Actionable Explainable AI (AxAI): A Practical Example with Aggregation Functions for Adaptive Classification and Textual Explanations for Interpretable Machine Learning

In many domains of our daily life (e.g., agriculture, forestry, health, etc.), both laymen and experts need to classify entities into two binary classes (yes/no, good/bad, sufficient/insufficient, benign/malign, etc.). For many entities, this decision is difficult and we need another class called “m...

Full description

Saved in:

Bibliographic Details
Published in:	Machine learning and knowledge extraction Vol. 4; no. 4; pp. 924 - 953
Main Authors:	Saranti, Anna, Hudec, Miroslav, Mináriková, Erika, Takáč, Zdenko, Großschedl, Udo, Koch, Christoph, Pfeifer, Bastian, Angerschmid, Alessa, Holzinger, Andreas
Format:	Journal Article
Language:	English
Published:	Basel MDPI AG 01.12.2022
Subjects:	actionable explainable AI aggregation functions Artificial intelligence Classification continuous XOR-problem Decision making Domains Electronic data processing Explainable artificial intelligence Fuzzy algorithms Fuzzy logic Fuzzy sets Fuzzy systems interpretable machine learning Linguistics Machine learning Methods Neural networks Norms ordinal sums Parameters Subject specialists Austria
ISSN:	2504-4990, 2504-4990
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	In many domains of our daily life (e.g., agriculture, forestry, health, etc.), both laymen and experts need to classify entities into two binary classes (yes/no, good/bad, sufficient/insufficient, benign/malign, etc.). For many entities, this decision is difficult and we need another class called “maybe”, which contains a corresponding quantifiable tendency toward one of these two opposites. Human domain experts are often able to mark any entity, place it in a different class and adjust the position of the slope in the class. Moreover, they can often explain the classification space linguistically—depending on their individual domain experience and previous knowledge. We consider this human-in-the-loop extremely important and call our approach actionable explainable AI. Consequently, the parameters of the functions are adapted to these requirements and the solution is explained to the domain experts accordingly. Specifically, this paper contains three novelties going beyond the state-of-the-art: (1) A novel method for detecting the appropriate parameter range for the averaging function to treat the slope in the “maybe” class, along with a proposal for a better generalisation than the existing solution. (2) the insight that for a given problem, the family of t-norms and t-conorms covering the whole range of nilpotency is suitable because we need a clear “no” or “yes” not only for the borderline cases. Consequently, we adopted the Schweizer–Sklar family of t-norms or t-conorms in ordinal sums. (3) A new fuzzy quasi-dissimilarity function for classification into three classes: Main difference, irrelevant difference and partial difference. We conducted all of our experiments with real-world datasets.
AbstractList	In many domains of our daily life (e.g., agriculture, forestry, health, etc.), both laymen and experts need to classify entities into two binary classes (yes/no, good/bad, sufficient/insufficient, benign/malign, etc.). For many entities, this decision is difficult and we need another class called “maybe”, which contains a corresponding quantifiable tendency toward one of these two opposites. Human domain experts are often able to mark any entity, place it in a different class and adjust the position of the slope in the class. Moreover, they can often explain the classification space linguistically—depending on their individual domain experience and previous knowledge. We consider this human-in-the-loop extremely important and call our approach actionable explainable AI. Consequently, the parameters of the functions are adapted to these requirements and the solution is explained to the domain experts accordingly. Specifically, this paper contains three novelties going beyond the state-of-the-art: (1) A novel method for detecting the appropriate parameter range for the averaging function to treat the slope in the “maybe” class, along with a proposal for a better generalisation than the existing solution. (2) the insight that for a given problem, the family of t-norms and t-conorms covering the whole range of nilpotency is suitable because we need a clear “no” or “yes” not only for the borderline cases. Consequently, we adopted the Schweizer–Sklar family of t-norms or t-conorms in ordinal sums. (3) A new fuzzy quasi-dissimilarity function for classification into three classes: Main difference, irrelevant difference and partial difference. We conducted all of our experiments with real-world datasets.
