• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 19
  • 3
  • 2
  • 1
  • Tagged with
  • 30
  • 30
  • 17
  • 15
  • 9
  • 8
  • 7
  • 7
  • 7
  • 6
  • 5
  • 5
  • 5
  • 4
  • 4
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
1

Network Representation Learning in Social Media

January 2018 (has links)
abstract: The popularity of social media has generated abundant large-scale social networks, which advances research on network analytics. Good representations of nodes in a network can facilitate many network mining tasks. The goal of network representation learning (network embedding) is to learn low-dimensional vector representations of social network nodes that capture certain properties of the networks. With the learned node representations, machine learning and data mining algorithms can be applied for network mining tasks such as link prediction and node classification. Because of its ability to learn good node representations, network representation learning is attracting increasing attention and various network embedding algorithms are proposed. Despite the success of these network embedding methods, the majority of them are dedicated to static plain networks, i.e., networks with fixed nodes and links only; while in social media, networks can present in various formats, such as attributed networks, signed networks, dynamic networks and heterogeneous networks. These social networks contain abundant rich information to alleviate the network sparsity problem and can help learn a better network representation; while plain network embedding approaches cannot tackle such networks. For example, signed social networks can have both positive and negative links. Recent study on signed networks shows that negative links have added value in addition to positive links for many tasks such as link prediction and node classification. However, the existence of negative links challenges the principles used for plain network embedding. Thus, it is important to study signed network embedding. Furthermore, social networks can be dynamic, where new nodes and links can be introduced anytime. Dynamic networks can reveal the concept drift of a user and require efficiently updating the representation when new links or users are introduced. However, static network embedding algorithms cannot deal with dynamic networks. Therefore, it is important and challenging to propose novel algorithms for tackling different types of social networks. In this dissertation, we investigate network representation learning in social media. In particular, we study representative social networks, which includes attributed network, signed networks, dynamic networks and document networks. We propose novel frameworks to tackle the challenges of these networks and learn representations that not only capture the network structure but also the unique properties of these social networks. / Dissertation/Thesis / Doctoral Dissertation Computer Science 2018
2

Rozpoznání zvukových událostí pomocí hlubokého učení / Deep learning based sound event recognition

Bajzík, Jakub January 2019 (has links)
This paper deals with processing and recognition of events in audio signal. The work explores the possibility of using audio signal visualization and subsequent use of convolutional neural networks as a classifier for recognition in real use. Recognized audio events are gunshots placed in a sound background such as street noise, human voice, animal sounds, and other forms of random noise. Before the implementation, a large database with various parameters, especially reverberation and time positioning within the processed section, is created. In this work are used freely available platforms Keras and TensorFlow for work with neural networks.
3

Strojové učení pro odpovídání na otázky v češtině / Machine Learning for Question Answering in Czech

Pastorek, Peter January 2020 (has links)
This Master's thesis deals with teaching neural network question answering in Czech. Neural networks are created in Python programming language using the PyTorch library. They are created based on the LSTM structure. They are trained on the Czech SQAD dataset. Because Czech data set is smaller than the English data sets, I opted to extend neural networks with algorithmic procedures. For easier application of algorithmic procedures and better accuracy, I divide question answering into smaller parts.
4

