Search Results (1 - 23 of 23 Results)

Sort By  
Sort Dir
 
Results per page  

Jagirdar, SureshInvestigation into Regression Analysis of Multivariate Additional Value and Missing Value Data Models Using Artificial Neural Networks and Imputation Techniques
Master of Science (MS), Ohio University, 2008, Industrial and Systems Engineering (Engineering and Technology)

Missing data or insufficient data is a major concern in statistical analysis, especially when the problem to be addressed is related to prediction. The present study is a quantitative analysis of data based on a 'regression technique' for the modeling and prediction of three different numerical data sets, named: Boston Housing, Saginaw Bay,and Reportable Outages. The goal is to enhance the regression results by using an artificial neural network to either impute missing data or supplement existing data using non-linear model. The present prediction problem focuses on developing a hybrid model to create additional data using a combination of model selection techniques such as cross validation estimate and regularization theory in order to reduce the effect of over fitting. The student model is constructed using the knowledge extracted from the teacher model. The knowledge is in the form of learning obtained through an Artificial Neural Network training of the data set/s. The learning derived from the training is also used to build a reverse engineered model to address the missing value data problem.

In the case of Reportable Outages, the student model achieved is the closest nonlinear model to the teacher model and succeeded in enhancing the regression analysis for the prediction problem. The Boston Housing student model contains a significant amount of correlation among the variables, which need additional data relational techniques to address the correlation. The enhancement of linear regression for the case of prediction for Saginaw Bay data is limited to nature and its complex processes.

The overall results achieved are encouraging and show promise for developing a model to create a needed data when data is highly correlated. More data cases need to be investigated using the reverse engineering technique of the Artificial Neural Network for predicting missing value data.

Committee:

Gary R. Weckman (Committee Chair); David Koonce (Committee Member); Scherwa Diana (Committee Member); Andrew Snow (Committee Member)

Subjects:

Industrial Engineering

Keywords:

Artificial Neural Network; Data Addition and Knowledge Extraction; Reverse Engineered Artificial Neural Network; Correlation Breakdown

Wilmot, Timothy AllenIntelligent Controls for a Semi-Active Hydraulic Prosthetic Knee
Master of Science in Electrical Engineering, Cleveland State University, 2011, Fenn College of Engineering
We discuss open loop control development and simulation results for a semi-active above-knee prosthesis. The control signal consists of two hydraulic valve settings. These valves control a rotary actuator that provides torque to the prosthetic knee. We develop open loop control using biogeography-based optimization (BBO), which is a recently developed evolutionary algorithm, and gradient descent. We use gradient descent to show that the control generated by BBO is locally optimal. This research contributes to the field of evolutionary algorithms by demonstrating that BBO is successful at finding optimal solutions to complex, real-world, nonlinear, time varying control problems. The research contributes to the field of prosthetics by showing that it is possible to find effective open loop control signals for a newly proposed semi-active hydraulic knee prosthesis. The control algorithm provides knee angle tracking with an RMS error of 7.9 degrees, and thigh angle tracking with an RMS error of 4.7 degrees. Robustness tests show that the BBO control solution is affected very little by disturbances added during the simulation. However, the open loop control is very sensitive to the initial conditions. So a closed loop control is needed to mitigate the effects of varying initial conditions. We implement a proportional, integral, derivative (PID) controller for the prosthesis and show that it is not a sufficient form of closed loop control. Instead, we implement artificial neural networks (ANNs) as the mechanism for closed loop control. We show that ANNs can greatly improve performance when noise and disturbance cause high tracking errors, thus reducing the risk of stumbles and falls. We also show that ANNs are able to improve average performance by as much as 8% over open loop control. We also discuss embedded system implementation with a microcontroller and associated hardware and software.

Committee:

Dan Simon, PhD (Advisor); Fuquin Xiong, PhD (Committee Member); Lili Dong, PhD (Committee Member)

Subjects:

Electrical Engineering; Engineering

Keywords:

prosthetic control; ANN; artificial neural network; BBO; biogeography based optimization; intelligent control; nonlinear control problem; time varying control problem; evolutionary algorithm; gradient descent

Bush, Brian O.Development of a fuzzy system design strategy using evolutionary computation
Master of Science (MS), Ohio University, 1996, Industrial and Manufacturing Systems Engineering (Engineering)

Natural language is perhaps the most powerful form of conveying information for any given problem or situation. Combining natural language and numerical information into fuzzy systems provide the framework to represent knowledge, constraints and inference procedures. Fuzzy systems are advantageous in the development of systems solutions that perform tasks such as automatic modeling, prediction, pattern recognition, and optimal decision making, control and planning. Thus, fuzzy systems are an essential tool for industrial and manufacturing systems engineering. Traditionally fuzzy system design is carried out by a time-consuming trial-and-error process, in order to incorporate expert knowledge into a fuzzy model. To date there is no systematic procedure to design fuzzy systems that has been met with wide-acceptance and usage. In this research, a formal methodology has been developed for the design and adaptation of effective fuzzy systems displaying both robustness and computational efficiency. The goal was to improve upon a functional fuzzy system by modifying the fuzzy sets of fuzzy rules using evolutionary computation principles. An experimental implementation was developed. The relative influence of selected factors such mutations and crossover schemes, mutations rates, and fuzzy rule structure upon the methodology's effectiveness within the experimental context were also addressed. Finally, the application of the methodology to function approximation, classification, regression, and the prediction of chaotic dynamics were accomplished to demonstrate the computational characteristics, complexity and inherent strength of the developed methodology.

