Research Publications

Information security is a fast-growing discipline, and therefore the effectiveness of security measures to protect sensitive information needs to be increased. Since people are generally susceptible to manipulation, humans often prove to be the weak link in the security chain. A social engineering attack targets this weakness by using various manipulation techniques to elicit individuals to perform sensitive requests. The field of social engineering is still in its infancy as far as formal definitions, attack frameworks, examples of attacks and detection models are concerned. This paper therefore proposes a revised version of the Social Engineering Attack Detection Model. The previous model was designed with a call centre environment in mind and is only able to cater for social engineering attacks that use bidirectional communication. Previous research discovered that social engineering attacks can be classified into three different categories, namely attacks that utilise bidirectional communication, unidirectional communication or indirect communication. The proposed (and revised) Social Engineering Attack Detection Model addresses this problem by extending the model to cater for social engineering attacks that use bidirectional communication, unidirectional communication or indirect communication. The revised Social Engineering Attack Detection Model is further verified using published generalised social engineering attack examples from each of the three categories mentioned.

@{568,
  author = {Francois Mouton and Louise Leenen and Hein Venter},
  title = {Social Engineering Attack Detection Model: SEADMv2},
  abstract = {Information security is a fast-growing discipline, and therefore the effectiveness of security measures to protect sensitive information needs to be increased. Since people are generally susceptible to manipulation, humans often prove to be the weak link in the security chain. A social engineering attack targets this weakness by using various manipulation techniques to elicit individuals to perform sensitive requests. The field of social engineering is still in its infancy as far as formal definitions, attack frameworks, examples of attacks and detection models are concerned. This paper therefore proposes a revised version of the Social Engineering Attack Detection Model. The previous model was designed with a call centre environment in mind and is only able to cater for social engineering attacks that use bidirectional communication. Previous research discovered that social engineering attacks can be classified into three different categories, namely attacks that utilise bidirectional communication, unidirectional communication or indirect communication. The proposed (and revised) Social Engineering Attack Detection Model addresses this problem by extending the model to cater for social engineering attacks that use bidirectional communication, unidirectional communication or indirect communication. The revised Social Engineering Attack Detection Model is further verified using published generalised social engineering attack examples from each of the three categories mentioned.},
  year = {2015},
  journal = {2015 International Conference on Cyberworlds (CW)},
  pages = {216-223},
  month = {2015},
  publisher = {IEEE},
  address = {Visby, Sweden},
  doi = {10.1109/CW.2015.52},
}

"Naturalised realism" is presented as a version of realism which is more compatible with the history of science than convergent or explanationist forms of realism. The account is unpacked according to four theses : 1) Whether realism is warranted with regards to a particular theory depends on the kind and quality of evidence available for that theory; 2) Reference is about causal interaction with the world; 3) Most of science happens somewhere in between instrumentalism and scientific realism on a continuum of stances towards the status of theories; 4) The degree to which realism is warranted has something to do with the degree to which theories successfully refer, rather than with the truth of theories.

@article{417,
  author = {Emma Ruttkamp-Bloem},
  title = {Repositioning realism},
  abstract = {"Naturalised realism" is presented as a version of realism which is more compatible with the history of science than convergent or explanationist forms of realism. The account is unpacked according to four theses : 1) Whether realism is warranted with regards to a particular theory depends on the kind and quality of evidence available for that theory; 2) Reference is about causal interaction with the world; 3) Most of science happens somewhere in between instrumentalism and scientific realism on a continuum of stances towards the status of theories; 4) The degree to which realism is warranted has something to do with the degree to which theories successfully refer, rather than with the truth of theories.},
  year = {2015},
  journal = {Philosphia Scientiæ},
  volume = {19},
  pages = {85-98},
  issue = {1},
  publisher = {Université Nancy 2},
  isbn = {1281-2463},
  doi = {10.4000/philosophiascientiae.1042},
}

