Research Publications

KnowIt (Knowledge discovery in time series data) is a flexible framework for building deep time series models and interpreting them. It is implemented as a Python toolkit, with source code and documentation available from this https URL. It imposes minimal assumptions about task specifications and decouples the definition of dataset, deep neural network architecture, and interpretability technique through well defined interfaces. This ensures the ease of importing new datasets, custom architectures, and the definition of different interpretability paradigms while maintaining on-the-fly modeling and interpretation of different aspects of a user's own time series data. KnowIt aims to provide an environment where users can perform knowledge discovery on their own complex time series data through building powerful deep learning models and explaining their behavior. With ongoing development, collaboration and application our goal is to make this a platform to progress this underexplored field and produce a trusted tool for deep time series modeling.

@article{531,
  author = {Marthinus Theunissen and Randle Rabe and Marelie Davel},
  title = {KnowIt: Deep Time Series Modeling and Interpretation},
  abstract = {KnowIt (Knowledge discovery in time series data) is a flexible framework for building deep time series models and interpreting them. It is implemented as a Python toolkit, with source code and documentation available from this https URL. It imposes minimal assumptions about task specifications and decouples the definition of dataset, deep neural network architecture, and interpretability technique through well defined interfaces. This ensures the ease of importing new datasets, custom architectures, and the definition of different interpretability paradigms while maintaining on-the-fly modeling and interpretation of different aspects of a user's own time series data. KnowIt aims to provide an environment where users can perform knowledge discovery on their own complex time series data through building powerful deep learning models and explaining their behavior. With ongoing development, collaboration and application our goal is to make this a platform to progress this underexplored field and produce a trusted tool for deep time series modeling.},
  year = {2025},
  journal = {arXiv},
}

In ensembles, improved generalization is frequently attributed to \emph{diversity} among members of the ensemble. By viewing a single neural network as an \emph{implicit ensemble}, we perform an exploratory investigation that applies well-known ensemble diversity measures to a neural network in order to study the relationship between diversity and generalization in the over-parameterized regime. Our results show that i) deeper layers of the network generally have higher levels of diversity—particularly for MLPs—and ii) layer-wise accuracy positively correlates with diversity. Additionally, we study the effects of well-known regularizers such as Dropout, DropConnect and batch size, on diversity and generalization. We generally find that increasing the strength of the regularizer increases the diversity in the neural network and this increase in diversity is positively correlated with model accuracy. We show that these results hold for several benchmark datasets (such as Fashion-MNIST and CIFAR-10) and architectures (MLPs and CNNs). Our findings suggest new avenues of research into the generalization ability of deep neural networks.

@article{530,
  author = {Ruan Van der Spoel and Randle Rabe},
  title = {Investigating the relationship between diversity and generalization in deep neural networks},
  abstract = {In ensembles, improved generalization is frequently attributed to \emph{diversity} among members of the ensemble. By viewing a single neural network as an \emph{implicit ensemble}, we perform an exploratory investigation that applies well-known ensemble diversity measures to a neural network in order to study the relationship between diversity and generalization in the over-parameterized regime. Our results show that i) deeper layers of the network generally have higher levels of diversity—particularly for MLPs—and ii) layer-wise accuracy positively correlates with diversity. Additionally, we study the effects of well-known regularizers such as Dropout, DropConnect and batch size, on diversity and generalization. We generally find that increasing the strength of the regularizer increases the diversity in the neural network and this increase in diversity is positively correlated with model accuracy. We show that these results hold for several benchmark datasets (such as Fashion-MNIST and CIFAR-10) and architectures (MLPs and CNNs). Our findings suggest new avenues of research into the generalization ability of deep neural networks.},
  year = {2025},
  journal = {Proceedings of the 7th Northern Lights Deep Learning Conference (NLDL)},
  volume = {307},
  pages = {375 - 387},
}

The performance of deep learning models is affected by not only data quantity but also data quality. Data pruning is a process by which practitioners can reduce the size of a dataset by only keeping the most important training data points, thereby achieving similar test set performance. We empirically investigate two popular data pruning methods under noisy and noiseless conditions and show that these methods fail in the presence of significant label noise. We highlight that the success of data pruning is distinctly affected by three factors: redundancy in the dataset, the presence of problematic samples, and interdependence between samples. We perform a detailed investigation on commonly used benchmark classification datasets and neural network architectures. We find that our observations are consistent across data distributions and training protocols.

@article{529,
  author = {Leon Freese and Marthinus Theunissen},
  title = {Data Pruning: Redundant, Problematic, and Interdependent Samples},
  abstract = {The performance of deep learning models is affected by not only data quantity but also data quality. Data pruning is a process by which practitioners can reduce the size of a dataset by only keeping the most important training data points, thereby achieving similar test set performance. We empirically investigate two popular data pruning methods under noisy and noiseless conditions and show that these methods fail in the presence of significant label noise. We highlight that the success of data pruning is distinctly affected by three factors: redundancy in the dataset, the presence of problematic samples, and interdependence between samples. We perform a detailed investigation on commonly used benchmark classification datasets and neural network architectures. We find that our observations are consistent across data distributions and training protocols.},
  year = {2025},
  journal = {Artificial Intelligence Research. SACAIR 2025. Communications in Computer and Information Science},
  volume = {vol 2784},
  month = {25 November 2025},
  doi = {https://doi.org/10.1007/978-3-032-11733-5_12},
}

Precision agriculture requires the estimation of plant growth stages in real-time. When the plant growth stage is known, the wastage of resources in cultivation, such as nutrients and water, is reduced as only the required resources need to be supplied. Plants at different growth stages, however, have similar morphological features, which can make autonomous growth stage estimation difficult. This paper presents two feature extraction methods for growth stage estimation: one that uses a bank of Gabor filters and morphological operations, and the other that uses pre-trained convolutional neural networks (CNNs) and transfer learning. We test these methods on a publicly available plant growth stage dataset (“bccr-segset“) for two species, canola and radish, grown and captured under indoor conditions. The two proposed feature extraction methods are compared, using support vector machines and boosted trees as classifiers. We find that both methods are suitable for real-time applications, and that CNN features outperform the hand-crafted features, both with regard to speed and accuracy. The best system (VGG-19 features, classified with a radial basis function support vector machine) obtained an accuracy of 98.4% for both species, processing an image in 0.08 seconds.

