To see the other types of publications on this topic, follow the link: ANN – Artificial Neural Networks.
Dissertations / Theses on the topic 'ANN – Artificial Neural Networks'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'ANN – Artificial Neural Networks.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Rodríguez, Villegas Antoni. "Polyp segmentation using artificial neural networks." Thesis, Linnéuniversitetet, Institutionen för datavetenskap och medieteknik (DM), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:lnu:diva-98001.
Full textAbstract:
Colorectal cancer is the second cause of cancer death in the world. Aiming to early detect and prevent this type of cancer, clinicians perform screenings through the colon searching for polyps (colorectal cancer precursor lesions).If found, these lesions are susceptible of being removed in order to further ana-lyze their malignancy degree. Automatic polyp segmentation is of primary impor-tance when it comes to computer-aided medical diagnosis using images obtained in colonoscopy screenings. These results allow for more precise medical diagnosis which can lead to earlier detection.This project proposed a neural network based solution for semantic segmenta-tion, using the U-net architecture.Combining different data augmentation techniques to alleviate the problem of data scarcity and conducting experiments on the different hyperparameters of the network, the U-net scored a mean Intersection over Union (IoU) of 0,6814. A final approach that combines prediction maps of different models scored a mean IoU of 0,7236.
2
Lundin, Johan. "Prediction of Protein Mutations Using Artificial Neural Networks." Thesis, University of Skövde, Department of Computer Science, 1999. http://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-400.
Full textAbstract:
<p>This thesis is concerned with the prediction of protein mutations using artificial neural networks. From the biological perspective it is of interest to investigate weather it is possible to find rules of mutation between evolutionary adjacent (or closely related) proteins. Techniques from computer science are used in order to see if it is possible to predict protein mutations i.e. using artificial neural networks. The computer science perspective of this work would be to try optimizing the results from the neural networks. However, the focus of this thesis is primarily on the biological perspective and the performance of the computer science methods are secondary objective i.e. the primary interest is to show the existence of rules for protein mutations.</p><p>The method used in this thesis consists two neural networks. One network is used to predict the actual protein mutations and the other network is used to make a compressed representation of each amino acid. By using a compression network it is possible to make the prediction network much smaller (each amino acid is represented by 3 nodes instead of 22 nodes). The compression network is an auto associative network and the prediction network is a standard feed-forward network. The prediction network predicts a block of amino acids at a time and for comparison a sliding window technique has also been tested.</p><p>It is my belief that the results in this thesis indicate that there exists rules for protein mutations. However, the tests done in this thesis is only performed on a small portion of all proteins. Some protein families tested show really good results while other families are not as good. I believe that extended work using optimized neural networks would improve the predictions further.</p>
3
Ghosh, Ranadhir, and n/a. "A Novel Hybrid Learning Algorithm For Artificial Neural Networks." Griffith University. School of Information Technology, 2003. http://www4.gu.edu.au:8080/adt-root/public/adt-QGU20030808.162355.
Full textAbstract:
Last few decades have witnessed the use of artificial neural networks (ANN) in many real-world applications and have offered an attractive paradigm for a broad range of adaptive complex systems. In recent years ANN have enjoyed a great deal of success and have proven useful in wide variety pattern recognition or feature extraction tasks. Examples include optical character recognition, speech recognition and adaptive control to name a few. To keep the pace with its huge demand in diversified application areas, many different kinds of ANN architecture and learning types have been proposed by the researchers to meet varying needs. A novel hybrid learning approach for the training of a feed-forward ANN has been proposed in this thesis. The approach combines evolutionary algorithms with matrix solution methods such as singular value decomposition, Gram-Schmidt etc., to achieve optimum weights for hidden and output layers. The proposed hybrid method is to apply evolutionary algorithm in the first layer and least square method (LS) in the second layer of the ANN. The methodology also finds optimum number of hidden neurons using a hierarchical combination methodology structure for weights and architecture. A learning algorithm has many facets that can make a learning algorithm good for a particular application area. Often there are trade offs between classification accuracy and time complexity, nevertheless, the problem of memory complexity remains. This research explores all the different facets of the proposed new algorithm in terms of classification accuracy, convergence property, generalization ability, time and memory complexity.
4
Ghosh, Ranadhir. "A Novel Hybrid Learning Algorithm For Artificial Neural Networks." Thesis, Griffith University, 2003. http://hdl.handle.net/10072/365961.
Full textAbstract:
Last few decades have witnessed the use of artificial neural networks (ANN) in many real-world applications and have offered an attractive paradigm for a broad range of adaptive complex systems. In recent years ANN have enjoyed a great deal of success and have proven useful in wide variety pattern recognition or feature extraction tasks. Examples include optical character recognition, speech recognition and adaptive control to name a few. To keep the pace with its huge demand in diversified application areas, many different kinds of ANN architecture and learning types have been proposed by the researchers to meet varying needs. A novel hybrid learning approach for the training of a feed-forward ANN has been proposed in this thesis. The approach combines evolutionary algorithms with matrix solution methods such as singular value decomposition, Gram-Schmidt etc., to achieve optimum weights for hidden and output layers. The proposed hybrid method is to apply evolutionary algorithm in the first layer and least square method (LS) in the second layer of the ANN. The methodology also finds optimum number of hidden neurons using a hierarchical combination methodology structure for weights and architecture. A learning algorithm has many facets that can make a learning algorithm good for a particular application area. Often there are trade offs between classification accuracy and time complexity, nevertheless, the problem of memory complexity remains. This research explores all the different facets of the proposed new algorithm in terms of classification accuracy, convergence property, generalization ability, time and memory complexity.<br>Thesis (PhD Doctorate)<br>Doctor of Philosophy (PhD)<br>School of Information Technology<br>Full Text
5
Turner, Joseph Vernon. "Application of Artificial Neural Networks in Pharmacokinetics." Thesis, The University of Sydney, 2003. http://hdl.handle.net/2123/488.
Full textAbstract:
Drug development is a long and expensive process. It is often not until potential drug candidates are administered to humans that accurate quantification of their pharmacokinetic characteristics is achieved. The goal of developing quantitative structure-pharmacokinetic relationships (QSPkRs) is to relate the molecular structure of a chemical entity with its pharmacokinetic characteristics. In this thesis artificial neural networks (ANNs) were used to construct in silico predictive QSPkRs for various pharmacokinetic parameters using different drug data sets. Drug pharmacokinetic data for all studies were taken from the literature. Information for model construction was extracted from drug molecular structure. Numerous theoretical descriptors were generated from drug structure ranging from simple constitutional and functional group counts to complex 3D quantum chemical numbers. Subsets of descriptors were selected which best modeled the target pharmacokinetic parameter(s). Using manual selective pruning, QSPkRs for physiological clearances, volumes of distribution, and fraction bound to plasma proteins were developed for a series of beta-adrenoceptor antagonists. All optimum ANN models had training and cross-validation correlations close to unity, while testing was performed with an independent set of compounds. In most cases the ANN models developed performed better than other published ANN models for the same drug data set. The ability of ANNs to develop QSPkRs with multiple target outputs was investigated for a series of cephalosporins. Multilayer perceptron ANN models were constructed for prediction of half life, volume of distribution, clearances (whole body and renal), fraction excreted in the urine, and fraction bound to plasma proteins. The optimum model was well able to differentiate compounds in a qualitative manner while quantitative predictions were mostly in agreement with observed literature values. The ability to make simultaneous predictions of important pharmacokinetic properties of a compound made this a valuable model. A radial-basis function ANN was employed to construct a quantitative structure-bioavailability relationship for a large, structurally diverse series of compounds. The optimum model contained descriptors encoding constitutional through to conformation dependent solubility characteristics. Prediction of bioavailability for the independent testing set were generally close to observed values. Furthermore, the optimum model provided a good qualitative tool for differentiating between drugs with either low or high experimental bioavailability. QSPkR models constructed with ANNs were compared with multilinear regression models. ANN models were shown to be more effective at selecting a suitable subset of descriptors to model a given pharmacokinetic parameter. They also gave more accurate predictions than multilinear regression equations. This thesis presents work which supports the use of ANNs in pharmacokinetic modeling. Successful QSPkRs were constructed using different combinations of theoretically-derived descriptors and model optimisation techniques. The results demonstrate that ANNs provide a valuable modeling tool that may be useful in drug discovery and development.
6
Turner, Joseph Vernon. "Application of Artificial Neural Networks in Pharmacokinetics." University of Sydney, 2003. http://hdl.handle.net/2123/488.
