convolutional networks (GCNs) were a great step towards extending deep learning to unstructured data such as graphs. But GCNs still need a constructed graph to work with. To solve this problem, classical graphs such as $k$-nearest neighbor are usually used to initialize the GCN. Although it is computationally efficient to construct $k$-nn gra...
Article
SpectralNet is a graph clustering method that uses neural network to find an embedding that separates the data. So far it was only used with k-nn graphs, which are usually constructed using a distance metric (e.g., Euclidean distance). k-nn graphs restrict the points to have a fixed number of neighbors regardless of the local statistics around them...
Article
Graph-based clustering methods like spectral clustering and SpectralNet are very efficient in detecting clusters of non-convex shapes. Unlike the popular k-means, graph-based clustering methods do not assume that each cluster has a single mean. However, these methods need a graph where vertices in the same cluster are connected by edges of large we...
Article
Full-text available
Partitioning trees are efficient data structures for $k$ -nearest neighbor search. Machine learning libraries commonly use a special type of partitioning trees called $k\text{d}$ -trees to perform $k$ -nn search. Unfortunately, $k\text{d}$ -trees can be ineffective in high dimensions because they need more tree levels to decrease the vector...
Article
Spectral clustering became a popular choice for data clustering for its ability of uncovering clusters of different shapes. However, it is not always preferable over other clustering methods due to its computational demands. One of the effective ways to bypass these computational demands is to perform spectral clustering on a subset of points (data...
Article
Approximate spectral clustering (ASC) was developed to overcome heavy computational demands of spectral clustering (SC). It maintains SC ability in predicting non-convex clusters. Since it involves a preprocessing step, ASC defines new similarity measures to assign weights on graph edges. Connectivity matrix (CONN) is an efficient similarity measur...
Article
The recently emerged spectral clustering surpasses conventional clustering methods by detecting clusters of any shape without the convexity assumption. Unfortunately, with a computational complexity of O(n ³ ), it was infeasible for multiple real applications, where n could be large. This stimulates researchers to propose the approximate spectral c...
Article
People flow information brings us useful knowledge in various industrial and social fields including traffic, disaster prevention and marketing. However, it is still an open problem to develop effective people flow analysis techniques. We suppose compression and data mining techniques are especially important for analysis and visualization of large...
Article
This paper presents a crowd-powered efficient impression evaluation system, and a visualization system for ranked impression evaluation results. The former system shows a lot of content images to participants and consumes their inputs as impression evaluations. Here, this system preferentially selects images which are estimated as to be highly or p...
Conference Paper
Estimating output changes by input changes is the main task in causal analysis. In previous work, input and output Self-Organizing Maps (SOMs) were associated when conducting causal analysis of multivariate and nonlinear data. Based on the SOM association, a weight distribution of the output conditional on a given input was obtained over the output...
Article
People flow information brings us useful knowledge in various industrial and social fields including traffic, disaster prevention, and marketing. However, it is still an open problem to develop effective people flow analysis techniques. We considered compression and data mining techniques are especially important for analysis and visualization of l...
Article
Estimating output changes by input changes is the main task in causal analysis. In previous work, input and output Self-Organizing Maps (SOMs) were associated for causal analysis of multivariate and nonlinear data. Based on the association, a weight distribution of the output conditional on a given input was obtained over the output map space. Such...
Article
Visualization is an extremely useful tool to understand similarity of impressions among large number of tunes, or relationships of individual characteristics among artists, effectively in a short time. We expect chord progressions are beneficial in addition to acoustic features to understand the relationships among tunes; however, there have been f...
Conference Paper
Protein is the major component of the organism. A concave (pocket) on a protein surface is known to be thebest target for a drug to react. We previously presented astudy on distance analysis between pockets and amino acidresidue. We firstly identified pockets on the protein surfaceand then calculated distances between atoms of an amino acidresidue...
Conference Paper
Understanding causality is very important for problem solving in many areas. However, conducting causal analysis for multivariate and nonlinear data, unlabeled in nature, still faces many problems with existing methods. Artificial Neural Networks have been developed for such data analyses and Backpropagation Network has been most used to learn the...
Article
Information visualization is an effective approach to analyze time-varying data in our daily lives. We commonly represent time-varying values applying polyline charts or heatmaps; however, it is difficult to simultaneously observe short-term features of time-varying values and cluster transitions while applying either polyline charts or heatmaps. T...
