Knowledge Representation and Reasoning Research Publications

Description Logics (DLs) under Rational Closure (RC) is a well-known framework for non-monotonic reasoning in DLs. In this paper, we address the concept subsumption decision problem under RC for nominal safe ELO⊥, a notable and practically important DL representative of the OWL 2 profile OWL 2 EL. Our contribution here is to define a polynomial time subsumption procedure for nominal safe ELO⊥ under RC that relies entirely on a series of classical, monotonic EL⊥ subsumption tests. Therefore, any existing classical monotonic EL⊥ reasoner can be used as a black box to implement our method. We then also adapt the method to one of the known extensions of RC for DLs, namely Defeasible Inheritance-based DLs without losing the computational tractability.

@article{221,
  author = {Giovanni Casini and Umberto Straccia and Tommie Meyer},
  title = {A polynomial Time Subsumption Algorithm for Nominal Safe ELO⊥ under Rational Closure},
  abstract = {Description Logics (DLs) under Rational Closure (RC) is a well-known framework for non-monotonic reasoning in DLs. In this paper, we address the concept subsumption decision problem under RC for nominal safe ELO⊥, a notable and practically important DL representative of the OWL 2 profile OWL 2 EL. Our contribution here is to define a polynomial time subsumption procedure for nominal safe ELO⊥ under RC that relies entirely on a series of classical, monotonic EL⊥ subsumption tests. Therefore, any existing classical monotonic EL⊥ reasoner can be used as a black box to implement our method. We then also adapt the method to one of the known extensions of RC for DLs, namely Defeasible Inheritance-based DLs without losing the computational tractability.},
  year = {2019},
  journal = {Information Sciences},
  volume = {501},
  pages = {588 - 620},
  publisher = {Elsevier},
  isbn = {0020-0255},
  url = {http://www.sciencedirect.com/science/article/pii/S0020025518307436},
  doi = {https://doi.org/10.1016/j.ins.2018.09.037},
}

Cybersecurity analysts rely on vast volumes of security event data to predict, identify, characterize, and deal with security threats. These analysts must understand and make sense of these huge datasets in order to discover patterns which lead to intelligent decision making and advance warnings of possible threats, and this ability requires automation. Big data analytics and artificial intelligence can improve cyber defense. Big data analytics methods are applied to large data sets that contain different data types. The purpose is to detect patterns, correlations, trends, and other useful information. Artificial intelligence provides algorithms that can reason or learn and improve their behavior, and includes semantic technologies. A large number of automated systems are currently based on syntactic rules which are generally not sophisticated enough to deal with the level of complexity in this domain. An overview of artificial intelligence and big data technologies in cyber defense is provided, and important areas for future research are identified and discussed.

@inbook{220,
  author = {Louise Leenen and Tommie Meyer},
  title = {Artificial Intelligence and Big Data Analytics in Support of Cyber Defense},
  abstract = {Cybersecurity analysts rely on vast volumes of security event data to predict, identify, characterize, and deal with security threats. These analysts must understand and make sense of these huge datasets in order to discover patterns which lead to intelligent decision making and advance warnings of possible threats, and this ability requires automation. Big data analytics and artificial intelligence can improve cyber defense. Big data analytics methods are applied to large data sets that contain different data types. The purpose is to detect patterns, correlations, trends, and other useful information. Artificial intelligence provides algorithms that can reason or learn and improve their behavior, and includes semantic technologies. A large number of automated systems are currently based on syntactic rules which are generally not sophisticated enough to deal with the level of complexity in this domain. An overview of artificial intelligence and big data technologies in cyber defense is provided, and important areas for future research are identified and discussed.},
  year = {2019},
  journal = {Developments in Information Security and Cybernetic Wars},
  pages = {42 - 63},
  publisher = {Information Science Reference, IGI Global},
  address = {United States of America},
  isbn = {9781522583042},
  doi = {10.4018/978-1-5225-8304-2.ch002},
}

