SlideShare a Scribd company logo
1 of 23
Download to read offline
The Socio-Technological
Integrator And Innovator
Digging Deeper into Data Processing with
Emphasis on Compositional and Microstructure
Data: Machine Learning in Support of
Archaeological Analysis
Liza Charalambous
liza.charalambous@eurocyinnovations.com
charalambous.elisavet@ucy.ac.cy
The Socio-Technological
Integrator And Innovator
Overview
1. Introduction
 Archaeological Process
 Data in many forms and types
2. Part I: Compositional Data
 Pre-Processing Practices
 Case Study & Experimental Results
3. Part II: Microstructure Data
 Microstructure Analysis
 Pattern Recognition for the Characterization of
Microstructure Data
4. Data Analysis Remarks
 Data Idiosyncrasies
The Socio-Technological
Integrator And Innovator
Profile and Background
 Real-time Monitoring
 Communication systems
 Security and Error Protection systems
 Research interests and Background
 Digital Signal Processing
 Artificial Intelligence
 Machine Learning
 Audio Coding
 PhD student in Computer Engineering at University of Cyprus
 In cooperation with the KIOS Research Center for Intelligent Systems and Networks
 NARNIA ITN ESR08 (starting date 01/11/2011)
 Educational Background
 BSc in IT and Multimedia Communications (2007-2010), Lancaster University, UK
 MSc in Digital Signal Processing and Intelligent Systems (2010-2011), Lancaster University,
UK
The Socio-Technological
Integrator And Innovator
Archaeological Data
Then Now
SKETCHES
STRATIGRAPHY LOGS
PETROGRAPHIC ANALYSIS
RELATIONAL
DATABASES
DIGITAL REPRESENTATIONS
3D RECONSTRUCTIONS
ELEMENTAL CONCENTRATIONS SPECTRA
The Socio-Technological
Integrator And Innovator
Gather Samples/
Artifacts
Technologies
Available
Methods
Data Analysis
Form Archaeological
Question
Interpretation
of Results
Analyze Objectives: What needs to
be proved?
Determine and gather the artifacts
of interest (based on the previously
formed question)
List available technologies for
deployment and analyze effectiveness
List available analysis methods
compatible to the selected technology
Application of Clustering/ Classification
algorithms so as to increase data
manageability
ARCHAEOLOGICAL PROCESS:
Steps
The Socio-Technological
Integrator And Innovator
“Too much and overly complicated data”
 Data analysis in archaeology, is sometimes
believed to take the form of:
 Simple projection of data (a feature against another)
 Employment of very simple clustering or other
dimensionality reduction methods
 Much attention is given when:
 Sampling
 Data preprocessing
ARCHAEOLOGICAL PROCESS:
Available Methods
belief that good data
will speak for themselves
The Socio-Technological
Integrator And Innovator
ARCHAEOLOGICAL PROCESS:
Technologies
 Analysis comes in different forms and shapes
 The result is usually in the form of:
 Peak elemental measurements → as a result of spectrum analysis
 Pictures or other schematic representations → commonly based on
the sample’s microstructure
 Each technology is dictated by its own characteristics,
integration of multiple technologies may not always be
beneficiary
The Socio-Technological
Integrator And Innovator
Overview
1. Introduction
 Archaeological Process
 Data in many forms and types
2. Part I: Compositional Data
 Pre-Processing Practices
 Case Study & Experimental Results
3. Part II: Microstructure Data
 Microstructure Analysis
 Pattern Recognition for the Characterization of
Microstructure Data
4. Data Analysis Remarks
 Data Idiosyncrasies
The Socio-Technological
Integrator And Innovator
Part I:
Compositional Data
Cu MnMg Ca
Ti
K
Fe SCr Al
 Compositional data are defined as
vectors of proportions
 strictly positive components
 constant sum; a restriction not always
maintained
 Chemical analysis is not really involved
in measuring, but in enumerating, or
counting, the number of each type of
atoms in a sample
 The results are usually given in relative
numbers (usually in % or ppm).
a) elemental concentrations are frequencies
of nominal or categorical classes (atoms)
of a classificatory concept (matter)
b) chemistry is usually interested not in
frequencies, but in relative frequencies.
The Socio-Technological
Integrator And Innovator
Part I:
Pre-Processing Practices
 General Belief:
The more precise and accurate the bulk chemical
determinations, the better the chance of making more plausible
and refined estimations.
 Reproducibility and comparability of results, is commonly
assured by adopting one of the following practices:
a) Transformation of the relative concentrations into base 10 values
b) Sub-compositional data: the dataset of interest only contains
proportions of the components constituting a sample
c) Calculation of averages
d) Elimination of chemical elements dominated by noisy readings or
incomplete measuring
The Socio-Technological
Integrator And Innovator
Part I:
Ceramics Case Study & Experimental Results
 Study the impact of pre-processing on datasets obtained from
ceramics with the use of NAA
 Investigations on the effect of the following parameters:
 Raw Vs. Log: the transformation of raw data into the equivalent 10-
base logarithm increased data separation (especially for the
heterogeneous ceramics)
 Sub-compositional data (with the addition of an extra column): has
not influenced in any significant way the product of analysis; practice
currently deployed in the archaeology domain
 Calculation of averages: reduced the variance of clusters between
successive runs; particularly useful for the analysis of homogeneous
material.
 Standardized and Normalized Data: no significant impact on the
commonly used analysis methods
The Socio-Technological
Integrator And Innovator
Overview
1. Introduction
 Archaeological Process
 Data in many forms and types
2. Part I: Compositional Data
 Pre-Processing Practices
 Case Study & Experimental Results
3. Part II: Microstructure Data
 Microstructure Analysis
 Pattern Recognition for the Characterization of
Microstructure Data
4. Data Analysis Remarks