Full textAbstract:
Drug development is a long and expensive process. It is often not until potential drug candidates are administered to humans that accurate quantification of their pharmacokinetic characteristics is achieved. The goal of developing quantitative structure-pharmacokinetic relationships (QSPkRs) is to relate the molecular structure of a chemical entity with its pharmacokinetic characteristics. In this thesis artificial neural networks (ANNs) were used to construct in silico predictive QSPkRs for various pharmacokinetic parameters using different drug data sets. Drug pharmacokinetic data for all studies were taken from the literature. Information for model construction was extracted from drug molecular structure. Numerous theoretical descriptors were generated from drug structure ranging from simple constitutional and functional group counts to complex 3D quantum chemical numbers. Subsets of descriptors were selected which best modeled the target pharmacokinetic parameter(s). Using manual selective pruning, QSPkRs for physiological clearances, volumes of distribution, and fraction bound to plasma proteins were developed for a series of beta-adrenoceptor antagonists. All optimum ANN models had training and cross-validation correlations close to unity, while testing was performed with an independent set of compounds. In most cases the ANN models developed performed better than other published ANN models for the same drug data set. The ability of ANNs to develop QSPkRs with multiple target outputs was investigated for a series of cephalosporins. Multilayer perceptron ANN models were constructed for prediction of half life, volume of distribution, clearances (whole body and renal), fraction excreted in the urine, and fraction bound to plasma proteins. The optimum model was well able to differentiate compounds in a qualitative manner while quantitative predictions were mostly in agreement with observed literature values. The ability to make simultaneous predictions of important pharmacokinetic properties of a compound made this a valuable model. A radial-basis function ANN was employed to construct a quantitative structure-bioavailability relationship for a large, structurally diverse series of compounds. The optimum model contained descriptors encoding constitutional through to conformation dependent solubility characteristics. Prediction of bioavailability for the independent testing set were generally close to observed values. Furthermore, the optimum model provided a good qualitative tool for differentiating between drugs with either low or high experimental bioavailability. QSPkR models constructed with ANNs were compared with multilinear regression models. ANN models were shown to be more effective at selecting a suitable subset of descriptors to model a given pharmacokinetic parameter. They also gave more accurate predictions than multilinear regression equations. This thesis presents work which supports the use of ANNs in pharmacokinetic modeling. Successful QSPkRs were constructed using different combinations of theoretically-derived descriptors and model optimisation techniques. The results demonstrate that ANNs provide a valuable modeling tool that may be useful in drug discovery and development.
7
Perchiazzi, Gaetano. "Artificial Neural Networks (ANN) in the Assessment of Respiratory Mechanics." Doctoral thesis, Uppsala : Acta Universitatis Upsaliensis : Univ.-bibl. [distributör], 2004. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-4665.
Full text
8
Miranda, Trujillo Luis Carlos. "Artificial Neural Networks in Greenhouse Modelling." Doctoral thesis, Humboldt-Universität zu Berlin, 2018. http://dx.doi.org/10.18452/19354.
Full textAbstract:
Moderne Präzisionsgartenbaulicheproduktion schließt hoch technifizierte Gewächshäuser, deren Einsatz in großem Maße von der Qualität der Sensorik- und Regelungstechnik abhängt, mit ein. Zu den Regelungsstrategien gehören unter anderem Methoden der Künstlichen Intelligenz, wie z.B. Künstliche Neuronale Netze (KNN, aus dem Englischen).
Die vorliegende Arbeit befasst sich mit der Eignung KNN-basierter Modelle als Bauelemente von Klimaregelungstrategien in Gewächshäusern. Es werden zwei Modelle vorgestellt: Ein Modell zur kurzzeitigen Voraussage des Gewächshausklimas (Lufttemperatur und relative Feuchtigkeit, in Minuten-Zeiträumen), und Modell zur Einschätzung von phytometrischen Signalen (Blatttemperatur, Transpirationsrate und Photosyntheserate). Eine Datenbank, die drei Kulturjahre umfasste (Kultur: Tomato), wurde zur Modellbildung bzw. -test benutzt.
Es wurde festgestellt, dass die ANN-basierte Modelle sehr stark auf die Auswahl der Metaparameter und Netzarchitektur reagieren, und dass sie auch mit derselben Architektur verschiedene Kalkulationsergebnisse liefern können. Nichtsdestotrotz, hat sich diese Art von Modellen als geeignet zur Einschätzung komplexer Pflanzensignalen sowie zur Mikroklimavoraussage erwiesen. Zwei zusätzliche Möglichkeiten zur Erstellung von komplexen Simulationen sind in der Arbeit enthalten, und zwar zur Klimavoraussage in längerer Perioden und zur Voraussage der Photosyntheserate. Die Arbeit kommt zum Ergebnis, dass die Verwendung von KNN-Modellen für neue Gewächshaussteuerungstrategien geeignet ist, da sie robust sind und mit der Systemskomplexität gut zurechtkommen. Allerdings muss beachtet werden, dass Probleme und Schwierigkeiten auftreten können. Diese Arbeit weist auf die Relevanz der Netzarchitektur, die erforderlichen großen Datenmengen zur Modellbildung und Probleme mit verschiedenen Zeitkonstanten im Gewächshaus hin.<br>One facet of the current developments in precision horticulture is the highly technified production under cover. The intensive production in modern greenhouses heavily relies on instrumentation and control techniques to automate many tasks. Among these techniques are control strategies, which can also include some methods developed within the field of Artificial Intelligence. This document presents research on Artificial Neural Networks (ANN), a technique derived from Artificial Intelligence, and aims to shed light on their applicability in greenhouse vegetable production. In particular, this work focuses on the suitability of ANN-based models for greenhouse environmental control. To this end, two models were built: A short-term climate prediction model (air temperature and relative humidity in time scale of minutes), and a model of the plant response to the climate, the latter regarding phytometric measurements of leaf temperature, transpiration rate and photosynthesis rate. A dataset comprising three years of tomato cultivation was used to build and test the models.
It was found that this kind of models is very sensitive to the fine-tuning of the metaparameters and that they can produce different results even with the same architecture. Nevertheless, it was shown that ANN are useful to simulate complex biological signals and to estimate future microclimate trends. Furthermore, two connection schemes are proposed to assemble several models in order to generate more complex simulations, like long-term prediction chains and photosynthesis forecasts. It was concluded that ANN could be used in greenhouse automation systems as part of the control strategy, as they are robust and can cope with the complexity of the system. However, a number of problems and difficulties are pointed out, including the importance of the architecture, the need for large datasets to build the models and problems arising from different time constants in the whole greenhouse system.
9
Moposita, Tatiana. "Artificial Neural Network (ANN) design using Compute-in-Memory." Electronic Thesis or Diss., Sorbonne université, 2023. http://www.theses.fr/2023SORUS682.
Full textAbstract:
De nos jours, l'ère du " More than Moore" a émergé comme une influence significative face aux limitations anticipées par la loi de Moore. Les systèmes informatiques explorent des technologies alternatives pour maintenir et améliorer les performances. Cette idée émergé pour résoudre les défis des systèmes électroniques inspirés des réseau biologiques, communément appelés Réseau Neurones Artificiels (ANN). L'utilisation des technologies emerging non-volatile memory (eNVM) est étudiée comme des alternatives prometteuses. Ces technologies offrent plusieurs avantages par rapport à la technologie CMOS traditionnelle, tels qu'une vitesse accrue, des densités plus élevées et une consommation d'énergie moindre. En conséquence, Compute-in-memory utilise les eNVM pour effectuer des calculs directement dans la mémoire, augmentant ainsi la capacité de mémoire et la vitesse de traitement. L'objectif de cette thèse se concentre sur la recherche de la conception de Réseau Neurones Artificiels en utilisant Compute-in-Memory, en employant des solutions matérielles efficaces pour les ANNs tant au niveau du circuit qu'au niveau de l'architecture. Les travaux de recherche récents dans ce contexte ont proposé des conceptions de circuits très efficaces pour optimiser les besoins de calcul énormes nécessaires au traitement des données par les ANNs. Ainsi, pour explorer les capacités d'un ANN au niveau du nœud de sortie, la conception de fonctions d'activation a été proposée. La sélection d'une fonction d'activation est significative car elle détermine la puissance et les capacités du réseau neuronal, et la précision des prédictions dépend principalement de ce choix. Pour évaluer l'efficacité d'une fonction d'activation conçue pour une implémentation analogique, les fonctions d'activation sigmoïde et softmax sont proposées. Cette thèse explore l'intégration de dispositifs mémoires émergents tels que la Spin-Transfer-Torque Magnetic Random Access Memory (STT-MRAM) avec la technologie CMOS. Cette approche combinée vise à tirer parti de la capacité intrinsèque de l'informatique en mémoire offerte par ces dispositifs. Perpendicular magnetic tunneling junction (MTJ) et des FinFET ont été pris en compte pour cette étude. Single-barrier (SMTJ) et double-barrier (DMTJ) sont considérés pour évaluer l'impact de la cellule STT-MRAM basée sur DMTJ par rapport à son homologue SMTJ conventionnel sur les performances d'un réseau neuronal à perceptrons multicouches (MLP) à deux couches. L'évaluation a été réalisée au moyen d'un cadre de simulation personnalisé, de niveaux de dispositif et de cellule jusqu'aux niveaux d'architecture mémoire et d'algorithme. De plus, pour améliorer l'efficacité énergétique d'une architecture Logic-in-Memory (LIM) basée sur les dispositifs STT-MTJ, une nouvelle architecture (SIMPLY+) issue de la logique Smart Material Implication (SIMPLY) et des technologies STT-MRAM basées sur MTJ perpendiculaires a été développée. Le schéma SIMPLY+ constitue une solution prometteuse pour le développement d'architectures informatiques en mémoire économes en énergie et fiables. Toutes les solutions de circuits ont été évaluées à l'aide de simulateurs de circuits commerciaux (par exemple, Cadence Virtuoso). L'activité de conception de circuits impliquant des dispositifs mémoires émergents a également nécessité l'utilisation et le calibrage de