Navigation in large scale environments is challenging because it requires accurate local map and global relocation ability. We present a new hybrid metric-topological-semantic map structure, called MTS-map, that allow...
详细信息
ISBN:
(纸本)9781479969340
Navigation in large scale environments is challenging because it requires accurate local map and global relocation ability. We present a new hybrid metric-topological-semantic map structure, called MTS-map, that allows a fine metric-based navigation and fast coarse query-based localisation. It consists of local sub-maps connected through two topological layers at metric and semantic levels. Semantic information is used to build concise local graph-based descriptions of sub-maps. We propose a robust and efficient algorithm that relies on MTS-map structure and semantic description of sub-maps to relocate very fast. We combine the discriminative power of semantics with the robustness of an interpretation tree to compare the graphs very fast and outperform state-of-the-art-techniques. The proposed approach is tested on a challenging dataset composed of more than 13000 real world images where we demonstrate the ability to relocate within 0.12ms.
We discuss a system which provides a single, unified model of oil and gas reservoirs that is used across a range of disciplines from geologists to reservoir engineers. It has to store, manipulate and display reservoir...
详细信息
Genetic programming (GP) has shown promising results in interpretable feature extraction, but few works considered both classification accuracy and data visualization as objectives. Evaluating the extracted features b...
详细信息
ISBN:
(纸本)9781728162157
Genetic programming (GP) has shown promising results in interpretable feature extraction, but few works considered both classification accuracy and data visualization as objectives. Evaluating the extracted features based on the combination of accuracy measures and visualization measures can help to achieve the two objectives simultaneously. However, the exploitation of improper visualization measures and combination methods will decrease the classification accuracy. In this paper, a novel feature extraction method based on GP and non-overlap degree is proposed to extract interpretable features for high accuracy and visualization. And a novel function that maximizes the product of the accuracy of a linear classifier and the non-overlap degree is proposed to evaluate the extracted features. The proposed method, named GP-ANO, is compared with other methods on five medical datasets by six common machine learning methods. The experimental results demonstrate that the GP-ANO method outperforms other compared methods in terms of both classification accuracy and data visualization.
An approach to analyzing Streaming Big Data as it comes in while maintaining the proper context of past events is to employ contiguous visualizations with an increasingly aggressive aggregation degree. This allows for...
详细信息
ISBN:
(纸本)9781728180144
An approach to analyzing Streaming Big Data as it comes in while maintaining the proper context of past events is to employ contiguous visualizations with an increasingly aggressive aggregation degree. This allows for the most recent data to be displayed in detail, while older data is shown in an aggregated form according to how long ago it was received. However, the transitions applied between visualizations with different aggregations must not compromise the understandability of the data flow. Particularly, new data should be perceived considering the context established by older data, and the visualizations should not be perceived as independent or unconnected. In this paper, we present the first study on transitions between two contiguous visualizations, focusing on time series data. We developed several animated transitions between a scatter plot, where all data points are individually represented as they arrive, and other visualizations where data is displayed in an aggregated form. We then conducted a user evaluation to assess the most appealing and effective transitions that allow for the best comprehension of the displayed data for each visualization pair.
Narrative visualization has become a crucial tool in data presentation, merging storytelling with data visualization to convey complex information in an engaging and accessible manner. In this study, we review the des...
详细信息
Data in the natural sciences can often be dense and difficult to understand. The process of visualizing this data helps to alleviate these issues. In this paper, we demonstrate how using digital theater software built...
详细信息
ISBN:
(纸本)9781479906048;9781479906024
Data in the natural sciences can often be dense and difficult to understand. The process of visualizing this data helps to alleviate these issues. In this paper, we demonstrate how using digital theater software built for planetaria can be an appropriate medium in which to facilitate these visualizations;not only because of the software's complex and comprehensive graphics engine, but also as a means to convey the information this data is representing to the general public in way that is understandable, accessible and enjoyable. We exemplify the use of this technology through a case study where the simulation of water molecules in the Nyack Floodplain on the Middle Fork Flathead River, are visualized with dome technology.
In order to overcome the problems of low precision of visual information mining and long time consuming of visual view generation in traditional interactive informationvisualization model, this paper proposes the app...
详细信息
The investigation of the VAST Contest collection provided a valuable test for text mining techniques. Our group has focused on creating analytical tools to unveil relevant patterns and to aid with the content navigati...
详细信息
ISBN:
(纸本)9781424416592
The investigation of the VAST Contest collection provided a valuable test for text mining techniques. Our group has focused on creating analytical tools to unveil relevant patterns and to aid with the content navigation in such text collections. Our results show how such an approach, in combination with visualization techniques, can ease the discovery process especially when multiple tools founded on the same approach to data mining are used in complement to and in concert with one another.
In this paper, we investigate on the relationship between player experience and body movements in a non-physical 3D computer game. During an experiment, the participants played a series of short game sessions and rate...
详细信息
ISBN:
(纸本)9781479935475
In this paper, we investigate on the relationship between player experience and body movements in a non-physical 3D computer game. During an experiment, the participants played a series of short game sessions and rated their experience while their body movements were tracked using a depth camera. The data collected was analysed and a neural network was trained to find the mapping between player body movements, player in-game behaviour and player experience. The results reveal that some aspects of player experience, such as anxiety or challenge, can be detected with high accuracy (up to 81 %). Moreover, taking into account the playing context, the accuracy can be raised up to 86%. Following such a multi-modal approach, it is possible to estimate the player experience in a non-invasive fashion during the game and, based on this information, the game content could be adapted accordingly.
When using Aspect-Oriented Programming, it is sometimes difficult to determine at which join point an aspect executes. Similarly, when considering one join point, knowing which aspects will execute there and in what o...
详细信息
ISBN:
(纸本)9780769543987
When using Aspect-Oriented Programming, it is sometimes difficult to determine at which join point an aspect executes. Similarly, when considering one join point, knowing which aspects will execute there and in what order is non-trivial. This makes it difficult to understand how the application will behave. A number of visualizations have been proposed that attempt to provide support for such program understanding. However, they neither scale up to large code bases nor scale down to understanding what happens at a single join point. In this paper, we present AspectMaps - a visualization that scales in both directions, thanks to a multi-level selective structural zoom. We show how the use of AspectMaps allows for program understanding of code with aspects, revealing both a wealth of information of what can happen at one particular join point as well as allowing to see the "big picture" on a larger code base. We demonstrate the usefulness of AspectMaps on an example and present the results of a small user study that shows that AspectMaps outperforms other aspect visualization tools. Note: This paper heavily uses colors. Please use a color version to better understand the ideas presented here.
暂无评论