1. Review Meeting
1st Reporting Period – Project Overview
Maria Letizia Gualandi
Gabriele Gattiglia
Francesca Anichini
Brussels, 22nd June 2017 | 9.30
REA, Covent Garden, 16 Place Rogier
2. Summary
Summary
• Project Overview:
• Objectives
• Real users needs
• Management:
• Results
• Problems and deviations
• Data Management Plan
• Financial issue
3. Review Meeting
1st Reporting Period – Project Overview
Every day, Archaeologists have to recognise and classify
thousand and thousand of pottery sherds
4. Review Meeting
1st Reporting Period – Project Overview
A lot of ceramic finds boxes
for a few m2 of excavated surface ...
5. Review Meeting
1st Reporting Period – Project Overview
Kwang-chih Chang, archaeologist in the Harvard University,
said that it is reasonable to estimate that 80 or 90% of the time and energy of an archaeologist
it is spent in the classification of excavation finds… (Rethinking Archaeology, 1967)
…and the 80-90 % of finds are pottery sherds
6. Review Meeting
1st Reporting Period – Project Overview
to lay the table
to cook food
to bottle food
to light
to carry food
This depends on the fact that from the Neolithic, pottery was used for a lot of utilitarian purposes
to store balms
and scented oils
7. Review Meeting
1st Reporting Period – Project Overview
In addition to this, pottery is indestructible: it breaks but does not disappear
like perishable goods (wood, textiles, food, parchment, papyrus…)
8. Review Meeting
1st Reporting Period – Project Overview
Consequently pottery sherds are
the index fossils for the Archaeologists,
who use them for:
- the comprehension and dating of the archaeological contexts,
- understanding the dynamics of production, trade flows, social interactions.
9. Review Meeting
1st Reporting Period – Project Overview
Therefore pottery is for the archaeologists
an extraordinary window open on the past
Unfortunately, classification of pottery
sherds requires complex skills
and it is a very time consuming activity,
both for researchers and professionals
10. Review Meeting
1st Reporting Period – Project Overview
To classify pottery sherds means
moving from the 3-dimensional fragment
to its 2-dimensional shape,
published in the catalogues
11. Review Meeting
1st Reporting Period – Project Overview
But the the catalogues are
many, fragmented and
incoherent.
Their consultation is a long
and fatiguing work
also when is available
a well furnished library …
… but it is not easy to have
a well furnished library in
remote corners of the
world where usually
Archaeologists work
(the desert of Egypt, the
Anatolian plateau,
a little island of the
Greece…)
12. Review Meeting
1st Reporting Period – Project Overview
ArchAIDE project
The objective of ArchAIDE is:
- to support the classification and interpretation
work of archaeologists with innovative
computer-based tools, able to provide the user
with features for the semiautomatic
description and matching of potsherds over
the huge existing ceramic catalogues;
- to support the work of archaeologists in order
to meet real user needs and generate
economic benefits, reducing time and costs.
This would create societal benefits from
cultural heritage, improving access, re-use and
exploitation of the digital cultural heritage in a
sustainable way.
IDEA
14. Review Meeting
1st Reporting Period – Project Overview
ArchAIDE approach is very similar
to archaeologists’s traditional working methods
For instance,
profile-based
approaches,
heavily used in
archaeological
practice, are an
ideal approach to
support
classification …
15. Review Meeting
1st Reporting Period – Project Overview
OBJECTIVES OF THE PROJECT:
1. Digital pottery catalogue
The first contribution of ArchAIDE will be an as-automatic-as-possible procedure
to transform the paper catalogues in a digital description,
to be used as a data pool for an accurate search and retrieval process
2a. A tool for on-site and off-site documentation of pottery sherds
A tool (mainly designed for mobile devices) that will support archaeologists
in recognizing and classifying potsherds during excavation and post-excavation analysis,
through an easy-to-use interface and efficient algorithms for characterisation, search
and retrieval of the visual/geometrical correspondences
2b. An automatic procedure or deriving a potsherd identity card
An automatic procedure to derive a complete potsherds identity card by transforming
the data collected into a formatted electronic document, printable or visual
3. A web-based real-time data visualisation
to improve access to archaeological heritage and generate new understanding
4. An open archive to allow the archival and re-use of archaeological data,
transforming them into common heritage and permitting economic sustainability
19. N. Title WP Leader Type Dissemination Due Date
D9.1 Communication plan 9 UNIPI Report Confidential (3) AUG.2016
D10.1 Dissemination plan 10 UoY Report Public (3) AUG.2016
D1.1 Quality plan 1 UNIPI Report Confidential (4) SEPT.2016
D9.2 Website and
Promotional kit
9 UNIPI Websites, patents
filling, etc.