Propositional Typicality Logic (PTL) is a recently proposed logic, obtained by enriching classical propositional logic with a typicality operator. 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. We investigate different (semantic) versions of entailment for PTL, based on the notion of Rational Closure as defined by Lehmann and Magidor for KLM-style conditionals, and constructed using minimality. 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 define two primary forms of entailment for PTL and discuss their advantages and disadvantages

@{363,
  author = {Richard Booth and Giovanni Casini and Tommie Meyer and Ivan Varzinczak},
  title = {On the Entailment Problem for a Logic of Typicality},
  abstract = {Propositional Typicality Logic (PTL) is a recently proposed logic, obtained by enriching classical propositional logic with a typicality operator. 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. We investigate different (semantic) versions of entailment for PTL, based on the notion of Rational Closure as defined by Lehmann and Magidor for KLM-style conditionals, and constructed using minimality. 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 define two primary forms of entailment for PTL and discuss their advantages and disadvantages},
  year = {2015},
  journal = {Twenty-Fourth International Joint Conference on Artificial Intelligence (IJCAI)},
  pages = {2805-2811},
  month = {25/07 - 31/07},
  publisher = {AAAI Press},
  url = {https://www.semanticscholar.org/paper/On-the-Entailment-Problem-for-a-Logic-of-Typicality-Booth-Casini/47bb88f18d591df1355c7ad53593a1f1b46522f0},
}

One way for an agent to deal with uncertainty about its beliefs is to maintain a probability distribution over the worlds it believes are possible. A belief change operation may recommend some previously believed worlds to become impossible and some previously disbelieved worlds to become possible. This work investigates how to redistribute probabilities due to worlds being added to and removed from an agent’s belief-state. Two related approaches are proposed and analyzed.

@{362,
  author = {Gavin Rens and Tommie Meyer},
  title = {A New Approach to Probabilistic Belief Change},
  abstract = {One way for an agent to deal with uncertainty about its beliefs is to maintain a probability distribution over the worlds it believes are possible. A belief change operation may recommend some previously believed worlds to become impossible and some previously disbelieved worlds to become possible. This work investigates how to redistribute probabilities due to worlds being added to and removed from an agent’s belief-state. Two related approaches are proposed and analyzed.},
  year = {2015},
  journal = {International Florida AI Research Society Conference (FLAIRS)},
  pages = {582-587},
  month = {18/05 - 20/05},
  publisher = {AAAI Press},
  url = {https://www.researchgate.net/publication/277004602_A_New_Approach_to_Probabilistic_Belief_Change},
}

This article reports on the investigation of the acoustic characteristics of the Afrikaans voiceless alveolar fricative /s/[1]. As yet, a palatal [ʃ] for /s/ has been reported only in a limited case, namely where /s/ is followed by palatal /j/, for example in the phrase is jy (‘are you’), pronounced as [ə-ʃəi]. This seems to be an instance of regressive coarticulation, resulting in coalescence of basic /s/ and /j/. The present study revealed that, especially in the pronunciation of young, white Afrikaans-speakers, /s/ is also palatalised progressively when preceded by /r/ in the coda cluster /rs/, and, to a lesser extent, also in other contexts where /r/ is involved, for example across syllable and word boundaries. Only a slight presence of palatalisation was detected in the production of /s/ in the speech of the white, older speakers of the present study. This finding might be indicative of a definite change in the Afrikaans consonant system. A post hoc reflection is offered here on the possible presence of /s/-fronting, especially in the speech of the younger females. Such pronunciation could very well be a prestige marker for affluent speakers of Afrikaans.

