No description available.

No description available.

No description available.

We introduce new methods for preprocessing and normalization of data acquired by gas/liquid chromatography coupled with mass spectrometry (GC/LC-MS). Normalization is desired prior to subsequent statistical analysis to adjust variabilities in ion intensities that are not caused by biological differences. There are different sources of experimental bias including variabilities in sample collection, sample storage, poor experimental design, noise, etc. Also, instrument variability in experiments involving a large number of runs leads to a significant drift in intensity measurements. We propose new normalization methods based on bootstrapping, Gaussian process regression, non-negative matrix factorization (NMF), and Bayesian hierarchical models. These methods model the bias by borrowing information across runs and features. Another novel aspect is utilizing scan-level data to improve the accuracy of quantification. We evaluated the performance of our method using simulated and experimental data. In comparison with several existing methods, the proposed methods yielded significant improvement. Gas chromatography coupled with mass spectrometry (GC-MS) is one of the technologies widely used for qualitative and quantitative analysis of small molecules. In particular, GC coupled to single quadrupole MS can be utilized for targeted analysis by selected ion monitoring (SIM). However, to our knowledge, there are no software tools specifically designed for analysis of GS-SIM-MS data. We introduce SIMAT, a new R package for quantitative analysis of the levels of targeted analytes. SIMAT provides guidance in choosing fragments for a list of targets. This is accomplished through an optimization algorithm that has the capability to select the most appropriate fragments from overlapping peaks based on a pre-specified library of background analytes. The tool also allows visualization of the total ion chromatogram (TIC) of runs and extracted ion chromatogram (EIC) of analytes of interest. Moreover, retention index (RI) calibration can be performed and raw GC-SIM-MS data can be imported in netCDF or NIST mass spectral library (MSL) formats. We evaluated the performance of SIMAT using several experimental data sets. Our results demonstrate that SIMAT performs better than AMDIS and MetaboliteDetector in terms of finding the correct targets in the acquired GC-SIM-MS data and estimating their relative levels. / Ph. D.

