Current Search: Neural networks Computer science (x)
View All Items
Pages
- Title
- Design of analog building blocks useful for artificial neural networks.
- Creator
- Renavikar, Ajit Anand., Florida Atlantic University, Shankar, Ravi, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
- Abstract/Description
-
Software simulations of a scaleable VLSI implementable architecture and algorithm for character recognition by a research group at Florida Atlantic University (FAU) have shown encouraging results. We address here hardware implementation issues pertinent to the classification phase of character recognition. Using the digit classification techniques developed at FAU as a foundation, we have designed and simulated general purpose building blocks useful for a possible implementation of a Digital ...
Show moreSoftware simulations of a scaleable VLSI implementable architecture and algorithm for character recognition by a research group at Florida Atlantic University (FAU) have shown encouraging results. We address here hardware implementation issues pertinent to the classification phase of character recognition. Using the digit classification techniques developed at FAU as a foundation, we have designed and simulated general purpose building blocks useful for a possible implementation of a Digital & Analog CMOS VLSI chip that is suitable for a variety of artificial neural network (ANN) architectures. HSPICE was used to perform circuit-level simulations of the building blocks. We present here the details of implementation of the recognition chip including the architecture, circuit design and the simulation results.
Show less - Date Issued
- 1996
- PURL
- http://purl.flvc.org/fcla/dt/15328
- Subject Headings
- Neural networks (Computer science), Artificial intelligence, Optical character recognition devices, Pattern recognition systems
- Format
- Document (PDF)
- Title
- Modeling of reverse osmosis plants using system identification and neural networks.
- Creator
- Saengrung, Anucha, Florida Atlantic University, Zilouchian, Ali, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
- Abstract/Description
-
Modeling of two reverse osmosis plants at FAU Gumbo Limbo facility and at the city of Boca Raton are investigated. System identification as well as artificial neural networks are utilized to carried out the tasks. The data for a six months operational period of both plants are utilized. The prediction error method and subspace method are utilized to estimate state-space model while the auto regression with extra input (ARX) model is estimated by using the least square method and the...
Show moreModeling of two reverse osmosis plants at FAU Gumbo Limbo facility and at the city of Boca Raton are investigated. System identification as well as artificial neural networks are utilized to carried out the tasks. The data for a six months operational period of both plants are utilized. The prediction error method and subspace method are utilized to estimate state-space model while the auto regression with extra input (ARX) model is estimated by using the least square method and the approximately optimal four-stage instrumental variable method. The training algorithms for artificial neural networks are based on backpropagation and radial basis network function (RBNF). The implementation of each methodology is performed step by step and finally, the results from both methodologies are analyzed and discussed. The results of the proposed study indicate that both system identification and neural networks algorithms can predict the outputs of both RO plants with the acceptable accuracy. Among all methodologies utilized in the thesis, the least square method for the auto regression with the extra input (ARX) model, can provide the best prediction for both RO plants.
Show less - Date Issued
- 2002
- PURL
- http://purl.flvc.org/fcla/dt/12963
- Subject Headings
- Saline water conversion--Reverse osmosis process, System identification, Neural networks (Computer science)
- Format
- Document (PDF)
- Title
- Neural Information Processing Underlying Rhythmic Bimanual Coordination: Theory, Method and Experiment.
- Creator
- Banerjee, Arpan, Jirsa, Viktor K., Florida Atlantic University
- Abstract/Description
-
How do neuronal connectivity and the dynamics of distributed brain networks process information during bimanual coordination? Contemporary brain theories of cognitive function posit spatial, temporal and spatiotemporal network reorganization as mechanisms for neural information processing. In this dissertation, rhythmic bimanual coordination is studied as a window into neural information processing and subsequently an investigation of underlying network reorganization processes is performed....
Show moreHow do neuronal connectivity and the dynamics of distributed brain networks process information during bimanual coordination? Contemporary brain theories of cognitive function posit spatial, temporal and spatiotemporal network reorganization as mechanisms for neural information processing. In this dissertation, rhythmic bimanual coordination is studied as a window into neural information processing and subsequently an investigation of underlying network reorganization processes is performed. Spatiotemporal reorganization between effectors (limbs) is parameterized in a theoretical model via a continuously varying cross-talk parameter that represents neural connectivity. Thereby, effector dynamics during coordinated behavior is shown to be influenced by the cross-talk parameter and time delays involved in signal processing. In particular, stability regimes of coordination patterns as a function of cross-talk, movement frequency and the time delays are derived. On the methodological front , spatiotemporal reorganization of neural masses are used to simulate electroencephalographic data. A suitable choice of experimental control conditions is used to derive a paradigmatic framework called Mode Level Cognitive Subtraction (MLCS) which is demonstrated to facilitate the disambiguation between spatial and temporal components of the reorganization processes to a quantifiable degree of certainty. In the experimental section, MLCS is applied to electroencephalographic recordings during rhythmic bimanual task conditions and unimanual control conditions. Finally, a classification of reorganization processes is achieved for differing stability states of coordination: inphase (mirror) primarily entails temporal reorganization of sensorimotor networks localized during unimanual movement whereas spatiotemporal reorganization is involved during antiphase (parallel) coordination.