@article{528,
  author = {Aldrin Ngorima and Albert Helberg and Marelie Davel},
  title = {Feature extraction for plant growth estimation},
  abstract = {Precision agriculture requires the estimation of plant growth stages in real-time. When the plant growth stage is known, the wastage of resources in cultivation, such as nutrients and water, is reduced as only the required resources need to be supplied. Plants at different growth stages, however, have similar morphological features, which can make autonomous growth stage estimation difficult. This paper presents two feature extraction methods for growth stage estimation: one that uses a bank of Gabor filters and morphological operations, and the other that uses pre-trained convolutional neural networks (CNNs) and transfer learning. We test these methods on a publicly available plant growth stage dataset (“bccr-segset“) for two species, canola and radish, grown and captured under indoor conditions. The two proposed feature extraction methods are compared, using support vector machines and boosted trees as classifiers. We find that both methods are suitable for real-time applications, and that CNN features outperform the hand-crafted features, both with regard to speed and accuracy. The best system (VGG-19 features, classified with a radial basis function support vector machine) obtained an accuracy of 98.4% for both species, processing an image in 0.08 seconds.},
  year = {2025},
  journal = {Artificial Intelligence Research. SACAIR 2025. Communications in Computer and Information Science},
  volume = {vol 2784},
  month = {25 November 2025},
  doi = {https://doi.org/10.1007/978-3-032-11733-5_5},
}

Criminal investigations involving cryptocurrencies are still premature with no standard investigative process to follow. This paper proposes a high-level methodology using open-source and analysed data to perform such investigations. It focuses on situations where Bitcoin is involved, but where other similar blockchains are concerned, the technical investigator should apply this methodology only after careful consideration. A case study approach is used to illustrate a cryptocurrency scamming platform, a giveaway scam, and divorce fraud. In all the cases, one needs to follow or trace the funds on the blockchain, referred to as on-chain analysis. The end goal of on-chain analysis is to find a destination address linked to identifiable information obtained from open-source data platforms-such as websites, social media, or a cryptocurrency exchange. Law enforcement can then be engaged to instruct the exchange to reveal all personal and transactional information linked to the address through a subpoena. A successful investigation will result in criminal prosecution and a potential recovery of funds. To maintain familiar investigation processes, the researchers looked at traditional (or non-technical) as well as technical investigation techniques.

@{523,
  author = {JG Botha and Louise Leenen and Kreaan Singh},
  title = {A Proposed Bitcoin Blockchain Investigation Methodology: Based on a Case Study Approach},
  abstract = {Criminal investigations involving cryptocurrencies are still premature with no standard investigative process to follow. This paper proposes a high-level methodology using open-source and analysed data to perform such investigations. It focuses on situations where Bitcoin is involved, but where other similar blockchains are concerned, the technical investigator should apply this methodology only after careful consideration. A case study approach is used to illustrate a cryptocurrency scamming platform, a giveaway scam, and divorce fraud. In all the cases, one needs to follow or trace the funds on the blockchain, referred to as on-chain analysis. The end goal of on-chain analysis is to find a destination address linked to identifiable information obtained from open-source data platforms-such as websites, social media, or a cryptocurrency exchange. Law enforcement can then be engaged to instruct the exchange to reveal all personal and transactional information linked to the address through a subpoena. A successful investigation will result in criminal prosecution and a potential recovery of funds. To maintain familiar investigation processes, the researchers looked at traditional (or non-technical) as well as technical investigation techniques.},
  year = {2025},
  journal = {Journal of Information Warfare},
  volume = {24},
  issue = {1},
  address = {ArmisteadTEC, LLC Virginia Beach, Virginia, USA},
}

The ocean plays a vital role in our society and represents a constantly changing landscape that is not well understood and therefore needs continuous monitoring and research. Sustainable monitoring is essential to assess both the current and future state of our oceans. However, conventional monitoring faces significant challenges, including issues of accessibility, and spatial and temporal constraints. The development of digital twins of the ocean (DTO) offers an emerging technology that could revolutionise our understanding of marine and coastal environments. Current DTO have shown effectiveness in monitoring marine and coastal environments in the European context. However, there is a need for a DTO for the Southern African and Western Indian Ocean regions that addresses specific concerns that are relevant to these regions. Successful development of a DTO depends on the availability of high-quality data. Therefore, various data inputs are necessary to build an accurate digital twin. This paper explores the data that can be utilised in a DTO, detailing how different ocean variables are collected and integrated into the digital twin. As a first step towards the development of a DTO in these regions, the paper proposes a data management plan and its implementation in the development of DTO. The data management plan is based on the phases of data in a geospatial data life cycle. Challenges regarding the management of data in this DTO and possible solutions are presented in the conclusion.

@article{522,
  author = {Shelley Haupt and Bolelang Sibolla and Raymond Molapo and Lizwe Mdakane and Nicolene Fourie},
  title = {Exploring the Use of Data in a Digital Twin for the Marine and Coastal Environment},
  abstract = {The ocean plays a vital role in our society and represents a constantly changing landscape that is not well understood and therefore needs continuous monitoring and research. Sustainable monitoring is essential to assess both the current and future state of our oceans. However, conventional monitoring faces significant challenges, including issues of accessibility, and spatial and temporal constraints. The development of digital twins of the ocean (DTO) offers an emerging technology that could revolutionise our understanding of marine and coastal environments. Current DTO have shown effectiveness in monitoring marine and coastal environments in the European context. However, there is a need for a DTO for the Southern African and Western Indian Ocean regions that addresses specific concerns that are relevant to these regions. Successful development of a DTO depends on the availability of high-quality data. Therefore, various data inputs are necessary to build an accurate digital twin. This paper explores the data that can be utilised in a DTO, detailing how different ocean variables are collected and integrated into the digital twin. As a first step towards the development of a DTO in these regions, the paper proposes a data management plan and its implementation in the development of DTO. The data management plan is based on the phases of data in a geospatial data life cycle. Challenges regarding the management of data in this DTO and possible solutions are presented in the conclusion.},
  year = {2025},
  journal = {International Jornal of Geo-Information},
  volume = {14},
  month = {03/2025},
  issue = {4},
  doi = {https://doi.org/10.3390/ijgi14040140},
}

