Master thesis is focused on optimization of cogeneration system for purpose of rating optimization methods and evaluating properties of these methods. For each method there is description together with block schemes. First part of thesis is devoted to description of methods and their comparison. Second part consists of development of hybrid algorithm, which is used to optimize cogeneration systém model. Each algorithm compared is together with hybrid algorithms included in annexes.

This work deals with particle swarm optimization. The theoretic part briefly describes the problem of optimization. The considerable part focuses on the overall description of particle swarm optimization (PSO). The principle, behavior, parameters, structure and modifications of PSO are described. The next part of the work is a recherché of variants of PSO, including hybridizations of PSO. In practical part the dynamic problems are analyzed and new designed algorithm for dynamic problems AHPSO is described (what it is based on, what was inspired, what elements are used and why). Algorithm is executed on the set of tasks (Moving peaks benchmark) and compared with the best publicly available variants of algorithm PSO on dynamic problems so far.

This master's thesis is about nature optimalization technigues. Evolution algortihms together with main thesis topic, Particle Swarm Optimization, is introduced in the following chapter. Car setup and simulator TORCS are introduced in next chapter. Design and implementation are introduced in next chapters. Destination of t master's thesis is finding optimal car setups for different curcuits.

Computational Intelligence has found a challenging testbed for various paradigms in the financial sector. Extensive research has resulted in numerous financial applications using neural networks and evolutionary computation, mainly genetic algorithms and genetic programming. More recent advances in the field of computational intelligence have not yet been applied as extensively or have not become available in the public domain, due to the confidentiality requirements of financial institutions. This study investigates how co-evolution together with the combination of par- ticle swarm optimisation and neural networks could be used to discover competitive security trading agents that could enable the timing of buying and selling securities to maximise net profit and minimise risk over time. The investigated model attempts to identify security trend reversals with the help of technical analysis methodologies. Technical market indicators provide the necessary market data to the agents and reflect information such as supply, demand, momentum, volatility, trend, sentiment and retracement. All this is derived from the security price alone, which is one of the strengths of technical analysis and the reason for its use in this study. The model proposed in this thesis evolves trading strategies within a single pop- ulation of competing agents, where each agent is represented by a neural network. The population is governed by a competitive co-evolutionary particle swarm optimi- sation algorithm, with the objective of optimising the weights of the neural networks. A standard feed forward neural network architecture is used, which functions as a market trend reversal confidence. Ultimately, the neural network becomes an amal- gamation of the technical market indicators used as inputs, and hence is capable of detecting trend reversals. Timely trading actions are derived from the confidence output, by buying and short selling securities when the price is expected to rise or fall respectively. No expert trading knowledge is presented to the model, only the technical market indicator data. The co-evolutionary particle swarm optimisation model facilitates the discovery of favourable technical market indicator interpretations, starting with zero knowledge. A competitive fitness function is defined that allows the evaluation of each solution relative to other solutions, based on predefined performance metric objectives. The relative fitness function in this study considers net profit and the Sharpe ratio as a risk measure. For the purposes of this study, the stock prices of eight large market capitalisation companies were chosen. Two benchmarks were used to evaluate the discovered trading agents, consisting of a Bollinger Bands/Relative Strength Index rule-based strategy and the popular buy-and-hold strategy. The agents that were discovered from the proposed hybrid computational intelligence model outperformed both benchmarks by producing higher returns for in-sample and out-sample data at a low risk. This indicates that the introduced model is effective in finding favourable strategies, based on observed historical security price data. Transaction costs were considered in the evaluation of the computational intelligent agents, making this a feasible model for a real-world application. Copyright / Dissertation (MSc)--University of Pretoria, 2010. / Computer Science / unrestricted

Real-world optimisation problems often are of a dynamic nature. Recently, much research has been done to apply particle swarm optimisation (PSO) to dynamic environments (DE). However, these research efforts generally focused on optimising one variation of the PSO algorithm for one type of DE. The aim of this work is to develop a more comprehensive view of PSO for DEs. This thesis studies different schemes of characterising and taxonomising DEs, performance measures used to quantify the performance of optimisation algorithms applied to DEs, various adaptations of PSO to apply PSO to DEs, and the effectiveness of these approaches on different DE types. The standard PSO algorithm has shown limitations when applied to DEs. To overcome these limitations, the standard PSO can be modi ed using personal best reevaluation, change detection and response, diversity maintenance, or swarm sub-division and parallel tracking of optima. To investigate the strengths and weaknesses of these approaches, a representative sample of algorithms, namely, the standard PSO, re-evaluating PSO, reinitialising PSO, atomic PSO (APSO), quantum swarm optimisation (QSO), multi-swarm, and self-adapting multi-swarm (SAMS), are empirically analysed. These algorithms are analysed on a range of DE test cases, and their ability to detect and track optima are evaluated using performance measures designed for DEs. The experiments show that QSO, multi-swarm and reinitialising PSO provide the best results. However, the most effective approach to use depends on the dimensionality, modality and type of the DEs, as well as on the objective of the algorithm. A number of observations are also made regarding the behaviour of the swarms, and the influence of certain control parameters of the algorithms evaluated. Copyright / Dissertation (MSc)--University of Pretoria, 2012. / Computer Science / unrestricted

