Motivation Reviewing the adverse event data collected in clinical trials is a lengthy and tedious process when these data are presented in the form of tables, data listings, and static graphs. Thus, to enable anyone i...
详细信息
Motivation Reviewing the adverse event data collected in clinical trials is a lengthy and tedious process when these data are presented in the form of tables, data listings, and static graphs. Thus, to enable anyone interested in exploring adverse event data efficiently and relatively independently, we developed AdEPro, a compact, powerful, and easy-to-use interactive app. Description and Use of the App AdEPro is an app for (audio-)visualizing adverse event data from clinical trials. The app dynamically displays the onset, severity, and development of selected adverse events on the individual subject level and on the treatment group level. This paper illustrates that there are numerous questions related to adverse events that can be approached by means of AdEPro, e.g., questions about temporal aspects of adverse events, associations between adverse events, and the influence of subject characteristics. AdEPro provides quick first answers to such questions;however, it does not provide statistical proof. Essentially, it acts as a versatile "hypothesis generator," helping the user to decide whether further analyses are indicated. No programming knowledge is required for exploring data by means of AdEPro. However, the user needs some basic knowledge of the software R and of extracting data from a clinical data base. The software code is open source, allowing modifications and expansions of the app, if desired. Availability and Implementation AdEPro can be freely obtained from. It runs on any computer on which R is installed. Patient data are stored and processed locally.
Although machine learning algorithms are progressively used in an expansive range of domains, the effective machine learning classifiers are often black-boxed, non-comprehensive to the end users and beyond their abili...
详细信息
ISBN:
(纸本)9781728191348
Although machine learning algorithms are progressively used in an expansive range of domains, the effective machine learning classifiers are often black-boxed, non-comprehensive to the end users and beyond their abilities to develop models themselves. To overcome this challenge, datavisualization combined with self-service or democratized machine learning is proposed in the form of the Iterative Logical Classifier (ILC) algorithm with an added advantage of outperforming the accuracies of black-box machine learning classifiers on benchmark datasets. The algorithm is based on the concept of Shifted Paired Coordinates that allow 2-D visualization of n-D data without loss of n-D information.
The dramatic development of Earth observation techniques leads to an explosion of Earth data. However, the increase of the Earth data size and their heterogeneity bring significant challenges to the storage, processin...
详细信息
ISBN:
(纸本)9781450360913
The dramatic development of Earth observation techniques leads to an explosion of Earth data. However, the increase of the Earth data size and their heterogeneity bring significant challenges to the storage, processing and visualization of the big Earth data. To address the problems caused by the huge Earth data-sets, a heterogeneous and interactive big Earth data framework is proposed in this paper, integrating raster-vector data cloud storage, data processing based on workflow and machine learning techniques and real-time rendering and interactivevisualization. The framework provides a theoretical reference for future implementations of the system.
data clustering algorithms have proved to be important and widely used methods of artificial intelligence and data mining for discovering unknown yet important patterns in datasets. Nevertheless, one of the additional...
详细信息
data clustering algorithms have proved to be important and widely used methods of artificial intelligence and data mining for discovering unknown yet important patterns in datasets. Nevertheless, one of the additional aspects of data clustering is proper interpretation of the clustering results. In this paper we aim to investigate possibilities of using both data clustering and visualization methods to analyze a sample diabetes dataset. In the first part, we focus on how to cluster a highly-dimensional sample dataset and then, we concentrate on how to properly visually present the clustering results in the most meaningful way to uncover potentially interesting behavioral patterns or features of diabetes patients. In this work we examine two clustering algorithms (DBSCAN, k-Means) along with several different distance measures. We also present sample visualizations of clustering results generated by an application which we have developed and discuss if the proposed way of clustering results visualization can be helpful in understanding the analyzed dataset and lead a viewer to drawing valuable conclusions about it. (C) 2019 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://***/licenses)/by-nc-nd/4.0/) Peer-review under responsibility of KES International.
This installment of Computer's series highlighting the work published in IEEE Computer Society journals comes from IEEE Transactions on visualization and Computer Graphics.
This installment of Computer's series highlighting the work published in IEEE Computer Society journals comes from IEEE Transactions on visualization and Computer Graphics.
Visualizing data is an essential part of good statistical practice. Plots are useful for revealing structure in the data, checking model assumptions, detecting outliers and finding unanticipated patterns. Post-analysi...
