Segui questo link per vedere altri tipi di pubblicazioni sul tema: Artificial neural networks.
Tesi sul tema "Artificial neural networks"
Cita una fonte nei formati APA, MLA, Chicago, Harvard e in molti altri stili
Vedi i top-50 saggi (tesi di laurea o di dottorato) per l'attività di ricerca sul tema "Artificial neural networks".
Accanto a ogni fonte nell'elenco di riferimenti c'è un pulsante "Aggiungi alla bibliografia". Premilo e genereremo automaticamente la citazione bibliografica dell'opera scelta nello stile citazionale di cui hai bisogno: APA, MLA, Harvard, Chicago, Vancouver ecc.
Puoi anche scaricare il testo completo della pubblicazione scientifica nel formato .pdf e leggere online l'abstract (il sommario) dell'opera se è presente nei metadati.
Vedi le tesi di molte aree scientifiche e compila una bibliografia corretta.
1
Boychenko, I. V., and G. I. Litvinenko. "Artificial neural networks." Thesis, Вид-во СумДУ, 2009. http://essuir.sumdu.edu.ua/handle/123456789/17044.
Testo completo
2
Menneer, Tamaryn Stable Ia. "Quantum artificial neural networks." Thesis, University of Exeter, 1999. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.286530.
Testo completo
3
Chambers, Mark Andrew. "Queuing network construction using artificial neural networks /." The Ohio State University, 2000. http://rave.ohiolink.edu/etdc/view?acc_num=osu1488193665234291.
Testo completo
4
Orr, Ewan. "Evolving Turing's Artificial Neural Networks." Thesis, University of Canterbury. Department of Physics and Astronomy, 2010. http://hdl.handle.net/10092/4620.
Testo completoAbstract (sommario):
Our project uses ideas first presented by Alan Turing. Turing's immense contribution to mathematics and computer science is widely known, but his pioneering work in artificial intelligence is relatively unknown. In the late 1940s Turing introduced discrete Boolean artificial neural networks and, it has been argued that, he suggested that these networks be trained via evolutionary algorithms. Both artificial neural networks and evolutionary algorithms are active fields of research. Turing's networks are very basic yet capable of complex tasks such as processing sequential input; consequently, they are an excellent model for investigating the application of evolutionary algorithms to artificial neural networks. We define an example of these networks using sequential input and output, and we devise evolutionary algorithms that train these networks. Our networks are discrete Boolean networks where every 'neuron' either performs NAND or identity, and they can represent any function that maps one sequence of bit strings to another. Our algorithms use supervised learning to discover networks that represent such functions. That is, when searching for a network that represents a particular function our algorithms use input-output pairs of that function as examples to aid the discovery of solution networks. To test our ideas we encode our networks and implement the algorithms in a computer program. Using this program we investigate the performance of our networks and algorithms on simple problems such as searching for networks that realize the parity function and the multiplexer function. This investigation includes the construction and testing of an intricate crossover operator. Because our networks are composed of simple 'neurons' they are a suitable test-bed for novel training schemes. To improve our evolutionary algorithms for some problems we employ the symmetry of the problem to reduce its search space. We devise and test a means of using subgroups of the group of permutation of inputs of a function to aid evolutionary searches search for networks that represent that function. In particular, we employ the action of the permutation group S₂ to 'cut down' the search space when we search for networks that represent functions such as parity.
5
Varoonchotikul, Pichaid. "Flood forecasting using artificial neural networks /." Lisse : Balkema, 2003. http://www.e-streams.com/es0704/es0704_3168.html.
Testo completo
6
Fraticelli, Chiara. "Λc reconstruction with artificial neural networks". Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2020. http://amslaurea.unibo.it/19985/.
Testo completoAbstract (sommario):
Il rivelatore ALICE studia collisioni di ioni pesanti ultrarelativistici in modo da creare e di conseguenza studiare lo stato della materia chiamato plasma di quark e gluoni. Questo obiettivo risulta difficoltoso data la sua vita breve, quindi facciamo riferimento a misure indirette per la prova della sua esistenza. In questa tesi abbiamo sfruttato tecniche di machine learning per studiare il decadimento del barione charmato Λc per dedurre alcune sue proprietà. In particolare abbiamo usato il metodo delle reti neurali per ricavare tutte le informazioni possibili con la tecninca di un'analisi multivariata.
7
Millevik, Daniel, and Michael Wang. "Stock Forecasting Using Artificial Neural Networks." Thesis, KTH, Skolan för datavetenskap och kommunikation (CSC), 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-166455.
