• Ingen resultater fundet

AUTOMATING ANALYSIS

N/A
N/A
Info
Hent
Protected

Academic year: 2022

Del "AUTOMATING ANALYSIS"

Copied!
35
0
0

Indlæser.... (se fuldtekst nu)

Hele teksten

(1)

AUTOMATING ANALYSIS

...and making it work

(2)

DEFORMALYZE

• Experts in

• Computed Tomography

• Image analysis

• Statistics

• Data mining

• Mathematical modelling

• Services

• Consultancy

• Data analysis

• Software development

• Algorithms

• Customized systems

(3)

OUTLINE

CT IMAGE ANALYSIS ? CASE: PIGCLASSWEB

ISSUES TO CONSIDER

(4)

ANALYSIS ?

Extraction of Information

(5)

CT IMAGE ANALYSIS

• Materials Science

(6)

CT IMAGE ANALYSIS

• Materials Science

• Grain size

(7)

CT IMAGE ANALYSIS

• Materials Science

• Grain size

• Metrology

• Wall thickness

(8)

CT IMAGE ANALYSIS

• Materials Science

• Grain size

• Metrology

• Wall thickness

• Medical

• Tumor detection

(9)

CT IMAGE ANALYSIS

• Materials Science

• Grain size

• Metrology

• Wall thickness

• Medical

• Tumor detection

• Industrial

• Meat quality

(10)

CASE: PIGCLASSWEB

(11)

CASE: PIGCLASSWEB

(12)

CASE: PIGCLASSWEB

- System for

Retrieving

Storing

Processing

Analysing

- CT scans of pig carcasses

- Web-based interface for

Visualisation

Simulation

Statistical analysis - In the browser

- Developed for

(13)

Data Acquisition

CASE: PIGCLASSWEB

Object

Data Transmission Processing

Simulation

Storage

(14)

Data Acquisition

Data Transmission Processing

Simulation Storage

Object

(15)

CASE: PIGCLASSWEB

Data Transmission Processing

Simulation Storage

Object

Data Acquisition

(16)

Processing

Simulation Storage

Object

Data Acquisition

Data Transmission

(17)

CASE: PIGCLASSWEB

Simulation Storage

Object

Data Acquisition

Data Transmission

Processing

(18)

Simulation Object

Data Acquisition

Data Transmission Processing

Storage

(19)

CASE: PIGCLASSWEB

Object

Data Acquisition

Data Transmission Processing

Storage

Simulation

(20)

DATA ACQUISITION

• Position object

• Consistently

• Minimize artefacts

• Optimal settings

• Resolution / Amount of data

• Energy

• Price

• Reconstruction algorithm

• Operator

• Discipline

• Immediate feedback helps

ISSUES TO CONSIDER

(21)

CHOICE OF COORDINATE SYSTEM

DATA PROCESSING

ISSUES TO CONSIDER

(22)

CHOICE OF COORDINATE SYSTEM

DATA PROCESSING

ISSUES TO CONSIDER

(23)

DATA PROCESSING

ISSUES TO CONSIDER

MEASUREMENT REPEATABILITY

(24)

USABILITY

• Speed of response

• Reduce amount of data

• Graceful degradation

• Optimize by precalculation

• K.I.S.S.

• Visua-less

• Minimize click-ratio

ISSUES TO CONSIDER

(25)

AUTOMATION

Key Selling Points !

(26)

AUTOMATION

Key Selling Points !

(27)

AUTOMATION

• Less operator workload

Key Selling Points !

(28)

AUTOMATION

• Less operator workload

• Minimize drag’n’drop operations

Key Selling Points !

(29)

AUTOMATION

• Less operator workload

• Minimize drag’n’drop operations

• Increased volume - more data

Key Selling Points !

(30)

AUTOMATION

• Less operator workload

• Minimize drag’n’drop operations

• Increased volume - more data

• Focus time on what is important

Key Selling Points !

(31)

AUTOMATION

• Less operator workload

• Minimize drag’n’drop operations

• Increased volume - more data

• Focus time on what is important

• Population based information

Key Selling Points !

(32)

AUTOMATION

• Less operator workload

• Minimize drag’n’drop operations

• Increased volume - more data

• Focus time on what is important

• Population based information

• Sorting

Key Selling Points !

(33)

AUTOMATION

• Less operator workload

• Minimize drag’n’drop operations

• Increased volume - more data

• Focus time on what is important

• Population based information

• Sorting

• Automatic QC

Key Selling Points !

(34)

AUTOMATION

• Less operator workload

• Minimize drag’n’drop operations

• Increased volume - more data

• Focus time on what is important

• Population based information

• Sorting

• Automatic QC

• Product insight

Key Selling Points !

(35)

AUTOMATION

• Less operator workload

• Minimize drag’n’drop operations

• Increased volume - more data

• Focus time on what is important

• Population based information

• Sorting

• Automatic QC

• Product insight

• Data re-use!

Key Selling Points !

Referencer

RELATEREDE DOKUMENTER

The goal of this section is to give some context in terms of Bayesian data analysis, natural language processing, and topic modelling, and to describe the author-topic model and

INTRODUCTION / THEORETICAL BACKGROUND / EXPERIMENT SETUP / SIMULATION / SCENARIO 3 ANALYSIS / PLAN / CONCLUSIONS.. VEHICLE BASED INNOVATION VEHICLE

When a person arrives to an area / location, the mobile device(smartphone or laptop) re- ceives a signal from a beacon and the mobile device sends this data with user identification

Functional magnetic reso- nance imaging (fMRI) generates vast amounts of data. The han- dling, processing, and analysis of fMRI data would be incon- ceivable without

It is hypothesized that efficient data processing, analysis and visualization of smart metering data can help the DSOs in making useful decisions for future grid planning,

- Processing analytical data for BI (overnight long running data transformation) Not only store but validate and distribute:. - Data from different sources must

In this section a data set for In section 4 paired comparison (PC) models will be presented, as an introduction to the PC based ranking models, which account for the main focus of

Performance analysis using simulation data generated by Henon map and autoregressive (AR) models at different lengths and coupling strengths revealed that the proposed mean of