The work described in this thesis contributes to the development of a system to evaluate sailing performance. This work was motivated by the lack of tools available to evaluate sailing performance. The goal of the work presented is to detect and classify the turns of a sailing yacht. Data was collected using a BlackBerry PlayBook affixed to a J/24 sailing yacht. This data was manually annotated with three types of turn: tack, gybe, and mark rounding. This manually annotated data was used to train classification methods. Classification methods tested were multi-layer perceptrons (MLPs) of two sizes in various committees and nearest- neighbour search. Pre-processing algorithms tested were Kalman filtering, categorization using quantiles, and residual normalization. The best solution was found to be an averaged answer committee of small MLPs, with Kalman filtering and residual normalization performed on the input as pre-processing.

The work environment of a mobile crane is hazardous where accidents can cause serious injuries or death for workers and non-workers. Therefore, the risk for these accidents should be avoided when possible. One way to avoid the potential accidents is to use mobile crane simulations instead, which removes the risk. Because of this, simulations have been developed to train operators and plan future operations. Mobile crane simulations can also be used to perform research related to mobile cranes, but for the result to be applicable to real-world settings the simulation has to be realistic enough. Therefore, this thesis evaluated an aspect of realism which is the lifting capacity of a mobile crane. This was done by having an artificial neural network train on values from load charts of a real crane, that was then used to predict the lifting capacities based on the boom length and the load radius of the virtual crane. An experiment was conducted in the simulation that collected the predicted lifting capacities which was then compared to the lifting capacities in the load charts of a real crane. The results showed that the lifting capacities could be predicted with little to no deviation except for in a few cases. When conducting the experiment, it was found that the virtual mobile crane could not reach all load radiuses documented in the real load charts. The predicted lifting capacities are concluded to be realistic enough for crane-related research, but should be refined if the lifting capacity plays a key role in the research. Future works such as improving and generalizing the artificial network, and performing the evaluation with user tests are prompted.

The vast majority of products and processes in industry and academia require human interaction. Thus, digital human models (DHMs) are becoming critical for improved designs, injury prevention, and a better understanding of human behavior. Although many capabilities in the DHM field continue to mature, there are still many opportunities for improvement, especially with respect to posture- and motion-prediction. Thus, this thesis investigates the use of artificial neural network (ANN) for improving predictive capabilities and for better understanding how and why human behave the way they do. With respect to motion prediction, one of the most challenging opportunities for improvement concerns computation speed. Especially, when considering dynamic motion prediction, the underlying optimization problems can be large and computationally complex. Even though the current optimization-based tools for predicting human posture are relatively fast and accurate and thus do not require as much improvement, posture prediction in general is a more tractable problem than motion prediction and can provide a test bead that can shed light on potential issues with motion prediction. Thus, we investigate the use of ANN with posture prediction in order to discover potential issues. In addition, directly using ANN with posture prediction provides a preliminary step towards using ANN to predict the most appropriate combination of performance measures (PMs) - what drives human behavior. The PMs, which are the cost functions that are minimized in the posture prediction problem, are typically selected manually depending on the task. This is perhaps the most significant impediment when using posture prediction. How does the user know which PMs should be used? Neural networks provide tools for solving this problem. This thesis hypothesizes that the ANN can be trained to predict human motion quickly and accurately, to predict human posture (while considering external forces), and to determine the most appropriate combination of PM(s) for posture prediction. Such capabilities will in turn provide a new tool for studying human behavior. Based on initial experimentation, the general regression neural network (GRNN) was found to be the most effective type of ANN for DHM applications. A semi-automated methodology was developed to ease network construction, training and testing processes, and network parameters. This in turn facilitates use with DHM applications. With regards to motion prediction, use of ANN was successful. The results showed that the calculation time was reduced from 1 to 40 minutes, to a fraction of a second without reducing accuracy. With regards to posture prediction, ANN was again found to be effective. However, potential issues with certain motion-prediction tasks were discovered and shed light on necessary future development with ANNs. Finally, a decision engine was developed using GRNN for automatically selecting four human PMs, and was shown to be very effective. In order to train this new approach, a novel optimization formulation was used to extract PM weights from pre-existing motion-capture data. Eventually, this work will lead to automatically and realistically driving predictive DHMs in a general virtual environment.

