Student Projects Multimedia Information Systems 2 VU (707.025) - - PowerPoint PPT Presentation

▶
student projects
SMART_READER_LITE
LIVE PREVIEW

Student Projects Multimedia Information Systems 2 VU (707.025) - - PowerPoint PPT Presentation

Feb 09, 2023 313 likes •680 views

Student Projects Multimedia Information Systems 2 VU (707.025) (Visual Analytics) SS 2016 Vedran Sabol Know-Center April 12 th 2016 April 12 th , 2016 MMIS2 VU - Projects Vedran Sabol Lecture Overview Motivation and Goals

slide-1
SLIDE 1

MMIS2 VU - Projects April 12th, 2016 Vedran Sabol

Student Projects

Multimedia Information Systems 2 VU (707.025)

(“Visual Analytics”)

SS 2016

Vedran Sabol Know-Center April 12th 2016

slide-2
SLIDE 2

MMIS2 VU - Projects April 12th, 2016 Vedran Sabol

Lecture Overview

  • Motivation and Goals
  • Four Project Topics
  • Overall project description
  • Implementation ideas
  • Data set suggestions
  • Next Steps

2

slide-3
SLIDE 3

MMIS2 VU - Projects April 12th, 2016 Vedran Sabol

Motivation

  • Web is man made but it behaves as a natural phenomenon
  • Complex system: technological and social
  • The Web is a technological infrastructure supporting processes of
  • Publishing, linking, connecting, communicating, collaborating etc.
  • Result: creation of huge amounts of data
  • Web data as object of analysis
  • Knowledge Discovery in the Web (Web Mining): automated analysis
  • Information and Data Visualisation: human visual pattern recognition
  • Visual Analytics: combine algorithmic and visual methods (human in the loop)

3

slide-4
SLIDE 4

MMIS2 VU - Projects April 12th, 2016 Vedran Sabol

Goals

  • Learn how to apply Visual Analytics methods in the Web
  • on Web data
  • using Web technologies
  • in selected Web-based scenarios
  • Learn about presenting Web data visually
  • Using Web technologies (HTML5)
  • to gain insights into
  • Multidimensional data (tables)
  • Recommended (multimedia) resources
  • Sensor and event data
  • Semantic knowledge bases (ontologies)

4

slide-5
SLIDE 5

MMIS2 VU - Projects April 12th, 2016 Vedran Sabol

Projects

  • Project topics

1. Visual exploration and filtering of recommender data 2. Sensor and time series visualisation 3. Visualisation recommendation for tabular data sets 4. Visualisation of semantic networks

  • Each group picks one topic
  • Number of groups per topic is limited
  • First come, first served
  • Topic registration: per Email to the tutor (b.taraghi@tugraz.at) and

lecturer (vsabol@know-center.at)

  • List your first and your second choice
  • If your first choice is already booked out: you will be notified by the tutor and

will have to live with your second choice

5

slide-6
SLIDE 6

MMIS2 VU - Projects April 12th, 2016 Vedran Sabol

Projects

  • The four project topics are fixed!
  • Each team must pick one of them
  • (or contact the lecturer directly if you think you have a much better idea)
  • Presented implementation ideas are not binding
  • But, they are aligned with the lecture topics
  • The listed data sets are suggestions
  • You are free to select any suitable data set for your demo
  • You have the choice of
  • implementing your own UI from scratch
  • extending an existing UI (topics 1 and 3), such as the Recommendation

Dashboard or VisWizard

6

slide-7
SLIDE 7

MMIS2 VU - Projects April 12th, 2016 Vedran Sabol

Project Topic 1

Visualisation of Recommender Results

7

slide-8
SLIDE 8

MMIS2 VU - Projects April 12th, 2016 Vedran Sabol

  • 1. Recommender Interfaces
  • Recommenders as ahead of time information retrieval engines
  • Recommendations are automatically generated
  • Depending on user’s context (and profile)
  • E.g. what the user is reading in the browser
  • Problem: recommendations may not be relevant
  • It is hard to guess user’s needs
  • Solution: visual tools for exploring, filtering and specifying interests
  • Ideally Personalised and context-sensitive
slide-9
SLIDE 9

MMIS2 VU - Projects April 12th, 2016 Vedran Sabol

  • 1. Recommender Interfaces – Project Ideas
  • Recommendation Dashboard (RD) interface provides
  • Filtering and bookmarking functionality
  • Views for temporal, geographical, topical and categorical data
  • Extend it with new views visualising e.g.
  • keyword-relationships based on co-occurrence
  • Image similarity maps etc.