@article{521,
  author = {Aldrin Ngorima and Albert Helberg and Marelie Davel},
  title = {Simplified Temporal Convolutional-Based Channel Estimation for a WiFi Vehicular Communication Channel},
  abstract = {},
  year = {2025},
  journal = {IEEE 3rd Wireless Africa Conference (WAC)},
  pages = {1 - 5},
  month = {02/2025},
  publisher = {IEEE},
  address = {Pretoria, South Africa},
  isbn = {979-8-3315-1758-8},
  doi = {10.1109/WAC63911.2025.10992609},
}

This paper delves into the intricacies of consensus processes within project teams, shedding light on determinants such as group size and the role of artefacts. By deploying both a simulation and a mathematical model, the study unfolds insights into the temporal and resource dynamics essential for consensus formation. Notably, for smaller teams, the quadratic dependence on team size underscores the complexities inherent in achieving consensus. In contrast, larger teams exhibit a linear relationship, hinting at a more scalable consensus process. The investigation introduces the influence of artefacts, emphasizing the significance it plays in streamlining consensus efforts. A noteworthy revelation is the substantial reduction, over 30%, in consensus time with the use of artefacts, underscoring their impact on communication and collaboration within teams. This finding underscores the pragmatic importance of well-structured documentation and artefacts in expediting consensus-building processes. Historic project failures often attributed to prolonged and intricate consensus processes. This research contributes valuable insights for project managers. By elucidating the interplay between team size, artefacts, and consensus, the study provides a nuanced understanding of project dynamics. This understanding, grounded in both simulation and mathematical models, offers practical guidance for project management strategies, enabling tailored approaches based on team size and organizational structure. Ultimately, this research advances the discourse on effective project management by unraveling the complexities of consensus processes and illuminating the transformative impact of artefacts.

@inbook{525,
  author = {Johannes Vorster and Louise Leenen},
  title = {Stochastic Consensus Simulation for Organizational Cooperation},
  abstract = {This paper delves into the intricacies of consensus processes within project teams, shedding light on determinants such as group size and the role of artefacts. By deploying both a simulation and a mathematical model, the study unfolds insights into the temporal and resource dynamics essential for consensus formation. Notably, for smaller teams, the quadratic dependence on team size underscores the complexities inherent in achieving consensus. In contrast, larger teams exhibit a linear relationship, hinting at a more scalable consensus process. The investigation introduces the influence of artefacts, emphasizing the significance it plays in streamlining consensus efforts. A noteworthy revelation is the substantial reduction, over 30%, in consensus time with the use of artefacts, underscoring their impact on communication and collaboration within teams. This finding underscores the pragmatic importance of well-structured documentation and artefacts in expediting consensus-building processes. Historic project failures often attributed to prolonged and intricate consensus processes. This research contributes valuable insights for project managers. By elucidating the interplay between team size, artefacts, and consensus, the study provides a nuanced understanding of project dynamics. This understanding, grounded in both simulation and mathematical models, offers practical guidance for project management strategies, enabling tailored approaches based on team size and organizational structure. Ultimately, this research advances the discourse on effective project management by unraveling the complexities of consensus processes and illuminating the transformative impact of artefacts.},
  year = {2024},
  journal = {Simulation and Modeling Methodologies, Technologies and Applications},
  volume = {1211},
  edition = {1},
  pages = {139-173},
  month = {December 2024},
  publisher = {Springer, Cham},
  isbn = {978-3-031-77603-8},
  doi = {https://doi.org/10.1007/978-3-031-77603-8_8},
}

This theoretical study investigates the influence of subversive agents on consensus-seeking processes within project teams. Departing from traditional cooperative team dynamics, the research introduces agents strategically working to influence views and decisions. Key findings reveal that yes-agents, actively advocating for specific views, can enhance consensus times but carry the risk of swaying decisions toward potentially incorrect outcomes. In contrast, subversive agents, by widening the range of options or polarizing the group, substantially delay consensus processes. Notably, the level of cooperation among subversive agents does not significantly impact consensus times, yet coordinated actions profoundly shape decision outcomes. Under specific conditions, even a small minority of subversive agents can significantly extend the time to reach consensus, showcasing their potent influence. This research contributes to understanding the interplay between cooperation, subversion, and decision-making, offering valuable insights for future exploration and empirical research.

@inbook{524,
  author = {Johannes Vorster and Louise Leenen},
  title = {Exploring the Impact of Subversive Agents on Consensus  Processes in Project Teams: Multi-agent Simulations.},
  abstract = {This theoretical study investigates the influence of subversive agents on consensus-seeking processes within project teams. Departing from traditional cooperative team dynamics, the research introduces agents strategically working to influence views and decisions. Key findings reveal that yes-agents, actively advocating for specific views, can enhance consensus times but carry the risk of swaying decisions toward potentially incorrect outcomes. In contrast, subversive agents, by widening the range of options or polarizing the group, substantially delay consensus processes. Notably, the level of cooperation among subversive agents does not significantly impact consensus times, yet coordinated actions profoundly shape decision outcomes. Under specific conditions, even a small minority of subversive agents can significantly extend the time to reach consensus, showcasing their potent influence. This research contributes to understanding the interplay between cooperation, subversion, and decision-making, offering valuable insights for future exploration and empirical research.},
  year = {2024},
  journal = {Simulation and Modeling Methodologies, Technologies and  Applications},
  volume = {1211},
  edition = {1},
  pages = {29-60},
  month = {Dec 2024},
  publisher = {Springer, Cham},
  isbn = {978-3-031-77603-8},
  doi = {https://doi.org/10.1007/978-3-031-77603-8_3},
}

@article{520,
  author = {William Brooks and Marelie Davel and Coenraad Mouton},
  title = {Does Simple Trump Complex? Comparing Strategies for Adversarial Robustness in DNNs},
  abstract = {},
  year = {2024},
  journal = {Artificial Intelligence Research. SACAIR 2024. Communications in Computer and Information Science},
  volume = {vol 2326},
  pages = {253 - 269},
  month = {12/2024},
  publisher = {Springer Nature Switzerland},
  address = {Cham},
  doi = {https://doi.org/10.1007/978-3-031-78255-8_15},
}

Batch normalization (BatchNorm) is a popular layer normalization technique used when training deep neural networks. It has been shown to enhance the training speed and accuracy of deep learning models. However, the mechanics by which BatchNorm achieves these benefits is an active area of research, and different perspectives have been proposed. In this paper, we investigate the effect of BatchNorm on the resulting hidden representations, that is, the vectors of activation values formed as samples are processed at each hidden layer. Specifically, we consider the sparsity of these representations, as well as their implicit clustering – the creation of groups of representations that are similar to some extent. We contrast image classification models trained with and without batch normalization and highlight consistent differences observed. These findings highlight that BatchNorm’s effect on representational sparsity is not a significant factor affecting generalization, while the representations of models trained with BatchNorm tend to show more advantageous clustering characteristics.