Clash Coordination is a crucial step in ensuring timely and cost-effective project delivery. While software tools like Navisworks and Solibri have improved the process of aggregating models and conducting clash tests and categorization, resolving clashes remains a slow and manual task. The reason for this slow process can be attributed to the meticulous nature of the process where design coordinators need to ensure that resolving one clash does not lead to new clashes. With the advent of machine learning and its application in construction, more research is being conducted to automate construction tasks to increase productivity and reduce the cost of the project. One such task currently being researched is to automate clash resolution. Researchers have explored the use of machine learning, specifically supervised learning, to automate clash resolution with successful outcomes. A search of the Web of Science database shows 7 publications that discuss the automation of clash resolution, automation of clash correction sequence, and automation of selection of relevant clashes. The authors to further analyze the content of these publications used VOSviewer to create a word map of keywords contained in the title, keywords, and abstract fields of these publications to analyze word co-occurrence. The word co-occurrence analysis revealed that the publications have explored supervised learning as the machine learning category of choice for automating clash resolution. However, the same analysis also showed the lack of terms such as data scrubbing, feature selection, feature engineering, and domain knowledge. These terms are an essential part of developing a machine-learning model. This analysis led the authors to believe that even though research is being conducted to automate clash resolution, a systematic approach to develop a machine learning model to support the automation of clash resolution is missing. Also, though these researches show significant accuracy in terms of automating clash resolution, they fail to justify the selection of their feature and label space. Another limitation of the current state of the art is that the effectiveness of supervised learning in automating tasks is limited by the availability of a large amount of labeled data, often unavailable. To address these research gaps, in this dissertation the author's first contribution to the body of knowledge is a phased systematic approach to develop an automation model for clash resolution. Since in machine learning selection of appropriate feature and label space is critical in developing an optimum and explainable solution, it is crucial to identify features that accurately represent a clash and also represent the factors industry experts consider when resolving the clash. Along with features, labels need to be selected as well to represent clash resolution options available to the industry. To achieve this in chapter 2 the author using modified Delphi captured the domain knowledge that industry experts utilize to resolve clashes. Factors considered by industry experts to decide on how clashes are resolved and options to resolve clashes are extracted from the domain knowledge. As a result of this research, the author identified 23 factors that industry experts consider when resolving clashes and 5 options available to resolve the clash. The work concludes by identifying factors and options that can serve as features and labels for a machine-learning algorithm to automate clash resolution. Once features and labels are identified the author in chapter 3 discusses the development of a prediction model to predict clash resolution options for a given clash. The discussion is focused on individual steps involved in the creation of machine learning models like data collection, data pre-processing, and machine learning algorithm development and selection. The author also addresses common challenges in the development of machine learning models like class imbalance and availability of limited data. The author utilizes a multi-label synthetic oversampling method (MLSOL) to generate different percentages of synthetic data to account for class imbalance and limited datasets. Using this dataset, the author then trained five different supervised learning algorithms and reported their accuracy. Based on this work the author concluded that increasing the dataset with 20% of synthetic data and using an artificial neural network to develop the machine learning model to automate clash resolution generated the best result with an average accuracy of around 80%. To address the limitation of using only supervised learning and as a second contribution to the body of knowledge, the author in chapter 4 proposes the use of reinforcement learning to train a Deep Q Network (DQN) agent capable of learning how to resolve clashes through interactions with a Building Information Model (BIM) environment containing clashes. The work discusses the implementation of a dynamic reward function to guide the agent in making decisions based on industry best practices. Additionally, it outlines the setup of the interaction between the agent and the environment to facilitate learning. Considering that reinforcement learning requires a significant amount of time to develop knowledge, the author also tested the effect of using a pre-trained supervised learning model to initialize the reinforcement learning policy function and guide knowledge exploration. This approach resulted in three variations of supervised-reinforcement learning. The supervised learning model used in this research demonstrated an accuracy of 31%. To demonstrate the utility of reinforcement learning in training an agent, the authors plotted graphs showing the number of clashes resolved per episode and the cumulative reward received per episode. The clashes resolved by the agent in this research were limited to clashes between ducts and pipes. These graphs illustrated that with each successive episode, the agent became increasingly proficient at resolving clashes. Among the variations of supervised-reinforcement learning, the one that exhibited the most stable learning graph utilized the weights of the supervised learning model to initialize the policy function of reinforcement learning. This research confirmed that reinforcement learning can be employed to train an automated model instead of relying solely on supervised learning, especially in scenarios where limited or no clash resolution data is available. Moreover, pre-training reinforcement learning using a supervised learning model led to more consistent learning outcomes. The research presented in this dissertation focuses on the holistic development of a machine learning model to automate clash resolution. By identifying appropriate features and labels before training the model the author ensures that the automation model accurately captures industry best practices and is explainable. Furthermore, by utilizing a systematic approach towards the development of a machine learning model the author addresses common challenges in developing a machine learning model and how we can overcome them. Lastly, through the utilization of supervised reinforcement learning the author proposes an alternative learning algorithm that can learn how to resolve clashes with fewer labeled examples through Building Information Model (BIM) interaction and with a more steady learning rate than reinforcement learning alone. / Doctor of Philosophy / Clash Coordination is a crucial step in ensuring timely and cost-effective project delivery. While software tools like Navisworks and Solibri have improved the process of aggregating models and conducting clash tests and categorization, resolving clashes remains a slow and manual task. The reason for this slow process can be attributed to the meticulous nature of the process where design coordinators need to make sure that resolving one clash does not lead to the creation of new clashes. Research has been conducted to improve the clash coordination process through automation using supervised learning, where a machine is taught to resolve clashes by understanding existing examples of clash resolutions. However, these researches do not provide enough evidence on how the example of clashes are presented to the machine and skip the details on common challenges associated with machine learning and how to overcome them. Also, as these researches focuses on training a machine using existing examples of clash resolution, a large number of examples are required to develop an effective machine-learning solution. The author of this dissertation addresses these limitations and contributes to the body of knowledge. In Chapter 2 the author discusses the use of modified Delphi to capture the industry's knowledge on how to make decisions about clash resolution and what options to consider when resolving clashes. The author also took measures during this process to reduce biases like intercoder reliability checks to make the results of modified Delphi more accurate. As a result of modified Delphi, the author identified 23 factors that industry experts consider when resolving clashes and 5 options available to resolve the clash. These identified factors and options were later utilized by the author in chapter 3 as features and labels to represent clash resolution examples. Using these examples, the author then developed a supervised learning model able to predict the most likely solution for a given clash with 80% accuracy. While developing the supervised learning model the author discusses common challenges associated with machine learning like class imbalance, data scrubbing, and un-normalized data and their mitigative measures. To address the limited availability of clash resolution examples the author in chapter 4 proposes and develops a supervised-reinforcement learning model. This model teaches how to resolve clashes by continuously interacting with a BIM model. To improve the learning rate the model also utilizes the knowledge gained through the development of a supervised learning model. This research shows that using reinforcement learning it is possible to train a machine to resolve clashes and adding knowledge from supervised learning to reinforcement learning results in a steadier learning rate for the machine. The research also shows that a more accurate supervised learning model can be developed using limited clash resolution examples using deep artificial neural networks, though this kind of approach increases the learning time and can lead to the issue of overfitting.

