DATA DRIVEN INTELLIGENT AGENT NETWORKS FOR ADAPTIVE MONITORING AND CONTROL

To analyze the characteristics and predict the dynamic behaviors of complex systems over time, comprehensive research to enable the development of systems that can intelligently adapt to the evolving conditions and infer new knowledge with algorithms that are not predesigned is crucially needed. This dissertation research studies the integration of the techniques and methodologies resulted from the fields of pattern recognition, intelligent agents, artificial immune systems, and distributed computing platforms, to create technologies that can more accurately describe and control the dynamics of real-world complex systems. The need for such technologies is emerging in manufacturing, transportation, hazard mitigation, weather and climate prediction, homeland security, and emergency response. Motivated by the ability of mobile agents to dynamically incorporate additional computational and control algorithms into executing applications, mobile agent technology is employed in this research for the adaptive sensing and monitoring in a wireless sensor network. Mobile agents are software components that can travel from one computing platform to another in a network and carry programs and data states that are needed for performing the assigned tasks. To support the generation, migration, communication, and management of mobile monitoring agents, an embeddable mobile agent system (Mobile-C) is integrated with sensor nodes. Mobile monitoring agents visit distributed sensor nodes, read real-time sensor data, and perform anomaly detection using the equipped pattern recognition algorithms. The optimal control of agents is achieved by mimicking the adaptive immune response and the application of multi-objective optimization algorithms. The mobile agent approach provides potential to reduce the communication load and energy consumption in monitoring networks. The major research work of this dissertation project includes: (1) studying effective feature extraction methods for time series measurement data; (2) investigating the impact of the feature extraction methods and dissimilarity measures on the performance of pattern recognition; (3) researching the effects of environmental factors on the performance of pattern recognition; (4) integrating an embeddable mobile agent system with wireless sensor nodes; (5) optimizing agent generation and distribution using artificial immune system concept and multi-objective algorithms; (6) applying mobile agent technology and pattern recognition algorithms for adaptive structural health monitoring and driving cycle pattern recognition; (7) developing a web-based monitoring network to enable the visualization and analysis of real-time sensor data remotely. Techniques and algorithms developed in this dissertation project will contribute to research advances in networked distributed systems operating under changing environments.

Water and sanitation accessibility and the health of rural Ugandans

The lack of access to sufficient water and sanitation facilities is one of the largest hindrances towards the sustainable development of the poorest 2.2 billion people in the world. Rural Uganda is one of the areas where such inaccessibility is seriously hampering their efforts at development. Many rural Ugandans must travel several kilometers to fetch adequate water and many still do not have adequate sanitation facilities. Such poor access to clean water forces Ugandans to spend an inordinate amount of time and energy collecting water - time and energy that could be used for more useful endeavors. Furthermore, the difficulty in getting water means that people use less water than they need to for optimal health and well-being. Access to other sanitation facilities can also have a large impact, particularly on the health of young children and the elderly whose immune systems are less than optimal. Hand-washing, presence of a sanitary latrine, general household cleanliness, maintenance of the safe water chain and the households’ knowledge about and adherence to sound sanitation practices may be as important as access to clean water sources. This report investigates these problems using the results from two different studies. It first looks into how access to water affects peoples’ use of it. In particular it investigates how much water households use as a function of perceived effort to fetch it. Operationally, this was accomplished by surveying nearly 1,500 residents in three different districts around Uganda about their water usage and the time and distance they must travel to fetch it. The study found that there is no statistically significant correlation between a family’s water usage and the perceived effort they must put forth to have to fetch it. On average, people use around 15 liters per person per day. Rural Ugandan residents apparently require a certain amount of water and will travel as far or as long as necessary to collect it. Secondly, a study entitled “What Works Best in Diarrheal Disease Prevention?” was carried out to study the effectiveness of five different water and sanitation facilities in reducing diarrheal disease incidences amongst children under five. It did this by surveying five different communities before and after the implementation of improvements to find changes in diarrheal disease incidences amongst children under five years of age. It found that household water treatment devices provide the best means of preventing diarrheal diseases. This is likely because water often becomes contaminated before it is consumed even if it was collected from a protected source.