Software practitioners lack a consistent approach to assessing and predicting quality within their products. This research proposes a software quality model that accounts for the influences of development team skill/experience, process maturity, and problem complexity throughout the software engineering life cycle. The model is structured using Bayesian Belief Networks and, unlike previous efforts, uses widely-accepted software engineering standards and in-use industry techniques to quantify the indicators and measures of software quality. Data from 28 software engineering projects was acquired for this study, and was used for validation and comparison of the presented software quality models. Three Bayesian model structures are explored and the structure with the highest performance in terms of accuracy of fit and predictive validity is reported. In addition, the Bayesian Belief Networks are compared to both Least Squares Regression and Neural Networks in order to identify the technique is best suited to modeling software product quality. The results indicate that Bayesian Belief Networks outperform both Least Squares Regression and Neural Networks in terms of producing modeled software quality variables that fit the distribution of actual software quality values, and in accurately forecasting 25 different indicators of software quality. Between the Bayesian model structures, the simplest structure, which relates software quality variables to their correlated causal factors, was found to be the most effective in modeling software quality. In addition, the results reveal that the collective skill and experience of the development team, over process maturity or problem complexity, has the most significant impact on the quality of software products.

Nowadays, space weather has become an international issue to the world's countries because of its catastrophic effect on space-borne and ground-based systems, and industries, impacting our lives. One of the main solar activities that is considered as a major driver of space weather is solar flares. Solar flares can be defined as an enormous eruption in the sun's atmosphere. This phenomenon happens when magnetic energy stored in twisted magnetic fields, usually near sunspots, is suddenly released. Yet, their occurrence is not fully understood. These flares can affect the Earth by the release of massive quantities of charged particles and electromagnetic radiation. Investigating the associations between solar flares and sunspot groups is helpful in comprehending the possible cause and effect relationships among solar flares and sunspot features. 01 This thesis proposes a new approach developed by integrating advances in image processing, machine learning, and deep learning with advances in solar physics to extract valuable knowledge from historical solar data related to sunspot regions and flares. This dissertation aims to achieve the following: 1) We developed a new prediction algorithm based on the Automated Solar Activity Prediction system (ASAP) system. The proposed algorithm updates the ASAP system by extending the training process and optimizing the learning rules to the optimize performance better. Two neural networks are used in the proposed approach. The first neural network is used to predict whether a specific sunspot class at a particular time is likely to produce a significant flare or not. The second neural network is used to predict the type of this flare, X or M-class. 2) We proposed a new system called the ASAP_Deep system built on top of the ASAP system introduced in [6] but improves the system with an updated deep learning-based prediction capability. In addition, we successfully apply Convolutional Neural Network (CNN) to the sunspot group image without any pr-eprocessing or feature extraction. Moreover, our system results are considerably better, especially for the false alarm ratio (FAR); this reduces the losses resulting from the protection measures applied by companies. In addition, the proposed system achieves a relatively high score of True Skill Statistic (TSS) and Heidke Skill Score (HSS). 3) We presented a novel system that used the Deep Belief Networks (DBNs) to predict the solar flares occurrence. The input data are SDO/HMI Intensitygram and Magnetogram images. The model outputs are "Flare or No-Flare" of significant flare occurrence (M and X-class flares). In addition, we created a dataset from the sunspots groups extracted from SDO HMI Intensitygram images. We compared the results obtained from the complete suggested system with those of three previous flare forecast models using several statistical metrics. In our view, these developed methods and results represent an excellent initial step toward enhancing the accuracy of flare forecasting, enhance our understanding of flare occurrence, and develop efficient flare prediction systems. The systems, implementation, results, and future work are explained in this dissertation.

No description available.

No description available.

This research explores the potential of improving the explainability of outliers using Bayesian Belief Networks as background knowledge. Outliers are deviations from the usual trends of data. Mining outliers may help discover potential anomalies and fraudulent activities. Meaningful outliers can be retrieved and analyzed by using domain knowledge. Domain knowledge (or background knowledge) is represented using probabilistic graphical models such as Bayesian belief networks. Bayesian networks are graph-based representation used to model and encode mutual relationships between entities. Due to their probabilistic graphical nature, Belief Networks are an ideal way to capture the sensitivity, causal inference, uncertainty and background knowledge in real world data sets. Bayesian Networks effectively present the causal relationships between different entities (nodes) using conditional probability. This probabilistic relationship shows the degree of belief between entities. A quantitative measure which computes changes in this degree of belief acts as a sensitivity measure . The first contribution of this research is enhancing the performance for measurement of sensitivity based on earlier research work, the Interestingness Filtering Engine Miner algorithm. The algorithm developed (IBOX - Interestingness based Bayesian outlier eXplainer) provides progressive improvement in the performance and sensitivity scoring of earlier works. Earlier approaches compute sensitivity by measuring divergence among conditional probability of training and test data, while using only couple of probabilistic interestingness measures such as Mutual information and Support to calculate belief sensitivity. With ingrained support from the literature as well as quantitative evidence, IBOX provides a framework to use multiple interestingness measures resulting in better performance and improved sensitivity analysis. The results provide improved performance, and therefore explainability of rare class entities. This research quantitatively validated probabilistic interestingness measures as an effective sensitivity analysis technique in rare class mining. This results in a novel, original, and progressive research contribution to the areas of probabilistic graphical models and outlier analysis.

