Computer Sciences Commons^™

Information Measures For Statistical Orbit Determination, Alinda Kenyana Mashiku

Open Access Dissertations

The current Situational Space Awareness (SSA) is faced with a huge task of tracking the increasing number of space objects. The tracking of space objects requires frequent and accurate monitoring for orbit maintenance and collision avoidance using methods for statistical orbit determination. Statistical orbit determination enables us to obtain estimates of the state and the statistical information of its region of uncertainty given by the probability density function (PDF). As even collision events with very low probability are important, accurate prediction of collisions require the representation of the full PDF of the random orbit state. Through representing the full PDF …

Prediction Of Emissions And Exhaust Temperature For Direct Injection Diesel Engine With Emulsified Fuel Using Ann, Görkem Kökkülünk, Erhan Akdoğan, Vezi̇r Ayhan

Turkish Journal of Electrical Engineering and Computer Sciences

Exhaust gases have many effects on human beings and the environment. Therefore, they must be kept under control. The International Convention for the Prevention of Pollution from Ships (MARPOL), which is concerned with the prevention of marine pollution, limits the emissions according to the regulations. In Emission Control Area (ECA) regions, which are determined by MARPOL as ECAs, the emission rates should be controlled. Direct injection (DI) diesel engines are commonly used as a propulsion system on ships. The prediction and control of diesel engine emission rates is not an easy task in real time. Therefore, in this study, an …

Dinosolve: A Protein Disulfide Bonding Prediction Server Using Context-Based Features To Enhance Prediction Accuracy, Ashraf Yaseen, Yaohang Li

Computer Science Faculty Publications

Background: Disulfide bonds play an important role in protein folding and structure stability. Accurately predicting disulfide bonds from protein sequences is important for modeling the structural and functional characteristics of many proteins.

Methods: In this work, we introduce an approach of enhancing disulfide bonding prediction accuracy by taking advantage of context-based features. We firstly derive the first-order and second-order mean-force potentials according to the amino acid environment around the cysteine residues from large number of cysteine samples. The mean-force potentials are integrated as context-based scores to estimate the favorability of a cysteine residue in disulfide bonding state as well as …

Motivated Learning For The Development Of Autonomous Agents, Janusz A. Starzyk, James T. Graham, Pawel Raif, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

A new machine learning approach known as motivated learning (ML) is presented in this work. Motivated learning drives a machine to develop abstract motivations and choose its own goals. ML also provides a self-organizing system that controls a machine’s behavior based on competition between dynamically-changing pain signals. This provides an interplay of externally driven and internally generated control signals. It is demonstrated that ML not only yields a more sophisticated learning mechanism and system of values than reinforcement learning (RL), but is also more efficient in learning complex relations and delivers better performance than RL in dynamically changing environments. In …

Forecasting Natural Gas Consumption In İstanbul Using Neural Networks And Multivariate Time Series Methods, Ömer Fahretti̇n Demi̇rel, Seli̇m Zai̇m, Ahmet Çalişkan, Pinar Özuyar

Turkish Journal of Electrical Engineering and Computer Sciences

The fast changes and developments in the world's economy have substantially increased energy consumption. Consequently, energy planning has become more critical and important. Forecasting is one of the main tools utilized in energy planning. Recently developed computational techniques such as genetic algorithms have led to easily produced and accurate forecasts. In this paper, a natural gas consumption forecasting methodology is developed and implemented with state-of-the-art techniques. We show that our forecasts are quite close to real consumption values. Accurate forecasting of natural gas consumption is extremely critical as the majority of purchasing agreements made are based on predictions. As a …

Decentralized Optimal Control Of A Class Of Interconnected Nonlinear Discrete-Time Systems By Using Online Hamilton-Jacobi-Bellman Formulation, Shahab Mehraeen, Sarangapani Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

In this paper, the direct neural dynamic programming technique is utilized to solve the Hamilton-Jacobi-Bellman equation forward-in-time for the decentralized near optimal regulation of a class of nonlinear interconnected discrete-time systems with unknown internal subsystem and interconnection dynamics, while the input gain matrix is considered known. Even though the unknown interconnection terms are considered weak and functions of the entire state vector, the decentralized control is attempted under the assumption that only the local state vector is measurable. the decentralized nearly optimal controller design for each subsystem consists of two neural networks (NNs), an action NN that is aimed to …

