Software maintenance reportedly accounts for much of the total cost associated with developing software. These costs occur because modifying software is a highly error-prone task. Changing software to correct faults or add new functionality can cause existing functionality to regress, introducing new faults. To avoid such defects, one can re-test software after modifications, a task commonly known as regression testing. Regression testing typically involves the re-execution of test cases developed for previous versions. Re-running all existing test cases, however, is often costly and sometimes even infeasible due to time and resource constraints. Re-running test cases that do not exercise changed or change-impacted parts of the program carries extra cost and gives no benefit. The research community has thus sought ways to optimize regression testing by lowering the cost of test re-execution while preserving its effectiveness. To this end, researchers have proposed selecting a subset of test cases according to a variety of criteria (test case selection) and reordering test cases for execution to maximize a score function (test case prioritization). This dissertation presents a novel framework for optimizing regression testing activities, based on a probabilistic view of regression testing. The proposed framework is built around predicting the probability that each test case finds faults in the regression testing phase, and optimizing the test suites accordingly. To predict such probabilities, we model regression testing using a Bayesian Network (BN), a powerful probabilistic tool for modeling uncertainty in systems. We build this model using information measured directly from the software system. Our proposed framework builds upon the existing research in this area in many ways. First, our framework incorporates different information extracted from software into one model, which helps reduce uncertainty by using more of the available information, and enables better modeling of the system. Moreover, our framework provides flexibility by enabling a choice of which sources of information to use. Research in software measurement has proven that dealing with different systems requires different techniques and hence requires such flexibility. Using the proposed framework, engineers can customize their regression testing techniques to fit the characteristics of their systems using measurements most appropriate to their environment. We evaluate the performance of our proposed BN-based framework empirically. Although the framework can help both test case selection and prioritization, we propose using it primarily as a prioritization technique. We therefore compare our technique against other prioritization techniques from the literature. Our empirical evaluation examines a variety of objects and fault types. The results show that the proposed framework can outperform other techniques on some cases and performs comparably on the others. In sum, this thesis introduces a novel Bayesian framework for optimizing regression testing and shows that the proposed framework can help testers improve the cost effectiveness of their regression testing tasks.

Boolean propositional satisfiability (SAT) and probabilistic reasoning represent two core problems in AI. Backtracking based algorithms have been applied in both problems. In this thesis, I investigate structure-based techniques for solving real world SAT and Bayesian networks, such as software testing and medical diagnosis instances. When solving a SAT instance using backtracking search, a sequence of decisions must be made as to which variable to branch on or instantiate next. Real world problems are often amenable to a divide-and-conquer strategy where the original instance is decomposed into independent sub-problems. Existing decomposition techniques are based on pre-processing the static structure of the original problem. I propose a dynamic decomposition method based on hypergraph separators. Integrating this dynamic separator decomposition into the variable ordering of a modern SAT solver leads to speedups on large real world SAT problems. Encoding a Bayesian network into a CNF formula and then performing weighted model counting is an effective method for exact probabilistic inference. I present two encodings for improving this approach with noisy-OR and noisy-MAX relations. In our experiments, our new encodings are more space efficient and can speed up the previous best approaches over two orders of magnitude. The ability to solve similar problems incrementally is critical for many probabilistic reasoning problems. My aim is to exploit the similarity of these instances by forwarding structural knowledge learned during the analysis of one instance to the next instance in the sequence. I propose dynamic model counting and extend the dynamic decomposition and caching technique to multiple runs on a series of problems with similar structure. This allows us to perform Bayesian inference incrementally as the evidence, parameter, and structure of the network change. Experimental results show that my approach yields significant improvements over previous model counting approaches on multiple challenging Bayesian network instances.

<p>In this paper, we propose a new learning algorithm for non-stationary Dynamic Bayesian Networks is proposed. Although a number of effective learning algorithms for non-stationary DBNs have previously been proposed and applied in Signal Pro- cessing and Computational Biology, those algorithms are based on batch learning algorithms that cannot be applied to online time-series data. Therefore, we propose a learning algorithm based on a Particle Filtering approach so that we can apply that algorithm to online time-series data. To evaluate our algorithm, we apply it to the simulated data set and the real-world financial data set. The result on the simulated data set shows that our algorithm performs accurately makes estimation and detects change. The result applying our algorithm to the real-world financial data set shows several features, which are suggested in previous research that also implies the effectiveness of our algorithm.</p> / Thesis

Since the development of high-throughput technologies, we can capture large quantities of gene¡¦s expression data from DNA microarray data, so there are some technologies have been proposed to model gene regulatory networks. Gene regulatory networks is mainly used to express the relationship between the genes, but only can express a simple relationship, and can¡¦t clearly show how the operation between genes regulatory. In the simulation method of gene regulation, the mathematical methods are more often used. In the mathematical methods, S-system is the most widely used in non-linear differential equations. When the use of mathematical simulation of gene regulatory networks, there are mainly two aspects¡G(1) deciding on the model structure and (2) estimating the involved parameter values. However, when using S-system simulated the gene regulatory networks, we can only know the gene profiles, and there is no way to know the regulatory relationships between genes, but in order to understand the relationship between genes, we must clearly understand how genes work. Therefore, we propose to encode parameter values to infer the regulatory parameter values between genes. We propose the method of encoding parameter values, and using six artificial genetic datasets, and assuming 100% parameter values are known, 90% known, 70% known, 50% known, 30% known, 10% known. The experimental results show, besides it can infer a high proportion of non-regulation, positive regulation and negative regulation, also can infer more precise parameter values, and also has a clear understanding of the regulatory relationship between genes.

