Noncoherent MIMO codes for low-medium SNRs, and layered MIMO space-time coding for coherent and noncoherent receivers by ElMossallamy, Mohamed Ali

“…Wireless communication systems rely on training the receiver to learn the channel state information (CSI) to communicate information effectively. …”
Get full text
Get full text

A comparative study of recurrent neural networks and statistical techniques for forecasting the stock prices of JSE-listed securities by Galant, Rushin

“…Historical data was collected for the period 2 January 2019 to 29 May 2020, with the 2019 calendar year being used as the training dataset. Both a train once and a Walkforward configuration were used. …”
Get full text

Price Prediction Models of Metals Considering International Crises by Ghali, Haidy

“…Then, the LSTM models are developed for each metal, and the dataset is divided into training, validation, and testing sets and mean square errors, root mean square errors, and absolute percentage errors are used to assess the model’s performance. …”
Get full text
Get full text

A comparison of Gaussian mixture variants with application to automatic phoneme recognition by Brand, Rinus

Get full text

Measuring, refining and calibrating speaker and language information extracted from speech by Brummer, Niko

Get full text

Cape Town road traffic accident analysis: Utilising supervised learning techniques and discussing their effectiveness by Du Toit, Christo

“…The RTA data was split into training, validation and test sets keeping the proportions of the injury-severity category consistent. …”
Get full text

Determination of chromic acid and sodium dichromate in a concentrated electrolytic solution with the aid of Artificial Neural Networks

Get full text
Get full text

Incorporating sensor measurements using data assimilation and machine learning to improve the accuracy of thermal finite element models

Get full text
Get full text

Fitness landscape analysis of feed-forward neural networks

Get full text

An investigation into the dynamic implementation of a 16-electrode FDM Electrical Impedance Tomography System by Goldswain, Gareth

“…Specifically, KRR's mean absolute prediction error was less than 1 % of the vessel's cross-sectional area. …”
Get full text

Driving factors for national competitiveness in Africa as measured by GDP per capita

Get full text

Proprioception, jumping capacity and agility in beach versus indoor volleyball players by Glossop-von Hirschfeld, Christine

“…If eligible to continue to take part in the study, participants completed two questionnaires (Training and Injury History questionnaire and OSTRC (Oslo Sports Trauma Research Centre) questionnaire), after which they completed seven physical tests (the wedge test, two-point discrimination test, modified balance error scoring system (mBESS) test, modified star excursion balance test (mSEBT), knee-to-wall test, single leg hamstring bridge test (SLHBT) and eccentric-concentric calf raise test). …”
Get full text

The prevalence and characteristics of chronic musculoskeletal pain in adult triathletes in South Africa by Francis, Glenda Chantelle

“…Apart from swimming, where those with pain were spending significantly longer training, the respondents showed no significant differences in training history or training characteristics. …”
Get full text

The prevalence of substance use in anaesthesia practitioners in South Africa by van Der Westhuizen, Justine

“…Years of experience and level of training were explored as possible risk factors for hazardous or harmful use. …”
Get full text

Short-term sea level forecasting using machine learning techniques: A case study for South Africa by Ingreso, Maria Kristina

“…Model performance was measured using the correlation coefficient (R), the root mean square error (RMSE), the bias and the Willmott indices of correlation. …”
Get full text

Robust voice activity detection for low-resource automatic speech recognition by Wilkinson, Nicholas

Get full text

Improving counting performance of densely flocked sheep in aerial imagery by Biggs, D. R.

Get full text

LSTM prediction capability on the South African JSE Top 40 of historical and live data by Elhag, Mohsen

“…Various LSTM models were trained with different configurations, and the results show that a single-layer LSTM model performs better than its multilayer counterpart in processing historical data, in terms of the mean absolute error (MAE), the root mean square error (RMSE), Mean Absolute Percentage Error (MAPE) and the R-squared. …”
Get full text

Adaptive digital image correlation using neural networks by Atkinson, Devan James

Get full text