Conference Paper
We commonly represent time-varying values as polyline charts or heatmaps; however, both type of techniques are difficult to simultaneously observe short-term features of time-varying values and cluster transitions. This poster proposes storyline-based visualization technique for consecutive numerical time-varying data. Storyline is a visualization...
Article
In this work, we introduce SentiCompass for exploring and comparing the sentiments of time-varying Twitter data. Our visualization design combines 2D psychology model of affect (i.e. emotion) with a time tunnel representation. To illustrate our visualization design, two case studies are conducted. They demonstrate the effectiveness of SentiCompass...
Article
In cartographic symbology, the evaluation of a symbol set's visual similarity is an important and frequently required task. Usually, after a set of map symbols are designed, the visual similarity of symbols need to be manually examined. To fully automate this task, in this paper, we propose two approaches based on entropy calculated on SOM surface...
Article
In this paper, we propose a data navigation approach for identifying the shape similarity of graphic logo images using enhanced SOM based visualization methods. Existing SOM based visualization methods have the limitation of not being able to show detailed local distance information and global similarity of data at the same time. Therefore, we prop...
Article
Real-world data sets produce unmanageably large contour trees because of noise. Contour Tree Simplification (CTS) would remove small scale branches, and maintain essential structure of data. Despite multiple measures of importance (MOIs) available, conventional CTS approaches often use a single MOI, which is not enough in evaluating the importance...
Conference Paper
Painting collections from the old masters are valuable cultural heritage of human history. Their artistic styles can be generally determined by their art periods. From analyzing and visualizing the relationships of different artistic styles, information can be found to facilitate art history studies. In this paper, we propose a Self-organizing Map...
Article
The continuously increasing amount of digital information available to computer users has led to the wide use of notification systems. Although these systems could support the management of information, they could also be an interruption to primary work. To minimize this interruption, a number of approaches, which notify the different categorical i...
Conference Paper
In the past, various problems in art imaging such as painter identification, painting image classification and retrieval were successfully solved by computer vision. However, very few works focused on analyzing the relationships among paintings of different artists. In this paper, we first define a set of image features in terms of abstract artisti...
Conference Paper
In order to support better design and understanding of categorical notification systems, we have investigated user's ability to recognize different visual cues that represent specific meanings. User's ability to remember the different meanings represented by the visual cues as well as discriminating those cues from each other determine their abilit...
Article
This paper investigates the appropriate region to place the remote scene in a synchronous distance learning environment to attain lecturer's awareness towards students' activities. We carried out experiments aimed to engineer the new design environment that improves current distance learning classrooms by finding the relationship between human fact...
Conference Paper
This paper presents an associated visualization model for the nonlinear and multivariate ecological data prediction processes. Estimating impacts of changes in environmental conditions on biological entities is one of the required ecological data analyses. For the causality analysis, it is desirable to explain complex relationships between influent...
Article
Real-world data sets produce unmanageably large contour trees because of noise and artifacts. It makes the contour tree impractical in data analysis and visualization. This paper proposes an importance-driven contour tree simplification approach which combines different measures of importance through an importance triangle to maximize advantages of...
Conference Paper
The Self-Organizing Maps (SOMs) are popular artificial neural networks that are often used for data analyses through clustering and visualisation. SOM’s mathematical model is inherently parallel. However, many implementations have not successfully exploited its parallelism because previous attempts often required cluster-like infrastructures. This...
Conference Paper
This paper presents an interactive hierarchical visualization system for an image retrieval application. This visualization system needs to present the similarities of images. Furthermore, it is required to provide an easy way to explore and navigate images' feature space at different levels of detail. Our system utilizes a Multi-layer Geodesic Sel...
Conference Paper
Spatialization methods create visualizations that allow users to analyze high-dimensional data in an intuitive manner and facilitates the extraction of meaningful information. Just as geographic maps are simplified representations of geographic spaces, these visualizations are essentially maps of abstract data spaces that are created through dimens...
Article
Transfer functions facilitate the volumetric data visualization by assigning optical properties to various data features and scalar values. Automation of transfer function specifications still remains a challenge in volume rendering. This paper presents an approach for automating transfer function generations by utilizing topological attributes der...