Audience	Academic
Author	Saranti, Anna Mináriková, Erika Holzinger, Andreas Pfeifer, Bastian Angerschmid, Alessa Großschedl, Udo Hudec, Miroslav Koch, Christoph Takáč, Zdenko
Author_xml	– sequence: 1 givenname: Anna orcidid: 0000-0002-1085-8428 surname: Saranti fullname: Saranti, Anna – sequence: 2 givenname: Miroslav orcidid: 0000-0002-2868-0322 surname: Hudec fullname: Hudec, Miroslav – sequence: 3 givenname: Erika orcidid: 0000-0002-4230-2109 surname: Mináriková fullname: Mináriková, Erika – sequence: 4 givenname: Zdenko orcidid: 0000-0003-0767-4756 surname: Takáč fullname: Takáč, Zdenko – sequence: 5 givenname: Udo surname: Großschedl fullname: Großschedl, Udo – sequence: 6 givenname: Christoph surname: Koch fullname: Koch, Christoph – sequence: 7 givenname: Bastian orcidid: 0000-0001-7035-9535 surname: Pfeifer fullname: Pfeifer, Bastian – sequence: 8 givenname: Alessa orcidid: 0000-0001-9209-6676 surname: Angerschmid fullname: Angerschmid, Alessa – sequence: 9 givenname: Andreas orcidid: 0000-0002-6786-5194 surname: Holzinger fullname: Holzinger, Andreas
BookMark	eNptUs1u1DAQjlCRKKUnXsASFxDaYif2OuYWrVqItAgO5RxNnHHqJWsHxwvLG_Ux600QVAj54NH4-xl9nufZmfMOs-wlo1dFoei7PXxDTjmlXD7JznNB-YorRc8e1c-yy2naUUpzqTij_Dy7r3S03kE7ILk-jgPYpa5q8ro6VvWb96QiXwIklIYhQWA_puefNt6Rqu8D9nDik5uDm4UmYnwgVQdjtD-QbAaYJmsSd0aB68gtHuNhlkpuDv6SahcxjAHjPMAn0HfWIdkiBGdd_yJ7amCY8PL3fZF9vbm-3XxcbT9_qDfVdqU5LeKqVUJoLdYpBSZVq5lAgWtDUxcUa1HK3HQGTKlaBakULevKQhjBdStNmRcXWb3odh52zRjsHsKvxoNt5oYPfQMhhTFgg5p2WEjDS5Vz5Los1hw0YK5MXq4LmrReLVpj8N8POMVm5w_BpfGbXIq1LBRTJ8erBdVDErXO-JjyTqfDvdXpj41N_UoKlkvO2InwdiHo4KcpoPkzJqPNaRWaR6uQ0OwftLZxjj3Z2OG_nAf-cLqf
CitedBy_id	crossref_primary_10_1016_j_ijhcs_2025_103444 crossref_primary_10_1016_j_ins_2023_119898 crossref_primary_10_3390_info14030164 crossref_primary_10_3390_s23073518 crossref_primary_10_1016_j_knosys_2023_110866 crossref_primary_10_1038_s41598_023_31807_1 crossref_primary_10_1002_widm_1554 crossref_primary_10_1145_3670685 crossref_primary_10_1016_j_ins_2023_119418 crossref_primary_10_3390_app14093911 crossref_primary_10_1007_s10044_025_01532_8 crossref_primary_10_1016_j_cogsys_2024_101243 crossref_primary_10_1080_00140139_2023_2243404 crossref_primary_10_1016_j_ijhcs_2023_103029 crossref_primary_10_1016_j_foreco_2023_121530 crossref_primary_10_3389_fpls_2024_1319938 crossref_primary_10_3389_fsysb_2023_1136999 crossref_primary_10_1016_j_artmed_2024_102770
Cites_doi	10.1109/ISCC.2017.8024530 10.1093/oso/9780198538493.001.0001 10.1109/CVPR.2016.90 10.1038/nature14236 10.1002/9781119256489 10.1007/BF00337288 10.1016/j.knosys.2021.107427 10.1038/nature21056 10.1007/s10489-018-1361-5 10.1371/journal.pone.0177544 10.1109/35.41401 10.1016/j.eswa.2012.07.032 10.1007/978-3-7908-1850-5 10.1109/MC.2021.3092610 10.1161/01.CIR.69.3.541 10.1016/j.inffus.2019.12.012 10.1259/bjr.20170545 10.1007/978-3-662-43505-2 10.3390/s22083043 10.1016/0002-9149(89)90524-9 10.1016/j.ins.2012.11.012 10.2140/pjm.1960.10.313 10.1109/FUZZ45933.2021.9494563 10.1016/j.patcog.2021.107899 10.1016/j.entcs.2009.07.045 10.1007/978-3-319-94463-0 10.1016/j.fss.2021.09.013 10.1016/j.clsr.2021.105587 10.1016/j.knosys.2021.106916 10.1145/3458652 10.3390/electronics10050593 10.1109/91.493904 10.1016/j.compbiomed.2022.105458 10.1145/3065386 10.1371/journal.pone.0130140 10.1007/978-3-031-04083-2_2 10.1016/0002-9149(72)90624-8 10.1016/j.inffus.2021.01.008 10.1186/s12859-015-0615-z 10.1016/0165-0114(92)90239-Z 10.1016/S1364-6613(99)01294-2 10.1007/978-3-7908-1796-6_11 10.1016/j.fss.2020.03.019 10.4018/jssci.2009010107 10.1016/j.patcog.2017.10.013 10.1007/978-3-031-14463-9_23
ContentType	Journal Article