A Real Time Fault Detection and Diagnosis System for Automotive Applications

doghri, ahmed January 2019 (has links)
Since its inception in the nineteenth century, the Internal Combustion Engine (ICE) remains the most prevalent technology in transportation systems to date. In order to minimize emissions, it is important that ICE is operated according to its optimized design conditions. As such, condition monitoring and Fault Detection and Diagnosis (FDD) tools can play an important role in detecting conditions that would affect the operability of the engine. In this research, different signal-based Fault Detection and Diagnosis (FDD) techniques are researched and implemented for fault condition monitoring of ICE. The implementation of prognostics for the engine in an automated form has important consequences that include cost savings, increased reliability, reduction of GHG emissions, better safety, and extended life for the vehicle. In this research, in order to carry out FDD onboard, a low-cost and flexible internet-based data-acquisition system (DAQ) was designed and implemented. The main part of the system is an embedded hardware running a full desktop version of Linux. This sensory system leverages the positive aspects of both real-time and general-purpose architectures to ensure engine monitoring at high sampling rates. Unlike other commercial DAQ systems, the software of this device is open-source, free of charge, and highly expandable to suit other FDD applications. In addition to data collection at high sampling rates, the FDD system includes advanced FDD strategies. The Fault Detection and Diagnosis strategies considered use a combination of Fourier Transforms (FT), Wavelet Transforms (WT), and Principal Component Analysis (PCA). Meanwhile, Fault Classification was carried using Neural Networks consisting of the Multi-Layer Perceptron (MLP). Three strategies were comparatively considered for the training of the Neural Network (NN), namely the Levenberg-Marquardt (LM), the Extended Kalman Filter (EKF), and the Smooth Variable Structure Filter (SVSF) techniques. The proposed FDD system was able to achieve 100% accuracy in classifying a set of engine faults. / Thesis / Master of Applied Science (MASc)
5

Dicotomia entre o discurso e a prática pedagógica na educação a distância

Braga, Clarissa Bittencourt de Pinho e January 2006 (has links)
220 f. / Submitted by Suelen Reis (suziy.ellen@gmail.com) on 2013-04-29T14:08:17Z No. of bitstreams: 1 Clarissa Braga.pdf: 830557 bytes, checksum: 3d0ca4aced5d0c4298844a1738cbdd2a (MD5) / Approved for entry into archive by Maria Auxiliadora Lopes(silopes@ufba.br) on 2013-06-11T13:41:26Z (GMT) No. of bitstreams: 1 Clarissa Braga.pdf: 830557 bytes, checksum: 3d0ca4aced5d0c4298844a1738cbdd2a (MD5) / Made available in DSpace on 2013-06-11T13:41:26Z (GMT). No. of bitstreams: 1 Clarissa Braga.pdf: 830557 bytes, checksum: 3d0ca4aced5d0c4298844a1738cbdd2a (MD5) Previous issue date: 2006 / As possibilidades educativas dos ambientes informais de aprendizagem da rede, quando aplicadas aos ambientes formais de aprendizagem, geram uma dicotomia entre o discurso e a prática pedagógica. Esta é a tese desenvolvida nos capítulos a seguir. As formas de interação em rede, de acesso ao conhecimento e as possibilidades de trocas de informação entre os internautas em um ambiente virtual informal sofrem alterações quando há a formalização dos cursos. Isto porque, o currículo traz condicionantes de tempo (carga horária, necessidade de avaliação em determinados períodos) e espaço (ambiente virtual do curso restrito aos inscritos, ferramentas de interação com moderadores) que irão impactar na sociabilidade do ambiente virtual formal. Para o desenvolvimento desta tese, foram analisadas três experiências pioneiras de utilização da rede nem um contexto educativo. A estratégia de análise foi a comparação entre o discurso e a prática pedagógica destas três experiências. A metodologia utilizada foi a abordagem dialética e a pesquisa de campo foi feita através de entrevistas com autores e executores dos cursos analisados. / Salvador
6

