Master of Science, The Ohio State University, 2022, Environment and Natural Resources

Understanding the drivers of “where” and “how many” is fundamental to wildlife ecology and conservation. For decades, species distribution modelers have drawn predictions of where species will occur from presence-only or presence/assumed-absence data and climate norms, topography, and vegetation while ignoring the rich history that land has to offer. Despite the recognized importance of incorporating detection processes into wildlife analyses and how land use history can affect present day populations, they largely are ignored for simplicity or a lack of data. This thesis begins by evaluating weather downscaling methods int the recent microclimc package to understand if the outputs are accurate and then passes those that are to distribution models for five species of plethodontid salamander which incorporates imperfect detection and a variety of historical disturbance. The resulting fit, predictions, and validation are compared between models that incorporate detection, disturbance, or both in addition to topographic features. Finally, it ends by using the robust toolset available through abundance modeling to examine “how many” individuals are present across a range of recent wildfire severity.

Committee: William Peterman (Advisor); Stephen Matthews (Committee Member); Gwilym Davies (Committee Member) Subjects: Ecology; Natural Resource Management; Wildlife Conservation

PhD, University of Cincinnati, 2017, Engineering and Applied Science: Aerospace Engineering

Machine Learning is a type of artificial intelligence that provides machines or networks the ability to learn from data without the need to explicitly program them. There are different kinds of machine learning techniques. This thesis discusses the applications of two of these approaches: Genetic Fuzzy Logic and Convolutional Neural Networks (CNN). Fuzzy Logic System (FLS) is a powerful tool that can be used for a wide variety of applications. FLS is a universal approximator that reduces the need for complex mathematics and replaces it with expert knowledge of the system to produce an input-output mapping using If-Then rules. The expert knowledge of a system can help in obtaining the parameters for small-scale FLSs, but for larger networks we will need to use sophisticated approaches that can automatically train the network to meet the design requirements. This is where Genetic Algorithms (GA) and EVE come into the picture. Both GA and EVE can tune the FLS parameters to minimize a cost function that is designed to meet the requirements of the specific problem. EVE is an artificial intelligence developed by Psibernetix that is trained to tune large scale FLSs. The parameters of an FLS can include the membership functions and rulebase of the inherent Fuzzy Inference Systems (FISs). The main issue with using the GFS is that the number of parameters in a FIS increase exponentially with the number of inputs thus making it increasingly harder to tune them. To reduce this issue, the FLSs discussed in this thesis consist of 2-input-1-output FISs in cascade (Chapter 4) or as a layer of parallel FISs (Chapter 7). We have obtained extremely good results using GFS for different applications at a reduced computational cost compared to other algorithms that are commonly used to solve the corresponding problems. In this thesis, GFSs have been designed for controlling an inverted double pendulum, a task allocation problem of clustering targets amongst a set of UAVs, a fire dete (open full item for complete abstract)

Committee: Kelly Cohen Ph.D. (Committee Chair); Raj Bhatnagar Ph.D. (Committee Member); Franck Cazaurang Ph.D. (Committee Member); Nicholas C. Ernest Ph.D. (Committee Member); Manish Kumar Ph.D. (Committee Member) Subjects: Aerospace Materials

Master of Science in Engineering, Youngstown State University, 2014, Rayen School of Engineering

Fire threatens man, animals, plants and properties. So there should be a very adequate, fast, and easy to install alarm systems to avoid the fire consequences. A wireless sensor network (WSN) with multiple wireless sensor nodes and a base station for fire detection is presented. It is a low-cost, easy to construct, highly efficient, fast, and reliable wireless sensor network. Wireless nodes measure the temperature and light intensity in their surrounding areas. The temperature and light data from the wireless nodes are used to detect the fire event and then the system sounds an alarm. The wireless sensor nodes collect and send data continuously to the base station, which is connected to a computer. Software application has been developed in order to conduct the data mining of the wireless sensor network. The WSN has shown the efficiency of mining real time data, reliability, and its flexibility for expansion.

Committee: Frank Li Ph.D. (Advisor); Jalal Jalali Ph.D. (Committee Member); Faramarz Mossayebi Ph.D. (Committee Member) Subjects: Electrical Engineering