Show less - Date Issued
- 2007
- PURL
- http://purl.flvc.org/fau/fd/FA00000849
- Subject Headings
- Neural networks (Computer science), Biological control systems, Mind and body, Cognitive psychology
- Format
- Document (PDF)
- Title
- Neural field dynamics under vari ation of local and global connectivity and finite t ransmission speeds.
- Creator
- Qubbaj, Murad R., Florida Atlantic University, Jirsa, Viktor K., Charles E. Schmidt College of Science, Department of Physics
- Abstract/Description
-
Spatially continuous networks with heterogeneous connections are ubiquitous in biological systems, in part icular neural systems. To understand the mutual effects of locally homogeneous and globally heterogeneous connectivity, the st ability of the steady state activity of a neural field as a fun ction of its connectivity is investigated. The variation of the connectivity is operationalized through manipulation of a heterogeneous two-point connection embedded into the otherwise homogeneous...
Show moreSpatially continuous networks with heterogeneous connections are ubiquitous in biological systems, in part icular neural systems. To understand the mutual effects of locally homogeneous and globally heterogeneous connectivity, the st ability of the steady state activity of a neural field as a fun ction of its connectivity is investigated. The variation of the connectivity is operationalized through manipulation of a heterogeneous two-point connection embedded into the otherwise homogeneous connectivity matrix and by variation of connectivity strength and transmission speed. A detailed discussion of the example of the real Ginzburg-Land au equation with an embedded two-point heterogeneous connection in addition to the homogeneous coupling due to the diffusion term is performed. The system is reduced to a set of delay differential equations and the stability di agrams as a function of the time delay and the local and global coupling strengths are computed. The major finding is that the stability of the heterogeneously connected elements with a well-defined velocity defines a lower bound for the stabil ity of the entire system . Diffusion and velocity dispersion always result in increased stability. Various other local architectures represented by exponentially decaying connectivity fun ctions are also discussed. The analysis shows that developmental changes such as the myelination of the cortical large-scale fib er system generally result in the stabilization of steady state activity via oscillatory instabilities independent of the local connectivity. Non-oscillatory (Turing) instabilities are shown to be independent of any influences of time delay.
Show less - Date Issued
- 2007
- PURL
- http://purl.flvc.org/fau/fd/FA00000873
- Subject Headings
- Mathematical physics, Connections (Mathematics), Superconductivity--Mathematics, Neural networks (Computer science)
- Format
- Document (PDF)
- Title
- Neural network based routing optimization for ATM switching networks.
- Creator
- Sen, Ercan., Florida Atlantic University, Pandya, Abhijit S., College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
- Abstract/Description
-
This dissertation proposes amodular Artificial Neural Network (ANN) based buffer allocation and routing control model for ATM switching networks. The proposed model considers limited buffer capacity which can adversely impact the switching performance of ATM switching networks. The proposed ANN based approach takes advantage of the favorable control characteristics of neural networks such as high adaptability and high speed collective computing power for effective buffer utilization. The...
Show moreThis dissertation proposes amodular Artificial Neural Network (ANN) based buffer allocation and routing control model for ATM switching networks. The proposed model considers limited buffer capacity which can adversely impact the switching performance of ATM switching networks. The proposed ANN based approach takes advantage of the favorable control characteristics of neural networks such as high adaptability and high speed collective computing power for effective buffer utilization. The proposed model uses complete sharing buffer allocation strategy and enhances its performance for high traffic loads by regulating the buffer allocation process dynamically via a neural network based controller. In this study, we considered the buffer allocation problem in the context of routing optimization in ATM networks. The modular structure of the proposed model separates the buffer allocation from the actual routing of ATM cells through the switching fabric and allows adaptation of the neural control for routing to different switching structures. The influence of limited buffer capacity, routing conflicts, statistical correlation between arriving ATM cells and cell burst length on ATM switching performance are analyzed and illustrated through computer simulation.
