Research Publications

2019

Botha L, Meyer T, Peñaloza R. A Bayesian Extension of the Description Logic ALC. European Conference on Logics in Artificial Intelligence. 2019. doi:https://doi.org/10.1007/978-3-030-19570-0 _ 22.

Description logics (DLs) are well-known knowledge representation formalisms focused on the representation of terminological knowledge. A probabilistic extension of a light-weight DL was recently proposed for dealing with certain knowledge occurring in uncertain contexts. In this paper, we continue that line of research by introducing the Bayesian extension BALC of the DL ALC. We present a tableau based procedure for deciding consistency, and adapt it to solve other probabilistic, contextual, and general inferences in this logic. We also show that all these problems remain ExpTime-complete, the same as reasoning in the underlying classical ALC.

@proceedings{237,
  author = {Leonard Botha and Thomas Meyer and Rafael Peñaloza},
  title = {A Bayesian Extension of the Description Logic ALC},
  abstract = {Description logics (DLs) are well-known knowledge representation formalisms focused on the representation of terminological knowledge. A probabilistic extension of a light-weight DL was recently proposed for dealing with certain knowledge occurring in uncertain contexts. In this paper, we continue that line of research by introducing the Bayesian extension BALC of the DL ALC. We present a tableau based procedure for deciding consistency, and adapt it to solve other probabilistic, contextual, and general inferences in this logic. We also show that all these problems remain ExpTime-complete, the same as reasoning in the underlying classical ALC.},
  year = {2019},
  journal = {European Conference on Logics in Artificial Intelligence},
  pages = {339 - 354},
  month = {07/05 - 11/05},
  publisher = {Springer},
  address = {Switzerland},
  isbn = {978-3-030-19569-4},
  url = {https://link.springer.com/chapter/10.1007%2F978-3-030-19570-0_22},
  doi = {https://doi.org/10.1007/978-3-030-19570-0 _ 22},
}
Thirion JWF, Van Heerden CJ, Giwa O, Davel MH. The South African directory enquiries (SADE) name corpus. Language Resources & Evaluation. 2019;54(1). doi:10.1007/s10579-019-09448-6.

We present the design and development of a South African directory enquiries corpus. It contains audio and orthographic transcriptions of a wide range of South African names produced by first-language speakers of four languages, namely Afrikaans, English, isiZulu and Sesotho. Useful as a resource to understand the effect of name language and speaker language on pronunciation, this is the first corpus to also aim to identify the ‘‘intended language’’: an implicit assumption with regard to word origin made by the speaker of the name. We describe the design, collection, annotation, and verification of the corpus. This includes an analysis of the algorithms used to tag the corpus with meta information that may be beneficial to pronunciation modelling tasks.

@article{280,
  author = {Jan Thirion and Charl Van Heerden and Oluwapelumi Giwa and Marelie Davel},
  title = {The South African directory enquiries (SADE) name corpus},
  abstract = {We present the design and development of a South African directory enquiries corpus. It contains audio and orthographic transcriptions of a wide range of South African names produced by first-language speakers of four languages, namely Afrikaans, English, isiZulu and Sesotho. Useful as a resource to understand the effect of name language and speaker language on pronunciation, this is the first corpus to also aim to identify the ‘‘intended language’’: an implicit assumption with regard to word origin made by the speaker of the name. We describe the design, collection, annotation, and verification of the corpus. This includes an analysis of the algorithms used to tag the corpus with meta information that may be beneficial to pronunciation modelling tasks.},
  year = {2019},
  journal = {Language Resources & Evaluation},
  volume = {54},
  pages = {155-184},
  issue = {1},
  publisher = {Springer},
  address = {Cape Town, South Africa},
  doi = {10.1007/s10579-019-09448-6},
}
Theunissen MW, Davel MH, Barnard E. Insights regarding overfitting on noise in deep learning. South African Forum for Artificial Intelligence Research (FAIR). 2019.

The understanding of generalization in machine learning is in a state of flux. This is partly due to the elatively recent revelation that deep learning models are able to completely memorize training data and still perform appropriately on out-of-sample data, thereby contradicting long-held intuitions about generalization. The phenomenon was brought to light and discussed in a seminal paper by Zhang et al. [24]. We expand upon this work by discussing local attributes of neural network training within the context of a relatively simple and generalizable framework. We describe how various types of noise can be compensated for within the proposed framework in order to allow the global deep learning model to generalize in spite of interpolating spurious function descriptors. Empirically, we support our postulates with experiments involving overparameterized multilayer perceptrons and controlled noise in the training data. The main insights are that deep learning models are optimized for training data modularly, with different regions in the function space dedicated to fitting distinct kinds of sample information. Detrimental overfitting is largely prevented by the fact that different regions in the function space are used for prediction based on the similarity between new input data and that which has been optimized for.