Multidisciplinary Design Optimization Of Transonic Airfoil Sections Using Multiobjective Optimization And Computational Intelligence Tools, Amit A. Kulkarni

Mechanical & Aerospace Engineering Theses & Dissertations

The design of transonic airfoils for civil aviation applications has been a major engineering challenge in the last fifty years. This design problem arises due to the need to limit shock wave drag at a given transonic speed. In recent years, the requirement to reduce the levels of aircraft noise has started to affect the airfoil design process. The multidisciplinary aerodynamic shape optimization problem is treated in this thesis using a multi-objective approach. The objectives correspond to the design of transonic airfoil sections with low drag during cruise and low trailing edge noise levels during the approach condition. The optimization …

Solving The Vehicle Re-Identification Problem By Using Neural Networks, Tanweer Rashid

Computational Modeling & Simulation Engineering Theses & Dissertations

Vehicle re-identification is the process by which vehicle attributes measured at one point on a road network are compared to vehicle attributes measured at another point in an effort to match vehicles without using any unique identifiers such as license plate numbers. A match is made if the two measurements are estimated to belong to the same vehicle. Vehicle attributes can be sensor readings such as loop induction signatures, or they can also be actual vehicle characteristics such as length, weight, number of axles, etc. This research makes use of vehicle length, travel time, axle spacing and axle weights for …

The Design Of A Computer System To Determine The Causes Of Edema Using Magnetic Resonance Spectroscopy, Carl Allen Fink

LSU Master's Theses

Diabetes is a growing problem in the U.S.A., closely linked to the current obesity epidemic. Two common complications of diabetes, osteomyelitis of the foot, and Charcot's joint, are impossible to differentiate via traditional Magnetic Resonance Imaging. The background of Magnetic Resonance Spectroscopy, which transforms the time-domain MRI signal into the frequency domain spectrum, is explored, and its use to aid in this differentiation is proposed. Artificial Neural Networks can be employed to evaluate the MRS data and to automate the process.

An Investigation Into The Use Of Neural Networks For The Prediction Of The Stock Exchange Of Thailand, Suchira Chaigusin

Theses: Doctorates and Masters

Stock markets are affected by many interrelated factors such as economics and politics at both national and international levels. Predicting stock indices and determining the set of relevant factors for making accurate predictions are complicated tasks. Neural networks are one of the popular approaches used for research on stock market forecast. This study developed neural networks to predict the movement direction of the next trading day of the Stock Exchange of Thailand (SET) index. The SET has yet to be studied extensively and research focused on the SET will contribute to understanding its unique characteristics and will lead to identifying …

A Structure First Image Inpainting Approach Based On Self-Organizing Map (Som), Bo Chen, Zhaoxia Wang, Ming Bai, Quan Wang, Zhen Sun

Research Collection School Of Computing and Information Systems

This paper presents a structure first image inpainting method based on self-organizing map (SOM). SOM is employed to find the useful structure information of the damaged image. The useful structure information which includes relevant edges of the image is used to simulate the structure information of the lost or damaged area in the image. The structure information is described by distinct or indistinct curves in an image in this paper. The obtained target curves separate the damaged area of the image into several parts. As soon as each part of the damaged image is restored respectively, the damaged image is …

Electroencephalogram Artifact Removal Using A Wavelet Neural Network, Hoang-Anh T. Nguyen

Electrical & Computer Engineering Theses & Dissertations

A wavelet neural network (WNN) technique rs developed for electroencephalogram (EEG) artifact removal without electrooculographic (EOG) recordings. The algorithm combines the universal approximation characteristics of neural networks and the time/frequency property of wavelet, where the neural network was trained on a simulated dataset with known ground truths. The contribution of this thesis is two-fold. First, many EEG artifact removal algorithms, including regression based methods, require reference EOG signals, which are not always available. To remove EEG ai1ifacts, a WNN tries to learn the characteristics of the artifacts first and does not need reference EOG signals once trained. Second, WNNs are …

Extreme Data Mining: Inference From Small Datasets, Răzvan Andonie

All Faculty Scholarship for the College of the Sciences

Neural networks have been applied successfully in many fields. However, satisfactory results can only be found under large sample conditions. When it comes to small training sets, the performance may not be so good, or the learning task can even not be accomplished. This deficiency limits the applications of neural network severely. The main reason why small datasets cannot provide enough information is that there exist gaps between samples, even the domain of samples cannot be ensured. Several computational intelligence techniques have been proposed to overcome the limits of learning from small datasets.