Show less - Date Issued
- 1996
- PURL
- http://purl.flvc.org/fcla/dt/12491
- Subject Headings
- Asynchronous transfer mode, Packet switching (Data transmission), Neural networks (Computer science)
- Format
- Document (PDF)
- Title
- Forecasting foreign exchange rates using neural networks.
- Creator
- Talati, Amit H., Florida Atlantic University, Pandya, Abhijit S., College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
- Abstract/Description
-
Time series is a phenomena which appears in the financial world in various forms. One of the objectives of time series is to forecast the future based on the past. The goal of this thesis is to use foreign exchange time series, and predict its future values and trends using neural networks. The thesis covers background work in this area and discusses the results obtained by other researchers. A neural network is then developed to predict the future values of the USD/GBP and USD/DEM exchange...
Show moreTime series is a phenomena which appears in the financial world in various forms. One of the objectives of time series is to forecast the future based on the past. The goal of this thesis is to use foreign exchange time series, and predict its future values and trends using neural networks. The thesis covers background work in this area and discusses the results obtained by other researchers. A neural network is then developed to predict the future values of the USD/GBP and USD/DEM exchange rates. Both single-step and iterated multi-step predictions are considered. The performance of neural networks strongly depends on the inputs supplied. The effect of the changes in the number of inputs is also considered, and a method suggested for deciding on the optimum number. The forecasting of foreign exchange rates is a challenge because of the dynamic nature of the FOREX market and its dependencies on world events. The tool used for building the neural network and validating the approach is "Brainmaker".
Show less - Date Issued
- 2000
- PURL
- http://purl.flvc.org/fcla/dt/12699
- Subject Headings
- Foreign exchange rates--Mathmematical models, Foreign exchange--Forecasting--Mathematical models, Neural networks (Computer science)
- Format
- Document (PDF)
- Title
- Tool wear monitoring using artificial neural networks.
- Creator
- Kurapati, Venkatesh., Florida Atlantic University, Masory, Oren, College of Engineering and Computer Science, Department of Ocean and Mechanical Engineering
- Abstract/Description
-
An on-line scheme for monitoring tool wear in unmanned machining operations using artificial neural networks (ANNs) is proposed. Various configurations of ANNs are studied to increase the accuracy of tool wear estimation. With this aim three configurations of the ANNs namely, an ANN without memory, an ANN with one phase memory, and an ANN with two phase memory are considered. Each ANN is trained to associate an input vector which consists of values of cutting conditions, with an output vector...
Show moreAn on-line scheme for monitoring tool wear in unmanned machining operations using artificial neural networks (ANNs) is proposed. Various configurations of ANNs are studied to increase the accuracy of tool wear estimation. With this aim three configurations of the ANNs namely, an ANN without memory, an ANN with one phase memory, and an ANN with two phase memory are considered. Each ANN is trained to associate an input vector which consists of values of cutting conditions, with an output vector containing flank wear as a single output. The training data and evaluation data is generated using the popular analytical tool wear model. The performance of all the ANNs are compared by considering four different cases of evaluation data. The proposed scheme of tool wear modeling using ANNs is easily extendible to include other cutting parameters and can be implemented in real-time.
Show less - Date Issued
- 1992
- PURL
- http://purl.flvc.org/fcla/dt/14868
- Subject Headings
- Neural networks (Computer science), Flexible manufacturing systems, Power tools, Machine tools--Data processing
- Format
- Document (PDF)
- Title
- An intelligent neural network forecaster to predict the Standard & Poor 500's index.
- Creator
- Shah, Sulay Bipin., Florida Atlantic University, Pandya, Abhijit S., College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
- Abstract/Description
-
In this thesis we present an intelligent forecaster based on neural network technology to capture the future path of the market indicator. This thesis is about the development of a new methodology in financial forecasting. An effort is made to develop a neural network forecaster using the financial indicators as the input variables. A complex recurrent neural network is used to capture the behavior of the nonlinear characteristics of the S&P 500. The main outcome of this research is, a...
Show moreIn this thesis we present an intelligent forecaster based on neural network technology to capture the future path of the market indicator. This thesis is about the development of a new methodology in financial forecasting. An effort is made to develop a neural network forecaster using the financial indicators as the input variables. A complex recurrent neural network is used to capture the behavior of the nonlinear characteristics of the S&P 500. The main outcome of this research is, a systematic way of constructing a forecaster for nonlinear and non-stationary data series of S&P 500 that leads to very good out-of-sample prediction. The results of the training and testing of the network are presented along with conclusion. The tool used for the validation of this research is "Brainmaker". This thesis also contains a brief survey of available tools for financial forecasting.