Committee:

Luis Rabelo (Advisor)

Subjects:

Engineering, Industrial

Keywords:

Fuzzy Systems; Artificial Neural Network; Computational Intelligence

Huang, I-Wen EvanUniform Corrosion and General Dissolution of Aluminum Alloys 2024-T3, 6061-T6, and 7075-T6
Doctor of Philosophy, The Ohio State University, 2016, Materials Science and Engineering
Uniform corrosion and general dissolution of aluminum alloys was not as well-studied in the past, although it was known for causing significant amount of weight loss. This work comprises four chapters to understand uniform corrosion of aluminum alloys 2024-T3, 6061-T6, and 7075-T6. A preliminary weight loss experiment was performed for distinguishing corrosion induced weight loss attributed to uniform corrosion and pitting corrosion. The result suggested that uniform corrosion generated a greater mass loss than pitting corrosion. First, to understand uniform corrosion mechanism and kinetics in different environments, a series of static immersion tests in NaCl solutions were performed to provide quantitative measurement of uniform corrosion. Thereafter, uniform corrosion development as a function of temperature, pH, Cl-, and time was investigated to understand the influence of environmental factors. Faster uniform corrosion rate has been found at lower temperature (20 and 40°C) than at higher temperature (60 and 80°C) due to accelerated corrosion product formation at high temperatures inhibiting corrosion reactions. Electrochemical tests including along with scanning electron microscopy (SEM) were utilized to study the temperature effect. Second, in order to further understand the uniform corrosion influence on pit growth kinetics, a long term exposures for 180 days in both immersion and ASTM-B117 test were performed. Uniform corrosion induced surface recession was found to have limited impact on pit geometry regardless of exposure methods. It was also found that the competition for limited cathodic current from uniform corrosion the primary rate limiting factor for pit growth. Very large pits were found after uniform corrosion growth reached a plateau due to corrosion product coverage. Also, optical microscopy and focused ion beam (FIB) imaging has provided more insights of distinctive pitting geometry and subsurface damages found from immersion samples and B117 samples. Although uniform corrosion was studied in various electrolytes, the pH impact was still difficult to discern due to ongoing cathodic reactions that changed electrolyte pH with time. Therefore, buffered pH electrolytes with pH values of 3, 5, 8, and 10 were prepared static immersion tests. Electrochemical experiments were performed in each buffered pH conditions for understanding corrosion mechanisms. Uniform corrosion was found exhibiting higher corrosion rate in buffered acidic and alkaline electrolytes due to pH- and temperature-dependent corrosion product precipitation. Observations were supported by electrochemical, SEM, and EDS observations. Due to the complexity of corrosion data, a reliable corrosion prediction based on empirical observations could be challenging. Artificial neural network (ANN) modeling was used for corrosion data pattern recognition by mimicking human neural network systems. Predictive models were developed based on corrosion data acquired in this study. The model was adaptable through iteratively update its prediction by error minimization during the training phase. Trained ANN model can predict uniform corrosion successfully. In addition to ANN, fuzzy curve analysis was utilized to rank the influence of each input (temperature, pH, Cl-, and time). For example, temperature and pH were found to be the most influential parameters to uniform corrosion. This information can provide feedback for ANN improvement, also known as “data pruning”.

Committee:

Rudolph Buchheit (Advisor); Gerald Frankel (Committee Member); Jenifer Locke (Committee Member); Christopher Taylor (Committee Member)

Subjects:

Engineering; Materials Science; Metallurgy

Keywords:

uniform corrosion, pitting, aluminum alloys, artificial neural network

Sullivan, John B.The application of an artificial neural network to a turning movement detector system
Master of Science (MS), Ohio University, 1991, Industrial and Manufacturing Systems Engineering (Engineering)
The application of an artificial neural network to a turning movement detector system

Committee:

Donald Scheck (Advisor)

Subjects:

Engineering, Industrial

Keywords:

Artificial Neural Network; Turning Movement Detector System

Okano, MakotoThe design of a PC based financial credit evaluation system involving an artificial neural network for the evaluation of industrial manufacturers
Master of Science (MS), Ohio University, 1994, Industrial and Manufacturing Systems Engineering (Engineering)

The Financial Loan Evaluation System (FLES) is based on a DOS operation system program to evaluate industrial manufacturers' financial situations. The FLES utilizes an artificial neural network (backpropagation) and evaluates the firm's financial loan proposal, based primarily on the financial ratio analysis method. Since the system is able to learn from past evaluation examples, it performs somewhat like an experienced human expert. Thus, unlike other expert system applications, the FLES allows a user to rebuild the system with less development time and cost when conditions and/or rules have changed.

In this thesis, FLES is trained by fifty loan evaluation examples. In the training examples, the inputs and target outputs are required to build a backpropagation network. The input data include financial ratios and finance-related information, while the output is a percentage of the proposed loan amount granted. The desired outputs are generated by the constant pair-wise comparison method because they are not provided by library sources as are the financial ratios.

The constant pair-wise comparison method determines what decision making criteria are the most and the least important by calculating for each a numerical weight. The FLES shows adequate responses in more than 75% of the loan evaluations when it is evaluated with fifty new examples. FLES is relatively easy to use and is capable of providing an answer to a user in approximately 30 to 60 minutes.