Deep Learning on Graph-structured Data

Lee, John Boaz T. 11 November 2019 (has links)
In recent years, deep learning has made a significant impact in various fields – helping to push the state-of-the-art forward in many application domains. Convolutional Neural Networks (CNN) have been applied successfully to tasks such as visual object detection, image super-resolution, and video action recognition while Long Short-term Memory (LSTM) and Transformer networks have been used to solve a variety of challenging tasks in natural language processing. However, these popular deep learning architectures (i.e., CNNs, LSTMs, and Transformers) can only handle data that can be represented as grids or sequences. Due to this limitation, many existing deep learning approaches do not generalize to problem domains where the data is represented as graphs – social networks in social network analysis or molecular graphs in chemoinformatics, for instance. The goal of this thesis is to help bridge the gap by studying deep learning solutions that can handle graph data naturally. In particular, we explore deep learning-based approaches in the following areas. 1. Graph Attention. In the real-world, graphs can be both large – with many complex patterns – and noisy which can pose a problem for effective graph mining. An effective way to deal with this issue is to use an attention-based deep learning model. An attention mechanism allows the model to focus on task-relevant parts of the graph which helps the model make better decisions. We introduce a model for graph classification which uses an attention-guided walk to bias exploration towards more task-relevant parts of the graph. For the task of node classification, we study a different model – one with an attention mechanism which allows each node to select the most task-relevant neighborhood to integrate information from. 2. Graph Representation Learning. Graph representation learning seeks to learn a mapping that embeds nodes, and even entire graphs, as points in a low-dimensional continuous space. The function is optimized such that the geometric distance between objects in the embedding space reflect some sort of similarity based on the structure of the original graph(s). We study the problem of learning time-respecting embeddings for nodes in a dynamic network. 3. Brain Network Discovery. One of the fundamental tasks in functional brain analysis is the task of brain network discovery. The brain is a complex structure which is made up of various brain regions, many of which interact with each other. The objective of brain network discovery is two-fold. First, we wish to partition voxels – from a functional Magnetic Resonance Imaging scan – into functionally and spatially cohesive regions (i.e., nodes). Second, we want to identify the relationships (i.e., edges) between the discovered regions. We introduce a deep learning model which learns to construct a group-cohesive partition of voxels from the scans of multiple individuals in the same group. We then introduce a second model which can recover a hierarchical set of brain regions, allowing us to examine the functional organization of the brain at different levels of granularity. Finally, we propose a model for the problem of unified and group-contrasting edge discovery which aims to discover discriminative brain networks that can help us to better distinguish between samples from different classes.
7

Detekce cesty ve venkovním prostředí zpracováním obrazu / Road detection in outdoor environment using image processing

Vrbičanová, Antónia January 2020 (has links)
The Master’s thesis deals with the issue of the road detection in the outdoor environment using image processing. It is highly required that the methods selected are robust to sudden light changes within the image and effective in detection of wide variety of road surfaces possibly comprising certain kinds of pollution. Two methods have been used in order to reach the desired goal. The initial method uses standard algorithms of the image processing. Main outcome of this method are highlighted road boundaries. The following methodisbasedonconvolutionalneuralnetworks.Inthiscasewehaveclassificationtask. The result of this method is the estimation of the road direction. In the whole process, severalneuralnetworkstructureshavebeendesigned.Afterthenetworktrainingthemost suitable one was selected. Eventually, the results have been retested using newly created test set. Both of these methods are implemented in programming language Python.
8

Alice in a township : accessible learning through an interactive communal educational environment

Maritz, Colette January 2012 (has links)
The Alice Project investigates the problem behind the lack of provision for children in developing areas. The project recognises the potential in formal educational facilities as being the most important designed children’s space in townships [as developed transit camps]. The study will aim to address school environments in an extroverted or interactive manner. This will be done in order to transform the school grounds into a community children’s ‘city of learning’ [H.Hertzberger.2008:127]. The study questions the one dimensional identity of current educational environments, while focusing on Olievenhoutbosch as the main research area [Olievenhoutbocsh Ministerial Housing Estate: July 2005] The study identifies the problem behind the dystopian institutional character of current educational facilities as; introverted layouts, isolation, mono function and functionally dominant and intimidating spaces [H.Zeither.1996:16; H.Hertzberger.2008:71]. In order to address dissertation elements of spatial alienation, the dissertation will investigate counter theories of contextual inclusion and humane places of interaction, using contextual informants of community use of spaces to assist in program allocation and determinants of spatial hierarchy, supported with theories by Jane Jacobs [1961] and Jan Gehl [2010 and 2011] on qualities of a humane compact city space. These theories will then be combined with educational design theories of learning spaces implemented as a city in miniature, ultimately allowing the educational environment to socially extrovert to include community life and achieve a social academic atmosphere through an interactive educational environment . / Dissertation MArch(Prof)--University of Pretoria, 2012. / Architecture / MArch(Prof) / Unrestricted
9