Copyright	COPYRIGHT 2022 MDPI AG 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml	– notice: COPYRIGHT 2022 MDPI AG – notice: 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID	AAYXX CITATION 8FE 8FG ABUWG AFKRA ARAPS AZQEC BENPR BGLVJ CCPQU DWQXO GNUQQ HCIFZ JQ2 K7- P5Z P62 PHGZM PHGZT PIMPY PKEHL PQEST PQGLB PQQKQ PQUKI PRINS DOA
DOI	10.3390/make4040047
DatabaseName	CrossRef ProQuest SciTech Collection ProQuest Technology Collection ProQuest Central (Alumni) ProQuest Central Advanced Technologies & Computer Science Collection ProQuest Central Essentials ProQuest Central ProQuest Technology Collection ProQuest One ProQuest Central ProQuest Central Student SciTech Premium Collection ProQuest Computer Science Collection Computer Science Database Advanced Technologies & Aerospace Database ProQuest Advanced Technologies & Aerospace Collection Proquest Central Premium ProQuest One Academic Publicly Available Content Database ProQuest One Academic Middle East (New) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Applied & Life Sciences ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China Directory of Open Access Journals
DatabaseTitle	CrossRef Publicly Available Content Database Advanced Technologies & Aerospace Collection Computer Science Database ProQuest Central Student Technology Collection ProQuest One Academic Middle East (New) ProQuest Advanced Technologies & Aerospace Collection ProQuest Central Essentials ProQuest Computer Science Collection ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Technology Collection ProQuest SciTech Collection ProQuest Central China ProQuest Central Advanced Technologies & Aerospace Database ProQuest One Applied & Life Sciences ProQuest One Academic UKI Edition ProQuest Central Korea ProQuest Central (New) ProQuest One Academic ProQuest One Academic (New)
DatabaseTitleList	CrossRef Publicly Available Content Database
Database_xml	– sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: PIMPY name: Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
EISSN	2504-4990
EndPage	953
ExternalDocumentID	oai_doaj_org_article_ec0de37f48924e4c8364acae29f28630 A751274112 10_3390_make4040047
GeographicLocations	Austria
GeographicLocations_xml	– name: Austria
GroupedDBID	AADQD AAFWJ AAYXX AFFHD AFKRA AFPKN AFZYC ALMA_UNASSIGNED_HOLDINGS ARAPS BENPR BGLVJ CCPQU CITATION GROUPED_DOAJ HCIFZ IAO ICD ITC K7- MODMG M~E OK1 PHGZM PHGZT PIMPY PQGLB 8FE 8FG ABUWG AZQEC DWQXO GNUQQ JQ2 P62 PKEHL PQEST PQQKQ PQUKI PRINS
ID	FETCH-LOGICAL-c403t-b955cc56004179bc15e5e6f055ca91be772fdfaf89b9a2fd5b1d835f54cb7f823
IEDL.DBID	DOA
ISICitedReferencesCount	18
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000902726900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2504-4990
IngestDate	Fri Oct 03 12:50:34 EDT 2025 Fri Jul 25 22:05:20 EDT 2025 Tue Nov 04 18:08:05 EST 2025 Tue Nov 18 22:21:45 EST 2025 Sat Nov 29 07:17:26 EST 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	4
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c403t-b955cc56004179bc15e5e6f055ca91be772fdfaf89b9a2fd5b1d835f54cb7f823
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0001-9209-6676 0000-0002-6786-5194 0000-0001-7035-9535 0000-0002-1085-8428 0000-0002-2868-0322 0000-0002-4230-2109 0000-0003-0767-4756
OpenAccessLink	https://doaj.org/article/ec0de37f48924e4c8364acae29f28630
PQID	2756739192
PQPubID	5046881
PageCount	30
ParticipantIDs	doaj_primary_oai_doaj_org_article_ec0de37f48924e4c8364acae29f28630 proquest_journals_2756739192 gale_infotracacademiconefile_A751274112 crossref_primary_10_3390_make4040047 crossref_citationtrail_10_3390_make4040047
PublicationCentury	2000