Testo completoAbstract (sommario):
This paper studies the potential of artificial neural networks (ANNs) in stock forecasting. It also investigates how the number of neurons in the network, as well as the distribution of the training data into training, validation and testing sets, affect the accuracy of the network. By using MATLAB and its Neural Network Toolbox tests were carried out with a two-layer feedforward neural network (FFNN). These are carried out by collecting five years of historical data from the Dow Jones Industrial Average (DJIA) stock index, which is then used for training the network. Finally, retraining the network with different configurations, with respect to the number of neurons and the training data distribution, in order to perform tests on a separate year of the DJIA stock index. The best acquired accuracy for predicting the closing stock price one day ahead is around 99\%. There are configurations that give worse accuracy. These are mainly the configurations using many neurons as well as the ones with low training data percentage. The conclusion is that there is potential for stock forecasting using ANNs but only predicting one day forward might not be practically useful. It is important to adapt the network to the given problem and its complexity and thus choosing the number of neurons accordingly. It will also be necessary to retrain the network several times in order to find one with good performance. Besides the training data distribution it is more important to gather enough data for the network's training set to allow it to adapt and generalize to the problem at hand.<br>Denna rapport studerar ifall artificiella neuronnät (ANN) potentiellt kan tillämpas på den finansiella marknaden för att förutspå aktiepriser. Det undersöks även hur antalet neuroner i nätverket och hur fördelningen av träningsdatat i träning, validering och testning, påverkar nätverkets noggrannhet. Tester utfördes på en ''two layer feedforward neural network'' (FFNN) med hjälp av MATLAB och dess Neural Network Toolbox. Dessa utfördes genom att samla fem år av historisk data för ''Dow Jones Industrial Average'' (DJIA) aktieindex som används för att träna nätverket. Slutligen så tränas nätverket i omgångar med olika konfigurationer bestående av ändringar på antalet neuroner och fördelningen av träningsdatat. Detta för att utföra tester på ett separat år av DJIA aktieindex. Den bästa noggrannheten som erhölls vid förutsägning av stängningspriset i börsen efter en dag är ca 99\%. Det finns konfigurationer som ger sämre noggrannhet. Dessa är i synnerhet konfigurationer med ett stort antal neuroner samt de med låg andel träningsdata. Slutsatsen är att det finns potential vid användning av artificiella neuronnät men det är inte praktiskt användbart att bara förutspå aktiepriser en dag framåt. Det är viktigt att anpassa nätverket till det givna problemet och dess komplexitet. Därför ska antalet neuroner i nätverket väljas därefter. Det är också nödvändigt att träna om nätverket ett flertal gånger för att erhålla ett med bra prestanda. Utöver fördelningen av träningsdatat så är det viktigare att samla tillräckligt med data för träningen av nätverket för att försäkra sig om att den anpassar och generaliserar sig till det aktuella problemet.
8
Prasad, Jayan Ganesh Information Technology & Electrical Engineering Australian Defence Force Academy UNSW. "Financial forecasting using artificial neural networks." Awarded by:University of New South Wales - Australian Defence Force Academy. School of Information Technology and Electrical Engineering, 2008. http://handle.unsw.edu.au/1959.4/38700.
Testo completoAbstract (sommario):
Despite the extent of a theoretical framework in financial market studies, a vast majority of the traders, investors and computer scientists have relied only on technical and timeseries data for predicting future prices. So far, the forecasting models have rarely incorporated macro-economic and market fundamentals successfully, especially with short-term predictions ranging less than a month. In this investigation on the predictability of certain financial markets, an attempt has been made to incorporate a un-exampled and encompassing set of parameters into an Artificial Neural Network prediction system. Experiments were carried out on three market instruments ??? namely currency exchange rates, share prices and oil prices. The choice of parameters for inclusion or exclusion, and the time frame adopted for the experimental sets were derived from the market literature. Good directional prediction accuracies were achieved for currency exchange rates and share prices with certain parameters as inputs, which consisted of predicting short-term movements based on past movements. These predictions were better than the results produced by a traditional least square prediction method. The trading strategy developed based on the predictions also achieved a higher percentage of winning trades. No significant predictions were observed for oil prices. These results open up questions in the microstructure of the markets and provide an insight into the inputs required for market forecasting in the corresponding time frame, for future investigation. The study concludes by advocating the use of trend based input parameters and suggests ways to improve neural network forecasting models.
9
Ng, Roger K. W. "Rapid prototyping of artificial neural networks." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1996. http://www.collectionscanada.ca/obj/s4/f2/dsk2/ftp04/mq23440.pdf.
Testo completo
10
Hook, Jaroslav. "Are artificial neural networks learning machines?" Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1998. http://www.collectionscanada.ca/obj/s4/f2/dsk2/ftp01/MQ38651.pdf.
Testo completo
11
Coulibaly, Paulin. "Artificial neural networks for hydrological forecasting." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 2000. http://www.collectionscanada.ca/obj/s4/f2/dsk1/tape4/PQDD_0028/NQ52236.pdf.
Testo completo
12
Baker, Thomas Edward. "Implementation limits for artificial neural networks." Full text open access at:, 1990. http://content.ohsu.edu/u?/etd,268.
Testo completo
13
Garvin, Alan David Morris. "Self-structuring of artificial neural networks." Thesis, University of Cambridge, 1994. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.307948.
Testo completo
14
Watkins, Bruce E. "Data compression using artificial neural networks." Thesis, Monterey, California. Naval Postgraduate School, 1991. http://hdl.handle.net/10945/25801.
Testo completoAbstract (sommario):
Approved for public release; distribution is unlimited<br>This thesis investigates the application of artificial neural networks for the compression
of image data. An algorithm is developed using the competitive learning
paradigm which takes advantage of the parallel processing and classification capability
of neural networks to produce an efficient implementation of vector quantization.