@proceedings{284,
  author = {Marthinus Theunissen and Marelie Davel and Etienne Barnard},
  title = {Insights regarding overfitting on noise in deep learning},
  abstract = {The understanding of generalization in machine learning is in a state of flux. This is partly due to the elatively recent revelation that deep learning models are able to completely memorize training data and still perform appropriately on out-of-sample data, thereby contradicting long-held intuitions about generalization. The phenomenon was brought to light and discussed in a seminal paper by Zhang et al. [24]. We expand upon this work by discussing local attributes of neural network training within the context of a relatively simple and generalizable framework. We describe how various types of noise can be compensated for within the proposed framework in order to allow the global deep learning model to generalize in spite of interpolating spurious function descriptors. Empirically, we support our postulates with experiments involving overparameterized multilayer perceptrons and controlled noise in the training data. The main insights are that deep learning models are optimized for training data modularly, with different regions in the function space dedicated to fitting distinct kinds of sample information. Detrimental overfitting is largely prevented by the fact that different regions in the function space are used for prediction based on the similarity between new input data and that which has been optimized for.},
  year = {2019},
  journal = {South African Forum for Artificial Intelligence Research (FAIR)},
  pages = {49-63},
  address = {Cape Town, South Africa},
}
Pretorius AP, Barnard E, Davel MH. ReLU and sigmoidal activation functions. South African Forum for Artificial Intelligence Research (FAIR). 2019.

The generalization capabilities of deep neural networks are not well understood, and in particular, the influence of activation functions on generalization has received little theoretical attention. Phenomena such as vanishing gradients, node saturation and network sparsity have been identified as possible factors when comparing different activation functions [1]. We investigate these factors using fully connected feedforward networks on two standard benchmark problems, and find that the most salient differences between networks with sigmoidal and ReLU activations relate to the way that class-distinctive information is propagated through a network.

@proceedings{279,
  author = {Arnold Pretorius and Etienne Barnard and Marelie Davel},
  title = {ReLU and sigmoidal activation functions},
  abstract = {The generalization capabilities of deep neural networks are not well understood, and in particular, the influence of activation functions on generalization has received little theoretical attention. Phenomena such as vanishing gradients, node saturation and network sparsity have been identified as possible factors when comparing different activation functions [1]. We investigate these factors using fully connected feedforward networks on two standard benchmark problems, and find that the most salient differences between networks with sigmoidal and ReLU activations relate to the way that class-distinctive information is propagated through a network.},
  year = {2019},
  journal = {South African Forum for Artificial Intelligence Research (FAIR)},
  pages = {37-48},
  month = {04/12-07/12},
  publisher = {CEUR Workshop Proceedings},
  address = {Cape Town, South Africa},
}
Lotz S, Beukes JP, Davel MH. Input parameter ranking for neural networks in a space weather regression problem. South African Forum for Artificial Intelligence Research (FAIR). 2019.

Geomagnetic storms are multi-day events characterised by significant perturbations to the magnetic field of the Earth, driven by solar activity. Numerous efforts have been undertaken to utilise in-situ measurements of the solar wind plasma to predict perturbations to the geomagnetic field measured on the ground. Typically, solar wind measurements are used as input parameters to a regression problem tasked with predicting a perturbation index such as the 1-minute cadence symmetric-H (Sym-H) index. We re-visit this problem, with two important twists: (i) An adapted feedforward neural network topology is designed to enable the pairwise analysis of input parameter weights. This enables the ranking of input parameters in terms of importance to output accuracy, without the need to train numerous models. (ii) Geomagnetic storm phase information is incorporated as model inputs and shown to increase performance. This is motivated by the fact that different physical phenomena are at play during different phases of a geomagnetic storm.

@proceedings{283,
  author = {Stefan Lotz and Jacques Beukes and Marelie Davel},
  title = {Input parameter ranking for neural networks in a space weather regression problem},
  abstract = {Geomagnetic storms are multi-day events characterised by significant perturbations to the magnetic field of the Earth, driven by solar activity. Numerous efforts have been undertaken to utilise in-situ measurements of the solar wind plasma to predict perturbations to the geomagnetic field measured on the ground. Typically, solar wind measurements are used as input parameters to a regression problem tasked with predicting a perturbation index such as the 1-minute cadence symmetric-H (Sym-H) index. We re-visit this problem, with two important twists:
(i) An adapted feedforward neural network topology is designed to enable the pairwise analysis of input parameter weights. This enables the ranking of input parameters in terms of importance to output accuracy, without the need to train numerous models. (ii) Geomagnetic storm phase information is incorporated as model inputs and shown to increase performance. This is motivated by the fact that different physical phenomena are at play during different phases of a geomagnetic storm.},
  year = {2019},
  journal = {South African Forum for Artificial Intelligence Research (FAIR)},
  pages = {133-144},
  publisher = {CEUR workshop proceedings},
  address = {Cape Town, South Africa},
}
Krynauw DD, Davel MH, Lotz S. Solar flare prediction with temporal convolutional networks (Work in progress). South African Forum for Artificial Intelligence Research (FAIR). 2019.

Sequences are typically modelled with recurrent architectures, but growing research is finding convolutional architectures to also work well for sequence modelling [1]. We explore the performance of Temporal Convolutional Networks (TCNs) when applied to an important sequence modelling task: solar flare prediction. We take this approach, as our future goal is to apply techniques developed for probing and interpreting general convolutional neural networks (CNNs) to solar flare prediction.

@proceedings{282,
  author = {Dewald Krynauw and Marelie Davel and Stefan Lotz},
  title = {Solar flare prediction with temporal convolutional networks (Work in progress)},
  abstract = {Sequences are typically modelled with recurrent architectures, but growing research is finding convolutional architectures to also work well for sequence modelling [1]. We explore the performance of Temporal Convolutional Networks (TCNs) when applied to an important sequence modelling task: solar flare prediction. We take this approach, as our future goal is to apply techniques developed for probing and interpreting general convolutional neural networks (CNNs) to solar flare prediction.},
  year = {2019},
  journal = {South African Forum for Artificial Intelligence Research (FAIR)},
  pages = {Work in progress},
  publisher = {CEUR workshop proceedings},
  isbn = {1613-0073},
}
Davel MH. Activation gap generators in neural networks. South African Forum for Artificial Intelligence Research. 2019.