 Data Idiosyncrasies
The Socio-Technological
Integrator And Innovator
Part II:
Microstructure Data
Involves the study of silicate and carbonate-based artifacts
which may be relatively unmodified from their original
geological parent raw materials
 Microstructure analysis is critical in extracting manufacturing
knowledge
 Can achieve resolution better than 1nm
 Can provide high quality imaging facilities together with
quantitative elemental analysis; using an energy dispersive
spectrometer
The Socio-Technological
Integrator And Innovator
Part II:
Microstructure Data Analysis
 Classification by taking into consideration how ceramics are
processed
 Related to the impact on material durability
 The nature of the ceramic microstructure, as a function of
temperature, can be related to the composition of the clay source
exploited
 Issues that an archaeological scientist may require to address
through SEM:
 Characterization of origin material
 Reconstruction of the technology involved in manufacture
 Influence of the place of manufacture or source of raw materials
 Changes that have occurred in the object during burial or storage
The Socio-Technological
Integrator And Innovator
Part II:
PR for the Characterization of Microstructure Data
Estimation of
Annealing
Temperature
Degree of
Vitrification
Porosity/
outer-
connection of
particles
Microstructure
Data
Evaluation of the sophistication of
firing process
Knowing the various nuances of materials and processing systems can
be overwhelming and confusing
 Properties of crystals
 Average size
 Orientation/Alignment
 Coarseness and depth of
primitive elements
 Vitrification Stage
 Identification of crystals
and degree of fusion
 Porosity
 Spread of pores
 Shape/size
The Socio-Technological
Integrator And Innovator
Part II:
PR for the Characterization of Microstructural Data
PIXEL POINT & GROUP PROCESSING
 Edge related operations
 Enhancement
 Segmentation
 Detection
 Texture Analysis
 Co-occurrence matrix: captures numerical
features which can be used to represent,
compare, and classify textures.
 Auto and cross correlation: can be used to
detect repetitive patterns of textures
 Estimation of patch similarity: gives the
ability to compare image regions
 Promoting of unit invariant measures
 Perforation
 Shape Factors
SHAPE FACTORS
 Aspect Ratio: function of the
largest and the smallest
diameters perpendicular to
each other
 Circularity: a function of the
perimeter and the area
 Elongation: ratio of minor axis
width to major axis length
ratio
 Compactness: measure of
object roundness area to
perimeter ratio
 Waviness shape factor of the
perimeter: often related to
fracture toughness of metals
and ceramics
The Socio-Technological
Integrator And Innovator
Overview
1. Introduction
 Archaeological Process
 Data in many forms and types
2. Part I: Compositional Data
 Pre-Processing Practices
 Case Study & Experimental Results
3. Part II: Microstructure Data
 Microstructure Analysis
 Pattern Recognition for the Characterization of
Microstructure Data
4. Data Analysis Remarks
 Data Idiosyncrasies
The Socio-Technological
Integrator And Innovator
 Not all features should be treated equally
 Artifacts are characterized by primary, secondary and
supplementary elements
 All artifacts regardless physical characteristics are treated
the same
 Size, shape, texture, contamination, aperture upon exposure
 Preprocessing steps and methodology
 Preprocessing of the data usually complies to the disciplines of
certain fixed procedures
 Effectiveness of an analysis method may be greatly influenced
by data preparation routines
 Important to maintain consistency
Data Analysis Remarks
The Socio-Technological
Integrator And Innovator
Problems of Archaeological Data
“THE VALUE OF DATA IS GIVEN BY THE ABILITY TO
EXTRACT INFORMATION.”
 Scarce and incomplete data
 High amounts of uncertainty and subjectivity
 Characterised by high degrees of redundancy
 Complex interactions between variables
 Analysis of findings with the use of different
technologies and analysts may result to be inaccurate
and imprecise
The Socio-Technological
Integrator And Innovator
 Barely affected by alteration or deterioration during burial,
they generally present the original trading goods, as far as
their material properties and composition are concerned.
 Very helpful in providing classification among ceramic assemblages
 Often giving information about their provenance or origin of
production
 Ceramics of the same production series may reveal a
characteristic elemental composition, usually distinct from
ceramics from other production places or series. Due to the:
 Geochemical diversity of raw material sources
 The variation in the pottery manufacturing process
DATA IDIOSYNCRASIES:
Ceramics
The Socio-Technological
Integrator And Innovator
 Prone to corrosion
 Different raw materials are
corroded at different rates and
degrees
 Corrosion is not uniform
 Assuming that the sample is
representative is not always trivial
 Sampling requires cleaning the outer surface
 Usually involves removing the outer coat
 Issues with licensing
 Due to the material’s flexibility, most of metal objects are not flat
 Alloys are challenging
DATA IDIOSYNCRASIES:
Metals
The Socio-Technological
Integrator And Innovator
 Notoriously homogeneous
 Very rarely found in large quantities
 Highly fragile
 Their usually thin structure makes artifact analysis a challenge
 Artifact in whole form are very rare to find
 Contamination over time
 Their analysis usually requires the use of acidic substances, for
cleaning the extra coating
 Sometimes alters some of their characteristics
 Against legislation restrictions
DATA IDIOSYNCRASIES:
Glass
The Socio-Technological
Integrator And Innovator
“I am enough of an artist to draw freely upon my imagination.
Imagination is more important than knowledge.
Knowledge is limited. Imagination encircles the world.”
Albert Einstein
Thank you for the attention!
Comments and Questions are Welcome!