Conference Paper
Full-text available
Vision-based hand pointing interactive systems always assume implicitly that users’ physical pointing accuracy is perfect. However, this may not be the case. We investigated the accuracy provided by users in three pointing strategies. Result showed that pointing inaccuracy can be as high as 239mm at 3 metres away and suggest that the line-up method...
Conference Paper
Full-text available
dTouch is a novel 3D pointing system that allows interaction with large displays from the use of a single webcam. An initial evaluation demonstrating the feasibility of our pointing technique is presented. We compared our prototype with a popular 2D pointing technique, used in the EyeToy game for the PlayStation console, in a usability study. Resul...
Chapter
This paper presents structural relationship preservation as a technique for improving efficiency of volume rendering-based 3D data analysis. In the presented approach, a mapping between data and renderings is defined and volumetric object appearances are determined by structural relationships of interest in the data space. Two typical relationships...
Conference Paper
Multivariate networks are data sets that describe not only the relationships between a set of entities but also their attributes. In this paper, we present a new technique to determine the layout of a multivariate network using geodesic self-organizing map (GeoSOM). During the training process of a GeoSOM, graph distances are non-linearly combined...
Article
This paper firstly presents an approach of parallel coordinates based parameter control panel (PCP). The PCP is used to control parameters of focal region-based volume rendering (FRVR) during data analysis. It uses a parallel coordinates style interface. Different rendering parameters represented with nodes on each axis, and renditions based on rel...
Conference Paper
Collaborative user applications such as tabletop applications are a challenge to develop because user behaviour is affected not only by the software interface but also by group dynamics. Feedback loops abound in this system so even relatively minor changes in the software can lead to large changes in user behaviour. Designing such interfaces with a...
Article
The active use of Access Grid systems by many scientific and engineering communities over several years has uncovered a number of architectural and usability problems of this technology. After examining the system architecture of the current Access Grid and the recent trend in the instant messaging systems, we devised an alternative advanced collab...
Article
Data visualization has become an important tool for analyzing very complex data. In particular, spatial visualization enables users to view data in a intuitive manner. It has typically been used to externalize clusters and their relationships which exist in highly complex multidimensional data. We envisage that not only cluster formation and relati...
Article
The two-dimensional (2D) Self-Organizing Map (SOM) has a well-known "border effect". Several spherical SOMs which use lattices of the tessellated icosahedron have been proposed to solve this problem. However, existing data structures for such SOMs are either not space efficient or are time consuming when searching the neighborhood. We introduce a 2...
Conference Paper
Full-text available
Despite many years of research in the area of human computer interaction, there are still remarkably few computing platforms in existence that permit remote collaboration over various software applications in an intense manner. Visualisation and interaction on a collaborative access table (ViCAT) is a new project whose aim is to allow intense colla...
Article
We have previously introduced a two-phase approach to visualize a multivariate network(5). Positions of the graph nodes were de- termined by their attributes and binary connectivity (connected or not-connected). This paper presents the improved method: 1) graph distances are combined with the node attributes to improve the final positions of the gr...
Chapter
This chapter has described some of the new algorithms and technologies for information display. In most cases, these are untested outside universities and research laboratories. However, it is clear that a number of them will eventually find their way into commercial tools. As more novel concepts in information display are invented and tested, the...
Conference Paper
Full-text available
Large displays are everywhere. However, the computer mouse remains the most common interaction tool for such displays. We propose a new approach for fingertip interaction with large display systems using monocular computer vision. By taking into account the location of the user and the interaction area available, we can estimate an interaction surf...
Conference Paper
The complexity and size of data is rapidly increasing in modern science, business and engineering. This has resulted in increasing demands for more sophisticated data analysis methods. Multidimensional scaling has been used to visualize large high-dimensional datasets in the form of a map. Such maps are very intuitive for us, as we are familiar wit...
Conference Paper
A multivariate network is a graph whose nodes con- tain multi-dimensional attributes. We propose a method to visualize such a network using spherical Self-Organizing Map (SOM) and circular layout. The spherical SOM produced an initial graph layout by grouping nodes with similar attributes to adjacent areas on the sphere. The circular layout algorit...
Article
This paper discusses the benefits of a component-oriented visual software authoring system that is based on open standards and provides the seamless integration of various software tools in a unified environment. It employs a visual component assembly paradigm for ease of construction, Java™ and JavaBeans™ component architecture for the open enviro...