modèles compacts basés sur Verilog-A pour intégrer le comportement de ces dispositifs dans l'outil de conception de circuits. Les solutions présentées dans cette thèse impliquent des techniques qui offrent des avancées significatives pour les futures applications. Du point de vue de la conception, l'intégration de modules logiques avec la mémoire STT-MRAM est très réalisable en raison de la compatibilité transparente entre les STT-MRAM et les circuits CMOS. Cette approche est non seulement avantageuse pour la technologie CMOS standard, mais elle exploite également le potentiel des technologies émergentes<br>Nowadays, the era of ”More than Moore” has arisen as a significant influence in light of the limitations anticipated by Moore’s law. The computing systems are exploring alternative technologies to sustain and enhance performance improvements. The idea of alternative innovative technologies has emerged in solving challenges of electronic systems inspired by biological neural networks, commonly referred to as Artificial Neural Network (ANN). The use of emerging non-volatile memory (eNVM) technologies are being explored as promising alternatives. These technologies offer several advantages over traditional CMOS technology, such as increased speed, higher densities, and lower power consumption. As a result, Compute-in-memory employs eNVMs to perform computation within the memory itself, hence increasing memory capacity and processing speed. The objective of this thesis focuses on the research of Artificial Neural Networks design using Compute in Memory, by employing efficient hardware solutions for ANNs at both circuit- and architecture-level. Recent research work in this context has proposed very efficient circuit designs to optimize the enormous computational needs required by data processing by ANNs. Therefore, to explore the capabilities of an ANN at the output node, the design of activation functions were proposed. The selection of an activation function is significant as it determines the power and capabilities of the neural network, and the accuracy of predictions is primarily dependent on this choice. To assess the effectiveness of an activation function designed for analog implementation, the sigmoid and the softmax activation function are proposed. Besides, this thesis explores the integration of emerging memory devices like Spin-Transfer-Torque Magnetic Random Access Memory (STT-MRAM) with CMOS technology. This combined approach aims to leverage the intrinsic capability of in-memory computing offered by these devices. STT-MRAMs based on state-of-the-art perpendicular magnetic tunneling junction (MTJ) and FinFETs has been considered for this study. Single-barrier magnetic tunnel junction (SMTJ) and double-barrier magnetic tunnel junction (DMTJ) devices are considered to evaluate the impact of STT-MRAM cell based on DMTJ against the conventional SMTJ counterpart on the performance of a two-layer multilayer perceptron (MLP) neural network. The assessment was carried out through a customized simulation framework from device and bitcell levels to memory architecture and algorithm levels. Moreover, to improve the energy-efficiency of a Logic-in-Memory (LIM) architecture based on STT-MTJ devices, a new architecture (SIMPLY+) from the Smart Material Implication (SIMPLY) logic and perpendicular MTJ based STT-MRAM technologies was developed. The SIMPLY+ scheme is a promising solution for the development of energy-efficient and reliable in-memory computing architectures. All circuit solutions were evaluated using commercial circuit simulators (e.g. Cadence Virtuoso). Circuit design activity involving emerging memory devices also required the use and calibration of Verilog-A based compact models to integrate the behavior of such devices into the circuit design tool. The solutions presented in this thesis involve techniques that offer significant advancements for future applications. From a design perspective, the integration of logic modules with STT-MRAM memory is highly feasible due to the seamless compatibility between STT-MRAMs and CMOS circuits. This approach not only proves advantageous for standard CMOS technology but also leverages the potential of emerging technologies
10
Townsend, Joseph Paul. "Artificial development of neural-symbolic networks." Thesis, University of Exeter, 2014. http://hdl.handle.net/10871/15162.
Full textAbstract:
Artificial neural networks (ANNs) and logic programs have both been suggested as means of modelling human cognition. While ANNs are adaptable and relatively noise resistant, the information they represent is distributed across various neurons and is therefore difficult to interpret. On the contrary, symbolic systems such as logic programs are interpretable but less adaptable. Human cognition is performed in a network of biological neurons and yet is capable of representing symbols, and therefore an ideal model would combine the strengths of the two approaches. This is the goal of Neural-Symbolic Integration [4, 16, 21, 40], in which ANNs are used to produce interpretable, adaptable representations of logic programs and other symbolic models. One neural-symbolic model of reasoning is SHRUTI [89, 95], argued to exhibit biological plausibility in that it captures some aspects of real biological processes. SHRUTI's original developers also suggest that further biological plausibility can be ascribed to the fact that SHRUTI networks can be represented by a model of genetic development [96, 120]. The aims of this thesis are to support the claims of SHRUTI's developers by producing the first such genetic representation for SHRUTI networks and to explore biological plausibility further by investigating the evolvability of the proposed SHRUTI genome. The SHRUTI genome is developed and evolved using principles from Generative and Developmental Systems and Artificial Development [13, 105], in which genomes use indirect encoding to provide a set of instructions for the gradual development of the phenotype just as DNA does for biological organisms. This thesis presents genomes that develop SHRUTI representations of logical relations and episodic facts so that they are able to correctly answer questions on the knowledge they represent. The evolvability of the SHRUTI genomes is limited in that an evolutionary search was able to discover genomes for simple relational structures that did not include conjunction, but could not discover structures that enabled conjunctive relations or episodic facts to be learned. Experiments were performed to understand the SHRUTI fitness landscape and demonstrated that this landscape is unsuitable for navigation using an evolutionary search. Complex SHRUTI structures require that necessary substructures must be discovered in unison and not individually in order to yield a positive change in objective fitness that informs the evolutionary search of their discovery. The requirement for multiple substructures to be in place before fitness can be improved is probably owed to the localist representation of concepts and relations in SHRUTI. Therefore this thesis concludes by making a case for switching to more distributed representations as a possible means of improving evolvability in the future.
11
Sun, Chang. "Scalability Analysis of Synchronous Data-Parallel Artificial Neural Network (ANN) Learners." Thesis, Virginia Tech, 2018. http://hdl.handle.net/10919/85020.
Full textAbstract:
Artificial Neural Networks (ANNs) have been established as one of the most important algorithmic tools in the Machine Learning (ML) toolbox over the past few decades. ANNs' recent rise to widespread acceptance can be attributed to two developments: (1) the availability of large-scale training and testing datasets; and (2) the availability of new computer architectures for which ANN implementations are orders of magnitude more efficient. In this thesis, I present research on two aspects of the second development. First, I present a portable, open source implementation of ANNs in OpenCL and MPI. Second, I present performance and scaling models for ANN algorithms on state-of-the-art Graphics Processing Unit (GPU) based parallel compute clusters.<br>Master of Science
12
Lind, Benjamin. "Artificial Neural Networks for Image Improvement." Thesis, Linköpings universitet, Datorseende, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-137661.
Full textAbstract:
After a digital photo has been taken by a camera, it can be manipulated to be more appealing. Two ways of doing that are to reduce noise and to increase the saturation. With time and skills in an image manipulating program, this is usually done by hand. In this thesis, automatic image improvement based on artificial neural networks is explored and evaluated qualitatively and quantitatively. A new approach, which builds on an existing method for colorizing gray scale images is presented and its performance compared both to simpler methods and the state of the art in image denoising. Saturation is lowered and noise added to original images, which the methods receive as inputs to improve upon. The new method is shown to improve in some cases but not all, depending on the image and how it was modified before given to the method.
13
Norman, Gustaf. "Sensor Validation Using Linear Parametric Models, Artificial Neural Networks and CUSUM." Thesis, Linköpings universitet, Reglerteknik, 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-119004.
Full textAbstract:
Siemens gas turbines are monitored and controlled by a large number of sensors and actuators. Process information is stored in a database and used for offline calculations and analyses. Before storing the sensor readings, a compression algorithm checks the signal and skips the values that explain no significant change. Compression of 90 % is not unusual. Since data from the database is used for analyses and decisions are made upon results from these analyses it is important to have a system for validating the data in the database. Decisions made on false information can result in large economic losses. When this project was initiated no sensor validation system was available. In this thesis the uncertainties in measurement chains are revealed. Methods for fault detection are investigated and finally the most promising methods are put to the test. Linear relationships between redundant sensors are derived and the residuals form an influence structure allowing the faulty sensor to be isolated. Where redundant sensors are not available, a gas turbine model is utilized to state the input-output relationships so that estimates of the sensor outputs can be formed. Linear parametric models and an ANN (Artificial Neural Network) are developed to produce the estimates. Two techniques for the linear parametric models are evaluated; prediction and simulation. The residuals are also evaluated in two ways; direct evaluation against a threshold and evaluation with the CUSUM (CUmulative SUM) algorithm. The results show that sensor validation using compressed data is feasible. Faults as small as 1% of the measuring range can be detected in many cases.