Committee:

Helmut Zwahlen (Advisor)

Subjects:

Engineering, Industrial

Keywords:

PC; Financial Credit Evaluation System Artificial Neural Network; Industrial Manufacturers

Cheng, ChaoApplication of Artificial Neural Networks in the Power Split Controller For a Series Hydraulic Hybrid Vehicle
Master of Science in Mechanical Engineering, University of Toledo, 2010, Mechanical Engineering

Hybridization of vehicles has been proven a good way to reduce fuel consumption significantly. Working prototypes of a series hydraulic hybrid vehicle (SHHV) are already under testing. The power split strategy for those prototypes is a rule-based controller, or called a “bang-bang” controller. The controller is designed based on engineer's intuition, to keep the engine working in the region with high efficiency and low fuel consumption rate. One of the problems of that design is that it only takes one component of the hydraulic hybrid system, the internal combustion engine, into account. It is a device centered rather than system centered design. As a result, the potential of the hydraulic hybrid system is not fully realized.

A more efficient power split strategy is conducted based on the Deterministic Dynamic Programming (DDP), which has been proved a powerful tool for optimal control. However, the DDP is a looking-forward tool, which means it uses the future driving conditions to split the power between the two sources for optimization. Successful applications of DDP used standard driving cycles as the known driving conditions. However, DDP is not applicable where the driving cycle is unknown. This means that the DDP could not be applied in real-time, unless the future driving conditions could be found.

The driving conditions in our everyday commute are extremely different with the typical driving cycles. And different drivers have different driving habits. However, a specific driver has a certain “driving cycle” for a certain commute, although which is not a standard one. As long as the certain “driving cycle” is known, The DDP algorithm could be applied for optimization. Artificial neural network (ANN) has the ability to “learn” the “driving cycle” from a certain driver and then to “predict” the driving conditions before its happening. The “prediction” method is the “time-series forecasting” method. ANN is a good tool for time series forecasting and has also been shown a better way for long term prediction. The ANN is conducted using the software MATLAB/Simulink. A three-layer feed-forward static ANN is built up in the Simulink environment.

The ANN model was able to predict the driving conditions with a twenty seconds window size which has been proven a tradeoff between the forecasting accuracy and the time consumed. The error between the predicted value and the desired value is within an accepted range. The network is tested based on three different driving cycles: federal urban driving schedule, city urban dynamometer driving schedule and highway urban dynamometer driving schedule respectively.

Committee:

Walter Olson (Advisor); Terry Ng (Committee Member); Yong Gan (Committee Member)

Subjects:

Mechanical Engineering

Keywords:

Series Hydraulic Hybrid Vehicle Control; Artificial Neural Network; Dynamic Programming

Moayed, Farman AminConstructing the Function of “Magnitude-of-Effect” for Artificial Neural Network (ANN) Models and Their Application in Occupational Safety and Health (OSH) Engineering
PhD, University of Cincinnati, 2008, Engineering : Industrial Engineering

Safety professionals and practitioners are always searching for methods to accurately assess the association between exposures and possible occupational disorders or diseases and predict the outcome of any outcome. Statistical analysis and logistic regression in particular are among the most popular tools being used by them. Artificial Neural Network (ANN) models are another method of predicting outcomes, which are gradually finding their way in the safety field. It has been shown that they are capable of predicting outcomes more accurately than logistic regression, but they are incapable of demonstrating the direct correlation between exposure variables and possible outcome variables. The first objective in this research was to demonstrate that Artificial Neural Network models can perform better that logistic regression models with data sets made of all ordinal variables, which has not been done so far. All the publications in this area were about either dichotomous or a combination of dichotomous and continuous variables.

The second objective of this study was to develop a mathematical function that can produce a measure to evaluate the direct association between exposure and possible outcome variables. This function was referred to as the function of Magnitude-of-Effect (MoE). Safety experts and practitioners can use the MoE function to interpret how strongly an exposure variable can affect the possible outcome variable. The significance of such achievement is that it can eliminate the artificial neural network models’ shortcoming and make them more applicable in the occupational safety and health engineering field.

The result of this study showed that artificial neural network models performed significantly better than logistic regression models with a data set of all ordinal variables. And also the suggested MoE function was capable and valid enough to show any correlation between exposure and possible outcome variables.

Committee:

Richard Shell, PhD (Committee Chair); Ash Genaidy, PhD (Committee Member); Anca Ralescu, PhD (Committee Member); Gary Weckman, PhD (Committee Member); John Funk, PhD (Committee Member)

Subjects:

Environmental Science; Health; Industrial Engineering; Occupational Safety

Keywords:

Logistic Regression; Artificial Neural Network; Magnitude-of-Effect; Work Compatibility System; Occupational Health and Safety