No framework exists that can explain and predict the generalisation ability of DNNs in general circumstances. In fact, this question has not been addressed for some of the least complicated of neural network architectures: fully-connected feedforward networks with ReLU activations and a limited number of hidden layers. Building on recent work [2] that demonstrates the ability of individual nodes in a hidden layer to draw class-specific activation distributions apart, we show how a simplified network architecture can be analysed in terms of these activation distributions, and more specifically, the sample distances or activation gaps each node produces. We provide a theoretical perspective on the utility of viewing nodes as activation gap generators, and define the gap conditions that are guaranteed to result in perfect classification of a set of samples. We support these conclusions with empirical results.

@proceedings{230,
  author = {Marelie Davel},
  title = {Activation gap generators in neural networks},
  abstract = {No framework exists that can explain and predict the generalisation ability of DNNs in general circumstances. In fact, this question has not been addressed for some of the least complicated of neural network architectures: fully-connected feedforward networks with ReLU activations and a limited number of hidden layers. Building on recent work [2] that demonstrates the ability of individual nodes in a hidden layer to draw class-specific activation distributions apart, we show how a simplified network architecture can be analysed in terms of these activation distributions, and more specifically, the sample distances or activation gaps each node produces. We provide a theoretical perspective on the utility of viewing nodes as activation gap generators, and define the gap conditions that are guaranteed to result in perfect classification of a set of samples. We support these conclusions with empirical results.},
  year = {2019},
  journal = {South African Forum for Artificial Intelligence Research},
  pages = {64-76},
  month = {04/12-06/12/2019},
  publisher = {CEUR workshop proceedings},
  address = {Cape Town, South Africa},
}
Du Toit T, Berndt J, Britz K, Fischer B. ConceptCloud 2.0: Visualisation and exploration of geolocation-rich semi-structured data sets. ICFCA 2019 Conference and Workshops. 2019. http://ceur-ws.org/Vol-2378/.

ConceptCloud is a flexible interactive tool for exploring, vi- sualising, and analysing semi-structured data sets. It uses a combination of an intuitive tag cloud visualisation with an underlying concept lattice to provide a formal structure for navigation through a data set. Con- ceptCloud 2.0 extends the tool with an integrated map view to exploit the geolocation aspect of data. The tool’s implementation of exploratory search does not require prior knowledge of the structure of the data or compromise on scalability, and provides seamless navigation through the tag cloud and the map viewer.

@misc{227,
  author = {Tiaan Du Toit and Joshua Berndt and Katarina Britz and Bernd Fischer},
  title = {ConceptCloud 2.0: Visualisation and exploration of geolocation-rich semi-structured data sets},
  abstract = {ConceptCloud is a flexible interactive tool for exploring, vi- sualising, and analysing semi-structured data sets. It uses a combination of an intuitive tag cloud visualisation with an underlying concept lattice to provide a formal structure for navigation through a data set. Con- ceptCloud 2.0 extends the tool with an integrated map view to exploit the geolocation aspect of data. The tool’s implementation of exploratory search does not require prior knowledge of the structure of the data or compromise on scalability, and provides seamless navigation through the tag cloud and the map viewer.},
  year = {2019},
  journal = {ICFCA 2019 Conference and Workshops},
  month = {06/2019},
  publisher = {CEUR-WS},
  isbn = {1613-0073},
  url = {http://ceur-ws.org/Vol-2378/},
}
Casini G, Meyer T, Varzinczak I. Simple Conditionals with Constrained Right Weakening. International Joint Conference on Artificial Intelligence. 2019. doi:10.24963/ijcai.2019/226.

In this paper we introduce and investigate a very basic semantics for conditionals that can be used to define a broad class of conditional reasoning systems. We show that it encompasses the most popular kinds of conditional reasoning developed in logic-based KR. It turns out that the semantics we propose is appropriate for a structural analysis of those conditionals that do not satisfy the property of Right Weakening. We show that it can be used for the further development of an analysis of the notion of relevance in conditional reasoning.

@proceedings{226,
  author = {Giovanni Casini and Thomas Meyer and Ivan Varzinczak},
  title = {Simple Conditionals with Constrained Right Weakening},
  abstract = {In this paper we introduce and investigate a very basic semantics for conditionals that can be used to define a broad class of conditional reasoning systems. We show that it encompasses the most popular kinds of conditional reasoning developed in logic-based KR. It turns out that the semantics we propose is appropriate for a structural analysis of those conditionals that do not satisfy the property of Right Weakening. We show that it can be used for the further development of an analysis of the notion of relevance in conditional reasoning.},
  year = {2019},
  journal = {International Joint Conference on Artificial Intelligence},
  pages = {1632-1638},
  month = {10/08-16/08},
  publisher = {International Joint Conferences on Artificial Intelligence},
  isbn = {978-0-9992411-4-1},
  url = {https://www.ijcai.org/Proceedings/2019/0226.pdf},
  doi = {10.24963/ijcai.2019/226},
}
Morris M, Ross T, Meyer T. Defeasible disjunctive datalog. Forum for Artificial Intelligence Research. 2019. http://ceur-ws.org/Vol-2540/FAIR2019_paper_38.pdf.