Show less - Date Issued
- 1999
- PURL
- http://purl.flvc.org/fcla/dt/15741
- Subject Headings
- Neural networks (Computer science), Stock price forecasting, Time-series analysis
- Format
- Document (PDF)
- Title
- An intelligent GMDH forecaster for forecasting certain variables in financial markets.
- Creator
- Mehta, Sandeep., Florida Atlantic University, Pandya, Abhijit S., College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
- Abstract/Description
-
In this thesis, application of GMDH Algorithm to real life problems is studied. A particular type of GMDH Algorithm namely TMNN is chosen for this purpose. An effort is made to forecast S&P Index Closing Value with the help of the forecaster. The performance of the TMNN Algorithm is simulated by implementing a tool in C++ for developing forecast models. The validation of this simulation tool is carried out with Sine Wave Values and performance analysis is done in a noisy environment. The...
Show moreIn this thesis, application of GMDH Algorithm to real life problems is studied. A particular type of GMDH Algorithm namely TMNN is chosen for this purpose. An effort is made to forecast S&P Index Closing Value with the help of the forecaster. The performance of the TMNN Algorithm is simulated by implementing a tool in C++ for developing forecast models. The validation of this simulation tool is carried out with Sine Wave Values and performance analysis is done in a noisy environment. The noisy environment tests the TMNN forecaster for its robustness. The primary goal of this research is to develop a simulation software based on TMNN Algorithm for forecasting stock market index values. The main inputs are previous day's closing values and the output is predicted closing index.
Show less - Date Issued
- 2002
- PURL
- http://purl.flvc.org/fcla/dt/12996
- Subject Headings
- GMDH algorithms, Neural networks (Computer science), Time-series analysis, Pattern recognition systems
- Format
- Document (PDF)
- Title
- A connectionist approach to adaptive reasoning: An expert system to predict skid numbers.
- Creator
- Reddy, Mohan S., Florida Atlantic University, Pandya, Abhijit S., College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
- Abstract/Description
-
This project illustrates the neural network approach to constructing a fuzzy logic decision system. This technique employs an artificial neural network (ANN) to recognize the relationships that exit between the various inputs and outputs. An ANN is constructed based on the variables present in the application. The network is trained and tested. Various training methods are explored, some of which include auxiliary input and output columns. After successful testing, the ANN is exposed to new...
Show moreThis project illustrates the neural network approach to constructing a fuzzy logic decision system. This technique employs an artificial neural network (ANN) to recognize the relationships that exit between the various inputs and outputs. An ANN is constructed based on the variables present in the application. The network is trained and tested. Various training methods are explored, some of which include auxiliary input and output columns. After successful testing, the ANN is exposed to new data and the results are grouped into fuzzy membership sets based membership evaluation rules. This data grouping forms the basis of a new ANN. The network is now trained and tested with the fuzzy membership data. New data is presented to the trained network and the results form the fuzzy implications. This approach is used to compute skid resistance values from G-analyst accelerometer readings on open grid bridge decks.
Show less - Date Issued
- 1996
- PURL
- http://purl.flvc.org/fcla/dt/15239
- Subject Headings
- Artificial intelligence, Fuzzy logic, Neural networks (Computer science), Pavements--Skid resistance
- Format
- Document (PDF)
- Title
- Handprinted character recognition and Alopex algorithm analysis.
- Creator
- Du, Jian., Florida Atlantic University, Shankar, Ravi
- Abstract/Description
-
A novel neural network, trained with the Alopex algorithm to recognize handprinted characters, was developed in this research. It was constructed by an encoded fully connected multi-layer perceptron (EFCMP). It consists of one input layer, one intermediate layer, and one encoded output layer. The Alopex algorithm is used to supervise the training of the EFCMP. Alopex is a stochastic algorithm used to solve optimization problems. The Alopex algorithm has been shown to accelerate the rate of...
Show moreA novel neural network, trained with the Alopex algorithm to recognize handprinted characters, was developed in this research. It was constructed by an encoded fully connected multi-layer perceptron (EFCMP). It consists of one input layer, one intermediate layer, and one encoded output layer. The Alopex algorithm is used to supervise the training of the EFCMP. Alopex is a stochastic algorithm used to solve optimization problems. The Alopex algorithm has been shown to accelerate the rate of convergence in the training procedure. Software simulation programs were developed for training, testing and analyzing the performance of this EFCMP architecture. Several neural networks with different structures were developed and compared. Optimization of the Alopex algorithm was explored through simulations of the EFCMP training procedure with the use of different parametric values for Alopex.
