Web based 3D medical data computing and visual synchronization can provide clinical users with critical information for distributed diagnosis and treatment. However, due to the limited internet bandwidth, high computa...
ISBN:
(数字)9781728103198
ISBN:
(纸本)9781728103204
Web based 3D medical data computing and visual synchronization can provide clinical users with critical information for distributed diagnosis and treatment. However, due to the limited internet bandwidth, high computational cost and increasing data size, real-time medical dataexploration and information sharing on internet is still a challenging task. Therefore, we developed a new internet based medical data computing and information visual distribution system, in which graphics processing units were utilized for parallel medical data computing and visualization, cloud was used for data storage, Apache HTTP Server and MySQL were employed for medical image management and analysis, and WebSocket Protocol was used for medical information visual synchronization. The major contributions include algorithms developed for high performance medical computing, and medical information sharing and visual synchronization on distributed web browsers. The developed system can provide medical users with intuitive feedback for collaborative diagnosis and remote therapy.
Recently, there have been several proposals to develop visual recommendation systems. The most advanced systems aim to recommend visualizations, which help users to find new correlations or identify an interesting dev...
Recently, there have been several proposals to develop visual recommendation systems. The most advanced systems aim to recommend visualizations, which help users to find new correlations or identify an interesting deviation based on the current context of the user's analysis. However, when recommending a visualization to a user, there is an inherent risk to visualize random fluctuations rather than solely true patterns: a problem largely ignored by current techniques. In this paper, we present VizCertify, a novel framework to improve the performance of visual recommendation systems by quantifying the statistical significance of recommended visualizations. The proposed methodology allows to control the probability of misleading visual recommendations using both classical statistical testing procedures and a novel application of the Vapnik Chervonenkis (VC) dimension towards visualization recommendation which results in an effective criterion to decide whether a recommendation corresponds to a true phenomenon or not.
With increasing availability of location-acquisition technologies, huge volumes of data tracking transportation system have been collected. These data are highly valuable for unveiling human mobility patterns, transpo...
详细信息
ISBN:
(数字)9783030005603
ISBN:
(纸本)9783030005603;9783030005597
With increasing availability of location-acquisition technologies, huge volumes of data tracking transportation system have been collected. These data are highly valuable for unveiling human mobility patterns, transportation system utilization, and urban planning. However, it is still highly challenging to visualize and explore transportation data. In this paper, an interactive visual analytic system, TranSeVis has been proposed. It has two visualization modules, one named region view provides geographical information and effective temporal information comparison, the other named road view provides detailed visualanalysis of mobility factors along routes or congestions spots. Besides, two case studies have been used to evaluate the visualization techniques and real-world taxi data sets have been used to demonstrate TranSeVis. Based on the results, TranSeVis offers transportation researchers an easy-to-use, efficient, and scalable platform to visualize and explore transportation data.
The proceedings contain 50 papers. The special focus in this conference is on Web Engineering. The topics include: Supervised group embedding for rumor detection in social media;fast incremental pagerank on dynamic ne...
ISBN:
(纸本)9783030192730
The proceedings contain 50 papers. The special focus in this conference is on Web Engineering. The topics include: Supervised group embedding for rumor detection in social media;fast incremental pagerank on dynamic networks;crowdsourced time-sync video recommendation via semantic-aware neural collaborative filtering;on Twitter bots behaving badly: Empirical study of code patterns on GitHub;CrowDIY: How to design and adapt collaborative crowdsourcing workflows under budget constraints;finding baby mothers on Twitter;an end-user pipeline for scraping and visualizing semi-structured data over the web;DotCHA: A 3D text-based scatter-type CAPTCHA;entropy and compression based analysis of web user interfaces;Augmenting LOD-based recommender systems using graph centrality measures;domain classifier: Compromised machines versus malicious registrations;the “game hack” scam;decentralized service registry and discovery in P2P networks using blockchain technology;amalgam: Hardware hacking for web developers with style (sheets);Jekyll RDF: Template-based linked data publication with minimized effort and maximum scalability;on the web platform cornucopia;Linked USDL extension for cloud services description;an automatic data service generation approach for cross-origin datasets;Merging intelligent API responses using a proportional representation approach;analyzing the evolution of linked vocabularies;ST-sem: A multimodal method for points-of-interest classification using street-level imagery;Comparison matrices of semantic RESTful APIs technologies;dragon: Decision tree learning for link discovery;catch & release: An approach to debugging distributed full-stack javascript applications;multi-device adaptation with liquid media queries;conversational dataexploration;distributed intelligent client-centric personalisation;webifying heterogenous internet of things devices;VR-powered scenario-based testing for visual and acoustic web of things services.
The exploration of high-dimensional real-valued data is one of the fundamental exploratory dataanalysis (EDA) tasks. Existing methods use predefined criteria for the representation of data. There is a lack of methods...
详细信息
ISBN:
(纸本)9781538655207
The exploration of high-dimensional real-valued data is one of the fundamental exploratory dataanalysis (EDA) tasks. Existing methods use predefined criteria for the representation of data. There is a lack of methods eliciting the user's knowledge from the data and showing patterns the user does not know yet. We provide a theoretical model where the user can input the patterns she has learned as knowledge. The background knowledge is used to find a MaxEnt distribution of the data, and the user is shown maximally informative projections in which the MaxEnt distribution and the data differ the most. We provide an interactive open source EDA system, study its performance, and present use cases on real data.
The proceedings contain 56 papers. The special focus in this conference is on e-Learning and Games. The topics include: Naturally Interact with Mobile Virtual Reality by CAT;hand Pose Estimation Using Convolutional Ne...