PublicationDate	2022-12-01
PublicationDateYYYYMMDD	2022-12-01
PublicationDate_xml	– month: 12 year: 2022 text: 2022-12-01 day: 01
PublicationDecade	2020
PublicationPlace	Basel
PublicationPlace_xml	– name: Basel
PublicationTitle	Machine learning and knowledge extraction
PublicationYear	2022
Publisher	MDPI AG
Publisher_xml	– name: MDPI AG
References	ref_50 Shehab (ref_11) 2022; 145 Hudec (ref_3) 2021; 220 ref_58 ref_13 Burt (ref_19) 2018; 91 Holzinger (ref_30) 2019; 49 ref_12 ref_56 ref_55 Patricia (ref_2) 2021; 17 ref_10 ref_54 Kohonen (ref_32) 1982; 43 ref_53 ref_52 ref_51 Esteva (ref_18) 2017; 542 Bartoszuk (ref_1) 2021; 231 ref_17 ref_15 ref_59 Detrano (ref_62) 1989; 64 Detrano (ref_64) 1984; 69 Wei (ref_6) 2021; 52 Uriz (ref_49) 2022; 441 Haq (ref_60) 2018; 2018 Stoeger (ref_23) 2021; 64 Holzinger (ref_24) 2021; 54 Nahar (ref_61) 2013; 40 ref_67 ref_22 French (ref_21) 1999; 3 Holzinger (ref_71) 2021; 71 ref_29 Yeom (ref_42) 2021; 115 ref_26 Holzinger (ref_14) 2022; 130 ref_72 Durante (ref_44) 2005; 41 ref_70 Couso (ref_27) 2013; 229 Lippmann (ref_31) 1989; 27 Bustince (ref_28) 2021; 414 ref_36 Mnih (ref_57) 2015; 518 ref_35 ref_34 Krizhevsky (ref_16) 2017; 60 ref_33 Abdar (ref_66) 2015; 8 Bedregal (ref_25) 2009; 247 ref_73 Schweizer (ref_46) 1960; 10 ref_39 Kannel (ref_63) 1972; 29 Arrieta (ref_7) 2020; 58 ref_37 Alber (ref_41) 2019; 20 Sojka (ref_68) 2020; 31 Kacprzyk (ref_69) 2009; 1 ref_47 ref_45 Mesquita (ref_65) 1996; 15 ref_43 ref_40 Gu (ref_38) 2018; 77 Liu (ref_48) 1992; 52 ref_9 ref_8 Zadeh (ref_4) 1996; 4 ref_5 Stoeger (ref_20) 2021; 42
References_xml	– ident: ref_59 doi: 10.1109/ISCC.2017.8024530 – ident: ref_33 doi: 10.1093/oso/9780198538493.001.0001 – ident: ref_37 doi: 10.1109/CVPR.2016.90 – ident: ref_5 – ident: ref_55 – volume: 518 start-page: 529 year: 2015 ident: ref_57 article-title: Human-level control through deep reinforcement learning publication-title: Nature doi: 10.1038/nature14236 – ident: ref_51 – ident: ref_45 doi: 10.1002/9781119256489 – volume: 43 start-page: 59 year: 1982 ident: ref_32 article-title: Self-organized formation of topologically correct feature maps publication-title: Biol. Cybern. doi: 10.1007/BF00337288 – volume: 231 start-page: 107427 year: 2021 ident: ref_1 article-title: T-norms or t-conorms? How to aggregate similarity degrees for plagiarism detection publication-title: Knowl.-Based Syst. doi: 10.1016/j.knosys.2021.107427 – volume: 542 start-page: 115 year: 2017 ident: ref_18 article-title: Dermatologist-level classification of skin cancer with deep neural networks publication-title: Nature doi: 10.1038/nature21056 – volume: 49 start-page: 2401 year: 2019 ident: ref_30 article-title: Interactive machine learning: Experimental evidence for the human in the algorithmic loop publication-title: Appl. Intell. doi: 10.1007/s10489-018-1361-5 – ident: ref_39 – ident: ref_17 doi: 10.1371/journal.pone.0177544 – volume: 27 start-page: 47 year: 1989 ident: ref_31 article-title: Pattern classification using neural networks publication-title: IEEE Commun. Mag. doi: 10.1109/35.41401 – volume: 40 start-page: 96 year: 2013 ident: ref_61 article-title: Computational intelligence for heart disease diagnosis: A medical knowledge driven approach publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2012.07.032 – ident: ref_35 – ident: ref_29 doi: 10.1007/978-3-7908-1850-5 – volume: 54 start-page: 78 year: 2021 ident: ref_24 article-title: Toward Human-AI Interfaces to Support Explainability and Causability in Medical AI publication-title: IEEE Comput. doi: 10.1109/MC.2021.3092610 – volume: 17 start-page: 15 year: 2021 ident: ref_2 