Visualization of Sensor Data Multimedia Information Systems 2 VU - PowerPoint PPT Presentation

Visualization of Sensor Data Multimedia Information Systems 2 VU (707.025) (“Visual Analytics”) SS 2016 Cecilia di Sciascio Know-Center April 19 th 2016 April 19 th , 2016 MMIS2 VU – Sensor Data Visusalization Vedran Sabol

Visualisation of Sensor Data • Massive production of sensor data  Mobile devices (quantify yourself)  Industrial sensors (Industry 4.0): monitoring, prediction etc.  Medicine: patient monitoring, brain-computer interfaces  Transportation  Climate, … • Problems to address:  Scalability: visualize massive amounts of data (high-frequency, long time range)  Handling many sensor channels at once  Interactive exploration techniques for sensor data: annotation, brushing and filtering, searching etc. April 19 th , 2016 MMIS2 VU - Sensor Data Visusalization 2 Cecilia di Sciascio

Scalability • Methods to visualise massive signals: down-sampling techniques, LOD rendering, data transfer protocols etc. • Downsampling e.g. Decimation April 19 th , 2016 MMIS2 VU - Sensor Data Visusalization 3 Cecilia di Sciascio

Scalability • Simultaneous visualisation of many sensor channels: dense views Downsampling can be problematic! Information Density April 19 th , 2016 MMIS2 VU - Sensor Data Visusalization Cecilia di Sciascio

Visualisation of Sensor Data – Tasks 1. Interactive exploration techniques for sensor data  Annotation tools: users describe phenomena April 19 th , 2016 MMIS2 VU - Sensor Data Visusalization 5 Cecilia di Sciascio

Visualisation of Sensor Data – Tasks 2. Show pattern overview: downsample, cluster (e.g. correlation) and show how “good” each cluster is with overlapping strokes. April 19 th , 2016 MMIS2 VU - Sensor Data Visusalization 6 Cecilia di Sciascio

Visualisation of Sensor Data – Tasks 3. Dense graphs: downsample signal and make color-coded groups by certain property (set threshold, +/-) April 19 th , 2016 MMIS2 VU - Sensor Data Visusalization 7 Cecilia di Sciascio

Visualisation of Sensor Data – Tasks 4. Brushing: multiple value-range filters, angle- (slope-) filter April 19 th , 2016 MMIS2 VU - Sensor Data Visusalization 8 Cecilia di Sciascio

Visualisation of Sensor Data – Tasks 5. Visualize any other kind of temporal series http://survey.timeviz.net/ April 19 th , 2016 MMIS2 VU - Sensor Data Visusalization 9 Cecilia di Sciascio

Visualisation of Sensor Data – Suggested Data Sets EEG Data:  http://sccn.ucsd.edu/~arno/fam2data/publicly_available_EEG_data.html  http://sccn.ucsd.edu/~arno/fam2data/publicly_available_EEG_data.html  http://bnci-horizon-2020.eu/database/data-sets • Ask for more data sets via email: cdisciascio@know-center.at April 19 th , 2016 MMIS2 VU - Sensor Data Visusalization 10 Cecilia di Sciascio

Thank you Questions? April 19 th , 2016 MMIS2 VU - Sensor Data Visusalization 11 Cecilia di Sciascio