Show less - Date Issued
- 1994
- PURL
- http://purl.flvc.org/fcla/dt/15012
- Subject Headings
- Algorithms, Neural networks (Computer science), Optical character recognition devices, Writing--Data processing, Image processing
- Format
- Document (PDF)
- Title
- Lifeline structures under earthquake excitations.
- Creator
- Reddy, Kondakrindhi Praveen., Florida Atlantic University, Yong, Yan, College of Engineering and Computer Science, Department of Ocean and Mechanical Engineering
- Abstract/Description
-
An analytical method is proposed for the response analysis of lifeline structures subjected to earthquake excitations. The main feature of the approach is to consider the vibrational motion as a result of the wave motion in a waveguide-like lifeline structure. Based on the theory of wave propagation, scattering matrices are derived to characterize the wave propagation in individual segments and wave reflections and transmissions at supports and boundaries. Response solution is derived in a...
Show moreAn analytical method is proposed for the response analysis of lifeline structures subjected to earthquake excitations. The main feature of the approach is to consider the vibrational motion as a result of the wave motion in a waveguide-like lifeline structure. Based on the theory of wave propagation, scattering matrices are derived to characterize the wave propagation in individual segments and wave reflections and transmissions at supports and boundaries. Response solution is derived in a closed form, suitable for stochastic analysis when the input is an earthquake excitation. A space-time earthquake ground motion model that accounts for both coherent decay and seismic wave propagation is used to specify motions at supports. The proposed technique can be used to obtain lifeline structural response accurately and determine the correlation between any two locations in an effective manner. The computational aspects of its implementation are also discussed. Numerical examples are presented to illustrate the application and efficiency of the proposed analytical scheme.
Show less - Date Issued
- 1993
- PURL
- http://purl.flvc.org/fcla/dt/14898
- Subject Headings
- Artificial intelligence, Fuzzy logic, Neural networks (Computer science), Pavements--Skid resistance
- Format
- Document (PDF)
- Title
- Estimation of Internet transit times using a fast-computing artificial neural network (FC-ANN).
- Creator
- Fasulo, Joseph V., Florida Atlantic University, Neelakanta, Perambur S.
- Abstract/Description
-
The objective of this research is to determine the macroscopic behavior of packet transit-times across the global Internet cloud using an artificial neural network (ANN). Specifically, the problem addressed here refers to using a "fast-convergent" ANN for the purpose indicated. The underlying principle of fast-convergence is that, the data presented in training and prediction modes of the ANN is in the entropy (information-theoretic) domain, and the associated annealing process is "tuned" to...
Show moreThe objective of this research is to determine the macroscopic behavior of packet transit-times across the global Internet cloud using an artificial neural network (ANN). Specifically, the problem addressed here refers to using a "fast-convergent" ANN for the purpose indicated. The underlying principle of fast-convergence is that, the data presented in training and prediction modes of the ANN is in the entropy (information-theoretic) domain, and the associated annealing process is "tuned" to adopt only the useful information content and discard the posentropy part of the data presented. To demonstrate the efficacy of the research pursued, a feedforward ANN structure is developed and the necessary transformations required to convert the input data from the parametric-domain to the entropy-domain (and a corresponding inverse transformation) are followed so as to retrieve the output in parametric-domain. The fast-convergent or fast-computing ANN (FC-ANN) developed is deployed to predict the packet-transit performance across the Internet. (Abstract shortened by UMI.)
Show less - Date Issued
- 2001
- PURL
- http://purl.flvc.org/fcla/dt/12835
- Subject Headings
- Neural networks (Computer science), Information theory, Packet switching (Data transmission), Internet
- Format
- Document (PDF)
- Title
- THE EFFECT OF LANE CHANGE VOLATILITY ON REAL TIME ACCIDENT PREDICTION.
- Creator
- Tesheira, Hamilton, Mahgoub, Imad, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
- Abstract/Description
-
According to a March 2019 publication by the National Highway Transportation Safety Administration(NHTSA), 62% of all police-reported accidents in the United States between 2011 and 2015 could have been prevented or mitigated with the use of five groups of collision avoidance technologies in passenger vehicles: (1) forward collision prevention, (2) lane keeping, (3) blind zone detection, (4) forward pedestrian impact, and (5) backing collision avoidance. These technologies work mostly by...
