In this thesis the verification of a neural network’s proficiency at labeling ionizing radiation particles from the unsorted output of a timepix3 camera is attempted. Focus is put on labeling single particles in separate data sequences with slightly preprocessed input data. Preprocessing of input data is done to simplify the patterns that should be recognized. Two major choices were available for this project, Elman-network and Jordan-network. A more complicated type was not an option because of the longer time needed to implement them. The network type chosen was Elman because of freedom in context size. The neural network is created and trained with the TensorFlow API in python with labeled data that was not created by hand. The network recognized the length difference between gamma particles and alpha particles. Beta particles were not considered by the network. It is concluded that the Elman-style network is not proficient in labeling the sequences, which were considered short enough and to have simple enough input data. A more modern network type is therefore likely required to solve this problem.

Made available in DSpace on 2014-06-12T15:58:28Z (GMT). No. of bitstreams: 2 arquivo4572_1.pdf: 1149011 bytes, checksum: 92aae8f6f9b5145bfcecb94d96dbbc0b (MD5) license.txt: 1748 bytes, checksum: 8a4605be74aa9ea9d79846c1fba20a33 (MD5) Previous issue date: 2004 / Instituto Federal de Educação, Ciência e Tecnologia de Pernambuco / Um nariz artificial é um sistema modular composto de duas partes principais: um sistema sensor, formado de elementos que detectam odores e um sistema de reconhecimento de padrões que classifica os odores detectados. Redes neurais artificiais têm sido utilizadas como sistema de reconhecimento de padrões para narizes artificiais e vêm apresentando resultados promissores. Desde os anos 80, pesquisas para criação de narizes artificiais, que permitam detectar e classificar odores, vapores e gases automaticamente, têm tido avanços significativos. Esses equipamentos podem ser utilizados no monitoramento ambiental para controlar a qualidade do ar, na área de saúde para realizar diagnóstico de doenças e nas indústrias de alimentos para o controle de qualidade e o monitoramento de processos de produção. Esta dissertação investiga a utilização de quatro técnicas diferentes de redes neurais para criação de sistemas de reconhecimento de padrões em narizes artificiais. O trabalho está dividido em quatro partes principais: (1) introdução aos narizes artificiais, (2) redes neurais artificiais para sistema de reconhecimento de padrões, (3) métodos para medir o desempenho de sistemas de reconhecimento de padrões e comparar os resultados e (4) estudo de caso. Os dados utilizados para o estudo de caso, foram obtidos por um protótipo de nariz artificial composto por um arranjo de oito sensores de polímeros condutores, expostos a nove tipos diferentes de aguarrás. Foram adotadas as técnicas Multi-Layer Perceptron (MLP), Radial Base Function (RBF), Probabilistic Neural Network (PNN) e Time Delay Neural Network (TDNN) para criar os sistemas de reconhecimento de padrões. A técnica PNN foi investigada em detalhes, por dois motivos principais: esta técnica é indicada para realização de tarefas de classificação e seu treinamento é feito em apenas um passo, o que torna a etapa de criação dessas redes muito rápida. Os resultados foram comparados através dos valores dos erros médios de classificação utilizando o método estatístico de Teste de Hipóteses. As redes PNN correspondem a uma nova abordagem para criação de sistemas de reconhecimento de padrões de odor. Estas redes tiveram um erro médio de classificação de 1.1574% no conjunto de teste. Este foi o menor erro obtido entre todos os sistemas criados, entretanto mesmo com o menor erro médio de classificação, os testes de hipóteses mostraram que os classificadores criados com PNN não eram melhores do que os classificadores criados com a arquitetura RBF, que obtiveram um erro médio de classificação de 1.3889%. A grande vantagem de criar classificadores com a arquitetura PNN foi o pequeno tempo de treinamento dos mesmos, chegando a ser quase imediato. Porém a quantidade de nodos na camada escondida foi muito grande, o que pode ser um problema, caso o sistema criado deva ser utilizado em equipamentos com poucos recursos computacionais. Outra vantagem de criar classificadores com redes PNN é relativa à quantidade reduzida de parâmetros que devem ser analisados, neste caso apenas o parâmetro relativo à largura da função Gaussiana precisou ser investigado

Detection of a human emotion from human speech is always a challenging task. Factors like intonation, pitch, and loudness of signal vary from different human voice. So, it's important to know the exact pitch, intonation and loudness of a speech for making it a challenging task for detection. Some voices exhibit high background noise which will affect the amplitude or pitch of the signal. So, knowing the detailed properties of a speech to detect emotion is mandatory. Detection of emotion in humans from speech signals is a recent research field. One of the scenarios where this field has been applied is in situations where the human integrity and security are at risk In this project we are proposing a set of features based on the decomposition signals from discrete wavelet transform to characterize different types of negative emotions such as anger, happy, sad, and desperation. The features are measured in three different conditions: (1) the original speech signals, (2) the signals that are contaminated with noise or are affected by the presence of a phone channel, and (3) the signals that are obtained after processing using an algorithm for Speech Enhancement Transform. According to the results, when the speech enhancement is applied, the detection of emotion in speech is increased and compared to results obtained when the speech signal is highly contaminated with noise. Our objective is to use Artificial neural network because the brain is the most efficient and best machine to recognize speech. The brain is built with some neural network. At the same time, Artificial neural networks are clearly advanced with respect to several features, such as their nonlinearity and high classification capability. If we use Artificial neural networks to evolve the machine or computer that it can detect the emotion. Here we are using feedforward neural network which is suitable for classification process and using sigmoid function as activation function. The detection of human emotion from speech is achieved by training the neural network with features extracted from the speech. To achieve this, we need proper features from the speech. So, we must remove background noise in the speech. We can remove background noise by using filters. wavelet transform is the filtering technique used to remove the background noise and enhance the required features in the speech.