@article{293,
  author = {Daan Wissing and Wikus Pienaar and Daniel Van Niekerk},
  title = {Palatalisation of /s/ in Afrikaans},
  abstract = {This article reports on the investigation of the acoustic characteristics of the Afrikaans voiceless alveolar fricative /s/[1]. As yet, a palatal [ʃ] for /s/ has been reported only in a limited case, namely where /s/ is followed by palatal /j/, for example in the phrase is jy (‘are you’), pronounced as [ə-ʃəi]. This seems to be an instance of regressive coarticulation, resulting in coalescence of basic /s/ and /j/. The present study revealed that, especially in the pronunciation of young, white Afrikaans-speakers, /s/ is also palatalised progressively when preceded by /r/ in the coda cluster /rs/, and, to a lesser extent, also in other contexts where /r/ is involved, for example across syllable and word boundaries. Only a slight presence of palatalisation was detected in the production of /s/ in the speech of the white, older speakers of the present study. This finding might be indicative of a definite change in the Afrikaans consonant system. A post hoc reflection is offered here on the possible presence of /s/-fronting, especially in the speech of the younger females. Such pronunciation could very well be a prestige marker for affluent speakers of Afrikaans.},
  year = {2015},
  journal = {Stellenbosch Papers in Linguistics Plus},
  volume = {48},
  pages = {137-158},
  publisher = {Stellenbosch University},
  doi = {10.5842/48-0-688},
}

The accuracy of automatic speech recognition (ASR) systems typically degrades when encountering code-switched speech. Some of this degradation is due to the unexpected pronunciation effects introduced when languages are mixed. Embedded (foreign) phonemes typically show more variation than phonemes from the matrix language: either approximating the embedded language pronunciation fairly closely, or realised as any of a set of phonemic counterparts from the matrix language. In this paper we describe a technique for predicting the phoneme substitutions that are expected to occur during code-switching, using non-acoustic features only. As case study we consider Sepedi/English code switching and analyse the different realisations of the English schwa. A code-switched speech corpus is used as input and vowel substitutions identified by auto-tagging this corpus based on acoustic characteristics. We first evaluate the accuracy of our auto-tagging process, before determining the predictability of our auto-tagged corpus, using non-acoustic features.

@{292,
  author = {Thipe Modipa and Marelie Davel},
  title = {Predicting vowel substitution in code-switched speech},
  abstract = {The accuracy of automatic speech recognition (ASR) systems typically degrades when encountering code-switched speech. Some of this degradation is due to the unexpected pronunciation effects introduced when languages are mixed. Embedded (foreign) phonemes typically show more variation than phonemes from the matrix language: either approximating the embedded language pronunciation fairly closely, or realised as any of a set of phonemic counterparts from the matrix language. In this paper we describe a technique for predicting the phoneme substitutions that are expected to occur during code-switching, using non-acoustic features only. As case study we consider Sepedi/English code switching and analyse the different realisations of the English schwa. A code-switched speech corpus is used as input and vowel substitutions identified by auto-tagging this corpus based on acoustic characteristics. We first evaluate the accuracy of our auto-tagging process, before determining the predictability of our auto-tagged corpus, using non-acoustic features.},
  year = {2015},
  journal = {Pattern Recognition Association of South Africa (PRASA)},
  pages = {154-159},
  month = {26/11-27/11},
  address = {Port Elizabeth, South Africa},
  isbn = {978-1-4673-7450-7, 978-1-4673-7449-1},
  doi = {10.1109/RoboMech.2015.7359515},
}

Automatic speech recognition (ASR) technology has matured over the past few decades and has made significant impacts in a variety of fields, from assistive technologies to commercial products. However, ASR system development is a resource intensive activity and requires language resources in the form of text annotated audio recordings and pronunciation dictionaries. Unfortunately, many languages found in the developing world fall into the resource-scarce category and due to this resource scarcity the deployment of ASR systems in the developing world is severely inhibited. One approach to assist with resource-scarce ASR system development, is to select 'useful' training samples which could reduce the resources needed to collect new corpora. In this work, we propose a new data selection framework which can be used to design a speech recognition corpus. We show for limited data sets, independent of language and bandwidth, the most effective strategy for data selection is frequency-matched selection and that the widely-used maximum entropy methods generally produced the least promising results. In our model, the frequency-matched selection method corresponds to a logarithmic relationship between accuracy and corpus size; we also investigated other model relationships, and found that a hyperbolic relationship (as suggested from simple asymptotic arguments in learning theory) may lead to somewhat better performance under certain conditions.