We have the following goals: i. To …

Zero-Sum Two-Player Game Theoretic Formulation Of Affine Nonlinear Discrete-Time Systems Using Neural Networks, S. Mehraeen, T. Dierks, S. Jagannathan, M. L. Crow

Electrical and Computer Engineering Faculty Research & Creative Works

In this paper, the nearly optimal solution for discrete-time (DT) affine nonlinear control systems in the presence of partially unknown internal system dynamics and disturbances is considered. the approach is based on successive approximate solution of the Hamilton-Jacobi-Isaacs (HJI) equation, which appears in optimal control. Successive approximation approach for updating control input and disturbance for DT nonlinear affine systems are proposed. Moreover, sufficient conditions for the convergence of the approximate HJI solution to the saddle-point are derived, and an iterative approach to approximate the HJI equation using a neural network (NN) is presented. Then, the requirement of full knowledge of …

Neural Network Control Of Quadrotor Uav Formations, Travis Dierks, Sarangapani Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

In this paper, a novel framework for leader-follower formation control is developed for the control of multiple quadrotors unmanned aerial vehicles (UAVs) based on spherical coordinates. the control objective for the follower UAV is to track its leader at a desired- separation, angle of incidence, and a bearing by using an auxiliary velocity control. Then, a novel neural network (NN) control law for the dynamical system is introduced to learn the complete dynamics of the UAV including unmodeled dynamics like aerodynamic friction. Additionally, the interconnection dynamic errors between the leader and its followers are explicitly considered, and the stability of …

Decentralized Control Of Large Scale Interconnected Systems Using Adaptive Neural Network-Based Dynamic Surface Control, Shahab Mehraeen, Sarangapani Jagannathan, Mariesa L. Crow

Electrical and Computer Engineering Faculty Research & Creative Works

A novel decentralized controller using the dynamic surface control (DSC) is proposed for a class of uncertain large scale interconnected nonlinear systems in strict feedback form while relaxing the "explosion of complexity" problem which is observed in the typical backstepping approach. the matching condition is not assumed when dealing with the interconnection terms. Neural networks (NNs) are utilized to approximate the uncertainties in both subsystem and interconnected terms. by using novel NN weight update laws, it is demonstrated using Lyapunov stability that the closed-loop signals are asymptotically stable in the presence of NN approximation errors in contrast with the uniform …

Artificial Intelligence – I: A Two-Step Approach For Improving Efficiency Of Feedforward Multilayer Perceptrons Network, Shoukat Ullah, Zakia Hussain

International Conference on Information and Communication Technologies

An artificial neural network has got greater importance in the field of data mining. Although it may have complex structure, long training time, and uneasily understandable representation of results, neural network has high accuracy and is preferable in data mining. This research paper is aimed to improve efficiency and to provide accurate results on the basis of same behaviour data. To achieve these objectives, an algorithm is proposed that uses two data mining techniques, that is, attribute selection method and cluster analysis. The algorithm works by applying attribute selection method to eliminate irrelevant attributes, so that input dimensionality is reduced …

Multilayer Image Inpainting Approach Based On Neural Networks, Quan Wang, Zhaoxia Wang, Che Sau Chang, Ting Yang

Research Collection School Of Computing and Information Systems

This paper describes an image inpainting approach based on the self-organizing map for dividing an image into several layers, assigning each damaged pixel to one layer, and then restoring these damaged pixels by the information of their respective layer. These inpainted layers are then fused together to provide the final inpainting results. This approach takes advantage of the neural network's ability of imitating human's brain to separate objects of an image into different layers for inpainting. The approach is promising as clearly demonstrated by the results in this paper.

