Terence van Zyl (0000-0003-4281-630X)

Personal information

Biography

I am interested in data science research pertaining to anomaly detection, predictive analytics, signal/image processing, streaming data analytics, machine learning, and data-intensive computing to deal with these spatial and temporal big data challenges. The applications can range anywhere from novel insights about our planet to disruptive technologies that change our world.

Activities

Collapse all

University of Johannesburg: Auckland Park, Gauteng, ZA

2020-07-01 to present | Professor - Nedbank Chair (Institute for Intelligent Systems)

Employment

Terence van Zyl

https://orcid.org/0000-0003-4281-630X

Personal information

Websites & social links

Other IDs

Countries

Biography

Activities

Employment (2)

University of Johannesburg: Auckland Park, Gauteng, ZA

University of the Witwatersrand: Johannesburg-Braamfontein, Gauteng, ZA

Education and qualifications (1)

University of Johannesburg: Johannesburg, Gauteng, ZA

Professional activities (1)

University of the Witwatersrand: Johannesburg-Braamfontein, Gauteng, ZA

Works (50 of 108)

Deep Learning Forecasting of Photovoltaics Output Using Digital Twin Data

Deep Learning-Based Network Intrusion Detection Systems: A Systematic Literature Review

Enhancing Credit Risk Assessment Through Transformer-Based Machine Learning Models

Price Gaps and Volatility: Do Weekend Gaps Tend to Close?

Impacts of Architectural Enhancements on Sequential Recommendation Models

Improving Semi-supervised Learning in Generative Adversarial Networks Using Variational AutoEncoders

Unit-Based Genetic Algorithmic Approach for Optimal Multipurpose Batch Plant Scheduling

Viability of Convolutional Variational Autoencoders for Lifelong Class Incremental Similarity Learning

Surrogate-assisted hyper-parameter search for portfolio optimisation: multi-period considerations

A Learnheuristic Approach to A Constrained Multi-Objective Portfolio Optimisation Problem

Machine Learning for Socially Responsible Portfolio Optimisation

A Statistics and Deep Learning Hybrid Method for Multivariate Time Series Forecasting and Mortality Modeling

An Empirical Comparison of Cross-Validation Procedures for Portfolio Selection

Deep Reinforcement Learning and Convex Mean-Variance Optimisation for Portfolio Management

Evaluating State of the Art, Forecasting Ensembles-and Meta-learning Strategies for Model Fusion

Full Rotation Hyper-ellipsoid Multivariate Adaptive Bandwidth Kernel Density Estimator

Fusion of Sentiment and Asset Price Predictions for Portfolio Optimization

Improving Cause-of-Death Classification from Verbal Autopsy Reports

Investigating Explainability Methods in Recurrent Neural Network Architectures for Financial Time Series Data

Investigating Transfer Learning in Graph Neural Networks

Knowledge Graph Fusion for Language Model Fine-tuning

Multi-modal Recommendation System with Auxiliary Information

Multivariate anomaly detection based on prediction intervals constructed using deep learning

Statistics and Deep Learning-based Hybrid Model for Interpretable Anomaly Detection

Surrogate-assisted evolutionary multi-objective optimisation applied to a pressure swing adsorption system

Surrogate-assisted strategies: the parameterisation of an infectious disease agent-based model

Towards a Methodology for Addressing Missingness in Datasets, with an Application to Demographic Health Datasets

Transfer Learning and Deep Metric Learning for Automated Galaxy Morphology Representation

Twin-Delayed Deep Deterministic Policy Gradient Algorithm for Portfolio Selection

Using Machine Learning to Fuse Verbal Autopsy Narratives and Binary Features in the Analysis of Deaths from Hyperglycaemia

Evaluating State-of-the-Art, Forecasting Ensembles and Meta-Learning Strategies for Model Fusion

AMA-K: Aggressive Multi-temporal Allocation with K Experts for Online Portfolio Selection

Comparing class-aware and pairwise loss functions for deep metric learning in wildlife re-identification

Comparing CNN Architectures for Land Cover Classification on Multispectral Images

ConVAEr: Convolutional Variational AutoEncodeRs for incremental similarity learning

Deep learning for financial time series forecast fusion and optimal portfolio rebalancing

Deep Similarity Learning for Sports Team Ranking

Deep/Transfer Learning with Feature Space Ensemble Networks (FeatSpaceEnsNets) and Average Ensemble Networks (AvgEnsNets) for Change Detection Using DInSAR Sentinel-1 and Optical Sentinel-2 Satellite Data Fusion

Determining real-time patterns of lightning strikes from sensor observations

Did we produce more waste during the covid-19 lockdowns? a remote sensing approach to landfill change analysis

Feature-weighted Stacking for Nonseasonal Time Series Forecasts: A Case Study of the COVID-19 Epidemic Curves

Incremental Class Learning using Variational Autoencoders with Similarity Learning

MA-FDRNN: Multi-asset fuzzy deep recurrent neural network reinforcement learning for portfolio management

Modeling E-Behaviour, Personality and Academic Performance with Machine Learning

Parden: Surrogate assisted hyper-parameter optimisation for portfolio selection

Surrogate Parameters Optimization for Data and Model Fusion of COVID-19 Time-series Data

The efficient frontiers of mean-variance portfolio rules under distribution misspecification

A Comparative Study of Ensemble Approaches to Fact-Checking for the FEVER Shared Task

A framework for online investment decisions

A method for dissolved gas forecasting in power transformers using ls-svm