Datalog is a declarative logic programming language that uses classical logical reasoning as its basic form of reasoning. Defeasible reasoning is a form of non-classical reasoning that is able to deal with exceptions to general assertions in a formal manner. The KLM approach to defeasible reasoning is an axiomatic approach based on the concept of plausible inference. Since Datalog uses classical reasoning, it is currently not able to handle defeasible implications and exceptions. We aim to extend the expressivity of Datalog by incorporating KLM-style defeasible reasoning into classical Datalog. We present a systematic approach to extending the KLM properties and a well-known form of defeasible entailment: Rational Closure. We conclude by exploring Datalog extensions of less conservative forms of defeasible entailment: Relevant and Lexicographic Closure.

@proceedings{225,
  author = {Matthew Morris and Tala Ross and Thomas Meyer},
  title = {Defeasible disjunctive datalog},
  abstract = {Datalog is a declarative logic programming language that uses classical logical reasoning as its basic form of reasoning. Defeasible reasoning is a form of non-classical reasoning that is able to deal with exceptions to general assertions in a formal manner. The KLM approach to defeasible reasoning is an axiomatic approach based on the concept of plausible inference. Since Datalog uses classical reasoning, it is currently not able to handle defeasible implications and exceptions. We aim to extend the expressivity of Datalog by incorporating KLM-style defeasible reasoning into classical Datalog. We present a systematic approach to extending the KLM properties and a well-known form of defeasible entailment: Rational Closure. We conclude by exploring Datalog extensions of less conservative forms of defeasible entailment: Relevant and Lexicographic Closure.},
  year = {2019},
  journal = {Forum for Artificial Intelligence Research},
  pages = {208-219},
  month = {03/12-06/12},
  publisher = {CEUR},
  isbn = {1613-0073},
  url = {http://ceur-ws.org/Vol-2540/FAIR2019_paper_38.pdf},
}
Harrison M, Meyer T. Rational preferential reasoning for datalog. Forum for Artificial Intelligence Research. 2019. http://ceur-ws.org/Vol-2540/FAIR2019_paper_67.pdf.

Datalog is a powerful language that can be used to represent explicit knowledge and compute inferences in knowledge bases. Datalog cannot represent or reason about contradictory rules, though. This is a limitation as contradictions are often present in domains that contain exceptions. In this paper, we extend datalog to represent contradictory and defeasible information. We define an approach to efficiently reason about contradictory information in datalog and show that it satisfies the KLM requirements for a rational consequence relation. Finally, we introduce an implementation of this approach in the form of a defeasible datalog reasoning tool and evaluate the performance of this tool.

@proceedings{224,
  author = {Michael Harrison and Thomas Meyer},
  title = {Rational preferential reasoning for datalog},
  abstract = {Datalog is a powerful language that can be used to represent explicit knowledge and compute inferences in knowledge bases. Datalog cannot represent or reason about contradictory rules, though. This is a limitation as contradictions are often present in domains that contain exceptions. In this paper, we extend datalog to represent contradictory and defeasible information. We define an approach to efficiently reason
about contradictory information in datalog and show that it satisfies the KLM requirements for a rational consequence relation. Finally, we introduce an implementation of this approach in the form of a defeasible datalog reasoning tool and evaluate the performance of this tool.},
  year = {2019},
  journal = {Forum for Artificial Intelligence Research},
  pages = {232-243},
  month = {03/12-06/12},
  publisher = {CEUR},
  isbn = {1613-0073},
  url = {http://ceur-ws.org/Vol-2540/FAIR2019_paper_67.pdf},
}
Chingoma J, Meyer T. Forrester’s paradox using typicality. Forum for Artificial Intelligence Research. 2019. http://ceur-ws.org/Vol-2540/FAIR2019_paper_54.pdf.

Deontic logic is a logic often used to formalise scenarios in the legal domain. Within the legal domain there are many exceptions and conflicting obligations. This motivates the enrichment of deontic logic with a notion of typicality which is based on defeasibility, with defeasibility allowing for reasoning about exceptions. Propositional Typicality Logic (PTL) is a logic that employs typicality. Deontic paradoxes are often used to examine logic systems as they provide undesirable results even if the scenarios seem intuitive. Forrester’s paradox is one of the most famous of these paradoxes. This paper shows that PTL can be used to represent and reason with Forrester’s paradox in such a way as to block undesirable conclusions without sacrificing desirable deontic properties.

@proceedings{223,
  author = {Julian Chingoma and Thomas Meyer},
  title = {Forrester’s paradox using typicality},
  abstract = {Deontic logic is a logic often used to formalise scenarios in the legal domain. Within the legal domain there are many exceptions and conflicting obligations. This motivates the enrichment of deontic logic with a notion of typicality which is based on defeasibility, with defeasibility allowing for reasoning about exceptions. Propositional Typicality Logic (PTL) is a logic that employs typicality. Deontic paradoxes are often used to examine logic systems as they provide undesirable results even if the scenarios seem intuitive. Forrester’s paradox is one of the most famous of these paradoxes. This paper shows that PTL can be used to represent and reason with Forrester’s paradox in such a way as to block undesirable conclusions without sacrificing desirable deontic properties.},
  year = {2019},
  journal = {Forum for Artificial Intelligence Research},
  pages = {220-231},
  month = {03/12-06/12},
  publisher = {CEUR},
  isbn = {1613-0073},
  url = {http://ceur-ws.org/Vol-2540/FAIR2019_paper_54.pdf},
}
Casini G, Harrison M, Meyer T, Swan R. Arbitrary Ranking of Defeasible Subsumption. 32nd International Work- shop on Description Logics. 2019. http://ceur-ws.org/Vol-2373/paper-9.pdf.