Humans make use of more than just the audio signal to perceive speech. Behavioral and neurological research has shown that a person's knowledge of how speech is produced influences what is perceived. With methods for collecting articulatory data becoming more ubiquitous, methods for extracting useful information are needed to make this data useful to speech scientists, and for speech technology applications. This dissertation presents feature extraction methods for ultrasound images of the tongue and for data collected with an Electro-Magnetic Articulograph (EMA). The usefulness of these features is tested in several phoneme classification tasks. Feature extraction methods for ultrasound tongue images presented here consist of automatically tracing the tongue surface contour using a modified Deep Belief Network (DBN) (Hinton et al. 2006), and methods inspired by research in face recognition which use the entire image. The tongue tracing method consists of training a DBN as an autoencoder on concatenated images and traces, and then retraining the first two layers to accept only the image at runtime. This 'translational' DBN (tDBN) method is shown to produce traces comparable to those made by human experts. An iterative bootstrapping procedure is presented for using the tDBN to assist a human expert in labeling a new data set. Tongue contour traces are compared with the Eigentongues method of (Hueber et al. 2007), and a Gabor Jet representation in a 6-class phoneme classification task using Support Vector Classifiers (SVC), with Gabor Jets performing the best. These SVC methods are compared to a tDBN classifier, which extracts features from raw images and classifies them with accuracy only slightly lower than the Gabor Jet SVC method.For EMA data, supervised binary SVC feature detectors are trained for each feature in three versions of Distinctive Feature Theory (DFT): Preliminaries (Jakobson et al. 1954), The Sound Pattern of English (Chomsky and Halle 1968), and Unified Feature Theory (Clements and Hume 1995). Each of these feature sets, together with a fourth unsupervised feature set learned using Independent Components Analysis (ICA), are compared on their usefulness in a 46-class phoneme recognition task. Phoneme recognition is performed using a linear-chain Conditional Random Field (CRF) (Lafferty et al. 2001), which takes advantage of the temporal nature of speech, by looking at observations adjacent in time. Results of the phoneme recognition task show that Unified Feature Theory performs slightly better than the other versions of DFT. Surprisingly, ICA actually performs worse than running the CRF on raw EMA data.

Deep neural networks represent an effective and universal model capable of solving a wide variety of tasks. This thesis is focused on three different types of deep neural networks - the multilayer perceptron, the convolutional neural network, and the deep belief network. All of the discussed network models are implemented on parallel hardware, and thoroughly tested for various choices of the network architecture and its parameters. The implemented system is accompanied by a detailed documentation of the architectural decisions and proposed optimizations. The efficiency of the implemented framework is confirmed by the results of the performed tests. A significant part of this thesis represents also additional testing of other existing frameworks which support deep neural networks. This comparison indicates superior performance to the tested rival frameworks of multilayer perceptrons and convolutional neural networks. The deep belief network implementation performs slightly better for RBM layers with up to 1000 hidden neurons, but has a noticeably inferior performance for more robust RBM layers when compared to the tested rival framework. Powered by TCPDF (www.tcpdf.org)