Show moreAccording to a March 2019 publication by the National Highway Transportation Safety Administration(NHTSA), 62% of all police-reported accidents in the United States between 2011 and 2015 could have been prevented or mitigated with the use of five groups of collision avoidance technologies in passenger vehicles: (1) forward collision prevention, (2) lane keeping, (3) blind zone detection, (4) forward pedestrian impact, and (5) backing collision avoidance. These technologies work mostly by reducing or removing the risks involved in a lane change maneuver; yet, the Broward transportation management system does not directly address these risk. Therefore, we are proposing a Machine Learning based approach to real-time accident prediction for Broward I-95 using the C5.1 Decision Tree and the Multi-Layer Perceptron Neural Network to address them. To do this, we design a new measure of volatility, Lane Change Volatility(LCV), which measures the potential for a lane change in a segment of the highway. Our research found that LCV is an important predictor of accidents in an exit zone and when considered in tandem with current system variable, such as lighting conditions, the machine learning classifiers are able to predict accidents in the exit zone with an accuracy rate of over 98%.
Show less - Date Issued
- 2019
- PURL
- http://purl.flvc.org/fau/fd/FA00013420
- Subject Headings
- Traffic accidents, Traffic accidents--Forecasting, Automobile driving--Lane changing, Perceptrons, Neural networks (Computer science)
- Format
- Document (PDF)
- Title
- A neural network-based receiver for interference cancellation in multi-user environment for DS/CDMA systems.
- Creator
- Shukla, Kunal Hemang., Florida Atlantic University, Pandya, Abhijit S., College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
- Abstract/Description
-
The objective of this work is to apply and investigate the performance of a neural network-based receiver for interference cancellation in multiuser direct sequence code division multiple access (DSCDMA) wireless networks. This research investigates a Receiver model which uses Neural Network receiver in combination with a conventional receiver system to provide an efficient mechanism for the Interference Suppression in DS/CDMA systems. The Conventional receiver is used for the time during...
Show moreThe objective of this work is to apply and investigate the performance of a neural network-based receiver for interference cancellation in multiuser direct sequence code division multiple access (DSCDMA) wireless networks. This research investigates a Receiver model which uses Neural Network receiver in combination with a conventional receiver system to provide an efficient mechanism for the Interference Suppression in DS/CDMA systems. The Conventional receiver is used for the time during which the neural network receiver is being trained. Once the NN receiver is trained the conventional receiver system is deactivated. It is demonstrated that this receiver when used along with an efficient Neural network model can outperform MMSE receiver or DFFLE receiver with significant advantages, such as improved bit-error ratio (BER) performance, adaptive operation, single-user detection in DS/CDMA environment and a near far resistant system.
Show less - Date Issued
- 2003
- PURL
- http://purl.flvc.org/fcla/dt/12975
- Subject Headings
- Neural networks (Computer science), Wireless communication systems, Code division multiple access
- Format
- Document (PDF)
- Title
- A new methodology to predict certain characteristics of stock market using time-series phenomena.
- Creator
- Shah, Trupti U., Florida Atlantic University, Pandya, Abhijit S., College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
- Abstract/Description
-
The goal of time series forecasting is to identify the underlying pattern and use these patterns to predict the future path of the series. To capture the future path of a dynamic stock market variable is one of the toughest challenges. This thesis is about the development of a new methodology in financial forecasting. An effort is made to develop a neural network forecaster using time-series phenomena. The main outcome of this new approach for financial forecasting is a systematic way of...
Show moreThe goal of time series forecasting is to identify the underlying pattern and use these patterns to predict the future path of the series. To capture the future path of a dynamic stock market variable is one of the toughest challenges. This thesis is about the development of a new methodology in financial forecasting. An effort is made to develop a neural network forecaster using time-series phenomena. The main outcome of this new approach for financial forecasting is a systematic way of constructing a Neural Network Forecaster for nonlinear and non-stationary time-series data that leads to very good out-of-sample prediction. The tool used for the validation of this research is "Brainmaker". This thesis also contains a small survey of available tools used for financial forecasting.
Show less - Date Issued
- 1999
- PURL
- http://purl.flvc.org/fcla/dt/15677
- Subject Headings
- Time-series analysis, Neural networks (Computer science), Stock price forecasting
- Format
- Document (PDF)
- Title
- FINANCIAL TIME-SERIES ANALYSIS WITH DEEP NEURAL NETWORKS.
