Li, Gang. / Thesis (Ph.D.)--Chinese University of Hong Kong, 2009. / Includes bibliographical references (leaves 121-136). / Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Abstract also in Chinese.

Transdisciplinary food systems research aims to merge insights from multiple fields, often revealing confounding, complex interactions. Computational modeling offers a means to discover patterns and formulate novel solutions to such systems-level problems. The best models serve as hubs—or boundary objects—which ground and unify a collaborative, iterative, and transdisciplinary process of stakeholder engagement. This dissertation demonstrates the application of agent-based modeling, network analytics, and evolutionary computational optimization to the pressing food systems problem areas of livestock epidemiology and global food security. It is comprised of a methodological introduction, an executive summary, three journal-article formatted chapters, and an overarching discussion section. Chapter One employs an agent-based computer model (RUSH-PNBM v.1.1) developed to study the potential impact of the trend toward increased producer specialization on resilience to catastrophic epidemics within livestock production chains. In each run, an infection is introduced and may spread according to probabilities associated with the various modes of contact between hog producer, feed mill, and slaughter plant agents. Experimental data reveal that more-specialized systems are vulnerable to outbreaks at lower spatial densities, have more abrupt percolation transitions, and are characterized by less-predictable outcomes; suggesting that reworking network structures may represent a viable means to increase biosecurity. Chapter Two uses a calibrated, spatially-explicit version of RUSH-PNBM (v.1.2) to model the hog production chains within three U.S. states. Key metrics are calculated after each run, some of which pertain to overall network structures, while others describe each actor’s positionality within the network. A genetic programming algorithm is then employed to search for mathematical relationships between multiple individual indicators that effectively predict each node’s vulnerability. This “meta-metric” approach could be applied to aid livestock epidemiologists in the targeting of biosecurity interventions and may also be useful to study a wide range of complex network phenomena. Chapter Three focuses on food insecurity resulting from the projected gap between global food supply and demand over the coming decades. While no single solution has been identified, scholars suggest that investments into multiple interventions may stack together to solve the problem. However, formulating an effective plan of action requires knowledge about the level of change resulting from a given investment into each wedge, the time before that effect unfolds, the expected baseline change, and the maximum possible level of change. This chapter details an evolutionary-computational algorithm to optimize investment schedules according to the twin goals of maximizing global food security and minimizing cost. Future work will involve parameterizing the model through an expert informant advisory process to develop the existing framework into a practicable food policy decision-support tool.

Water is vital to man and its quality it a serious topic of concern. Addressing sustainability issues requires new understanding of water quality and water transport. Past research in hydrology has focused primarily on physics-based models to explain hydrological transport and water quality processes. The widespread use of in situ hydrological instrumentation has provided researchers a wealth of data to use for analysis and therefore use of data mining for data-driven modeling is warranted. In fact, this relatively new field of hydroinformatics makes use of the vast data collection and communication networks that are prevalent in the field of hydrology. In this Thesis, a data-driven approach for analyzing water quality is introduced. Improvements in the data collection of information system allow collection of large volumes of data. Although improvements in data collection systems have given researchers sufficient information about various systems, they must be used in conjunction with novel data-mining algorithms to build models and recognize patterns in large data sets. Since the mid 1990's, data mining has been successful used for model extraction and describing various phenomena of interest.

Heating, ventilating and air-conditioning (HVAC) system is complex non-linear system with multi-variables simultaneously contributing to the system process. It poses challenges for both system modeling and performance optimization. Traditional modeling methods based on statistical or mathematical functions limit the characteristics of system operation and management. Data-driven models have shown powerful strength in non-linear system modeling and complex pattern recognition. Sufficient successful applications of data mining have proved its capability in extracting models accurately describing the relation of inner system. The heuristic techniques such as neural networks, support vector machine, and boosting tree have largely expanded to the modeling process of HVAC system. Evolutionary computation has rapidly merged to the center stage of solving the multi-objective optimization problem. Inspired from the biology behavior, it has shown the tremendous power in finding the optimal solution of complex problem. Different applications of evolutionary computation can be found in business, marketing, medical and manufacturing domains. The focus of this thesis is to apply the evolutionary computation approach in optimizing the performance of HVAC system. The energy saving can be achieved by implementing the optimal control setpoints with IAQ maintained at an acceptable level. A trade-off between energy saving and indoor air quality maintenance is also investigated by assigning different weights to the corresponding objective function. The major contribution of this research is to provide the optimal settings for the existing system to improve its efficiency and different preference-based operation methods to optimally utilize the resources.