Gao, ZhenningParallel and Distributed Implementation of A Multilayer Perceptron Neural Network on A Wireless Sensor Network
Master of Science, University of Toledo, Engineering (Computer Science)
This thesis presents a study on implementing the multilayer perceptron neural network on the wireless sensor network in a parallel and distributed way. We take advantage of the topological resemblance between the multilayer perceptron and wireless sensor network. A single neuron in the multilayer perceptron neural network is implemented on a wireless sensor node, and the connections between neurons are achieved by the wireless links between nodes. While the computation of the multilayer perceptron benefits from the massive parallelism and the fully distribution when the wireless sensor network is serving as the hardware platform, it is still unknown whether the delay and drop phenomena for message packets carrying neuron outputs would prohibit the multilayer perceptron from getting a decent performance. A simulation-based empirical study is conducted to assess the performance profile of the multilayer perceptron on a number of different problems. Simulation study is performed using a simulator which is developed in-house for the unique requirements of the study proposed herein. The simulator only simulates the major effects of wireless sensor network operation which influence the running of multilayer perceptron. A model for delay and drop in wireless sensor network is proposed for creating the simulator. The setting of the simulation is well defined. Back-Propagation with Momentum learning is employed as the learning algorithms for the neural network. A formula for the number of neurons in the hidden layer neuron is chosen by empirical study. The simulation is done under different network topology and condition of delay and drop for the wireless sensor network. Seven data sets, namely Iris, Wine, Ionosphere, Dermatology, Handwritten Numerical, Isolet and Gisette, with the attributes counts up to 5000 and instances counts up to 7797 are employed to profile the performance. The simulation results are compared with those from the literature and through the non-distributed multilayer perceptron. Comparative performance evaluation suggests that the performance of multilayer perceptron using wireless sensor network as the hardware platform is comparable with other machine learning algorithms and as good as the non-distributed multilayer perceptron. The time and message complexity have been analyzed and it shows the scalability of the proposed method is promising.

Committee:

Gursel Serpen (Advisor); Mohsin Jamali (Committee Member); Ezzatollah Salari (Committee Member)

Subjects:

Artificial Intelligence; Computer Science

Keywords:

Artificial Intelligence; Artificial Neural Network; Machine Learning; Multilayer Perceptron; Wireless Sensor Network; Parallel Computing; Distributed Computing

Gurudath, NikitaDiabetic Retinopathy Classification Using Gray Level Textural Contrast and Blood Vessel Edge Profile Map
Master of Science (MS), Ohio University, 2014, Electrical Engineering (Engineering and Technology)
Diabetic retinopathy is an inevitable cause of diabetes that eventually leads to blindness without early detection and treatment. This thesis incorporates classification of an input fundus image into one of the three classes, healthy/normal, Non-Proliferative Diabetic Retinopathy (NPDR) and Proliferative Diabetic Retinopathy (PDR). In this research, an approach to automate the identification of the presence of diabetic retinopathy from color fundus images of the retina has been proposed. The blood vessel edge profile from these images is obtained using Gaussian kernel as the filtering function. A local entropy based thresholding using fixed as well as adaptive mask has been conducted. Gradient driven second order statistic contrast in four orientations and fractal features quantify the classes. The number of features vary based on the experiment. Classification has been achieved using two well-known techniques – Artificial Neural Network (ANN) and Support Vector Machines (SVM). The results of this research are compared to those obtained from other approaches developed in the literature.

Committee:

Mehmet Celenk (Advisor); H. Bryan Riley (Advisor)

Subjects:

Biomedical Engineering; Electrical Engineering; Engineering; Medical Imaging; Ophthalmology

Keywords:

Diabetic retinopathy; Fundus images; Gaussian filtering; Texture and fractal features; Artificial Neural Network; Support Vector Machines

Birkmire, Brian MichaelWeapon Engagement Zone Maximum Launch Range Approximation using a Multilayer Perceptron
Master of Science in Computer Engineering (MSCE), Wright State University, 2011, Computer Engineering
This thesis investigates the use of an artificial neural network (ANN), in particular a Multi-Layer Perceptron (MLP), to perform function approximation on truth data representing a weapon engagement zone's (WEZ) maximum launch range. The WEZ of an air-to-air missile represents the boundaries and zones of effectiveness for a one-vs-one air-to-air combat engagement [13]. The intent is for the network to fuse table lookup and interpolation functionality into a physically compact and computationally efficient package, while improving approximation accuracy over conventional methods. Data was collected from simulated firings of a notional air-to-air missile model and used to train a two layer perceptron using the Bayesian Regularization training algorithm. The resulting best network was able to improve approximation accuracy and reduce the amount of truth data needed. With basic feasibility established, future efforts can be focused on more comprehensive comparisons with existing methods and deployment within practical models.

Committee:

John Gallagher, PhD (Advisor); Mateen Rizki, PhD (Committee Member); Michael Raymer, PhD (Committee Member)

Subjects:

Computer Engineering; Computer Science

Keywords:

air-to-air missile; weapon engagement zone; artificial neural network; maximum launch range; virtual simulation

Monnin, JasonA VALIDATION OF A PROTOTYPE DRY ELECTRODE SYSTEM FOR ELECTROENCEPHALOGRAPHY
Master of Science in Engineering (MSEgr), Wright State University, 2011, Biomedical Engineering
Current physiologically-driven operator cognitive state assessment technology relies primarily on electroencephalographic (EEG) signals. Traditionally, gel-based electrodes have been used; however, the application of gel-based electrodes on the scalp requires expertise and a considerable amount of preparation time. Additionally, discomfort can occur from the abrasion of the scalp during preparation, and the electrolyte will also begin to dry out over extended periods of time. These drawbacks have hindered the transition of operator state assessment technology into an operational environment. QUASAR, Inc., (San Diego, CA) has developed a prototype dry electrode system for electroencephalography that requires minimal preparation. A comparison of the dry electrode system to traditional wet electrodes was conducted and is presented here. The results show that initially the EEG recorded by the dry electrode system was quite similar to that recorded by the wet electrodes, but the similarity decreased over a testing period of six months. For cognitive state assessment, the dry electrodes were able to achieve classification accuracies within one to two percent of those achieved by the wet electrodes, with no decrease in accuracy over time. The results suggest that the dry electrode system is capable of recording electroencephalographic signals to be used in cognitive state assessment, and aiding in the transition of that technology into an operational environment. Further work should be conducted to improve the reliability of this novel system.