@article{518,
  author = {Harmen Potgieter and Coenraad Mouton and Marelie Davel},
  title = {Impact of Batch Normalization on Convolutional Network Representations},
  abstract = {Batch normalization (BatchNorm) is a popular layer normalization technique used when training deep neural networks. It has been shown to enhance the training speed and accuracy of deep learning models. However, the mechanics by which BatchNorm achieves these benefits is an active area of research, and different perspectives have been proposed. In this paper, we investigate the effect of BatchNorm on the resulting hidden representations, that is, the vectors of activation values formed as samples are processed at each hidden layer. Specifically, we consider the sparsity of these representations, as well as their implicit clustering – the creation of groups of representations that are similar to some extent. We contrast image classification models trained with and without batch normalization and highlight consistent differences observed. These findings highlight that BatchNorm’s effect on representational sparsity is not a significant factor affecting generalization, while the representations of models trained with BatchNorm tend to show more advantageous clustering characteristics.},
  year = {2024},
  journal = {Artificial Intelligence Research (SACAIR 2024)},
  volume = {vol 2326},
  pages = {235 - 252},
  month = {12/2024},
  publisher = {Springer Nature Switzerland},
  address = {Cham},
  doi = {https://doi.org/10.1007/978-3-031-78255-8_14},
}

Due to the scarcity of data in low-resourced languages, the development of language models for these languages has been very slow. Currently, pre-trained language models have gained popularity in natural language processing, especially, in developing domain-specific models for low-resourced languages. In this study, we experiment with the impact of using occlusion-based techniques when training a language model for a text generation task. We curate 2 new datasets, the Sepedi monolingual (SepMono) dataset from several South African resources and the Sepedi radio news (SepNews) dataset from the radio news domain. We use the SepMono dataset to pre-train transformer-based models using the occlusion and non-occlusion pre-training techniques and compare performance. The SepNews dataset is specifically used for fine-tuning. Our results show that the non-occlusion models perform better compared to the occlusion-based models when measuring validation loss and perplexity. However, analysis of the generated text using the BLEU score metric, which measures the quality of the generated text, shows a slightly higher BLEU score for the occlusion-based models compared to the non-occlusion models.

@article{517,
  author = {Simon Ramalepe and Thipe Modipa and Marelie Davel},
  title = {Pre-training a Transformer-Based Generative Model Using a Small Sepedi Dataset},
  abstract = {Due to the scarcity of data in low-resourced languages, the development of language models for these languages has been very slow. Currently, pre-trained language models have gained popularity in natural language processing, especially, in developing domain-specific models for low-resourced languages. In this study, we experiment with the impact of using occlusion-based techniques when training a language model for a text generation task. We curate 2 new datasets, the Sepedi monolingual (SepMono) dataset from several South African resources and the Sepedi radio news (SepNews) dataset from the radio news domain. We use the SepMono dataset to pre-train transformer-based models using the occlusion and non-occlusion pre-training techniques and compare performance. The SepNews dataset is specifically used for fine-tuning. Our results show that the non-occlusion models perform better compared to the occlusion-based models when measuring validation loss and perplexity. However, analysis of the generated text using the BLEU score metric, which measures the quality of the generated text, shows a slightly higher BLEU score for the occlusion-based models compared to the non-occlusion models.},
  year = {2024},
  journal = {Artificial Intelligence Research. SACAIR 2024. Communications in Computer and Information Science},
  volume = {vol 2326},
  pages = {319-333},
  month = {12/2024},
  publisher = {Springer Nature Switzerland},
  address = {Cham},
  doi = {https://doi.org/10.1007/978-3-031-78255-8_19},
}

Vehicular communication systems face significant challenges due to high mobility and rapidly changing environments, which affect the channel over which the signals travel. To address these challenges, neural network (NN)-based channel estimation methods have been suggested. These methods are primarily trained on high signal-to-noise ratio (SNR) with the assumption that training a NN in less noisy conditions can result in good generalisation. This study examines the effectiveness of training NN-based channel estimators on mixed SNR datasets compared to training solely on high SNR datasets, as seen in several related works. Estimators evaluated in this work include an architecture that uses convolutional layers and self-attention mechanisms; a method that employs temporal convolutional networks and data pilot-aided estimation; two methods that combine classical methods with multilayer perceptrons; and the current state-of-the-art model that combines Long-Short-Term Memory networks with data pilot-aided and temporal averaging methods as post processing. Our results indicate that using only high SNR data for training is not always optimal, and the SNR range in the training dataset should be treated as a hyperparameter that can be adjusted for better performance. This is illustrated by the better performance of some models in low SNR conditions when trained on the mixed SNR dataset, as opposed to when trained exclusively on high SNR data.

