This study focuses on heavy metal pollution in Yunnan Province and designed and developed a data informatization platform for soil environmental quality monitoring and data informatization for pollution control. The p...
详细信息
With the growing availability of data processing and machine learning infrastructures, crowd analysis is becoming an important tool to tackle economic, social, and environmental challenges in smart communities. The he...
详细信息
With the growing availability of data processing and machine learning infrastructures, crowd analysis is becoming an important tool to tackle economic, social, and environmental challenges in smart communities. The heterogeneous crowd movement data captured by IoT solutions can inform policy-making and quick responses to community events or incidents. However, conventional crowd-monitoring techniques using video cameras and facial recognition are intrusive to everyday life. This article introduces a novel non-intrusive crowd monitoring solution which uses 1,500+ software-defined networks (SDN) assisted WiFi access points as 24/7 sensors to monitor and analyze crowd information. Prototypes and crowd behavior models have been developed using over 900 million WiFi records captured on a university campus. We use a range of datavisualization and time-series dataanalysis tools to uncover complex and dynamic patterns in large-scale crowd data. The results can greatly benefit organizations and individuals in smart communities for data-driven service improvement.
This work presents the first application of an Augmented Reality (AR) and Virtual Reality (VR) environment for the navigation and analysis of complex 3D metrology datasets in chip manufacturing and debugging. Our plat...
详细信息
ISBN:
(纸本)9798350360615;9798350360608
This work presents the first application of an Augmented Reality (AR) and Virtual Reality (VR) environment for the navigation and analysis of complex 3D metrology datasets in chip manufacturing and debugging. Our platform overcomes the limitations of traditional 2D datavisualization by facilitating seamless access, navigation, and co-registration of multi-modal datasets acquired through tomographic scanning probe microscopy, 3D rendering software, and finite element simulations. Our goal is to demonstrate the functionality and advantages of such a platform for the analysis of complex 3D datasets, typically generated during the process of failure analysis (FA). First, we describe our platform with details for the access and navigation of existing datasets. Second, we offer the seamless presentation of various co-registered datasets acquired by a combination of tomographic scanning probe microscopy, multiple FA techniques, and 3D finite elements software simulations. Our first-person perspective enables the enhancement of data navigation for each of these tasks. For example, with the simultaneous observation of static 2D information about the sample under study e.g., graphic data stream (GDS) floorplan or scanning electron microscopy (SEM), while offering 3D interactive inspection of an inherently tomographic dataset.
In the design of visual analytics systems, good understanding of user intents can make systems adapt to user needs and help users better complete analytical tasks. However, user intent is difficult to observe directly...
详细信息
ISBN:
(纸本)9798350393811;9798350393804
In the design of visual analytics systems, good understanding of user intents can make systems adapt to user needs and help users better complete analytical tasks. However, user intent is difficult to observe directly. Current work tends to focus more on analyzing user behaviors and overlook the potential connections between data. In this paper, we propose an approach to understanding user intents by automatically extracting data features and combining them with user interaction history. We develop a framework for understanding user intents based on graph neural networks to support two high-level tasks: 1) real-time recommendation for the next interaction based on interaction history, and 2) real-time storytelling to characterize user intents. In our framework, we apply an SR-GATNE model based on graph neural networks to real-time recommendations and story generation. We incorporate the framework in a visual analytics system for industry analysis and evaluating the system. Results of evaluation show that our approach can help users complete the tasks better and improve their experience in analytical tasks.
With the rapid accumulation of text data produced by data-driven techniques, the task of extracting "data annotations"-concise, high-quality data summaries from unstructured raw text-has become increasingly ...
详细信息
ISBN:
(纸本)9798350321241
With the rapid accumulation of text data produced by data-driven techniques, the task of extracting "data annotations"-concise, high-quality data summaries from unstructured raw text-has become increasingly important. The recent advances in weak supervision and crowd-sourcing techniques provide promising solutions to efficiently create annotations (labels) for large-scale technical text data. However, such annotations may fail in practice because of the change in annotation requirements, application scenarios, and modeling goals, where label validation and relabeling by domain experts are required. To approach this issue, we present LabelVizier, a human-in-the-loop workflow that incorporates domain knowledge and user-specific requirements to reveal actionable insights into annotation flaws, then produce better-quality labels for large-scale multi-label datasets. We implement our workflow as an interactive notebook to facilitate flexible error profiling, in-depth annotation validation for three error types, and efficient annotation relabeling on different data scales. We evaluated our workflow in assisting the validation and relabelling of technical text annotation with two use cases and four expert reviews. The results show that LabelVizier is applicable in various application scenarios, and users with different knowledge backgrounds have diverse preferences for the tool usage.
For next generation platforms, the paradigm of task-based parallelism has the potential to overcome some of the accompanying challenges. This paradigm has already been applied by the visualization community to specifi...
