Real-world optimisation problems are often very complex. Population-based metaheuristics, such as evolutionary algorithms and particle swarm optimisation (PSO) algorithms, have been successful in solving many of these problems, but it is well known that they sometimes fail. Over the last few decades the focus of research in the field has been largely on the algorithmic side with relatively little attention being paid to the study of the problems. Questions such as ‘Which algorithm will most accurately solve my problem?’ or ‘Which algorithm will most quickly produce a reasonable answer to my problem?’ remain unanswered. This thesis contributes to the understanding of optimisation problems and what makes them hard for algorithms, in particular PSO algorithms. Fitness landscape analysis techniques are developed to characterise continuous optimisation problems and it is shown that this characterisation can be used to predict PSO failure. An essential feature of this approach is that multiple problem characteristics are analysed together, moving away from the idea of a single measure of problem hardness. The resulting prediction models not only lead to a better understanding of the algorithms themselves, but also takes the field a step closer towards the goal of informed decision-making where the most appropriate algorithm is chosen to solve any new complex problem. / Thesis (PhD)--University of Pretoria, 2014. / Computer Science / unrestricted

Yes / A compact planar monopole antenna is proposed for ultra-wideband applications. The antenna has a microstrip line feed and band-rejected characteristics and consists of a ring patch and partial ground plane with a defective ground structure of rectangular shape. An annular strip is etched above the radiating element and two slots, one C-shaped and one arc-shaped, are embedded in the radiating patch. The proposed antenna has been optimized using bio-inspired algorithms, namely Particle Swarm Optimization and the Firefly Algorithm, based on a new software algorithm (Antenna Optimizer). Multi-objective optimization achieves rejection bands at 3.3 to 3.7 GHz for WiMAX, 5.15 to 5.825 GHz for the 802.11a WLAN system or HIPERLAN/2, and 7.25 to 7.745 GHz for C-band satellite communication systems. Validated results show wideband performance from 2.7 to 10.6 GHz with S11 ˂ -10 dB. The antenna has compact dimensions of 28 × 30 mm2. The radiation pattern is comparatively stable across the operating band with a relatively stable gain except in the notched bands. / This work was supported in part by the United Kingdom Engineering and Physical Science Research Council (EPSRC) under Grant EP/E022936A, TSB UK under grant application KTP008734 and the Iraqi Ministry of Higher Education and Scientific Research.

Yes / Owing to the high specific energy consumption associated with thermal desalination technologies such as Multi Effect Distillation (MED), there is a wide interest to develop a cost-effective desalination technology. This study focuses on improving the operational, economic, and environmental perspectives of hybrid MED-TVC (thermal vapour compression) process via optimisation. Application of particle swarm optimisation (PSO) in several engineering disciplines have been noted but its potential has not been exploited fully in desalination technologies especially MED-TVC in the past. A multi-objective non-linear optimisation framework based on PSO is constructed here. Two of our earlier models have been used to predict the key process performance and cost indicators. The models are embedded within the PSO optimisation algorithm to develop a new hybrid optimisation model which minimises the total freshwater production cost, total specific energy consumption and brine flow rate while maintaining a fixed freshwater production for a given number of effects and seawater conditions. The steam flow rate and temperature are considered as control variables of the optimisation problem to achieve the objective function. The PSO has successfully achieved the optimum indexes for the hybrid MED-TVC process for a wide range of number of effects. It also shows a maximum reduction of freshwater production cost by 36.5%, a maximum energy saving by 32.1% and a maximum reduction of brine flow rate by 38.3%, while maintaining the productivity of freshwater.