<p>The mental workload for fighter pilots in modern air combat is extremely high. The pilot has to make fast dynamic decisions under high uncertainty and high time pressure. This is hard to perform in close encounters, but gets even harder when operating beyond visual range when the sensors of an aircraft become the pilot's eyes and ears. Although sensors provide good estimates for position and speed of an opponent, there is a big loss in the assessment of a situation. Important tactical events or situations can occur without the pilot noticing, which can change the outcome of a mission completely. This makes the development of an automated situation assessment system very important for future fighter aircraft. </p><p>This Master Thesis investigates the possibilities to design and implement an automated situation assessment system in a fighter aircraft. A Fuzzy-Bayesian hybrid technique is used in order to cope with the stochastic environment and making the development of the tactical situations library as clear and simple as possible.</p>

Probabilistic graphical models (PGMs) provide the capability of evaluating uncertainty and variability of product use in addition to correlating the results with aspects of the usage context. Although energy consumption during use can cause a majority of a product's environmental impact, common practice is to neglect operational variability in life cycle inventories (LCIs). Therefore, the relationship between a product's usage context and its environmental performance is rarely considered in design evaluations. This dissertation demonstrates a method for describing the usage context as a set of factors and representing the usage context through a PGM. The application to LCIs is demonstrated through the use of a lightweight vehicle design example. Although replacing steel vehicle parts with aluminum parts reduces the weight and can increase fuel economy, the energy invested in production of aluminum parts is much larger than that of steel parts. The tradeoff between energy investment and fuel savings is highly dependent upon the vehicle fuel economy and lifetime mileage. The demonstration PGM is constructed from relating factors such as driver behavior, alternative driving schedules, and residential density with local conditional probability distributions derived from publicly available data sources. Unique scenarios are then assembled from sets of conditions on these factors to provide insight for sources of variance. The vehicle example demonstrated that implementation of realistic usage scenarios via a PGM can provide a much higher fidelity investigation of energy savings during use and that distinct scenarios can have significantly different implications for the effectiveness of lightweight vehicle designs. Scenarios with large families, for example, yield high energy savings, especially if the vehicle is used for commuting or stop-and-go traffic conditions. Scenarios of small families and efficient driving schedules yield lower energy savings for lightweight vehicle designs. / text

As CMOS scaling faces a technological barrier in the near future, novel design paradigms are being proposed to keep up with the ever growing need for computation power and speed. Most of these novel technologies have device sizes comparable to atomic and molecular scales. At these levels the quantum mechanical effects play a dominant role in device performance, thus inducing uncertainty. The wave nature of particle matter and the uncertainty associated with device operation make a case for probabilistic modeling of the device. As the dimensions go down to a molecular scale, functioning of a nano-device will be governed primarily by the atomic level device physics. Modeling a device at such a small scale will require taking into account the quantum mechanical phenomenon inherent to the device. In this dissertation, we studied one such nano-device: Quantum-Dot Cellular Automata (QCA). We used probabilistic modeling to perform a fast approximation based method to estimate error, power and reliability in large QCA circuits. First, we associate the quantum mechanical probabilities associated with each QCA cell to design and build a probabilistic Bayesian network. Our proposed modeling is derived from density matrix-based quantum modeling, and it takes into account dependency patterns induced by clocking. Our modeling scheme is orders of magnitude faster than the coherent vector simulation method that uses quantum mechanical simulations. Furthermore, our output node polarization values match those obtained from the state of the art simulations. Second, we use this model to approximate power dissipated in a QCA circuit during a non-adiabatic switching event and also to isolate the thermal hotspots in a design. Third, we also use a hierarchical probabilistic macromodeling scheme to model QCA designs at circuit level to isolate weak spots early in the design process. It can also be used to compare two functionally equivalent logic designs without performing the expensive quantum mechanical simulations. Finally, we perform optimization studies on different QCA layouts by analyzing the designs for error and power over a range of kink energies.To the best of our knowledge the non-adiabatic power model presented in this dissertation is the first work that uses abrupt clocking scheme to estimate realistic power dissipation. All prior works used quasi-adiabatic power dissipation models. The hierarchical macromodel design is also the first work in QCA design that uses circuit level modeling and is faithful to the underlying layout level design. The effect of kink energy to study power-error tradeoffs will be of great use to circuit designers and fabrication scientists in choosing the most suitable design parameters such as cell size and grid spacing.

