An Epileptic Seizure Detection Method from EEG Signals based on a Classifier-Driven Feature Reduction Technique by Kamel, Raymond N.

“…This thesis work aims to develop a robust and stable algorithm for epileptic seizure detection through the classification of EEG signals. …”
Get full text
Get full text

Optimal allocation of distributed generation for power loss reduction and voltage profile improvement by Oluwole, Osaloni Oluwafunso

“…The majority of the proposed algorithms emphasize real power losses only in their formulations. …”
Get full text

Screening for Proteinopathic-related Dementias in Low-resource Clinical Contexts: A Machine Learning Approach by Lewis, Raphaella

“…Information from 20 clinical variables were used as features for the analysis. We used C5.0 algorithms to identify the most important features for PRD diagnosis and to derive an algorithm that could accurately diagnose these types of dementia. …”
Get full text

Market state discovery by Singo, Unarine

“…Furthermore, ASPC does not rely on the art of selecting good hyper-parameters such as, the number of states a priori. ICC's utility as a market state discovery algorithm is limited.…”
Get full text

Automatic building footprint extraction using remote sensing data within the City of Cape Town

Get full text

AN EFFICIENT INTERFERENCE AVOIDANCE SCHEME FOR DEVICE-TODEVICE ENABLED FIFTH GENERATION NARROWBAND INTERNET OF THINGS NETWOKS’ by unknown

“…Various existing interference mitigation solutions either add to the network's overhead, computational complexity and delay or are hampered by low data rate and coverage. These algorithms are unsuitable for an NB-IoT network owing to the low-complexity nature. …”
Get full text

Reconstruction of Functions From Non-uniformly Distributed Sampled Data in Shift-Invariant Frame Subspaces by Mkhaliphi, Mkhuseli Bruce

“…The impact of additive white Gaussian noise on the performance of the two algorithms is also investigated. The numerical tools utilized in this research consist of the theory of discrete irregular sampling, frames, and iterative techniques. …”
Get full text

Joint call admission control incorporating pricing for congestion control to enhance QoS and ensure revenue for network operators in next generation wireless networks by Kabahuma, Sarah

“…An analytical model based on a multi-dimensional Markov decision process is used to model JCAC algorithm in an NGWN. The JCAC algorithm used is load-based whereby calls arriving in the network are admitted to the least loaded RATs. …”
Get full text

SdrLift: A Domain-Specific Intermediate Hardware Synthesis Framework for Prototyping Software-Defined Radios by Tsoeunyane, Lekhobola Joachim

“…In order to alleviate these problems, Domain-Specific Languages (DSL) have been introduced to capture algorithms at a high level of abstraction with more expressive power and providing domain-specific optimizations that factor in new transformations and the trade-off between resource utilization and system performance. …”
Get full text

Non-intrusive efficiency estimation of induction machines under various power supplies by Gajjar, Chetan Sudhir

“…Coupled with vibration sensors used to determine a motor's speed, measured input voltages and currents are used to deduce a machine efficiency-load profile through the use of a modified evolutionary algorithm, the Non-Intrusive Efficiency Estimation using Population-Based Incremental Learning(NIEE-PBIL) algorithm. …”
Get full text

An Optimized LTE-Based Technique for Drone Base Station 3D Placement and Resource Allocation in Delay-Sensitive M2M Networks by Fahim, Ahmed

“…The proposed exact optimization algorithm utilizes the outer-approximation technique along with the penalty method in search of the global optimal point in the problem feasible space. …”
Get full text
Get full text

Distributed binary decision diagrams by Fasan, Mary Oluwasola

Get full text

Development of scalable hybrid switching-based software-defined networking using reinforcement learning by Blose, Max

“…We are therefore of the opinion that the hybrid switching model proposed utilizing machine learning algorithms can address the scalability issues in the design of SDN controller networks, particularly in data centre environments where high switching speeds are of paramount importance.…”
Get full text

Development of scalable hybrid switching-based software-defined networking using reinforcement learning by Blose, Max

“…We are therefore of the opinion that the hybrid switching model proposed utilizing machine learning algorithms can address the scalability issues in the design of SDN controller networks, particularly in data centre environments where high switching speeds are of paramount importance.…”
Get full text

Energy management of micro-grid using cooperative game theory by Oladejo, Ismaheel Oyeyemi

“…This is in contrast with other heuristic algorithms such as genetic algorithm (GA) and particle swarm optimization (PSO) that require other control parameters (i.e. …”
Get full text

Phytoplankton community structure determined through remote sensing and in situ optical measurements by Evers-King, Hayley Louise

Get full text

Robust control of a triple-effect evaporator

Get full text

The impact of voltage unbalance and regulation on the life expectancy of LV induction machines by Mponwana, Samuel

“…The quality of supply from power utilities can lead to them being operated under unbalanced voltage conditions. …”
Get full text

Person of interest rapid identification and tracking (POIRIT) assistance system by Arif, Danish

“…Additionally, the research considers environmental factors like fog and smog, incorporating the Retinex Algorithm with Wavelet transform for effective fog removal. …”
Get full text

Exploring the potential of using unmanned aerial system imageries in managing the Miombo woodlands of Zambia

Get full text
Get full text