Multi-Stage, tree searched, and classification vector quantization codebook design
techniques are adapted to the neural network design to reduce the computational
cost and hardware requirements. The results show that the new algorithm provides
a substantial reduction in computational costs and an improvement in performance.
15
Gulliford, Sarah Louise. "Artificial neural networks applied to radiotherapy." Thesis, Institute of Cancer Research (University Of London), 2003. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.404474.
Testo completo
16
Townsend, Joseph Paul. "Artificial development of neural-symbolic networks." Thesis, University of Exeter, 2014. http://hdl.handle.net/10871/15162.
Testo completoAbstract (sommario):
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.
17
Zhong, Xiaolin. "Robot calibration using artificial neural networks." Thesis, Edinburgh Napier University, 1995. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.295387.
Testo completo
18
Lukashev, A. "Basics of artificial neural networks (ANNs)." Thesis, Київський національний університет технологій та дизайну, 2018. https://er.knutd.edu.ua/handle/123456789/11353.
Testo completo
19
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.
Testo completoAbstract (sommario):
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.
20
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.
Testo completoAbstract (sommario):
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.
21
Miranda, Trujillo Luis Carlos. "Artificial Neural Networks in Greenhouse Modelling." Doctoral thesis, Humboldt-Universität zu Berlin, 2018. http://dx.doi.org/10.18452/19354.
Testo completoAbstract (sommario):
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.
22
Guiga, Linda. "Software protections for artificial neural networks." Electronic Thesis or Diss., Institut polytechnique de Paris, 2022. http://www.theses.fr/2022IPPAT024.
Testo completoAbstract (sommario):
Les réseaux de neurones (NNs) sont très présents dans notre vie quotidienne, à travers les smartphones, la reconnaissance faciale et biométrique ou même le domaine médical. Leur sécurité est donc de la plus haute importance. Si de tels modèles fuitent, cela mettrait non seulement en péril la confidentialité de données sensibles, mais porterait aussi atteinte à la propriété intellectuelle. La sélection d’une architecture adaptée et l'entraînement de ses paramètres prennent du temps - parfois des mois -- et nécessitent d'importantes ressources informatiques. C'est pourquoi un NN constitue une propriété intellectuelle. En outre, une fois l'architecture et/ou les paramètres connus d'un utilisateur malveillant, de multiples attaques peuvent être menées, telles des attaques contradictoires. Un attaquant trompe alors le modèle en ajoutant à l’entrée un bruit indétectable par l’œil humain. Cela peut mener à des usurpations d'identité. Les attaques par adhésion, qui visent à divulguer des informations sur les données d'entraînement, sont également facilitées par un accès au modèle. Plus généralement, lorsqu'un utilisateur malveillant a accès à un modèle, il connaît les sorties du modèle, ce qui lui permet de le tromper plus facilement. La protection des NNs est donc primordiale. Mais depuis 2016, ils sont la cible d'attaques de rétro-ingénierie de plus en plus puissantes. Les attaques de rétro-ingénierie mathématique résolvent des équations ou étudient la structure interne d'un modèle pour révéler ses paramètres. Les attaques par canaux cachés exploitent des fuites dans l'implémentation d'un modèle – par exemple à travers le cache ou la consommation de puissance – pour extraire le modèle. Dans cette thèse, nous visons à protéger les NNs en modifiant leur structure interne et en changeant leur implémentation logicielle.Nous proposons quatre nouvelles défenses. Les trois premières considèrent un contexte de boîte grise où l'attaquant a un accès partiel au modèle, et exploitent des modèles parasites pour contrer trois types d'attaques.Nous abordons d'abord des attaques mathématiques qui récupèrent les paramètres d'un modèle à partir de sa structure interne. Nous proposons d'ajouter un -- ou plusieurs -- réseaux de neurones par convolution (CNNs) parasites à divers endroits du modèle de base et de mesurer leur impact sur la structure en observant la modification des exemples contradictoires générés .La méthode précédente ne permet pas de contrer les attaques par canaux cachés extrayant les paramètres par l'analyse de la consommation de puissance ou électromagnétique. Pour cela, nous proposons d'ajouter du dynamisme au protocole précédent. Au lieu de considérer un -- ou plusieurs -- parasite(s) fixe(s), nous incorporons différents parasites à chaque exécution, à l'entrée du modèle de base. Cela nous permet de cacher l'entrée, nécessaire à l’extraction précise des poids. Nous montrons l'impact de cette défense à travers deux attaques simulées. Nous observons que les modèles parasites changent les exemples contradictoires. Notre troisième contribution découle de cela. Nous incorporons dynamiquement un autre type de parasite, des autoencodeurs, et montrons leur efficacité face à des attaques contradictoires courantes. Dans une deuxième partie, nous considérons un contexte de boîte noire où l'attaquant ne connaît ni l'architecture ni les paramètres. Les attaques d’extraction d'architecture reposent sur l'exécution séquentielle des NNs. La quatrième et dernière contribution que nous présentons dans cette thèse consiste à réordonner les calculs des neurones. Nous proposons de calculer les valeurs des neurones par blocs en profondeur, et d'ajouter de l’aléa. Nous prouvons que ce réarrangement des calculs empêche un attaquant de récupérer l’architecture du modèle initial<br>In a context where Neural Networks (NNs) are very present in our daily lives, be it through smartphones, face and biometrics recognition or even in the medical field, their security is of the utmost importance. If such models leak information, not only could it imperil the privacy of sensitive data, but it could also infringe on intellectual property.Selecting the correct architecture and training the corresponding parameters is time-consuming -- it can take months -- and requires large computational resources. This is why an NN constitutes intellectual property. Moreover, once a malicious user knows the architecture and/or