Analysis Of Electroencephalogram Signals For The Identification Of Mental Tasks, My Thy Thi Tran

Electrical & Computer Engineering Theses & Dissertations

Electroencephalogram (EEG) signals can be used for implicit communication such as to control robots or medical equipment by brain activity or to detect an individual's intentions of committing premeditated crimes. An EEG based brain-computer interface allows paralyzed patients to express their thoughts. However, biological and technical artifacts heavily interfered with EEG signals due to blinking of the eyes, muscle activities and line noise. Sometimes the noise interference due to signal artifacts becomes more prominent than the information content. This thesis investigates novel feature extraction methodologies in EEG signals to represent different thought processes and employs neural network-based pattern classification techniques …

Sub-Symbolic Re-Representation To Facilitate Learning Transfer, Dan A. Ventura

Faculty Publications

We consider the issue of knowledge (re-)representation in the context of learning transfer and present a subsymbolic approach for effecting such transfer. Given a set of data, manifold learning is used to automatically organize the data into one or more representational transformations, which are then learned with a set of neural networks. The result is a set of neural filters that can be applied to new data as re-representation operators. Encouraging preliminary empirical results elucidate the approach and demonstrate its feasibility, suggesting possible implications for the broader field of creativity.

Multi-Order Neurons For Evolutionary Higher Order Clustering And Growth, Kiruthika Ramanathan, Sheng Uei Guan

Research Collection School Of Computing and Information Systems

This letter proposes to use multiorder neurons for clustering irregularly shaped data arrangements. Multiorder neurons are an evolutionary extension of the use of higher-order neurons in clustering. Higher-order neurons parametrically model complex neuron shapes by replacing the classic synaptic weight by higher-order tensors. The multiorder neuron goes one step further and eliminates two problems associated with higher-order neurons. First, it uses evolutionary algorithms to select the best neuron order for a given problem. Second, it obtains more information about the underlying data distribution by identifying the correct order for a given cluster of patterns. Empirically we observed that when the …

Improving Machine Learning Through Oracle Learning, Joshua Ephraim Menke

Theses and Dissertations

The following dissertation presents a new paradigm for improving the training of machine learning algorithms, oracle learning. The main idea in oracle learning is that instead of training directly on a set of data, a learning model is trained to approximate a given oracle's behavior on a set of data. This can be beneficial in situations where it is easier to obtain an oracle than it is to use it at application time. It is shown that oracle learning can be applied to more effectively reduce the size of artificial neural networks, to more efficiently take advantage of domain experts …

Clustering And Combinatorial Optimization In Recursive Supervised Learning, Kiruthika Ramanathan, Sheng Uei Guan

Research Collection School Of Computing and Information Systems

The use of combinations of weak learners to learn a dataset has been shown to be better than the use of a single strong learner. In fact, the idea is so successful that boosting, an algorithm combining several weak learners for supervised learning, has been considered to be the best off the shelf classifier. However, some problems still exist, including determining the optimal number of weak learners and the over fitting of data. In an earlier work, we developed the RPHP algorithm which solves both these problems by using a combination of global search, weak learning and pattern distribution. In …

Firearm Identification With Hierarchical Neural Networks By Analyzing The Firing Pin Images Retrieved From Cartridge Cases, Dongguang Li

Research outputs pre 2011

When a gun is fired, characteristic markings on the cartridge and projectile of a bullet are produced. Over thirty different features can be distinguished from observing these marks, which in combination produce a "fingerprint" for identification of a firearm. ln this paper, through the use of hierarchial neural networks a firearm identification system based on cartridge case images is proposed. We focus on the cartridge case identification of rim-fire mechanism. Experiments show that the model proposed has high performance and robustness by integrating two levels Self- Organizing Feature Map (SOFM) neural networks and the decision-making strategy. This model will also …

Exploration Of Computational Methods For Classification Of Movement Intention During Human Voluntary Movement From Single Trial Eeg, Ou Bai, Peter Lin, Sherry Vorbach, Jiang Li, Steve Furlani, Mark Hallett

Electrical & Computer Engineering Faculty Publications

Objective: To explore effective combinations of computational methods for the prediction of movement intention preceding the production of self-paced right and left hand movements from single trial scalp electroencephalogram (EEG).