<p>Estuaries interfacing with the land, atmosphere and open oceans can be influenced in a variety of ways by anthropogenic activities. Centuries of overexploitation, habitat transformation, and pollution have degraded estuarine ecological health. Key concerns of public and environmental managers of estuaries include water quality, particularly the enrichment of nutrients, increased chlorophyll a concentrations, increased hypoxia/anoxia, and increased Harmful Algal Blooms (HABs). One reason for the increased nitrogen loading over the past two decades is the proliferation of concentrated animal feeding operations (CAFOs) in coastal areas. This dissertation documents a study of estuarine eutrophication modeling, including modeling of major source of nitrogen in the watershed, the use of the Bayesian Networks (BNs) for modeling eutrophication dynamics in an estuary, a documentation of potential problems of using BNs, and a continuous BN model for addressing these problems.</p><p>Environmental models have emerged as great tools to transform data into useful information for managers and policy makers. Environmental models contain uncertainty due to natural ecosystems variability, current knowledge of environmental processes, modeling structure, computational restrictions, and problems with data/observations due to measurement error or missingness. Many methodologies capable of quantifying uncertainty have been developed in the scientic literature. Examples of such methods are BNs, which utilize conditional probability tables to describe the relationships among variables. This doctoral dissertation demonstrates how BNs, as probabilistic models, can be used to model eutrophication in estuarine ecosystems and to explore the effects of plausible future climatic and nutrient pollution management scenarios on water quality indicators. The results show interaction among various predictors and their impact on ecosystem health. The synergistic eftects between nutrient concentrations and climate variability caution future management actions.</p><p>BNs have several distinct strengths such as the ability to update knowledge based on Bayes' theorem, modularity, accommodation of various knowledge sources and data types, suitability to both data-rich and data-poor systems, and incorporation of uncertainty. Further, BNs' graphical representation facilitates communicating models and results with environmental managers and decision-makers. However, BNs have certain drawbacks as well. For example, they can only handle continuous variables under severe restrictions (1- Each continuous variable be assigned a (linear) conditional Normal distribution; 2- No discrete variable have continuous parents). The solution, thus far, to address this constraint has been discretizing variables. I designed an experiment to evaluate and compare the impact of common discretization methods on BNs. The results indicate that the choice of discretization method severely impacts the model results; however, I was unable to provide any criteria to select an optimal discretization method.</p><p>Finally, I propose a continuous variable Bayesian Network methodology and demonstrate its application for water quality modeling in estuarine ecosystems. The proposed method retains advantageous characteristics of BNs, while it avoids the drawbacks of discretization by specifying the relationships among the nodes using statistical and conditional probability models. The Bayesian nature of the proposed model enables prompt investigation of observed patterns, as new conditions unfold. The network structure presents the underlying ecological ecosystem processes and provides a basis for science communication. I demonstrate model development and temporal updating using the New River Estuary, NC data set and spatial updating using the Neuse River Estuary, NC data set.</p> / Dissertation

Με τη συνεχώς αυξανόμενη παρουσία αυτόματων συστημάτων στην καθημερινότητά μας, εισέρχεται και το βάρος της αλληλεπίδρασης με αυτά τα συστήματα εξαιτίας της έλλειψης συναισθηματικής νοημοσύνης από την πλευρά των μηχανών [1]. Η συναισθηματική πληροφορία που μεταδίδεται μέσω της ανθρώπινης ομιλίας αποτελεί σημαντικό παράγοντα στις ανθρώπινες επικοινωνίες και αλληλεπιδράσεις. Όταν οι άνθρωποι αλληλεπιδρούν με μηχανές ή υπολογιστικά συστήματα υπάρχει ένα κενό μεταξύ της πληροφορίας που μεταδίδεται και αυτής που γίνεται αντιληπτή. Η εργασία αυτή επικεντρώνεται στον τρόπο με τον οποίο ένα υπολογιστικό σύστημα μπορεί να αντιληφθεί την συναισθηματική πληροφορία που υποβόσκει στην ανθρώπινη ομιλία χρησιμοποιώντας την πληροφορία που βρίσκεται στα διάφορα γλωσσολογικά μοντέλα. Γίνεται μελέτη ενός συστήματος αναγνώρισης της συναισθηματικής κατάστασης του ομιλητή, και πιο συγκεκριμένα επικεντρωνόμαστε στην επεξεργασία ομιλίας και την εξαγωγή των κατάλληλων παραμέτρων, οι οποίες θα μπορέσουν να χαρακτηρίσουν μονοσήμαντα κάθε συναισθηματική κατάσταση. Κάνουμε επεξεργασία οπτικοακουστικού υλικού χρησιμοποιώντας διάφορα εργαλεία λογισμικού με σκοπό να αντλήσουμε αξιόπιστη γλωσσολογική πληροφορία, η οποία να είναι αντιπροσωπευτική των διαφόρων συναισθημάτων που εξετάζουμε. Συνδυάζοντας τη γλωσσολογική με την ακουστική πληροφορία καταλήγουμε σε ένα ολοκληρωμένο μοντέλο αναγνώρισης συναισθημάτων. Τα αποτελέσματά μας υποδεικνύουν το ποσοστό κατά το οποίο τα εξαγόμενα γλωσσολογικά μοντέλα μπορούν να μας προσφέρουν αξιόπιστη αναγνώριση συναισθημάτων ενός ομιλητή. / Along with the constantly increasing presence of automatic systems in our everyday lives, there comes the problem of interaction with thesse sytems because of the lack of artificial intelligence from the systems themselves. Emotion information transcripted through human language is an important factor of human interactions and conversations. When people interact with computer systems though, there is a gap between the information sent and the information perceived. This diploma thesis focuses on the way a computer system can perceive the information of emotions that underlies in human speech, by using the information found in linguistic models. We study a recognition system for the emotional state of the speaker himself and specifically we focus on the speech recognition and its parameters, which could uniquely identify every emotional state. We edit some video samples using the appropriate software in order to draw credible linguistic information, which is representative of the examined emotions. By combining the linguistic information with the aural information, we can reach a state where we can have a complete speech recognition system. The results of our work present the percentage at which these models can provide acceptable emotional recognition of a speaker.

No description available.