the parameters, multiple attacks can be carried out, such as adversarial ones. Adversarial attackers craft a malicious datapoint by adding a small noise to the original input, such that the noise is undetectable to the human eye but fools the model. Such attacks could be the basis of impersonations. Membership attacks, which aim at leaking information about the training dataset, are also facilitated by the knowledge of a model. More generally, when a malicious user has access to a model, she also has access to the manifold of the model's outputs, making it easier for her to fool the model.Protecting NNs is therefore paramount. However, since 2016, they have been the target of increasingly powerful reverse-engineering attacks. Mathematical reverse-engineering attacks solve equations or study a model's internal structure to reveal its parameters. On the other hand, side-channel attacks exploit leaks in a model's implementation -- such as in the cache or power consumption -- to uncover the parameters and architecture. In this thesis, we seek to protect NN models by changing their internal structure and their software implementation.To this aim, we propose four novel countermeasures. In the first three, we consider a gray-box context where the attacker has partial access to the model, and we leverage parasitic models to counter three types of attacks.We first tackle mathematical attacks that recover a model's parameters based on its internal structure. We propose to add one -- or multiple -- parasitic Convolutional Neural Networks (CNNs) at various locations in the base model and measure the incurred change in the structure by observing the modification in generated adversarial samples.However, the previous method does not thwart side-channel attacks that extract the parameters through the analysis of power or electromagnetic consumption. To mitigate such attacks, we propose to add dynamism to the previous protocol. Instead of considering one -- or several -- fixed parasite(s), we incorporate different parasites at each run, at the entrance of the base model. This enables us to hide a model's input, necessary for precise weight extraction. We show the impact of this dynamic incorporation through two simulated attacks.Along the way, we observe that parasitic models affect adversarial examples. Our third contribution is derived from this, as we suggest a novel method to mitigate adversarial attacks. To this effect, we dynamically incorporate another type of parasite: autoencoders. We demonstrate the efficiency of this countermeasure against common adversarial attacks.In a second part, we focus on a black-box context where the attacker knows neither the architecture nor the parameters. Architecture extraction attacks rely on the sequential execution of NNs. The fourth and last contribution we present in this thesis consists in reordering neuron computations. We propose to compute neuron values by blocks in a depth-first fashion, and add randomness to this execution. We prove that this new way of carrying out CNN computations prevents a potential attacker from recovering a small enough set of possible architectures for the initial model
23
Bolt, George Ravuama. "Fault tolerance in artificial neural networks : are neural networks inherently fault tolerant?" Thesis, University of York, 1992. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.317683.
Testo completo
24
NAPOLI, CHRISTIAN. "A-I: Artificial intelligence." Doctoral thesis, Università degli studi di Catania, 2016. http://hdl.handle.net/20.500.11769/490996.
Testo completoAbstract (sommario):
In this thesis we proposed new neural architectures and information theory approaches. By means of wavelet analysis, neural networks, and the results of our own creations, namely the wavelet recurrent neural networks and the radial basis probabilistic neural networks,we tried to better understand, model and cope with the human behavior itself. The first idea was to model the workers of a crowdsourcing project as nodes on a cloud-computing system, we also hope to have exceeded the limits of such a definition. We hope to have opened a door on new possibilities to model the behavior of socially interconnected groups of people cooperating for the execution of a common task. We showed how it is possible to use the Wavelet Recurrent Neural Networks to model a quite complex thing such as the availability of resources on an online service or a computational cloud, then we showed that, similarly, the availability of crowd workers can be modeled, as well as the execution time of tasks performed by crowd workers. Doing that we created a tool to tamper with the timeline, hence allowing us to obtain predictions regarding the status of the crowd in terms of available workers and executed workflows. Moreover, with our inanimate reasoner based on the developed Radial Basis Probabilistic Neural Networks, firstly applied to social networks, then applied to living companies, we also understood how to model and manage cooperative networks in terms of workgroups creation and optimization. We have done that by automatically interpreting worker profiles, then automatically extrapolating and interpreting the relevant information among hundreds of features for each worker in order to create workgroups based on their skills, professional attitudes, experience, etc. Finally, also thanks to the suggestions of prof. Michael Bernstein of the Stanford University, we simply proposed to connect the developed automata. We made use of artificial intelligence to model the availability of human resources, but then we had to use a second level of artificial intelligence in order to model human workgroups and skills, finally we used a third level of artificial intelligence to model workflows executed by the said human resources once organized in groups and levels according to their experiences. In our best intentions, such a three level artificial intelligence could address the limits that, until now, have refrained the crowds from growing up as companies, with a well recognizable pyramidal structure, in order to reward experience, skill and professionalism of their workers. We cannot frankly say whether our work will really contribute or not to the so called "crowdsourcing revolution", but we hope at least to have shedded some light on the agreeable possibilities that are yet to come.
