Visual data analysis (VDA) is a visualization approach that combines vector and raster graphics to provide insights into various aspects of multidimensional datasets. VDA methods have found application in aerospace en...
详细信息
ISBN:
(纸本)0818620838
Visual data analysis (VDA) is a visualization approach that combines vector and raster graphics to provide insights into various aspects of multidimensional datasets. VDA methods have found application in aerospace engineering research. VDA is being used to develop nondestructive evaluation testing techniques for graphite epoxy composites by providing insights into stress waves propagating through them. Visual data analysis was used to analyze stress wave propagation, determine the origin of an unexplained wave distortion, and create a theoretical model to eliminate the distortion utilizing mathematical modeling.
The rapid development of computer technology has brought promises for the education science, especially English teaching. In order to improve the current English teaching research, the paper recommends data visualizat...
详细信息
ISBN:
(纸本)9781424435197
The rapid development of computer technology has brought promises for the education science, especially English teaching. In order to improve the current English teaching research, the paper recommends data visualization technology as a valuable tool and demonstrates it with college students' scores in an English test. During the process, data of the students' scores are transformed and displayed with graphics, and analyzed. In view of the visualization findings, the paper has put forward some advice to guide future English teaching.
Users of traditional web search engines commonly find it difficult to evaluate the results of their web searches. We suggest the use of informationvisualization and interactive visual manipulation as methods for impr...
详细信息
ISBN:
(纸本)9780769527475
Users of traditional web search engines commonly find it difficult to evaluate the results of their web searches. We suggest the use of informationvisualization and interactive visual manipulation as methods for improving the ability of users to evaluate the results of a web search. In this paper, we present the results of a user study that compared the search results interface provided by Google to that of two systems we have developed: HotMap and Concept Highlighter We found that users were able to perform their searches faster with HotMap, were able to find more relevant documents with Concept Highlighter and generally ranked these interfaces higher than Google with respect to subjective measures. When given a choice between these interfaces, participants ranked HotMap the highest, followed by Google and Concept Highlighter These results indicate that even though the list-based representation of search results are common among search engines, visual and interactive interfaces to web search results can be more efficient, effective, and satisfying to the users.
Nowadays user-generated content is growing in a digital world, where many individuals can post texts about various products in order to express their feedback. Reviews about products are critical as they guide others ...
详细信息
ISBN:
(纸本)9781728101088
Nowadays user-generated content is growing in a digital world, where many individuals can post texts about various products in order to express their feedback. Reviews about products are critical as they guide others to use it or not which affect the production profit, and popularity. Amazon is one of the companies that provide reviews of users regarding all its products. Since reviews are textual and varying;an interactive representation would be supportive to users through summarizing opinions and providing feedback. In this paper, a visual analytics tool proposed;as a dashboard;a user-friendly analysis of books' reviews on Amazon. Interactive Packed bubbles, Linear chart, Stacked bars, and Word-cloud are four visualization techniques incorporated together enabling users to explore relationships between multiple objectives at the same time in an interactive manner. Besides, visual sentiment analysis of opinions extracted from the user reviews of books whether positive, neutral or negative is provided to support users' decision.
Deep learning is actively used in a wide range of fields for scientific discovery. To effectively apply deep learning to a particular problem, it is important to select an appropriate network architecture and other hy...
详细信息
ISBN:
(纸本)9781728108582
Deep learning is actively used in a wide range of fields for scientific discovery. To effectively apply deep learning to a particular problem, it is important to select an appropriate network architecture and other hyper-parameters (at each layer). Evolving architectures and hyper-parameters using a genetic algorithm is one current approach to search the huge space of all possible configurations to find those more optimal for the problem. However, examining an evolutionary process and tuning the genetic algorithm are challenging, pushing most users to treat the process as a black box. To address this challenge, we propose a visualization system for evolutionary neural networks for deep learning. The key feature of our visualization system is to provide a visual analytics environment for evaluating a genetic algorithm in order to improve the underlying operations to reduce time to find good solutions. Our system is able to not only visualize how a genetic algorithm traverses its search space but also allows users to examine evolving networks in-depth to get insights to improve performance through interactive visualization components.
Within metagenomics, "Contig Binning" is an important step in the process of reconstructing genomes of species in mixed cultures and environmental samples. We present an interactive visual environment which ...