@article{291,
  author = {Neil Kleynhans and Etienne Barnard},
  title = {Efficient data selection for ASR},
  abstract = {Automatic speech recognition (ASR) technology has matured over the past few decades and has made significant impacts in a variety of fields, from assistive technologies to commercial products. However, ASR system development is a resource intensive activity and requires language resources in the form of text annotated audio recordings and pronunciation dictionaries. Unfortunately, many languages found in the developing world fall into the resource-scarce category and due to this resource scarcity the deployment of ASR systems in the developing world is severely inhibited. One approach to assist with resource-scarce ASR system development, is to select 'useful' training samples which could reduce the resources needed to collect new corpora. In this work, we propose a new data selection framework which can be used to design a speech recognition corpus. We show for limited data sets, independent of language and bandwidth, the most effective strategy for data selection is frequency-matched selection and that the widely-used maximum entropy methods generally produced the least promising results. In our model, the frequency-matched selection method corresponds to a logarithmic relationship between accuracy and corpus size; we also investigated other model relationships, and found that a hyperbolic relationship (as suggested from simple asymptotic arguments in learning theory) may lead to somewhat better performance under certain conditions.},
  year = {2015},
  journal = {Language Resources and Evaluation},
  volume = {49},
  pages = {327-353},
  issue = {2},
  publisher = {Springer Science+Business Media},
  address = {Dordrecht},
  doi = {10.1007/s10579-014-9285-0},
}

Large amounts of untranscribed audio data are generated every day. These audio resources can be used to develop robust acoustic models that can be used in a variety of speech-based systems. Manually transcribing this data is resource intensive and requires funding, time and expertise. Lightly-supervised training techniques, however, provide a means to rapidly transcribe audio, thus reducing the initial resource investment to begin the modelling process. Our findings suggest that the lightly-supervised training technique works well for English but when moving to an agglutinative language, such as isiZulu, the process fails to achieve the performance seen for English. Additionally, phone-based performances are significantly worse when compared to an approach using word-based language models. These results indicate a strong dependence on large or well-matched text resources for lightly-supervised training techniques.

@{290,
  author = {Neil Kleynhans and Febe De Wet and Etienne Barnard},
  title = {Unsupervised acoustic model training: comparing South African English and isiZulu},
  abstract = {Large amounts of untranscribed audio data are generated every day. These audio resources can be used to develop robust acoustic models that can be used in a variety of speech-based systems. Manually transcribing this data is resource intensive and requires funding, time and expertise. Lightly-supervised training techniques, however, provide a means to rapidly transcribe audio, thus reducing the initial resource investment to begin the modelling process. Our findings suggest that the lightly-supervised training technique works well for English but when moving to an agglutinative language, such as isiZulu, the process fails to achieve the performance seen for English. Additionally, phone-based performances are significantly worse when compared to an approach using word-based language models. These results indicate a strong dependence on large or well-matched text resources for lightly-supervised training techniques.},
  year = {2015},
  journal = {Pattern Recognition Association of South Africa (PRASA)},
  pages = {136-141},
  address = {Port Elizabeth, South Africa},
  isbn = {978-1-4673-7450-7, 978-1-4673-7449-1},
  doi = {10.1109/RoboMech.2015.7359512},
}

Text-based language identification (T-LID) of isolated words has been shown to be useful for various speech processing tasks, including pronunciation modelling and data categorisation. When the words to be categorised are proper names, the task becomes more difficult: not only do proper names often have idiosyncratic spellings, they are also often considered to be multilingual. We, therefore, investigate how an existing T-LID technique can be adapted to perform multilingual word classification. That is, given a proper name, which may be either mono- or multilingual, we aim to determine how accurately we can predict how many possible source languages the word has, and what they are. Using a Joint Sequence Model-based approach to T-LID and the SADE corpus - a newly developed proper names corpus of South African names - we experiment with different approaches to multilingual T-LID. We compare posterior-based and likelihood-based methods and obtain promising results on a challenging task.