25
Lindefelt, Lisa. "Predicting gene expression using artificial neural networks." Thesis, University of Skövde, Department of Computer Science, 2002. http://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-707.
Testo completoAbstract (sommario):
<p>Today one of the greatest aims within the area of bioinformatics is to gain a complete understanding of the functionality of genes and the systems behind gene regulation. Regulatory relationships among genes seem to be of a complex nature since transcriptional control is the result of complex networks interpreting a variety of inputs. It is therefore essential to develop analytical tools detecting complex genetic relationships.</p><p>This project examines the possibility of the data mining technique artificial neural network (ANN) detecting regulatory relationships between genes. As an initial step for finding regulatory relationships with the help of ANN the goal of this project is to train an ANN to predict the expression of an individual gene. The genes predicted are the nuclear receptor PPAR-g and the insulin receptor. Predictions of the two target genes respectively were made using different datasets of gene expression data as input for the ANN. The results of the predictions of PPAR-g indicate that it is not possible to predict the expression of PPAR-g under the circumstances for this experiment. The results of the predictions of the insulin receptor indicate that it is not possible to discard using ANN for predicting the gene expression of an individual gene.</p>
26
Cavaco, Philip. "Artificial Grammar Recognition Using Spiking Neural Networks." Thesis, Mälardalen University, School of Innovation, Design and Engineering, 2009. http://urn.kb.se/resolve?urn=urn:nbn:se:mdh:diva-5875.
Testo completoAbstract (sommario):
<p>This thesis explores the feasibility of Artificial Grammar (AG) recognition using spiking neural networks. A biologically inspired minicolumn model is designed as the base computational unit. Two network topographies are defined with different ideologies. Both networks consists of minicolumn models, referred to as nodes, connected with excitatory and inhibitory connections. The first network contains nodes for every bigram and trigram producible by the grammar’s finite state machine (FSM). The second network has only nodes required to identify unique internal states of the FSM. The networks produce predictable activity for tested input strings. Future work to improve the performance of the networks is discussed. The modeling framework developed can be used by neurophysiological research to implement network layouts and compare simulated performance characteristics to actual subject performance.</p>
27
Guler, Altug. "Seismic Vulnerability Assessment Using Artificial Neural Networks." Master's thesis, METU, 2005. http://etd.lib.metu.edu.tr/upload/12606067/index.pdf.
Testo completoAbstract (sommario):
In this study, an alternative seismic vulnerability assessment model is developed. For this purpose, one of the most popular artificial intelligence techniques, Artificial Neural Network (ANN), is used.
Many ANN models are generated using 4 different network training functions, 1 to 50 hidden neurons and combination of structural parameters like number of stories, normalized redundancy scores, overhang ratios, soft story indices, normalized total column areas, normalized total wall areas are used to achieve the best assessment performance.
Duzce database is used throughout the thesis for training ANN. A neural network simulator is developed in Microsoft Excel using the weights and parameters obtained from the best model created at Duzce damage database studies. Afyon, Erzincan, and Ceyhan databases are simulated using the developed simulator. A recently created database named Zeytinburnu is used for the projection purposes. The building sesimic vulnerability assessment of Zeytinburnu area is conducted on 3043 buildings using the proposed procedure.
28
Frøyen, Even Bruvik. "Exploring Learning in Evolutionary Artificial Neural Networks." Thesis, Norges teknisk-naturvitenskapelige universitet, Institutt for datateknikk og informasjonsvitenskap, 2011. http://urn.kb.se/resolve?urn=urn:nbn:no:ntnu:diva-15689.
Testo completoAbstract (sommario):
Evolutionary artificial neural networks can adapt to new circumstances, and handle slight changes without catastrophic failure. However, under constantly changing circumstances, resulting in unpredictable grounds for evaluating success, the lack of memory of previous adaptations are a limiting factor. While further evolution can allow adaptations to new changes, the same is required for a return to a previous environment. To reduce the need for further evolution to deal with previously seen problems, this thesis looks at an approach to encourage previous knowledge to be retained across generations. It does this using back propagation in conjunction with an implementation of the HyperNEAT neuroevolutionary algorithm.
29
Turner, Joe. "Application of artificial neural networks in pharmacokinetics /." Connect to full text, 2003. http://setis.library.usyd.edu.au/adt/public_html/adt-NU/public/adt-NU20031007.090937/index.html.
Testo completo
30
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.
Testo completo
31
Hasan, Usama. "Artificial neural networks for voltage collapse monitoring." Thesis, Imperial College London, 1998. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.286623.
Testo completo
32
Porter, Nicholas David. "Facial feature processing using artificial neural networks." Thesis, University of Warwick, 1998. http://wrap.warwick.ac.uk/59539/.