In this study, the impact of multiple image preprocessing methods on Convolutional Neural Networks (CNN) was studied. Metrics such as accuracy, precision, recall and F1-score (Hossin et al. 2011) were evaluated. Specifically, this study is geared towards malaria classification using the data set made available by the U.S. National Library of Medicine (Malaria Datasets n.d.). This data set contains images of thin blood smears, where uninfected and parasitized blood cells have been segmented. In the study, 3 CNN models were proposed for the parasitization classification task. Each model was trained on the original data set and 4 preprocessed data sets. The preprocessing methods used to create the 4 data sets were grayscale, normalization, histogram equalization and contrast limited adaptive histogram equalization (CLAHE). The impact of CLAHE preprocessing yielded a 1.46% (model 1) and 0.61% (model 2) improvement over the original data set, in terms of F1-score. One model (model 3) provided inconclusive results. The results show that CNN’s can be used for parasitization classification, but the impact of preprocessing is limited. / I denna studie studerades effekten av flera bildförbehandlingsmetoder på Convolutional Neural Networks (CNN). Mätvärden såsom accuracy, precision, recall och F1-score (Hossin et al. 2011) utvärderades. Specifikt är denna studie inriktad på malariaklassificering med hjälp av ett dataset som tillhandahålls av U.S. National Library of Medicine (Malaria Datasets n.d.). Detta dataset innehåller bilder av tunna blodutstryk, med segmenterade oinfekterade och parasiterade blodceller. I denna studie föreslogs 3 CNN-modeller för parasiteringsklassificeringen. Varje modell tränades på det ursprungliga datasetet och 4 förbehandlade dataset. De förbehandlingsmetoder som användes för att skapa de 4 dataseten var gråskala, normalisering, histogramutjämning och kontrastbegränsad adaptiv histogramutjämning (CLAHE). Effekten av CLAHE-förbehandlingen gav en förbättring av 1.46% (modell 1) och 0.61% (modell 2) jämfört med det ursprungliga datasetet, vad gäller F1-score. En modell (modell 3) gav inget resultat. Resultaten visar att CNN:er kan användas för parasiteringsklassificering, men effekten av förbehandling är begränsad.