article-title: Optimal design of type-2 fuzzy systems for diabetes classification based on genetic algorithms publication-title: Int. J. Hybrid Intell. Syst. – ident: ref_58 – volume: 69 start-page: 541 year: 1984 ident: ref_64 article-title: Bayesian probability analysis: A prospective demonstration of its clinical utility in diagnosing coronary disease publication-title: Circulation doi: 10.1161/01.CIR.69.3.541 – volume: 58 start-page: 82 year: 2020 ident: ref_7 article-title: Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI publication-title: Inf. Fusion doi: 10.1016/j.inffus.2019.12.012 – volume: 91 start-page: 20170545 year: 2018 ident: ref_19 article-title: Deep learning beyond cats and dogs: Recent advances in diagnosing breast cancer with deep neural networks publication-title: Br. J. Radiol. doi: 10.1259/bjr.20170545 – ident: ref_26 doi: 10.1007/978-3-662-43505-2 – ident: ref_12 doi: 10.3390/s22083043 – ident: ref_56 – volume: 64 start-page: 304 year: 1989 ident: ref_62 article-title: International application of a new probability algorithm for the diagnosis of coronary artery disease publication-title: Am. J. Cardiol. doi: 10.1016/0002-9149(89)90524-9 – ident: ref_52 – volume: 229 start-page: 122 year: 2013 ident: ref_27 article-title: Similarity and dissimilarity measures between fuzzy sets: A formal relational study publication-title: Inf. Sci. doi: 10.1016/j.ins.2012.11.012 – volume: 15 start-page: 139 year: 1996 ident: ref_65 article-title: The maximum heart rate in the exercise test: The 220-age formula or Sheffield’s table? publication-title: Rev. Port. Cardiol. Orgao Of. Soc. Port. Cardiol. Port. J. Cardiol. Off. J. Port. Soc. Cardiol. – volume: 52 start-page: 6866 year: 2021 ident: ref_6 article-title: Global fusion of multiple order relations and hesitant fuzzy decision analysis publication-title: Appl. Intell. – ident: ref_72 – volume: 10 start-page: 313 year: 1960 ident: ref_46 article-title: Statistical metric spaces publication-title: Pac. J. Math. doi: 10.2140/pjm.1960.10.313 – volume: 130 start-page: 40 year: 2022 ident: ref_14 article-title: Challenges in Artificial Intelligence for Smart Forestry publication-title: Eur. Res. Consort. Informatics Math. (ERCIM) News – ident: ref_8 doi: 10.1109/FUZZ45933.2021.9494563 – volume: 115 start-page: 107899 year: 2021 ident: ref_42 article-title: Pruning by explaining: A novel criterion for deep neural network pruning publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2021.107899 – volume: 247 start-page: 5 year: 2009 ident: ref_25 article-title: Xor-implications and E-implications: Classes of fuzzy implications based on fuzzy Xor publication-title: Electron. Notes Theor. Comput. Sci. doi: 10.1016/j.entcs.2009.07.045 – ident: ref_53 – ident: ref_36 doi: 10.1007/978-3-319-94463-0 – volume: 441 start-page: 169 year: 2022 ident: ref_49 article-title: Discrete IV dG-Choquet integrals with respect to admissible orders publication-title: Fuzzy Sets Syst. doi: 10.1016/j.fss.2021.09.013 – volume: 42 start-page: 105587 year: 2021 ident: ref_20 article-title: Legal aspects of data cleansing in medical AI publication-title: Comput. Law Secur. Rev. doi: 10.1016/j.clsr.2021.105587 – ident: ref_34 – ident: ref_47 – volume: 8 start-page: 31 year: 2015 ident: ref_66 article-title: Using decision trees in data mining for predicting factors influencing of heart disease publication-title: Carpathian J. Electron. Comput. Eng. – volume: 220 start-page: 106916 year: 2021 ident: ref_3 article-title: Classification by ordinal sums of conjunctive and disjunctive functions for explainable AI and interpretable machine learning