Propositional Typicality Logic (PTL) is a recently proposed logic, obtained by enriching classical propositional logic with a typicality operator capturing the most typical (alias normal or conventional) situations in which a given sentence holds. The semantics of PTL is in terms of ranked models as studied in the well-known KLM approach to preferential reasoning and therefore KLM-style rational consequence relations can be embedded in PTL. In spite of the non-monotonic features introduced by the semantics adopted for the typicality operator, the obvious Tarskian definition of entailment for PTL remains monotonic and is therefore not appropriate in many contexts. Our first important result is an impossibility theorem showing that a set of proposed postulates that at first all seem appropriate for a notion of entailment with regard to typicality cannot be satisfied simultaneously. Closer inspection reveals that this result is best interpreted as an argument for advocating the development of more than one type of PTL entailment. In the spirit of this interpretation, we investigate three different (semantic) versions of entailment for PTL, each one based on the definition of rational closure as introduced by Lehmann and Magidor for KLM-style conditionals, and constructed using different notions of minimality.

@article{219,
  author = {Richard Booth and Giovanni Casini and Tommie Meyer and Ivan Varzinczak},
  title = {On rational entailment for Propositional Typicality Logic},
  abstract = {Propositional Typicality Logic (PTL) is a recently proposed logic, obtained by enriching classical propositional logic with a typicality operator capturing the most typical (alias normal or conventional) situations in which a given sentence holds. The semantics of PTL is in terms of ranked models as studied in the well-known KLM approach to preferential reasoning and therefore KLM-style rational consequence relations can be embedded in PTL. In spite of the non-monotonic features introduced by the semantics adopted for the typicality operator, the obvious Tarskian definition of entailment for PTL remains monotonic and is therefore not appropriate in many contexts. Our first important result is an impossibility theorem showing that a set of proposed postulates that at first all seem appropriate for a notion of entailment with regard to typicality cannot be satisfied simultaneously. Closer inspection reveals that this result is best interpreted as an argument for advocating the development of more than one type of PTL entailment. In the spirit of this interpretation, we investigate three different (semantic) versions of entailment for PTL, each one based on the definition of rational closure as introduced by Lehmann and Magidor for KLM-style conditionals, and constructed using different notions of minimality.},
  year = {2019},
  journal = {Artificial Intelligence},
  volume = {227},
  pages = {103178},
  publisher = {Elsevier},
  isbn = {0004-3702},
  url = {https://www.sciencedirect.com/science/article/abs/pii/S000437021830506X?via%3Dihub},
  doi = {https://doi.org/10.1016/j.artint.2019.103178},
}

The Governments, military forces and other organisations responsible for cybersecurity deal with vast amounts of data that has to be understood in order to lead to intelligent decision making. Due to the vast amounts of information pertinent to cybersecurity, automation is required for processing and decision making, specifically to present advance warning of possible threats. The ability to detect patterns in vast data sets, and being able to understanding the significance of detected patterns are essential in the cyber defence domain. Big data technologies supported by semantic technologies can improve cybersecurity, and thus cyber defence by providing support for the processing and understanding of the huge amounts of information in the cyber environment. The term big data analytics refers to advanced analytic techniques such as machine learning, predictive analysis, and other intelligent processing techniques applied to large data sets that contain different data types. The purpose is to detect patterns, correlations, trends and other useful information. Semantic technologies is a knowledge representation paradigm where the meaning of data is encoded separately from the data itself. The use of semantic technologies such as logicbased systems to support decision making is becoming increasingly popular. However, most automated systems are currently based on syntactic rules. These rules are generally not sophisticated enough to deal with the complexity of decisions required to be made. The incorporation of semantic information allows for increased understanding and sophistication in cyber defence systems. This paper argues that both big data analytics and semantic technologies are necessary to provide counter measures against cyber threats. An overview of the use of semantic technologies and big data technologies in cyber defence is provided, and important areas for future research in the combined domains are discussed.