Groups of starlings can form impressive shapes as they travel northward together in the springtime. This is among a group of natural phenomena based on swarm behaviour. The research field of artificial intelligence in computer science, particularly the areas of robotics and image processing, has in recent decades given increasing attention to the underlying structures. The behaviour of these intelligent swarms has opened new approaches for face detection as well. G. Beni and J. Wang coined the term “swarm intelligence” to describe this type of group behaviour. In this context, intelligence describes the ability to solve complex problems. The objective of this project is to automatically find exactly one face on a photo or video material by means of swarm intelligence. The process developed for this purpose consists of a combination of various known structures, which are then adapted to the task of face detection. To illustrate the result, a 3D hat shape is placed on top of the face using an example application program.:1 Introduction 1.1 Face Detection 1.2 Swarm Intelligence and Particle Swarm Optimisation Fundamentals 3 Face Detection by Means of Particle Swarm Optimisation 3.1 Swarms and Particles 3.2 Behaviour Patterns 3.2.1 Opportunism 3.2.2 Avoidance 3.2.3 Other Behaviour Patterns 3.3 Stop Criterion 3.4 Calculation of the Solution 3.5 Example Application 4 Summary and Outlook

Die Optimierung spielt in der Industrie und Technik eine entscheidende Rolle. Für einen Betrieb ist es beispielsweise äußerst wichtig, die zur Verfügung stehenden Ressourcen optimal zu nutzen und Betriebsabläufe effizient zu gestalten. Damit diese Vorhaben umgesetzt werden können, setzt man Methoden der Optimierung ein. Die Zielstellungen werden als eine abstrakte mathematische Aufgabe formuliert und anschließend wird versucht, dieses Problem mit einem Optimierungsverfahren zu lösen. Da die Komplexität der Problemstellungen in der Praxis ansteigt, sind exakte Verfahren in der Regel nicht mehr effizient anwendbar, sodass andere Methoden zum Lösen dieser Aufgaben entwickelt werden müssen, die in angemessener Zeit eine akzeptable Lösung finden. Solche Methoden werden als Approximationsalgorithmen bezeichnet. Im Gegensatz zu den exakten Verfahren ist der Verlauf der Optimierung bei dieser Verfahrensklasse vom Zufall abhängig. Dadurch lassen sich in der Regel keine Konvergenzaussagen beweisen. Dennoch hat sich gezeigt, dass Approximationsalgorithmen viel versprechende Ergebnisse für eine Vielzahl von unterschiedlichen Problemstellungen liefern. Zwei Approximationsalgorithmen werden in dieser Arbeit vorgestellt, untersucht und erweitert. Zum einen steht ein Verfahren im Vordergrund, welches aus Beobachtungen in der Natur entstanden ist. Es gibt Lebewesen, die durch verblüffend einfache Strategien in der Lage sind, komplexe Probleme zu lösen. Beispielsweise bilden Fische Schwärme, um sich vor Fressfeinden zu schützen. Der Fischschwarm kann dabei als selbstorganisierendes System verstanden werden, bei dem die Aktivitäten der einzelnen Fische hauptsächlich von den Bewegungen der Nachbarfische abhängig sind. An diesem erfolgreichen Schwarmverhalten ist der moderne Approximationsalgorithmus der Partikelschwarmoptimierung angelehnt. Weiterhin wird ein ersatzmodellgestütztes Verfahren präsentiert. Der Ausgangspunkt dieses Optimierungsverfahrens ist der Aufbau von Ersatzmodellen, um das Verhalten der Zielfunktionen anhand der bisherigen Auswertungen vorhersagen zu können. Damit so wenig wie möglich Funktionsauswertungen vorgenommen werden müssen, wird bei diesem Verfahren ein hoher Aufwand in die Wahl der Punkte investiert, welche auszuwerten sind. Die vorliegende Diplomarbeit gliedert sich wie folgt. Zunächst werden die mathematischen Grundlagen für das Verständnis der weiteren Ausführungen gelegt. Insbesondere werden multikriterielle Optimierungsaufgaben betrachtet und klassische Lösungsansätze aufgezeigt. Das dritte Kapitel beschäftigt sich mit der Partikelschwarmoptimierung. Dieser „naturanaloge Approximationsalgorithmus“ wird ausführlich dargelegt und analysiert. Dabei stehen die Funktionsweise und der Umgang mit mehreren Zielen und Restriktionen im Vordergrund der Ausarbeitung. Ein ersatzmodellgestütztes Optimierungsverfahren wird im Anschluss darauf vorgestellt und erweitert. Neben der Verfahrensanalyse, ist die Behebung der vorhandenen Schwachstellen ein vorrangiges Ziel dieser Untersuchung. Die eingeführten und implementierten Verfahren werden im fünften Kapitel an geeigneten analytischen und technischen Problemen verifiziert und mit anderen Approximationsalgorithmen verglichen. Anschließend werden Empfehlungen für die Verwendung der Verfahren gegeben. Die gewonnenen Kenntnisse werden im letzten Kapitel zusammengefasst und es wird ein Ausblick für zukünftige Forschungsthemen gegeben