solutions publication-title: Knowl. Based Syst. doi: 10.1016/j.knosys.2021.106916 – volume: 64 start-page: 34 year: 2021 ident: ref_23 article-title: Medical Artificial Intelligence: The European Legal Perspective publication-title: Commun. ACM doi: 10.1145/3458652 – ident: ref_67 – ident: ref_9 doi: 10.3390/electronics10050593 – volume: 4 start-page: 103 year: 1996 ident: ref_4 article-title: Fuzzy logic = computing with words publication-title: IEEE Trans. Fuzzy Syst. doi: 10.1109/91.493904 – volume: 20 start-page: 1 year: 2019 ident: ref_41 article-title: iNNvestigate neural networks! publication-title: J. Mach. Learn. Res. (JMLR) – volume: 41 start-page: 315 year: 2005 ident: ref_44 article-title: Semicopulae publication-title: Kybernetika – ident: ref_73 – volume: 145 start-page: 105458 year: 2022 ident: ref_11 article-title: Machine learning in medical applications: A review of state-of-the-art methods publication-title: Comput. Biol. Med. doi: 10.1016/j.compbiomed.2022.105458 – volume: 60 start-page: 84 year: 2017 ident: ref_16 article-title: Imagenet classification with deep convolutional neural networks publication-title: Commun. ACM doi: 10.1145/3065386 – ident: ref_40 doi: 10.1371/journal.pone.0130140 – ident: ref_10 doi: 10.1007/978-3-031-04083-2_2 – ident: ref_50 – volume: 29 start-page: 154 year: 1972 ident: ref_63 article-title: Natural history of angina pectoris in the Framingham study: Prognosis and survival publication-title: Am. J. Cardiol. doi: 10.1016/0002-9149(72)90624-8 – ident: ref_54 – volume: 31 start-page: 841 year: 2020 ident: ref_68 article-title: Linguistic Summaries in Evaluating Elementary Conditions, Summarizing Data and Managing Nested Queries publication-title: Informatica – volume: 71 start-page: 28 year: 2021 ident: ref_71 article-title: Towards Multi-Modal Causability with Graph Neural Networks enabling Information Fusion for explainable AI publication-title: Inf. Fusion doi: 10.1016/j.inffus.2021.01.008 – ident: ref_70 doi: 10.1186/s12859-015-0615-z – volume: 52 start-page: 305 year: 1992 ident: ref_48 article-title: Entropy, distance measure and similarity measure of fuzzy sets and their relations publication-title: Fuzzy Sets Syst. doi: 10.1016/0165-0114(92)90239-Z – ident: ref_15 – volume: 3 start-page: 128 year: 1999 ident: ref_21 article-title: Catastrophic forgetting in connectionist networks publication-title: Trends Cogn. Sci. doi: 10.1016/S1364-6613(99)01294-2 – volume: 2018 start-page: 3860146 year: 2018 ident: ref_60 article-title: A hybrid intelligent system framework for the prediction of heart disease using machine learning algorithms publication-title: Mob. Inf. Syst. – ident: ref_43 doi: 10.1007/978-3-7908-1796-6_11 – volume: 414 start-page: 1 year: 2021 ident: ref_28 article-title: d-Choquet integrals: Choquet integrals based on dissimilarities publication-title: Fuzzy Sets Syst. doi: 10.1016/j.fss.2020.03.019 – volume: 1 start-page: 100 year: 2009 ident: ref_69 article-title: Protoforms of linguistic database summaries as a human consistent tool for using natural language in data mining publication-title: Int. J. Softw. Sci. Comput. Intell. doi: 10.4018/jssci.2009010107 – ident: ref_22 – volume: 77 start-page: 354 year: 2018 ident: ref_38 article-title: Recent advances in convolutional neural networks publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2017.10.013 – ident: ref_13 doi: 10.1007/978-3-031-14463-9_23
SSID	ssj0002794104
Score	2.3447175
Snippet	In many domains of our daily life (e.g., agriculture, forestry, health, etc.), both laymen and experts need to classify entities into two binary classes...