Reliability is one of the most serious issues confronted by microelectronics industry as feature sizes scale down from deep submicron to sub-100-nanometer and nanometer regime. Due to processing defects and increased noise effects, it is almost impractical to come up with error-free circuits. As we move beyond 22nm, devices will be operating very close to their thermal limit making the gates error-prone and every gate will have a finite propensity of providing erroneous outputs. Additional factors increasing the erroneous behaviors are low operating voltages and extremely high frequencies. These types of errors are not captured by current defect and fault tolerant mechanisms as they might not be present during the testing and reconfiguration. Hence Reliability-centric CAD analysis tool is becoming more essential not only to combat defect and hard faults but also errors that are transient and probabilistic in nature.In this dissertation, we address three broad categories of errors. First, we focus on random pattern testability of logic circuits with respect to hard or permanent faults. Second, we model the effect of single-event-upset (SEU) at an internal node to primary outputs. We capture the temporal nature of SEUs by adding timing information to our model. Finally, we model the dynamic error in nano-domain computing, where reliable computation has to be achieved with "systemic" unreliable devices, thus making the entire computation process probabilistic rather than deterministic in nature.Our central theoretical scheme relies on Bayesian Belief networks that are compact efficient models representing joint probability distribution in a minimal graphical structure that not only uses conditional independencies to model the underlying probabilistic dependence but also uses them for computational advantage. We used both exact and approximate inference which has let us achieve order of magnitude improvements in both accuracy and speed and have enabled us t o study larger benchmarks than the state-of-the-art. We are also able to study error sensitivities, explore design space, and characterize the input space with respect to errors and finally, evaluate the effect of redundancy schemes.

RFID technologies are being recently adopted in the retail space tracking consumer in-store movements. The RFID-collected data are location sensitive and constantly updated as a consumer moves inside a store. By capturing the entire shopping process including the movement path rather than analyzing merely the shopping basket at check-out, the RFID-collected data provide unique and exciting opportunities to study consumer purchase behavior and thus lead to actionable marketing applications.This dissertation research focuses on (a) advancing the representation and management of the RFID-collected shopping path data; (b) analyzing, modeling and predicting customer shopping activities with a spatial pattern discovery approach and a dynamic probabilistic modeling based methodology to enable advanced spatial business intelligence. The spatial pattern discovery approach identifies similar consumers based on a similarity metric between consumer shopping paths. The direct applications of this approach include a novel consumer segmentation methodology and an in-store real-time product recommendation algorithm. A hierarchical decision-theoretic model based on dynamic Bayesian networks (DBN) is developed to model consumer in-store shopping activities. This model can be used to predict a shopper's purchase goal in real time, infer her shopping actions, and estimate the exact product she is viewing at a time. We develop an approximate inference algorithm based on particle filters and a learning procedure based on the Expectation-Maximization (EM) algorithm to perform filtering and prediction for the network model. The developed models are tested on a real RFID-collected shopping trip dataset with promising results in terms of prediction accuracies of consumer purchase interests.This dissertation contributes to the marketing and information systems literature in several areas. First, it provides empirical insights about the correlation between spatial movement patterns and consumer purchase interests. Such correlation is demonstrated with in-store shopping data, but can be generalized to other marketing contexts such as store visit decisions by consumers and location and category management decisions by a retailer. Second, our study shows the possibility of utilizing consumer in-store movement to predict consumer purchase. The predictive models we developed have the potential to become the base of an intelligent shopping environment where store managers customize marketing efforts to provide location-aware recommendations to consumers as they travel through the store.

Boolean propositional satisfiability (SAT) and probabilistic reasoning represent two core problems in AI. Backtracking based algorithms have been applied in both problems. In this thesis, I investigate structure-based techniques for solving real world SAT and Bayesian networks, such as software testing and medical diagnosis instances. When solving a SAT instance using backtracking search, a sequence of decisions must be made as to which variable to branch on or instantiate next. Real world problems are often amenable to a divide-and-conquer strategy where the original instance is decomposed into independent sub-problems. Existing decomposition techniques are based on pre-processing the static structure of the original problem. I propose a dynamic decomposition method based on hypergraph separators. Integrating this dynamic separator decomposition into the variable ordering of a modern SAT solver leads to speedups on large real world SAT problems. Encoding a Bayesian network into a CNF formula and then performing weighted model counting is an effective method for exact probabilistic inference. I present two encodings for improving this approach with noisy-OR and noisy-MAX relations. In our experiments, our new encodings are more space efficient and can speed up the previous best approaches over two orders of magnitude. The ability to solve similar problems incrementally is critical for many probabilistic reasoning problems. My aim is to exploit the similarity of these instances by forwarding structural knowledge learned during the analysis of one instance to the next instance in the sequence. I propose dynamic model counting and extend the dynamic decomposition and caching technique to multiple runs on a series of problems with similar structure. This allows us to perform Bayesian inference incrementally as the evidence, parameter, and structure of the network change. Experimental results show that my approach yields significant improvements over previous model counting approaches on multiple challenging Bayesian network instances.