9 Automatic Resource Recommendation (Chrome plug-in) Visual Analysis

1 2 3

Set Filters

slide-10
SLIDE 10

MMIS2 VU - Projects April 12th, 2016 Vedran Sabol

  • 1. Recommender Interfaces – Project Ideas
  • The RD micro-visualisations show the currently

active filter set

  • Temporal, spatial topical, categorical etc.
  • Improvements
  • Make micro-visualisations interactive
  • Add zooming, panning, selection etc.
  • Including touch interactivity for the mobile
  • Add new/improved visual metaphors, e.g.
  • Hierarchies and graphs
  • Collection interfaces (topical overview, image browser etc.)
slide-11
SLIDE 11

MMIS2 VU - Projects April 12th, 2016 Vedran Sabol

  • 1. Recommender Interfaces – Project Ideas
  • Improve the uRank topical exploration interface
  • New tag-cloud view for the keywords
  • Replace stacked bar with new document content visualisations
  • Implement a new re-ranking algorithm

11 pick keywords change weights Re-ranking of documents Inspection: highlight keywords in content

slide-12
SLIDE 12

MMIS2 VU - Projects April 12th, 2016 Vedran Sabol

  • 1. Recommender Interfaces – Suggested Data Sets
  • Scientific and cultural heritage data
  • Returned by the EEXCESS recommender and retrieved directly by the

Recommendation Dashboard UI

  • Goodie: 2 integrated test data sets available for offline testing
  • Details to be introduced in the lecture on 19.04.2016
  • Europeana data APIs: http://labs.europeana.eu/api

12

slide-13
SLIDE 13

MMIS2 VU - Projects April 12th, 2016 Vedran Sabol

Project Topic 2

Visualisation of Sensor Data

13

slide-14
SLIDE 14

MMIS2 VU - Projects April 12th, 2016 Vedran Sabol

  • 2. 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.

14

slide-15
SLIDE 15

MMIS2 VU - Projects April 12th, 2016 Vedran Sabol

  • 2. Visualisation of Sensor Data – Project Ideas
  • Scalability
  • methods to visualise massive signals: down-sampling techniques, LOD

rendering, data transfer protocols etc.

  • Simultaneous visualisation of very many sensor channels: dense views

Information Density

Downsampling can be problematic!

slide-16
SLIDE 16

MMIS2 VU - Projects April 12th, 2016 Vedran Sabol

  • 2. Visualisation of Sensor Data – Project Ideas
  • Interactive exploration techniques for sensor data
  • Annotation tools: users describe phenomena (collaboratively)
  • Show a pattern overview grouped by annotations (on right)

16

slide-17
SLIDE 17

MMIS2 VU - Projects April 12th, 2016 Vedran Sabol

  • 2. Visualisation of Sensor Data – Project Ideas
  • Brushing: multiple value-range filters, angle- (slope-) filter

17 1. 2. 3.

  • Searching interfaces: including similarity computation, ranking and result browsing
slide-18
SLIDE 18

MMIS2 VU - Projects April 12th, 2016 Vedran Sabol

  • 2. Visualisation of Sensor Data – Suggested Data Sets
  • EEG Data:

http://sccn.ucsd.edu/~arno/fam2data/publicly_available_EEG_data.html

  • Additional data sets will be introduced in a lecture on 19.04.2016

18

slide-19
SLIDE 19

MMIS2 VU - Projects April 12th, 2016 Vedran Sabol

Project Topic 3

Visualisation of Tabular Data

19

slide-20
SLIDE 20

MMIS2 VU - Projects April 12th, 2016 Vedran Sabol

  • 3. Visualisation of Tabular Data
  • Data properties
  • Multiple columns containing heterogeneous data types
  • A large number of rows
  • Potentially multiple values per cell
  • Data element is a row: described by multiple attributes
  • Multi-dimensional data
  • Visualisation: specialised representations for different data types

20

slide-21
SLIDE 21

MMIS2 VU - Projects April 12th, 2016 Vedran Sabol

  • 3. Visualisation of Tabular Data - Project Ideas
  • Multi-visualisation UI
  • Use data-type specific visualisations
  • Choose meaningful representations for your data
  • Implement view coordination for interactive analysis
  • Interactions in one view are represented in all others
  • Provide data aggregation and or filtering functions
  • Extend the VisWizard or implement your own UI

21

slide-22
SLIDE 22

MMIS2 VU - Projects April 12th, 2016 Vedran Sabol

  • 3. Visualisation of Tabular Data - Project Ideas
  • Algorithms for automated visualisation
  • Use knowledge about data, visualisations or even users to automate

visualisation selection and configuration

  • Extract (or use available) data semantics to support the process
  • Consider the user profile
  • Replace the current VisWizard algorithms

22

slide-23
SLIDE 23

MMIS2 VU - Projects April 12th, 2016 Vedran Sabol

  • 3. Visualisation of Tabular Data - Project Ideas
  • Implement or extend metaphors for high-dimensional data
  • Extend parallel coordinates (e.g. with histograms or hierarchical information)
  • Implement a dimensionality reduction method to layout data in 2D

23

Data

Feature Extraction

Multi-dimensional Feature Vectors

Dimensionality Reduction

Information Landscape (similarity layout)

slide-24
SLIDE 24

MMIS2 VU - Projects April 12th, 2016 Vedran Sabol

  • 3. Visualisation of Tabular Data – Suggested Data Sets
  • Open governmental data such as from
  • Land Steiermark (CSV and Excel files):
  • CSV (Excel): http://data.steiermark.at/cms/ziel/95564282/DE/
  • EU Open data Portal
  • RDF Data Cubes (semantically described multidimensional data):

http://open-data.europa.eu/en/sparqlep

  • Data in various formats: https://open-data.europa.eu/en/data/
  • Details to be introduced in the lecture on 26.04.2016

