A hierarchical latent variable model for data visualization

Visualization has proven to be a powerful and widely-applicable tool for the analysis and interpretation of multivariate data. Most visualization algorithms aim to find a projection from the data space down to a two-dimensional visualization space. However, for complex data sets living in a high-dimensional space, it is unlikely that a single two-dimensional projection can reveal all of the interesting structure. We therefore introduce a hierarchical visualization algorithm which allows the complete data set to be visualized at the top level, with clusters and subclusters of data points visualized at deeper levels. The algorithm is based on a hierarchical mixture of latent variable models, whose parameters are estimated using the expectation-maximization algorithm. We demonstrate the principle of the approach on a toy data set, and we then apply the algorithm to the visualization of a synthetic data set in 12 dimensions obtained from a simulation of multiphase flows in oil pipelines, and to data in 36 dimensions derived from satellite images     

Exploiting second-order dissimilarity representations for hierarchical clustering and visualization

Data Mining and Knowledge Discovery - The representation of objects is crucial for the learning process, often having a large impact on the application performance. The dissimilarity space (DS) is...     

A hierarchical SOM-based intrusion detection system

Purely based on a hierarchy of self-organizing feature maps (SOMs), an approach to network intrusion detection is investigated. Our principle interest is to establish just how far such an approach can be taken in practice. To do so, the KDD benchmark data set from the International Knowledge Discovery and Data Mining Tools Competition is employed. Extensive analysis is conducted in order to assess the significance of the features employed, the partitioning of training data and the complexity of the architecture. Contributions that follow from such a holistic evaluation of the SOM include recognizing that (1) best performance is achieved using a two-layer SOM hierarchy, based on all 41-features from the KDD data set. (2) Only 40% of the original training data is sufficient for training purposes. (3) The ‘Protocol’ feature provides the basis for a switching parameter, thus supporting modular solutions to the detection problem. The ensuing detector provides false positive and detection rates of 1.38% and 90.4% under test conditions; where this represents the best performance to date of a detector based on an unsupervised learning algorithm.     

A knowledge-based system for visualization design

Vista is a knowledge-based system that helps scientists design visualization techniques. It generates a technique for a given data set and lets users modify the design interactively using a compositional design methodology. To ensure the effectiveness of its designs, Vista uses many rules, mostly heuristic in nature, that were acquired through literature surveys and discussions with visualization experts. In general, Vista's design was based on research in graphical perception. It extends the design methodology of Automatic Presentation Tool (APT) (J.D. Mckinlay, 1986), a presentation tool for 2D graphics, to three dimensions. While Vista's primary function is to automatically generate an effective visualization technique design for a given data set, it also allows users to interactively modify this design and renders the resulting image using a variety of rendering algorithms     

Interactive visualization and analysis of hierarchical neuralprojections for data mining

Dimensionality reducing mappings, often also denoted as multidimensional scaling, are the basis for multivariate data projection and visual analysis in data mining. Topology and distance preserving mapping techniques-e.g., Kohonen's self-organizing feature map (SOM) or Sammon's nonlinear mapping (NLM)-are available to achieve multivariate data projections for the following interactive visual analysis process. For large data bases, however, NLM computation becomes intractable. Also, if additional data points or data sets are to be included in the projection, a complete recomputation of the mapping is required. In general, a neural network could learn the mapping and serve for arbitrary additional data projection. However, the computational costs would also be high, and convergence is not easily achieved. In this work, a convenient hierarchical neural projection approach is introduced, where first an unsupervised neural network-e.g., a SOM-quantizes the data base, followed by fast NLM mapping of the quantized data. In the second stage of the hierarchy, an enhancement of the NLM by a recall algorithm is applied. The training and application of a second neural network, which is learning the mapping by function approximation, is quantitatively compared with this new approach. Efficient interactive visualization and analysis techniques, exploiting the achieved hierarchical neural projection for data mining, are presented.     