More Related Content

What's hot

High Performance Nanocomposites for Mechanical Application: Design, Preparati...
High Performance Nanocomposites for Mechanical Application: Design, Preparati...High Performance Nanocomposites for Mechanical Application: Design, Preparati...
High Performance Nanocomposites for Mechanical Application: Design, Preparati...Alessio Passalacqua
 
International Journal of Bioinformatics & Biosciences (IJBB)
International Journal of Bioinformatics & Biosciences (IJBB)International Journal of Bioinformatics & Biosciences (IJBB)
International Journal of Bioinformatics & Biosciences (IJBB)ijfcst journal
 
Kaolinite/Polypropylene Nanocomposites. Part 3: 3D Printing
Kaolinite/Polypropylene Nanocomposites. Part 3: 3D PrintingKaolinite/Polypropylene Nanocomposites. Part 3: 3D Printing
Kaolinite/Polypropylene Nanocomposites. Part 3: 3D PrintingIRJET Journal
 
Main agri topics (51)
Main agri topics (51)Main agri topics (51)
Main agri topics (51)rohan_sagar
 

What's hot (9)

SEED IMAGE ANALYSIS
SEED IMAGE ANALYSISSEED IMAGE ANALYSIS
SEED IMAGE ANALYSIS
 
Yanning Li_CV
Yanning Li_CVYanning Li_CV
Yanning Li_CV
 
High Performance Nanocomposites for Mechanical Application: Design, Preparati...
High Performance Nanocomposites for Mechanical Application: Design, Preparati...High Performance Nanocomposites for Mechanical Application: Design, Preparati...
High Performance Nanocomposites for Mechanical Application: Design, Preparati...
 
International Journal of Bioinformatics & Biosciences (IJBB)
International Journal of Bioinformatics & Biosciences (IJBB)International Journal of Bioinformatics & Biosciences (IJBB)
International Journal of Bioinformatics & Biosciences (IJBB)
 
NON DESTRUCTIVE TESTING OF WELDED METALS TO ENHANCE THE QUALITY OF MATERIALS
NON DESTRUCTIVE TESTING OF WELDED METALS TO ENHANCE THE QUALITY OF MATERIALSNON DESTRUCTIVE TESTING OF WELDED METALS TO ENHANCE THE QUALITY OF MATERIALS
NON DESTRUCTIVE TESTING OF WELDED METALS TO ENHANCE THE QUALITY OF MATERIALS
 
Final Poster
Final PosterFinal Poster
Final Poster
 
Presentation leaflet - "Materials Research and Technology" (MRT) department
Presentation leaflet - "Materials Research and Technology" (MRT) departmentPresentation leaflet - "Materials Research and Technology" (MRT) department
Presentation leaflet - "Materials Research and Technology" (MRT) department
 
Kaolinite/Polypropylene Nanocomposites. Part 3: 3D Printing
Kaolinite/Polypropylene Nanocomposites. Part 3: 3D PrintingKaolinite/Polypropylene Nanocomposites. Part 3: 3D Printing
Kaolinite/Polypropylene Nanocomposites. Part 3: 3D Printing
 
Main agri topics (51)
Main agri topics (51)Main agri topics (51)
Main agri topics (51)
 

Viewers also liked

Ką apie medijas išpranašavo Back to the Future 2?
Ką apie medijas išpranašavo Back to the Future 2?Ką apie medijas išpranašavo Back to the Future 2?
Ką apie medijas išpranašavo Back to the Future 2?Karolis Rimkus
 
Post Power Syndrom
Post Power SyndromPost Power Syndrom
Post Power SyndromRahma Setya
 
Meaningful Marketing on the Budget: Karolis Rimkus at Best of Digital Marketi...
Meaningful Marketing on the Budget: Karolis Rimkus at Best of Digital Marketi...Meaningful Marketing on the Budget: Karolis Rimkus at Best of Digital Marketi...
Meaningful Marketing on the Budget: Karolis Rimkus at Best of Digital Marketi...Karolis Rimkus
 
A 1 Staffing Well Get The Job Done!
A 1 Staffing Well Get The Job Done!A 1 Staffing Well Get The Job Done!
A 1 Staffing Well Get The Job Done!a1staffing
 