14
Lukashev, A. "Basics of artificial neural networks (ANNs)." Thesis, Київський національний університет технологій та дизайну, 2018. https://er.knutd.edu.ua/handle/123456789/11353.
Full text
15
Stromatias, Evangelos. "Scalability and robustness of artificial neural networks." Thesis, University of Manchester, 2016. https://www.research.manchester.ac.uk/portal/en/theses/scalability-and-robustness-of-artificial-neural-networks(b73b3f77-2bc3-4197-bd0f-dc7501b872cb).html.
Full textAbstract:
Artificial Neural Networks (ANNs) appear increasingly and routinely to gain popularity today, as they are being used in several diverse research fields and many different contexts, which may range from biological simulations and experiments on artificial neuronal models to machine learning models intended for industrial and engineering applications. One example is the recent success of Deep Learning architectures (e.g., Deep Belief Networks [DBN]), which appear in the spotlight of machine learning research, as they are capable of delivering state-of-the-art results in many domains. While the performance of such ANN architectures is greatly affected by their scale, their capacity for scalability both for training and during execution is limited by the increased power consumption and communication overheads, implicitly posing a limiting factor on their real-time performance. The on-going work on the design and construction of spike-based neuromorphic platforms offers an alternative for running large-scale neural networks, such as DBNs, with significantly lower power consumption and lower latencies, but has to overcome the hardware limitations and model specialisations imposed by these type of circuits. SpiNNaker is a novel massively parallel fully programmable and scalable architecture designed to enable real-time spiking neural network (SNN) simulations. These properties render SpiNNaker quite an attractive neuromorphic exploration platform for running large-scale ANNs, however, it is necessary to investigate thoroughly both its power requirements as well as its communication latencies. This research focusses on around two main aspects. First, it aims at characterising the power requirements and communication latencies of the SpiNNaker platform while running large-scale SNN simulations. The results of this investigation lead to the derivation of a power estimation model for the SpiNNaker system, a reduction of the overall power requirements and the characterisation of the intra- and inter-chip spike latencies. Then it focuses on a full characterisation of spiking DBNs, by developing a set of case studies in order to determine the impact of (a) the hardware bit precision; (b) the input noise; (c) weight variation; and (d) combinations of these on the classification performance of spiking DBNs for the problem of handwritten digit recognition. The results demonstrate that spiking DBNs can be realised on limited precision hardware platforms without drastic performance loss, and thus offer an excellent compromise between accuracy and low-power, low-latency execution. These studies intend to provide important guidelines for informing current and future efforts around developing custom large-scale digital and mixed-signal spiking neural network platforms.
16
Chamanirad, Mohsen. "Design and implementation of controller for robotic manipulators using Artificial Neural Networks." Thesis, Mälardalen University, School of Innovation, Design and Engineering, 2009. http://urn.kb.se/resolve?urn=urn:nbn:se:mdh:diva-6297.
Full textAbstract:
<p>In this thesis a novel method for controlling a manipulator with arbitrary number of Degrees of freedom is proposed, the proposed method has the main advantages of two common controllers, the simplicity of PID controller and the robustness and accuracy of adaptive controller. The controller architecture is based on an Artificial Neural Network (ANN) and a PID controller.</p><p>The controller has the ability of solving inverse dynamics and inverse kinematics of robot with two separate Artificial Neural Networks. Since the ANN is learning the system parameters by itself the structure of controller can easily be changed to</p><p>improve the performance of robot.</p><p>The proposed controller can be implemented on a FPGA board to control the robot in real-time or the response of the ANN can be calculated offline and be reconstructed by controller using a lookup table. Error between the desired trajectory path and the path of the robot converges to zero rapidly and as the robot performs its tasks the controller learns the robot parameters and generates better control signal. The performance of controller is tested in simulation and on a real manipulator with satisfactory results.</p>
17
Styren, Buster. "Uveal melanoma identification using artificial neural networks." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-241086.
Full textAbstract:
Uveal melanoma is a deadly form of cancer that can develop from a uveal nevus in the eye fundus. By using deep convolutional networks this thesis aims to classify fundus images based on malignancy. A baseline model was compared against two state-of-the-art networks, Inceptionv3 and ResNet. The baseline model was trained using different gradient descent optimizers and image augmentations to find the best hyper parameters for the data. The state-of-the-art networks achieved comparable accuracy, with Inception-v3 achieving 0.912 AUC after training on 8360 samples. With 96% sensitivity, the same value as ophthalmologists, the top network achieves a specificity of 59% meaning that the network can greatly reduce theamount of manual naevi eye examinations by filtering out healthy subjects.<br>Uvealt melanom är en dödlig form av cancer som orsakas av pigmenförändringar i retina. Sjukdomen har en hög risk at metastasera sig i levern och när metastaserna är kliniskt manifesta är överlevnaden i allmänhet begränsad till några få månader. Genom att träna ett neuralt nätverk är målet med detta arbete att klassificera ögonbottenbilder på chorioidala naevi som benigna eller maligna. Detta har genomförts genom att utvärdera tre olika faltningsnätverk. Nätverken Inception-v3 och ResNet har jämförts med ett simpelt sex-lagers nätverk. En rad olika konfigurationer av hyperparametrar har utvärderats för att hitta en optimal modell. Efter träning på 8360 datapunkter nådde Inception-v3 ett AUC-värde på 0.912. Med 96% sensitivitet, vilket är samma nivå som oftalmologer, uppnår nätverket 59% specificitet. Alltså kan nätverket filtrera bort en stor del av de friska patienter som undersöks av läkare. Detta kan därför innebära en stor resurseffektivisering av patienter med pigmentförändringar i retina.
18
Lynch, Dustin Shane. "Asset Allocation Technique for a Diversified Investment Portfolio Using Artificial Neural Networks." Ohio University / OhioLINK, 2015. http://rave.ohiolink.edu/etdc/view?acc_num=ohiou1432805760.
Full text
19
Xu, Siyao. "THE RECONSTRUCTION OF CLOUD-FREE REMOTE SENSING IMAGES: AN ARTIFICIAL NEURAL NETWORKS (ANN) APPROACH." [Kent, Ohio] : Kent State University, 2009. http://rave.ohiolink.edu/etdc/view?acc%5Fnum=kent1248112891.
Full textAbstract:
Thesis (M.A.)--Kent State University, 2009.<br>Title from PDF t.p. (viewed Mar. 11, 2010). Advisor: Mandy Munro-Stasiuk. Keywords: Remote Sensing Image; Cloud-free; Artificial Neural Networks. Includes bibliographical references (p. 57-59).
20
Gou, Zhenkun. "Canonical correlation analysis and artificial neural networks." Thesis, University of the West of Scotland, 2003. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.269409.
Full text
21
Chen, Jian-Rong. "Theory and applications of artificial neural networks." Thesis, Durham University, 1991. http://etheses.dur.ac.uk/6240/.
Full textAbstract:
In this thesis some fundamental theoretical problems about artificial neural networks and their application in communication and control systems are discussed. We consider the convergence properties of the Back-Propagation algorithm which is widely used for training of artificial neural networks, and two stepsize variation techniques are proposed to accelerate convergence. Simulation results demonstrate significant improvement over conventional Back-Propagation algorithms. We also discuss the relationship between generalization performance of artificial neural networks and their structure and representation strategy. It is shown that the structure of the network which represent a priori knowledge of the environment has a strong influence on generalization performance. A Theorem about the number of hidden units and the capacity of self-association MLP (Multi-Layer Perceptron) type network is also given in the thesis. In the application part of the thesis, we discuss the feasibility of using artificial neural networks for nonlinear system identification. Some advantages and disadvantages of this approach are analyzed. The thesis continues with a study of artificial neural networks applied to communication channel equalization and the problem of call access control in broadband ATM (Asynchronous Transfer Mode) communication networks. A final chapter provides overall conclusions and suggestions for further work.
22
Haskett, Kevin Joseph. "Iris Biometric Identification Using Artificial Neural Networks." DigitalCommons@CalPoly, 2018. https://digitalcommons.calpoly.edu/theses/1947.
Full textAbstract:
A biometric method is a more secure way of personal identification than passwords. This thesis examines the iris as a personal identifier with the use of neural networks as the classifier. A comparison of different feature extraction methods that include the Fourier transform, discrete cosine transform, the eigen analysis method, and the wavelet transform, is performed. The robustness of each method, with respect to distortion and noise, is also studied.
23
Tarullo, Viviana. "Artificial Neural Networks for classification of EMG data in hand myoelectric control." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2019. http://amslaurea.unibo.it/19195/.