In this paper we propose an algorithm that generalises existing procedures for the implementation of defeasible reasoning in the framework of Description Logics (DLs). One of the well-known approaches to defeasible reasoning, the so-called KLM approach, is based on con- structing specific rankings of defeasible information, and using these rankings to determine priorities in case of conflicting information. Here we propose a procedure that allows us to input any possible ranking of the defeasible concept inclusions contained in the knowledge base. We analyse and investigate the forms of defeasible reasoning obtained when conclusions drawn are obtained using these rankings.

@misc{222,
  author = {Giovanni Casini and Michael Harrison and Thomas Meyer and Reid Swan},
  title = {Arbitrary Ranking of Defeasible Subsumption},
  abstract = {In this paper we propose an algorithm that generalises existing procedures for the implementation of defeasible reasoning in the framework of Description Logics (DLs). One of the well-known approaches to defeasible reasoning, the so-called KLM approach, is based on con- structing specific rankings of defeasible information, and using these rankings to determine priorities in case of conflicting information. Here we propose a procedure that allows us to input any possible ranking of the defeasible concept inclusions contained in the knowledge base. We analyse and investigate the forms of defeasible reasoning obtained when conclusions drawn are obtained using these rankings.},
  year = {2019},
  journal = {32nd International Work- shop on Description Logics},
  month = {06/2019},
  url = {http://ceur-ws.org/Vol-2373/paper-9.pdf},
}
Casini G, Straccia U, Meyer T. A polynomial Time Subsumption Algorithm for Nominal Safe ELO⊥ under Rational Closure. Information Sciences. 2019;501. doi:https://doi.org/10.1016/j.ins.2018.09.037.

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 Thomas 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},
}
Leenen L, Meyer T. Artificial Intelligence and Big Data Analytics in Support of Cyber Defense. In: Developments In Information Security And Cybernetic Wars. United States of America: Information Science Reference, IGI Global; 2019. doi:10.4018/978-1-5225-8304-2.ch002.

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 Thomas 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},
}
Booth R, Casini G, Meyer T, Varzinczak I. On rational entailment for Propositional Typicality Logic. Artificial Intelligence . 2019;227. doi:https://doi.org/10.1016/j.artint.2019.103178.

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 Thomas 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},
}
Mbonye V, Price CS. A model to evaluate the quality of Wi-Fi perfomance: Case study at UKZN Westville campus. 2nd International Conference on Advances in Big Data, Computing and Data Communication Systems (icABCD 2019). 2019.

Understanding how satisfied users are with services is very important in the delivery of quality services and in improving them. While studies have investigated perceptions of Wi-Fi among students, there is still a gap in understanding the overall perception of quality of service in terms of the different factors that may affect Wi-Fi service quality. Brady & Cronin Jr’s service quality model proposes that outcome quality, physical environment quality and interaction quality affect service quality. Sub-constructs for the independent variables were generated, and Likert-scale items developed for each sub-construct, based on the literature. 373 questionnaires were administered to University of KwaZulu-Natal (UKZN) Westville campus students. Factor analysis was to confirm the sub-constructs. Multiple regression analysis was used to test the model’s ability to predict Wi-Fi service quality. Of the three independent constructs, the outcome quality mean had the highest value (4.53), and it was similar to how the students rated service quality (4.52). All the constructs were rated at above the neutral score of 4. In the factor analysis, two physical environment quality items were excluded, and one service quality item was categorised with the expertise sub-construct of interaction quality. Using multiple regression analysis, the model showed that the independent constructs predict service quality with an R2 of 59.5%. However, when models for individual most-used locations (the library and lecture venues) were conducted, the R2 improved. The model can be used to understand users’ perceptions of outcome quality, physical environment quality and interaction quality which influence the quality of Wi-Fi performance, and evaluate the Wi-Fi performance quality of different locations.

@proceedings{217,
  author = {V. Mbonye and C. Sue Price},
  title = {A model to evaluate the quality of Wi-Fi perfomance: Case study at UKZN Westville campus},
  abstract = {Understanding how satisfied users are with services is very important in the delivery of quality services and in improving them. While studies have investigated perceptions of Wi-Fi among students, there is still a gap in understanding the overall perception of quality of service in terms of the different factors that may affect Wi-Fi service quality.  Brady & Cronin Jr’s service quality model proposes that outcome quality, physical environment quality and interaction quality affect service quality.  Sub-constructs for the independent variables were generated, and Likert-scale items developed for each sub-construct, based on the literature.  373 questionnaires were administered to University of KwaZulu-Natal (UKZN) Westville campus students.  Factor analysis was to confirm the sub-constructs.  Multiple regression analysis was used to test the model’s ability to predict Wi-Fi service quality.
Of the three independent constructs, the outcome quality mean had the highest value (4.53), and it was similar to how the students rated service quality (4.52).  All the constructs were rated at above the neutral score of 4.  In the factor analysis, two physical environment quality items were excluded, and one service quality item was categorised with the expertise sub-construct of interaction quality.  Using multiple regression analysis, the model showed that the independent constructs predict service quality with an R2 of 59.5%.  However, when models for individual most-used locations (the library and lecture venues) were conducted, the R2 improved.  The model can be used to understand users’ perceptions of outcome quality, physical environment quality and interaction quality which influence the quality of Wi-Fi performance, and evaluate the Wi-Fi performance quality of different locations.},
  year = {2019},
  journal = {2nd International Conference on Advances in Big Data, Computing and Data Communication Systems (icABCD 2019)},
  pages = {291-297},
  month = {05/08 - 06/08},
  publisher = {IEEE},
  address = {Danvers MA},
  isbn = {978-1-5386-9235-6},
}
Nudelman Z, Moodley D, Berman S. Using Bayesian Networks and Machine Learning to Predict Computer Science Success. Annual Conference of the Southern African Computer Lecturers' Association. 2019. https://link.springer.com/chapter/10.1007/978-3-030-05813-5_14.