@article{516,
  author = {Aldrin Ngorima and Albert Helberg and Marelie Davel},
  title = {Neural Network-Based Vehicular Channel Estimation Performance: Effect of Noise in the Training Set},
  abstract = {Vehicular communication systems face significant challenges due to high mobility and rapidly changing environments, which affect the channel over which the signals travel. To address these challenges, neural network (NN)-based channel estimation methods have been suggested. These methods are primarily trained on high signal-to-noise ratio (SNR) with the assumption that training a NN in less noisy conditions can result in good generalisation. This study examines the effectiveness of training NN-based channel estimators on mixed SNR datasets compared to training solely on high SNR datasets, as seen in several related works. Estimators evaluated in this work include an architecture that uses convolutional layers and self-attention mechanisms; a method that employs temporal convolutional networks and data pilot-aided estimation; two methods that combine classical methods with multilayer perceptrons; and the current state-of-the-art model that combines Long-Short-Term Memory networks with data pilot-aided and temporal averaging methods as post processing. Our results indicate that using only high SNR data for training is not always optimal, and the SNR range in the training dataset should be treated as a hyperparameter that can be adjusted for better performance. This is illustrated by the better performance of some models in low SNR conditions when trained on the mixed SNR dataset, as opposed to when trained exclusively on high SNR data.},
  year = {2024},
  journal = {Artificial Intelligence Research. SACAIR 2024. Communications in Computer and Information Science},
  volume = {vol 2326},
  pages = {192 - 206},
  month = {12/2024},
  publisher = {Springer Nature Switzerland},
  address = {Cham},
  isbn = {978-3-031-78255-8},
  doi = {https://doi.org/10.1007/978-3-031-78255-8_12},
}

In modern communication systems, having an accurate channel estimator is crucial. However, when there is mobility, it becomes difficult to estimate the channel and the pilot signals, which are used for channel estimation, become insufficient. In this paper, we introduce the use of Temporal
Convolutional Networks (TCNs) with data pilot-aided (DPA) channel estimation and temporal averaging (TA) to estimate vehicle-to-vehicle same direction with Wall (VTV-SDWW) channels. The TCN-DPA-TA estimator showed an improvement in Bit Error Rate (BER) performance of up to 1 order of magnitude. Furthermore, the BER performance of the TCN-DPA without TA also improved by up to 0.7 magnitude compared to the best classical estimator.

@article{515,
  author = {Aldrin Ngorima and Albert Helberg and Marelie Davel},
  title = {A Data Pilot-Aided Temporal Convolutional Network for Channel Estimation in IEEE 802.11p Vehicle-to-Vehicle Communications},
  abstract = {In modern communication systems, having an accurate channel estimator is crucial. However, when there is mobility, it becomes difficult to estimate the channel and the pilot signals, which are used for channel estimation, become insufficient. In this paper, we introduce the use of TemporalConvolutional Networks (TCNs) with data pilot-aided (DPA) channel estimation and temporal averaging (TA) to estimate vehicle-to-vehicle same direction with Wall (VTV-SDWW) channels. The TCN-DPA-TA estimator showed an improvement in Bit Error Rate (BER) performance of up to 1 order of magnitude. Furthermore, the BER performance of the TCN-DPA without TA also improved by up to 0.7 magnitude compared to the best classical estimator.},
  year = {2024},
  journal = {Southern Africa Telecommunication Networks and Applications Conference (SATNAC)},
  pages = {356–361},
}

It has been observed that the input space of deep neural network classifiers can exhibit ‘fragmentation’, where the model function rapidly changes class as the input space is traversed. The severity of this fragmentation tends to follow the double descent curve, achieving a maximum at the interpolation regime. We study this phenomenon in the context of image classification and ask whether fragmentation could be predictive of generalization performance. Using a fragmentation-based complexity measure, we show this to be possible by achieving good performance on the PGDL (Predicting Generalization in Deep Learning) benchmark. In addition, we report on new observations related to fragmentation, namely (i) fragmentation is not limited to the input space but occurs in the hidden representations as well, (ii) fragmentation follows the trends in the validation error throughout training, and (iii) fragmentation is not a direct result of increased weight norms. Together, this indicates that fragmentation is a phenomenon worth investigating further when studying the generalization ability of deep neural networks.

@misc{514,
  author = {Coenraad Mouton and Randle Rabe and Daniël Haasbroek and Marthinus Theunissen and Harmen Potgieter and Marelie Davel},
  title = {Is network fragmentation a useful complexity measure?},
  abstract = {It has been observed that the input space of deep neural network classifiers can exhibit ‘fragmentation’, where the model function rapidly changes class as the input space is traversed. The severity of this fragmentation tends to follow the double descent curve, achieving a maximum at the interpolation regime. We study this phenomenon in the context of image classification and ask whether fragmentation could be predictive of generalization performance. Using a fragmentation-based complexity measure, we show this to be possible by achieving good performance on the PGDL (Predicting Generalization in Deep Learning) benchmark. In addition, we report on new observations related to fragmentation, namely (i) fragmentation is not limited to the input space but occurs in the hidden representations as well, (ii) fragmentation follows the trends in the validation error throughout training, and (iii) fragmentation is not a direct result of increased weight norms. Together, this indicates that fragmentation is a phenomenon worth investigating further when studying the generalization ability of deep neural networks.},
  year = {2024},
  journal = {NeurIPS 2024 Workshop SciForDL},
  month = {12/2024},
}

The choice of airfoil parameterisation method significantly influences the overall wing optimisation performance by affecting the flexibility and computational efficiency of the process. Ideally, one should be able to intuitively constrain airfoil shape and structural characteristics as input to the optimisation process. Current parameterisation techniques lack the flexibility to generate airfoils efficiently by specifying parsimonious shape and structural features. To address this limitation, a deep learning framework is proposed, enabling conditional airfoil generation from an airfoil’s shape and structural feature definition. Specifically, we demonstrate the application of Bidirectional Long Short Term Memory models and Bayesian Gaussian Mixture models to derive airfoil coordinates from a compact set of shape and structural characteristics that we define. The proposed framework is shown to achieve favorable airfoil performance optimisation due to improved exploration and exploitation of the design space, compared to traditional approaches. Overall, the proposed optimisation framework is able to realise a 9.04% performance improvement over an airfoil design optimised with traditional parameterisation techniques.