Testo completoAbstract (sommario):
Describing a human face is a natural ability used in eveyday life. To the police, a witness description of a suspect is key evidence in the identification of the suspect. However, the process of examining "mug shots" to find a match to the description is tedious and often unfruitful. If a description could be stored with each photograph and used as a searchable index, this would provide a much more effective means of using "mug shots" for identification purposes. A set of descriptive measures have been defined by Shepherd [73] which seek to describe faces in a manner that may be used for just this purpose. This work investigates methods of automatically determining these descriptive measures from digitised images. Analysis is performed on the images to establish the potential for distinguishing between different categories in these descriptions. This reveals that while some of the classifications are relatively linear, others are very non-linear. Artificial neural networks (ANNs), being often used as non-linear classifiers, are considered as a means of automatically performing the classification of the images. As a comparison, simple linear classifiers are also applied to the same problems.
33
Muthuraman, Sethuraman. "The evolution of modular artificial neural networks." Thesis, Robert Gordon University, 2005. http://hdl.handle.net/10059/284.
Testo completoAbstract (sommario):
This thesis describes a novel approach to the evolution of Modular Artificial Neural Networks. Standard Evolutionary Algorithms, used in this application include: Genetic Algorithms, Evolutionary Strategies, Evolutionary Programming and Genetic Programming; however, these often fail in the evolution of complex systems, particularly when such systems involve multi-domain sensory information which interacts in complex ways with system outputs. The aim in this work is to produce an evolutionary method that allows the structure of the network to evolve from simple to complex as it interacts with a dynamic environment. This new algorithm is therefore based on Incremental Evolution. A simulated model of a legged robot was used as a test-bed for the approach. The algorithm starts with a simple robotic body plan. This then grows incrementally in complexity along with its controlling neural network and the environment it reacts with. The network grows by adding modules to its structure - so the technique may also be termed a Growth Algorithm. Experiments are presented showing the successful evolution of multi-legged gaits and a simple vision system. These are then integrated together to form a complete robotic system. The possibility of the evolution of complex systems is one advantage of the algorithm and it is argued that it represents a possible path towards more advanced artificial intelligence. Applications in Electronics, Computer Science, Mechanical Engineering and Aerospace are also discussed.
34
Chen, Jian-Rong. "Theory and applications of artificial neural networks." Thesis, Durham University, 1991. http://etheses.dur.ac.uk/6240/.
Testo completoAbstract (sommario):
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.
35
D'Souza, Winston Anthony. "Real-time applications of artificial neural networks." Thesis, University of Aberdeen, 2007. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.445136.
Testo completoAbstract (sommario):
This research takes an innovative look at two distinct applications of Artificial Neural Networks (ANNs) concerning the manipulation of data within real-time systems. The first contribution of this research involves the filtering of errors associated with data emergent from Inertial Navigation Systems (INS) by adopting an ANN filter. This novel approach when compared to present day optimal estimation filter techniques for random data such as the Kalman Filter (KF) and its variants, offers a better estimated response without the need to mathematically model error. In addition to this advantage, due to its inherent properties of effortlessly handling nonlinear data, the ANN filter eliminates the need to convert such data into their linear forms thereby maintaining the integrity of the original data. Furthermore, since the ANN filter is considerably more economical compared to a KF, it makes itself a likely candidate for low-cost applications. Results from this research have indicated that the performance of an ANN filter when used for real-time applications within INS, offers a similar degree of accuracy of estimation as well as shorter correction times for such signals compared to the former. ANN filters though, are not “plug-n-play” devices but require adequate training before they can function reliably and independently of any aiding or correction source (e.g. Kalman Filters). However, with the continual growth in their knowledge and increased training, they perfect their correction ability considerably. The second contribution of this research was in the area of on-line data compression. This innovative approach builds on the strengths of present day compression schemes. However, unlike current schemes that continually compresses data (such as web pages) transmitted through a network every time they are requested, the ANN scheme points to data they may already be pre-compressed and stored within the client’s memory at an earlier stage. If clients request such data that has already been pre-compressed using this scheme, these are decompressed locally from its resident memory. If clients do not hold a pre-compressed page due to it being unknown or is an updated version of the web page in its memory, it downloads the web page using the contemporary on-line real-time compression scheme (e.g. mod_gzip). With this approach therefore, a client’s browser does not have to download every web page requested from the Internet but just the previously unseen ones thereby reducing user perceived latency. Results from this research have indicated that the ANN scheme for on-line data compression is fairly reliable in correctly recognising web pages previously used for training though there have been some difficulties with regard to web pages not adopting the standard 128 character ASCII code such as Unicode. As this scheme presently operates entirely in software, it offers some difficulties with regard to the recognition time involved in identifying web pages previously browsed or even unseen by the user. It is hoped that this problem will be mitigated if this scheme is migrated into hardware using these parallel processors.
36
Zhu, Kangmin. "ECG feature recognition using artificial neural networks." Thesis, University of Essex, 1992. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.316072.
Testo completo
37
Kurd, Zeshan. "Artificial neural networks in safety-critical applications." Thesis, University of York, 2005. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.428472.
Testo completo
38
Rust, Alistair Gibson. "Developmental self-organisation in artificial neural networks." Thesis, University of Hertfordshire, 1998. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.268042.
Testo completo
39
Ferguson, Alistair. "Learning in RAM-based artificial neural networks." Thesis, University of Hertfordshire, 1995. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.283866.