@inbook{206,
  author = {Tommie Meyer and Louise Leenen},
  title = {Semantic Technologies and Big Data Analytics for Cyber Defence},
  abstract = {The Governments, military forces and other organisations responsible for cybersecurity deal with vast amounts of data that has to be understood in order to lead to intelligent decision making. Due to the vast amounts of information pertinent to cybersecurity, automation is required for processing and decision making, specifically to present advance warning of possible threats. The ability to detect patterns in vast data sets, and being able to understanding the significance of detected patterns are essential in the cyber defence domain. Big data technologies supported by semantic technologies can improve cybersecurity, and thus cyber defence by providing support for the processing and understanding of the huge amounts of information in the cyber environment.

The term big data analytics refers to advanced analytic techniques such as machine learning, predictive analysis, and other intelligent processing techniques applied to large data sets that contain different data types. The purpose is to detect patterns, correlations, trends and other useful information. Semantic technologies is a knowledge representation paradigm where the meaning of data is encoded separately from the data itself. The use of semantic technologies such as logicbased systems to support decision making is becoming increasingly popular. However, most automated systems are currently based on syntactic rules. These rules are generally not sophisticated enough to deal with the complexity of decisions required to be made. The incorporation of semantic information allows for increased understanding and sophistication in cyber defence systems.

This paper argues that both big data analytics and semantic technologies are necessary to provide counter measures against cyber threats. An overview of the use of semantic technologies and big data technologies in cyber defence is provided, and important areas for future research in the combined domains are discussed.},
  year = {2018},
  journal = {Information Retrieval and Management: Concepts, Methodologies, Tools, and Applications},
  pages = {1375-1388},
  publisher = {IGI Global},
  isbn = {9781522551911},
  url = {https://researchspace.csir.co.za/dspace/bitstream/handle/10204/8932/Leenen_2016.pdf?sequence=1},
}

Description Logics (DLs) that support uncertainty are not as well studied as their crisp alternatives, thereby limiting their use in real world domains. The Bayesian DL BEL and its extensions have been introduced to deal with uncertain knowledge without assuming (probabilistic) independence between axioms. In this paper we combine the classical DL ALC with Bayesian Networks. Our new DL includes a solution to the consistency checking problem and changes to the tableaux algorithm that are not a part of BEL. Furthermore, BALC also supports probabilistic assertional information which was not studied for BEL. We present algorithms for four categories of reasoning problems for our logic; two versions of concept satisability (referred to as total concept satis- ability and partial concept satisability respectively), knowledge base consistency, subsumption, and instance checking. We show that all reasoning problems in BALC are in the same complexity class as their classical variants, provided that the size of the Bayesian Network is included in the size of the knowledge base.

@{205,
  author = {Leonard Botha and Tommie Meyer and Rafael Peñaloza},
  title = {The Bayesian Description Logic BALC},
  abstract = {Description Logics (DLs) that support uncertainty are not as well studied as their crisp alternatives, thereby limiting their use in real world domains. The Bayesian DL BEL and its extensions have been introduced to deal with uncertain knowledge without assuming (probabilistic) independence between axioms. In this paper we combine the classical DL ALC with Bayesian Networks. Our new DL includes a solution to the consistency checking problem and changes to the tableaux algorithm that are not a part of BEL. Furthermore, BALC also supports probabilistic assertional information which was not studied for BEL. We present algorithms for four categories of reasoning problems for our logic; two versions of concept satisability (referred to as total concept satis- ability and partial concept satisability respectively), knowledge base consistency, subsumption, and instance checking. We show that all reasoning problems in BALC are in the same complexity class as their classical variants, provided that the size of the Bayesian Network is included in the size of the knowledge base.},
  year = {2018},
  journal = {International Workshop on Description Logics},
  month = {27/10-29/10},
  url = {http://ceur-ws.org/Vol-2211/},
}