@article{513,
  author = {Vincent Le Roux and Marelie Davel and Johan Bosman},
  title = {Parsimonious airfoil Parameterisation: A deep learning framework with Bidirectional LSTM and Gaussian Mixture models},
  abstract = {The choice of airfoil parameterisation method significantly influences the overall wing optimisation performance by affecting the flexibility and computational efficiency of the process. Ideally, one should be able to intuitively constrain airfoil shape and structural characteristics as input to the optimisation process. Current parameterisation techniques lack the flexibility to generate airfoils efficiently by specifying parsimonious shape and structural features. To address this limitation, a deep learning framework is proposed, enabling conditional airfoil generation from an airfoil’s shape and structural feature definition. Specifically, we demonstrate the application of Bidirectional Long Short Term Memory models and Bayesian Gaussian Mixture models to derive airfoil coordinates from a compact set of shape and structural characteristics that we define. The proposed framework is shown to achieve favorable airfoil performance optimisation due to improved exploration and exploitation of the design space, compared to traditional approaches. Overall, the proposed optimisation framework is able to realise a 9.04% performance improvement over an airfoil design optimised with traditional parameterisation techniques.},
  year = {2024},
  journal = {Expert Systems With Applications},
  volume = {255},
  month = {10 July 2024},
  doi = {https://doi.org/10.1016/j.eswa.2024.124726},
}

Understanding generalization in deep neural networks is an active area of research. A promising avenue of exploration has been that of margin measurements: the shortest distance to the decision boundary for a given sample or its representation internal to the network. While margins have been shown to be correlated with the generalization ability of a model when measured at its hidden representations (hidden margins), no such link between large margins and generalization has been established for input margins. We show that while input margins are not generally predictive of generalization, they can be if the search space is appropriately constrained. We develop such a measure based on input margins, which we refer to as ‘constrained margins’. The predictive power of this new measure is demonstrated on the ‘Predicting Generalization in Deep Learning’ (PGDL) dataset and contrasted with hidden representation margins. We find that constrained margins achieve highly competitive scores and outperform other margin measurements in general. This provides a novel insight on the relationship between generalization and classification margins, and highlights the importance of considering the data manifold for investigations of generalization in DNNs

@inbook{512,
  author = {Coenraad Mouton and Marthinus Theunissen and Marelie Davel},
  title = {Input margins can predict generalization too},
  abstract = {Understanding generalization in deep neural networks is an active area of research. A promising avenue of exploration has been that of margin measurements: the shortest distance to the decision boundary for a given sample or its representation internal to the network. While margins have been shown to be correlated with the generalization ability of a model when measured at its hidden representations (hidden margins), no such link between large margins and generalization has been established for input margins. We show that while input margins are not generally predictive of generalization, they can be if the search space is appropriately constrained. We develop such a measure based on input margins, which we refer to as ‘constrained margins’. The predictive power of this new measure is demonstrated on the ‘Predicting Generalization in Deep Learning’ (PGDL) dataset and contrasted with hidden representation margins. We find that constrained margins achieve highly competitive scores and outperform other margin measurements in general. This provides a novel insight on the relationship between generalization and classification margins, and highlights the importance of considering the data manifold for investigations of generalization in DNNs},
  year = {2024},
  journal = {In Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence and Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence and Fourteenth Symposium on Educational Advances in Artificial Intelligence (AAAI'24/IAAI'24/E},
  pages = {14379 - 14387},
  month = {20 February 2024},
  publisher = {AAAI Conference on Artificial Intelligence (AAAI)},
}

Data analysis-based decision-making is performed daily by domain experts. As data grows, getting access to relevant data becomes a challenge. In an approach known as Ontology-based data access (OBDA), ontologies are advocated as a suitable formal tool to address complex data access. This technique combines a domain ontology with a data source by using a declarative mapping specification to enable data access using a domain vocabulary. We investigate this approach by studying the theoretical background; conducting a literature review on the implementation of OBDA in production systems; implementing OBDA on a relational dataset using an OBDA tool and; providing results and analysis of query answering. We selected Ontop (https://ontop-vkg.org) to illustrate how this technique enhances the data usage of the GitHub community. Ontop is an open-source OBDA tool applied in the domain of relational databases. The implementation consists of the GHTorrent dataset and an extended SemanGit ontology. We perform a set of queries to highlight a subset of the features of this data access approach. The results look positive and can assist various use cases related to GitHub data with a semantic approach. OBDA does provide benefits in practice, such as querying in domain vocabulary and making use of reasoning over the axioms in the ontology. However, the practical impediments we observe are in the “manual” development of a domain ontology and the creation of a mapping specification which requires deep knowledge of a domain and the data. Also, implementing OBDA within the practical context of an information system requires careful consideration for a suitable user interface to facilitate the query construction from ontology vocabulary. Finally, we conclude with a summary of the paper and direction for future research.

@inbook{526,
  author = {Yahlieel Jafta and Louise Leenen and Thomas Meyer},
  title = {Investigating Ontology-Based Data Access with GitHub},
  abstract = {Data analysis-based decision-making is performed daily by domain experts. As data grows, getting access to relevant data becomes a challenge. In an approach known as Ontology-based data access (OBDA), ontologies are advocated as a suitable formal tool to address complex data access. This technique combines a domain ontology with a data source by using a declarative mapping specification to enable data access using a domain vocabulary. We investigate this approach by studying the theoretical background; conducting a literature review on the implementation of OBDA in production systems; implementing OBDA on a relational dataset using an OBDA tool and; providing results and analysis of query answering. We selected Ontop (https://ontop-vkg.org) to illustrate how this technique enhances the data usage of the GitHub community. Ontop is an open-source OBDA tool applied in the domain of relational databases. The implementation consists of the GHTorrent dataset and an extended SemanGit ontology. We perform a set of queries to highlight a subset of the features of this data access approach. The results look positive and can assist various use cases related to GitHub data with a semantic approach. OBDA does provide benefits in practice, such as querying in domain vocabulary and making use of reasoning over the axioms in the ontology. However, the practical impediments we observe are in the “manual” development of a domain ontology and the creation of a mapping specification which requires deep knowledge of a domain and the data. Also, implementing OBDA within the practical context of an information system requires careful consideration for a suitable user interface to facilitate the query construction from ontology vocabulary. Finally, we conclude with a summary of the paper and direction for future research.},
  year = {2023},
  journal = {The Semantic Web},
  volume = {13870},
  pages = {644–660},
  month = {22 May 2023},
  publisher = {Springer, Cham},
  address = {Switzerland},
  isbn = {978-3-031-33455-9},
  doi = {https://doi.org/10.1007/978-3-031-33455-9_38},
}

• Complex time series data often encountered in scientific and engineering domains. • Deep learning (DL) is particularly successful here: – large data sets, multivariate input and/or ouput, – highly complex sequences of interactions. • Model interpretability: – Ability to understand a model’s decisions in a given context [1]. – Techniques typically not originally developed for time series data. – Time series interpretations themselves become uninterpretable. • Knowledge Discovery: – DL has potential to reveal interesting patterns in large data sets. – Potential to produce novel insights about the task itself [2, 3]. • ‘know-it’: Collaborative project that studies knowledge discovery in time series data.