@{289,
  author = {Oluwapelumi Giwa and Marelie Davel},
  title = {Text-based Language Identification of Multilingual Names},
  abstract = {Text-based language identification (T-LID) of isolated words has been shown to be useful for various speech processing tasks, including pronunciation modelling and data categorisation. When the words to be categorised are proper names, the task becomes more difficult: not only do proper names often have idiosyncratic spellings, they are also often considered to be multilingual. We, therefore, investigate how an existing T-LID technique can be adapted to perform multilingual word classification. That is, given a proper name, which may be either mono- or multilingual, we aim to determine how accurately we can predict how many possible source languages the word has, and what they are. Using a Joint Sequence Model-based approach to T-LID and the SADE corpus - a newly developed proper names corpus of South African names - we experiment with different approaches to multilingual T-LID. We compare posterior-based and likelihood-based methods and obtain promising results on a challenging task.},
  year = {2015},
  journal = {Pattern Recognition Association of South Africa (PRASA)},
  pages = {166-171},
  address = {Port Elizabeth, South Africa},
  isbn = {978-1-4673-7450-7, 978-1-4673-7449-1},
  doi = {10.1109/RoboMech.2015.7359517},
}

Pronunciation lexicons can range from fully graphemic (modeling each word using the orthography directly) to fully phonemic (first mapping each word to a phoneme string). Between these two options lies a continuum of modeling options. We analyze techniques that can improve the accuracy of a graphemic system without requiring significant effort to design or implement. The analysis is performed in the context of the IARPA Babel project, which aims to develop spoken term detection systems for previously unseen languages rapidly, and with minimal human effort. We consider techniques related to letter-to-sound mapping and language-independent syllabification of primarily graphemic systems, and discuss results obtained for six languages: Cebuano, Kazakh, Kurmanji Kurdish, Lithuanian, Telugu and Tok Pisin.

@{288,
  author = {Marelie Davel and Etienne Barnard and Charl Van Heerden and William Hartman and Damianos Karakos and Richard Schwartz and Stavros Tsakalidis},
  title = {Exploring minimal pronunciation modeling for low resource languages},
  abstract = {Pronunciation lexicons can range from fully graphemic (modeling each word using the orthography directly) to fully phonemic (first mapping each word to a phoneme string). Between these two options lies a continuum of modeling options. We analyze techniques that can improve the accuracy of a graphemic system without requiring significant effort to design or implement. The analysis is performed in the context of the IARPA Babel project, which aims to develop spoken term detection systems for previously unseen languages rapidly, and with minimal human effort. We consider techniques related to letter-to-sound mapping and language-independent syllabification of primarily graphemic systems, and discuss results obtained for six languages: Cebuano, Kazakh, Kurmanji Kurdish, Lithuanian, Telugu and Tok Pisin.},
  year = {2015},
  journal = {Interspeech},
  pages = {538-542},
  address = {Dresden, Germany},
}

We experiment with a new method to create synthetic models of rare and unseen triphones in order to supplement limited automatic speech recognition (ASR) training data. A trajectory model is used to characterise seen transitions at the spectral level, and these models are then used to create features for unseen or rare triphones. We find that a fairly restricted model (piece-wise linear with three line segments per channel of a diphone transition) is able to represent training data quite accurately. We report on initial results when creating additional triphones for a single-speaker data set, finding small but significant gains, especially when adding additional samples of rare (rather than unseen) triphones.

@{287,
  author = {Jaco Badenhorst and Marelie Davel},
  title = {Synthetic triphones from trajectory-based feature distributions},
  abstract = {We experiment with a new method to create synthetic models of rare and unseen triphones in order to supplement limited automatic speech recognition (ASR) training data. A trajectory model is used to characterise seen transitions at the spectral level, and these models are then used to create features for unseen or rare triphones. We find that a fairly restricted model (piece-wise linear with three line segments per channel of a diphone transition) is able to represent training data quite accurately. We report on initial results when creating additional triphones for a single-speaker data set, finding small but significant gains, especially when adding additional samples of rare (rather than unseen) triphones.},
  year = {2015},
  journal = {Pattern Recognition Association of South Africa (PRASA)},
  pages = {118-122},
  address = {Port Elizabeth, South Africa},
  isbn = {978-1-4673-7450-7, 978-1-4673-7449-1},
  doi = {10.1109/RoboMech.2015.7359509},
}