Public (6) NOV.2016
D10.2 Data Management
Plan
10 UoY Report Public (6) NOV.2016
D1.2 IPR and knowledge
Management Plan
1 UNIPI Report Confidential (8) JAN.2017
D2.1 Detailed system specification,
including the representation
structure for shape data
2 UNIPI Report Confidential (8) JAN. 2017
D1.3 Financial report 1 1 UNIPI Report Confidential (12) MAY 2017
D1.4 Progress report 1 1 UNIPI Report Public (12) MAY 2017
D6.1 Algorithms for pairwise
similarity between ceramics
based on appearance (software)
6 TAU Other Confidential (12) MAY 2017
What’s done, is done
20. N. Title WP Leader Due Date Verification
MS1 Preliminary report about the
archaeological and technical
specification of the system. The
release of this report permit to
start WPs 3, 4 and 6.
2 UNIPI (4) SEPT.2016 Release of the deliverable
D2.1 Report on
methodologies, scenario and
user requirements.
MS2 First version of the database
ready for being populated
3 UoY (8) JAN.2017 Release of the deliverable
D3.1 Final release of the
database implementation
(software)
MS3 First validated version of the
technologies for the digitization of
paper catalogues ready to be
used for starting DB population
4 CNR (8) JAN.2017 Achievement of MS4 First
release
of the populated database
What’s done, is done
22. 1. Enable scalable and cost-effective documentation of archaeological findings.
Completion criteria:
The demonstration of a hardware and software system prototype capable to quickly
and semi-automatically acquire shape characteristics of archaeological findings
(focusing on small scale artefacts and based on digital photography).
M21(early release)
M32 (final release)
Objectives
23. Activities:
• eliciting the requirements of the archaeologists in terms of which information
need to be stored, the level of details and the format;
• discussion about the way in which the mobile and desktop tools would integrate
in the archaeological processes (excavation, classification, dating, etc.).
Results:
• the final design of the “Results Database” (to store findings data)
• and the production of preliminary design of the mobile app functionalities based
on the User Centered Design methodology
Objectives
24. 2. Enable digitization of current catalogues (by automatic processes), including
the conversion from raster to digital conceptual models of the artefact classes
defined in the catalogues.
Completion Criteria:
demonstration of a system prototype for the digitization of the catalogue and the
production of conceptual models of the classes defined.
M16 (final release)
M18 (evaluation)
Objectives
25. Activities:
• choice of the pottery classes and the associated paper catalogues;
• mapping of the structure of the paper catalogues;
• Definition of the geometric and appearance features that can be extracted from
the catalogues and from the images taken on-site.
Objectives
Results:
• development of OCR tools
to support the work of
database population;
• development, for shape-
based classification, of an
automatic digitization
pipeline, to extract the
geometric features and
build a 3D representation;
• first prototype of the tools
in M8.
26. 3. Enable on-the-field support to the archaeologist in the interpretation phase.
Completion criteria:
The demonstration of an enhanced version of the system running on mobile
platforms, which will include also the component supporting the interpretation
phase. Instruments for supporting the professional in the visual analysis of the
finding.
M21 (early release)
M32 (final release)
M32 (evaluation)
Objectives
27. +
SeARCH
1210-1280
Table ware
Pisa
Flat
Basin
Geometric decoration
Maiolica arcaica
G., Berti, 1997
La maiolica
Arcaia Pisana
Activities:
• realisation of the ArchAIDE
system Mock-up;
• definition of the technical
architecture for the mobile
tool and desktop tool.
Results:
• implementation of the core
components of the mobile
tool (communication, user
authentication, 2D image
acquisition, etc.)
Objectives
28. 4. Enable the archival of all data produced on a remote archive, supporting also
access through advanced presentation tools.
Completion Criteria:
The demonstration of the complete version of the system running on mobile
platforms and standard web-based interface, which will include the final
component for data archival on remote repositories. The system will enable the
archival of all data produced: textual data, raw images, models produced (2D
drawings, 3D models), results of the interpretation phase, etc.
M21 (early release)
M32 (final release)
M32 (evaluation)
Objectives
29. Activities:
• definition of the “Reference database” to
be used for matching and interpretation
of excavation findings.
• analysis and design of the visual
presentation of the ceramic types
Results:
• first release of the Reference Database:
the system allows the archival of
information, depictions (2D, 3D, SVG,
etc.) and geographical info about origin,
fabrics and occurrences (where was
found);
• starting the population of the database;
• first prototype of user interface.