Full textAbstract:
This thesis studies the state-of-the-art in myoelectric control of active hand prostheses for people with trans-radial amputation using pattern recognition and machine learning techniques. Our work is supported by Centro Protesi INAIL in Vigorso di Budrio (BO). We studied the control system developed by INAIL consisting in acquiring EMG signals from amputee subjects and using pattern recognition methods for the classifcation of acquired signals, associating them with specifc gestures and consequently commanding the prosthesis. Our work consisted in improving classifcation methods used in the learning phase. In particular, we proposed a classifer based on a neural network as a valid alternative to the INAIL one-versus-all approach to multiclass classifcation.
24
Coughlin, Michael J., and n/a. "Calibration of Two Dimensional Saccadic Electro-Oculograms Using Artificial Neural Networks." Griffith University. School of Applied Psychology, 2003. http://www4.gu.edu.au:8080/adt-root/public/adt-QGU20030409.110949.
Full textAbstract:
The electro-oculogram (EOG) is the most widely used technique for recording eye movements in clinical settings. It is inexpensive, practical, and non-invasive. Use of EOG is usually restricted to horizontal recordings as vertical EOG contains eyelid artefact (Oster & Stern, 1980) and blinks. The ability to analyse two dimensional (2D) eye movements may provide additional diagnostic information on pathologies, and further insights into the nature of brain functioning. Simultaneous recording of both horizontal and vertical EOG also introduces other difficulties into calibration of the eye movements, such as different gains in the two signals, and misalignment of electrodes producing crosstalk. These transformations of the signals create problems in relating the two dimensional EOG to actual rotations of the eyes. The application of an artificial neural network (ANN) that could map 2D recordings into 2D eye positions would overcome this problem and improve the utility of EOG. To determine whether ANNs are capable of correctly calibrating the saccadic eye movement data from 2D EOG (i.e. performing the necessary inverse transformation), the ANNs were first tested on data generated from mathematical models of saccadic eye movements. Multi-layer perceptrons (MLPs) with non-linear activation functions and trained with back propagation proved to be capable of calibrating simulated EOG data to a mean accuracy of 0.33° of visual angle (SE = 0.01). Linear perceptrons (LPs) were only nearly half as accurate. For five subjects performing a saccadic eye movement task in the upper right quadrant of the visual field, the mean accuracy provided by the MLPs was 1.07° of visual angle (SE = 0.01) for EOG data, and 0.95° of visual angle (SE = 0.03) for infrared limbus reflection (IRIS®) data. MLPs enabled calibration of 2D saccadic EOG to an accuracy not significantly different to that obtained with the infrared limbus tracking data.
25
Coughlin, Michael J. "Calibration of Two Dimensional Saccadic Electro-Oculograms Using Artificial Neural Networks." Thesis, Griffith University, 2003. http://hdl.handle.net/10072/365854.
Full textAbstract:
The electro-oculogram (EOG) is the most widely used technique for recording eye movements in clinical settings. It is inexpensive, practical, and non-invasive. Use of EOG is usually restricted to horizontal recordings as vertical EOG contains eyelid artefact (Oster & Stern, 1980) and blinks. The ability to analyse two dimensional (2D) eye movements may provide additional diagnostic information on pathologies, and further insights into the nature of brain functioning. Simultaneous recording of both horizontal and vertical EOG also introduces other difficulties into calibration of the eye movements, such as different gains in the two signals, and misalignment of electrodes producing crosstalk. These transformations of the signals create problems in relating the two dimensional EOG to actual rotations of the eyes. The application of an artificial neural network (ANN) that could map 2D recordings into 2D eye positions would overcome this problem and improve the utility of EOG. To determine whether ANNs are capable of correctly calibrating the saccadic eye movement data from 2D EOG (i.e. performing the necessary inverse transformation), the ANNs were first tested on data generated from mathematical models of saccadic eye movements. Multi-layer perceptrons (MLPs) with non-linear activation functions and trained with back propagation proved to be capable of calibrating simulated EOG data to a mean accuracy of 0.33° of visual angle (SE = 0.01). Linear perceptrons (LPs) were only nearly half as accurate. For five subjects performing a saccadic eye movement task in the upper right quadrant of the visual field, the mean accuracy provided by the MLPs was 1.07° of visual angle (SE = 0.01) for EOG data, and 0.95° of visual angle (SE = 0.03) for infrared limbus reflection (IRIS®) data. MLPs enabled calibration of 2D saccadic EOG to an accuracy not significantly different to that obtained with the infrared limbus tracking data.<br>Thesis (PhD Doctorate)<br>Doctor of Philosophy (PhD)<br>School of Applied Psychology<br>Griffith Health<br>Full Text
26
Зубенко, О. В., Л. М. Семенова, O. V. Zubenko, and L. M. Semenova. "Artificial Neural Networks and Their Current Level of Development." Thesis, Міжнародний гуманітарний університет; Південний регіональний центр Національної академії правових наук України, 2018. http://ir.lib.vntu.edu.ua//handle/123456789/24113.
Full textAbstract:
Neural networks, as one of the leading modern areas of information technology development, are reviewed in this work. The general concept of the neural network, the main types of them, as well their current level of development are presented.<br>В роботі розглянуто нейронні мережі як один з провідних сучасних напрямків розвитку інформаційних технологій. Представлено загальну концепцію нейронної мережі, основні різновиди таких мереж та їх сучасний рівень розвитку.
27
Shi, Arthur Q. X. "Structural Damage Assessment Using Artificial Neural Networks and Artificial Immune Systems." DigitalCommons@CalPoly, 2015. https://digitalcommons.calpoly.edu/theses/1499.
Full textAbstract:
Structural health monitoring (SHM) systems have been technologically advancing over the past few years. Improvements in fabrication and microelectronics allow the development of highly sophisticated sensor arrays, capable of detecting and transmitting an unprecedented amount of data. As the complexity of the hardware increases, research has been performed in developing the means to best utilize and effectively process the data. Algorithms from other computational fields are being introduced for the first time into SHM systems. Among them, the artificial neural network (ANN) and artificial immune systems (AIS) show great potential. In this thesis, features are extracted out of the acceleration data with the use of discrete wavelet transforms (DWT)s first. The DWT coefficients are used to calculate energy ratios, which are then classified using a neural network and an AIS algorithm known as negative selection (NS). The effectiveness of both methods are validated using simulated acceleration data of a four story structure exhibiting various damage states via computer simulation.
28
Erdebil, Yonca. "Modeling severe ATV injuries using artificial neural networks." Thesis, University of Ottawa (Canada), 2005. http://hdl.handle.net/10393/26897.
Full textAbstract:
This thesis develops a model for severe all-terrain vehicle (ATV) injuries using artificial neural networks (ANNs) with data from the Canadian Hospitals Injury Reporting and Prevention Program (CHIRPP) and analyzes the model to find the contribution of each factor in predicting severe injury. From the analysis of the model, recommendations are made on the factors that should be investigated further to reduce severe injuries.
An analysis of ANN architecture shows that a configuration with no hidden nodes or layers results in optimal performance. The performance results of the ANN gives a logarithmic-sensitivity index of 0.09, sensitivity of 44%, specificity of 84%, correct classification rate (CCR) of 70% and receiver operating curve (ROC) area of 0.72. The most important input factors for predicting severe injury are: nature of injury, helmet, age group, mechanism, seat position, circumstances of collapse, body part and sex.
29
Mbandi, Aderiana Mutheu. "Using linear regression and ANN techniques in determining variable importance." Thesis, Cape Peninsula University of Technology, 2009. http://hdl.handle.net/20.500.11838/879.
Full textAbstract:
Thesis (MTech (Chemical Engineering))--Cape Peninsula University of Technology, 2009.
Includes bibliographical references (leaves 95-100).<br>The use of Neural Networks in chemical engineering is well documented. There has
also been an increase in research concerned with the explanatory capacity of Neural
Networks although this has been hindered by the regard of Artificial Neural Networks
(ANN’s) as a black box technology.
Determining variable importance in complex systems that have many variables as
found in the fields of ecology, water treatment, petrochemical production, and
metallurgy, would reduce the variables to be used in optimisation exercises, easing
complexity of the model and ultimately saving money. In the process engineering
field, the use of data to optimise processes is limited if some degree of process
understanding is not present.
The project objective is to develop a methodology that uses Artificial Neural Network
(ANN) technology and Multiple Linear Regression (MLR) to identify explanatory
variables in a dataset and their importance on process outputs. The methodology is
tested by using data that exhibits defined and well known numeric relationships. The
numeric relationships are presented using four equations.
The research project assesses the relative importance of the independent variables
by using the “dropping method” on a regression model and ANN’s. Regression used
traditionally to determine variable contribution could be unsuccessful if a highly nonlinear
relationship exists. ANN’s could be the answer for this shortcoming.
For differentiation, the explanatory variables that do not contribute significantly
towards the output will be named “suspect variables”. Ultimately the suspect
variables identified in the regression model and ANN should be the same, assuming
a good regression model and network. The dummy variables introduced to the four equations are successfully identified as
suspect variables. Furthermore, the degree of variable importance was determined
using linear regression and ANN models. As the equations complexity increased, the
linear regression models accuracy decreased, thus suspect variables are not
correctly identified. The complexity of the equations does not affect the accuracy of
the ANN model, and the suspect variables are correctly identified.