In this paper we present what we believe to be the first systematic approach for extending the framework for defeasible entailment first presented by Kraus, Lehmann, and Magidor—the so-called KLM approach. Drawing on the properties for KLM, we first propose a class of basic defeasible entailment relations. We characterise this basic framework in three ways: (i) semantically, (ii) in terms of a class of properties, and (iii) in terms of ranks on statements in a knowlege base. We also provide an algorithm for computing the basic framework. These results are proved through various representation results. We then refine this framework by defining the class of rational defeasible entailment relations. This refined framework is also characterised in thee ways: semantically, in terms of a class of properties, and in terms of ranks on statements. We also provide an algorithm for computing the refined framework. Again, these results are proved through various representation results. We argue that the class of rational defeasible entailment relations—a strengthening of basic defeasible entailment which is itself a strengthening of the original KLM proposal—is worthy of the term rational in the sense that all of them can be viewed as appropriate forms of defeasible entailment. We show that the two well-known forms of defeasible entailment, rational closure and lexicographic closure, fall within our rational defeasible framework. We show that rational closure is the most conservative of the defeasible entailment relations within the framework (with respect to subset inclusion), but that there are forms of defeasible entailment within our framework that are more “adventurous” than lexicographic closure.

@{200,
  author = {Giovanni Casini and Tommie Meyer and Ivan Varzinczak},
  title = {Defeasible Entailment: from Rational Closure to Lexicographic Closure and Beyond},
  abstract = {In this paper we present what we believe to be the first systematic approach for extending the framework for defeasible entailment first presented by Kraus, Lehmann, and Magidor—the so-called KLM approach. Drawing on the properties for KLM, we first propose a class of basic defeasible entailment relations. We characterise this basic framework in three ways: (i) semantically, (ii) in terms of a class of properties, and (iii) in terms of ranks on statements in a knowlege base. We also provide an algorithm for computing the basic framework. These results are proved through various representation results. We then refine this framework by defining the class of rational defeasible entailment relations. This refined framework is also characterised in thee ways: semantically, in terms of a class of properties, and in terms of ranks on statements. We also provide an algorithm for computing the refined framework. Again, these results are proved through various representation results.

We argue that the class of rational defeasible entailment relations—a strengthening of basic defeasible entailment which is itself a strengthening of the original KLM proposal—is worthy of the term rational in the sense that all of them can be viewed as appropriate forms of defeasible entailment. We show that the two well-known forms of defeasible entailment, rational closure and lexicographic closure, fall within our rational defeasible framework. We show that rational closure is the most conservative of the defeasible entailment relations within the framework (with respect to subset inclusion), but that there are forms of defeasible entailment within our framework that are more “adventurous” than lexicographic closure.},
  year = {2018},
  journal = {7th International Workshop on Non-Monotonic Reasoning (NMR 2018)},
  pages = {109-118},
  month = {27/10-29/10},
  url = {http://orbilu.uni.lu/bitstream/10993/37393/1/NMR2018Paper.pdf},
}

We propose a new framework for reasoning about the reputation of multiple agents, based on the partially observable Markov decision process (POMDP). It is general enough for the specification of a variety of stochastic multi-agent system (MAS) domains involving the impact of agents on each other’s reputations. Assuming that an agent must maintain a good enough reputation to survive in the system, a method for an agent to select optimal actions is developed.

@{198,
  author = {Gavin Rens and Tommie Meyer and A. Nayak},
  title = {Maximizing Expected Impact in an Agent Reputation Network},
  abstract = {We propose a new framework for reasoning about the reputation of multiple agents, based on the partially observable Markov decision process (POMDP). It is general enough for the specification of a variety of stochastic multi-agent system (MAS) domains involving the impact of agents on each other’s reputations. Assuming that an agent must maintain a good enough reputation to survive in the system, a method for an agent to select optimal actions is developed.},
  year = {2018},
  journal = {41st German Conference on AI, Berlin, Germany, September 24–28, 2018},
  pages = {99-106},
  month = {24/09-28/09},
  publisher = {Springer},
  isbn = {978-3-030-00110-0},
  url = {https://www.springer.com/us/book/9783030001100},
}