Abstract not available

Traditionally, an evolutionary algorithm (EA) operates on a single population with no restrictions on possible mating pairs. Interesting changes to the behaviour of EAs emerge when the structure of the population is altered so that mating between individuals is restricted. Variants of EAs that use such populations are grouped into the field of spatially-structured EAs (SSEAs). Previous research into the behaviour of SSEAs has primarily focused on the impact space has on the selection pressure in the system. Selection pressure is usually characterised by takeover times and the ratio between the neighbourhood size and the overall dimension of space. While this research has given indications into where and when the use of an SSEA might be suitable, it does not provide a complete coverage of system behaviour in SSEAs. This thesis presents new research into areas of SSEA behaviour that have been left either unexplored or briefly touched upon in current EA literature. The behaviour of genetic drift in finite panmictic populations is well understood. This thesis attempts to characterise the behaviour of genetic drift in spatially-structured populations. First, an empirical investigation into genetic drift in two commonly encountered topologies, rings and torii, is performed. An observation is made that genetic drift in these two configurations of space is independent of the genetic structure of individuals and additive of the equivalent-sized panmictic population. In addition, localised areas of homogeneity present themselves within the structure purely as a result of drifting. A model based on the theory of random walks to absorbing boundaries is presented which accurately characterises the time to fixation through random genetic drift in ring topologies. A large volume of research has gone into developing niching methods for solving multimodal problems. Previously, these techniques have used panmictic populations. This thesis introduces the concept of localised niching, where the typically global niching methods are applied to the overlapping demes of a spatially structured population. Two implementations, local sharing and local clearing are presented and are shown to be frequently faster and more robust to parameter settings, and applicable to more problems than their panmictic counterparts. Current SSEAs typically use a single fitness function across the entire population. In the context of multimodal problems, this means each location in space attempts to discover all the optima. A preferable situation would be to use the inherent spatial properties of an SSEA to localise optimisation of peaks. This thesis adapts concepts from multiobjective optimisation with environmental gradients and applies them to multimodal problems. In addition to adapting to the fitness landscape, individuals evolve towards their preferred environmental conditions. This has the effect of separating individuals into regions that concentrate on different optima with the global fitness function. The thesis also gives insights into the expected number of individuals occupying each optima in the problem. The SSEAs and related models developed in this thesis are of interest to both researchers and end-users of evolutionary computation. From the end-user�s perspective, the developed SSEAs require less a priori knowledge of a given problem domain in order to operate effectively, so they can be more readily applied to difficult, poorly-defined problems. Also, the theoretical findings of this thesis provides a more complete understanding of evolution within spatially-structured populations, which is of interest not only to evolutionary computation practitioners, but also to researchers in the fields of population genetics and ecology.

Wave Energy Converters (WECs) promise to be a viable alternative to current electrical generation methods. However, these WECs must become more efficient before wide-scale industrial use can become cost-effective. The efficiency of a WEC is primarily dependent upon its geometry and ballast configuration which are both difficult to evaluate, due to slow computation time and high computation cost of current models. In this thesis, we use evolutionary algorithms to optimize the ballast geometry of a wave energy generator using a two step process. First, we generate a function approximator (neural network) to predict wave energy converter power output with respect to key geometric design variables. This is a critical step as the computation time of using a full model (e.g., AQWA) to predict energy output prohibits the use of an evolutionary algorithm for design optimization. The function approximator reduced the computation time by over 99% while having an average error of only 3.5%. The evolutionary algorithm optimized the weight distribution of a WEC, resulting in an 84% improvement in power output over a ballast-free WEC. / Graduation date: 2012

A connectivity adjusting learning algorithm, Optimal Brain Growth (OBG) was proposed. Contrast to the conventional training methods for the Artificial Neural Network (ANN) which focus on the weight-only optimization, the OBG method trains both weights and connectivity of a network in a single training process. The standard Back-Propagation (BP) algorithm was extended to exploit the error gradient information of the latent connection whose current weight has zero value. Based on this, the OBG algorithm makes a rational decision between a further adjustment of an existing connection weight and a creation of a new connection having zero weight. The training efficiency of a growing network is maintained by freezing stabilized connections in the further optimization process. A stabilized computational unit is also decomposed into two units and a particular set of decomposition rules guarantees a seamless local re-initialization of a training trajectory. The OBG method was tested for the multiple canonical, regression and classification problems and for a surrogate modeling of the pressure distribution on transonic airfoils. The OBG method showed an improved learning capability in computationally efficient manner compared to the conventional weight-only training using connectivity-fixed Multilayer Perceptrons (MLPs).

Thesis (Ph. D.)--Missouri University of Science and Technology, 2009. / Vita. The entire thesis text is included in file. Title from title screen of thesis/dissertation PDF file (viewed January 5, 2010) Includes bibliographical references (p. 152-159).

Thesis (M.S.)--Mississippi State University. Department of Computer Science. / Title from title screen. Includes bibliographical references.