A hierarchical taxonomic system for computer architectures

A novel hierarchical architectural taxonomic system that appears to possess the desirable characteristics of a good taxonomic scheme is presented. The author focuses on the endoarchitecture, i.e. the logical structure, control and behavior of the integrated system of hardware components. The starting point for this system is D.B. Skillicorn's scheme (see ibid., vol.21, no.11, p.46-57, 1988). However, the system both extends and departs from Skillicorn's scheme, using formulas inspired by chemical notation to classify computer architectures in a way that provides both predictive power and explanatory capabilities     

Comparison of visualization of optimal clustering using self-organizing map and growing hierarchical self-organizing map in cellular manufacturing system

The present research deals with the cell formation problem (CFP) of cellular manufacturing system which is a NP-hard problem thus, the development of optimum machine-part cell formation algorithms has always been the primary attraction in the design of cellular manufacturing system. In this proposed work, the self-organizing map (SOM) approach has been used which is able to project data from a high-dimensional space to a low-dimensional space so it is considered a visualized approach for explaining a complicated CFP data set. However, for a large data set with a high dimensionality, a traditional flat SOM seems difficult to further explain the concepts inside the clusters. We propose one such possible solution for a large CFP data set by using the SOM in a hierarchical manner known as growing hierarchical self-organizing map (GHSOM). In the present work, the two novel contributions using GHSOM are: the choice of optimum architecture through the minimum pattern units extracted at layer 1 for the respective threshold values and selection. Furthermore, the experimental results clearly indicated that the machine-part visual clustering using GHSOM can be successfully applied in identifying a cohesive set of part family that is processed by a machine group. Computational experience specifically with the proposed GHSOM algorithm, on a set of 15 CFP problems from the literature, has shown that it performs remarkably well. The GHSOM algorithm obtained solutions that are at least as good as the ones found the literature. For 75% of the cell formation problems, the GHSOM algorithm improved the goodness of cell formation through GTE performance measure using SOM as well as best one from the literature, in some cases by as much as more than 12.81% (GTE). Thus, comparing the results of the experiment in this paper with the SOM and GHSOM using the paired t-test it has been revealed that the GHSOM approach performed better than the SOM approach so far the group technology efficiency (GTE) measures of performance of the goodness of cell formation is concerned.     

A BIM-based visualization and warning system for fire rescue

Structural fires are common disasters. In Taiwan, about 100 firefighters die during fire rescues each year, primarily because they are unaware of the causes of the fire and unfamiliar with the location’s environment. Meanwhile, evacuees often die in the panic of evacuation. To solve these problems, this research proposes a Building Information Modeling (BIM)-based visualization and warning system for fire rescue. A fire dynamics simulator (FDS) simulates various conditions of structural fires in conjunction with the visualization and integration properties of BIM, and the simulation results for temperature, carbon monoxide, and visibility can be integrated and presented in the BIM model for briefing purposes before rescue operations begin. In addition, this research integrates Internet of Things (IoT) technology, which allows real-time situation monitoring. In the event of a fire, the BIM model will immediately display the situation of the fire scene and control LED escape route pointers according to the actual situation. The primary objective of this system is to provide useful information to firefighters such that they can be aware of the fire’s environment and create an effective rescue plan. Moreover, the automated LED escape route pointer may assist the building’s occupants to escape, provide the firefighters with valuable information, and allow them quickly to discover hazards so that the number of casualties can be minimized.     

A cortex-like learning machine for temporal hierarchical pattern clustering, detection, and recognition

A learning machine, called a clustering interpreting probabilistic associative memory (CIPAM), is proposed. CIPAM consists of a clusterer and an interpreter. The clusterer is a recurrent hierarchical neural network of unsupervised processing units (UPUs). The interpreter is a number of supervised processing units (SPUs) that branch out from the clusterer. Each processing unit (PU), UPU or SPU, comprises “dendritic encoders” for encoding inputs to the PU, “synapses” for storing resultant codes, a “nonspiking neuron” for generating inhibitory graded signals to modulate neighboring spiking neurons, “spiking neurons” for computing the subjective probability distribution (SPD) or the membership function, in the sense of fuzzy logic, of the label of said inputs to the PU and generating spike trains with the SPD or membership function as the firing rates, and a masking matrix for maximizing generalization. While UPUs employ unsupervised covariance learning mechanisms, SPUs employ supervised ones. They both also have unsupervised accumulation learning mechanisms. The clusterer of CIPAM clusters temporal and spatial data. The interpreter interprets the resultant clusters, effecting detection and recognition of temporal and hierarchical causes.     