SourceID	doaj proquest gale crossref
SourceType	Open Website Aggregation Database Enrichment Source Index Database
StartPage	924
SubjectTerms	actionable explainable AI aggregation functions Artificial intelligence Classification continuous XOR-problem Decision making Domains Electronic data processing Explainable artificial intelligence Fuzzy algorithms Fuzzy logic Fuzzy sets Fuzzy systems interpretable machine learning Linguistics Machine learning Methods Neural networks Norms ordinal sums Parameters Subject specialists
SummonAdditionalLinks	– databaseName: Computer Science Database dbid: K7- link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LjxMxDI5g4cCFhwBRWFAOK_GQop08ZibDBQVExQpYcVjQ3qI8KwS0pe0ifhI_EzuTdkECLtxGGbeTyl8d22N_JuRAp8CFk5LpmANTMrTM68hZTsGFhsecy_yUD2_642N9ejq8qwm3dS2r3NrEYqjjImCO_BBpyns5gEPybPmV4dQofLtaR2hcJJe4EBxx_rpnuxyLALBBuDG25UmI7g-_uE9JFdz2vx1Eha__b1a5HDXTa_-7yevkanUyqRlRcYNcSPOb5IcpLQzYKkWx8q62TVFzRB-Z7-bo8VNq6EhfBHoDEYfEwRQTtdTMICyfFSXSKZyEBawU_F1qoluixaRluibWHY1Sbh7pCRj-s_JV8LQx6zh-6LzSETfwttRzJlqpXme3yPvpy5MXr1id08CCauSG-aFtQ0DXCceZ-cDb1KYuN7DqBu4TOPA5Zpf14AcHl63nERy_3Krg-6yFvE325ot5ukOoV6kH-eQ7nSBwh_C5cZ1PYvAanuDUhDzZKs2GSmKOszQ-WwhmUMP2Fw1PyMFOeDlyd_xZ7DlqfyeChNtlYbGa2fr_tSk0Mck-Kw0Ba1JBy0654GBnWehONhPyELFj0SzAhgDoY3cD_Cwk2LKmB88KvDcuJmR_ix1b7cXangPn7r9v3yNXBDZglIKafbK3WZ2l--Ry-Lb5uF49KPD_CU2_Evc priority: 102 providerName: ProQuest
Title	Actionable Explainable AI (AxAI): A Practical Example with Aggregation Functions for Adaptive Classification and Textual Explanations for Interpretable Machine Learning
URI	https://www.proquest.com/docview/2756739192 https://doaj.org/article/ec0de37f48924e4c8364acae29f28630
Volume	4
WOSCitedRecordID	wos000902726900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2504-4990 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002794104 issn: 2504-4990 databaseCode: DOA dateStart: 20190101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2504-4990 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002794104 issn: 2504-4990 databaseCode: M~E dateStart: 20190101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: Advanced Technologies & Aerospace Database customDbUrl: eissn: 2504-4990 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002794104 issn: 2504-4990 databaseCode: P5Z dateStart: 20210101 isFulltext: true titleUrlDefault: https://search.proquest.com/hightechjournals providerName: ProQuest – providerCode: PRVPQU databaseName: Computer Science Database customDbUrl: eissn: 2504-4990 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002794104 issn: 2504-4990 databaseCode: K7- dateStart: 20210101 isFulltext: true titleUrlDefault: http://search.proquest.com/compscijour providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 2504-4990 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002794104 issn: 2504-4990 databaseCode: BENPR dateStart: 20210101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: Publicly Available Content Database customDbUrl: eissn: 2504-4990 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002794104 issn: 2504-4990 databaseCode: PIMPY dateStart: 20210101 