Hispana. Acceso en línea al Patrimonio Cultural Digital Español

Está en:  › Datos do registro

A comparison of neural and non-neural machine learning models for food safety risk prediction with European Union RASFF data.

Identificadores del recurso

0956-7135

http://hdl.handle.net/10641/2670

10.1016/j.foodcont.2021.108697

Procedencia

(Repositorio Institucional de la Universidad Francisco de Vitoria)

Ficha

Título:: A comparison of neural and non-neural machine learning models for food safety risk prediction with European Union RASFF data.
Tema:: Food and feed safety; Machine learning; Deep learning; Random forest; Entity embedding; Prediction
Descrición:: European Union launched the RASFF portal in 1977 to ensure cross-border monitoring and a quick reaction when public health risks are detected in the food chain. There are not enough resources available to guarantee a comprehensive inspection policy, but RASFF data has enormous potential as a preventive tool. However, there are few studies of food and feed risk issues prediction and none with RASFF data. Although deep learning models are good prediction systems, it must be confirmed whether in this field they behave better than other machine learning techniques. The importance of categorical variables encoding as input for numerical models should be specially studied. Results in this paper show that deep learning with entity embedding is the best combination, with accuracies of 86.81%, 82.31%, and 88.94% in each of the three stages of the simplified RASFF process in which the tests were carried out. However, the random forest models with one hot encoding offer only slightly worse results, so it seems that in the quality of the results the coding has more weight than the prediction technique. Our work also demonstrates that the use of probabilistic predictions (an advantage of neural models) can also be used to optimize the number of inspections that can be carried out.; pre-print; 301 KB
Idioma:: English
Relación:: https://www.sciencedirect.com/science/article/abs/pii/S0956713521008355?via%3Dihub
Autor/Productor:: Nogales Moyano, Alberto; Díaz Morón, Rodrigo; García Tejedor, Álvaro José
Editor:: Food control
Dereitos:: Atribución-NoComercial-SinDerivadas 3.0 España; http://creativecommons.org/licenses/by-nc-nd/3.0/es/; openAccess
Data:: 2022-01-14T09:07:15Z; 2022
Tipo de recurso:: article

oai_dc

Descargar XML

<?xml version="1.0" encoding="UTF-8" ?>

<oai_dc:dc schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
1. <dc:title>A comparison of neural and non-neural machine learning models for food safety risk prediction with European Union RASFF data.</dc:title>
2. <dc:creator>Nogales Moyano, Alberto</dc:creator>
3. <dc:creator>Díaz Morón, Rodrigo</dc:creator>
4. <dc:creator>García Tejedor, Álvaro José</dc:creator>
5. <dc:subject>Food and feed safety</dc:subject>
6. <dc:subject>Machine learning</dc:subject>
7. <dc:subject>Deep learning</dc:subject>
8. <dc:subject>Random forest</dc:subject>
9. <dc:subject>Entity embedding</dc:subject>
10. <dc:subject>Prediction</dc:subject>
11. <dc:description>European Union launched the RASFF portal in 1977 to ensure cross-border monitoring and a quick reaction when public health risks are detected in the food chain. There are not enough resources available to guarantee a comprehensive inspection policy, but RASFF data has enormous potential as a preventive tool. However, there are few studies of food and feed risk issues prediction and none with RASFF data. Although deep learning models are good prediction systems, it must be confirmed whether in this field they behave better than other machine learning techniques. The importance of categorical variables encoding as input for numerical models should be specially studied. Results in this paper show that deep learning with entity embedding is the best combination, with accuracies of 86.81%, 82.31%, and 88.94% in each of the three stages of the simplified RASFF process in which the tests were carried out. However, the random forest models with one hot encoding offer only slightly worse results, so it seems that in the quality of the results the coding has more weight than the prediction technique. Our work also demonstrates that the use of probabilistic predictions (an advantage of neural models) can also be used to optimize the number of inspections that can be carried out.</dc:description>
12. <dc:description>pre-print</dc:description>
13. <dc:description>301 KB</dc:description>
14. <dc:date>2022-01-14T09:07:15Z</dc:date>
15. <dc:date>2022-01-14T09:07:15Z</dc:date>
16. <dc:date>2022</dc:date>
17. <dc:type>article</dc:type>
18. <dc:identifier>0956-7135</dc:identifier>
19. <dc:identifier>http://hdl.handle.net/10641/2670</dc:identifier>
20. <dc:identifier>10.1016/j.foodcont.2021.108697</dc:identifier>
21. <dc:language>eng</dc:language>
22. <dc:relation>https://www.sciencedirect.com/science/article/abs/pii/S0956713521008355?via%3Dihub</dc:relation>
23. <dc:rights>Atribución-NoComercial-SinDerivadas 3.0 España</dc:rights>
24. <dc:rights>http://creativecommons.org/licenses/by-nc-nd/3.0/es/</dc:rights>
25. <dc:rights>openAccess</dc:rights>
26. <dc:publisher>Food control</dc:publisher>
</oai_dc:dc>

didl

Descargar XML

<?xml version="1.0" encoding="UTF-8" ?>

<d:DIDL schemaLocation="urn:mpeg:mpeg21:2002:02-DIDL-NS http://standards.iso.org/ittf/PubliclyAvailableStandards/MPEG-21_schema_files/did/didl.xsd">
1. <d:DIDLInfo>
  1. <dcterms:created schemaLocation="http://purl.org/dc/terms/ http://dublincore.org/schemas/xmls/qdc/dcterms.xsd">2022-01-14T09:07:15Z</dcterms:created>
  </d:DIDLInfo>
2. <d:Item id="hdl_10641_2670">
  1. <d:Descriptor>
    1. <d:Statement mimeType="application/xml; charset=utf-8">
      1. <dii:Identifier schemaLocation="urn:mpeg:mpeg21:2002:01-DII-NS http://standards.iso.org/ittf/PubliclyAvailableStandards/MPEG-21_schema_files/dii/dii.xsd">urn:hdl:10641/2670</dii:Identifier>
      </d:Statement>
    </d:Descriptor>
  2. <d:Descriptor>
    1. <d:Statement mimeType="application/xml; charset=utf-8">
      1. <oai_dc:dc schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
        <dc:title>A comparison of neural and non-neural machine learning models for food safety risk prediction with European Union RASFF data.</dc:title>
        <dc:creator>Nogales Moyano, Alberto</dc:creator>
        <dc:creator>Díaz Morón, Rodrigo</dc:creator>
        <dc:creator>García Tejedor, Álvaro José</dc:creator>
        <dc:subject>Food and feed safety</dc:subject>
        <dc:subject>Machine learning</dc:subject>
        <dc:subject>Deep learning</dc:subject>
        <dc:subject>Random forest</dc:subject>
        <dc:subject>Entity embedding</dc:subject>
        <dc:subject>Prediction</dc:subject>
        <dc:description>European Union launched the RASFF portal in 1977 to ensure cross-border monitoring and a quick reaction when public health risks are detected in the food chain. There are not enough resources available to guarantee a comprehensive inspection policy, but RASFF data has enormous potential as a preventive tool. However, there are few studies of food and feed risk issues prediction and none with RASFF data. Although deep learning models are good prediction systems, it must be confirmed whether in this field they behave better than other machine learning techniques. The importance of categorical variables encoding as input for numerical models should be specially studied. Results in this paper show that deep learning with entity embedding is the best combination, with accuracies of 86.81%, 82.31%, and 88.94% in each of the three stages of the simplified RASFF process in which the tests were carried out. However, the random forest models with one hot encoding offer only slightly worse results, so it seems that in the quality of the results the coding has more weight than the prediction technique. Our work also demonstrates that the use of probabilistic predictions (an advantage of neural models) can also be used to optimize the number of inspections that can be carried out.</dc:description>
        <dc:date>2022-01-14T09:07:15Z</dc:date>
        <dc:date>2022-01-14T09:07:15Z</dc:date>
        <dc:date>2022</dc:date>
        <dc:type>article</dc:type>
        <dc:identifier>0956-7135</dc:identifier>
        <dc:identifier>http://hdl.handle.net/10641/2670</dc:identifier>
        <dc:identifier>10.1016/j.foodcont.2021.108697</dc:identifier>
        <dc:language>eng</dc:language>
        <dc:relation>https://www.sciencedirect.com/science/article/abs/pii/S0956713521008355?via%3Dihub</dc:relation>
        <dc:rights>http://creativecommons.org/licenses/by-nc-nd/3.0/es/</dc:rights>
        <dc:rights>openAccess</dc:rights>
        <dc:rights>Atribución-NoComercial-SinDerivadas 3.0 España</dc:rights>
        <dc:publisher>Food control</dc:publisher>
        </oai_dc:dc>
      </d:Statement>
    </d:Descriptor>
  3. <d:Component id="10641_2670_1">
    1. <d:Resource mimeType="application/pdf" ref="http://ddfv.ufv.es/bitstream/10641/2670/1/1.-%20A%20comparison%20of%20neural%20and%20non-neural%20machine%20learning%20models%20for%20food%20safety%20risk%20prediction%20with%20European%20Union%20RASFF%20data.pdf" />
    </d:Component>
  </d:Item>
</d:DIDL>