Extracting hierarchical spatial and temporal features for human action recognition

Human action recognition is a challenging computer vision task and many efforts have been made to improve the performance. Most previous work has concentrated on the hand-crafted features or spatial-temporal features learned from multiple contiguous frames. In this paper, we present a dual-channel model to decouple the spatial and temporal feature extraction. More specifically, we propose to capture the complementary static form information from single frame and dynamic motion information from multi-frame differences in two separate channels. In both channels we use two stacked classical subspace networks to learn hierarchical representations, which are subsequently fused for action recognition. Our model is trained and evaluated on three typical benchmarks: KTH, UCF and Hollywood2 datasets. The experimental results illustrate that our approach achieves comparable performances to the state-of-the-art methods. In addition, both feature analysis and control experiments are also carried out to demonstrate the effectiveness of the proposed approach for feature extraction and thereby action recognition.     

The effects of hierarchical structure and visualization ability on computerized information retrieval

This study examined the effects of visualization ability on search time in databases with different hierarchical structures. It was designed to determine whether manipulation of the hierarchical structures of information could accommodate the needs of low‐visualization ability users. The task consisted of finding specific “target” files in each of the four different data structures that varied in depth of organization. The study found the expected effects of organizational structure and visualization ability on retrieval time from the database. It did not find any evidence of an interaction between the two variables on performance. The results suggest that individual differences in performance are the result of differences in perceptual speed and that altering the structure of the information in a database is not an effective way to accommodate to low‐visualization ability users.     

A hierarchical expert system for computer process control

This paper reports on the design and implementation of an expert system for computer process control (HESCPC). The complexity of the expertise necessary for computer process control applications requires that the expert system architecture be structured into a hierarchy of classes of specialized experts. The architecture of HESCPC integrates four classes of expert systems: operator/manager companion expert class, control system algorithm design expert class, hardware expert class, and software expert class. The paper is concerned with the design and implementation of the general system architecture, an operator adviser expert for a nuclear power plant and a control system designer expert using a state space feedback approach. Although the design and implementation aspects of all experts are discussed, the emphasis is on the latter.

At this stage of the HESCPC development, the declarative knowledge represented by 423 metarules and 1261 rules is distributed on a hierarchical structure among 20 experts on different levels of the hierarchy which are able to communicate among themselves to solve difficult control problems.

Examples of control system design sessions of linear mono and multivariable systems using feedback state space approach are given. A run time of an operator-adviser data-driven expert system for a nuclear plant is also presented.     

A hierarchical knowledge based system for airplane classification

Airplane classification is used as an application domain to illustrate how hierarchical reasoning on large knowledge bases can be implemented. The knowledge base is organized as a two-dimensional hierarchy: one dimension corresponds to the levels of complexity often seen in computer vision, and the other dimension corresponds to the complexity of hypothesis used in the reasoning process. Reasoning proceeds top-down, from more abstract levels with fewer details toward levels with more details. Whenever possible, with the help of domain knowledge, decision is taken at a higher level, which significantly reduces processing time. A software package called RuBICS (Rule-Based Image Classification System) is described, and some examples of airplane classification are shown     

A hierarchical language identification system for Indian languages

Automatic spoken Language IDentification (LID) is the task of identifying the language from a short duration of speech signal uttered by an unknown speaker. In this work, an attempt has been made to develop a two level language identification system for Indian languages using acoustic features. In the first level, the system identifies the family of the spoken language, and then it is fed to the second level which aims at identifying the particular language in the corresponding family. The performance of the system is analyzed for various acoustic features and different classifiers. The suitable acoustic feature and the pattern classification model are suggested for effective identification of Indian languages. The system has been modeled using hidden Markov model (HMM), Gaussian mixture model (GMM) and artificial neural networks (ANN). We studied the discriminative power of the system for the features mel frequency cepstral coefficients (MFCC), MFCC with delta and acceleration coefficients and shifted delta cepstral (SDC) coefficients. Then the LID performance as a function of the different training and testing set sizes has been studied. To carry out the experiments, a new database has been created for 9 Indian languages. It is shown that GMM based LID system using MFCC with delta and acceleration coefficients is performing well with 80.56% accuracy. The performance of GMM based LID system with SDC is also considerable.     