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Rb9MwELbQ4IGXCQQThTH5YdIAKVoSO4nDm4dWUY1VEdqmwYtlO-dqA8q0ddN-Ej-TOzvbigTiZS9RlV4b13exvy-9-46xTQW-KK0QmeqDz6TwVeZUX2QBvPV50YcQ-6ccfWqmU3V83HZLrb4oJyzJA6eJ2waf9yCaIBUyBZBeiVpab6FsQ6lqEdk6op4lMnUa_05rJRKNVJAnkNdv_7DfQMaIbf7YgqJS_7_W47jJjJ-w1QEdcp1G9ZQ9gPkz9kvH2gOqceKUMjfUO3E94W_0tZ68fc81T7pDOOFoYknxl9MTVq5nyKdncfb5GLewGGUcgSrXvT2jpY7HtpiUMJSs7LznB7hiX8avwqulx4XpQ3cpijSA_ZiICXzQaJ09Z4fj3YMPH7OhwULmZS4WmWurynvCPNSHzPmiggrqkONZ2xYOEHmHPtigWtdafFm5okfEFirpXRNUKdbYyvznHF4w7iQ0aA-uVoCMG3lvbmuHXnIKr2DliL27mXPjB_VxaoLx3SALIQeZJQeN2Oat8VkS3fi72Q4579aElLLjCYwfM8SP-V_8jNgWud7Q_YwDwghNZQn4s0gZy-gGIRHCrqIcsfWb6DDDjX5hSD2_ES3i5Jf3MZpX7HFJ9RUxX2adrSzOL-E1e-SvFicX5xvs4c7utPu8EWMdj3tNhseu-orvdJP97stvFcsKVg
linkProvider	Directory of Open Access Journals
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lj9MwELZWCxJceAgQZRfwYREPKdokdhIHCaHwqLZqt-JQ0N6M7YyjFWxb2i6Pf8SJ38iMk3ZBAm574BY5k8RxPs-MnZlvGNtT4JLUCBGp2rtICpdFVtVJ5MEZFye196F-yrtRMR6ro6PyzRb7sc6FobDKtU4MirqeOdoj3yea8kKU6JA8n3-KqGoU_V1dl9BoYTGEb19wybZ8NniF3_dBmvZfT14eRF1VgcjJWKwiW2aZc2ToqfiWdUkGGeQ-xlZTJhbQ3fS1N16VtjR4mNmkRjfFZ9LZwisiOkCVf0EKVRBX_7CINns6KYIblzdtGqAQZbx_Yj6ADPOk-M3whfoAf7MCwbT1r_5vg3KNXemcaF61qL_OtmB6g32vQooGpYJxiizs0sJ4NeCPqq_V4PFTXvGWnglxiSKGiJE5bUTzqmkW0ASQ8j5a-jAZOfrzvKrNnCwCD9VDKa6qlTLTmk_QsJ2GW-HT2l3V9qKzSE7qwGGIVwXeUdk2N9nbcxmcW2x7OpvCbcathALlweYKZF4KJWKTW0hLq_AJRvbYkzVItOtI2qlWyEeNizVClP4FUT22txGet9wkfxZ7QWjbiBCheGiYLRrd6ScNLq5BFF4qXJCDdErk0jiDPfOpykXcYw8Jq5rUHnYIJ3KbvYGvRQRiuirQc0TvNEl7bHeNVd3pw6U-A-qdf5--zy4dTA5HejQYD3fY5ZSSTULw0C7bXi1O4S676D6vjpeLe2Hqcfb-vGH9E-zdcXg
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lj9MwELZWC0JceAgQhQV8WMRDiprETuIgIRRYKqou1R4WtDdjO-NoBbSl7fL4R_wGfh0zTtIFCbjtgVuVThLH-eZhZ-YbxnYVuCQ1QkSq9i6SwmWRVXUSeXDGxUntfeif8na_mE7V0VF5sMV-9LUwlFbZ28RgqOu5oz3yIdGUF6LEgGTou7SIg73Rs8WniDpI0ZfWvp1GC5EJfPuCy7fV0_Eevuv7aTp6efjiVdR1GIicjMU6smWWOUdOnxpxWZdkkEHuYzxqysQChp6-9sar0pYGf2Y2qTFk8Zl0tvCKSA_Q_J9DL5yRjk2KaLO_kyLQcanTlgQKUcbDj-Y9yKAzxW9OMPQK-JtHCG5udPl_nqAr7FIXXPOq1YarbAtm19j3KpRuUIkYp4zDrlyMV2P-sPpajR894RVvaZsQryhiiDCZ0wY1r5pmCU0ALx9hBBCUlGOcz6vaLMhT8NBVlPKtWikzq_khTspJuBTerd1tbU86zfCkAbwOeazAO4rb5jp7cyaTc4Ntz-YzuMm4lVCgPNhcgcxLoURscgtpaRXewcgBe9wDRruOvJ16iHzQuIgjdOlf0DVguxvhRctZ8mex54S8jQgRjYcD82WjO7ulwcU1iMJLhQt1kE6JXBpncGQ-VbmIB-wB4VaTOcQBoYK3VR34WEQspqsCI0qMWpN0wHZ63OrOTq70KWhv_fvve-wColnvj6eT2-xiSjUoIadoh22vlydwh513n9fHq-XdoIWcvTtrVP8EgP56Mg
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Actionable+Explainable+AI+%28AxAI%29%3A+A+Practical+Example+with+Aggregation+Functions+for+Adaptive+Classification+and+Textual+Explanations+for+Interpretable+Machine+Learning&rft.jtitle=Machine+learning+and+knowledge+extraction&rft.au=Anna+Saranti&rft.au=Miroslav+Hudec&rft.au=Erika+Min%C3%A1rikov%C3%A1&rft.au=Zdenko+Tak%C3%A1%C4%8D&rft.date=2022-12-01&rft.pub=MDPI+AG&rft.eissn=2504-4990&rft.volume=4&rft.issue=4&rft.spage=924&rft.epage=953&rft_id=info:doi/10.3390%2Fmake4040047&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_ec0de37f48924e4c8364acae29f28630
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2504-4990&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2504-4990&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2504-4990&client=summon