Objectives
30. 5. Enable reuse of all data collected and preserved in the open data repository
Completion Criteria:
The realisation of an open data archival policy, which is able to provide long-
term preservation and as wide as possible data reuse.
The release of web APIs for REST services, in order to allow the creation of new
applications and the possible economic exploitation of the data collected.
M32 (final release)
Objectives
31. Activities:
Discussion about policy to be
adopted in order to educate
users to open data
Results:
Online data management plan
(D10.2) completed and
available to all partners:
http://dmponline.dcc.ac.uk/pr
ojects/archaide-horizon-2020-
dmp
Objectives
32. TASK 10.2 Data preservation
Leader: UoY
• Main reference document is the Data Management Plan (DMP)
https://dmponline.dcc.ac.uk/projects/archaide-horizon-2020-dmp
• Created using the Open Research Data Pilot tool
• Follows Guidelines on FAIR Data Management in Horizon 2020
• The DMP is a living document – periodically reviewed and edited to reflect
changes in the project.
• DMP outlines requirements that influence the project during immediate
lifetime e.g.
• Metadata
• Formats
• Also covers work of the ADS in holding the data in perpetuity:
• Open Access
• Interoperability (Open formats, metadata)
Data Preservation
33.
34. Data Preservation
TASK 10.2 Data preservation
Leader: UoY
• At the end of the project the following data will the archived with the
ADS:
• All data within the Reference database (catalogue data, images,
models etc)
• A subset of data (copyright permitting) from the first use of the
Results database
• Data available via its own collection within ADS archive
• Accompanied by rich metadata permitting wide array of re-use
• Potential for use of object-level data within the ADS Linked Data store
35. 6. Evaluating the impact in real conditions
Completion Criteria:
The objective and subjective evaluation of principal system components,
performed by means of experiments and user studies developed in real working
conditions.
Month 32 (final release)
Objectives
36. 6. Evaluating the impact in real
conditions
Activities
• Discussion about real user needs;
• Discussion about archaeological sites for test bed cases.
Results
• realisation of the ArchAIDE system Mock-up, designed for working in real
excavation condition.
37. 7. Establishing the conditions for a successful adoption and exploitation of
project outcomes
Completion Criteria
Live demonstration of the system in real excavation settings; the delivery of the
tools to sample users even external to the consortium.
Setting-up of the dissemination and commercialisation network, including an
attractive and regularly updated website and other communication means.
Active consideration of standardisation opportunities of the domain.
Month 33 (final release)
Objectives
38. Activities:
• discussion on the potential exploitation
of the outcomes. In particular, the issue
of copyright (re-use of data) and the
perspective role and use of the ArchAIDE
database were taken into account.
Results
• D1.2 IPR and Knowledge Management
Plan
• D10.5 Preliminary Exploitation Plan as a
living document
Objectives
40. Problems and deviations
Task 5.3 Database population
the work on
the medieval
and
postmedieval
pottery was
more complex
than expected
complexity
of appearance
based
similarity
training
quantity and
quality of
data
41. Problems and deviations
Mitigation measures
we propose extension of WP5 to month 28
• 12 pottery catalogues are already scanned;
• More than 500 form types already populate the database
• The archaeological partners have achieved the possibility to
obtain new photomaterial from 36 excavations
sites/Museums/research teams in Spain and in Italy
• UB will start a PhD on ArchAIDE for working on Majolica
• UNIPI will start to work with students
• We have more than 20 associates that can take pottery
photographs
42. Problems and deviations
Task 6.1 Appearance-based search
and retrieval over a database of shapes
lack of
training data
no unified
archaeological
definition for
appearance-
based similarity
Less
structured
catalogues
43. Problems and deviations
Mitigation measures
Working on Stamps for developing appearance based similarity.
less images needed
more online useful photomaterial
Working on Majolica di Montelupo for developing appearance based similarity.
well structured catalogue
44. Problems and deviations
Task 9.2 “The project logo will
be trademarked at the EU
Office for harmonization in the
Internal Market”
different
possibilities
for
trademarking
it have been
studied
UNIPI is the
only partner
interested in
trademarking
it
the project
logo has been
created
decision of postponing the trademarking
45. Problems and deviations
Creation of
the
"Associates”
page on the
website.
communication
through social
media
Task 9.3 “We will send online newsletter, (…). Newsletter
will be available in pdf format through the project website.”