Yes / Speed optimization of liner vessels has significant economic and environmental impact for reducing fuel cost and Green House Gas (GHG) emission as the shipping over maritime logistics takes more than 70% of world transportation. While slow steaming is widely used as best practices for liner shipping companies, they are also under the pressure to maintain service level agreement (SLA) with their cargo clients. Thus, deciding optimal speed that minimizes fuel consumption while maintaining SLA is managerial decision problem. Studies in the literature use theoretical fuel consumption functions in their speed optimization models but these functions have limitations due to weather conditions in voyages. This paper uses weather archive data to estimate the real fuel consumption function for speed optimization problems. In particular, Copernicus data set is used as the source of big data and data mining technique is applied to identify the impact of weather conditions based on a given voyage route. Particle swarm optimization, a metaheuristic optimization method, is applied to find Pareto optimal solutions that minimize fuel consumption and maximize SLA. The usefulness of the proposed approach is verified through the real data obtained from a liner company and real world implications are discussed.

Yes / Aggressive posts containing symbolic and offensive images, inappropriate gestures along with provocative textual comments are growing exponentially in social media with the availability of inexpensive data services. These posts have numerous negative impacts on the reader and need an immediate technical solution to filter out aggressive comments. This paper presents a model based on a Convolutional Neural Network (CNN) and Binary Particle Swarm Optimization (BPSO) to classify the social media posts containing images with associated textual comments into non-aggressive, medium-aggressive and high-aggressive classes. A dataset containing symbolic images and the corresponding textual comments was created to validate the proposed model. The framework employs a pre-trained VGG-16 to extract the image features and a three-layered CNN to extract the textual features in parallel. The hybrid feature set obtained by concatenating the image and the text features were optimized using the BPSO algorithm to extract the more relevant features. The proposed model with optimized features and Random Forest classifier achieves a weighted F1-Score of 0.74, an improvement of around 3% over unoptimized features.

This thesis investigates the task of estimating the pose of a hand interacting with an object from a depth image. The main contribution of this thesis is the development of our discriminative one-shot hand-object pose estimation system. To the best of our knowledge, this is the first attempt at a one-shot hand-object pose estimation system. It is a two stage system consisting of convolutional neural networks. The first stage segments the object out of the hand from the depth image. This hand-minus-object depth image is combined with the original input depth image to form a 2-channel image for use in the second stage, pose estimation. We show that using this 2-channel image produces better pose estimation performance than a single stage pose estimation system taking just the input depth map as input. We also believe that we are amongst the first to research hand-object segmentation. We use fully convolutional neural networks to perform hand-object segmentation from a depth image. We show that this is a superior approach to random decision forests for this task. Datasets were created to train our hand-object pose estimator stage and hand-object segmentation stage. The hand-object pose labels were estimated semi-automatically with a combined manual annotation and generative approach. The segmentation labels were inferred automatically with colour thresholding. To the best of our knowledge, there were no public datasets for these two tasks when we were developing our system. These datasets have been or are in the process of being publicly released.

Replacing humans with underwater robots for accomplishing marine tasks such as oceanic supervision and undersea operations have been an endeavour from long time ago. Hence, a number of underwater robots have been developed. Among those underwater robots, developing biomimetic swimming robots has been appealing for many researchers and institutes since these robots have shown superior performance. Biomimetic swimming robots have higher swimming efficiency, manoeuvrability and noiseless performance. However, the existing biomimetic swimming robots are specialised for a single gait of locomotion like cruising, manoeuvrability and accelerating while for efficient accomplishment of marine tasks, an underwater robot needs to have multiple gaits of locomotion. In order to develop multiple-gaited swimming robots, the optimal characteristics of each gait of swimming must be combined together, whereas the combination is not usually possible. The problem needs to be addressed during the design process. Moreover, the optimality of the actuation mechanism of robots - that do not utilise any artificial muscle - could be assured using the mathematical model employed for simulation of their swimming behaviour. However, the existing models are incomplete and, accordingly, not reliable since their assumptions like the constant speed of flow around the fish robot could be used when the average speed of the flow is determined during experiment while before development of robots, the flow speed is not known. In addition to that, the simulation results must be optimised using the experimental observations in nature and analytical results while the optimisation algorithms are based on one fitness function. The aforementioned problems as well as the fabrication challenges of free-swimming biomimetic robots are addressed in a development process of multiple-gaited fish-mimetic robots introduced by the author in this thesis. This development method engages the improvement of all development steps of fish robots including design, mathematical modelling, optimisation and fabrication steps. In this thesis, the aforementioned steps are discussed and the contributions of the method for each step are introduced. As an outcome of the project, two prototypes of fish robots called UC-Ika 1 & 2 are built.