Reklamos prekybos centruose apžvalga
Reklamos prekybos centruose apžvalgaReklamos prekybos centruose apžvalga
Reklamos prekybos centruose apžvalgaKarolis Rimkus
 
Undusting the foundations of compositional analysis approaches of ceramic arc...
Undusting the foundations of compositional analysis approaches of ceramic arc...Undusting the foundations of compositional analysis approaches of ceramic arc...
Undusting the foundations of compositional analysis approaches of ceramic arc...Liza Charalambous
 
Išskirtinės reklamos JAV vakarų pakrantėje
Išskirtinės reklamos JAV vakarų pakrantėjeIšskirtinės reklamos JAV vakarų pakrantėje
Išskirtinės reklamos JAV vakarų pakrantėjeKarolis Rimkus
 
Kekurangan cairan
Kekurangan cairanKekurangan cairan
Kekurangan cairanRahma Setya
 
Automated Motion Detection from space in sea surveillance
Automated Motion Detection from space in sea surveillanceAutomated Motion Detection from space in sea surveillance
Automated Motion Detection from space in sea surveillanceLiza Charalambous
 
Stresor Psikologik Lansia
Stresor Psikologik LansiaStresor Psikologik Lansia
Stresor Psikologik LansiaRahma Setya
 
Pendidikan Kesehatan Masyarakat
Pendidikan Kesehatan MasyarakatPendidikan Kesehatan Masyarakat
Pendidikan Kesehatan MasyarakatRahma Setya
 
Atgal į mokyklą: nestandartinės reklamos kanalai
Atgal į mokyklą: nestandartinės reklamos kanalaiAtgal į mokyklą: nestandartinės reklamos kanalai
Atgal į mokyklą: nestandartinės reklamos kanalaiKarolis Rimkus
 
Kas yra media agentūra ir kaip jai pateikti rėmimo pasiūlymus
Kas yra media agentūra ir kaip jai pateikti rėmimo pasiūlymusKas yra media agentūra ir kaip jai pateikti rėmimo pasiūlymus
Kas yra media agentūra ir kaip jai pateikti rėmimo pasiūlymusKarolis Rimkus
 
Gouth Athritis (Asam Urat)
Gouth Athritis (Asam Urat)Gouth Athritis (Asam Urat)
Gouth Athritis (Asam Urat)Rahma Setya
 
A Strategy for Reliability Evaluation and Fault Diagnosis of Autonomous Under...
A Strategy for Reliability Evaluation and Fault Diagnosis of Autonomous Under...A Strategy for Reliability Evaluation and Fault Diagnosis of Autonomous Under...
A Strategy for Reliability Evaluation and Fault Diagnosis of Autonomous Under...Koorosh Aslansefat
 

Viewers also liked (19)

カタログ2011ss
カタログ2011ssカタログ2011ss
カタログ2011ss
 
Ką apie medijas išpranašavo Back to the Future 2?
Ką apie medijas išpranašavo Back to the Future 2?Ką apie medijas išpranašavo Back to the Future 2?
Ką apie medijas išpranašavo Back to the Future 2?
 
Post Power Syndrom
Post Power SyndromPost Power Syndrom
Post Power Syndrom
 
Meaningful Marketing on the Budget: Karolis Rimkus at Best of Digital Marketi...
Meaningful Marketing on the Budget: Karolis Rimkus at Best of Digital Marketi...Meaningful Marketing on the Budget: Karolis Rimkus at Best of Digital Marketi...
Meaningful Marketing on the Budget: Karolis Rimkus at Best of Digital Marketi...
 
A 1 Staffing Well Get The Job Done!
A 1 Staffing Well Get The Job Done!A 1 Staffing Well Get The Job Done!
A 1 Staffing Well Get The Job Done!
 
Ageing proses
Ageing prosesAgeing proses
Ageing proses
 
Reklamos prekybos centruose apžvalga
Reklamos prekybos centruose apžvalgaReklamos prekybos centruose apžvalga
Reklamos prekybos centruose apžvalga
 
Undusting the foundations of compositional analysis approaches of ceramic arc...
Undusting the foundations of compositional analysis approaches of ceramic arc...Undusting the foundations of compositional analysis approaches of ceramic arc...
Undusting the foundations of compositional analysis approaches of ceramic arc...
 
ijazah dan transkip
ijazah dan transkipijazah dan transkip
ijazah dan transkip
 
Išskirtinės reklamos JAV vakarų pakrantėje
Išskirtinės reklamos JAV vakarų pakrantėjeIšskirtinės reklamos JAV vakarų pakrantėje
Išskirtinės reklamos JAV vakarų pakrantėje
 
Kekurangan cairan
Kekurangan cairanKekurangan cairan
Kekurangan cairan
 
Automated Motion Detection from space in sea surveillance
Automated Motion Detection from space in sea surveillanceAutomated Motion Detection from space in sea surveillance
Automated Motion Detection from space in sea surveillance
 
Stresor Psikologik Lansia
Stresor Psikologik LansiaStresor Psikologik Lansia
Stresor Psikologik Lansia
 
