Evgheni Polisciuc

Why so many people? Explaining Nonhabitual Transport Overcrowding With Internet Data

Public transport smartcard data can be used for detection of large crowds. By comparing statistics on habitual behavior (e.g., average by time of day), one can specifically identify nonhabitual crowds, which are often very problematic for transport systems. While habitual overcrowding (e.g., peak hour) is well understood both by traffic managers and travelers, nonhabitual overcrowding hotspots can become even more disruptive and unpleasant because they are generally unexpected. By quickly understanding such cases, a transport manager can react and mitigate transport system disruptions. We propose a probabilistic data analysis model that breaks each nonhabitual overcrowding hotspot into a set of explanatory components. The potential explanatory components are initially retrieved from social networks and special events websites and then processed through text-analysis techniques. Finally, for each such component, the probabilistic model estimates a specific share in the total overcrowding counts. We first validate with synthetic data and then test our model with real data from the public transport system (EZLink) of Singapore, focused on three case study areas. We demonstrate that it is able to generate explanations that are intuitively plausible and consistent both locally (correlation coefficient, i.e., CC, from 85% to 99% for the three areas) and globally (CC from 41.2% to 83.9%). This model is directly applicable to any other domain sensitive to crowd formation due to large social events (e.g., communications, water, energy, waste).

Visualizing urban mobility

The goal of this research is understanding urban mobility through the visualization of the use of public transport systems. We focus on the visualization of anomalies regarding the number of passengers. To find patterns of use we analyze the raw data, which contains people counts for every bus stop in Coimbra. For each stop, and for each day of the week, we calculate the average number of passengers and its standard deviation for each 30 minute interval. This allows us to identify situations that deviate from the norm.

Flow Map of Products Transported among Warehouses and Supermarkets

Representing large amounts of data using flow maps involves dealing with the reduction of visual cluttering. This article presents a method for generating flow maps and visualizing products being transported from warehouse to supermarkets in a major retail company in Portugal. Our approach uses a swarm-based system to reduce visual clutter, bundling edges in an organic fashion and improving clarity. Additionally, the Dorling cartograms technique is applied to reduce overlapping of graphical elements that render locations in geographic space. Finally, different design decisions enable a multi-perspective visualization of the same

Time-series Application on Big Data - Visualization of Consumption in Supermarkets

The evolution of technology is changing how people work within organizations. Information about customer consumption leads to a new era of business intelligence, wherein Big Data is analyzed to improve business. In this project we apply information visualization in the context of Big Data for product’s consumption. The aim of this project is to visualize the evolution of consumption, to detect typical and periodic behaviors and emphasize the atypical ones. In this article we present our workflow—from finding periodic behaviors to create a final visualization using time-series and small-multiples techniques. With the final visualization we are able to show consumption behaviors and highlight the deviations from typical consumption days.

Arc and Swarm-based Representations of Customer’s Flows among Supermarkets

Representing large amounts of flows involves dealing with the representation of directionality and the reduction of visual cluttering. This article describes the application of two flow representation techniques to the visualization of transitions of customers among supermarkets over time. The first approach relies in arc representations together with a combination of methods to represent directionality of transitions. The other approach uses a swarm-based system in order to reduce visual clutter, bundling edges in an organic fashion and improving clarity.

Towards Partially Automatic Search of Edge Bundling Parameters

Edge bundling methods are used in flow maps and graphs to reduce the visual clutter, which is generated when representing complex and heterogeneous data. Nowadays, there are many edge bundling algorithms that have been successfully applied to a wide range of problems in graph representation. However, the majority of these methods are still difficult to use and apply on real world problems by the experts from other areas. This is due to the complexity of the algorithms and concepts behind them, as well as a strong dependence on their parametrization. In addition, the majority of edge bundling methods need to be fine-tuned when applied on different datasets. This paper presents a new approach that helps finding near-optimal parameters for solving such issues in edge bundling algorithms, regardless of the configuration of the input graph. Our method is based on evolutionary computation, allowing the users to find edge bundling solutions for their needs. In order to understand the effectiveness of the evolutionary algorithm in such kind of tasks, we performed experiments with automatic fitness functions, as well as with partially user-guided evolution. We tested our approach in the optimization of the parameters of two different edge bundling algorithms. Results are compared using objective criteria and a critical discussion of the obtained graphical solutions.

On the role of aesthetics in genetic algorithms applied to graph drawing

Despite the role that aesthetics plays in information visualization, it is often downplayed or ignored in favor of functionality. However, by understanding how graphical representations are perceived it is also possible to improve them and create more comprehensible data visualizations. Meaningful relationships and data patterns can easily get lost among the representation of large and complex datasets. Various methods have been created to reduce visual clutter by either sorting nodes to minimize the number of intersecting edges, or by grouping edges into bundles with clear directions. In information visualization, perception principles have started being integrated into evolutionary computation in order to solve aesthetic problems, as they are capable of looking for solutions that may be found beyond local optima. In this paper we present a study on the importance of aesthetics and how evolutionary approaches can be used to influence visualization. This is supplemented with two case studies involving the design of genetic algorithms for reducing visual clutter through edge crossing minimization and edge bundling parameter optimization.

Iso-edges for the Geovisualization of Consumptions

Data Visualization is emerging as a tool to understand and explore data in various ways. It enables us to interpret, synthesise, and present complex and vast amounts of information. We use Data Visualization to represent the evolution of consumptions in 729 hypermarkets and supermarkets of the biggest Portuguese retail company, for a time span of two years. We aim to apply an Information Visualization technique in order to study how, through Data Visualization, we can represent, synthesize, and interpret consumptions’ data. The geospatial data enables us to represent the consumptions in the different municipal districts and to analyze how consumptions evolve over time. To present this data, we apply an isoline approach, introducing a new technique called iso-edges. We also implement an interface for the exploration and analysis of the data.

Swarm-Based Edge Bundling Applied to Flow Mapping

Applying flow maps in large datasets involves dealing with the reduction of visual cluttering. Nowadays, a technique known as edge bundling, which is geometric in nature, is often applied to reduce visual clutter and create meaningful traces that highlight the main streams of flow. This article presents an alternative approach of edge bundling for generating flow maps. Our approach uses a swarm-based system to reduce visual clutter, bundling edges in an organic fashion and improving clarity. The method takes into account the properties of data, edges and nodes, to bundle edges in a meaningful way while tracing lines that do not interfere visually with the nodes. Additionally, the Dorling cartograms technique is applied to reduce overlapping of graphical elements that render locations in geographic space. The method is demonstrated with application in the analysis of the US migration flow and transportation of products among warehouses and supermarkets of a major retail company in Portugal.