Deep Learning on Graph-structured Data

Lee, John Boaz T 11 November 2019 (has links)
In recent years, deep learning has made a significant impact in various fields – helping to push the state-of-the-art forward in many application domains. Convolutional Neural Networks (CNN) have been applied successfully to tasks such as visual object detection, image super-resolution, and video action recognition while Long Short-term Memory (LSTM) and Transformer networks have been used to solve a variety of challenging tasks in natural language processing. However, these popular deep learning architectures (i.e., CNNs, LSTMs, and Transformers) can only handle data that can be represented as grids or sequences. Due to this limitation, many existing deep learning approaches do not generalize to problem domains where the data is represented as graphs – social networks in social network analysis or molecular graphs in chemoinformatics, for instance. The goal of this thesis is to help bridge the gap by studying deep learning solutions that can handle graph data naturally. In particular, we explore deep learning-based approaches in the following areas. 1. Graph Attention. In the real-world, graphs can be both large – with many complex patterns – and noisy which can pose a problem for effective graph mining. An effective way to deal with this issue is to use an attention-based deep learning model. An attention mechanism allows the model to focus on task-relevant parts of the graph which helps the model make better decisions. We introduce a model for graph classification which uses an attention-guided walk to bias exploration towards more task-relevant parts of the graph. For the task of node classification, we study a different model – one with an attention mechanism which allows each node to select the most task-relevant neighborhood to integrate information from. 2. Graph Representation Learning. Graph representation learning seeks to learn a mapping that embeds nodes, and even entire graphs, as points in a low-dimensional continuous space. The function is optimized such that the geometric distance between objects in the embedding space reflect some sort of similarity based on the structure of the original graph(s). We study the problem of learning time-respecting embeddings for nodes in a dynamic network. 3. Brain Network Discovery. One of the fundamental tasks in functional brain analysis is the task of brain network discovery. The brain is a complex structure which is made up of various brain regions, many of which interact with each other. The objective of brain network discovery is two-fold. First, we wish to partition voxels – from a functional Magnetic Resonance Imaging scan – into functionally and spatially cohesive regions (i.e., nodes). Second, we want to identify the relationships (i.e., edges) between the discovered regions. We introduce a deep learning model which learns to construct a group-cohesive partition of voxels from the scans of multiple individuals in the same group. We then introduce a second model which can recover a hierarchical set of brain regions, allowing us to examine the functional organization of the brain at different levels of granularity. Finally, we propose a model for the problem of unified and group-contrasting edge discovery which aims to discover discriminative brain networks that can help us to better distinguish between samples from different classes.
10

Mapping Building Damage Caused by Earthquakes Using Satellite Imagery and Deep Learning

Ji, Min 23 July 2020 (has links)
Buildings are essential parts to human life, which provide the place to dwell, educate, entertain, etc. However, they are usually vulnerable to earthquakes, and collapsed buildings are the main factor of fatalities and directly impact livelihoods. It is particularly important to quickly and accurately obtain damaged building conditions for further planning rescue. Remote sensing has the ability to quickly capture the information of damaged buildings in a large area, and remote sensing imagery has been used by government organizations, international agencies, and insurance industries for assessing post-event damage. The application of deep learning is encouraged by recent technological developments, enabling the processing of increasing amounts of data in a reasonable time as well as the use of more complex models. In this thesis, deep learning is explored for identifying collapsed buildings using very high-resolution remote sensing imagery after the 2010 Haiti earthquake. In the present study, a simple architecture of convolutional neural network (CNN) model was proposed to evaluate the potential of CNN for extracting features and detecting collapsed buildings using only post-event very high-resolution remote sensing imagery. Three balancing methods were considered to reduce the effect of the imbalance problem for the performance of the CNN, and the results showed that a suitable balancing method should be considered when facing imbalance dataset to retrieve the distribution of collapsed buildings. To improve the classification accuracy, pre- and post-event very high-resolution remote sensing imagery were considered, and a conventional classification method was combined with the CNN. Compared to conventional texture features, deep features learnt from CNNs had better performance for identifying collapsed buildings, and the accuracy was further improved by combing CNN features with random forest classifier. For the limited dataset, a pretrained CNN model was applied to detect collapsed buildings, and the effect of data augmentation was also investigated. The experimental results demonstrated that the pretrained CNN model outperformed the model trained from scratch for identifying collapsed buildings.

Page generated in 0.0616 seconds