ISBN:
(纸本)9783030237110
The proceedings contain 56 papers. The special focus in this conference is on e-Learning and Games. The topics include: Naturally Interact with Mobile Virtual Reality by CAT;hand Pose Estimation Using Convolutional Neural Networks and Support Vector Regression;texture Image Segmentation Based on Stationary Directionlet Domain Probabilistic Graphical Model;using Face Recognition to Detect "Ghost Writer" Cheating in Examination;improved Modular Convolution Neural Network for Human Pose Estimation;humanoid Robot Control Based on Deep Learning;a Novel Feature-Based Pose Estimation Method for 3D Faces;A Combined Deep Learning and Semi-supervised Classification Algorithm for LS Area;static Gesture Recognition Method Based on 3D Human Hand Joints;a Plant Growing Game Based on Mobile Terminal and Embedded Technology;A WebRTC e-Learning System Based on Kurento Media Server;the Research on Serious Games in Social Skills Training for Children with Autism;hands on Work Game: Neuro-Pedagogical Method to Improve Math Fraction Teaching;analysis of College Students’ Employment, Unemployment and Enrollment with Self-Organizing Maps;a Study of Negative Emotion Regulation of College Students by Social Games Design;research on Mobile Learning System of Colleges and Universities;a Mobile Learning System with Multi-point Interaction;e-learning Rhythm Design: Case Study Using Fighting Games;developing an Augmented Reality Multiplayer Learning Game: Lessons Learned;Collecting visual Effect Linked data Using GWAP;interactive Web 3D Contents Development Framework Based on Linked data for Japanese History Education;the Dilemma and exploration of the Innovation of Internal Governance in Higher Education Institutions;a Motion-Driven System for Performing Art.
Using human fixation behavior, we can interfere regions that require to be processed at high resolution and where stronger compression can be favored. Analyzing the visual scan path solely based on a predefined set of...
详细信息
ISBN:
(纸本)9781450357876
Using human fixation behavior, we can interfere regions that require to be processed at high resolution and where stronger compression can be favored. Analyzing the visual scan path solely based on a predefined set of regions of interest (ROIs) limits the exploration room of the analysis. Insights can only be gained for those regions that the data analyst considered worthy of labeling. Furthermore, visualexploration is naturally time-dependent: A short initial overview phase may be followed by an in-depth analysis of regions that attracted the most attention. Therefore, the shape and size of regions of interest may change over time. Automatic ROI generation can help in automatically reshaping the ROIs to the data of a time slice. We developed three novel methods for automatic ROI generation and show their applicability to different eye tracking data sets. The methods are publicly available as part of the EyeTrace software at http://***/***
With the internet, massively heterogeneous data sources need to be understood and classified to provide suitable services to users such as content observation, dataexploration, e-commerce, or adaptive learning enviro...
详细信息
ISBN:
(纸本)9781450356169
With the internet, massively heterogeneous data sources need to be understood and classified to provide suitable services to users such as content observation, dataexploration, e-commerce, or adaptive learning environments. The key to providing these services is applying machine learning (ML) in order to generate structures via clustering and classification. Due to the intricate processes involved in ML, visual tools are needed to support designing and evaluating the ML pipelines. In this contribution, we propose a comprehensive tool that facilitates the analysis and design of ML-based clustering algorithms using multiple visualization features such as semantic zoom, glyphs, and histograms.
With the increasing popularity of portable eye tracking devices, one can conveniently use them to find fixation points, i.e., the location and region one is attracted by and looking at. However, region of interest alo...
详细信息
ISBN:
(纸本)9783030275389;9783030275372
With the increasing popularity of portable eye tracking devices, one can conveniently use them to find fixation points, i.e., the location and region one is attracted by and looking at. However, region of interest alone is not enough to fully support further behavior and psychological analysis since it ignores the abundant information of visual information one perceives. Rather than the raw coordinates, we are interested to know the visual content one is looking at. In this work, we first collect a video dataset using a wearable eye tracker in an autism screening room setting with 14 different commonly used assessment tools. We then propose an improved fixation identification algorithm to select stable and reliable fixation points. The fixation points are used to localize and select object proposals in combination with object proposal generation methods. Moreover, we propose a cropping generation algorithm to determine the optimal bounding boxes of viewing objects based on the input proposals and fixation points. The resulted cropped images form a dataset for the subsequent object recognition task. We adopt the AlexNet based convolutional neural network framework for object recognition. Our evaluation metrics include classification accuracy and intersection-over-union (IoU), and the proposed framework achieves 92.5% and 88.3% recognition accuracy on different testing sessions, respectively.
In several fields handling event data, exploring periodicity and similarity of the occurrence times of events is an important task. When we analyze event data, we often focus on temporal features of event groups, peri...
详细信息
ISBN:
(纸本)9781538672020
In several fields handling event data, exploring periodicity and similarity of the occurrence times of events is an important task. When we analyze event data, we often focus on temporal features of event groups, periodic features of events, and similarity of temporal features among event groups. This paper illustrates a visualization method to efficiently observe such features for multiple events. The method represents the temporal features of each event group with a glyph and represents the periodic features and their similarity with an arrangement of glyphs. To determine an arrangement of glyphs, a ChronoView graph representing periodic features of event groups is integrated with pseudo multidimensional scaling (MDS) in a 3D space. This paper also demonstrates the effectiveness of the visualization method for temporal dataanalysis with a use case exploring significant events from an actual dataset.
暂无评论