dim

Descargar XML

<?xml version="1.0" encoding="UTF-8" ?>

<dim:dim schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
1. <dim:field authority="209" confidence="600" element="contributor" mdschema="dc" qualifier="author">Nogales Moyano, Alberto</dim:field>
2. <dim:field authority="f0774269-0cb0-435e-afc4-937b0528e7cc" confidence="600" element="contributor" mdschema="dc" qualifier="author">Díaz Morón, Rodrigo</dim:field>
3. <dim:field authority="75" confidence="600" element="contributor" mdschema="dc" qualifier="author">García Tejedor, Álvaro José</dim:field>
4. <dim:field element="date" mdschema="dc" qualifier="accessioned">2022-01-14T09:07:15Z</dim:field>
5. <dim:field element="date" mdschema="dc" qualifier="available">2022-01-14T09:07:15Z</dim:field>
6. <dim:field element="date" mdschema="dc" qualifier="issued">2022</dim:field>
7. <dim:field element="identifier" lang="spa" mdschema="dc" qualifier="issn">0956-7135</dim:field>
8. <dim:field element="identifier" mdschema="dc" qualifier="uri">http://hdl.handle.net/10641/2670</dim:field>
9. <dim:field element="identifier" lang="spa" mdschema="dc" qualifier="doi">10.1016/j.foodcont.2021.108697</dim:field>
10. <dim:field element="description" lang="spa" mdschema="dc" qualifier="abstract">European Union launched the RASFF portal in 1977 to ensure cross-border monitoring and a quick reaction when public health risks are detected in the food chain. There are not enough resources available to guarantee a comprehensive inspection policy, but RASFF data has enormous potential as a preventive tool. However, there are few studies of food and feed risk issues prediction and none with RASFF data. Although deep learning models are good prediction systems, it must be confirmed whether in this field they behave better than other machine learning techniques. The importance of categorical variables encoding as input for numerical models should be specially studied. Results in this paper show that deep learning with entity embedding is the best combination, with accuracies of 86.81%, 82.31%, and 88.94% in each of the three stages of the simplified RASFF process in which the tests were carried out. However, the random forest models with one hot encoding offer only slightly worse results, so it seems that in the quality of the results the coding has more weight than the prediction technique. Our work also demonstrates that the use of probabilistic predictions (an advantage of neural models) can also be used to optimize the number of inspections that can be carried out.</dim:field>
11. <dim:field element="description" lang="spa" mdschema="dc" qualifier="version">pre-print</dim:field>
12. <dim:field element="description" lang="spa" mdschema="dc" qualifier="extent">301 KB</dim:field>
13. <dim:field element="language" lang="spa" mdschema="dc" qualifier="iso">eng</dim:field>
14. <dim:field element="publisher" lang="spa" mdschema="dc">Food control</dim:field>
15. <dim:field element="rights" lang="*" mdschema="dc">Atribución-NoComercial-SinDerivadas 3.0 España</dim:field>
16. <dim:field element="rights" lang="*" mdschema="dc" qualifier="uri">http://creativecommons.org/licenses/by-nc-nd/3.0/es/</dim:field>
17. <dim:field element="rights" lang="spa" mdschema="dc" qualifier="accessRights">openAccess</dim:field>
18. <dim:field element="subject" lang="spa" mdschema="dc">Food and feed safety</dim:field>
19. <dim:field element="subject" lang="spa" mdschema="dc">Machine learning</dim:field>
20. <dim:field element="subject" lang="spa" mdschema="dc">Deep learning</dim:field>
21. <dim:field element="subject" lang="spa" mdschema="dc">Random forest</dim:field>
22. <dim:field element="subject" lang="spa" mdschema="dc">Entity embedding</dim:field>
23. <dim:field element="subject" lang="spa" mdschema="dc">Prediction</dim:field>
24. <dim:field element="title" lang="spa" mdschema="dc">A comparison of neural and non-neural machine learning models for food safety risk prediction with European Union RASFF data.</dim:field>
25. <dim:field element="type" lang="spa" mdschema="dc">article</dim:field>
26. <dim:field element="relation" lang="spa" mdschema="dc" qualifier="publisherversion">https://www.sciencedirect.com/science/article/abs/pii/S0956713521008355?via%3Dihub</dim:field>
</dim:dim>

etdms

Descargar XML

<?xml version="1.0" encoding="UTF-8" ?>

<thesis schemaLocation="http://www.ndltd.org/standards/metadata/etdms/1.0/ http://www.ndltd.org/standards/metadata/etdms/1.0/etdms.xsd">
1. <title>A comparison of neural and non-neural machine learning models for food safety risk prediction with European Union RASFF data.</title>
2. <creator>Nogales Moyano, Alberto</creator>
3. <creator>Díaz Morón, Rodrigo</creator>
4. <creator>García Tejedor, Álvaro José</creator>
5. <subject>Food and feed safety</subject>
6. <subject>Machine learning</subject>
7. <subject>Deep learning</subject>
8. <subject>Random forest</subject>
9. <subject>Entity embedding</subject>
10. <subject>Prediction</subject>
11. <description>European Union launched the RASFF portal in 1977 to ensure cross-border monitoring and a quick reaction when public health risks are detected in the food chain. There are not enough resources available to guarantee a comprehensive inspection policy, but RASFF data has enormous potential as a preventive tool. However, there are few studies of food and feed risk issues prediction and none with RASFF data. Although deep learning models are good prediction systems, it must be confirmed whether in this field they behave better than other machine learning techniques. The importance of categorical variables encoding as input for numerical models should be specially studied. Results in this paper show that deep learning with entity embedding is the best combination, with accuracies of 86.81%, 82.31%, and 88.94% in each of the three stages of the simplified RASFF process in which the tests were carried out. However, the random forest models with one hot encoding offer only slightly worse results, so it seems that in the quality of the results the coding has more weight than the prediction technique. Our work also demonstrates that the use of probabilistic predictions (an advantage of neural models) can also be used to optimize the number of inspections that can be carried out.</description>
12. <date>2022-01-14</date>
13. <date>2022-01-14</date>
14. <date>2022</date>
15. <type>article</type>
16. <identifier>0956-7135</identifier>
17. <identifier>http://hdl.handle.net/10641/2670</identifier>
18. <identifier>10.1016/j.foodcont.2021.108697</identifier>
19. <language>eng</language>
20. <relation>https://www.sciencedirect.com/science/article/abs/pii/S0956713521008355?via%3Dihub</relation>
21. <rights>http://creativecommons.org/licenses/by-nc-nd/3.0/es/</rights>
22. <rights>openAccess</rights>
23. <rights>Atribución-NoComercial-SinDerivadas 3.0 España</rights>
24. <publisher>Food control</publisher>
</thesis>