Article
Self-Organizing map (SOM) is a widely used tool to find clustering and also to visualize high dimensional data. Several spherical SOMs have been proposed to create a more accurate representation of the data by removing the "border effect". In this paper, we compare several spherical lattices for the purpose of implementation of a SOM. We then intro...
Conference Paper
The augmented desk is gaining popularity in recent HCI research. Its layout of a large horizontal screen on the desk enhances immersive and intense collaborative experiences. A responsive and unimpeded input interface is important for an efficient interaction in such an environment. In this paper, we developed a real-time stereo vision-based finger...
Conference Paper
Colours are three dimensional data. However, all commercial colour pickers project three-dimensional (3-D) colour spaces into two dimensional (2-D) palettes. The projection often results in a set of colours perceptually inappropriate to describe the data they present. This paper initially compares several popular 2-D colour pickers and then describ...
Conference Paper
Full-text available
This paper introduces a novel approach towards direct interaction with large display systems. Monocular computer vision is utilised to avoid restraints imposed by input devices. Tracking the user's head and determining the view frustum in real-time is one of the key processes in our proposed human-computer interaction system. We also proposed using...
Conference Paper
The Self-Organizing Map (SOM) is one of the popular Artificial Neural Networks which is a useful in clustering and visualizing complex high dimensional data. Conventional SOMs are based on the two-dimensional (2D) grid structure, which usually results in less accurate representation of the data. Several SOMs using spherical data structures have bee...
Conference Paper
Skeletal animation is a concept that has been used in the areas of motion pictures and computer games to create realistic motion for the animation of artic- ulated characters. Recent work has applied skeletal animation techniques from inverse kinematics to the field of graph interaction. The previous work intro- duced an interesting idea suggesting...
Conference Paper
Presenting large amounts of information in a limited screen space is a significant challenge in the field of Information Visualization. With the rapid development and growing use of small handheld devices such as PDAs this issue has become more important. Many Focus+Context techniques have been developed to address it but very few of them would eff...
Conference Paper
We present a new paradigm for achieving focus+context visualizations called smooth structural zooming, which varies the level of detail of the data in different areas of the visualization, as opposed to geometrically distorting the visualization or employing rapid zooming techniques. A smooth structural zooming technique for horizontal-vertical (h-...
Article
This paper describes a new type of low-cost interactive active range finder and illustrates the effect of introducing interactivity to the range-acquisition process. The new range finder consists of only one camera and a laser pointer to which three LEDs are attached. When a user scans the laser, the camera captures the image of spots (one from the...
Conference Paper
This paper discusses the benefits of a Component-Oriented visual software authoring system that provides the seamless integration of various software tools in a unified environment. It employs a visual component assembly paradigm for ease of construction, Java™ and JavaBeans™ component architecture for the open environment, and recursive developmen...
Conference Paper
The inclusion tree layout convention involves drawing trees as nested rectangles rather than the more common node-link diagrams. Finding good inclusion layouts presents some unique challenges, for example, the quantification of what is meant by the "size" of a rectangle. This paper empirically evaluates and investigates several rectangle size measu...
Article
The fundamental goal of the GeoVISTA Studio project is to improve geoscientific analysis by providing an environment that operationally integrates a wide range of analysis activities, including those both computationally and visually based. Improving the infrastructure used in analysis has far-reaching potential to better integrate human-based and...
Article
The main objective of the GeoVISTA Studio project is to improve geoscientific analysis by providing an environment that operationally integrates a wide range of analysis activities, including those both computationally and visually based.
Article
One barrier to the uptake of geocomputation is that, unlike GIS, it has no system or toolbox that provides easy access to useful functionality. This paper describes an experimental environment, GeoVISTA Studio, that attempts to address this shortcoming. Studio is a Java-based, visual programming environment that allows for the rapid development of...
Article
This paper describes a feasibility study of ''multi-agent oriented'' techniques on a 2-D and 3-D object recognition system. The main aim of the project is to develop an inspection supporting tool that understands objects in both 2-D and 3-D in a unified system. 2-D and 3-D worlds are mapped to each other via agent-like entities each of which holds...
Article
This paper describes a feasibility study of multi-agent oriented" techniques on a 2-D and 3-D object recognition system. The main aim of the project is to develop an inspection supporting tool that understands objects in both 2-D and 3-D in a uni ed system. 2-D and 3-D worlds are mapped to each other via agent-like entities each of which holds a co...