@{507,
  author = {Marelie Davel and Stefan Lotz and Marthinus Theunissen and Almaro De Villiers and Chara Grant and Randle Rabe and Cleo Conacher},
  title = {Knowledge Discovery in Time Series Data},
  abstract = {• Complex time series data often encountered in scientific and engineering domains.
• Deep learning (DL) is particularly successful here:
– large data sets, multivariate input and/or ouput,
– highly complex sequences of interactions.
• Model interpretability:
– Ability to understand a model’s decisions in a given context [1].
– Techniques typically not originally developed for time series data.
– Time series interpretations themselves become uninterpretable.
• Knowledge Discovery:
– DL has potential to reveal interesting patterns in large data sets.
– Potential to produce novel insights about the task itself [2, 3].
• ‘know-it’: Collaborative project that studies knowledge discovery in
time series data.},
  year = {2023},
  journal = {Deep Learning Indaba 2023},
  month = {September 2023},
}

The design of minimum phase finite impulse response (FIR) filters is considered. The study demonstrates that the residual errors achieved by current state-of-the-art design methods are nowhere near the smallest error possible on a finite resolution digital computer. This is shown to be due to conceptual errors in the literature pertaining to what constitutes a factorable linear phase filter. This study shows that factorisation is possible with a zero residual error (in the absence of machine finite resolution error) if the linear operator or matrix representing the linear phase filter is positive definite. Methodology is proposed able to design a minimum phase filter that is optimal—in the sense that the residual error is limited only by the finite precision of the digital computer, with no systematic error. The study presents practical application of the proposed methodology by designing two minimum phase Chebyshev FIR filters. Results are compared to state-of-the-art methods from the literature, and it is shown that the proposed methodology is able to reduce currently achievable residual errors by several orders of magnitude.

@article{506,
  author = {Jan Olivier and Etienne Barnard},
  title = {Minimum phase finite impulse response filter design},
  abstract = {The design of minimum phase finite impulse response (FIR) filters is considered. The study demonstrates that the residual errors achieved by current state-of-the-art design methods are nowhere near the smallest error possible on a finite resolution digital computer. This is shown to be due to conceptual errors in the literature pertaining to what constitutes a factorable linear phase filter. This study shows that factorisation is possible with a zero residual error (in the absence of machine finite resolution error) if the linear operator or matrix representing the linear phase filter is positive definite. Methodology is proposed able to design a minimum phase filter that is optimal—in the sense that the residual error is limited only by the finite precision of the digital computer, with no systematic error. The study presents practical application of the proposed methodology by designing two minimum phase Chebyshev FIR filters. Results are compared to state-of-the-art methods from the literature, and it is shown that the proposed methodology is able to reduce currently achievable residual errors by several orders of magnitude.},
  year = {2023},
  journal = {The Institute of Engineering and Technology},
  volume = {17},
  edition = {7},
  month = {July 2023},
  doi = {https://doi.org/10.1049/sil2.12166},
}

Channel estimation is a critical component of vehicular communications systems, especially in high-mobility scenarios. The IEEE 802.11p standard uses preamble-based channel estimation, which is not sufficient in these situations. Recent work has proposed using deep neural networks for channel estimation in IEEE 802.11p. While these methods improved on earlier baselines they still can perform poorly, especially in very high mobility scenarios. This study proposes a novel approach that uses two independent LSTM cells in parallel and averages their outputs to update cell states. The proposed approach improves normalised mean square error, surpassing existing deep learning approaches in very high mobility scenarios.

@inbook{504,
  author = {Aldrin Ngorima and Albert Helberg and Marelie Davel},
  title = {Sequence Based Deep Neural Networks for Channel Estimation in Vehicular Communication Systems},
  abstract = {Channel estimation is a critical component of vehicular communications systems, especially in high-mobility scenarios. The IEEE 802.11p standard uses preamble-based channel estimation, which is not sufficient in these situations. Recent work has proposed using deep neural networks for channel estimation in IEEE 802.11p. While these methods improved on earlier baselines they still can perform poorly, especially in very high mobility scenarios. This study proposes a novel approach that uses two independent LSTM cells in parallel and averages their outputs to update cell states. The proposed approach improves normalised mean square error, surpassing existing deep learning approaches in very high mobility scenarios.},
  year = {2023},
  journal = {Artificial Intelligence Research. SACAIR 2023. Communications in Computer and Information Science},
  volume = {1976},
  pages = {176 - 186},
  month = {29 November 2023},
  publisher = {Springer, Cham},
  isbn = {978-3-031-49001-9},
  doi = {https://doi.org/10.1007/978-3-031-49002-6_12},
}

In this study we examine the radial dependence of the inertial and dissipation range indices, as well as the spectral break separating the inertial and dissipation range in power density spectra of interplanetary magnetic field fluctuations using Parker Solar Probe data from the fifth solar encounter between ∼0.1 and ∼0.7 au. The derived break wavenumber compares reasonably well with previous estimates at larger radial distances and is consistent with gyro-resonant damping of Alfvénic fluctuations by thermal protons. We find that the inertial scale power-law index varies between approximately −1.65 and −1.45. This is consistent with either the Kolmogorov (−5/3) or Iroshnikov–Kraichnan (−3/2) values, and has a very weak radial dependence with a possible hint that the spectrum becomes steeper closer to the Sun. The dissipation range power-law index, however, has a clear dependence on radial distance (and turbulence age), decreasing from −3 near 0.7 au (4 days) to −4 [±0.3] at 0.1 au (0.75 days) closer to the Sun.