The use of R2 and average error in establishing a criterion for identifying suspect
variables is explored. It is established that the cumulative variable importance
percentage (additive percentage), has to be below 5% for the explanatory variable to
be considered a suspect variable. Combining linear regression and ANN provides insight into the importance of explanatory variables and indeed suspect variables and their contribution can be determined. Suspect variables can be eliminated from the model once identified
simplifying the model, and increasing accuracy of the model.
30
Ennett, Colleen Michelle. "Coronary surgery mortality prediction using artificial neural networks." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1999. http://www.collectionscanada.ca/obj/s4/f2/dsk1/tape7/PQDD_0020/MQ48150.pdf.
Full text
31
Risi, Sebastian. "Towards Evolving More Brain-Like Artificial Neural Networks." Doctoral diss., University of Central Florida, 2012. http://digital.library.ucf.edu/cdm/ref/collection/ETD/id/5460.
Full textAbstract:
An ambitious long-term goal for neuroevolution, which studies how artificial evolutionary processes can be driven to produce brain-like structures, is to evolve neurocontrollers with a high density of neurons and connections that can adapt and learn from past experience. Yet while neuroevolution has produced successful results in a variety of domains, the scale of natural brains remains far beyond reach. In this dissertation two extensions to the recently introduced Hypercube-based NeuroEvolution of Augmenting Topologies (HyperNEAT) approach are presented that are a step towards more brain-like artificial neural networks (ANNs). First, HyperNEAT is extended to evolve plastic ANNs that can learn from past experience. This new approach, called adaptive HyperNEAT, allows not only patterns of weights across the connectivity of an ANN to be generated by a function of its geometry, but also patterns of arbitrary local learning rules. Second, evolvable-substrate HyperNEAT (ES-HyperNEAT) is introduced, which relieves the user from deciding where the hidden nodes should be placed in a geometry that is potentially infinitely dense. This approach not only can evolve the location of every neuron in the network, but also can represent regions of varying density, which means resolution can increase holistically over evolution. The combined approach, adaptive ES-HyperNEAT, unifies for the first time in neuroevolution the abilities to indirectly encode connectivity through geometry, generate patterns of heterogeneous plasticity, and simultaneously encode the density and placement of nodes in space. The dissertation culminates in a major application domain that takes a step towards the general goal of adaptive neurocontrollers for legged locomotion.<br>ID: 031001435; System requirements: World Wide Web browser and PDF reader.; Mode of access: World Wide Web.; Adviser: Kenneth O. Stanley.; Title from PDF title page (viewed June 24, 2013).; Thesis (Ph.D.)--University of Central Florida, 2012.; Includes bibliographical references (p. 165-178).<br>Ph.D.<br>Doctorate<br>Computer Science<br>Engineering and Computer Science<br>Computer Science
32
Carey, Howard J. III. "EEG Interictal Spike Detection Using Artificial Neural Networks." VCU Scholars Compass, 2016. http://scholarscompass.vcu.edu/etd/4648.
Full textAbstract:
Epilepsy is a neurological disease causing seizures in its victims and affects approximately 50 million people worldwide. Successful treatment is dependent upon correct identification of the origin of the seizures within the brain. To achieve this, electroencephalograms (EEGs) are used to measure a patient’s brainwaves. This EEG data must be manually analyzed to identify interictal spikes that emanate from the afflicted region of the brain. This process can take a neurologist more than a week and a half per patient. This thesis presents a method to extract and process the interictal spikes in a patient, and use them to reduce the amount of data for a neurologist to manually analyze. The effectiveness of multiple neural network implementations is compared, and a data reduction of 3-4 orders of magnitude, or upwards of 99%, is achieved.
33
Rodrigo, Hansapani Sarasepa. "Bayesian Artificial Neural Networks in Health and Cybersecurity." Scholar Commons, 2017. http://scholarcommons.usf.edu/etd/6940.
Full textAbstract:
Being in the era of Big data, the applicability and importance of data-driven models like artificial neural network (ANN) in the modern statistics have increased substantially. In this dissertation, our main goal is to contribute to the development and the expansion of these ANN models by incorporating Bayesian learning techniques. We have demonstrated the applicability of these Bayesian ANN models in interdisciplinary research including health and cybersecurity.
Breast cancer is one of the leading causes of deaths among females. Early and accurate diagnosis is a critical component which decides the survival of the patients. Including the well known ``Gail Model", numerous efforts are being made to quantify the risk of diagnosing malignant breast cancer. However, these models impose some limitations on their use of risk prediction. In this dissertation, we have developed a diagnosis model using ANN to identify the potential breast cancer patients with their demographic factors and the previous mammogram results. While developing the model, we applied the Bayesian regularization techniques (evidence procedure), along with the automatic relevance determination (ARD) prior, to minimize the network over-fitting. The optimal Bayesian network has 81\% overall accuracy in correctly classifying the actual status of breast cancer patients, 59\% sensitivity in accurately detecting the malignancy and 83\% specificity in correctly detecting non-malignancy. The area under the receiver operating characteristic curve (0.7940) shows that this is a moderate classification model.
We then present a new Bayesian ANN model for developing a nonlinear Poisson regression model which can be used for count data modeling. Here, we have summarized all the important steps involved in developing the ANN model, including the forward-propagation, backward-propagation and the error gradient calculations of the newly developed network. As a part of this, we have introduced a new activation function into the output layer of the ANN and error minimizing criterion, using count data. Moreover, we have expanded our model to incorporate the Bayesian learning techniques. The performance our model is tested using simulation data.
In addition to that, a piecewise constant hazard model is developed by extending the above nonlinear Poisson regression model under the Bayesian setting. This model can be utilized over the other conventional methods for accurate survival time prediction. With this, we were able to significantly improve the prediction accuracies. We captured the uncertainties of our predictions by incorporating the error bars which could not achieve with a linear Poisson model due to the overdispersion in the data. We also have proposed a new hybrid learning technique, and we evaluated the performance of those techniques with a varying number of hidden nodes and data size.
Finally, we demonstrate the suitability of Bayesian ANN models for time series forecasting by using an online training algorithm. We have developed a vulnerability forecast model for the Linux operating system by using this approach.
34
Suzdalev, Ivan. "Artificial neural networks to updrafts localization and forecasting." Doctoral thesis, Lithuanian Academic Libraries Network (LABT), 2013. http://vddb.laba.lt/obj/LT-eLABa-0001:E.02~2013~D_20130308_165902-64063.
Full textAbstract:
The dissertation examines the thermal flow detection and prediction prob-lems during an autonomous aircraft flight. The main research object is the thermal flows and artificial neural networks. Thermal flows are a very im-portant source for improving autonomous aircraft flight parameters, such as flight time and duration.
The primary aim of the dissertation is to create methodologies and algorithms to detect, identify and to successfully predict the parameters the thermal flows. The application are of the methods and algorithms developed is autonomous aircraft control system synthesis, research on mesoscale meteorological phenomena and synthesis of computing systems using biological models.
The following objectives are carried out: thermal flow sensing using aircraft navigational parameters measurement data, thermal flow simulation modeling and data input necessary for modeling.
The dissertation consists of an introduction, four chapters, conclusions, bibliography, and list of author publications on the topic as well as three annexes.
The introductory chapter discusses the research problem and the relevance of the research described in the thesis, formulates the goal and objectives, describes the research methodology, scientific novelty, the practical significance of the results, hypotheses. In the end of the introduction a list of author's publications on the topic and the structure of the dissertation are presented.
The first section provides a review of previous... [to full text]<br>Disertacijoje nagrinėjamos terminių srautų paieškos ir prognozavimo autonominio orlaivio skrydžio metu problemos. Pagrindinis tyrimų objektas yra terminių srautų aparatinis aptikimas ir prognozavimas. Terminiai srautai yra labai svarbus autonominio orlaivio skrydžio charakteristikų, kaip antai skrydžio laikas ir trukmė, gerinimo šaltinis.
Pagrindinis disertacijos tikslas – sukurti metodikas ir algoritmus, leidžiančius aptikti terminį srautą, nustatyti bei sėkmingai prognozuoti jo parametrus. Sukurtų metodų ir algoritmų taikymo sritis – autonominių orlaivių valdymo sistemų sintezė, meteorologiniai mezomastelinių meteorologinių reiškinių tyrimai, biologinius skaičiavimo modelius naudojančių sistemų sintezė.
Darbe sprendžiami keli uždaviniai: terminio srauto aptikimas naudojant orlaivio navigacinių parametrų matavimo duomenis, terminio srauto modeliavimas bei modeliui reikalingų duomenų pateikimas.
Disertaciją sudaro įvadas, keturi skyriai, rezultatų apibendrinimas, naudotos literatūros ir autoriaus publikacijų disertacijos tema sąrašai ir tris priedai.