Pendidikan Kesehatan Masyarakat
Pendidikan Kesehatan MasyarakatPendidikan Kesehatan Masyarakat
Pendidikan Kesehatan Masyarakat
 
Meningitis
Meningitis Meningitis
Meningitis
 
Atgal į mokyklą: nestandartinės reklamos kanalai
Atgal į mokyklą: nestandartinės reklamos kanalaiAtgal į mokyklą: nestandartinės reklamos kanalai
Atgal į mokyklą: nestandartinės reklamos kanalai
 
Kas yra media agentūra ir kaip jai pateikti rėmimo pasiūlymus
Kas yra media agentūra ir kaip jai pateikti rėmimo pasiūlymusKas yra media agentūra ir kaip jai pateikti rėmimo pasiūlymus
Kas yra media agentūra ir kaip jai pateikti rėmimo pasiūlymus
 
Gouth Athritis (Asam Urat)
Gouth Athritis (Asam Urat)Gouth Athritis (Asam Urat)
Gouth Athritis (Asam Urat)
 
A Strategy for Reliability Evaluation and Fault Diagnosis of Autonomous Under...
A Strategy for Reliability Evaluation and Fault Diagnosis of Autonomous Under...A Strategy for Reliability Evaluation and Fault Diagnosis of Autonomous Under...
A Strategy for Reliability Evaluation and Fault Diagnosis of Autonomous Under...
 

Similar to Digging deeper into data processing with emphasis on computational and microstructure data_f

Data Science Solutions by Materials Scientists: The Early Case Studies
Data Science Solutions by Materials Scientists: The Early Case StudiesData Science Solutions by Materials Scientists: The Early Case Studies
Data Science Solutions by Materials Scientists: The Early Case StudiesTony Fast
 
An Introduction to CEMMNT
An Introduction to CEMMNTAn Introduction to CEMMNT
An Introduction to CEMMNTCEMMNT
 
J4.pdf additive manufacturing papers to study
J4.pdf additive manufacturing papers to studyJ4.pdf additive manufacturing papers to study
J4.pdf additive manufacturing papers to studyendarapuarun
 
Unraveling the Secrets to Optimizing Yield in Semiconductor Manufacturing.pptx
Unraveling the Secrets to Optimizing Yield in Semiconductor Manufacturing.pptxUnraveling the Secrets to Optimizing Yield in Semiconductor Manufacturing.pptx
Unraveling the Secrets to Optimizing Yield in Semiconductor Manufacturing.pptxyieldWerx Semiconductor
 
Establishing weightages of Criteria and Key Aspects for Quality Assessment of...
Establishing weightages of Criteria and Key Aspects for Quality Assessment of...Establishing weightages of Criteria and Key Aspects for Quality Assessment of...
Establishing weightages of Criteria and Key Aspects for Quality Assessment of...IRJET Journal
 
The Case for Materials Characterization
The Case for Materials CharacterizationThe Case for Materials Characterization
The Case for Materials CharacterizationRobert Cormia
 
Rocca Fellow Pedroni
Rocca Fellow PedroniRocca Fellow Pedroni
Rocca Fellow PedroniRocca Fellows
 
Information sciences to fuel the data age of materials science
Information sciences to fuel the data age of materials scienceInformation sciences to fuel the data age of materials science
Information sciences to fuel the data age of materials scienceTony Fast
 
A review study of mechanical fatigue testing methods for small scale metal ma...
A review study of mechanical fatigue testing methods for small scale metal ma...A review study of mechanical fatigue testing methods for small scale metal ma...
A review study of mechanical fatigue testing methods for small scale metal ma...Alexander Decker
 
Advanced Intelligent Systems - 2020 - Sha - Artificial Intelligence to Power ...
Advanced Intelligent Systems - 2020 - Sha - Artificial Intelligence to Power ...Advanced Intelligent Systems - 2020 - Sha - Artificial Intelligence to Power ...
Advanced Intelligent Systems - 2020 - Sha - Artificial Intelligence to Power ...remAYDOAN3
 
Nikolaos Sotiriou, Presentation VLE-200989847
Nikolaos Sotiriou, Presentation VLE-200989847Nikolaos Sotiriou, Presentation VLE-200989847
Nikolaos Sotiriou, Presentation VLE-200989847Nicholas Sotiriou
 
The Role of Probe Card Manufacturers in Advancing Semiconductor Technology
The Role of Probe Card Manufacturers in Advancing Semiconductor TechnologyThe Role of Probe Card Manufacturers in Advancing Semiconductor Technology
The Role of Probe Card Manufacturers in Advancing Semiconductor TechnologySemi Probes Inc
 
A survey on fem modelling for composites
A survey on fem modelling for compositesA survey on fem modelling for composites
A survey on fem modelling for compositeseSAT Publishing House
 
1.07_Barrick_SETACPittsburgh.pdf
1.07_Barrick_SETACPittsburgh.pdf1.07_Barrick_SETACPittsburgh.pdf
1.07_Barrick_SETACPittsburgh.pdfAndrew Barrick
 