Bayesian Networks and Machine Learning techniques were evaluated and compared for predicting academic performance of Computer Science students at the University of Cape Town. Bayesian Networks performed similarly to other classification models. The causal links inherent in Bayesian Networks allow for understanding of the contributing factors for academic success in this field. The most effective indicators of success in first-year ‘core’ courses in Computer Science included the student’s scores for Mathematics and Physics as well as their aptitude for learning and their work ethos. It was found that unsuccessful students could be identified with ≈ 91% accuracy. This could help to increase throughput as well as student wellbeing at university.

@proceedings{216,
  author = {Z. Nudelman and Deshen Moodley and S. Berman},
  title = {Using Bayesian Networks and Machine Learning to Predict Computer Science Success},
  abstract = {Bayesian Networks and Machine Learning techniques were evaluated and compared for predicting academic performance of Computer Science students at the University of Cape Town. Bayesian Networks performed similarly to other classification models. The causal links inherent in Bayesian Networks allow for understanding of the contributing factors for academic success in this field. The most effective indicators of success in first-year ‘core’ courses in Computer Science included the student’s scores for Mathematics and Physics as well as their aptitude for learning and their work ethos. It was found that unsuccessful students could be identified with   ≈ 91% accuracy. This could help to increase throughput as well as student wellbeing at university.},
  year = {2019},
  journal = {Annual Conference of the Southern African Computer Lecturers' Association},
  pages = {207-222},
  month = {18/06/2018 - 20/06/2018},
  publisher = {Springer},
  isbn = {978-3-030-05813-5},
  url = {https://link.springer.com/chapter/10.1007/978-3-030-05813-5_14},
}
name T. Test. In: Test; 2019.

Testing

@inbook{239,
  author = {Test name},
  title = {Test},
  abstract = {Testing},
  year = {2019},
  publisher = {Test},
}
Daykin JW, Groult R, Guesnet Y, et al. Efficient pattern matching in degenerate strings with the Burrows–Wheeler transform. Information Processing Letters. 2019;147. doi:https://doi.org/10.1016/j.ipl.2019.03.003.

A degenerate or indeterminate string on an alphabet SIGMA is a sequence of non-empty subsets of SIGMA . Given a degenerate string t of length n and its Burrows–Wheeler transform we present a new method for searching for a degenerate pattern of length m in t running in O ( mn ) time on a constant size alphabet SIGMA . Furthermore, it is a hybrid pattern matching technique that works on both regular and degenerate strings. A degenerate string is said to be conservative if its number of non-solid letters is upper-bounded by a fixed positive constant q; in this case we show that the search time complexity is O ( qm^2 ) for counting the number of occurrences and O ( qm^2 + occ ) for reporting the found occurrences where occ is the number of occurrences of the pattern in t. Experimental results show that our method performs well in practice.

@article{264,
  author = {J.W. Daykin and R. Groult and Y. Guesnet and T. Lecroq and A. Lefebvre and M. Leonard and L. Mouchard and E. Prieur-Gaston and Bruce Watson},
  title = {Efficient pattern matching in degenerate strings with the Burrows–Wheeler transform},
  abstract = {A degenerate or indeterminate string on an alphabet SIGMA is a sequence of non-empty subsets of SIGMA . Given a degenerate string t of length n and its Burrows–Wheeler transform we present a new method for searching for a degenerate pattern of length m in t running in O ( mn ) time on a constant size alphabet SIGMA . Furthermore, it is a hybrid pattern matching technique that works on both regular and degenerate strings. A degenerate string is said to be conservative if its number of non-solid letters is upper-bounded by a fixed positive constant q; in this case we show that the search time complexity is O ( qm^2 ) for counting the number of occurrences and O ( qm^2 + occ ) for reporting the found occurrences where occ is the number of occurrences of the pattern in t. Experimental results show that our method performs well in practice.},
  year = {2019},
  journal = {Information Processing Letters},
  volume = {147},
  pages = {82 - 87},
  publisher = {Elsevier},
  doi = {https://doi.org/10.1016/j.ipl.2019.03.003},
}
blah. In: Blah. B;ah; 2019.

Blah

@inbook{228,
  author = {Blah},
  title = {blah},
  abstract = {Blah},
  year = {2019},
  journal = {Blah},
  publisher = {B;ah},
}

2018

van der Merwe A, Gerber A. Guidelines for using Bloom’s Taxonomy Table as Alignment Tool between Goals and Assessment. SACLA. 2018.

In academia lecturers are often appointed based on their research profile and not their teaching and learning (T&L) experience. Although universities do emphasize T&L, it might often not even be mentioned during interviews. In the field of education lecturers are more aware of using tools such as Bloom’s Taxonomy during their T&L activities. However, in the field of information systems limited academic papers are available on how lecturers can align their goals with the assessment in their courses. In this paper Bloom’s Taxonomy Table was used to evaluate the alignment of goals of the case and the assessment done on a fourth-year level subject offered in the information systems field. The purpose of the paper was firstly to reflect on the practice of using Bloom’s Taxonomy Table as an evaluation tool and then secondly to provide a set of guidelines for lecturers who want to use Bloom’s Taxonomy Table in alignment studies.