Įvadiniame skyriuje aptariama tiriamoji problema, darbo aktualumas, aprašomas tyrimų objektas, formuluojamas darbo tikslas bei uždaviniai, aprašoma tyrimų metodika, darbo mokslinis naujumas, darbo rezultatų praktinė reikšmė, ginamieji teiginiai. Įvado pabaigoje pristatomos disertacijos tema autoriaus paskelbtos publikacijos ir konferencijų pranešimai bei disertacijos struktūra.
Pirmajame skyriuje pateikiama su disertacijos... [toliau žr. visą tekstą]
35
Yates, W. B. "Algebraic specification and correctness of artificial neural networks." Thesis, Swansea University, 1994. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.636706.
Full textAbstract:
This thesis proposes a framework, based on formal methods, for the design, specification, and analysis of 1. neurocomputers as seen from the perspective of hardware, and 2. real world tasks as seen from the perspective of a user, in order to give useful definitions of correctness. We apply the theory of synchronous concurrent algorithms to a number of well known neural network models. This gives us a detailed, and precise description of the spatial and temporal behaviour of the network's operation. Such an operational semantics is necessary for defining a notion of correctness for such sytems. In order to formally specify a task and define its correctness we extend the standard treatment of synchronous concurrent algorithm correctness to the case of approximate correctness, and using mathematical tools from universal algebra and topology, examine the semantics of a number of natural 'approximate specifications'. We apply this framework to two case studies: the requirements analysis of a hospital waiting list management system, and the implementation of a hypothetical anti-ballistic missile firing system.
36
侯江濤 and Kong-to William Hau. "Artificial neural networks, motor programs and motor learning." Thesis, The University of Hong Kong (Pokfulam, Hong Kong), 1999. http://hub.hku.hk/bib/B31240227.
Full text
37
Clark, Jonathan Y. "Botanical identification and classification using artificial neural networks." Thesis, University of Reading, 2000. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.269973.
Full text
38
Whittington, Gary. "Theory, application and implementation of artificial neural networks." Thesis, University of Aberdeen, 1993. http://digitool.abdn.ac.uk/R?func=search-advanced-go&find_code1=WSN&request1=AAIU069169.
Full textAbstract:
This thesis examines the theoretical and practical problems associated with the application of Artificial Neural Networks (ANN). The research reported focuses upon the ANN model proposed by Kohonen, the self-organising Kohonen Feature Map (KFM). This thesis is divided into three main sections: theory, implementation and application. The theoretical section of this thesis examines the properties and limitations of the Kohonen Feature Map network and its derivative models. Based upon this examination a novel class of network models, the Adaptive Kohonen Feature Map (AKFM) model, is proposed to overcome specific limitations of the original model. By utilising these network models a hierarchical ANN architecture, the Hierarchical Adaptive Kohonen Feature Map (HAKFM) model, is proposed and its properties described. The second section of this thesis examines the implementation of ANN. The discussion is divided into two sections, software and hardware, with the emphasis being placed upon the former. In particular the methodologies required for the implementation of ANN systems are examined in detail. The effectiveness of these techniques are reported based upon experimental results gathered from the construction of several prototype systems and computer simulations. The final section of this thesis addresses the requirement to migrate ANN from the laboratory environments into the real-world. To address this requirement a methodology is outlined for the development of ANN based applications and systems. The methodology provides an integrated framework to assist with this process. The methodology is intended to support several different perspectives upon this multifaceted task, including those of the application engineers' and the project managers'. This methodology comprises several phases that each include a definition of an aim and objectives thus enabling the progress of the whole project to be monitored.
39
Hau, Kong-to William. "Artificial neural networks, motor programs and motor learning /." Hong Kong : University of Hong Kong, 1999. http://sunzi.lib.hku.hk/hkuto/record.jsp?B2177920X.
Full text
40
Al-Bulushi, Nabil. "Predicting reservoir properties using artificial neural networks (ANNs)." Thesis, Imperial College London, 2008. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.498402.
Full text
41
Docking, Philip John. "Differentiating noise and modulators in artificial neural networks." Thesis, Open University, 1991. http://oro.open.ac.uk/57348/.
Full text
42
Gritsenko, Andrey. "Bringing interpretability and visualization with artificial neural networks." Diss., University of Iowa, 2017. https://ir.uiowa.edu/etd/5764.
Full textAbstract:
Extreme Learning Machine (ELM) is a training algorithm for Single-Layer Feed-forward Neural Network (SLFN). The difference in theory of ELM from other training algorithms is in the existence of explicitly-given solution due to the immutability of initialed weights. In practice, ELMs achieve performance similar to that of other state-of-the-art training techniques, while taking much less time to train a model. Experiments show that the speedup of training ELM is up to the 5 orders of magnitude comparing to standard Error Back-propagation algorithm.
ELM is a recently discovered technique that has proved its efficiency in classic regression and classification tasks, including multi-class cases. In this thesis, extensions of ELMs for non-typical for Artificial Neural Networks (ANNs) problems are presented. The first extension, described in the third chapter, allows to use ELMs to get probabilistic outputs for multi-class classification problems. The standard way of solving this type of problems is based 'majority vote' of classifier's raw outputs. This approach can rise issues if the penalty for misclassification is different for different classes. In this case, having probability outputs would be more useful. In the scope of this extension, two methods are proposed. Additionally, an alternative way of interpreting probabilistic outputs is proposed.
ELM method prove useful for non-linear dimensionality reduction and visualization, based on repetitive re-training and re-evaluation of model. The forth chapter introduces adaptations of ELM-based visualization for classification and regression tasks. A set of experiments has been conducted to prove that these adaptations provide better visualization results that can then be used for perform classification or regression on previously unseen samples.
Shape registration of 3D models with non-isometric distortion is an open problem in 3D Computer Graphics and Computational Geometry. The fifth chapter discusses a novel approach for solving this problem by introducing a similarity metric for spectral descriptors. Practically, this approach has been implemented in two methods. The first one utilizes Siamese Neural Network to embed original spectral descriptors into a lower dimensional metric space, for which the Euclidean distance provides a good measure of similarity. The second method uses Extreme Learning Machines to learn similarity metric directly for original spectral descriptors. Over a set of experiments, the consistency of the proposed approach for solving deformable registration problem has been proven.
43
Krishnamurthy, Raju Chemical Sciences & Engineering Faculty of Engineering UNSW. "Prediction of consumer liking from trained sensory panel information: evaluation of artificial neural networks (ANN)." Awarded by:University of New South Wales. Chemical Sciences & Engineering, 2007. http://handle.unsw.edu.au/1959.4/40746.
Full textAbstract:
This study set out to establish artificial neural networks (ANN) as an alternate to regression methods (multiple linear, principal components and partial least squares regression) to predict consumer liking from trained sensory panel data. The study has two parts viz., I) Flavour study - evaluation of ANNs to predict consumer flavour preferences from trained sensory panel data and 2) Fragrance study ??? evaluation of different ANN architectures to predict consumer fragrance liking from trained sensory panel data. In this study, a multi-layer feedforward neural network architecture with input, hidden and output layer(s) was designed. The back-propagation algorithm was utilised in training of neural networks. The network learning parameters such as learning rate and momentum rate were optimised by the grid experiments for a fixed number of learning cycles. In flavour study, ANNs were trained using the trained sensory panel raw data as well as transformed data. The networks trained with sensory panel raw data achieved 98% correct learning, whereas the testing was within the range of 28 -35%. A suitable transformation methods were applied to reduce the variations in trained sensory panel raw data. The networks trained with transformed sensory panel data achieved between 80-90% correct learning and 80-95% correct testing. In fragrance study, ANNs were trained using the trained sensory panel raw data as well as principal component data. The networks trained with sensory panel raw data achieved 100% correct learning, and testing was in a range of 70-94%. Principal component analysis was applied to reduce redundancy in the trained sensory panel data. The networks trained with principal component data achieved about 100% correct learning and 90% correct testing. It was shown that due to its excellent noise tolerance property and ability to predict more than one type of consumer liking using a single model, the ANN approach promises to be an effective modelling tool.
44
Winter, Marylin. "Artificial neural networks and map-matching for GPS navigation." Thesis, University of South Wales, 2006. https://pure.southwales.ac.uk/en/studentthesis/artificial-neural-networks-and-mapmatching-for-gps-navigation(67bf2a4a-fcd2-4a86-8895-0ed296461bc5).html.
Full textAbstract:
Global navigation satellite systems (GNSS), such as the Global Positioning System (GPS) have been increasingly used in navigation and tracking of vehicles. Using GPS, certain positioning errors and limitations, such as multipath effects and the geometric position of the satellites (DOP) or signal obstructions by high buildings, trees and terrain, have to be considered. Generally travel on road or footpath, map-matching algorithms can be used to correlate the computed system location with a digital map network. Map Matched GPS (MMGPS) is a test-bed simulator for researching algorithms and techniques to reduce the error in position provided by a low cost stand-alone GPS receiver. In order to correctly map-match the GPS positions, a decision about the correct road can be difficult, especially at road junctions, slip roads or almost parallel roads. Investigations into the use of artificial neural networks (ANNs) for reliability and accuracy improvement of map-matched GPS positioning was initiated in previous research [Winter, 2002]. However, there are generally strong interference effects that lead to slow learning and poor generalization when a single ANN is trained to perform different subtasks on different occasions [Jacobs et al., 1991], e.g. correct transport network (TN) segment selection considering different TN geometry. Interference can be reduced by training a system composed of several different "expert" ANNs using a TN geometry indicator to decide which of the experts should be used for each training case. An aim of this research was the design, development and implementation of such a modular neural network (MNN). This work uses a new measure for indicating TN geometry, directly derived from GPS positions in MMGPS. An improvement of more than 50% to traditional map-matching techniques was achieved using the proposed MNN approach, when the correct road could not be uniquely identified by map-matching.