Reliable results are crucial when working with medical decision support systems. A decision support system should be reliable but also be interpretable, i.e. able to show how it has inferred its conclusions. In this thesis, the preprocessing perceptron is presented as a simple but effective and efficient analysis method to consider when creating medical decision support systems. The preprocessing perceptron has the simplicity of a perceptron combined with a performance comparable to the multi-layer perceptron. The research in this thesis has been conducted within the fields of medical informatics and intelligent computing. The original idea of the production line as a tool for a domain expert to extract information, build decision support systems and integrate them in the existing system is described. In the introductory part of the thesis, an introduction to feed-forward neural networks and fuzzy logic is given as a background to work with the preprocessing perceptron. Input to a decision support system is crucial and it is described how to gather a data set, decide how many and what kind of inputs to use. Outliers, errors and missing data are covered as well as normalising of the input. Training is done in a backpropagation-like manner where the division of the data set into a training and a test set can be done in several different ways just as the training itself can have variations. Three major groups of methods to estimate the discriminance effect of the preprocessing perceptron are described and a discussion of the trade-off between complexity and approximation strength are included. Five papers are presented in this thesis. Case studies are shown where the preprocessing perceptron is compared to multi-layer perceptrons, statistical approaches and other mathematical models. The model is extended to a generalised preprocessing perceptron and the performance of this new model is compared to the traditional feed-forward neural networks. Results concerning the preprocessing layer and its connection to multivariate decision limits are included. The well-known ROC curve is described and introduced fully into the field of computer science as well as the improved curve, the QROC curve. Finally a tutorial to the program trainGPP is presented. It describes how to work with the preprocessing perceptron from the moment when a data file is provided to the moment when a new decision support system is built.

This thesis deals with problems of recognition of an electrometer´s state from sensing image. It is tangibly about electrometer´s scanning by a mobile phone´s camera. There is a surface with an electrometer´s dial which is detected and on this surface the particular numbers are detected consequently. The numbers are recognized via neural network. For more information from this image there are used some techniques of image segmentation to check the status. For the classification of the segmentation´s outputs are used classification tools, especially a support vector machine (SVM) and neural networks. Problems of image segmentations are solved by using OpenCV library. OpenCV is used for the implementation of the vector machine either. Application is on Android platform. Part of the thesis is concerned in a creation of a desktop application which is instrumental towards testing of neural network. The thesis also describes how to save the necessary data gathering in the course of the recognition which are used for working with neural network. The part of the thesis also deals with running web which will be evolved for the opportunity to participate in the further development of the system. There is available a public repository with source codes created during implementation.

Prediction of energy load profiles is an important topic in Smart Grid technologies. Accurate forecasts can lead to reduced costs and decreased dependency on commercial power suppliers by adapting to prices on energy market, efficient utilisation of solar and wind energy and sophisticated load scheduling. This thesis compares various statistical and machine learning models and their ability to forecast load profile for an entire day divided into 48 half-hour intervals. Additionally, we examine various preprocessing methods and their influence on the accuracy of the models. We also compare a variety of imputation methods that are designed to reconstruct missing observation commonly present in energy consumption data.

With arrival of affordable digital technology we are increasingly coming into contact with digital images. Cameras are no longer dedicated devices, but part of almost every mobile phone, PDA and laptop. This paper discusses methods for enhancing quality of digital images with focus on removing noise, creating high dynamic range (HDR) images and extending depth of field (DOF). It contains familiarization with technical means for acquiring digital image, explains origin of image noise. Further attention is drawn to HDR, from explaining the term, physical basis, difference between HDR sensing and HDR displaying, to survey and historical development of methods dealing with creating HDR images. The next part is explaining DOF when displaying, physical basis of this phenomenon and review of methods used for DOF extension. The paper mentions problem of acquiring images needed for solving given tasks and designs method for acquiring images. Using it a database of test images for each task was created. Part of the paper also deals with design of a program, that implements discussed methods, for solving the given tasks. With help of proposed class imgmap, quality of output images is improved, by modifying maps of input images. The paper describes methods, improvements, means of setting parameters and their effects on algorithms and control of program using proposed GUI. Finally, comparison with free software for extending DOF takes place. The proposed software provides at least comparable results, the correct setting of parameters for specific cases allows to achieve better properties of the resulting image. Time requirements of image processing are worse because designed software was not optimised.