Article
This paper describes a system which encodes a free-form three-dimensional (3D) object using Artificial Neural Networks. The types of surface shapes which the system is able to handle include not only pre-defined surfaces such as simple piecewise quadric surfaces but also more complex free-form surfaces. The system utilizes two Self-Organizing Maps...
Article
Computer technologies have been rapidly improving throughout the last couple of decades, and they are now at the stage of allowing scientiststo carry out data analyses that deal with very complex and multivariate datasets. Moreover, there are growing numbersof researchers who wish to carry out such tasks in real-time. Traditional data analyses and...
Conference Paper
In recent times, the analysis of SOM (self-organising map) performance has concentrated on optimising the gain decay, rather than the size, form and decay of the neighbourhood function. We propose that the size, form and decay of region size plays a much more significant role in the learning, and especially in the development, of topographic featur...
Conference Paper
In this paper, empirical results are presented which suggest that size and rate of decay of region size plays a much more significant role in the learning, and especially the development of topographic feature maps. Using these results as a basis, a scheme for decaying region size during SOM training is proposed. The proposed technique provides nea...
Conference Paper
Full-text available
This paper describes object-centered symbolic representation and distributed matching strategies of 3D objects in a schematic form which occur in engineering drawings and maps. The object-centered representation has a hierarchical structure and is constructed from symbolic representations of schematics. With this representation, two independent sch...
Conference Paper
Full-text available
This paper describes a low-cost interactive active monocular range finder and illustrates the effect of introducing interactivity to the range acquisition process. The range finder consists of only one camera and a laser pointer to which three LEDs are attached. When a user scans the laser along surfaces of objects, the camera captures the image of...
Article
A free-form three-dimensional (3-D) object recognition system using artificial neural networks (ANNs) is described. The system is able to leam and recognize 3-D objects that have various surface shapes. The types of surface shapes the system is able to handle include not only predefined surfaces such as simple piecewise quadric surfaces but also mo...
Article
Cartographers have made a shift from pen and ink to digital production methods; but the digital revolution remains unfinished. Two important methods that digital production makes possible are the use of animation, and the use of three-dimensional representation. Animation, here, is considered to involve the use of motion, especially motion without...
Article
The rapid improvement in modern electrical engineering and computing technologies enables us to obtain massive amounts of geospatial data, and the complexity and diversity of the data continue to grow. This trend in data acquisition makes heavy demands on data analysis and visualization tools. The tools themselves need to evolve so that they can ha...
Article
DrawTop is a proxy program for assisting remote collab- oration through a sharable and annotatable desktop. It is useful for intense collaboration between remote participants. It exploits the existing remote desktop sharing provided by Virtual Network Computing (VNC). It not only supports multiple users using the VNC proxy but also provides a share...
Article
The contour tree is a topological abstraction of a scalar field. It represents the nesting relationships of connected compo- nents of isosurfaces or contours. The real-world data sets produce unmanageably large contour trees because of noise and artifacts. This makes the contour tree impractical for data analysis and visualization. A meaningful sim...
Article
With the abundance of high performance personal computers, rendering thousands to millions of polygons per second is an inexpensive task. In recent years, there have been advances in networking technologies that have enabled applications to become distributed over a network and many applications require this functionality. These applications can ra...
Article
In order to remove the "border eect", several spherical Self-Organizing Maps (SOM) based on the geodesic dome have been proposed. However, existing neighborhood searching methods on the geodesic dome are much more time-consuming than searching on the normal rectangular/hexagonal grid. In this paper, we present detailed descriptions of the algorithm...
Article
Full-text available
One barrier to the uptake of Geocomputatio n is that, unlike GIS, it has no system or toolbox that provides easy access to useful functionality. This paper describes an experimental environment, GeoVISTA Studio, that attempts to address this shortcoming. Studio is a Java -based, visual programming environment that allows for the rapid, programming...
Article
This paper provides an overview of a novel approach towards direct interaction with large display systems using natural hand pointing. Determining two points in 3D space and extracting the line of pointing is one of the key processes in our proposed human-computer interaction system. To avoid restraints imposed by input devices, our system uses mon...
Article
We present a new method for achieving Focus + Context vi- sualizations called smooth structural zooming, which varies the level of detail of the data being visualized, rather than geometrically distorting the visualization. We apply a pre- liminary smooth structural zooming technique to the hor- izontal{vertical (h{v) inclusion tree layout conventi...