Belief change and non-monotonic reasoning are usually viewed as two sides of the same coin, with results showing that one can formally be defined in terms of the other. In this paper we investigate the integration of the two formalisms by studying belief change for a (preferential) non-monotonic framework. We show that the standard AGM approach to belief change can be transferred to a preferential non-monotonic framework in the sense that change operations can be defined on conditional knowledge bases. We take as a point of departure the results presented by Casini and Meyer (2017), and we develop and extend such results with characterisations based on semantics and entrenchment relations, showing how some of the constructions defined for propositional logic can be lifted to our preferential non-monotonic framework.

@{197,
  author = {Giovanni Casini and F. Eduardo and Tommie Meyer and Ivan Varzinczak},
  title = {A Semantic Perspective on Belief Change in a Preferential Non-Monotonic Framework},
  abstract = {Belief change and non-monotonic reasoning are usually viewed as two sides of the same coin, with results showing that one can formally be defined in terms of the other. In this paper we investigate the integration of the two formalisms by studying belief change for a (preferential) non-monotonic framework. We show that the standard AGM approach to belief change can be transferred to a preferential non-monotonic framework in the sense that change operations can be defined on conditional knowledge bases. We take as a point of departure the results presented by Casini and Meyer (2017), and we develop and extend such results with characterisations based on semantics and entrenchment relations, showing how some of the constructions defined for propositional logic can be lifted to our preferential non-monotonic framework.},
  year = {2018},
  journal = {16th International Conference on Principles of Knowledge Representation and Reasoning},
  pages = {220-229},
  month = {27/10-02/11},
  publisher = {AAAI Press},
  address = {United States of America},
  isbn = {978-1-57735-803-9},
  url = {https://dblp.org/db/conf/kr/kr2018.html},
}

Belief change and non-monotonic reasoning are usually viewed as two sides of the same coin, with results showing that one can formally be defined in terms of the other. In this paper we show that we can also integrate the two formalisms by studying belief change within a (preferential) non-monotonic framework. This integration relies heavily on the identification of the monotonic core of a non-monotonic framework. We consider belief change operators in a non-monotonic propositional setting with a view towards preserving consistency. These results can also be applied to the preservation of coherence—an important notion within the field of logic-based ontologies. We show that the standard AGM approach to belief change can be adapted to a preferential non-monotonic framework, with the definition of expansion, contraction, and revision operators, and corresponding representation results. Surprisingly, preferential AGM belief change, as defined here, can be obtained in terms of classical AGM belief change.

@{167,
  author = {Giovanni Casini and Tommie Meyer},
  title = {Belief Change in a Preferential Non-Monotonic Framework},
  abstract = {Belief change and non-monotonic reasoning are usually viewed as two sides of the same coin, with results showing that one can formally be defined in terms of the other. In this paper we show that we can also integrate the two formalisms by studying belief change within a (preferential) non-monotonic framework. This integration relies heavily on the identification of the monotonic core of a non-monotonic framework. We consider belief change operators in a non-monotonic propositional setting with a view towards preserving consistency. These results can also be applied to the preservation of coherence—an important notion within the field of logic-based ontologies. We show that the standard AGM approach to belief change can be adapted to a preferential non-monotonic framework, with the definition of expansion, contraction, and revision operators, and corresponding representation results. Surprisingly, preferential AGM belief change, as defined here, can be obtained in terms of classical AGM belief change.},
  year = {2017},
  journal = {International Joint Conference on Artificial Intelligence (IJCAI-17)},
  pages = {929-935},
  month = {19/08-25/08},
  isbn = {978-0-9992411-0-3},
}