Using Associates and social media as a different
method to communicate and involve audience
Each partner will use its mailing list for communicating
to the audience
48. Financial Statement
Reporting Period 1
Periodic summary financial statement - Reporting Period 1
Direct personnel costs declared as actual costs 521.522,98 €
Direct personnel costs declared as unit costs (average costs) 21.884,72 €
Direct cost of subcontracting - €
Use of in kind contribution from third party - €
Other direct costs 38.664,47 €
Indirect costs 145.518,06 €
Total costs 727.590,23 €
Maximun EU contribution 690.715,40 €
Requested EU contribution 690.715,40 €
50. Financial Statement
Reporting Period 1
521,522.98 €
21,884.72 € - € - €
38,664.47 €
145,518.06 €
€1,569,087.40
€139,486.19 €122,000.00
€302,040.00
€502,653.40
- €
200,000.00 €
400,000.00 €
600,000.00 €
800,000.00 €
1,000,000.00 €
1,200,000.00 €
1,400,000.00 €
1,600,000.00 €
1,800,000.00 €
Direct personnel costs
declared as actual costs
Direct personnel costs
declared as unit costs
(average costs)
Direct cost of
subcontracting
Use of in kind
contribution from third
party
Other direct costs Indirect costs
Categories of cost: Reporting Period 1 / Budget of action
33,24%
15,69%
12,80%
51. Financial Statement
Reporting Period 1
Categories of cost for Reporting Period 1
89%
4%
7%
Direct personnel costs declared as
actual costs
Direct personnel costs declared as unit
costs (average costs)
Other direct costs
52. Financial Statement
Reporting Period 1
Travel
54%
Other Good &
Services
36%
Equipment
10%
Other direct costs
Travel 20.829,34 €
Other good &
services
13.861,13 €
Equipment 3.974,10€
53. Financial Statement
Reporting Period 1
RP1 – Categories of cost for each partner
- €
20,000.00 €
40,000.00 €
60,000.00 €
80,000.00 €
100,000.00 €
120,000.00 €
140,000.00 €
UNIPI CNR TAU UoY UB UCO BARAKA ELEMENTS INERA
Direct personnel costs declared as actual costs Direct personnel costs declared as unit costs (average costs) Other direct costs Indirect costs
55. Financial Statement
Reporting Period 1
€55,503.65
€1,340.68
€7,119.00
€31,738.94
€3,039.81
€63.43
P E RS ONNE L C OS T S T RA VE L OT H E R GOOD& S E RVIC E S
WP9 - Communication WP10 - Dissemination
Total funding amount used for dissemination and communication activities: €98.805,52
Equal to 13,58% of the total costs involved in the first Reporting Period
Total personnel costs used for dissemination and communication activities: €87.242,60
Equal to 16,05% of the personnel costs involved in the first Reporting Period
56. This project has received funding from the European Union’s Horizon 2020 research
and innovation programme under grant agreement N.693548
The views and opinions expressed in this presentation are
the sole responsibility of the authors and do not necessarily
reflect the views of the European Commission.
Editor's Notes
Enable scalable and cost-effective documentation of archaeological findings.
Enable digitization of current catalogues (by automatic processes), including the conversion from raster to digital conceptual models of the artefact classes defined in the catalogues.
Enable on-the-field support to the archaeologist in the interpretation phase.
Enable the archival of all data produced on a remote archive, supporting also access through advanced presentation tools.
Enable reuse of all data collected and preserved in the open data repository
Evaluating the impact in real conditions
Establishing the conditions for a successful adoption and exploitation of project outcomes
The first step toward the achievement of this objective has been the realisation of the ArchAIDE system Mock-up, designed for working in real excavation condition.
Main steps for evaluating the impact in real working conditions will start on M22 with the beginning of WP8.
the quantity and quality of data requested by WP6 must be wider than estimated.
We reach results on catalogues population but they are not enough for training the algorithms
the work on the medieval and postmedieval pottery, which is of fundamental importance for developing the appearance based similarity training in WP6, was more complex than expected
the archaeological partners found new archaeological excavations from which new photomaterial can be obtained. However, the agreements with the Principal Investigators of these excavations taken over the last few months have led to an increase in time.
UB start a PhD on ArchAIDE
We reach results on catalogues population but they are not enough for training the algorithms
Deliverable 6.1 has not been achieved on the due date. The deviation is due to the lack of training data.
we propose an extension of WP5 to month 28. The date of the deliverable of WP5 will not be affected by this extension as well as it will not affect the work on WP7 and 8.
o The problem is related to the state of the art in the medieval and postmedieval archaeological pottery studies.