详细信息
ISBN:
(纸本)9781479962273
Within metagenomics, "Contig Binning" is an important step in the process of reconstructing genomes of species in mixed cultures and environmental samples. We present an interactive visual environment which enables a biologist to statistically analyze the multiple dimensions of data that are typically used during binning, and integrate and compare the results of various binning methods. Our system features a web-based parallel coordinate visualization at the front end and a R server back end for analysis and semi-supervised clustering of contig data.
In this paper we present a demonstrator that visualizes simulations of sonar performance in a geographical information system, based on detailed bottom topography. The sonar performance predictions are calculated by t...
详细信息
ISBN:
(纸本)9781479900008;9781479900022
In this paper we present a demonstrator that visualizes simulations of sonar performance in a geographical information system, based on detailed bottom topography. The sonar performance predictions are calculated by the acoustic ray trace model LYBIN, which will be described briefly. The main purpose of this paper is to demonstrate how visualization of acoustic data in a geographical information system can improve sonar operations, by obtaining better knowledge of how the marine environment influences the sonar performance. We will point out how to make sonar performance modelling tools both easier to use and how to improve the user intelligibility.
Most of today's commercial companies heavily rely on social media and community management tools to interact with their clients and analyze their online behaviour. Nonetheless, these tools still lack evolved data ...
详细信息
ISBN:
(纸本)9781509018574
Most of today's commercial companies heavily rely on social media and community management tools to interact with their clients and analyze their online behaviour. Nonetheless, these tools still lack evolved data mining and visualization features to tailor the analysis in order to support useful marketing decisions. We present an original methodology that aims at formalizing the marketing need of the company and develop a tool that can support it. The methodology is derived from the Cross-Industry Standard Process for Data Mining (CRISP-DM) and includes additional steps dedicated to the design and development of visualizations of mined data. We followed the methodology in two use cases with Swiss companies. First, we developed a prototype that aims at understanding the needs of tourists based on Flickr and Instagram data. In that use case, we extend the existing literature by enriching hashtags analysis methods with a semantic network based on Linked Data. Second, we analyzed internal customer data of an online discount retailer to help them define guerilla marketing measures. We report on the challenges of integrating Facebook data in the process. Informal feedback from domain experts confirms the strong potential of such advanced analytic features based on social data to inform marketing decisions.
We have developed a system that can semi automatically extract numerical and named entity sets from a large number of Japanese documents and can create various kinds of tables and graphs. In our experiments, our syste...
详细信息
ISBN:
(纸本)9781424427796
We have developed a system that can semi automatically extract numerical and named entity sets from a large number of Japanese documents and can create various kinds of tables and graphs. In our experiments, our system has semiautomatically created approximately 300 kinds of graphs and tables at precisions of 0.2-0.8 with only two hours of manual preparation from a two-year stack of newspapers articles. Note that these newspaper articles contained a large quantity of data, and all of them could not be read or checked manually in such a short amount of time. From this perspective, we concluded that our system is useful and convenient for extracting information from a large number of documents.
Event-based encoding reduces the amount of generated data while keeping relevant information in the measured magnitude. While this encoding is mostly associated with spiking neuromorphic systems, it can be used in a b...
详细信息
ISBN:
(纸本)9781509028702
Event-based encoding reduces the amount of generated data while keeping relevant information in the measured magnitude. While this encoding is mostly associated with spiking neuromorphic systems, it can be used in a broad spectrum of tasks. The extension of event-based data representation to other sensors would provide advantages related to bandwidth reduction, lower computing requirements, increased processing speed and data processing. This work describes two event-based encoding procedures (magnitude-event and rate-event) for two sensors widely used in industry, especially for navigation in mobile systems: digital magnetic compass and ultrasonic distance sensor. Encoded data meet Address Event Representation (AER) format for further transmission, processing and visualization. Two encoding procedures and their associated AER conversion from sensor data are described, using an AVR microprocontroller to perform the task in real-time. Results are transmitted to a computer via USART, displayed and recorded using Matlab or jAER visualization tool. A comparison with classic transmitting and processing of sensor data is done to evaluate the convenience of the proposed encoding. Results show that data transmission bandwith can be reduced up to 95% under certain conditions, envisaging that pure or mixed regular/event-based data sensors are desirable for high speed transmission and low computer processing while keeping relevant information, which is highly desirable for mobile systems.
暂无评论