@proceedings{260,
  author = {Alta van der Merwe and Aurona Gerber},
  title = {Guidelines for using Bloom’s Taxonomy Table as Alignment Tool between Goals and Assessment},
  abstract = {In academia lecturers are often appointed based on their research profile and not their teaching and learning (T&L) experience. Although universities do emphasize T&L, it might often not even be mentioned during interviews. In the field of education lecturers are more aware of using tools such as Bloom’s Taxonomy during their T&L activities. However, in the field of information systems limited academic papers are available on how lecturers can align their goals with the assessment in their courses. In this paper Bloom’s Taxonomy Table was used to evaluate the alignment of goals of the case and the assessment done on a fourth-year level subject offered in the information systems field. The purpose of the paper was firstly to reflect on the practice of using Bloom’s Taxonomy Table as an evaluation tool and then secondly to provide a set of guidelines for lecturers who want to use Bloom’s Taxonomy Table in alignment studies.},
  year = {2018},
  journal = {SACLA},
  pages = {278 - 290},
  month = {18/06 - 20/06},
  publisher = {Springer},
  isbn = {978-0-720-80192-8},
}
Thomas A, Gerber A, van der Merwe A. Ontology-Based Spatial Pattern Recognition in Diagrams. Artificial Intelligence Applications and Innovations. 2018. https://www.springer.com/us/book/9783319920061.

Diagrams are widely used in our day to day communication. A knowledge of the spatial patterns used in diagrams is essential to read and understand them. In the context of diagrams, spatial patterns mean accepted spatial arrangements of graphical and textual elements used to represent diagram-specific concepts. In order to assist with the automated understanding of diagrams by computer applications, this paper presents an ontology-based approach to recognise diagram-specific concepts from the spatial patterns in diagrams. Specifically, relevant spatial patterns of diagrams are encoded in an ontology, and the automated instance classification feature of the ontology reasoners is utilised to map spatial patterns to diagram-specific concepts depicted in a diagram. A prototype of this approach to support automated recognition of UML and domain concepts from class diagrams and its performance are also discussed in this paper. This paper concludes with a reflection of the strengths and limitations of the proposed approach.

@proceedings{257,
  author = {Anitta Thomas and Aurona Gerber and Alta van der Merwe},
  title = {Ontology-Based Spatial Pattern Recognition in Diagrams},
  abstract = {Diagrams are widely used in our day to day communication. A knowledge of the spatial patterns used in diagrams is essential to read and understand them. In the context of diagrams, spatial patterns mean accepted spatial arrangements of graphical and textual elements used to represent diagram-specific concepts. In order to assist with the automated understanding of diagrams by computer applications, this paper presents an ontology-based approach to recognise diagram-specific concepts from the spatial patterns in diagrams. Specifically, relevant spatial patterns of diagrams are encoded in an ontology, and the automated instance classification feature of the ontology reasoners is utilised to map spatial patterns to diagram-specific concepts depicted in a diagram. A prototype of this approach to support automated recognition of UML and domain concepts from class diagrams and its performance are also discussed in this paper. This paper concludes with a reflection of the strengths and limitations of the proposed approach.},
  year = {2018},
  journal = {Artificial Intelligence Applications and Innovations},
  pages = {61 -72},
  month = {25/05 - 27/05},
  publisher = {Springer},
  isbn = {978-3-319-92007-8},
  url = {https://www.springer.com/us/book/9783319920061},
}
Gerber A. Computational Ontologies as Classification Artifacts in IS Research. AMCIS. 2018. https://aisel.aisnet.org/amcis2018/Semantics/Presentations/5/.

Based on previous work on classification in IS research, this paper reports on an experimental investigation into the use of computational ontologies as classification artifacts, given the classification approaches identified in information systems (IS) research. The set-theoretical basis of computational ontologies ensures particular suitability for classification functions, and classification was identified as an accepted approach to develop contributions to IS research. The main contribution of the paper is a set of guidelines that IS researchers could use when adopting a classification approach and constructing an ontology as the resulting classification artifact. The guidelines were extracted by mapping an ontology construction approach to the classification approaches of IS research. Ontology construction approaches have been developed in response to the significant adoption of computational ontologies in the broad field of computing and IS since the acceptance of the W3C standards for ontology languages. These W3C standards also resulted in the development of tools such as ontology editors and reasoners. The advantages of using computational ontologies as classification artifacts thus include standardized representation, as well as the availability of associated technologies such as reasoners that could, for instance, ensure that implicit assumptions are made explicit and that the ontology is consistent and satisfiable. The research results from this experimental investigation extend the current work on classification in IS research.