marc

Descargar XML

<?xml version="1.0" encoding="UTF-8" ?>

<record schemaLocation="http://www.loc.gov/MARC21/slim http://www.loc.gov/standards/marcxml/schema/MARC21slim.xsd">
1. <leader>00925njm 22002777a 4500</leader>
2. <datafield ind1=" " ind2=" " tag="042">
  1. <subfield code="a">dc</subfield>
  </datafield>
3. <datafield ind1=" " ind2=" " tag="720">
  1. <subfield code="a">Nogales Moyano, Alberto</subfield>
  2. <subfield code="e">author</subfield>
  </datafield>
4. <datafield ind1=" " ind2=" " tag="720">
  1. <subfield code="a">Díaz Morón, Rodrigo</subfield>
  2. <subfield code="e">author</subfield>
  </datafield>
5. <datafield ind1=" " ind2=" " tag="720">
  1. <subfield code="a">García Tejedor, Álvaro José</subfield>
  2. <subfield code="e">author</subfield>
  </datafield>
6. <datafield ind1=" " ind2=" " tag="260">
  1. <subfield code="c">2022</subfield>
  </datafield>
7. <datafield ind1=" " ind2=" " tag="520">
  1. <subfield code="a">European Union launched the RASFF portal in 1977 to ensure cross-border monitoring and a quick reaction when public health risks are detected in the food chain. There are not enough resources available to guarantee a comprehensive inspection policy, but RASFF data has enormous potential as a preventive tool. However, there are few studies of food and feed risk issues prediction and none with RASFF data. Although deep learning models are good prediction systems, it must be confirmed whether in this field they behave better than other machine learning techniques. The importance of categorical variables encoding as input for numerical models should be specially studied. Results in this paper show that deep learning with entity embedding is the best combination, with accuracies of 86.81%, 82.31%, and 88.94% in each of the three stages of the simplified RASFF process in which the tests were carried out. However, the random forest models with one hot encoding offer only slightly worse results, so it seems that in the quality of the results the coding has more weight than the prediction technique. Our work also demonstrates that the use of probabilistic predictions (an advantage of neural models) can also be used to optimize the number of inspections that can be carried out.</subfield>
  </datafield>
8. <datafield ind1="8" ind2=" " tag="024">
  1. <subfield code="a">0956-7135</subfield>
  </datafield>
9. <datafield ind1="8" ind2=" " tag="024">
  1. <subfield code="a">http://hdl.handle.net/10641/2670</subfield>
  </datafield>
10. <datafield ind1="8" ind2=" " tag="024">
  1. <subfield code="a">10.1016/j.foodcont.2021.108697</subfield>
  </datafield>
11. <datafield ind1=" " ind2=" " tag="653">
  1. <subfield code="a">Food and feed safety</subfield>
  </datafield>
12. <datafield ind1=" " ind2=" " tag="653">
  1. <subfield code="a">Machine learning</subfield>
  </datafield>
13. <datafield ind1=" " ind2=" " tag="653">
  1. <subfield code="a">Deep learning</subfield>
  </datafield>
14. <datafield ind1=" " ind2=" " tag="653">
  1. <subfield code="a">Random forest</subfield>
  </datafield>
15. <datafield ind1=" " ind2=" " tag="653">
  1. <subfield code="a">Entity embedding</subfield>
  </datafield>
16. <datafield ind1=" " ind2=" " tag="653">
  1. <subfield code="a">Prediction</subfield>
  </datafield>
17. <datafield ind1="0" ind2="0" tag="245">
  1. <subfield code="a">A comparison of neural and non-neural machine learning models for food safety risk prediction with European Union RASFF data.</subfield>
  </datafield>
</record>