Optimization problems are vital in physical sciences, commercial and finance matters. In a nutshell, almost everyone is the stake-holder in certain optimization problems aiming at minimizing the cost of production and losses of system, and also maximizing the profit. In control systems, the optimal configuration problems are essential that have been solved by various newly developed methods. The literature is exhaustively explored for an appropriate optimization method to solve such kind of problems. Particle Swarm Optimization is found to be one of the best among several optimization methods by analysing the experimental results. Two novel PSO variants are introduced in this thesis. The first one is named as N State Markov Jumping Particle Swarm Optimization, which is based on the stochastic technique and Markov chain in updating the particle velocity. We have named the second variant as N State Switching Particle Swarm Optimization, which is based on the evolutionary factor information for updating the velocity. The proposed algorithms are then applied to some widely used mathematical benchmark functions. The statistical results of 30 independent trails illustrate the robustness and accuracy of the proposed algorithms for most of the benchmark functions. The better results in terms of mean minimum evaluation errors and the shortest computation time are illustrated. In order to verify the satisfactory performance and robustness of the proposed algorithms, we have further formulated some basic applications in power system operations. The first application is about the static Economic Load Dispatch and the second application is on the Dynamic Economic Load Dispatch. These are highly complex and non-linear problems of power system operations consisting of various systems and generator constraints. Basically, in the static Economic Load Dispatch, a single load is considered for calculating the cost function. In contrast, the Dynamic Economic Load Dispatch changes the load demand for the cost function dynamically with time. In such a challenging and complex environment the proposed algorithms can be applied. The empirical results obtained by applying both of the proposed methods have substantiated their adaptability and robustness into the real-world environment. It is shown in the numerical results that the proposed algorithms are robust and accurate as compared to the other algorithms. The proposed algorithms have produced consistent best values for their objectives, where satisfying all constraints with zero penalty.

Games have been investigated as computationally complex problems since the inception of artificial intelligence in the 1950’s. Originally, search-based techniques were applied to create a competent (and sometimes even expert) game player. The search-based techniques, such as game trees, made use of human-defined knowledge to evaluate the current game state and recommend the best move to make next. Recent research has shown that neural networks can be evolved as game state evaluators, thereby removing the human intelligence factor completely. This study builds on the initial research that made use of evolutionary programming to evolve neural networks in the game learning domain. Particle Swarm Optimisation (PSO) is applied inside a coevolutionary training environment to evolve the weights of the neural network. The training technique is applied to both the zero sum and non-zero sum game domains, with specific application to Tic-Tac-Toe, Checkers and the Iterated Prisoners Dilemma (IPD). The influence of the various PSO parameters on playing performance are experimentally examined, and the overall performance of three different neighbourhood information sharing structures compared. A new coevolutionary scoring scheme and particle dispersement operator are defined, inspired by Formula One Grand Prix racing. Finally, the PSO is applied in three novel ways to evolve strategies for the IPD – the first application of its kind in the PSO field. The PSO-based coevolutionary learning technique described and examined in this study shows promise in evolving intelligent evaluators for the aforementioned games, and further study will be conducted to analyse its scalability to larger search spaces and games of varying complexity. / Dissertation (MSc)--University of Pretoria, 2005. / Computer Science / unrestricted

京都大学 / 0048 / 新制・課程博士 / 博士(工学) / 甲第18568号 / 工博第3929号 / 新制||工||1604(附属図書館) / 31468 / 京都大学大学院工学研究科都市社会工学専攻 / (主査)教授 谷口 栄一, 准教授 宇野 伸宏, 准教授 山田 忠史 / 学位規則第4条第1項該当 / Doctor of Philosophy (Engineering) / Kyoto University / DGAM