Streamed data classification problems (SDCPs) require classifiers with the ability to learn and to adjust to the underlying relationships in data streams, in real-time. This requirement poses a challenge to classifiers, because the learning task is no longer just to find the optimal decision boundaries, but also to track changes in the decision boundaries as new training data is received. The challenge is due to concept drift, i.e. the changing of decision boundaries over time. Changes include disappearing, appearing, or shifting decision boundaries. This thesis proposes an online learning approach for feed forward neural networks (FFNNs) that meets the requirements of SDCPs. The approach uses regularisation to optimise the architecture via the weights, and quantum particle swarm optimisation (QPSO) to dynamically adjust the weights. The learning approach is applied to a FFNN, which uses rectified linear activation functions, to form a novel SDCP classifier. The classifier is empirically investigated on several SDCPs. Both weight decay (WD) and weight elimination (WE) are investigated as regularisers. Empirical results show that using QPSO with no regularisation, causes the classifier to completely saturate. However, using QPSO with regularisation enables the classifier to dynamically adapt both its implicit architecture and weights as decision boundaries change. Furthermore, the results favour WE over WD as a regulariser for QPSO. / Dissertation (MSc)--University of Pretoria, 2020. / National Research Foundation (NRF) / Computer Science / MSc / Unrestricted

In the process industries, cooling capacity is an important enabler for the facility to manufacture on specification product. The cooling water network is an important part of the over-all cooling system of the facility. In this research a cooling water circuit consisting of 3 cooling towers in parallel, 2 cooling water pumps in parallel, and 11 heat exchangers in parallel, is modelled. The model developed is based on first principles and captures the dynamic, non-linear, interactive nature of the plant. The modelled plant is further complicated by continuous, as well as discrete process variables, giving the model a hybrid nature. Energy consumption is included in the model as it is a very important parameter for plant operation. The model is fitted to real industry data by using a particle swarm optimisation approach. The model is suitable to be used for optimisation and control purposes. Cooling water networks are often not instrumented and actuated, nor controlled or optimised. Significant process benefits can be achieved by better process end-user temperature control, and direct monetary benefits can be obtained from electric power minimisation. A Hybrid Non-Linear Model Predictive Control strategy is developed for these control objectives, and simulated on the developed first principles dynamic model. Continuous and hybrid control cases are developed, and tested on process scenarios that reflect conditions seen in a real plant. Various alternative techniques are evaluated in order to solve the Hybrid Non-Linear Control problem. Gradient descent with momentum is chosen and configured to be used to solve the continuous control problem. For the discrete control problem a graph traversal algorithm is developed and joined to the continuous control algorithm to form a Hybrid Non-Linear Model Predictive controller. The potential monetary benefits that can be obtained by the plant owner through implementing the designed control strategy, are estimated. A powerful computation platform is designed for the plant model and controller simulations. / Thesis (PhD)--University of Pretoria, 2019. / Electrical, Electronic and Computer Engineering / PhD / Unrestricted

Particle Swam Optimization (PSO) is especially useful for rapid optimization of problems involving multiple objectives and constraints in dynamic environments. It regularly and substantially outperforms other algorithms in benchmark tests. This paper describes research leading to the application of PSO to the autonomous asset management problem in electronic warfare. The PSO speed provides fast optimization of frequency allocations for receivers and jammers in highly complex and dynamic environments. The key contribution is the simultaneous optimization of the frequency allocations, signal priority, signal strength, and the spatial locations of the assets. The fitness function takes into account the assets' locations in 2 dimensions, maximizing their spatial distribution while maintaining allocations based on signal priority and power. The fast speed of the optimization enables rapid responses to changing conditions in these complex signal environments, which can have real-time battlefield impact. Results optimizing receiver frequencies and locations in 2 dimensions have been successful. Current run-times are between 450ms (3 receivers, 30 transmitters) and 1100ms (7 receivers, 50 transmitters) on a single-threaded x86 based PC. Run-times can be substantially decreased by an order of magnitude when smaller swarm populations and smart swarm termination methods are used, however a trade off exists between run-time and repeatability of solutions. The results of the research on the PSO parameters and fitness function for this problem are demonstrated.