详细信息
ISBN:
(数字)9781665491563
ISBN:
(纸本)9781665491563
For next generation platforms, the paradigm of task-based parallelism has the potential to overcome some of the accompanying challenges. This paradigm has already been applied by the visualization community to specific algorithms and problems. However, one advantage of the task-based paradigm-the interleaving of workshould lead to better utilization of resources and ultimately lower execution times if the paradigm is applied to whole pipelines. In order to investigate this potential, we build a prototype framework for composable task-based parallel visualization algorithms. With this we explore the combination of a strictly task-based approach with the addition of a pipeline layer for visualization algorithms. This additional layer eases the composition of larger task-based parallel visualization applications without the need to explicitly define the exact connection in a task graph between algorithms. In this manner, task-based visualization algorithms can be designed towards a common interface, be easily combined, and still benefit from the advantages of the task-based paradigm across algorithm boundaries, such as latency hiding. We explore the design implications of this combination and show initial results of the scalability and the impact of task interleaving on the runtime of exemplary pipelines.
Many software and hardware applications generate an increasing volume of data and logs in real-time. Visual analytics is essential to support system monitoring and analysis of such data. For example, the world's l...
详细信息
Many software and hardware applications generate an increasing volume of data and logs in real-time. Visual analytics is essential to support system monitoring and analysis of such data. For example, the world's largest radio telescope, the Square Kilometer Array (SKA), is expected to generate an estimated 160 TB a second of raw data captured from different sources. Transporting large amounts of data from distributed sources to a web browser for visualization is time-consuming due to data transport latencies. In addition, visualizing real-time data in the browser is challenging and limited by the data rates which a web browser can handle. We propose a novel low latency data streaming architecture, which uses a messaging system for real-time data transport to the web browser. Based on this architecture, we propose techniques and provide a tool for analyzing the performance of serialization protocols and the web-visualization rendering pipeline. We empirically evaluate the performance of our architecture using three visualizations use cases relevant to the SKA. Our system proved extremely useful in streaming high-volume data in real-time with low latency and greatly enhanced the web-visualization performance by enabling streaming an optimal number of data points to different visualizations.
Fluorescence microscope dataanalysis for liquid biopsy needs to be evidenced by object visualization on the display. This visualization heavily depends on the operator's tuning of the display settings, which is t...
详细信息
ISBN:
(纸本)9798350312249
Fluorescence microscope dataanalysis for liquid biopsy needs to be evidenced by object visualization on the display. This visualization heavily depends on the operator's tuning of the display settings, which is typically achieved through conventional linear stretching or windowing/leveling techniques. However, manual tuning can introduce variability and bias, leading to reduced throughput of analysis verifications. We propose a novel method for enhancing multi-channel fluorescence images by optimizing the visualization of assay-related objects. This problem is formulated as a variational minimax optimization of the histogram-equalizing energy with data distortion regularization. Our method seamlessly merges the resolved, enhanced objects of interest with the background, resulting in high performance and overall visual coherence.
In parallel ray tracing, techniques fall into one of two camps: imageparallel techniques aim at increasing frame rate by replicating scene data across nodes and splitting the rendering work across different ranks, and...
详细信息
ISBN:
(数字)9781665491563
ISBN:
(纸本)9781665491563
In parallel ray tracing, techniques fall into one of two camps: imageparallel techniques aim at increasing frame rate by replicating scene data across nodes and splitting the rendering work across different ranks, and data-parallel techniques aim at increasing the size of the model that can be rendered by splitting the model across multiple ranks, but typically cannot scale much in frame rate. We propose and evaluate a hybrid approach that combines the advantages of both by splitting a set of N x M ranks into M islands of N ranks each and using data-parallel rendering within each island and image parallelism across islands. We discuss the integration of this concept into four wildly different parallel renderers and evaluate the efficacy of this approach based on multiple different data sets.
The process of visual analytics is composed of the visual data exploration tasks supporting analytical reasoning. When performing analytical tasks with the interactive visual interfaces displayed by the large screen, ...
详细信息
The process of visual analytics is composed of the visual data exploration tasks supporting analytical reasoning. When performing analytical tasks with the interactive visual interfaces displayed by the large screen, physical discomforts such as gorilla-arm effect can be easily caused. To enrich the input space for analysts, there has been some researches concerning the cross-device analysis combining mobile devices with the large display. Although the effectiveness of expert-level designs has been demonstrated, little is known of the ordinary users' preferences for using a mobile device to issue commands, especially the small one like smartwatch. We implement a three-stage study to investigate and validate these preferences. A total of 181 distinctive gestural inputs and 52 interface designs for 21 tasks were collected from analysts. Expert designers selected the best practices from these user-defined interactions. A performance test was subsequently developed to assess the selected interactions in terms of quantitative statistics and subjective ratings. Our work provides empirical support and proposes a set of design guidelines for optimizing watch-based interactions aimed at remote control of visual data on the large display. Through this research, we hope to advance the development of smartwatches as visual analytics tools and provide visual analysts with a better usage experience.
暂无评论