- Creator
- Rimal, Binod, Hahn, William Edward, Florida Atlantic University, Department of Mathematical Sciences, Charles E. Schmidt College of Science
- Abstract/Description
-
Financial time-series data are noisy, volatile, and nonlinear. The classic statistical linear models may not capture those underlying structures of the data. The rapid advancement in artificial intelligence and machine learning techniques, availability of large-scale data, and increased computational capabilities of a machine opens the door to developing sophisticated deep learning models to capture the nonlinearity and hidden information in the data. Creating a robust model by unlocking the...
Show moreFinancial time-series data are noisy, volatile, and nonlinear. The classic statistical linear models may not capture those underlying structures of the data. The rapid advancement in artificial intelligence and machine learning techniques, availability of large-scale data, and increased computational capabilities of a machine opens the door to developing sophisticated deep learning models to capture the nonlinearity and hidden information in the data. Creating a robust model by unlocking the power of a deep neural network and using real-time data is essential in this tech era. This study constructs a new computational framework to uncover the information in the financial time-series data and better inform the related parties. It carries out the comparative analysis of the performance of the deep learning models on stock price prediction with a well-balanced set of factors from fundamental data, macroeconomic data, and technical indicators responsible for stock price movement. We further build a novel computational framework through a merger of recurrent neural networks and random compression for the time-series analysis. The performance of the model is tested on a benchmark anomaly time-series dataset. This new computational framework in a compressed paradigm leads to improved computational efficiency and data privacy. Finally, this study develops a custom trading simulator and an agent-based hybrid model by combining gradient and gradient-free optimization methods. In particular, we explore the use of simulated annealing with stochastic gradient descent. The model trains a population of agents to predict appropriate trading behaviors such as buy, hold, or sell by optimizing the portfolio returns. Experimental results on S&P 500 index show that the proposed model outperforms the baseline models.
Show less - Date Issued
- 2022
- PURL
- http://purl.flvc.org/fau/fd/FA00014009
- Subject Headings
- Neural networks (Computer science), Deep learning (Machine learning), Time-series analysis, Stocks, Simulated annealing (Mathematics)
- Format
- Document (PDF)
- Title
- PRESERVING KNOWLEDGE IN SIMULATED BEHAVIORAL ACTION LOOPS.
- Creator
- St.Clair, Rachel, Barenholtz, Elan, Hahn, William, Florida Atlantic University, Center for Complex Systems and Brain Sciences, Charles E. Schmidt College of Science
- Abstract/Description
-
One basic goal of artificial learning systems is the ability to continually learn throughout that system’s lifetime. Transitioning between tasks and re-deploying prior knowledge is thus a desired feature of artificial learning. However, in the deep-learning approaches, the problem of catastrophic forgetting of prior knowledge persists. As a field, we want to solve the catastrophic forgetting problem without requiring exponential computations or time, while demonstrating real-world relevance....
Show moreOne basic goal of artificial learning systems is the ability to continually learn throughout that system’s lifetime. Transitioning between tasks and re-deploying prior knowledge is thus a desired feature of artificial learning. However, in the deep-learning approaches, the problem of catastrophic forgetting of prior knowledge persists. As a field, we want to solve the catastrophic forgetting problem without requiring exponential computations or time, while demonstrating real-world relevance. This work proposes a novel model which uses an evolutionary algorithm similar to a meta-learning objective, that is fitted with a resource constraint metrics. Four reinforcement learning environments are considered with the shared concept of depth although the collection of environments is multi-modal. This system shows preservation of some knowledge in sequential task learning and protection of catastrophic forgetting in deep neural networks.
Show less - Date Issued
- 2022
- PURL
- http://purl.flvc.org/fau/fd/FA00013896
- Subject Headings
- Artificial intelligence, Deep learning (Machine learning), Reinforcement learning, Neural networks (Computer science)
- Format
- Document (PDF)
- Title
- DATA-DRIVEN IDENTIFICATION AND CONTROL OF TURBULENT STRUCTURES USING DEEP NEURAL NETWORKS.
- Creator
- Jagodinski, Eric, Verma, Siddhartha, Florida Atlantic University, Department of Ocean and Mechanical Engineering, College of Engineering and Computer Science
- Abstract/Description
-
Wall-bounded turbulent flows are pervasive in numerous physics and engineering applications. Such flows tend to have a strong impact on the design of ships, airplanes and rockets, industrial chemical mixing, wind and hydrokinetic energy, utility infrastructure and innumerable other fields. Understanding and controlling wall bounded turbulence has been a long-pursued endeavor yielding plentiful scientific and engineering discoveries, but there is much that remains unexplained from a...