Committee:

Ping He, PhD (Advisor); James Christensen, PhD (Committee Member); Julie Skipper, PhD (Committee Member)

Subjects:

Biomedical Engineering

Keywords:

dry electrode; wet electrode; EEG; operator state assessment; magnitude squared coherence; artificial neural network

Narayanan, PavaneshSensor-less Control of Shape Memory Alloy Using Artificial Neural Network and Variable Structure Controller
Master of Science, University of Toledo, 2014, Mechanical Engineering
This thesis presents an accurate and robust method to determine the angular position of a rotary manipulator using artificial neural network (ANN). A bias type, single degree of freedom rotary manipulator actuated by shape memory alloy (SMA) is used. During the operation of rotary manipulator, the SMA actuator experiences a complex thermo-mechanical loading due to varying stress and temperature, causing the transformation temperature to shift. An ANN is developed to accurately estimate the manipulator position. The ANN estimated position is then used to control the rotary manipulator and track different reference signals using a modified variable structure controller. The results of ANN validation and position control are presented. A novel method for controlling SMA actuator is proposed where the desired position is converted to corresponding resistance value using an ANN. This desired resistance value is compared with actual resistance to control the rotary manipulator. The results for ANN validation and position control are also presented.

Committee:

Mohammad Elahinia, Phd (Committee Chair); Manish Kumar, Phd (Committee Member); Mehdi Pourazady, Phd (Committee Member)

Subjects:

Artificial Intelligence; Mechanical Engineering

Keywords:

Shape Memory Alloys; Smart Actuators; Artificial Neural Network; Variable Structure Control; Hysteresis Modeling

Ponnileth Rajendran, AnanthakrishnanScalable Hardware Architecture for Memristor Based Artificial Neural Network Systems
MS, University of Cincinnati, 2016, Engineering and Applied Science: Computer Engineering
Since the physical realization of the Memristor by HP labs in 2008, research on Memristors and Memristive devices gained momentum, with focus primarily on modelling and fabricating Memristors and in developing applications for Memristive devices. The Memristor’s potential can be exploited in applications such as neuromorphic engineering, memory technology and analog and digital logic circuit implementations. Research on Memristor based neural networks have thus far focused on developing algorithms and methodologies for implementation. The Memristor Bridge Synapse, a Wheatstone bridge-like circuit composed of four Memristors is a very effective way to implement weights in hardware neural networks. Research on Memristor Bridge Synapse implementations coupled with the Random Weight Change Algorithm proved effective in learning complex functions with potential for implementation on hardware with simple and efficient circuity. However, the simulations and experiments conducted was purely on software and was only proof of concept. Realizing neural networks using the Memristor Bridge Synapse capable of on-chip training requires an effective hardware architecture with numerous components and complex timing. This thesis presents a scalable hardware architecture for implementing artificial neural networks using the Memristor Bridge Synapse capable of being trained on-chip using the Random Weight Change algorithm. Individual components required for implementing training logic, timing and evaluation are described and simulated using SPICE. A complete training simulation for a small neural network based on the proposed architecture was performed using HSPICE. A prototypical placement and routing tool for the architecture is also presented.

Committee:

Ranganadha Vemuri, Ph.D. (Committee Chair); Wen-Ben Jone, Ph.D. (Committee Member); Carla Purdy, Ph.D. (Committee Member)

Subjects:

Computer Engineering

Keywords:

Memristor;Artificial Neural Network;Hardware;Architecture;Bridge Synapse;Memristive

Brown, Michael KennethLandslide Detection and Susceptibility Mapping Using LiDAR and Artificial Neural Network Modeling: A Case Study in Glacially Dominated Cuyahoga River Valley, Ohio
Master of Science (MS), Bowling Green State University, 2012, Geology
The purpose of this study was to detect shallow landslides using hillshade maps derived from Light Detection and Ranging (LiDAR)-based Digital Elevation Model (DEM) and validated by field inventory. The landslide susceptibility mapping used an Artificial Neural Network (ANN) approach and back propagation method that was tested in the northern portion of the Cuyahoga Valley National Park CVNP) located in Northeast Ohio. The relationship between landslides and different predictor attributes extracted from the LiDAR-based-DEM such as slope, profile and plan curvatures, upslope drainage area, annual solar radiation, and wetness index was evaluated using a Geographic Information System (GIS) based investigation. The approach presented in this thesis required a training study area for the development of the susceptibility model and a validation study area to test the model. The results from the validation showed that within the very high susceptibility class, a total of 42 % of known landslides that were associated with 1.6% of total area were correctly predicted. On the other hand, the very low susceptibility class that represented 82 % of the total area was associated with 1 % of correctly predicted landslides. The results suggest that the majority of the known landslides occur within a small portion of the study area, which is consistent with field investigation and other studies. Sample probabilistic maps of landslide susceptibility potential and other products from this approach are summarized and presented for visualization which is intended to help park officials in effective management and planning.