The language fuzzing with name binding project generates syntactically valid test programs that exercise the name binding semantics of a language processor. We introduce generation algorithm and a tool, NameFuzz, for the test suite generation. It achieves this by by parsing in a ANTLR grammar representing the context free grammar of the language, along with the language’s name binding rules in the NaBL meta-language. The test sentences are intended to be either accepted (positive test cases) or rejected (failing test cases) by the language processor. The intention is to promote confidence in the language processor as far as semantic correctness is concerned. The generated test suite in syntactically correct, but the limitations of not taking type checking into account or having a method to evaluate expressions lead to a large number of test sentences that are semantically incorrect. To a degree these limitations are overcome by the combinatorial nature of the generation algorithm that ensures that each possible type correct sentence is generated as well.

@phdthesis{137,
  author = {G. Newman and Bernd Fischer},
  title = {Language Fuzzing with Name Binding},
  abstract = {The language fuzzing with name binding project generates syntactically valid test programs that exercise the name binding semantics of a language processor. We introduce generation algorithm and a tool, NameFuzz, for the test suite generation. It achieves this by by parsing in a ANTLR grammar representing the context free grammar of the language, along with the language’s name binding rules in the NaBL meta-language. The test sentences are intended to be either accepted (positive test cases) or rejected (failing test cases) by the language processor. The intention is to promote confidence in the language processor as far as semantic correctness is concerned. The generated test suite in syntactically correct, but the limitations of not taking type checking into account or having a method to evaluate expressions lead to a large number of test sentences that are semantically incorrect. To a degree these limitations are overcome by the combinatorial nature of the generation algorithm that ensures that each possible type correct sentence is generated as well.},
  year = {2015},
  volume = {Honours},
}

Visualising software can be a tedious and cluttered affair with the design process and development often being out of sync. Some development methodologies even largely do away with the design entirely and focus on short bursts of coding and validation to make sure the project is still on the right track. This document focuses on deriving a methodology and subsequent tool to iteratively and progressively expand concepts, the understanding of the project and development cycles. An existing visualisation is adapted to better suit the needs of the designer by providing the ability to view the project from different layers of abstraction in one concise visualisation.

@phdthesis{136,
  author = {J. Breytenbach and Bernd Fischer},
  title = {Progressive Software Design Tool},
  abstract = {Visualising software can be a tedious and cluttered affair with the design process and development often being out of sync. Some development methodologies even largely do away with the design entirely and focus on short bursts of coding and validation to make sure the project is still on the right track. This document focuses on deriving a methodology and subsequent tool to iteratively and progressively expand concepts, the understanding of the project and development cycles. An existing visualisation is adapted to better suit the needs of the designer by providing the ability to view the project from different layers of abstraction in one concise visualisation.},
  year = {2015},
  volume = {Honours},
}

In this paper, we enrich description logics (DLs) with non-monotonic reasoning features in a number of ways. We start by investigating a notion of defeasible conditional in the spirit of KLM-style defeasible consequence. In particular, we consider a natural and intuitive semantics for defeasible subsumption in terms of DL interpretations enriched with a preference relation. We propose and investigate syntactic properties (à la Gentzen) for both preferential and rational conditionals and prove representation results for the description logic ALC. This representation result paves the way for more effective decision procedures for defeasible reasoning in DLs. We then move to non-monotonicity in DLs at the level of entailment. We investigate versions of entailment in the context of both preferential and rational subsumption, relate them to preferential and rational closure, and show that computing them can be reduced to classical ALC entailment. This provides further evidence that our semantic constructions are appropriate in a non-monotonic DL setting. One of the barriers to evaluating performance scalability of rational closure is the abscence of naturally occurring DL-based ontologies with defeasible features. We overcome this barrier by devising an approach to introduce defeasible subsumption into classical real world ontologies. This culminates in a set of semi-natural defeasible ontologies that is used, together with a purely artificial set, to test our rational closure algorithms. We found that performance is scalable on the whole with no major bottlenecks.