Testo completo
40
Berry, Ian Michael. "Data classification using unsupervised artificial neural networks." Thesis, University of Sussex, 1997. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.390079.
Testo completo
41
Gavrilov, Alexander I. "Welding process engineering with artificial neural networks." Thesis, De Montfort University, 2005. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.420851.
Testo completo
42
ABELEM, ANTONIO JORGE GOMES. "ARTIFICIAL NEURAL NETWORKS IN TIME SERIES FORECASTING." PONTIFÍCIA UNIVERSIDADE CATÓLICA DO RIO DE JANEIRO, 1994. http://www.maxwell.vrac.puc-rio.br/Busca_etds.php?strSecao=resultado&nrSeq=8489@1.
Testo completoAbstract (sommario):
COORDENAÇÃO DE APERFEIÇOAMENTO DO PESSOAL DE ENSINO SUPERIOR<br>Esta dissertação investiga a utilização de Redes Neurais
Artificiais (RNAs) na previsão de séries temporais, em
particular de séries financeiras, consideradas uma classe
especial de séries temporais, caracteristicamente ruídos e
sem periodicidade aparente. O trabalho envolve quatro
partes principais: um estudo sobre redes neurais
artificiais e séries temporais; a modelagem das RNAs para
previsão de séries temporais; o desenvolvimento de um
ambiente de simulação; e o estudo de caso.
No estudo sobre Redes Neurais Artificiais e séries
temporais fez-se um levantamento preliminar das aplicações
de RNAs na previsão de séries. Constatou-se a
predominância do uso do algoritmos de retropropagação do
erro para o treinamento das redes, bem como dos modelos
estatísticos de regressão, de médias móveis e de
alisamento exponencial nas comparações com os resultados
da rede.
Na modelagem das RNAs de retropropagação do erro
considerou-se três fatores determinantes no desempenho da
rede: convergência, generalização e escalabilidade. Para o
controle destes fatores usou-se mecanismos como; escolha
da função de ativação dos neurônios - sigmóide ou tangente
hiperbólica; escolha da função erro - MSE (Mean Square
Error) ou MAD (Mean Absolutd Deviation); e escolha dos
parâmetros de controle do gradiente descendente e do
temapo de treinamento - taxa de aprendizado e termo de
momento. Por fim, definiu-se a arquitetura da rede em
função da técnica utilizada para a identificação de
regularidades na série (windowing) e da otimização dos
fatores indicadores de desempenho da rede.
O ambiente de simulação foi desenvolvido em linguagem C e
contém 3.600 linhas de códigos divididas em três módulos
principais: interface com o usuário, simulação e funções
secundárias. O módulo de interface com o usuário é
responsável pela configuração e parametrização da rede,
como também pela visualização gráfica dos resultados;
módulo de simulação executa as fases de treinamento e
testes das RNAs; o módulo de funções secundárias cuida do
pré/pós-processamento dos dados, da manipulação de
arquivos e dos cálculos dos métodos de avaliação
empregados.
No estudo de caso, as RNAs foram modeladas para fazer
previsões da série do preço do ouro no mercado
internacional. Foram feitas previsões univariadas single e
multi-step e previsões multivariadas utilizando taxas de
câmbio de moedas estrangeiras. Os métodos utilizandos para
a avaliação do desempenho da rede foram: coeficiente U de
Theil, MSE (Mean Square Error), NRMSE (Normalized Root
Mean Square Error), POCID (Percentage Of Change In
Direction), scattergram e comparação gráfica. Os
resultados obtidos, além de avaliados com os métodos
acima, foram comparados com o modelo de Box-Jenkins e
comprovaram a superioridade das RNAs no tratamento de
dados não-lineares e altamente ruidosos.<br>This dissertation investigates the use of Artificial
Neural Nerworks (ANNs) in time series forecastig,
especially financial time series, which are typically
noisy and with no apparent periodicity. The dissertation
covers four major parts: the study of Artificial Neural
Networks and time series; the desing of ANNs applied to
time series forecasting; the development of a simulation
enironment; and a case study.
The first part of this dissertation involved the study of
Artficial Neural Netwrks and time series theory, resulting
in an overview of ANNs utilization in time series
forecasting. This overview confirmed the predominance of
Backpropagations as the training algorithm, as well as the
employment of statistical models, such as regression and
moving average, for the Neural Network evaluation.
In the design of ANNS, three performance measures were
considered: covergence, generalization and scalability. To
control these parameters, the following methods were
applied: choice of activation function - sigmoid or
hiperbolic tangent; choice of cost function - MSE (Mean
Square Error) or MAD (Mean Absolute Deviation); choise of
parameteres for controlling the gradiente descendent and
learning times - the learning rate and momentum term; and
network architecture.
The simulation environment was developed in C language,
with 3,600 lines of code distributed in three main
modules: the user interface, the simulaton and the support
functions modules. The user interface module is
responsaible for the network configuration and for the
graphical visualization. The simulation module performs
the training and testing of ANNs. The support functions
module takes care of the pre and pos processin, the files
management and the metrics calculation.