Final Report Functional Coatings for 3D Printed Parts_JONATHANAMBROSE
Final Report Functional Coatings for 3D Printed Parts_JONATHANAMBROSEFinal Report Functional Coatings for 3D Printed Parts_JONATHANAMBROSE
Final Report Functional Coatings for 3D Printed Parts_JONATHANAMBROSEJonathan Ambrose
 

Similar to Digging deeper into data processing with emphasis on computational and microstructure data_f (20)

Data Science Solutions by Materials Scientists: The Early Case Studies
Data Science Solutions by Materials Scientists: The Early Case StudiesData Science Solutions by Materials Scientists: The Early Case Studies
Data Science Solutions by Materials Scientists: The Early Case Studies
 
An Introduction to CEMMNT
An Introduction to CEMMNTAn Introduction to CEMMNT
An Introduction to CEMMNT
 
J4.pdf additive manufacturing papers to study
J4.pdf additive manufacturing papers to studyJ4.pdf additive manufacturing papers to study
J4.pdf additive manufacturing papers to study
 
Unraveling the Secrets to Optimizing Yield in Semiconductor Manufacturing.pptx
Unraveling the Secrets to Optimizing Yield in Semiconductor Manufacturing.pptxUnraveling the Secrets to Optimizing Yield in Semiconductor Manufacturing.pptx
Unraveling the Secrets to Optimizing Yield in Semiconductor Manufacturing.pptx
 
Establishing weightages of Criteria and Key Aspects for Quality Assessment of...
Establishing weightages of Criteria and Key Aspects for Quality Assessment of...Establishing weightages of Criteria and Key Aspects for Quality Assessment of...
Establishing weightages of Criteria and Key Aspects for Quality Assessment of...
 
The Case for Materials Characterization
The Case for Materials CharacterizationThe Case for Materials Characterization
The Case for Materials Characterization
 
Rocca Fellow Pedroni
Rocca Fellow PedroniRocca Fellow Pedroni
Rocca Fellow Pedroni
 
Resume_Spackman_2017
Resume_Spackman_2017Resume_Spackman_2017
Resume_Spackman_2017
 
Mems ppt
Mems pptMems ppt
Mems ppt
 
Information sciences to fuel the data age of materials science
Information sciences to fuel the data age of materials scienceInformation sciences to fuel the data age of materials science
Information sciences to fuel the data age of materials science
 
Harrison - Low Density Materials - Spring Review 2013
Harrison - Low Density Materials - Spring Review 2013Harrison - Low Density Materials - Spring Review 2013
Harrison - Low Density Materials - Spring Review 2013
 
A review study of mechanical fatigue testing methods for small scale metal ma...
A review study of mechanical fatigue testing methods for small scale metal ma...A review study of mechanical fatigue testing methods for small scale metal ma...
A review study of mechanical fatigue testing methods for small scale metal ma...
 
Advanced Intelligent Systems - 2020 - Sha - Artificial Intelligence to Power ...
Advanced Intelligent Systems - 2020 - Sha - Artificial Intelligence to Power ...Advanced Intelligent Systems - 2020 - Sha - Artificial Intelligence to Power ...
Advanced Intelligent Systems - 2020 - Sha - Artificial Intelligence to Power ...
 
Nikolaos Sotiriou, Presentation VLE-200989847
Nikolaos Sotiriou, Presentation VLE-200989847Nikolaos Sotiriou, Presentation VLE-200989847
Nikolaos Sotiriou, Presentation VLE-200989847
 
The Role of Probe Card Manufacturers in Advancing Semiconductor Technology
The Role of Probe Card Manufacturers in Advancing Semiconductor TechnologyThe Role of Probe Card Manufacturers in Advancing Semiconductor Technology
The Role of Probe Card Manufacturers in Advancing Semiconductor Technology
 
A survey on fem modelling for composites
A survey on fem modelling for compositesA survey on fem modelling for composites
A survey on fem modelling for composites
 
PM_PhD_thesis
PM_PhD_thesisPM_PhD_thesis
PM_PhD_thesis
 
Bionanomanufacturing at IPT
Bionanomanufacturing at IPTBionanomanufacturing at IPT
Bionanomanufacturing at IPT
 
1.07_Barrick_SETACPittsburgh.pdf
1.07_Barrick_SETACPittsburgh.pdf1.07_Barrick_SETACPittsburgh.pdf
1.07_Barrick_SETACPittsburgh.pdf
 
Final Report Functional Coatings for 3D Printed Parts_JONATHANAMBROSE
Final Report Functional Coatings for 3D Printed Parts_JONATHANAMBROSEFinal Report Functional Coatings for 3D Printed Parts_JONATHANAMBROSE
Final Report Functional Coatings for 3D Printed Parts_JONATHANAMBROSE
 

Digging deeper into data processing with emphasis on computational and microstructure data_f