24

slide-25
SLIDE 25

MMIS2 VU - Projects April 12th, 2016 Vedran Sabol

Project Topic 4

Visualisation Semantic Networks

25

slide-26
SLIDE 26

MMIS2 VU - Projects April 12th, 2016 Vedran Sabol

  • 4. Visualisation of Semantic Networks
  • Display and navigate structure of large graphs, e.g.
  • Ontologies: semantic networks
  • Consist of nodes and relations with precisely defined semantics
  • Alignment of ontologies: map concepts from two semantic networks
  • nto each other
  • Extract graphs from unstructured text
  • Entities (persons, organisations, locations etc.): Natural Language Processing (NLP)

methods

  • Relations between entities: e.g. co-occurrence in documents, sentences.
slide-27
SLIDE 27

MMIS2 VU - Projects April 12th, 2016 Vedran Sabol

  • 4. Visualisation of Semantic Networks – Project Ideas
  • Graph layout algorithms, such as

27 27

Edge Routing: Edge bundling:

Fs Fe

Force-directed layout:

i

d

1

d

3

d

2

d

slide-28
SLIDE 28

MMIS2 VU - Projects April 12th, 2016 Vedran Sabol

  • 4. Visualisation of Semantic Networks – Project Ideas
  • Graph visualisation showing semantic relationships
  • Icon, shape and colour coding for relation and node types
  • Interaction: expanding the network in a particular direction
  • Visual methods for graph querying (e.g. “blossom node”: Chile)

28

slide-29
SLIDE 29

MMIS2 VU - Projects April 12th, 2016 Vedran Sabol

  • 4. Visualisation of Semantic Networks – Project Ideas
  • Ontology alignment
  • Ontologies define concepts (vocabularies) and relationships between them
  • Problem: different domains and view-points - diversity of conceptualizations
  • Ontology alignment: map concepts from different ontologies

Semantic Mediation Tool External Knowledge (WordNet…) Statistical Methods Visual Interface Linguistic Methods Explore, Understand, Review Knowledge Base Ontology A Ontology B Aligned Ontologies

match match

slide-30
SLIDE 30

MMIS2 VU - Projects April 12th, 2016 Vedran Sabol

  • 4. Visualisation of Semantic Networks – Suggested Data Sets
  • DBPedia data sets: http://wiki.dbpedia.org/Datasets
  • Ontology Alignment Evaluation Initiative (OAEI):

http://oaei.ontologymatching.org/2012/ (e.g. anatomy)

  • More details to be given in the lecture on the 10.05.
slide-31
SLIDE 31

MMIS2 VU - Projects April 12th, 2016 Vedran Sabol

Technical Prerequisites

  • Client: HTML5/JavaScript (a must)
  • With visualisation libraries such as D3.js, Sigma.js or Raphäel
  • Server:
  • Java (with Tomcat or Jetty)
  • Possibly using Apache Jena (Semantic Web framework)
  • Python
  • Possibly with NumPy (large array/matrix), SciPy (scientific/technical computing)
  • <your preferred Web development language/framework>
  • Also see

http://kti.tugraz.at/staff/vsabol/courses/mmis2/en/links.html

  • You don’t need everything, but some of these will be helpful

31

slide-32
SLIDE 32

MMIS2 VU - Projects April 12th, 2016 Vedran Sabol

Next Steps

  • Attend the next lectures with focus on the particular projects
  • 19.04.2016: 19.04.2016: Recommendation User Interfaces, Sensor Data

Visualisation (Cecilia, Gerwald)

  • 26.04.2016: Personalised, Automated Visualisation of Highdimensional Data

(Belgin)

  • 10.05.2016: Visual Analytics for Unstructured and Network Data (Vedran)
  • Lecture content
  • Introduction of visualisation and algorithm fundamentals
  • Technical information on software frameworks where you will integrate your

results

  • Ask questions to the framework authors!

32

slide-33
SLIDE 33

MMIS2 VU - Projects April 12th, 2016 Vedran Sabol

Next Steps

  • Upcoming deadlines:
  • Team building: 22.04.2016 (group registration in TeachCenter)
  • Project plan: 29.04.2016
  • Plan presentations: 03.05.2016

33

slide-34
SLIDE 34

MMIS2 VU - Projects April 12th, 2016 Vedran Sabol

Thank you

Questions?

34

slide-35
SLIDE 35

MMIS2 VU - Projects April 12th, 2016 Vedran Sabol

Exploit your Project Results

  • Possibility to develop your MMIS2 projects further
  • as Bachelor or Master’s Thesis
  • Contribute to EU research projects (EEXCESS, AFEL, MoreGrasp)
  • Open-source code base
  • Perform usability evaluations
  • Scientific publication, if results are adequate

35