@misc{130,
  author = {Katarina Britz and Giovanni Casini and Tommie Meyer and Kody Moodley and U. Sattler and Ivan Varzinczak},
  title = {Rational Defeasible Reasoning for Expressive Description Logics},
  abstract = {In this paper, we enrich description logics (DLs) with non-monotonic reasoning features in a number of ways. We start by investigating a notion of defeasible conditional in the spirit of KLM-style defeasible consequence. In particular, we consider a natural and intuitive semantics for defeasible subsumption in terms of DL interpretations enriched with a preference relation. We propose and investigate syntactic properties (à la Gentzen) for both preferential and rational conditionals and prove representation results for the description logic ALC. This representation result paves the way for more effective decision procedures for defeasible reasoning in DLs. We then move to non-monotonicity in DLs at the level of entailment. We investigate versions of entailment in the context of both preferential and rational subsumption, relate them to preferential and rational closure, and show that computing them can be reduced to classical ALC entailment. This provides further evidence that our semantic constructions are appropriate in a non-monotonic DL setting. One of the barriers to evaluating performance scalability of rational closure is the abscence of naturally occurring DL-based ontologies with defeasible features. We overcome this barrier by devising an approach to introduce defeasible subsumption into classical real world ontologies. This culminates in a set of semi-natural defeasible ontologies that is used, together with a purely artificial set, to test our rational closure algorithms. We found that performance is scalable on the whole with no major bottlenecks.},
  year = {2015},
}

No Abstract

@{129,
  author = {Steve Kroon and S. Nienaber and M.J. Booysen},
  title = {A Comparison of Low-Cost Monocular Vision Techniques for Pothole Distance Estimation},
  abstract = {No Abstract},
  year = {2015},
  journal = {IEEE Symposium Series on Computational Intelligence: IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems},
  pages = {419-426},
  month = {08/12-10/12},
}

No Abstract

@article{128,
  author = {Brink van der Merwe and W.C. Visser and Heila van der Merwe and S.E.A. Nel and O. Tkachuk},
  title = {Environment Modeling Using Runtime Values for JPF-Android},
  abstract = {No Abstract},
  year = {2015},
  journal = {ACM SIGSOFT Software Engineering Notes},
  volume = {40},
  pages = {1-5},
  issue = {6},
  publisher = {ACM},
  address = {New York, USA},
  url = {http://dx.doi.org/10.1145/2830719.2830727},
}

Proactive monitoring and control of indoor air quality in homes where there are pregnant mothers and infants is essential for healthy development and well-being of children. This is especially true in low income households where cooking practices and exposure to harmful pollutants produced by nearby industries can negatively impact on a healthy home environment. Interdisciplinary expert knowledge is required to make sense of dynamic and complex environmental phenomena from multivariate low level sensor observations and high level human activities to detect health risks and enact decisions about control. We have developed an ontology for indoor environmental quality monitoring and control based on an ongoing real world case study in Durban, South Africa. We implemented an Indoor Air Quality Index and a thermal comfort index which can be automatically determined by reasoning on the ontology. We evaluated the ontology by populating it with test sensor data and showing how it can be queried to analyze health risk situations and determine control actions. Our evaluation shows that the ontology can be used for real world indoor monitoring and control applications in resource constrained settings.