Committee:

Peter Gorsevski, PhD (Advisor); Charles Onasch, PhD (Committee Member); Xinyue Ye, PhD (Committee Member)

Subjects:

Geographic Information Science; Geology; Geomorphology

Keywords:

Artificial Neural Network Analysis; Landslide Susceptibility; LiDAR; Cuyahoga River Valley

Li, JiakaiAI-WSN: Adaptive and Intelligent Wireless Sensor Networks
Doctor of Philosophy in Engineering, University of Toledo, 2012, College of Engineering

This dissertation research proposes embedding artificial neural networks into wireless sensor networks in parallel and distributed processing framework to implant intelligence for in-network processing, wireless protocol or application support, and infusion of adaptation capabilities. The goal is to develop in-network "intelligent computation" and "adaptation" capability for wireless sensor networks to improve their functionality, utility and survival aspects. The characteristics of wireless sensor networks bring many challenges, such as the ultra large number of sensor nodes, complex dynamics of network operation, changing topology structure, and the most importantly, the limited resources including power, computation, storage, and communication capability. All these require the applications and protocols running on wireless sensor network to be not only energy-efficient, scalable and robust, but also "adapt" to changing environment or context, and application scope and focus among others, and demonstrate intelligent behavior. The expectation from the research endeavor is to introduce computational intelligence capability for the wireless sensor networks to become adaptive to changes within a variety of operational contexts and to exhibit intelligent behavior.

The proposed novel approach entails embedding a wireless sensor network with an artificial neural network algorithm while preserving the parallelism and distributed nature of computations associated with the neural network algorithm. The procedure of embedding an artificial neural network, which may be configured for a problem either at wireless protocol or application levels, into the wireless sensor network hardware platform, which is a parallel and distributed processing system that is composed of a network of motes, is defined. This procedure is demonstrated for a case study with a Hopfield neural network and a minimum weakly connected dominating set problem as the model of wireless sensor network backbone or infrastructure. Issues and challenges pertaining to scalability, solution quality, and computational complexity for time and message are addressed through a comprehensive simulation study. Simulation study is performed using the TOSSIM environment for wireless sensor networks with mote counts up to 1000.

A comparative performance evaluation is performed. Solution quality, time and message complexity results for other centralized and distributed algorithms for connected dominating set construction as reported in the literature are used. Additionally, in-house simulation of non-distributed version of the proposed model is implemented to serve as a comparison benchmark and link to the studies in the literature. It is determined through the simulation study that the most critical factors that affect both the time complexity and the message complexity are the network size and time interval. The normalized computation time increases somewhat linearly for the most part for increases in the mote count the exception of the time interval value of 0.1 sec. The message complexity also increases with the increase in the mote count. The message complexity is not sensitive to the radio range but very sensitive to the time interval. All other parameters kept constant, the message complexity decreases with the increase in the time interval value on a consistent basis for all mote counts simulated. For smaller values of time interval, the network is more active due to motes waking up and exchanging messages more frequently, which leads to increased message complexity. The solution quality as measured by the size of the weakly connected dominating set by the proposed model is competitive with the performance exhibited by other algorithms reported in literature given all the adverse effects of computation being realized on a wireless sensor network platform. In light of the fact that there is significant opportunity to improve the entire wireless protocol stack for drastically reducing the time and space complexities through more efficient MAC, time synchronization and routing protocols, there is a strong prospect for the proposed architecture to scale up to tens of thousands of motes.

Committee:

Gursel Serpen (Committee Chair); Junghwan Kim (Committee Member); Mohsin Jamali (Committee Member); Jackson Carvalho (Committee Member); Eddie Chou (Committee Member)

Subjects:

Computer Science; Electrical Engineering

Keywords:

artificial neural network; wireless sensor network; parallel and distributed processing; weakly connected dominating set; sensor network infrastructure; Hopfield network; connected dominating set

CHANG, DYI-HUEYANALYSIS AND MODELING OF SPACE-TIME ORGANIZATION OF REMOTELY SENSED SOIL MOISTURE
PhD, University of Cincinnati, 2002, Engineering : Environmental Engineering
The characterization and modeling of the spatial variability of soil moisture is an important problem for various hydrological, ecological, and atmospheric processes. This dissertation proposes a compact representation of interdependencies among soil moisture distribution and environmental factors using two complimentary approaches. In the first approach, a stochastic framework is developed for characterizing the soil moisture distribution. The resulting model provides closed form analytical solutions for (a) the variance of soil moisture distribution; (b) the covariance between soil moisture distribution and soil properties; and (c) the covariance between soil moisture distribution and topography as a function of soil heterogeneity, topography and soil moisture. Series of simulations are performed using various combinations of parameters. Comparisons between simulated results and a number of field observations show qualitative agreement. Application of the proposed stochastic framework requires statistical information of soil characteristics. In the second approach, possibility of inferring soil physical properties from remotely sensed brightness temperature maps is explored. Remotely sensed brightness temperature data from a single drying cycle from Washita '92 Experiment and two different ANN architectures (Feed-Forward Neural Network (FFNN), Self Organizing Map (SOM)) are used to classify soil types into three categories. Results show that FFNN yield better classification accuracy (about 80% accuracy) than SOM (about 70% accuracy). The SOM, however, has an advantage because it requires very little information regarding soil properties. To classify soil into more than three categories, this study suggests the use of multiple-drying-cycle brightness temperature data. Use of multiple-drying-cycle brightness temperature data from the Southern Great Plains suggests that it is possible to classify soil into more than three groups. It appears that the requirement of rapidly changing decision boundary, in the case of space-time evolution of brightness temperature data, will restrict the FFNN model to yield better accuracy. Motivated by these observations, a simple prototype-based classifier, known as 1-NN model, is used which yield 86% classification accuracy for six textural groups. A comparison of classification error regions for both models suggests that, for the given input representation, further improvement in classification accuracy is feasible with different ANN structure.