Electromagnetic (EM) imaging schemes are inherently non-linear and ill-posed. Albeit there exist remedies to these fundamental problems, more efficient solutions are still being sought. To this end, in this thesis, the non-linearity is tackled in- corporating a multitude of techniques (ranging from Born approximation (linear), inexact Newton (linearized) to complete nonlinear iterative Landweber schemes) that can account for weak to strong scattering problems. The ill-posedness of the EM inverse scattering problem is circumvented by formulating the above methods into a minimization problem with a sparsity constraint. More specifically, four novel in- verse scattering schemes are formulated and implemented. (i) A greedy algorithm is used together with a simple artificial neural network (ANN) for efficient and accu- rate EM imaging of weak scatterers. The ANN is used to predict the sparsity level of the investigation domain which is then used as the L0 - constraint parameter for the greedy algorithm. (ii) An inexact Newton scheme that enforces the sparsity con- straint on the derivative of the unknown material properties (not necessarily sparse) is proposed. The inverse scattering problem is formulated as a nonlinear function of the derivative of the material properties. This approach results in significant spar- sification where any sparsity regularization method could be efficiently applied. (iii) A sparsity regularized nonlinear contrast source (CS) framework is developed to di- rectly solve the nonlinear minimization problem using Landweber iterations where the convergence is accelerated using a self-adaptive projected accelerated steepest descent algorithm. (iv) A 2.5D finite difference frequency domain (FDFD) based in- verse scattering scheme is developed for imaging scatterers embedded in lossy and inhomogeneous media. The FDFD based inversion algorithm does not require the Green’s function of the background medium and appears a promising technique for biomedical and subsurface imaging with a reasonable computational time. Numerical experiments, which are carried out using synthetically generated mea- surements, show that the images recovered by these sparsity-regularized methods are sharper and more accurate than those produced by existing methods. The methods developed in this work have potential application areas ranging from oil/gas reservoir engineering to biological imaging where sparse domains naturally exist.

No description available.

No description available.

This diploma thesis deals with the detection of fire and smoke from the image signal. The approach of this work uses a combination of convolutional and recurrent neural network. Machine learning models created in this work contain inception modules and blocks of long short-term memory. The research part describes selected models of machine learning used in solving the problem of fire detection in static and dynamic image data. As part of the solution, a data set containing videos and still images used to train the designed neural networks was created. The results of this approach are evaluated in conclusion.

Structural health monitoring (SHM) systems have been technologically advancing over the past few years. Improvements in fabrication and microelectronics allow the development of highly sophisticated sensor arrays, capable of detecting and transmitting an unprecedented amount of data. As the complexity of the hardware increases, research has been performed in developing the means to best utilize and effectively process the data. Algorithms from other computational fields are being introduced for the first time into SHM systems. Among them, the artificial neural network (ANN) and artificial immune systems (AIS) show great potential. In this thesis, features are extracted out of the acceleration data with the use of discrete wavelet transforms (DWT)s first. The DWT coefficients are used to calculate energy ratios, which are then classified using a neural network and an AIS algorithm known as negative selection (NS). The effectiveness of both methods are validated using simulated acceleration data of a four story structure exhibiting various damage states via computer simulation.

The aim of this work was to develop the method for classification of ECG beats into two classes, namely ischemic and non-ischemic beats. Heart beats (P-QRS-T cycles) selected from animals orthogonal ECGs were preprocessed and used as the input signals. Spectral features vectors (values of cross spectral coherency), principal component and HRV parameters were derived from the beats. The beats were classified using feedforward multilayer neural network designed in Matlab. Classification performance reached the value approx. from 87,2 to 100%. Presented results can be suitable in future studies aimed at automatic classification of ECG.

Diplomová práce se zabývá problematikou použití umělé inteligence v managementu rizik v kontextu malé výrobní společnosti Princ parket. Práce představuje společnost a přináší analýzu rizik, která vede k rozhodnutí zaměřit se na riziko poškození dobrého jména z důvodu produkce vadných výrobků. Jejím výsledkem je poskytnutí vyvinutých nástrojů RETUNN využívající metod Neuronových sítí, které umožňují predikci rizika a následnou implementaci opatření na snížení tohoto rizika.