详细信息
Visualizing data is an essential part of good statistical practice. Plots are useful for revealing structure in the data, checking model assumptions, detecting outliers and finding unanticipated patterns. Post-analysis visualization is commonly used to communicate the results of statistical analyses. The availability of good statistical visualization software is key in effectively performing data analysis and in exploring and developing new methods for datavisualization. Compared to static visualization, interactivevisualization adds natural and powerful ways to explore the data. With interactivevisualization an analyst can dive into the data and quickly react to visual clues by, for example, re-focusing and creating interactive queries of the data. Further, linking visual attributes of the data points such as color and size allows the analyst to compare different visual representations of the data such as histograms and *** this thesis, we explore and develop new interactive data visualization and exploration tools for high-dimensional data. The original focus of our research was a software implementation of navigation graphs. Navigation graphs are navigational infrastructures for controlled exploration of high-dimensional data. As part of this thesis, we developed the first interactive implementation of these navigation graphs called RnavGraph. With RnavGraph we explored various features for enhancing the usability of navigation graphs. We concluded that a powerful interactive scatterplot display and methods to deal with large graphs were two areas that would add great value to the navigation graph ***''s scatterplot display proved to be particularly useful for data analysis and we continued our research with the design and implementation of a general-purpose interactivevisualization toolkit called loon. The core contributions of loon are as follows. loon implements a general design for interactive statistical graphic displays that
data clustering algorithms have proved to be important and widely used methods of artificial intelligence and data mining for discovering unknown yet important patterns in datasets. Nevertheless, one of the additional...
详细信息
data clustering algorithms have proved to be important and widely used methods of artificial intelligence and data mining for discovering unknown yet important patterns in datasets. Nevertheless, one of the additional aspects of data clustering is proper interpretation of the clustering results. In this paper we aim to investigate possibilities of using both data clustering and visualization methods to analyze a sample diabetes dataset. In the first part, we focus on how to cluster a highly-dimensional sample dataset and then, we concentrate on how to properly visually present the clustering results in the most meaningful way to uncover potentially interesting behavioral patterns or features of diabetes patients. In this work we examine two clustering algorithms (DBSCAN, k-Means) along with several different distance measures. We also present sample visualizations of clustering results generated by an application which we have developed and discuss if the proposed way of clustering results visualization can be helpful in understanding the analyzed dataset and lead a viewer to drawing valuable conclusions about it.
visualization as a mean of big data management is the new century revolution. Managing data has become a great challenge today, as the amount of raw data size is increasing *** data like electricity consumption, a new...
详细信息
ISBN:
(纸本)9781538627563
visualization as a mean of big data management is the new century revolution. Managing data has become a great challenge today, as the amount of raw data size is increasing *** data like electricity consumption, a new data value is received every minute from different areas. This creates the well-known five challenges for any data analyst trying to deliver a visual representation of such huge raw data. Adding to that, a data analyst should understand the four dimensions of the given data;Volume, variety, velocity and veracity. The integration of big data and visualization is the key to addressing real market significant shift in enterprise technology. The aim of the paper is to give an insight of 'how to manage' Qatars electricity consumption from raw data provided by electricity companies. This can lead to a much better visualization solution as analysts and top-level managers can understand how to act towards their resources and plan.
A prototype of interactive data visualization is proposed for Building Management Systems (BMS). The aim is to enhance traditional data presentation format such as graphs and tables to support expert users in early op...
详细信息
A prototype of interactive data visualization is proposed for Building Management Systems (BMS). The aim is to enhance traditional data presentation format such as graphs and tables to support expert users in early open-ended exploration of building data. Based on data recorded over 3 years in areal office building in Switzerland, a case study is conducted involving 12 practicing expert users with engineering background. Both exploratory and qualitative in nature, this evaluation allows to : (1) show the ability of expert users to use advanced visualization tools to derive meaningful conclusions in limited time, (2) demonstrate the relevance of visual analytics results for the building physics field. (C) 2017 The Authors. Published by Elsevier Ltd.
A prototype of interactive data visualization is proposed for Building Management Systems (BMS). The aim is to enhance traditional data presentation format such as graphs and tables to support expert users in early op...
详细信息
A prototype of interactive data visualization is proposed for Building Management Systems (BMS). The aim is to enhance traditional data presentation format such as graphs and tables to support expert users in early open-ended exploration of building data. Based on data recorded over 3 years in a real office building in Switzerland, a case study is conducted involving 12 practicing expert users with engineering background. Both exploratory and qualitative in nature, this evaluation allows to : (1) show the ability of expert users to use advanced visualization tools to derive meaningful conclusions in limited time, (2) demonstrate the relevance of visual analytics results for the building physics field.
暂无评论