Committee:

Dr. Shafiqul Islam (Advisor)

Keywords:

soil moisture; stochastic; artificial neural network; remote sensing; soil properties

Chowdhury, SushmitArtificial Neural Network Based Geometric Compensation for Thermal Deformation in Additive Manufacturing Processes
MS, University of Cincinnati, 2016, Engineering and Applied Science: Mechanical Engineering
Additive manufacturing (AM) processes involve the fabrication of parts in a layer wise manner. The layers of material are deposited using a variety of established methodologies, the most popular of which involve either the use of a powerful laser to sinter/melt successive layers of metal/alloy/polymer powders or, the deposition of layers of polymers through a heated extrusion head at a controlled rate. The thermal nature of these processes coupled with the varying contours of the part at different heights, causes the development of temperature gradients throughout the part and as a result, the part undergoes irregular deformations. These deformations ultimately lead to dimensional inaccuracies in the manufactured part. An Artificial Neural Network (ANN) based methodology is proposed in this research to make the required compensations to the part’s geometric design, which will help to counter the thermal deformations in the manufactured part. In this methodology, a feed-forward ANN model is trained using an error backpropagation algorithm to study part deformations resulting in the part during the AM process. The trained network is subsequently implemented on the part Stereolithography (STL) file to effect the required geometrical compensations. Two case studies are presented to illustrate the implementation of the proposed methodology. A novel approach to evaluate the final part profile resulting from the AM process, with respect to the original part CAD model profile has also been developed. This metric is used to quantify the performance of the proposed methodology. The results of the case studies show substantial improvement in the part accuracy and thus validate the ANN based geometric compensation approach.

Committee:

Sam Anand, Ph.D. (Committee Chair); Michael Alexander-Ramos, Ph.D. (Committee Member); Jing Shi, Ph.D. (Committee Member)

Subjects:

Mechanical Engineering

Keywords:

Additive Manufacturing;Thermal Deformation;Compensation;Artificial Neural Network

Iacianci, Bryon C.Confidence Intervals on Cost Estimates When Using a Feature-based Approach
Master of Science (MS), Ohio University, 2012, Industrial and Systems Engineering (Engineering and Technology)

This research explains the methodology for deriving the confidence interval on the cost estimate of a part, when a feature-based approach is used. The components of a steam turbine are used in order to demonstrate the methodology. With a parametric approach to estimate cost, developing a confidence interval is straightforward because there is one cost-estimating relationship (CER) that incorporates a design's parameters. However, in feature-based cost estimating, there are multiple CERs that each estimate the cost of a part feature and the feature estimates are accumulated to get the total manufacturing cost. This makes deriving a confidence interval more complex, since the variance in each CER must be incorporated into determining the overall variance of the estimate.

Confidence intervals are derived for multiple CER generation techniques that utilize both regression and Artificial Neural Networks. The differences between their parametric and feature-based results are statistically tested to determine whether a difference exists. The testing shows that in 7 out 8 instances tested, the differences between the two approaches were not found to be statistically significantly different. Feature-based models are more transparent than multivariate models because exactly how each parameter affects an estimate can be easily determined. When there is no difference between the two methods than the feature-based method should be used by the analyst.

Committee:

Dale Masel, PhD (Committee Chair); Robert Judd, PhD (Committee Member); Gary Weckman, PhD (Committee Member); Gary Coombs (Committee Member)

Subjects:

Engineering; Industrial Engineering

Keywords:

cost estimating relationship; artificial neural network; confidence interval; cost prediction; CER; ANN; composite confidence interval; feature based

Dravenstott, Ronald W.Restaurant Industry Stock Price Forecasting Model Utilizing Artificial Neural Networks to Combine Fundamental and Technical Analysis
Master of Science (MS), Ohio University, 2012, Industrial and Systems Engineering (Engineering and Technology)
Stock price forecasting is a classic problem facing analysts. Forcasting models have been developed for predicting individual stocks and stock indices around the world and in numerous industries. According to a literature review, these models have yet to be applied to the restaurant industry. Strategies for forecasting typically include fundamental and technical variables. In this thesis, fundamental and technical inputs were combined into an Artificial Neural Network stock prediction model for the restaurant industry. Models were designed to forecast 1 week, 4 weeks, and 13 weeks into the future. The model performed better than the benchmarks. The prediction accuracy of the model reached as high as 60%. The model with the most success was a Multilayer Perceptron Artificial Neural Network with 2 hidden layers having 40 and 20 processing elements in those layers using the hyperbolic tangent transfer function and Delta Bar Delta learning algorithm.