mets

Descargar XML

<?xml version="1.0" encoding="UTF-8" ?>

<mets ID=" DSpace_ITEM_10641-2670" OBJID=" hdl:10641/2670" PROFILE="DSpace METS SIP Profile 1.0" TYPE="DSpace ITEM" schemaLocation="http://www.loc.gov/METS/ http://www.loc.gov/standards/mets/mets.xsd">
1. <metsHdr CREATEDATE="2022-09-20T09:25:41Z">
  1. <agent ROLE="CUSTODIAN" TYPE="ORGANIZATION">
    1. <name>DDFV</name>
    </agent>
  </metsHdr>
2. <dmdSec ID="DMD_10641_2670">
  1. <mdWrap MDTYPE="MODS">
    1. <xmlData schemaLocation="http://www.loc.gov/mods/v3 http://www.loc.gov/standards/mods/v3/mods-3-1.xsd">
      1. <mods:mods schemaLocation="http://www.loc.gov/mods/v3 http://www.loc.gov/standards/mods/v3/mods-3-1.xsd">
        <mods:name>
        <mods:role>
        <mods:roleTerm type="text">author</mods:roleTerm>
        </mods:role>
        <mods:namePart>Nogales Moyano, Alberto</mods:namePart>
        </mods:name>
        <mods:name>
        <mods:role>
        <mods:roleTerm type="text">author</mods:roleTerm>
        </mods:role>
        <mods:namePart>Díaz Morón, Rodrigo</mods:namePart>
        </mods:name>
        <mods:name>
        <mods:role>
        <mods:roleTerm type="text">author</mods:roleTerm>
        </mods:role>
        <mods:namePart>García Tejedor, Álvaro José</mods:namePart>
        </mods:name>
        <mods:extension>
        <mods:dateAccessioned encoding="iso8601">2022-01-14T09:07:15Z</mods:dateAccessioned>
        </mods:extension>
        <mods:extension>
        <mods:dateAvailable encoding="iso8601">2022-01-14T09:07:15Z</mods:dateAvailable>
        </mods:extension>
        <mods:originInfo>
        <mods:dateIssued encoding="iso8601">2022</mods:dateIssued>
        </mods:originInfo>
        <mods:identifier type="issn">0956-7135</mods:identifier>
        <mods:identifier type="uri">http://hdl.handle.net/10641/2670</mods:identifier>
        <mods:identifier type="doi">10.1016/j.foodcont.2021.108697</mods:identifier>
        <mods:abstract>European Union launched the RASFF portal in 1977 to ensure cross-border monitoring and a quick reaction when public health risks are detected in the food chain. There are not enough resources available to guarantee a comprehensive inspection policy, but RASFF data has enormous potential as a preventive tool. However, there are few studies of food and feed risk issues prediction and none with RASFF data. Although deep learning models are good prediction systems, it must be confirmed whether in this field they behave better than other machine learning techniques. The importance of categorical variables encoding as input for numerical models should be specially studied. Results in this paper show that deep learning with entity embedding is the best combination, with accuracies of 86.81%, 82.31%, and 88.94% in each of the three stages of the simplified RASFF process in which the tests were carried out. However, the random forest models with one hot encoding offer only slightly worse results, so it seems that in the quality of the results the coding has more weight than the prediction technique. Our work also demonstrates that the use of probabilistic predictions (an advantage of neural models) can also be used to optimize the number of inspections that can be carried out.</mods:abstract>
        <mods:language>
        <mods:languageTerm authority="rfc3066">eng</mods:languageTerm>
        </mods:language>
        <mods:accessCondition type="useAndReproduction">Atribución-NoComercial-SinDerivadas 3.0 España</mods:accessCondition>
        <mods:subject>
        <mods:topic>Food and feed safety</mods:topic>
        </mods:subject>
        <mods:subject>
        <mods:topic>Machine learning</mods:topic>
        </mods:subject>
        <mods:subject>
        <mods:topic>Deep learning</mods:topic>
        </mods:subject>
        <mods:subject>
        <mods:topic>Random forest</mods:topic>
        </mods:subject>
        <mods:subject>
        <mods:topic>Entity embedding</mods:topic>
        </mods:subject>
        <mods:subject>
        <mods:topic>Prediction</mods:topic>
        </mods:subject>
        <mods:titleInfo>
        <mods:title>A comparison of neural and non-neural machine learning models for food safety risk prediction with European Union RASFF data.</mods:title>
        </mods:titleInfo>
        <mods:genre>article</mods:genre>
        </mods:mods>
      </xmlData>
    </mdWrap>
  </dmdSec>
3. <amdSec ID="TMD_10641_2670">
  1. <rightsMD ID="RIG_10641_2670">
    1. <mdWrap MDTYPE="OTHER" MIMETYPE="text/plain" OTHERMDTYPE="DSpaceDepositLicense">
      1. <binData>LSBFbCByZXBvc2l0b3JpbyBpbnN0aXR1Y2lvbmFsIGRlIGxhIFVuaXZlcnNpZGFkIEZyYW5jaXNjbyBkZSBWaXRvcmlhIGRlIE1hZHJpZCAoRERGViksIHBvbmUgYSBkaXNwb3NpY2nDs24gZGUgbG9zIHVzdWFyaW9zIGxhIHBsYXRhZm9ybWEgZGlnaXRhbCBhYmllcnRhIHkgZGUgYWNjZXNvIGxpYnJlIGRlIGxhIHByb2R1Y2Npw7NuIGNpZW50w61maWNhIGRlIGxhIGluc3RpdHVjacOzbi4KCi0gQSB0YWxlcyBmaW5lcywgbG9zIGF1dG9yZXMgZGVjbGFyYW4gcXVlIHNvbiB0aXR1bGFyZXMgZGUgbG9zIGRlcmVjaG9zIGRlIHByb3BpZWRhZCBpbnRlbGVjdHVhbCBkZSBsYSBvYnJhIHkgcXVlIMOpc3RhIGVzIG9yaWdpbmFsLgoKLSBNZWRpYW50ZSBsYSBhY2VwdGFjacOzbiBkZSBlc3RhIGxpY2VuY2lhLCBlbCBhdXRvciwgY29tbyB0aXR1bGFyIGRlIGxvcyBkZXJlY2hvcyBkZSBhdXRvciwgYXV0b3JpemEgeSBjZWRlIGEgbGEgVW5pdmVyc2lkYWQgRnJhbmNpc2NvIGRlIFZpdG9yaWEsIGRlIGZvcm1hIGdyYXR1aXRhIHkgbm8gZXhjbHVzaXZhLCBwb3IgZWwgbcOheGltbyBwbGF6byBsZWdhbCB5IGNvbiDDoW1iaXRvIHVuaXZlcnNhbCwgbG9zIGRlcmVjaG9zIGRlIHJlcHJvZHVjY2nDs24sIGRpc3RyaWJ1Y2nDs24sIGNvbXVuaWNhY2nDs24gcMO6YmxpY2EsIGluY2x1aWRvIGVsIGRlcmVjaG8gZGUgcHVlc3RhIGEgZGlzcG9zaWNpw7NuIGVsZWN0csOzbmljYSwgeSBsYSB0cmFuc2Zvcm1hY2nDs24gZGUgZm9ybWF0byBzb2JyZSBsYSBvYnJhIGluZGljYWRhLCBzaSBmdWVyYSBlbCBjYXNvLgoKLSBFbiBlbCBjYXNvIGRlIGNlc2nDs24gZGUgZGVyZWNob3MgZGUgZXhwbG90YWNpw7NuIGEgdGVyY2Vyb3MsIGRlY2xhcmEgcXVlIGN1ZW50YSBjb24gbGEgYXV0b3JpemFjacOzbiBkZSBkaWNob3MgdGl0dWxhcmVzIHkgcXVlIGhhIG9idGVuaWRvIGVsIHBlcm1pc28gc2luIHJlc3RyaWNjaW9uZXMgZGVsIHByb3BpZXRhcmlvIGRlbCBjb3B5cmlnaHQgcGFyYSBvdG9yZ2FyIGEgbGEgaW5zdGl0dWNpw7NuIGxvcyBkZXJlY2hvcyByZXF1ZXJpZG9zIHBhcmEgZXN0YSBsaWNlbmNpYSB5IHF1ZSBkaWNobyBwcm9waWV0YXJpbyBjb25vY2UgZWwgdGV4dG8gbyBlbCBjb250ZW5pZG8gZGUgbGEgb2JyYS4KCi0gU2kgZnVlcmEgdW5hIG9icmEgcGF0cm9jaW5hZGEgcG9yIGFsZ3VuYSBpbnN0aXR1Y2nDs24gZGlzdGludGEgYSBsYSBVbml2ZXJzaWRhZCBGcmFuY2lzY28gZGUgVml0b3JpYSwgZGVjbGFyYSBxdWUgZW4gY2FzbyBuZWNlc2FyaW8sIGN1ZW50YSBjb24gbG9zIHBlcm1pc29zIHBlcnRpbmVudGVzLCBkZSBsYSBpbnN0aXR1Y2nDs24gbyBlbnRpZGFkLCBxdWUgbGUgcGVybWl0YW4gbGEgZGlmdXNpw7NuIGRlIGRpY2hhIG9icmEuCgotIExhIFVuaXZlcnNpZGFkIEZyYW5jaXNjbyBkZSBWaXRvcmlhIG5vIHRpZW5lIGxhIHRpdHVsYXJpZGFkIGRlIGxvcyBkZXJlY2hvcyBzb2JyZSBsYSBvYnJhLCBxdWUgY29ycmVzcG9uZGVuIGFsIGF1dG9yLCBwZXJvIHNpbiBlbWJhcmdvIMOpc3RhIGxpY2VuY2lhIGRhIGRlcmVjaG8gYSByZXByb2R1Y2lybGEgZW4gdW4gc29wb3J0ZSBkaWdpdGFsLCBkaXN0cmlidWlyIGEgbG9zIHVzdWFyaW9zIGNvcGlhcyBlbGVjdHLDs25pY2FzIGRlIGxhIG9icmEgZW4gZm9ybWF0byBkaWdpdGFsLCBjb211bmljYWNpw7NuIHDDumJsaWNhIHkgc3UgcHVlc3RhIGEgZGlzcG9zaWNpw7NuIGEgdHJhdsOpcyBkZSB1biBhcmNoaXZvIGFiaWVydG8gaW5zdGl0dWNpb25hbC4KCi0gTGEgb2JyYSBzZSBwb25kcsOhIGEgZGlzcG9zaWNpw7NuIGRlIGxvcyB1c3VhcmlvcyBwYXJhIHF1ZSBoYWdhbiBkZSBlbGxhIHVuIHVzbyBqdXN0byB5IHJlc3BldHVvc28gY29uIGxvcyBkZXJlY2hvcyBkZSBhdXRvciwgc2VhIGNvbiBmaW5lcyBkZSBlc3R1ZGlvLCBpbnZlc3RpZ2FjacOzbiBvIGN1YWxxdWllciBvdHJvIGZpbiBsw61jaXRvLCB5IGRlIGFjdWVyZG8gYSBsYXMgY29uZGljaW9uZXMgZXN0YWJsZWNpZGFzIGVuIGxhIGxpY2VuY2lhIENyZWF0aXZlIENvbW1vbnMsIGRlIG1vZG8gcXVlIGxhcyBvYnJhcyBwdWVkYW4gc2VyIGRpc3RyaWJ1aWRhcywgY29waWFkYXMgeSBleGhpYmlkYXMgc2llbXByZSBxdWUgc2UgY2l0ZSBsYSBhdXRvcsOtYSB5IG5vIHNlIG9idGVuZ2EgYmVuZWZpY2lvIGNvbWVyY2lhbC4gUG9yIHRhbnRvLCBsYSBVbml2ZXJzaWRhZCBubyBhc3VtaXLDoSByZXNwb25zYWJpbGlkYWQgYWxndW5hIHBvciBsYSBmb3JtYSBlZmVjdGl2YSBlbiBxdWUgbG9zIHVzdWFyaW9zIHV0aWxpY2VuIGVsIG1hdGVyaWFsIHB1ZXN0byBhIHN1IGRpc3Bvc2ljacOzbi4KCi0gRWwgYXV0b3IgcG9kcsOhIHNvbGljaXRhciBsYSByZXRpcmFkYSBkZSBsYSBvYnJhIGRlbCByZXBvc2l0b3JpbyBwb3IgY2F1c2EganVzdGlmaWNhZGEuIAoK</binData>
      </mdWrap>
    </rightsMD>
  </amdSec>
4. <amdSec ID="FO_10641_2670_1">
  1. <techMD ID="TECH_O_10641_2670_1">
    1. <mdWrap MDTYPE="PREMIS">
      1. <xmlData schemaLocation="http://www.loc.gov/standards/premis http://www.loc.gov/standards/premis/PREMIS-v1-0.xsd">
        <premis:premis>
        <premis:object>
        <premis:objectIdentifier>
        <premis:objectIdentifierType>URL</premis:objectIdentifierType>
        <premis:objectIdentifierValue>http://ddfv.ufv.es/bitstream/10641/2670/1/1.-%20A%20comparison%20of%20neural%20and%20non-neural%20machine%20learning%20models%20for%20food%20safety%20risk%20prediction%20with%20European%20Union%20RASFF%20data.pdf</premis:objectIdentifierValue>
        </premis:objectIdentifier>
        <premis:objectCategory>File</premis:objectCategory>
        <premis:objectCharacteristics>
        <premis:fixity>
        <premis:messageDigestAlgorithm>MD5</premis:messageDigestAlgorithm>
        <premis:messageDigest>91e1ace94b7dc8ec184f51d5dbf8607a</premis:messageDigest>
        </premis:fixity>
        <premis:size>307510</premis:size>
        <premis:format>
        <premis:formatDesignation>
        <premis:formatName>application/pdf</premis:formatName>
        </premis:formatDesignation>
        </premis:format>
        </premis:objectCharacteristics>
        <premis:originalName>1.- A comparison of neural and non-neural machine learning models for food safety risk prediction with European Union RASFF data.pdf</premis:originalName>
        </premis:object>
        </premis:premis>
        </xmlData>
      </mdWrap>
    </techMD>
  </amdSec>
5. <amdSec ID="FT_10641_2670_4">
  1. <techMD ID="TECH_T_10641_2670_4">
    1. <mdWrap MDTYPE="PREMIS">
      1. <xmlData schemaLocation="http://www.loc.gov/standards/premis http://www.loc.gov/standards/premis/PREMIS-v1-0.xsd">
        <premis:premis>
        <premis:object>
        <premis:objectIdentifier>
        <premis:objectIdentifierType>URL</premis:objectIdentifierType>
        <premis:objectIdentifierValue>http://ddfv.ufv.es/bitstream/10641/2670/4/1.-%20A%20comparison%20of%20neural%20and%20non-neural%20machine%20learning%20models%20for%20food%20safety%20risk%20prediction%20with%20European%20Union%20RASFF%20data.pdf.txt</premis:objectIdentifierValue>
        </premis:objectIdentifier>
        <premis:objectCategory>File</premis:objectCategory>
        <premis:objectCharacteristics>
        <premis:fixity>
        <premis:messageDigestAlgorithm>MD5</premis:messageDigestAlgorithm>
        <premis:messageDigest>cf45a7eab7187437daa0e7ca3499c36b</premis:messageDigest>
        </premis:fixity>
        <premis:size>57511</premis:size>
        <premis:format>
        <premis:formatDesignation>
        <premis:formatName>text/plain</premis:formatName>
        </premis:formatDesignation>
        </premis:format>
        </premis:objectCharacteristics>
        <premis:originalName>1.- A comparison of neural and non-neural machine learning models for food safety risk prediction with European Union RASFF data.pdf.txt</premis:originalName>
        </premis:object>
        </premis:premis>
        </xmlData>
      </mdWrap>
    </techMD>
  </amdSec>
6. <fileSec>
  1. <fileGrp USE="ORIGINAL">
    1. <file ADMID="FO_10641_2670_1" CHECKSUM="91e1ace94b7dc8ec184f51d5dbf8607a" CHECKSUMTYPE="MD5" GROUPID="GROUP_BITSTREAM_10641_2670_1" ID="BITSTREAM_ORIGINAL_10641_2670_1" MIMETYPE="application/pdf" SEQ="1" SIZE="307510">
      1. <FLocat LOCTYPE="URL" href="http://ddfv.ufv.es/bitstream/10641/2670/1/1.-%20A%20comparison%20of%20neural%20and%20non-neural%20machine%20learning%20models%20for%20food%20safety%20risk%20prediction%20with%20European%20Union%20RASFF%20data.pdf" type="simple" />
      </file>
    </fileGrp>
  2. <fileGrp USE="TEXT">
    1. <file ADMID="FT_10641_2670_4" CHECKSUM="cf45a7eab7187437daa0e7ca3499c36b" CHECKSUMTYPE="MD5" GROUPID="GROUP_BITSTREAM_10641_2670_4" ID="BITSTREAM_TEXT_10641_2670_4" MIMETYPE="text/plain" SEQ="4" SIZE="57511">
      1. <FLocat LOCTYPE="URL" href="http://ddfv.ufv.es/bitstream/10641/2670/4/1.-%20A%20comparison%20of%20neural%20and%20non-neural%20machine%20learning%20models%20for%20food%20safety%20risk%20prediction%20with%20European%20Union%20RASFF%20data.pdf.txt" type="simple" />
      </file>
    </fileGrp>
  </fileSec>
7. <structMap LABEL="DSpace Object" TYPE="LOGICAL">
  1. <div ADMID="DMD_10641_2670" TYPE="DSpace Object Contents">
    1. <div TYPE="DSpace BITSTREAM">
      1. <fptr FILEID="BITSTREAM_ORIGINAL_10641_2670_1" />
      </div>
    </div>
  </structMap>
</mets>