In the scheme of Non Destructive Testing (NDT), defect detection is an important process. Traditional image processing techniques have successfully been used for defect recognition. Usage of machine learning techniques is still in the initial stages of development. Convolution Neural Networks (CNN) is widely used for object classification one such scenario is defect classification in weld tubes. With the advent of deep learning techniques such as transfer learning, we can transfer knowledge gained in one domain successfully into other. Pre-trained models successfully learn features from large scale datasets that can be used for in domains having sparse data and smaller datasets. The aim of this work is to help a manual inspector in recognition of defects on the weld tubes. With a given set of images, we proceed by forming unique pipeline architecture for automatic defect recognition. The research in this thesis focuses on extraction of welds using image segmentation techniques, creating a dataset of defects and using it to on pre-trained Convolution Neural Networks of VGG16, VGG19, Inception V3 and ResNet101. We evaluate the models on different metrics finding the best suited model for the created dataset. Further a prototype sliding window solution is used to find defects over the extracted weld region. We also present the limitations of this approach and suggest modifications that can be implemented in the future.

This master's thesis is focused on segmentation of the scene from traffic environment. The solution to this problem is segmentation neural networks, which enables classification of every pixel in the image. In this thesis is created segmentation neural network, that has reached better results than present state-of-the-art architectures. This work is also focused on the segmentation of the top view of the road, as there are no freely available annotated datasets. For this purpose, there was created automatic tool for generation of synthetic datasets by using PC game Grand Theft Auto V. The work compares the networks, that have been trained solely on synthetic data and the networks that have been trained on both real and synthetic data. Experiments prove, that the synthetic data can be used for segmentation of the data from the real environment. There has been implemented a system, that enables work with segmentation neural networks.

This work focuses on a theoretical explanation of heart rhythm disorders and the possibility of their automatic detection using deep learning networks. For the purposes of this work, a total of 6884 10-second ECG recordings with measured eight leads were used. Those recordings were divided into 5 groups according to heart rhythm into a group of records with atrial fibrillation, sinus rhythms, supraventricular rhythms, ventricular rhythms, and the last group consisted of the others records. Individual groups were unbalanced represented and more than 85 % of the total number of data are sinus rhythm group records. The used classification methods served effectively as a record detector of the largest group and the most effective of all was a procedure consisting of a 2D convolutional neural network into which data entered in the form of scalalograms (classification procedure number 3). It achieved results of precision of 91%, recall of 96% and F1-score values of 0.93. On the contrary, when classifying all groups at the same time, there were no such quality results for all groups. The most efficient procedure seems to be a variant composed of PCA on eight input signals with the gain of one output signal, which becomes the input of a 1D convolutional neural network (classification procedure number 5). This procedure achieved the following F1-score values: 1) group of records with atrial fibrillation 0.54, 2) group of sinus rhythms 0.91, 3) group of supraventricular rhythms 0.65, 4) group of ventricular rhythms 0.68, 5) others records 0.65.

This work focuses on creating mobile application, that helps visitors of galleries and museums to find, in a more easier way, interesting information about visual art objects.

This master’s thesis deals with designs and implementation of systems for music cover recognition. The introduction part is devoted to the calculation parameters from audio signal using Music Information Retrieval techniques. Subsequently, various forms of cover versions and musical aspects that cover versions share are defined. The thesis also deals in detail with the creation and distribution of a database of cover versions. Furthermore, the work presents methods and techniques for comparing and processing the calculated parameters. Attention is then paid to the OTI method, CSM calculation and methods dealing with parameter selection. The next part of the thesis is devoted to the design of systems for recognizing cover versions. Then there are compared systems already designed for recognizing cover versions. Furthermore, the thesis describes machine learning techniques and evaluation methods for evaluating the classification with a special emphasis on artificial neural networks. The last part of the thesis deals with the implementation of two systems in MATLAB and Python. These systems are then tested on the created database of cover versions.

The aim of this work is to design and implement a method for the evolutionary design of neural networks with generative encoding. The proposed method is based on J. F. Miller's approach and uses a brain model that is gradually developed and which allows extraction of traditional neural networks. The development of the brain is controlled by programs created using cartesian genetic programming. The project was implemented in Python with the use of Numpy library. Experiments have shown that the proposed method is able to construct neural networks that achieve over 90 % accuracy on smaller datasets. The method is also able to develop neural networks capable of solving multiple problems at once while slightly reducing accuracy.

Sectors of security, safety, and defence require methods for identifying people on the individual level. Automation of these tasks has the potential of outperforming manual labor, as well as relieving workloads. The ever-extending surveillance camera networks, advances in human pose estimation from monocular cameras, together with the progress of deep learning techniques, pave the way for automated walking gait analysis as an identification method. This thesis investigates the use of 2D kinematic pose sequences to represent gait, monocularly extracted from a limited dataset containing walking individuals captured from five camera views. The sequential information of the gait is captured using recurrent neural networks. Techniques in deep metric learning are applied to evaluate two network models, with contrasting output dimensionalities, against deep-metric-, and non-deep-metric-based embedding spaces. The results indicate that the gait representation, network designs, and network learning structure show promise when identifying individuals, scaling particularly well to unseen individuals. However, with the limited dataset, the network models performed best when the dataset included the labels from both the individuals and the camera views simultaneously, contrary to when the data only contained the labels from the individuals without the information of the camera views. For further investigations, an extension of the data would be required to evaluate the accuracy and effectiveness of these methods, for the re-identification task of each individual. / <p>Examensarbetet är utfört vid Institutionen för teknik och naturvetenskap (ITN) vid Tekniska fakulteten, Linköpings universitet</p>