In order to determine which pieces of ceramics could be considered as belonging to the same class, there must be some definition on when is the appearance difference is actually acceptable (and is considered as the same class) and when it’s too big (and therefore considered of different classes). However, in recent discussions it was raised that there’s no archaeological consensus on how to measure similarity as:
in some cases, it’s defined mainly by colour (and patterns may change);
in others it’s defined by the pattern;
and more.
For this reason, it’s currently not possible to develop a similarity algorithm – since there’s no definition of what is considered similar;
o Lacking data: as described in the work package “the similarity would be learned from examples that are tagged as similar or not-similar”. However, this requires many samples per class, and currently some catalogues only present one canonical image per class, thus preventing learning the similarity. therefore, it is not possible to train neural network classifiers on real pottery data;
o The data are unlabelled – a critical component for training a machine learning algorithm is to actually have the input data classified and labelled so that we can train the algorithm to recognize similar images as belonging to this class. Unfortunately, the current data is not labelled in any automatically consumable way; annotations are sometimes included in big paragraphs of text, but not in a machine consumable manner;
o there is no unified archaeological definition for “appearance-based similarity” – In order to determine which pieces of ceramics could be considered as belonging to the same class, there must be some definition on when is the appearance difference is actually acceptable (and is considered as the same class) and when it’s too big (and therefore considered of different classes). However, in recent discussions it was raised that there’s no archaeological consensus on how to measure similarity as:
in some cases, it’s defined mainly by colour (and patterns may change);
in others it’s defined by the pattern;
and more.
For this reason, it’s currently not possible to develop a similarity algorithm – since there’s no definition of what is considered similar;
o Lacking data: as described in the work package “the similarity would be learned from examples that are tagged as similar or not-similar”. However, this requires many samples per class, and currently some catalogues only present one canonical image per class, thus preventing learning the similarity. therefore, it is not possible to train neural network classifiers on real pottery data;
the project logo has been created;
different possibility for trademarking it have been studied;
UNIPI is the only partner interested in trademarking it;
decision of postponing the trademarking until the applicable commercial categories will be clearer and the Exploitation Plan is more defined
creation of the newsletter has been postponed;
it has been decided to use a faster and friendly way of communication through social media
it has been created the "Associates” page on the website, as a different method to communicate and involve the audience.
Useremo gli associates
E le mailing list dei partners
o
Being a draft, we have to say that not all partners has been able to provide the financial data updated to the end of the reporting period on month 12th, because not all the administrative offices are used to recorde the financial data within ten days after the end of the worked month. All partners worked as hard as possible to fill in the form with the more updated data as possible. As agreed with the PO the updated data will be submitted by 15th July.
You can see here the periodic summary financial statement for the consortium regarding the first reporting period divided for categories of cost.
Overall, the total amount spent in this period is equal to 27,61% of the total amount and it’s consistent with the activities carried out in the period
In the first reporting period the consortium has spent the 33,24% of the planned Direct personnel costs declared as actual costs and the 15,69% of the planned direct personnel costs declared as unit costs, used by the Spanish Enterprises, Baraka and Elements.
Subcontracting costs have not yet been used. This category of cost was introduced by the amendment procedure after the European Commission decision to not recognize as Personnel costs the Italian contracts called “Assegni di ricerca”, used by University of Pisa. Now, given the changes of the Annotated model Grant Agreement, these costs has been reported as “direct personnel cost”.
In the first reporting period, the higher costs were the personnel costs to an amount of 93% (89 and 4 as unit costs) and the 7% to other direct costs.
As for the other direct costs, 54% are travel costs covering the travels of the partners to attend 4 meetings (the kick-off meeting in Pisa; a technical general meeting in Barcelona; a technical meeting and a general meeting in Pisa), conferences and communication events, and travels for contacting museums and excavation teams.
The 36% of other good and services has covered the promotional kit, the organisation of the meetings and the first part of the video communication.
10% has been dedicated to Tel Aviv university’s equipment.
Here you can see the categories of cost divided for each beneficiary. In this first year University of Pisa and CNR were the most involved; Baraka and Elements the less ones, they will have more efforts when the WP8 will start on month 22.
Here you can see the use of resources and the planned effort for each WP. The use of resources is in compliance with the activities carried out.
Finally, the total funding amount used for dissemination and communication activities is equal to 13,58% of the total costs spent in the first reporting period and the personnel costs are equal to 16.05% of the personnel costs involved in the 1° reporting period. The use of resources was greater for communication activities than dissemination activities, given fact that has been created the whole communication structure (internal and public) and the dissemination of the results will be more intense in the second and third year.