As the nature of information stored digitally becomes more important and confidential, the security of the systems put in place to protect this information needs to be increased. The human element, however, remains a vulnerability of the system and it is this vulnerability that social engineers attempt to exploit. The Social Engineering Attack Detection Model version 2 (SEADMv2) has been proposed to help people identify malicious social engineering attacks. Prior to this study, the SEADMv2 had not been implemented as a user friendly application or tested with real subjects. This paper describes how the SEADMv2 was implemented as an Android application. This Android application was tested on 20 subjects, to determine whether it reduces the probability of a subject falling victim to a social engineering attack or not. The results indicated that the Android implementation of the SEADMv2 significantly reducedthe number of subjects that fell victim to social engineering attacks. The Android application also significantly reduced the number of subjects that fell victim to malicious social engineering attacks, bidirectional communication social engineering attacks and indirect communication social engineering attacks. The Android application did not have a statistically significant effect on harmless scenarios and unidirectional communication social engineering attacks.

@{166,
  author = {F. Mouton and M. Teixeira and Tommie Meyer},
  title = {Benchmarking a Mobile Implementation of the Social Engineering Prevention Training Tool},
  abstract = {As the nature of information stored digitally becomes more important and confidential, the security of the systems put in place to protect this information needs to be increased. The human element, however, remains a vulnerability of the system and it is this vulnerability that social engineers attempt to exploit. The Social Engineering Attack Detection Model version 2 (SEADMv2) has been proposed to help people identify malicious social engineering attacks. Prior to this study, the SEADMv2 had not been implemented as a user friendly application or tested with real subjects. This paper describes how the SEADMv2 was implemented as an Android application. This Android application was tested on 20 subjects, to determine whether it reduces the probability of a subject falling victim to a social engineering attack or not. The results indicated that the Android implementation of the SEADMv2 significantly reducedthe number of subjects that fell victim to social engineering attacks. The Android application also significantly reduced the number of subjects that fell victim to malicious social engineering attacks, bidirectional communication social engineering attacks and indirect communication social engineering attacks. The Android application did not have a statistically significant effect on harmless scenarios and unidirectional communication social engineering attacks.},
  year = {2017},
  journal = {Information Security for South Africa (ISSA)},
  pages = {106-116},
  month = {16/08-17/08},
  isbn = {978-1-5386-0545-5},
}

Recent extensions of description logics for dealing with different forms of non-monotonic reasoning don’t take us beyond the case of defeasible subsumption. In this paper we enrich the DL EL⊥ with a (constrained version of) a typicality operator •, the intuition of which is to capture the most typical members of a class, providing us with the DL EL•⊥. We argue that EL•⊥ is the smallest step one can take to increase the expressivity beyond the case of defeasible subsumption for DLs, while still retaining all the rationality properties an appropriate notion of defeasible subsumption is required to satisfy, and investigate what an appropriate notion of non-monotonic entailment for EL• ⊥ should look like.

@misc{165,
  author = {Richard Booth and Giovanni Casini and Tommie Meyer and Ivan Varzinczak},
  title = {Extending Typicality for Description Logics},
  abstract = {Recent extensions of description logics for dealing with different forms of non-monotonic reasoning don’t take us beyond the case of defeasible subsumption. In this paper we enrich the DL EL⊥ with a (constrained version of) a typicality operator •, the intuition of which is to capture the most typical members of a class, providing us with the DL EL•⊥. We argue that EL•⊥ is the smallest step one can take to increase the expressivity beyond the case of defeasible subsumption for DLs, while still retaining all the rationality properties an appropriate notion of defeasible subsumption is required to satisfy, and investigate what an appropriate notion of non-monotonic entailment for EL• ⊥ should look like.},
  year = {2017},
  url = {http://orbilu.uni.lu/bitstream/10993/32165/1/TforDL-Technical_report.pdf},
}

Imaging is a form of probabilistic belief change which could be employed for both revision and update. In this paper, we propose a new framework for probabilistic belief change based on imaging, called Expected Distance Imaging (EDI). EDI is sufficiently general to define Bayesian conditioning and other forms of imaging previously defined in the literature. We argue that, and investigate how, EDI can be used for both revision and update. EDI’s definition depends crucially on a weight function whose properties are studied and whose effect on belief change operations is analysed. Finally, four EDI instantiations are proposed, two for revision and two for update, and probabilistic rationality postulates are suggested for their analysis.