Show moreWall-bounded turbulent flows are pervasive in numerous physics and engineering applications. Such flows tend to have a strong impact on the design of ships, airplanes and rockets, industrial chemical mixing, wind and hydrokinetic energy, utility infrastructure and innumerable other fields. Understanding and controlling wall bounded turbulence has been a long-pursued endeavor yielding plentiful scientific and engineering discoveries, but there is much that remains unexplained from a fundamental viewpoint. One unexplained phenomenon is the formation and impact of coherent structures like the ejections of slow near-wall fluid into faster moving ow which have been shown to correlate with increases in friction drag. This thesis focuses on recognizing and regulating organized structures within wall-bounded turbulent flows using a variety of machine learning techniques to overcome the nonlinear nature of this phenomenon. Deep Learning has provided new avenues of analyzing large amounts of data by applying techniques modeled after biological neurons. These techniques allow for the discovery of nonlinear relationships in massive, complex systems like the data found frequently in fluid dynamics simulation. Using a neural network architecture called Convolutional Neural Networks that specializes in uncovering spatial relationships, a network was trained to estimate the relative intensity of ejection structures within turbulent flow simulation without any a priori knowledge of the underlying flow dynamics. To explore the underlying physics that the trained network might reveal, an interpretation technique called Gradient-based Class Activation Mapping was modified to identify salient regions in the flow field which most influenced the trained network to make an accurate estimation of these organized structures. Using various statistical techniques, these salient regions were found to have a high correlation to ejection structures, and to high positive kinetic energy production, low negative production, and low energy dissipation regions within the flow. Additionally, these techniques present a general framework for identifying nonlinear causal structures in general three-dimensional data in any scientific domain where the underlying physics may be unknown.
Show less - Date Issued
- 2022
- PURL
- http://purl.flvc.org/fau/fd/FA00014119
- Subject Headings
- Turbulent flow, Turbulence, Neural networks (Computer science), Deep learning (Machine learning)
- Format
- Document (PDF)
- Title
- FROM DNA TO GRAVITATIONAL WAVES: APPLICATIONS OF STATISTICS AND MACHINE LEARNING.
- Creator
- Alemrajabi, Mahsa Firouzabad, Tichy, Wolfgang, Assis, Raquel, Florida Atlantic University, Department of Physics, Charles E. Schmidt College of Science
- Abstract/Description
-
In the current world of fast-paced data production, statistics and machine learning tools are essential for interpreting and utilizing the full potential of this data. This dissertation comprises three studies employing statistical analysis and Convolutional Neural Network models. First, the research investigates the genetic evolution of the SARS-CoV-2 RNA molecule, emphasizing the role of epistasis in the RNA virus’s ability to adapt and survive. Through statistical tests, this study...
Show moreIn the current world of fast-paced data production, statistics and machine learning tools are essential for interpreting and utilizing the full potential of this data. This dissertation comprises three studies employing statistical analysis and Convolutional Neural Network models. First, the research investigates the genetic evolution of the SARS-CoV-2 RNA molecule, emphasizing the role of epistasis in the RNA virus’s ability to adapt and survive. Through statistical tests, this study validates the significant impacts of genetic interactions and mutations on the virus’s structural changes over time, offering insights into its evolutionary dynamics. Secondly, the dissertation explores medical diagnosis by implementing Convolutional Neural Networks to differentiate between lung CT-scans of COVID-19 and non-COVID patients. This portion of the research demonstrates the capability of deep learning to enhance diagnostic processes, thereby reducing time and increasing accuracy in clinical settings. Lastly, we delve into gravitational wave detection, an area of astrophysics requiring precise data analysis to identify signals from cosmic events such as black hole mergers. Our goal is to utilize Convolutional Neural Network models in hopes of improving the sensitivity and accuracy of detecting these difficult to catch signals, pushing the boundaries of what we can observe in the universe. The findings of this dissertation underscore the utility of combining statistical methods and machine learning models to solve problems that are not only varied but also highly impactful in their respective fields.
Show less - Date Issued
- 2024
- PURL
- http://purl.flvc.org/fau/fd/FA00014454
- Subject Headings
- Neural networks (Computer science), Gravitational waves, Deep learning (Machine learning), Diagnosis, Epistasis, Genetic
- Format
- Document (PDF)