mods

Descargar XML

<?xml version="1.0" encoding="UTF-8" ?>

<mods:mods schemaLocation="http://www.loc.gov/mods/v3 http://www.loc.gov/standards/mods/v3/mods-3-1.xsd">
1. <mods:name>
  1. <mods:namePart>Nogales Moyano, Alberto</mods:namePart>
  </mods:name>
2. <mods:name>
  1. <mods:namePart>Díaz Morón, Rodrigo</mods:namePart>
  </mods:name>
3. <mods:name>
  1. <mods:namePart>García Tejedor, Álvaro José</mods:namePart>
  </mods:name>
4. <mods:extension>
  1. <mods:dateAvailable encoding="iso8601">2022-01-14T09:07:15Z</mods:dateAvailable>
  </mods:extension>
5. <mods:extension>
  1. <mods:dateAccessioned encoding="iso8601">2022-01-14T09:07:15Z</mods:dateAccessioned>
  </mods:extension>
6. <mods:originInfo>
  1. <mods:dateIssued encoding="iso8601">2022</mods:dateIssued>
  </mods:originInfo>
7. <mods:identifier type="issn">0956-7135</mods:identifier>
8. <mods:identifier type="uri">http://hdl.handle.net/10641/2670</mods:identifier>
9. <mods:identifier type="doi">10.1016/j.foodcont.2021.108697</mods:identifier>
10. <mods:abstract>European Union launched the RASFF portal in 1977 to ensure cross-border monitoring and a quick reaction when public health risks are detected in the food chain. There are not enough resources available to guarantee a comprehensive inspection policy, but RASFF data has enormous potential as a preventive tool. However, there are few studies of food and feed risk issues prediction and none with RASFF data. Although deep learning models are good prediction systems, it must be confirmed whether in this field they behave better than other machine learning techniques. The importance of categorical variables encoding as input for numerical models should be specially studied. Results in this paper show that deep learning with entity embedding is the best combination, with accuracies of 86.81%, 82.31%, and 88.94% in each of the three stages of the simplified RASFF process in which the tests were carried out. However, the random forest models with one hot encoding offer only slightly worse results, so it seems that in the quality of the results the coding has more weight than the prediction technique. Our work also demonstrates that the use of probabilistic predictions (an advantage of neural models) can also be used to optimize the number of inspections that can be carried out.</mods:abstract>
11. <mods:language>
  1. <mods:languageTerm>eng</mods:languageTerm>
  </mods:language>
12. <mods:accessCondition type="useAndReproduction">http://creativecommons.org/licenses/by-nc-nd/3.0/es/</mods:accessCondition>
13. <mods:accessCondition type="useAndReproduction">openAccess</mods:accessCondition>
14. <mods:accessCondition type="useAndReproduction">Atribución-NoComercial-SinDerivadas 3.0 España</mods:accessCondition>
15. <mods:subject>
  1. <mods:topic>Food and feed safety</mods:topic>
  </mods:subject>
16. <mods:subject>
  1. <mods:topic>Machine learning</mods:topic>
  </mods:subject>
17. <mods:subject>
  1. <mods:topic>Deep learning</mods:topic>
  </mods:subject>
18. <mods:subject>
  1. <mods:topic>Random forest</mods:topic>
  </mods:subject>
19. <mods:subject>
  1. <mods:topic>Entity embedding</mods:topic>
  </mods:subject>
20. <mods:subject>
  1. <mods:topic>Prediction</mods:topic>
  </mods:subject>
21. <mods:titleInfo>
  1. <mods:title>A comparison of neural and non-neural machine learning models for food safety risk prediction with European Union RASFF data.</mods:title>
  </mods:titleInfo>
22. <mods:genre>article</mods:genre>
</mods:mods>