@misc{164,
  author = {Gavin Rens and Tommie Meyer},
  title = {Imagining Probabilistic Belief Change as Imaging},
  abstract = {Imaging is a form of probabilistic belief change which could be employed for both revision and update. In this paper, we propose a new framework for probabilistic belief change based on imaging, called Expected Distance Imaging (EDI). EDI is sufficiently general to define Bayesian conditioning and other forms of imaging previously defined in the literature. We argue that, and investigate how, EDI can be used for both revision and update. EDI’s definition depends crucially on a weight function whose properties are studied and whose effect on belief change operations is analysed. Finally, four EDI instantiations are proposed, two for revision and two for update, and probabilistic rationality postulates are suggested for their analysis.},
  year = {2017},
  url = {https://arxiv.org/pdf/1705.01172.pdf},
}

This paper reports on an investigation into the use of ontology technologies to support taxonomic functions. Support for taxonomy is imperative given several recent discussions and publications that voiced concern over the taxonomic impediment within the broader context of the life sciences. Taxonomy is defined as the scientific classification, description and grouping of biological organisms into hierarchies based on sets of shared characteristics, and documenting the principles that enforce such classification. Under taxonomic functions we identified two broad categories: the classification functions concerned with identification and naming of organisms, and secondly classification functions concerned with categorization and revision (i.e. grouping and describing, or revisiting existing groups and descriptions). Ontology technologies within the broad field of artificial intelligence include computational ontologies that are knowledge representation mechanisms using standardized representations that are based on description logics (DLs). This logic base of computational ontologies provides for the computerized capturing and manipulation of knowledge. Furthermore, the set-theoretical basis of computational ontologies ensures particular suitability towards classification, which is considered as a core function of systematics or taxonomy. Using the specific case of Afrotropical bees, this experimental research study represents the taxonomic knowledge base as an ontology, explore the use of available reasoning algorithms to draw the necessary inferences that support taxonomic functions (identification and revision) over the ontology and implement a Web-based application (the WOC). The contributions include the ontology, a reusable and standardized computable knowledge base of the taxonomy of Afrotropical bees, as well as the WOC and the evaluation thereof by experts.

@article{163,
  author = {Aurona Gerber and Nishal Morar and Tommie Meyer and C. Eardley},
  title = {Ontology-based support for taxonomic functions},
  abstract = {This paper reports on an investigation into the use of ontology technologies to support taxonomic functions. Support for taxonomy is imperative given several recent discussions and publications that voiced concern over the taxonomic impediment within the broader context of the life sciences. Taxonomy is defined as the scientific classification, description and grouping of biological organisms into hierarchies based on sets of shared characteristics, and documenting the principles that enforce such classification. Under taxonomic functions we identified two broad categories: the classification functions concerned with identification and naming of organisms, and secondly classification functions concerned with categorization and revision (i.e. grouping and describing, or revisiting existing groups and descriptions).

Ontology technologies within the broad field of artificial intelligence include computational ontologies that are knowledge representation mechanisms using standardized representations that are based on description logics (DLs). This logic base of computational ontologies provides for the computerized capturing and manipulation of knowledge. Furthermore, the set-theoretical basis of computational ontologies ensures particular suitability towards classification, which is considered as a core function of systematics or taxonomy.

