20170222-NOOR

Experiment design

Revision of networks of ontologies with random replace for 100000 iterations (4 agents; 100000 iterations)

Hypotheses:

• eventually the random modality would reach a 100% recall

Experimental setting: Repetition of 20170216-NOOR for replace/random over 100000 iterations

Experiment

Experimenter: Jérôme Euzenat (INRIA)

Date: 20170222

Lazy lavender hash: dc342dca26a5a6feff895b2a1829b04e7dfaa5ae

Parameters: params.sh

Command line (script.sh):

java -Dlog.level=INFO -cp lib/lazylav/ll.jar:lib/slf4j/logback-classic-1.1.9.jar:lib/slf4j/logback-core-1.1.9.jar:. fr.inria.exmo.lazylavender.engine.Monitor -DrevisionModality=replace -DnbAgents=4 -DnbRun=10 -DnbIterations=100000 -DexpandAlignments=random -DreportPrecRec

Class used: NOOEnvironment, AlignmentAdjustingAgent, AlignmentRevisionExperiment, ActionLogger, AverageLogger, Monitor

Execution environment: Debian Linux virtual machine configured with four processors and 20GB of RAM running under a Dell PowerEdge T610 with 4*Intel Xeon Quad Core 1.9GHz E5-2420 processors, under Linux ProxMox 2 (Debian). - Java 1.8.0 HotSpot

Raw results

20170215b-NOOR-4-10000-replace-random.tsv 20170215b-NOOR-4-10000-replace-random.txt 20170222-NOOR-4-100000-replace-random.tsv 20170222-NOOR-4-100000-replace-random.txt

Result exploration

F-measure and success rate evolution:

Precision and recall evolution:

(drawn from data scaled every 100 measures)

Analysis

Key points:

• There does not seem to be any notable convergence
• The values at 10000 and those at 100000 are roughly the same
• However, precision seems to be very slowly increasing, but not recall (likely due to shadowing/functionality)

Further experiments:

• none

This file can be retrieved from URL https://sake.re/20170222-NOOR

It is possible to check out the repository by cloning https://felapton.inrialpes.fr/cakes/20170222-NOOR.git

This experiment has been transferred from its initial location at https://gforge.inria.fr (not available any more)