ASK-GraphView: A large scale graph visualization system

We describe ASK-GraphView, a node-link-based graph visualization system that allows clustering and interactive navigation of large graphs, ranging in size up to 16 million edges. The system uses a scalable architecture and a series of increasingly sophisticated clustering algorithms to construct a hierarchy on an arbitrary, weighted undirected input graph. By lowering the interactivity requirements we can scale to substantially bigger graphs. The user is allowed to navigate this hierarchy in a top down manner by interactively expanding individual clusters. ASK-GraphView also provides facilities for filtering and coloring, annotation and cluster labeling     

A watershed data management and visualization system using code-first approach

With rapid growth of population and economic development in northwest China, water resource over-exploitation has led to severe deterioration of watershed ecosystems. In this study, we developed a hydrological information platform (called Watershed Datacenter System) for sharing, managing, analyzing and visualizing a diverse range of hydrologic data collected at watershed scale. This platform can help investigators and geotechnical experts to conduct watershed researches with the intensive data convenience. This Watershed Datacenter system (WDC) is developed with Entity Framework 6 (EF6) approach which based on Model-View-Controller (MVC) architecture pattern and several other useful technologies, such as ArcGIS API and Responsive web design. Observation Database Model (ODM), hydrological model as a service, Web services and time-series analysis tools are seamlessly integrated into our WDC with the help of open source HIS (Hydrologic Information System) from the CUAHSI (Consortium of Universities for the Advancement of Hydrologic Science, Inc.). The results demonstrate that the WDC offers quite a few advantageous features for managing and analyzing of the data for watershed research.     

A GIS-based borehole data management and 3D visualization system

The use of subsurface data for problem solving is limited in part by the freedom the user has in their choice of data structures. If a user is allowed to work with the data in a familiar way, they can spend more time performing analysis tasks and less time restructuring data, thus increasing productivity and reducing the risks associated with a series of data modification cycles. Borehole information system (BoreIS) is based upon this principle. Design was guided by interviews with geologists who were targeted as potential users of the software, and BoreIS was developed as an extension to ESRI's ArcScene three-dimensional (3D) GIS environment. BoreIS uses borehole or well data supplied by the user to develop a 3D GIS representation which can be queried, visualized, and analysed. By asking relevant questions about data stored in Excel spreadsheets, BoreIS can automate many high-level GIS functions so that an inexperienced GIS user can still use the system. By matching table elements to spatially and geologically significant terms through the interactive setup, users can work with the data more closely matched to the geological problem domain. This allows the novice user to use powerful GIS functions to discover spatial patterns in their data. BoreIS’ interactive manipulation of terms in complex queries, simple addition of contoured surfaces, and masking by lithology or formation helps geologists find spatial patterns in their data, beyond the limits of data tables and flat maps.     

A sequential method for system identification in hierarchical structure

Implicit in all of hierarchical systems theory is the idea that it is generally easier to deal with several low order systems than with one system of high order. The basic idea of hierarchical systems theory is to decompose a large dimensional system into smaller dimensioned sub-systems in such a way that the overall system objectives can be met.

This paper is concerned with the application of hierarchical system theory to the identification problem. Specifically, the equations associated with a given identification problem are recast such that they may be decomposed into infimal subproblems of system identification which can be coordinated using hierarchical systems theory.

The maximum a posteriori approach to system identification is taken. This leads to a two point boundary value problem solution which determines optimum state and parameter estimates and estimates of any unknown prior statistics. Invariant imbedding is used to resolve this two point boundary value problem such that a recursive or sequential solution to the identification problem is obtained. Several examples indicate the use of the identification algorithms.     

Dynamic aspect-based rating system and visualization

User Modeling and User-Adapted Interaction - With an increasing number of product reviews available online, it has become impractical for potential customers to perceive all the available reviews...