Using the specific case of Afrotropical bees, this experimental research study represents the taxonomic knowledge base as an ontology, explore the use of available reasoning algorithms to draw the necessary inferences that support taxonomic functions (identification and revision) over the ontology and implement a Web-based application (the WOC). The contributions include the ontology, a reusable and standardized computable knowledge base of the taxonomy of Afrotropical bees, as well as the WOC and the evaluation thereof by experts.},
  year = {2017},
  journal = {Ecological Informatics},
  volume = {41},
  pages = {11-23},
  publisher = {Elsevier},
  isbn = {1574-9541},
  url = {https://ac.els-cdn.com/S1574954116301959/1-s2.0-S1574954116301959-main.pdf?_tid=487687ca-01b3-11e8-89aa-00000aacb35e&acdnat=1516873196_6a2c94e428089403763ccec46613cf0f},
}

We propose an architecture for agent control, where the agent stores its beliefs and environment models as logical sentences. Given successive observations, the agent’s current state (of beliefs) is maintained by a combination of probability, POMDP and belief change theory. Two existing logics are employed for knowledge representation and reasoning: the stochastic decision logic of Rens et al. (2015) and p-logic of Zhuanget al. (2017) (a restricted version of a logic designedby Fagin et al. (1990)). The proposed architecture assumes two streams of observations: active, which correspond to agent intentions and passive, which is received without the agent’s direct involvement. Stochastic uncertainty, and ignorance due to lack of information are both dealt with in the architecture. Planning, and learning of environment models are assumed present but are not covered in this proposal.

@misc{155,
  author = {Gavin Rens and Tommie Meyer and Deshen Moodley},
  title = {A Stochastic Belief Management Architecture for Agent Control},
  abstract = {We propose an architecture for agent control, where the agent stores its beliefs and environment models as logical sentences. Given successive observations, the agent’s current state (of beliefs) is maintained by a combination of probability, POMDP and belief change theory. Two existing logics are employed for knowledge representation and reasoning: the stochastic decision logic of Rens et al. (2015) and p-logic of Zhuanget al. (2017) (a restricted version of a logic designedby Fagin et al. (1990)). The proposed architecture assumes two streams of observations: active, which correspond to agent intentions and passive, which is received without the agent’s direct involvement. Stochastic uncertainty, and ignorance due to lack of information are both dealt with in the architecture. Planning, and learning of environment models are assumed present but are not covered in this proposal.},
  year = {2017},
  url = {http://pubs.cs.uct.ac.za/archive/00001201/01/AGA_2017_Rens_et_al.pdf},
}

We propose a method for an agent to revise its incomplete probabilistic beliefs when a new piece of propositional information is observed. In this work, an agent’s beliefs are represented by a set of probabilistic formulae – a belief base. The method involves determining a representative set of ‘boundary’ probability distributions consistent with the current belief base, revising each of these probability distributions and then translating the revised information into a new belief base. We use a version of Lewis Imaging as the revision operation. The correctness of the approach is proved. The expressivity of the belief bases under consideration are rather restricted, but has some applications. We also discuss methods of belief base revision employing the notion of optimum entropy, and point out some of the benefits and difficulties in those methods. Both the boundary distribution method and the optimum entropy method are reasonable, yet yield different results.

@misc{131,
  author = {Gavin Rens and Tommie Meyer and Giovanni Casini},
  title = {Revising Incompletely Specified Convex Probabilistic Belief Bases},
  abstract = {We propose a method for an agent to revise its incomplete probabilistic beliefs when a new piece of propositional information is observed. In this work, an agent’s beliefs are represented by a set of probabilistic formulae – a belief base. The method involves determining a representative set of ‘boundary’ probability distributions consistent with the current belief base, revising each of these probability distributions and then translating the revised information into a new belief base. We use a version of Lewis Imaging as the revision operation. The correctness of the approach is proved. The expressivity of the belief bases under consideration are rather restricted, but has some applications. We also discuss methods of belief base revision employing the notion of optimum entropy, and point out some of the benefits and difficulties in those methods. Both the boundary distribution method and the optimum entropy method are reasonable, yet yield different results.},
  year = {2016},
  isbn = {ISSN 0933-6192},
}