@proceedings{256,
  author = {Aurona Gerber},
  title = {Computational Ontologies as Classification Artifacts in IS Research},
  abstract = {Based on previous work on classification in IS research, this paper reports on an experimental investigation into the use of computational ontologies as classification artifacts, given the classification approaches identified in information systems (IS) research. The set-theoretical basis of computational ontologies ensures particular suitability for classification functions, and classification was identified as an accepted approach to develop contributions to IS research. The main contribution of the paper is a set of guidelines that IS researchers could use when adopting a classification approach and constructing an ontology as the resulting classification artifact. The guidelines were extracted by mapping an ontology construction approach to the classification approaches of IS research. Ontology construction approaches have been developed in response to the significant adoption of computational ontologies in the broad field of computing and IS since the acceptance of the W3C standards for ontology languages. These W3C standards also resulted in the development of tools such as ontology editors and reasoners. The advantages of using computational ontologies as classification artifacts thus include standardized representation, as well as the availability of associated technologies such as reasoners that could, for instance, ensure that implicit assumptions are made explicit and that the ontology is consistent and satisfiable. The research results from this experimental investigation extend the current work on classification in IS research.},
  year = {2018},
  journal = {AMCIS},
  month = {16/09 - 18/09},
  isbn = {978-0-9966831-6-6},
  url = {https://aisel.aisnet.org/amcis2018/Semantics/Presentations/5/},
}
Moodley D, Pillay A, Seebregts C. Establishing a Health Informatics Research Laboratory in South Africa . Digital Re-imagination Colloquium 2018. 2018. http://uir.unisa.ac.za/bitstream/handle/10500/25615/Digital%20Skills%20Proceedings%202018.pdf?sequence=1&isAllowed=y.

Aim/Purpose The aim of this project was to explore models for stimulating health informatics innovation and capacity development in South Africa. Background There is generally a critical lack of health informatics innovation and capacity in South Africa and sub-Saharan Africa. This is despite the wide anticipation that digital health systems will play a fundamental role in strengthening health systems and improving service delivery Methodology We established a program over four years to train Masters and Doctoral students and conducted research projects across a wide range of biomedical and health informatics technologies at a leading South African university. We also developed a Health Architecture Laboratory Innovation and Development Ecosystem (HeAL-IDE) designed to be a long-lasting and potentially reproducible output of the project. Contribution We were able to demonstrate a successful model for building innovation and capacity in a sustainable way. Key outputs included: (i)a successful partnership model; (ii) a sustainable HeAL-IDE; (iii) research papers; (iv) a world-class software product and several demonstrators; and (iv) highly trained staff. Findings Our main findings are that: (i) it is possible to create a local ecosystem for innovation and capacity building that creates value for the partners (a university and a private non-profit company); (ii) the ecosystem is able to create valuable outputs that would be much less likely to have been developed singly by each partner, and; (iii) the ecosystem could serve as a powerful model for adoption in other settings. Recommendations for Practitioners Non-profit companies and non-governmental organizations implementing health information systems in South Africa and other low resource settings have an opportunity to partner with local universities for purposes of internal capacity development and assisting with the research, reflection and innovation aspects of their projects and programmes. Recommendation for Researchers Applied health informatics researchers working in low resource settings could productively partner with local implementing organizations in order to gain a better understanding of the challenges and requirements at field sites and to accelerate the testing and deployment of health information technology solutions. Impact on Society This research demonstrates a model that can deliver valuable software products for public health. Future Research It would be useful to implement the model in other settings and research whether the model is more generally useful

@proceedings{252,
  author = {Deshen Moodley and Anban Pillay and Chris Seebregts},
  title = {Establishing a Health Informatics Research Laboratory in South Africa},
  abstract = {Aim/Purpose 
The aim of this project was to explore models for stimulating health
informatics innovation and capacity development in South Africa.
Background 
There is generally a critical lack of health informatics innovation and capacity in South Africa and sub-Saharan Africa. This is despite the wide anticipation that digital health systems will play a fundamental role in strengthening health systems and improving service delivery
Methodology 
We established a program over four years to train Masters and Doctoral students and conducted research projects across a wide range of biomedical and health informatics technologies at a leading South African university. We also developed a Health Architecture Laboratory Innovation and Development Ecosystem (HeAL-IDE) designed to be a long-lasting and potentially reproducible output of the project.
Contribution 
We were able to demonstrate a successful model for building innovation and capacity in a sustainable way. Key outputs included: (i)a successful partnership model; (ii) a sustainable HeAL-IDE; (iii) research papers; (iv) a world-class software product and several
demonstrators; and (iv) highly trained staff.
Findings 
Our main findings are that: (i) it is possible to create a local ecosystem for innovation and capacity building that creates value for the partners (a university and a private non-profit company); (ii) the ecosystem is able to create valuable outputs that would be much less likely to have been developed singly by each partner, and; (iii) the ecosystem could serve as a powerful model for adoption in other settings.
Recommendations for Practitioners
Non-profit companies and non-governmental organizations implementing health information systems in South Africa and other low resource settings have an opportunity to partner with local universities for purposes of internal capacity development and assisting with the research, reflection and innovation aspects of their projects and programmes.
Recommendation for Researchers
Applied health informatics researchers working in low resource settings could productively partner with local implementing organizations in order to gain a better understanding of the challenges and requirements at field sites and to accelerate the testing and deployment of health information technology solutions.
Impact on Society 
This research demonstrates a model that can deliver valuable software products for public health.
Future Research 
It would be useful to implement the model in other settings and research whether the model is more generally useful},
  year = {2018},
  journal = {Digital Re-imagination Colloquium 2018},
  pages = {16 - 24},
  month = {13/03 - 15/03},
  publisher = {NEMISA},
  isbn = {978-0-6399275-0-3},
  url = {http://uir.unisa.ac.za/bitstream/handle/10500/25615/Digital%20Skills%20Proceedings%202018.pdf?sequence=1&isAllowed=y},
}
  • CSIR
  • DSI
  • Covid-19