Committee:

Gary Weckman, PhD (Committee Chair); Tao Yuan, PhD (Committee Member); Namkyu Park, PhD (Committee Member); Andy Snow, PhD (Committee Member)

Subjects:

Engineering; Finance; Industrial Engineering

Keywords:

Artificial Neural Network; ANN; Restaurant; Stock Price Forecast; Fundamental Analysis; Technical Analysis

Crossen, Samantha LokelaniInvestigation of Variability in Cognitive State Assessment based on Electroencephalogram-derived Features
Master of Science in Engineering (MSEgr), Wright State University, 2011, Biomedical Engineering
To implement adaptive aiding in modern aviation systems there is a need for accurate and reliable classification of cognitive workload. Using electroencephalogram (EEG)-derived features, it has been reported that an Artificial Neural Network (ANN) can achieve 95% or higher classification accuracy on the same day for an individual operator, but only 70% or less on a different day. To gain a further insight into this discrepancy, data from a previous study was utilized to study the classification variability. The EEG-derived features were first calculated by spectral power estimation. The variability was then analyzed by performing cognitive workload classification in which different methods of training and testing were used and different classifiers were implemented to compare classification accuracies. The classifiers include an ANN, Adaboost Algorithm, and a t-test method. The results show that when the ANN or Adaboost method is used, the amount of overlapping among training and testing data impacts the classification accuracy significantly. When there is no overlap, all classifiers can only achieve an accuracy of about 70%, with the Adaboost outperforming other classifiers slightly. By allowing some overlap, the accuracy of the ANN or Adaboost method increases significantly. It was concluded that the main source of the classification variability is the inherent variability of the EEG-derived features.

Committee:

Ping He, PhD (Advisor); James Christensen, PhD (Committee Member); Yan Liu, PhD (Committee Member)

Subjects:

Biomedical Research

Keywords:

Electroencephalogram (EEG); Artificial Neural Network (ANN); AdaBoost Algorithm; Workload Classification; Feature Variability

Abounia Omran, BehzadApplication of Data Mining and Big Data Analytics in the Construction Industry
Doctor of Philosophy, The Ohio State University, 2016, Food, Agricultural and Biological Engineering
In recent years, the digital world has experienced an explosion in the magnitude of data being captured and recorded in various industry fields. Accordingly, big data management has emerged to analyze and extract value out of the collected data. The traditional construction industry is also experiencing an increase in data generation and storage. However, its potential and ability for adopting big data techniques have not been adequately studied. This research investigates the trends of utilizing big data techniques in the construction research community, which eventually will impact construction practice. For this purpose, the application of 26 popular big data analysis techniques in six different construction research areas (represented by 30 prestigious construction journals) was reviewed. Trends, applications, and their associations in each of the six research areas were analyzed. Then, a more in-depth analysis was performed for two of the research areas including construction project management and computation and analytics in construction to map the associations and trends between different construction research subjects and selected analytical techniques. In the next step, the results from trend and subject analysis were used to identify a promising technique, Artificial Neural Network (ANN), for studying two construction-related subjects, including prediction of concrete properties and prediction of soil erosion quantity in highway slopes. This research also compared the performance and applicability of ANN against eight predictive modeling techniques commonly used by other industries in predicting the compressive strength of environmentally friendly concrete. The results of this research provide a comprehensive analysis of the current status of applying big data analytics techniques in construction research, including trends, frequencies, and usage distribution in six different construction-related research areas, and demonstrate the applicability and performance level of selected data analytics techniques with an emphasis on ANN in construction-related studies. The main purpose of this dissertation was to help practitioners and researchers identify a suitable and applicable data analytics technique for their specific construction/research issue(s) or to provide insights into potential research directions.

Committee:

Qian Chen, Dr. (Advisor)

Subjects:

Civil Engineering; Comparative Literature; Computer Science

Keywords:

Construction Industry; Big Data; Data Analytics; Data mining; Artificial Neural Network; ANN; Compressive Strength; Environmentally Friendly Concrete; Soil Erosion; Highway Slope; Predictive Modeling; Comparative Analysis

Gnanasekar, NithyakumaranTemperature and Hourly Precipitation Prediction System for Road Bridge using Artificial Neural Networks
MS, University of Cincinnati, 2015, Engineering and Applied Science: Computer Science
UCII has designed and built the Weather monitoring system for Bridges, at multiple locations in North America. The Weather Monitoring System collects data from the local weather stations, airports around the bridge and the sensors installed on the bridge. This data is analyzed for inclement weather conditions on and around the bridge and whenever an abnormal behavior is detected, “Alarms” are sent out via email. Using the large amount of data collected from various stations and sensors correlation between every variable is studied. This detailed study is later used to build Eight Hour Ahead Temperature Prediction system and a Four Hours Ahead Hourly Precipitation Prediction System. The Prediction system uses machine learning techniques to predict new data based on prior data. The Atmospheric variables collected such as temperature, pressure, humidity, hourly precipitation, wind speed, wind direction, solar radiation is analyzed. The correlation between the afore-mentioned variables on time scale is also analyzed and is discussed in detail which aided in building the Prediction models. The prediction system uses an Artificial Neural network to train and provide predictions. The prediction system was designed and built to be used alongside Weather Monitoring system built by UCII and to further its intelligence coefficient in predicting inclement weather condition.

Committee:

Arthur Helmicki, Ph.D. (Committee Chair); Victor Hunt, Ph.D. (Committee Member); Paul Talaga, Ph.D. (Committee Member)

Subjects:

Engineering

Keywords:

Artificial Neural Network;Road way bridge;local weather prediction;weather monitoring system