  • 1. The Socio-Technological Integrator And Innovator Digging Deeper into Data Processing with Emphasis on Compositional and Microstructure Data: Machine Learning in Support of Archaeological Analysis Liza Charalambous liza.charalambous@eurocyinnovations.com charalambous.elisavet@ucy.ac.cy
  • 2. The Socio-Technological Integrator And Innovator Overview 1. Introduction  Archaeological Process  Data in many forms and types 2. Part I: Compositional Data  Pre-Processing Practices  Case Study & Experimental Results 3. Part II: Microstructure Data  Microstructure Analysis  Pattern Recognition for the Characterization of Microstructure Data 4. Data Analysis Remarks  Data Idiosyncrasies
  • 3. The Socio-Technological Integrator And Innovator Profile and Background  Real-time Monitoring  Communication systems  Security and Error Protection systems  Research interests and Background  Digital Signal Processing  Artificial Intelligence  Machine Learning  Audio Coding  PhD student in Computer Engineering at University of Cyprus  In cooperation with the KIOS Research Center for Intelligent Systems and Networks  NARNIA ITN ESR08 (starting date 01/11/2011)  Educational Background  BSc in IT and Multimedia Communications (2007-2010), Lancaster University, UK  MSc in Digital Signal Processing and Intelligent Systems (2010-2011), Lancaster University, UK
  • 4. The Socio-Technological Integrator And Innovator Archaeological Data Then Now SKETCHES STRATIGRAPHY LOGS PETROGRAPHIC ANALYSIS RELATIONAL DATABASES DIGITAL REPRESENTATIONS 3D RECONSTRUCTIONS ELEMENTAL CONCENTRATIONS SPECTRA
  • 5. The Socio-Technological Integrator And Innovator Gather Samples/ Artifacts Technologies Available Methods Data Analysis Form Archaeological Question Interpretation of Results Analyze Objectives: What needs to be proved? Determine and gather the artifacts of interest (based on the previously formed question) List available technologies for deployment and analyze effectiveness List available analysis methods compatible to the selected technology Application of Clustering/ Classification algorithms so as to increase data manageability ARCHAEOLOGICAL PROCESS: Steps
  • 6. The Socio-Technological Integrator And Innovator “Too much and overly complicated data”  Data analysis in archaeology, is sometimes believed to take the form of:  Simple projection of data (a feature against another)  Employment of very simple clustering or other dimensionality reduction methods  Much attention is given when:  Sampling  Data preprocessing ARCHAEOLOGICAL PROCESS: Available Methods belief that good data will speak for themselves
  • 7. The Socio-Technological Integrator And Innovator ARCHAEOLOGICAL PROCESS: Technologies  Analysis comes in different forms and shapes  The result is usually in the form of:  Peak elemental measurements → as a result of spectrum analysis  Pictures or other schematic representations → commonly based on the sample’s microstructure  Each technology is dictated by its own characteristics, integration of multiple technologies may not always be beneficiary
  • 8. The Socio-Technological Integrator And Innovator Overview 1. Introduction  Archaeological Process  Data in many forms and types 2. Part I: Compositional Data  Pre-Processing Practices  Case Study & Experimental Results 3. Part II: Microstructure Data  Microstructure Analysis  Pattern Recognition for the Characterization of Microstructure Data 4. Data Analysis Remarks  Data Idiosyncrasies
  • 9. The Socio-Technological Integrator And Innovator Part I: Compositional Data Cu MnMg Ca Ti K Fe SCr Al  Compositional data are defined as vectors of proportions  strictly positive components  constant sum; a restriction not always maintained  Chemical analysis is not really involved in measuring, but in enumerating, or counting, the number of each type of atoms in a sample  The results are usually given in relative numbers (usually in % or ppm). a) elemental concentrations are frequencies of nominal or categorical classes (atoms) of a classificatory concept (matter) b) chemistry is usually interested not in frequencies, but in relative frequencies.
  • 10. The Socio-Technological Integrator And Innovator Part I: Pre-Processing Practices  General Belief: The more precise and accurate the bulk chemical determinations, the better the chance of making more plausible and refined estimations.  Reproducibility and comparability of results, is commonly assured by adopting one of the following practices: a) Transformation of the relative concentrations into base 10 values b) Sub-compositional data: the dataset of interest only contains proportions of the components constituting a sample c) Calculation of averages d) Elimination of chemical elements dominated by noisy readings or incomplete measuring
  • 11. The Socio-Technological Integrator And Innovator Part I: Ceramics Case Study & Experimental Results  Study the impact of pre-processing on datasets obtained from ceramics with the use of NAA  Investigations on the effect of the following parameters:  Raw Vs. Log: the transformation of raw data into the equivalent 10- base logarithm increased data separation (especially for the heterogeneous ceramics)  Sub-compositional data (with the addition of an extra column): has not influenced in any significant way the product of analysis; practice currently deployed in the archaeology domain  Calculation of averages: reduced the variance of clusters between successive runs; particularly useful for the analysis of homogeneous material.  Standardized and Normalized Data: no significant impact on the commonly used analysis methods
  • 12. The Socio-Technological Integrator And Innovator Overview 1. Introduction  Archaeological Process  Data in many forms and types 2. Part I: Compositional Data  Pre-Processing Practices  Case Study & Experimental Results 3. Part II: Microstructure Data  Microstructure Analysis  Pattern Recognition for the Characterization of Microstructure Data 4. Data Analysis Remarks  Data Idiosyncrasies