ore

Descargar XML

<?xml version="1.0" encoding="UTF-8" ?>

<atom:entry schemaLocation="http://www.w3.org/2005/Atom http://www.kbcafe.com/rss/atom.xsd.xml">
1. <atom:id>http://hdl.handle.net/10641/2670/ore.xml</atom:id>
2. <atom:link href="http://hdl.handle.net/10641/2670" rel="alternate" />
3. <atom:link href="http://hdl.handle.net/10641/2670/ore.xml" rel="http://www.openarchives.org/ore/terms/describes" />
4. <atom:link href="http://hdl.handle.net/10641/2670/ore.xml#atom" rel="self" type="application/atom+xml" />
5. <atom:published>2022-01-14T09:07:15Z</atom:published>
6. <atom:updated>2022-01-14T09:07:15Z</atom:updated>
7. <atom:source>
  1. <atom:generator>DDFV</atom:generator>
  </atom:source>
8. <atom:title>A comparison of neural and non-neural machine learning models for food safety risk prediction with European Union RASFF data.</atom:title>
9. <atom:author>
  1. <atom:name>Nogales Moyano, Alberto</atom:name>
  </atom:author>
10. <atom:author>
  1. <atom:name>Díaz Morón, Rodrigo</atom:name>
  </atom:author>
11. <atom:author>
  1. <atom:name>García Tejedor, Álvaro José</atom:name>
  </atom:author>
12. <atom:category label="Aggregation" scheme="http://www.openarchives.org/ore/terms/" term="http://www.openarchives.org/ore/terms/Aggregation" />
13. <atom:category scheme="http://www.openarchives.org/ore/atom/modified" term="2022-01-14T09:07:15Z" />
14. <atom:category label="DSpace Item" scheme="http://www.dspace.org/objectModel/" term="DSpaceItem" />
15. <atom:link href="http://ddfv.ufv.es/bitstream/10641/2670/1/1.-%20A%20comparison%20of%20neural%20and%20non-neural%20machine%20learning%20models%20for%20food%20safety%20risk%20prediction%20with%20European%20Union%20RASFF%20data.pdf" length="307510" rel="http://www.openarchives.org/ore/terms/aggregates" title="1.- A comparison of neural and non-neural machine learning models for food safety risk prediction with European Union RASFF data.pdf" type="application/pdf" />
16. <oreatom:triples>
  1. <rdf:Description about="http://hdl.handle.net/10641/2670/ore.xml#atom">
    1. <rdf:type resource="http://www.dspace.org/objectModel/DSpaceItem" />
    2. <dcterms:modified>2022-01-14T09:07:15Z</dcterms:modified>
    </rdf:Description>
  2. <rdf:Description about="http://ddfv.ufv.es/bitstream/10641/2670/1/1.-%20A%20comparison%20of%20neural%20and%20non-neural%20machine%20learning%20models%20for%20food%20safety%20risk%20prediction%20with%20European%20Union%20RASFF%20data.pdf">
    1. <rdf:type resource="http://www.dspace.org/objectModel/DSpaceBitstream" />
    2. <dcterms:description>ORIGINAL</dcterms:description>
    </rdf:Description>
  3. <rdf:Description about="http://ddfv.ufv.es/bitstream/10641/2670/2/license_rdf">
    1. <rdf:type resource="http://www.dspace.org/objectModel/DSpaceBitstream" />
    2. <dcterms:description>CC-LICENSE</dcterms:description>
    </rdf:Description>
  4. <rdf:Description about="http://ddfv.ufv.es/bitstream/10641/2670/3/license.txt">
    1. <rdf:type resource="http://www.dspace.org/objectModel/DSpaceBitstream" />
    2. <dcterms:description>LICENSE</dcterms:description>
    </rdf:Description>
  5. <rdf:Description about="http://ddfv.ufv.es/bitstream/10641/2670/4/1.-%20A%20comparison%20of%20neural%20and%20non-neural%20machine%20learning%20models%20for%20food%20safety%20risk%20prediction%20with%20European%20Union%20RASFF%20data.pdf.txt">
    1. <rdf:type resource="http://www.dspace.org/objectModel/DSpaceBitstream" />
    2. <dcterms:description>TEXT</dcterms:description>
    </rdf:Description>
  6. <rdf:Description about="http://ddfv.ufv.es/bitstream/10641/2670/5/1.-%20A%20comparison%20of%20neural%20and%20non-neural%20machine%20learning%20models%20for%20food%20safety%20risk%20prediction%20with%20European%20Union%20RASFF%20data.pdf.jpg">
    1. <rdf:type resource="http://www.dspace.org/objectModel/DSpaceBitstream" />
    2. <dcterms:description>THUMBNAIL</dcterms:description>
    </rdf:Description>
  </oreatom:triples>
</atom:entry>

qdc

Descargar XML

<?xml version="1.0" encoding="UTF-8" ?>

<qdc:qualifieddc schemaLocation="http://purl.org/dc/elements/1.1/ http://dublincore.org/schemas/xmls/qdc/2006/01/06/dc.xsd http://purl.org/dc/terms/ http://dublincore.org/schemas/xmls/qdc/2006/01/06/dcterms.xsd http://dspace.org/qualifieddc/ http://www.ukoln.ac.uk/metadata/dcmi/xmlschema/qualifieddc.xsd">
1. <dc:title>A comparison of neural and non-neural machine learning models for food safety risk prediction with European Union RASFF data.</dc:title>
2. <dc:creator>Nogales Moyano, Alberto</dc:creator>
3. <dc:creator>Díaz Morón, Rodrigo</dc:creator>
4. <dc:creator>García Tejedor, Álvaro José</dc:creator>
5. <dc:subject>Food and feed safety</dc:subject>
6. <dc:subject>Machine learning</dc:subject>
7. <dc:subject>Deep learning</dc:subject>
8. <dc:subject>Random forest</dc:subject>
9. <dc:subject>Entity embedding</dc:subject>
10. <dc:subject>Prediction</dc:subject>
11. <dcterms:abstract>European Union launched the RASFF portal in 1977 to ensure cross-border monitoring and a quick reaction when public health risks are detected in the food chain. There are not enough resources available to guarantee a comprehensive inspection policy, but RASFF data has enormous potential as a preventive tool. However, there are few studies of food and feed risk issues prediction and none with RASFF data. Although deep learning models are good prediction systems, it must be confirmed whether in this field they behave better than other machine learning techniques. The importance of categorical variables encoding as input for numerical models should be specially studied. Results in this paper show that deep learning with entity embedding is the best combination, with accuracies of 86.81%, 82.31%, and 88.94% in each of the three stages of the simplified RASFF process in which the tests were carried out. However, the random forest models with one hot encoding offer only slightly worse results, so it seems that in the quality of the results the coding has more weight than the prediction technique. Our work also demonstrates that the use of probabilistic predictions (an advantage of neural models) can also be used to optimize the number of inspections that can be carried out.</dcterms:abstract>
12. <dcterms:dateAccepted>2022-01-14T09:07:15Z</dcterms:dateAccepted>
13. <dcterms:available>2022-01-14T09:07:15Z</dcterms:available>
14. <dcterms:created>2022-01-14T09:07:15Z</dcterms:created>
15. <dcterms:issued>2022</dcterms:issued>
16. <dc:type>article</dc:type>
17. <dc:identifier>0956-7135</dc:identifier>
18. <dc:identifier>http://hdl.handle.net/10641/2670</dc:identifier>
19. <dc:identifier>10.1016/j.foodcont.2021.108697</dc:identifier>
20. <dc:language>eng</dc:language>
21. <dc:relation>https://www.sciencedirect.com/science/article/abs/pii/S0956713521008355?via%3Dihub</dc:relation>
22. <dc:rights>http://creativecommons.org/licenses/by-nc-nd/3.0/es/</dc:rights>
23. <dc:rights>openAccess</dc:rights>
24. <dc:rights>Atribución-NoComercial-SinDerivadas 3.0 España</dc:rights>
25. <dc:publisher>Food control</dc:publisher>
</qdc:qualifieddc>

rdf

Descargar XML

<?xml version="1.0" encoding="UTF-8" ?>

<rdf:RDF schemaLocation="http://www.openarchives.org/OAI/2.0/rdf/ http://www.openarchives.org/OAI/2.0/rdf.xsd">
1. <ow:Publication about="oai:ddfv.ufv.es:10641/2670">
  1. <dc:title>A comparison of neural and non-neural machine learning models for food safety risk prediction with European Union RASFF data.</dc:title>
  2. <dc:creator>Nogales Moyano, Alberto</dc:creator>
  3. <dc:creator>Díaz Morón, Rodrigo</dc:creator>
  4. <dc:creator>García Tejedor, Álvaro José</dc:creator>
  5. <dc:subject>Food and feed safety</dc:subject>
  6. <dc:subject>Machine learning</dc:subject>
  7. <dc:subject>Deep learning</dc:subject>
  8. <dc:subject>Random forest</dc:subject>
  9. <dc:subject>Entity embedding</dc:subject>
  10. <dc:subject>Prediction</dc:subject>
  11. <dc:description>European Union launched the RASFF portal in 1977 to ensure cross-border monitoring and a quick reaction when public health risks are detected in the food chain. There are not enough resources available to guarantee a comprehensive inspection policy, but RASFF data has enormous potential as a preventive tool. However, there are few studies of food and feed risk issues prediction and none with RASFF data. Although deep learning models are good prediction systems, it must be confirmed whether in this field they behave better than other machine learning techniques. The importance of categorical variables encoding as input for numerical models should be specially studied. Results in this paper show that deep learning with entity embedding is the best combination, with accuracies of 86.81%, 82.31%, and 88.94% in each of the three stages of the simplified RASFF process in which the tests were carried out. However, the random forest models with one hot encoding offer only slightly worse results, so it seems that in the quality of the results the coding has more weight than the prediction technique. Our work also demonstrates that the use of probabilistic predictions (an advantage of neural models) can also be used to optimize the number of inspections that can be carried out.</dc:description>
  12. <dc:date>2022-01-14T09:07:15Z</dc:date>
  13. <dc:date>2022-01-14T09:07:15Z</dc:date>
  14. <dc:date>2022</dc:date>
  15. <dc:type>article</dc:type>
  16. <dc:identifier>0956-7135</dc:identifier>
  17. <dc:identifier>http://hdl.handle.net/10641/2670</dc:identifier>
  18. <dc:identifier>10.1016/j.foodcont.2021.108697</dc:identifier>
  19. <dc:language>eng</dc:language>
  20. <dc:relation>https://www.sciencedirect.com/science/article/abs/pii/S0956713521008355?via%3Dihub</dc:relation>
  21. <dc:rights>http://creativecommons.org/licenses/by-nc-nd/3.0/es/</dc:rights>
  22. <dc:rights>openAccess</dc:rights>
  23. <dc:rights>Atribución-NoComercial-SinDerivadas 3.0 España</dc:rights>
  24. <dc:publisher>Food control</dc:publisher>
  </ow:Publication>
</rdf:RDF>