@{127,
  author = {Jude Adeleke and Deshen Moodley},
  title = {An Ontology for Proactive Indoor Environmental Quality Monitoring and Control},
  abstract = {Proactive monitoring and control of indoor air quality in homes where there are pregnant mothers and infants is essential for healthy development and well-being of children. This is especially true in low income households where cooking practices and exposure to harmful pollutants produced by nearby industries can negatively impact on a healthy home environment. Interdisciplinary expert knowledge is required to make sense of dynamic and complex environmental phenomena from multivariate low level sensor observations and high level human activities to detect health risks and enact decisions about control. We have developed an ontology for indoor environmental quality monitoring and control based on an ongoing real world case study in Durban, South Africa. We implemented an Indoor Air Quality Index and a thermal comfort index which can be automatically determined by reasoning on the ontology. We evaluated the ontology by populating it with test sensor data and showing how it can be queried to analyze health risk situations and determine control actions. Our evaluation shows that the ontology can be used for real world indoor monitoring and control applications in resource constrained settings.},
  year = {2015},
  journal = {The 2015 Annual Conference of the South African Institute of Computer Scientists and Information Technologists (SAICSIT '15)},
  month = {28/09-30/09},
  address = {New York, NY, USA ©2015},
  isbn = {978-1-4503-3683-3},
}

No Abstract

@article{126,
  author = {Bernd Fischer and G.J. Greene},
  title = {Interactive tag cloud visualization of software version control repositories},
  abstract = {No Abstract},
  year = {2015},
  journal = {Software Visualization (VISSOFT)},
  pages = {56-65},
  url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7332415&isnumber=7332403},
}

Data-driven elicitation of ontologies from structured data is a well-recognized knowledge acquisition bottleneck. The development of efficient techniques for (semi-)automating this task is therefore practically vital --- yet, hindered by the lack of robust theoretical foundations. In this paper, we study the problem of learning Description Logic TBoxes from interpretations, which naturally translates to the task of ontology learning from data. In the presented framework, the learner is provided with a set of positive interpretations (i.e., logical models) of the TBox adopted by the teacher. The goal is to correctly identify the TBox given this input. We characterize the key constraints on the models that warrant finite learnability of TBoxes expressed in selected fragments of the Description Logic $\mathcal{EL}$ and define corresponding learning algorithms.

@{125,
  author = {Katarina Britz and Simon Klarman},
  title = {Ontology learning from interpretations in lightweight description logics},
  abstract = {Data-driven elicitation of ontologies from structured data is a well-recognized knowledge acquisition bottleneck. The development of efficient techniques for (semi-)automating this task is therefore practically vital --- yet, hindered by the lack of robust theoretical foundations. In this paper, we study the problem of learning Description Logic TBoxes from interpretations, which naturally translates to the task of ontology learning from data. In the presented framework, the learner is provided with a set of positive interpretations (i.e., logical models) of the TBox adopted by the teacher. The goal is to correctly identify the TBox given this input. We characterize the key constraints on the models that warrant finite learnability of TBoxes expressed in selected fragments of the Description Logic $\mathcal{EL}$ and define corresponding learning algorithms.},
  year = {2015},
  journal = {25th International Conference on Inductive Logic Programming},
  month = {20/08-22/08},
}

No Abstract

@inbook{124,
  author = {Marne de Vries and Aurona Gerber and Alta van der Merwe},
  title = {The enterprise engineering domain},
  abstract = {No Abstract},
  year = {2015},
  journal = {Advances in Enterprise Engineering IX},
  publisher = {Springer},
  isbn = {978-3-319-19296-3},
  url = {http://link.springer.com/chapter/10.1007%2F978-3-319-19297-0_4},
}

No Abstract

@article{123,
  author = {Alta van der Merwe and Rennie Naidoo and Aurona Gerber},
  title = {Understanding familiarization processes with Design Science Research: A social representation analysis.},
  abstract = {No Abstract},
  year = {2015},
  journal = {South African Computer Journal},
  volume = {65},
  isbn = {ISSN: 2313-7835},
  url = {http://sacj.cs.uct.ac.za/index.php/sacj/issue/view/2},
}

No Abstract

@{122,
  author = {Paula Kotzé and Alta van der Merwe and Aurona Gerber},
  title = {Design Science Research as Research Approach in Doctoral Studies},
  abstract = {No Abstract},
  year = {2015},
  journal = {AMCIS 2015, the 2015 Americas Conference on Information Systems},
  month = {13/08-15/08},
}