  • 13. The Socio-Technological Integrator And Innovator Part II: Microstructure Data Involves the study of silicate and carbonate-based artifacts which may be relatively unmodified from their original geological parent raw materials  Microstructure analysis is critical in extracting manufacturing knowledge  Can achieve resolution better than 1nm  Can provide high quality imaging facilities together with quantitative elemental analysis; using an energy dispersive spectrometer
  • 14. The Socio-Technological Integrator And Innovator Part II: Microstructure Data Analysis  Classification by taking into consideration how ceramics are processed  Related to the impact on material durability  The nature of the ceramic microstructure, as a function of temperature, can be related to the composition of the clay source exploited  Issues that an archaeological scientist may require to address through SEM:  Characterization of origin material  Reconstruction of the technology involved in manufacture  Influence of the place of manufacture or source of raw materials  Changes that have occurred in the object during burial or storage
  • 15. The Socio-Technological Integrator And Innovator Part II: PR for the Characterization of Microstructure Data Estimation of Annealing Temperature Degree of Vitrification Porosity/ outer- connection of particles Microstructure Data Evaluation of the sophistication of firing process Knowing the various nuances of materials and processing systems can be overwhelming and confusing  Properties of crystals  Average size  Orientation/Alignment  Coarseness and depth of primitive elements  Vitrification Stage  Identification of crystals and degree of fusion  Porosity  Spread of pores  Shape/size
  • 16. The Socio-Technological Integrator And Innovator Part II: PR for the Characterization of Microstructural Data PIXEL POINT & GROUP PROCESSING  Edge related operations  Enhancement  Segmentation  Detection  Texture Analysis  Co-occurrence matrix: captures numerical features which can be used to represent, compare, and classify textures.  Auto and cross correlation: can be used to detect repetitive patterns of textures  Estimation of patch similarity: gives the ability to compare image regions  Promoting of unit invariant measures  Perforation  Shape Factors SHAPE FACTORS  Aspect Ratio: function of the largest and the smallest diameters perpendicular to each other  Circularity: a function of the perimeter and the area  Elongation: ratio of minor axis width to major axis length ratio  Compactness: measure of object roundness area to perimeter ratio  Waviness shape factor of the perimeter: often related to fracture toughness of metals and ceramics
  • 17. The Socio-Technological Integrator And Innovator Overview 1. Introduction  Archaeological Process  Data in many forms and types 2. Part I: Compositional Data  Pre-Processing Practices  Case Study & Experimental Results 3. Part II: Microstructure Data  Microstructure Analysis  Pattern Recognition for the Characterization of Microstructure Data 4. Data Analysis Remarks  Data Idiosyncrasies
  • 18. The Socio-Technological Integrator And Innovator  Not all features should be treated equally  Artifacts are characterized by primary, secondary and supplementary elements  All artifacts regardless physical characteristics are treated the same  Size, shape, texture, contamination, aperture upon exposure  Preprocessing steps and methodology  Preprocessing of the data usually complies to the disciplines of certain fixed procedures  Effectiveness of an analysis method may be greatly influenced by data preparation routines  Important to maintain consistency Data Analysis Remarks
  • 19. The Socio-Technological Integrator And Innovator Problems of Archaeological Data “THE VALUE OF DATA IS GIVEN BY THE ABILITY TO EXTRACT INFORMATION.”  Scarce and incomplete data  High amounts of uncertainty and subjectivity  Characterised by high degrees of redundancy  Complex interactions between variables  Analysis of findings with the use of different technologies and analysts may result to be inaccurate and imprecise
  • 20. The Socio-Technological Integrator And Innovator  Barely affected by alteration or deterioration during burial, they generally present the original trading goods, as far as their material properties and composition are concerned.  Very helpful in providing classification among ceramic assemblages  Often giving information about their provenance or origin of production  Ceramics of the same production series may reveal a characteristic elemental composition, usually distinct from ceramics from other production places or series. Due to the:  Geochemical diversity of raw material sources  The variation in the pottery manufacturing process DATA IDIOSYNCRASIES: Ceramics
  • 21. The Socio-Technological Integrator And Innovator  Prone to corrosion  Different raw materials are corroded at different rates and degrees  Corrosion is not uniform  Assuming that the sample is representative is not always trivial  Sampling requires cleaning the outer surface  Usually involves removing the outer coat  Issues with licensing  Due to the material’s flexibility, most of metal objects are not flat  Alloys are challenging DATA IDIOSYNCRASIES: Metals
  • 22. The Socio-Technological Integrator And Innovator  Notoriously homogeneous  Very rarely found in large quantities  Highly fragile  Their usually thin structure makes artifact analysis a challenge  Artifact in whole form are very rare to find  Contamination over time  Their analysis usually requires the use of acidic substances, for cleaning the extra coating  Sometimes alters some of their characteristics  Against legislation restrictions DATA IDIOSYNCRASIES: Glass
  • 23. The Socio-Technological Integrator And Innovator “I am enough of an artist to draw freely upon my imagination. Imagination is more important than knowledge. Knowledge is limited. Imagination encircles the world.” Albert Einstein Thank you for the attention! Comments and Questions are Welcome!