@inbook{503,
  author = {Stefan Lotz and Amore Nel and Robert Wicks and Owen Roberts and Nicholas Engelbrecht and Roelf Strauss and Gert Botha and Eduard Kontar and Alexander Pitňa and Stuart Bale},
  title = {The Radial Variation of the Solar Wind Turbulence Spectra near the Kinetic Break Scale from Parker Solar Probe Measurements},
  abstract = {In this study we examine the radial dependence of the inertial and dissipation range indices, as well as the spectral break separating the inertial and dissipation range in power density spectra of interplanetary magnetic field fluctuations using Parker Solar Probe data from the fifth solar encounter between ∼0.1 and ∼0.7 au. The derived break wavenumber compares reasonably well with previous estimates at larger radial distances and is consistent with gyro-resonant damping of Alfvénic fluctuations by thermal protons. We find that the inertial scale power-law
index varies between approximately −1.65 and −1.45. This is consistent with either the Kolmogorov (−5/3) or Iroshnikov–Kraichnan (−3/2) values, and has a very weak radial dependence with a possible hint that the spectrum becomes steeper closer to the Sun. The dissipation range power-law index, however, has a clear dependence on radial distance (and turbulence age), decreasing from −3 near 0.7 au (4 days) to −4 [±0.3] at 0.1 au (0.75 days) closer to the Sun.},
  year = {2023},
  journal = {The Astrophysical Journal},
  volume = {942},
  edition = {2},
  month = {01/2023},
  publisher = {The American Astronomical Society},
  doi = {10.3847/1538-4357/aca903},
}

Code-switching is a phenomenon that occurs mostly in multilingual countries where multilingual speakers often switch between languages in their conversations. The unavailability of large scale code-switched corpora hampers the development and training of language models for the generation of code-switched text. In this study, we explore the initial phase of collecting and creating Sepedi-English code-switched corpus for generating synthetic news. Radio news and the frequency of code-switching on read news were considered and analysed. We developed and trained a Transformer-based language model using the collected code-switched dataset. We observed that the frequency of code-switched data in the dataset was very low at 1.1%. We complemented our dataset with the news headlines dataset to create a new dataset. Although the frequency was still low, the model obtained the optimal loss rate of 2,361 with an accuracy of 66%.

@article{502,
  author = {Simon Ramalepe and Thipe Modipa and Marelie Davel},
  title = {The Analysis of the Sepedi-English Code-switched Radio News Corpus},
  abstract = {Code-switching is a phenomenon that occurs mostly in multilingual countries where multilingual speakers often switch between languages in
their conversations. The unavailability of large scale code-switched corpora hampers the development and training of language models for the generation of code-switched text. In this study, we explore the initial phase of collecting and creating Sepedi-English code-switched corpus for generating synthetic news. Radio news and the frequency of code-switching on read news were considered and analysed. We developed and trained a Transformer-based language model using the collected code-switched dataset. We observed that the frequency of code-switched data in the dataset was very low at 1.1%. We complemented our dataset with the news headlines dataset to create a new dataset.
Although the frequency was still low, the model obtained the optimal loss rate of 2,361 with an accuracy of 66%.},
  year = {2023},
  journal = {Journal of the Digital Humanities Association of Southern Africa},
  volume = {4},
  edition = {1},
  month = {2023-01-25},
  issue = {Vol. 4 No. 01 (2022): Proceedings of the 3rd workshop on Resources for African Indigenous Languages (RAIL)},
  doi = {https://doi.org/10.55492/dhasa.v4i01.4444},
}

Code-switched data is rarely available in written form and this makes the development of large datasets required to train codeswitched language models difficult. Currently, available Sepedi-English code-switched corpora are not large enough to train a Transformer-based model for this language pair. In prior work, larger synthetic datasets have been constructed using a combination of a monolingual and a parallel corpus to approximate authentic code-switched text. In this study, we develop and analyse a new Sepedi-English news dataset (SepEnews). We collect and curate data from local radio news bulletins and use this to augment two existing sources collected from Sepedi newspapers and news headlines, respectively. We then develop and train a Transformer-based model for generating historic code-switched news, and demonstrate and analyse the system’s performance.

@{501,
  author = {Simon Ramalepe and Thipe Modipa and Marelie Davel},
  title = {Transformer-based text generation for code-switched Sepedi-English news},
  abstract = {Code-switched data is rarely available in written form and this makes the development of large datasets required to train codeswitched language models difficult. Currently, available Sepedi-English code-switched corpora are not large enough to train a Transformer-based
model for this language pair. In prior work, larger synthetic datasets have been constructed using a combination of a monolingual and a parallel
corpus to approximate authentic code-switched text. In this study, we develop and analyse a new Sepedi-English news dataset (SepEnews). We collect and curate data from local radio news bulletins and use this to augment two existing sources collected from Sepedi newspapers and news headlines, respectively. We then develop and train a Transformer-based model for generating historic code-switched news, and demonstrate and analyse the system’s performance.},
  year = {2023},
  journal = {Southern African Conference for Artificial Intelligence Research (SACAIR)},
  pages = {84 - 97},
  month = {December 2023},
}

Heterogeneous tabular data is a common and important data format. This empirical study investigates how the performance of deep transformer models compares against benchmark gradient boosting decision tree (GBDT) methods, the more typical modelling approach. All models are optimised using a Bayesian hyperparameter optimisation protocol, which provides a stronger comparison than the random grid search hyperparameter optimisation utilized in earlier work. Since feature skewness is typically handled differently for GBDT and transformer-based models, we investigate the effect of a pre-processing step that normalises feature distribution on the model comparison process. Our analysis is based on the Rossmann Store Sales dataset, a widely recognized benchmark for regression tasks.

@{500,
  author = {Coenraad Middel and Marelie Davel},
  title = {Comparing Transformer-based and GBDT models on tabular data: A Rossmann Store Sales case study},
  abstract = {Heterogeneous tabular data is a common and important data format. This empirical study investigates how the performance of deep transformer models compares against benchmark gradient boosting decision tree (GBDT) methods, the more typical modelling approach. All models are optimised using a Bayesian hyperparameter optimisation protocol, which provides a stronger comparison than the random grid search hyperparameter optimisation utilized in earlier work. Since feature skewness is typically handled differently for GBDT and transformer-based models, we investigate the effect of a pre-processing step that normalises feature distribution on the model comparison process. Our analysis is based on the Rossmann Store Sales dataset, a widely recognized benchmark for regression tasks.},
  year = {2023},
  journal = {Southern African Conference for Artificial Intelligence Research (SACAIR)},
  pages = {115 - 129},
  month = {December 2023},
}