Citations

... However, it is not enough to only use range queries to find the similar elements in some applications, such as social network, pattern recognition and information retrieval. At this time, clustering is commonly used for nearest neighbor searching [46][47][48][49]. For example, to settle the clustering problem on multi-view data, where every data point has multiple representations, Yuan et al. [49] propose a robust self-tuning multi-view clustering method to introduce a sum-of-norm loss function to settle the problem. ...
... We used this approach when the true number of clusters was known (e.g., synthetic data and data from UCI repository). However, when k was unknown like in image segmentation, we used an automatic detection scheme (Alshammari and Takatsuka, 2019). It starts by measuring the separation power of a given eigenvector. ...
... An alternative is to combine artificial neuronal networks (ANNs) with advanced information visualisation techniques in a single DSS. Based on the demand, the aim of this study is to assess a new DSS model using a novel approach, a self-organising map network (SOMNet) [21,22], combined with the EbCA [11] for the use of knowledgeguided mental health planning. The SOMNet was developed to facilitate interactive visual data mining of complex data to enable domain experts to (1) generate and verify hypotheses; (2) express interest through the process of KDD; (3) enhance information transferring between analysts and decision-makers; (4) specify information processing and present outcomes of analytical reasoning processes; and (5) identify hidden information and elicit tacit knowledge that can be formalised and transformed into rules for further data analysis [23][24][25]. ...
... An alternative is to combine artificial neuronal networks (ANNs) with advanced information visualisation techniques in a single DSS. Based on the demand, the aim of this study is to assess a new DSS model using a novel approach, a self-organising map network (SOMNet) [21,22], combined with the EbCA [11] for the use of knowledgeguided mental health planning. The SOMNet was developed to facilitate interactive visual data mining of complex data to enable domain experts to (1) generate and verify hypotheses; (2) express interest through the process of KDD; (3) enhance information transferring between analysts and decision-makers; (4) specify information processing and present outcomes of analytical reasoning processes; and (5) identify hidden information and elicit tacit knowledge that can be formalised and transformed into rules for further data analysis [23][24][25]. ...
... It was proposed in this work by examination of Principal Component Analysis (PCA), Independent Components Analysis (ICA), and Non-negative Matrix Factorization (NMF). Heatmaps and Wi-Fi, as displayed, (heat mapbased Wi-Fi fingerprinting: HMF) can further develop existing Wi-Fi fingerprinting plans like Radar and Horus [17]. This work concentrates on heat map-based timevarying data, visualization technique, and highlighting an intelligent instrument in order to show significant information and time ensures for shape fitting sizes of heatmap and spotlight on significant information things or time steps. ...
... For disease spreading, this encoding can be used to show contacts in the same ward and forms a key part of our approach. Research in storyline visualization has focused on optimizing the compactness of storyline visualizations (either automatic or users-assisted) [4,23,37,47,48,51,61,62,67,68], reducing crossings [25,32,70,79], plotting approaches [60], combining storylines with event-based methods [3], genealogical data [31], streaming and dynamic data [66,81], and contacts between living things or actors exhibiting similar behavior [52]. Reda et al. [52] is the closest approach to ours, but it needs to consider all contacts in the storyline. ...
... Linear arrangement (A3) [24] is the third proposed arrangement. Approaches using this arrangement [25][26][27][28][29] represent visualization of emotions, time, statistics [30], or topics. Peltonen et al. [27], for example, proposed a circle view of negative feedback for exploratory search. ...
... A notable exception is the CIELAB color model [6], which was designed to be largely perceptually uniform, meaning that the Euclidean distance between any two points should correspond to their relative perceptual difference. This makes it particularly useful for our application, since we want to visualize positions as colors, similar to what has previously been tried for self-organizing maps [7]. CIELAB represents colors using three values: perceptual lightness (L*) and two pairs of complementary colors, namely green-red (a*) and blue-yellow (b*). ...
... We asked them to pick animal stickers as cues for reflection, as opposed to having pre-selected animals or colored shapes. Prior work suggests that one shape or color cue is not inherently superior to another, because each individual interprets these shapes and color differently [67]. Therefore, as the system is targeted at children in the early stages of literacy development, allowing the children to preselect the notification shape may have better efficacy as opposed to generic cues. ...