The case study concerned with the designing of an ANN to
forescast the gold price in the international market. Two
kinds of prediction were used: univariate - single and
multi-step, and multivariate. The metrics used to evaluate
the ANN performance were: U of Theil`s coeficient, MSE
(Mean Square Error), NRMSE (Normalized Mean Saquare
Error), POCID (Percentage Of Cnage In Direction),
scattergram and graphical comparison. The results were
also comapred with the Box-Jenkins model, confirming the
superiority of ANN in handling non-linear and noisy data.
43
Han, Ying. "Analysing time series using artificial neural networks." Thesis, University of the West of Scotland, 2003. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.398318.
Testo completo
44
Kendall, Gary David. "Non-linear modelling through artificial neural networks." Thesis, King's College London (University of London), 1998. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.300608.
Testo completo
45
Nordström, Tomas. "Highly parallel computers for artificial neural networks." Doctoral thesis, Luleå tekniska universitet, 1995. http://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-25655.
Testo completoAbstract (sommario):
During a number of years the two fields of artificial neural networks (ANNs) and highly parallel computing have both evolved rapidly. In this thesis the possibility of combining these fields is explored, investigating the design and usage of highly parallel computers for ANN calculations. A new system-architecture REMAP (Real-time, Embedded, Modular, Adaptive, Parallel processor) is presented as a candidate platform for future action-oriented systems. With this new system-architecture, multi-modular networks of cooperating and competing ANNs can be realized. For action-oriented systems, concepts like real-time interaction with the environment, embeddedness, and learning with selforganization are important. In this thesis the requirements for efficient mapping of ANN algorithms onto the suggested architecture are identified. This has been accomplished by studies of ANN implementations on general purpose parallel computers as well as designs of new parallel systems particularly suited to ANN computing. The suggested architecture incorporates highly parallel, communicating processing modules, each constructed as a linear SIMD (Single Instruction stream, Multiple Data stream) array, internally connected using a ring topology, but also supporting broadcast and reduction operations. Many of the analyzed ANN models are similar in structure and can be studied in a unified context. A new superclass of ANN models called localized learning systems (LLSs) is therefore suggested and defined. A parallel computer implementation of LLSs is analyzed and the importance of the reduction operations is recognized. The study of various LLS models and other commonly used ANN models not contained in the LLS class, like the multilayer perceptron with error back-propagation, establishes REMAP modules as an excellent architecture for many different ANN models, useful in the design of action-oriented systems.<br>Godkänd; 1995; 20070426 (ysko)
46
Vieira, Cristiano Ribeiro. "Forecasting financial markets with artificial neural networks." Master's thesis, Instituto Superior de Economia e Gestão, 2013. http://hdl.handle.net/10400.5/6340.
Testo completoAbstract (sommario):
Mestrado em Matemática Financeira<br>Artificial Neural Networks are exible nonlinear mathematical models widely used in forecasting. This work is intended to investigate the support these models can give to nancial economists predicting prices movements of oil and gas companies listed in stock exchanges. Multilayer Perceptron models with logistic activation functions achieved better results predicting the direction of stocks returns than traditional linear regressions and better performances in companies with lower market capitalization. Furthermore, multilayer perceptron with eight hidden units in the hidden layer had better predictive ability
than a neural network with four hidden neurons.
47
Dermelov, D. O. "Artificial neural networks in self-driving cars." Thesis, Київський національний університет технологій та дизайну, 2019. https://er.knutd.edu.ua/handle/123456789/14355.
Testo completo
48
Haskett, Kevin Joseph. "Iris Biometric Identification Using Artificial Neural Networks." DigitalCommons@CalPoly, 2018. https://digitalcommons.calpoly.edu/theses/1947.
Testo completoAbstract (sommario):
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.
49
Edara, Praveen Kumar. "Mode Choice Modeling Using Artificial Neural Networks." Thesis, Virginia Tech, 2003. http://hdl.handle.net/10919/9845.
Testo completoAbstract (sommario):
Artificial intelligence techniques have produced excellent results in many diverse fields of engineering. Techniques such as neural networks and fuzzy systems have found their way into transportation engineering. In recent years, neural networks are being used instead of regression techniques for travel demand forecasting purposes. The basic reason lies in the fact that neural networks are able to capture complex relationships and learn from examples and also able to adapt when new data become available. The primary goal of this thesis is to develop mode choice models using artificial neural networks and compare the results with traditional mode choice models like the multinomial logit model and linear regression method. The data used for this modeling is extracted from the American Travel Survey data. Data mining procedures like clustering are used to process the extracted data. The results of three models are compared based on residuals and error criteria. It is found that neural network approach produces the best results for the chosen set of explanatory variables. The possible reasons for such results are identified and explained to the extent possible. The three major objectives of this thesis are to: present an approach to handle the data from a survey database, address the mode choice problem using artificial neural networks, and compare the results of this approach with the results of traditional models vis-à-vis logit model and linear regression approach. The results of this research work should encourage more transportation researchers and professionals to consider artificial intelligence tools for solving transportation planning problems.<br>Master of Science
50
Muralidharan, Nair Mithun. "Statistical Leakage Estimation Using Artificial Neural Networks." University of Cincinnati / OhioLINK, 2014. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1413471610.
Testo completo