45
Anderson, Jerone S. "A Study of Nutrient Dynamics in Old Woman Creek Using Artificial Neural Networks and Bayesian Belief Networks." Ohio University / OhioLINK, 2009. http://rave.ohiolink.edu/etdc/view?acc_num=ohiou1242921000.
Full text
46
Nigrini, L. B., and G. D. Jordaan. "Short term load forecasting using neural networks." Journal for New Generation Sciences, Vol 11, Issue 3: Central University of Technology, Free State, Bloemfontein, 2013. http://hdl.handle.net/11462/646.
Full textAbstract:
Published Article<br>Several forecasting models are available for research in predicting the shape of electric load curves. The development of Artificial Intelligence (AI), especially Artificial Neural Networks (ANN), can be applied to model short term load forecasting. Because of their input-output mapping ability, ANN's are well-suited for load forecasting applications.
ANN's have been used extensively as time series predictors; these can include feed-forward networks that make use of a sliding window over the input data sequence. Using a combination of a time series and a neural network prediction method, the past events of the load data can be explored and used to train a neural network to predict the next load point.
In this study, an investigation into the use of ANN's for short term load forecasting for Bloemfontein, Free State has been conducted with the MATLAB Neural Network Toolbox where ANN capabilities in load forecasting, with the use of only load history as input values, are demonstrated.
47
Dai, Jing. "Reservoir-computing-based, biologically inspired artificial neural networks and their applications in power systems." Diss., Georgia Institute of Technology, 2013. http://hdl.handle.net/1853/47646.
Full textAbstract:
Computational intelligence techniques, such as artificial neural networks (ANNs), have been widely used to improve the performance of power system monitoring and control. Although inspired by the neurons in the brain, ANNs are largely different from living neuron networks (LNNs) in many aspects. Due to the oversimplification, the huge computational potential of LNNs cannot be realized by ANNs. Therefore, a more brain-like artificial neural network is highly desired to bridge the gap between ANNs and LNNs.
The focus of this research is to develop a biologically inspired artificial neural network (BIANN), which is not only biologically meaningful, but also computationally powerful. The BIANN can serve as a novel computational intelligence tool in monitoring, modeling and control of the power systems.
A comprehensive survey of ANNs applications in power system is presented. It is shown that novel types of reservoir-computing-based ANNs, such as echo state networks (ESNs) and liquid state machines (LSMs), have stronger modeling capability than conventional ANNs. The feasibility of using ESNs as modeling and control tools is further investigated in two specific power system applications, namely, power system nonlinear load modeling for true load harmonic prediction and the closed-loop control of active filters for power quality assessment and enhancement. It is shown that in both applications, ESNs are capable of providing satisfactory performances with low computational requirements.
A novel, more brain-like artificial neural network, i.e. biologically inspired artificial neural network (BIANN), is proposed in this dissertation to bridge the gap between ANNs and LNNs and provide a novel tool for monitoring and control in power systems. A comprehensive survey of the spiking models of living neurons as well as the coding approaches is presented to review the state-of-the-art in BIANN research. The proposed BIANNs are based on spiking models of living neurons with adoption of reservoir-computing approaches. It is shown that the proposed BIANNs have strong modeling capability and low computational requirements, which makes it a perfect candidate for online monitoring and control applications in power systems.
BIANN-based modeling and control techniques are also proposed for power system applications. The proposed modeling and control schemes are validated for the modeling and control of a generator in a single-machine infinite-bus system under various operating conditions and disturbances. It is shown that the proposed BIANN-based technique can provide better control of the power system to enhance its reliability and tolerance to disturbances.
To sum up, a novel, more brain-like artificial neural network, i.e. biologically inspired artificial neural network (BIANN), is proposed in this dissertation to bridge the gap between ANNs and LNNs and provide a novel tool for monitoring and control in power systems. It is clearly shown that the proposed BIANN-based modeling and control schemes can provide faster and more accurate control for power system applications.
The conclusions, the recommendations for future research, as well as the major contributions of this research are presented at the end.
48
Li, Tan. "Tire-Pavement Interaction Noise (TPIN) Modeling Using Artificial Neural Network (ANN)." Diss., Virginia Tech, 2017. http://hdl.handle.net/10919/87417.
Full textAbstract:
Tire-pavement interaction is a dominant noise source for passenger cars and trucks above 25 mph (40 km/h) and 43 mph (70 km/h), respectively. For the same pavement, tires with different tread pattern and construction generate noise of different levels and frequencies. In the present study, forty-two different tires were tested over a range of speeds (45-65 mph, i.e., 72-105 km/h) on a non-porous asphalt pavement (a section of U.S. Route 460, both eastbound and westbound). An On-Board Sound Intensity (OBSI) system was instrumented on the test vehicle to collect the tire noise data at both the leading and trailing edge of the tire contact patch. An optical sensor recording the once-per-revolution signal of the wheel was also installed to monitor the vehicle speed and, more importantly, to provide the data needed to perform the order tracking analysis in order to break down the tire noise into two components. These two components are: the tread pattern and the non-tread pattern noise. Based on the experimental noise data collected, two artificial neural networks (ANN) were developed to predict the tread pattern (ANN1) and the non-tread pattern noise (ANN2) components, separately. The inputs of ANN1 are the coherent tread profile spectrum and the air volume velocity spectrum calculated from the digitized 3D tread pattern. The inputs of ANN2 are the tire size and tread rubber hardness. The vehicle speed is also included as input for the two ANN's. The optimized ANN's are able to predict the tire-pavement interaction noise well for different tires on the pavement tested. Another outcome of this work is the complete literature review on Tire-Pavement Interaction Noise (TPIN), as an appendix of this dissertation and covering ~1000 references, which might be the most comprehensive compilation of this topic.<br>PHD
49
Boudani, Nabil I. "Cascade artificial neural networks technique for solving ellipsometry problems." FIU Digital Commons, 1998. http://digitalcommons.fiu.edu/etd/1781.
Full textAbstract:
Ellipsometry is a well known optical technique used for the characterization of reflective surfaces in study and films between two media. It is based on measuring the change in the state of polarization that occurs as a beam of polarized light is reflected from or transmitted through the film. Measuring this change can be used to calculate parameters of a single layer film such as the thickness and the refractive index. However, extracting these parameters of interest requires significant numerical processing due to the noninvertible equations. Typically, this is done using least squares solving methods which are slow and adversely affected by local minima in the solvable surface. This thesis describes the development and implementation of a new technique using only Artificial Neural Networks (ANN) to calculate thin film parameters. The new method offers a speed in the orders of magnitude faster than preceding methods and convergence to local minima is completely eliminated.
50
Marcham, Laurence John. "Control of industrial manipulator vibration using artificial neural networks." Thesis, Southampton Solent University, 1997. http://ssudl.solent.ac.uk/1270/.
Full textAbstract:
This research project is a study of the application of artificial neural networks to the control of robot manipulator vibration, specifically concentrating on the improvement of dynamic path accuracy during linear motion. The aim of the investigation was to achieve this through compensation of the inherent vibration experienced at the end effctor. The first phase of the project was concerned with the mechanical structure of the manipulator with the specific aim of attaining a comprehensive understanding of robot manipulator vibration. This was achieved through the formaulation of a mathematical model using Lagrangian mechanics and through an empirical description, obtained through the implementation of laser interferometry and experimental modal analysis. The laser interferometry data were used to produce an empirical model, using an artificial neeural network (ANN) architecture, to learn to predict the vibration experienced at the end-effector. The second phase of the project concentrated on the simulation and design of an ANN based active vibration compensation system. The ANN architecture used was a time delay Elman network and the learning algorith used was a modified stochastic/backpropagation strategy. In simulation the controller was able to realise a reduction in vibration of 83.6 percent after training. After implementing the controller on a PUMA562C industrial manipulator a modest reduction of 16 per cent was achieved. The considerably lower magnitude of reduction was caused by the under-specified design of mechanical actuator Finally to assess the performance characteristics of the ANN based controller an analysis of the adaptive capabilities of the system to slowly changing manipulator characteristics and a comparison of the systems capabilities with a digital PID phase inverse controller applied to the control problem were investigated. The ANN based controller was capable of providing limited reakl-time adaption due to continuous reinforcement feedback. The ANN controller produced ann additional 6 percent reduction in vibration over the PID controller, despite a significantly lower sampling rate.