Methods: Twelve naïve subjects performed self-paced movements consisting of three key strokes with either hand. EEG was recorded from 128 channels. The exploration was performed offline on single trial EEG data. We proposed that a successful computational procedure for classification would consist of spatial filtering, temporal filtering, feature selection, and pattern classification. A systematic investigation was performed with combinations of spatial filtering using principal component analysis (PCA), independent component analysis …

Min–Max Hyperellipsoidal Clustering For Anomaly Detection In Network Security, Suseela T. Sarasamma, Qiuming Zhu

Computer Science Faculty Publications

A novel hyperellipsoidal clustering technique is presented for an intrusion-detection system in network security. Hyperellipsoidal clusters toward maximum intracluster similarity and minimum intercluster similarity are generated from training data sets. The novelty of the technique lies in the fact that the parameters needed to construct higher order data models in general multivariate Gaussian functions are incrementally derived from the data sets using accretive processes. The technique is implemented in a feedforward neural network that uses a Gaussian radial basis function as the model generator. An evaluation based on the inclusiveness and exclusiveness of samples with respect to specific criteria is …

Learning As A Nonlinear Line Of Attraction For Pattern Association, Classification And Recognition, Ming-Jung Seow

Electrical & Computer Engineering Theses & Dissertations

Development of a mathematical model for learning a nonlinear line of attraction is presented in this dissertation, in contrast to the conventional recurrent neural network model in which the memory is stored in an attractive fixed point at discrete location in state space. A nonlinear line of attraction is the encapsulation of attractive fixed points scattered in state space as an attractive nonlinear line, describing patterns with similar characteristics as a family of patterns.

It is usually of prime imperative to guarantee the convergence of the dynamics of the recurrent network for associative learning and recall. We propose to alter …

Gaussian Mixture Models And Neural Networks For Automatic Speaker Identification, Usha Gayatri Chalkapally

Electrical & Computer Engineering Theses & Dissertations

Automatic Speaker Recognition is the process of automatically recognizing who is speaking on the basis of individual information contained in speech signals. This technique of Automatic Speaker Recognition makes it possible to use the speaker's voice to verify their identity and control access to services such as voice dialing, banking by telephone, telephone shopping, database access services, information services, voice mail, security control for confidential information areas, and remote access to computers.

In this thesis, the techniques of Gaussian Mixture Models and Neural Networks for Automatic Speaker Identification are presented. Algorithms for Speaker Identification using Gaussian Mixture Models were developed, …

Whole Word Phonetic Displays For Speech Articulation Training, Fansheng Meng

Electrical & Computer Engineering Theses & Dissertations

The main objective of this dissertation is to investigate and develop speech recognition technologies for speech training for people with hearing impairments. During the course of this work, a computer aided speech training system for articulation speech training was also designed and implemented. The speech training system places emphasis on displays to improve children's pronunciation of isolated Consonant-Vowel-Consonant (CVC) words, with displays at both the phonetic level and whole word level. This dissertation presents two hybrid methods for combining Hidden Markov Models (HMMs) and Neural Networks (NNs) for speech recognition. The first method uses NN outputs as posterior probability estimators …

Hybrid Committee Classifier For A Computerized Colonic Polyp Detection System, Jiang Li, Jianhua Yao, Nicholas Petrick, Ronald M. Summers, Amy K. Hara, Joseph M. Reinhardt (Ed.), Josien P.W. Pluim (Ed.)

Electrical & Computer Engineering Faculty Publications

We present a hybrid committee classifier for computer-aided detection (CAD) of colonic polyps in CT colonography (CTC). The classifier involved an ensemble of support vector machines (SVM) and neural networks (NN) for classification, a progressive search algorithm for selecting a set of features used by the SVMs and a floating search algorithm for selecting features used by the NNs. A total of 102 quantitative features were calculated for each polyp candidate found by a prototype CAD system. 3 features were selected for each of 7 SVM classifiers which were then combined to form a committee of SVMs classifier. Similarly, features …