xoai

Descargar XML

<?xml version="1.0" encoding="UTF-8" ?>

<metadata schemaLocation="http://www.lyncode.com/xoai http://www.lyncode.com/xsd/xoai.xsd">
1. <element name="dc">
  1. <element name="contributor">
    1. <element name="author">
      1. <element name="none">
        <field name="value">Nogales Moyano, Alberto</field>
        <field name="authority">209</field>
        <field name="confidence">600</field>
        <field name="value">Díaz Morón, Rodrigo</field>
        <field name="authority">f0774269-0cb0-435e-afc4-937b0528e7cc</field>
        <field name="confidence">600</field>
        <field name="value">García Tejedor, Álvaro José</field>
        <field name="authority">75</field>
        <field name="confidence">600</field>
        </element>
      </element>
    </element>
  2. <element name="date">
    1. <element name="accessioned">
      1. <element name="none">
        <field name="value">2022-01-14T09:07:15Z</field>
        </element>
      </element>
    2. <element name="available">
      1. <element name="none">
        <field name="value">2022-01-14T09:07:15Z</field>
        </element>
      </element>
    3. <element name="issued">
      1. <element name="none">
        <field name="value">2022</field>
        </element>
      </element>
    </element>
  3. <element name="identifier">
    1. <element name="issn">
      1. <element name="spa">
        <field name="value">0956-7135</field>
        </element>
      </element>
    2. <element name="uri">
      1. <element name="none">
        <field name="value">http://hdl.handle.net/10641/2670</field>
        </element>
      </element>
    3. <element name="doi">
      1. <element name="spa">
        <field name="value">10.1016/j.foodcont.2021.108697</field>
        </element>
      </element>
    </element>
  4. <element name="description">
    1. <element name="abstract">
      1. <element name="spa">
        <field name="value">European Union launched the RASFF portal in 1977 to ensure cross-border monitoring and a quick reaction when public health risks are detected in the food chain. There are not enough resources available to guarantee a comprehensive inspection policy, but RASFF data has enormous potential as a preventive tool. However, there are few studies of food and feed risk issues prediction and none with RASFF data. Although deep learning models are good prediction systems, it must be confirmed whether in this field they behave better than other machine learning techniques. The importance of categorical variables encoding as input for numerical models should be specially studied. Results in this paper show that deep learning with entity embedding is the best combination, with accuracies of 86.81%, 82.31%, and 88.94% in each of the three stages of the simplified RASFF process in which the tests were carried out. However, the random forest models with one hot encoding offer only slightly worse results, so it seems that in the quality of the results the coding has more weight than the prediction technique. Our work also demonstrates that the use of probabilistic predictions (an advantage of neural models) can also be used to optimize the number of inspections that can be carried out.</field>
        </element>
      </element>
    2. <element name="version">
      1. <element name="spa">
        <field name="value">pre-print</field>
        </element>
      </element>
    3. <element name="extent">
      1. <element name="spa">
        <field name="value">301 KB</field>
        </element>
      </element>
    </element>
  5. <element name="language">
    1. <element name="iso">
      1. <element name="spa">
        <field name="value">eng</field>
        </element>
      </element>
    </element>
  6. <element name="publisher">
    1. <element name="spa">
      1. <field name="value">Food control</field>
      </element>
    </element>
  7. <element name="rights">
    1. <element name="*">
      1. <field name="value">Atribución-NoComercial-SinDerivadas 3.0 España</field>
      </element>
    2. <element name="uri">
      1. <element name="*">
        <field name="value">http://creativecommons.org/licenses/by-nc-nd/3.0/es/</field>
        </element>
      </element>
    3. <element name="accessRights">
      1. <element name="spa">
        <field name="value">openAccess</field>
        </element>
      </element>
    </element>
  8. <element name="subject">
    1. <element name="spa">
      1. <field name="value">Food and feed safety</field>
      2. <field name="value">Machine learning</field>
      3. <field name="value">Deep learning</field>
      4. <field name="value">Random forest</field>
      5. <field name="value">Entity embedding</field>
      6. <field name="value">Prediction</field>
      </element>
    </element>
  9. <element name="title">
    1. <element name="spa">
      1. <field name="value">A comparison of neural and non-neural machine learning models for food safety risk prediction with European Union RASFF data.</field>
      </element>
    </element>
  10. <element name="type">
    1. <element name="spa">
      1. <field name="value">article</field>
      </element>
    </element>
  11. <element name="relation">
    1. <element name="publisherversion">
      1. <element name="spa">
        <field name="value">https://www.sciencedirect.com/science/article/abs/pii/S0956713521008355?via%3Dihub</field>
        </element>
      </element>
    </element>
  </element>
2. <element name="bundles">
  1. <element name="bundle">
    1. <field name="name">ORIGINAL</field>
    2. <element name="bitstreams">
      1. <element name="bitstream">
        <field name="name">1.- A comparison of neural and non-neural machine learning models for food safety risk prediction with European Union RASFF data.pdf</field>
        <field name="originalName">1.- A comparison of neural and non-neural machine learning models for food safety risk prediction with European Union RASFF data.pdf</field>
        <field name="description" />
        <field name="format">application/pdf</field>
        <field name="size">307510</field>
        <field name="url">http://ddfv.ufv.es/bitstream/10641/2670/1/1.-%20A%20comparison%20of%20neural%20and%20non-neural%20machine%20learning%20models%20for%20food%20safety%20risk%20prediction%20with%20European%20Union%20RASFF%20data.pdf</field>
        <field name="checksum">91e1ace94b7dc8ec184f51d5dbf8607a</field>
        <field name="checksumAlgorithm">MD5</field>
        <field name="sid">1</field>
        </element>
      </element>
    </element>
  2. <element name="bundle">
    1. <field name="name">CC-LICENSE</field>
    2. <element name="bitstreams">
      1. <element name="bitstream">
        <field name="name">license_rdf</field>
        <field name="originalName">license_rdf</field>
        <field name="format">application/rdf+xml; charset=utf-8</field>
        <field name="size">811</field>
        <field name="url">http://ddfv.ufv.es/bitstream/10641/2670/2/license_rdf</field>
        <field name="checksum">4d01a8abc68801ab758ec8c2c04918c3</field>
        <field name="checksumAlgorithm">MD5</field>
        <field name="sid">2</field>
        </element>
      </element>
    </element>
  3. <element name="bundle">
    1. <field name="name">LICENSE</field>
    2. <element name="bitstreams">
      1. <element name="bitstream">
        <field name="name">license.txt</field>
        <field name="originalName">license.txt</field>
        <field name="format">text/plain; charset=utf-8</field>
        <field name="size">2418</field>
        <field name="url">http://ddfv.ufv.es/bitstream/10641/2670/3/license.txt</field>
        <field name="checksum">8b6e3a0bc6a1ca51936267b0e6e4740c</field>
        <field name="checksumAlgorithm">MD5</field>
        <field name="sid">3</field>
        </element>
      </element>
    </element>
  4. <element name="bundle">
    1. <field name="name">TEXT</field>
    2. <element name="bitstreams">
      1. <element name="bitstream">
        <field name="name">1.- A comparison of neural and non-neural machine learning models for food safety risk prediction with European Union RASFF data.pdf.txt</field>
        <field name="originalName">1.- A comparison of neural and non-neural machine learning models for food safety risk prediction with European Union RASFF data.pdf.txt</field>
        <field name="description">Extracted text</field>
        <field name="format">text/plain</field>
        <field name="size">57511</field>
        <field name="url">http://ddfv.ufv.es/bitstream/10641/2670/4/1.-%20A%20comparison%20of%20neural%20and%20non-neural%20machine%20learning%20models%20for%20food%20safety%20risk%20prediction%20with%20European%20Union%20RASFF%20data.pdf.txt</field>
        <field name="checksum">cf45a7eab7187437daa0e7ca3499c36b</field>
        <field name="checksumAlgorithm">MD5</field>
        <field name="sid">4</field>
        </element>
      </element>
    </element>
  5. <element name="bundle">
    1. <field name="name">THUMBNAIL</field>
    2. <element name="bitstreams">
      1. <element name="bitstream">
        <field name="name">1.- A comparison of neural and non-neural machine learning models for food safety risk prediction with European Union RASFF data.pdf.jpg</field>
        <field name="originalName">1.- A comparison of neural and non-neural machine learning models for food safety risk prediction with European Union RASFF data.pdf.jpg</field>
        <field name="description">Generated Thumbnail</field>
        <field name="format">image/jpeg</field>
        <field name="size">1456</field>
        <field name="url">http://ddfv.ufv.es/bitstream/10641/2670/5/1.-%20A%20comparison%20of%20neural%20and%20non-neural%20machine%20learning%20models%20for%20food%20safety%20risk%20prediction%20with%20European%20Union%20RASFF%20data.pdf.jpg</field>
        <field name="checksum">06c282c360fe7bd9cab5cbed46315389</field>
        <field name="checksumAlgorithm">MD5</field>
        <field name="sid">5</field>
        </element>
      </element>
    </element>
  </element>
3. <element name="others">
  1. <field name="handle">10641/2670</field>
  2. <field name="identifier">oai:ddfv.ufv.es:10641/2670</field>
  3. <field name="lastModifyDate">2022-01-27 10:00:11.142</field>
  </element>
4. <element name="repository">
  1. <field name="name">DDFV</field>
  2. <field name="mail">dspace@ufv.es</field>
  </element>
5. <element name="license">
  1. <field name="bin">LSBFbCByZXBvc2l0b3JpbyBpbnN0aXR1Y2lvbmFsIGRlIGxhIFVuaXZlcnNpZGFkIEZyYW5jaXNjbyBkZSBWaXRvcmlhIGRlIE1hZHJpZCAoRERGViksIHBvbmUgYSBkaXNwb3NpY2nDs24gZGUgbG9zIHVzdWFyaW9zIGxhIHBsYXRhZm9ybWEgZGlnaXRhbCBhYmllcnRhIHkgZGUgYWNjZXNvIGxpYnJlIGRlIGxhIHByb2R1Y2Npw7NuIGNpZW50w61maWNhIGRlIGxhIGluc3RpdHVjacOzbi4KCi0gQSB0YWxlcyBmaW5lcywgbG9zIGF1dG9yZXMgZGVjbGFyYW4gcXVlIHNvbiB0aXR1bGFyZXMgZGUgbG9zIGRlcmVjaG9zIGRlIHByb3BpZWRhZCBpbnRlbGVjdHVhbCBkZSBsYSBvYnJhIHkgcXVlIMOpc3RhIGVzIG9yaWdpbmFsLgoKLSBNZWRpYW50ZSBsYSBhY2VwdGFjacOzbiBkZSBlc3RhIGxpY2VuY2lhLCBlbCBhdXRvciwgY29tbyB0aXR1bGFyIGRlIGxvcyBkZXJlY2hvcyBkZSBhdXRvciwgYXV0b3JpemEgeSBjZWRlIGEgbGEgVW5pdmVyc2lkYWQgRnJhbmNpc2NvIGRlIFZpdG9yaWEsIGRlIGZvcm1hIGdyYXR1aXRhIHkgbm8gZXhjbHVzaXZhLCBwb3IgZWwgbcOheGltbyBwbGF6byBsZWdhbCB5IGNvbiDDoW1iaXRvIHVuaXZlcnNhbCwgbG9zIGRlcmVjaG9zIGRlIHJlcHJvZHVjY2nDs24sIGRpc3RyaWJ1Y2nDs24sIGNvbXVuaWNhY2nDs24gcMO6YmxpY2EsIGluY2x1aWRvIGVsIGRlcmVjaG8gZGUgcHVlc3RhIGEgZGlzcG9zaWNpw7NuIGVsZWN0csOzbmljYSwgeSBsYSB0cmFuc2Zvcm1hY2nDs24gZGUgZm9ybWF0byBzb2JyZSBsYSBvYnJhIGluZGljYWRhLCBzaSBmdWVyYSBlbCBjYXNvLgoKLSBFbiBlbCBjYXNvIGRlIGNlc2nDs24gZGUgZGVyZWNob3MgZGUgZXhwbG90YWNpw7NuIGEgdGVyY2Vyb3MsIGRlY2xhcmEgcXVlIGN1ZW50YSBjb24gbGEgYXV0b3JpemFjacOzbiBkZSBkaWNob3MgdGl0dWxhcmVzIHkgcXVlIGhhIG9idGVuaWRvIGVsIHBlcm1pc28gc2luIHJlc3RyaWNjaW9uZXMgZGVsIHByb3BpZXRhcmlvIGRlbCBjb3B5cmlnaHQgcGFyYSBvdG9yZ2FyIGEgbGEgaW5zdGl0dWNpw7NuIGxvcyBkZXJlY2hvcyByZXF1ZXJpZG9zIHBhcmEgZXN0YSBsaWNlbmNpYSB5IHF1ZSBkaWNobyBwcm9waWV0YXJpbyBjb25vY2UgZWwgdGV4dG8gbyBlbCBjb250ZW5pZG8gZGUgbGEgb2JyYS4KCi0gU2kgZnVlcmEgdW5hIG9icmEgcGF0cm9jaW5hZGEgcG9yIGFsZ3VuYSBpbnN0aXR1Y2nDs24gZGlzdGludGEgYSBsYSBVbml2ZXJzaWRhZCBGcmFuY2lzY28gZGUgVml0b3JpYSwgZGVjbGFyYSBxdWUgZW4gY2FzbyBuZWNlc2FyaW8sIGN1ZW50YSBjb24gbG9zIHBlcm1pc29zIHBlcnRpbmVudGVzLCBkZSBsYSBpbnN0aXR1Y2nDs24gbyBlbnRpZGFkLCBxdWUgbGUgcGVybWl0YW4gbGEgZGlmdXNpw7NuIGRlIGRpY2hhIG9icmEuCgotIExhIFVuaXZlcnNpZGFkIEZyYW5jaXNjbyBkZSBWaXRvcmlhIG5vIHRpZW5lIGxhIHRpdHVsYXJpZGFkIGRlIGxvcyBkZXJlY2hvcyBzb2JyZSBsYSBvYnJhLCBxdWUgY29ycmVzcG9uZGVuIGFsIGF1dG9yLCBwZXJvIHNpbiBlbWJhcmdvIMOpc3RhIGxpY2VuY2lhIGRhIGRlcmVjaG8gYSByZXByb2R1Y2lybGEgZW4gdW4gc29wb3J0ZSBkaWdpdGFsLCBkaXN0cmlidWlyIGEgbG9zIHVzdWFyaW9zIGNvcGlhcyBlbGVjdHLDs25pY2FzIGRlIGxhIG9icmEgZW4gZm9ybWF0byBkaWdpdGFsLCBjb211bmljYWNpw7NuIHDDumJsaWNhIHkgc3UgcHVlc3RhIGEgZGlzcG9zaWNpw7NuIGEgdHJhdsOpcyBkZSB1biBhcmNoaXZvIGFiaWVydG8gaW5zdGl0dWNpb25hbC4KCi0gTGEgb2JyYSBzZSBwb25kcsOhIGEgZGlzcG9zaWNpw7NuIGRlIGxvcyB1c3VhcmlvcyBwYXJhIHF1ZSBoYWdhbiBkZSBlbGxhIHVuIHVzbyBqdXN0byB5IHJlc3BldHVvc28gY29uIGxvcyBkZXJlY2hvcyBkZSBhdXRvciwgc2VhIGNvbiBmaW5lcyBkZSBlc3R1ZGlvLCBpbnZlc3RpZ2FjacOzbiBvIGN1YWxxdWllciBvdHJvIGZpbiBsw61jaXRvLCB5IGRlIGFjdWVyZG8gYSBsYXMgY29uZGljaW9uZXMgZXN0YWJsZWNpZGFzIGVuIGxhIGxpY2VuY2lhIENyZWF0aXZlIENvbW1vbnMsIGRlIG1vZG8gcXVlIGxhcyBvYnJhcyBwdWVkYW4gc2VyIGRpc3RyaWJ1aWRhcywgY29waWFkYXMgeSBleGhpYmlkYXMgc2llbXByZSBxdWUgc2UgY2l0ZSBsYSBhdXRvcsOtYSB5IG5vIHNlIG9idGVuZ2EgYmVuZWZpY2lvIGNvbWVyY2lhbC4gUG9yIHRhbnRvLCBsYSBVbml2ZXJzaWRhZCBubyBhc3VtaXLDoSByZXNwb25zYWJpbGlkYWQgYWxndW5hIHBvciBsYSBmb3JtYSBlZmVjdGl2YSBlbiBxdWUgbG9zIHVzdWFyaW9zIHV0aWxpY2VuIGVsIG1hdGVyaWFsIHB1ZXN0byBhIHN1IGRpc3Bvc2ljacOzbi4KCi0gRWwgYXV0b3IgcG9kcsOhIHNvbGljaXRhciBsYSByZXRpcmFkYSBkZSBsYSBvYnJhIGRlbCByZXBvc2l0b3JpbyBwb3IgY2F1c2EganVzdGlmaWNhZGEuIAoK</field>
  </element>
</metadata>