No description available.

Thesis (Ed.D.)--Boston University.

Context. Software defect prediction is essential in reducing software development costs and in helping companies save their reputation. Defect prediction uses mathematical models to identify patterns associated with defects within code. Resources spent reviewing the entire code can be minimised by focusing on defective parts of the code. Recent findings suggest many published prediction models may not be reliable. Critical scientific methods for identifying reliable research are Replication and Reproduction. Replication can test the external validity of studies while Reproduction can test their internal validity. Aims. The aims of my dissertation are first to study the use and quality of replications and reproductions in defect prediction. Second, to identify factors that aid or hinder these scientific methods. Methods. My methodology is based on tracking the replication of 208 defect prediction studies identified in a highly cited Systematic Literature Review (SLR) [Hall et al. 2012]. I analyse how often each of these 208 studies has been replicated and determine the type of replication carried out. I use quality, citation counts, publication venue, impact factor, and data availability from all the 208 papers to see if any of these factors are associated with the frequency with which they are replicated. I further reproduce the original studies that have been replicated in order to check their internal validity. Finally, I identify factors that affect reproducibility. Results. Only 13 (6%) of the 208 studies are replicated, most of which fail a quality check. Of the 13 replicated original studies, 62% agree with their replications and 38% disagree. The main feature of a study associated with being replicated is that original papers appear in the Transactions of Software Engineering (TSE) journal. The number of citations an original paper had was also an indicator of the probability of being replicated. In addition, studies conducted using closed source data have more replications than those based on open source data. Of the 4 out of 5 papers I reproduced, their results differed with those of the original by more than 5%. Four factors are likely to have caused these failures: i) lack of a single version of the data initially used by the original; ii) the different dataset versions available have different properties that impact model performance; iii) unreported data preprocessing; and iv) inconsistent results from alternative versions of the same tools. Conclusions. Very few defect prediction studies are replicated. The lack of replication and failure of reproduction means that it remains unclear how reliable defect prediction is. Further investigation into this failure provides key aspects researchers need to consider when designing primary studies, performing replication and reproduction studies. Finally, I provide practical steps for improving the likelihood of replication and the chances of validating a study by reporting key factors.

Specialist degree in education, Eastern Illinois University. / Includes bibliographical references (leaves 35-36).

Thesis (Ph. D.)--University of Nevada, Reno, 2005. / "August 2005." Includes bibliographical references. Online version available on the World Wide Web. Library also has microfilm. Ann Arbor, Mich. : ProQuest Information and Learning Company, [2005]. 1 microfilm reel ; 35 mm.

A study was conducted to quantify weather conditions at specific growth stages of Canadian western Spring wheat (Triticum aestivum) and relate those growing conditions to variations in wheat grade and quality characteristics and to develop pre-harvest prediction models for wheat quality using weather input data. Six Canadian western spring wheat genotypes were grown in five locations across the Canadian prairies during the 2003 and 2004 growing seasons. Intensive weather data was collected during the growing season at each location and used to calculate accumulated heat stress, useful heat, moisture demand, moisture supply, moisture use and moisture stress variables for numerous crop development stages. Grain samples were graded, milled and underwent an extensive analysis of flour, dough, and bread making quality. ANOVA indicated that genotype, environment and their interactions had significant effects on most quality parameters tested. Environmental contribution to wheat quality variance was considerably larger than the variance contribution of either genotype or GxE interaction. Using the weather and crop development stage information, significant regression equations with high regression coefficients were developed for most quality parameters using just a single independent weather variable. Multiple regression equations with even higher R2 values were developed using three complex weather variables, leading to the opportunity to predict wheat quality 2-5 weeks prior to harvest. Equally strong prediction models were developed utilizing basic weather variables which could be obtained from weather stations monitoring only daily maximum and minimum air temperature and precipitation. The development periods of planting to jointing and anthesis to soft dough were the stages most frequently exhibiting the highest correlation to wheat quality indicating weather needs to be monitored during the entire growing season to accurately predict quality. Grain quality forecast models were validated using 2005 weather and crop data. Prediction models developed from the 2003 and 2004 data required modification in order to accurately and consistently predict the grain properties in 2005. / February 2007

If the primary sequence of a protein is known, what is its three-dimensional structure? This is one of the most challenging problems in molecular biology and has many applications in proteomics. During the last three decades, this issue has been extensively researched. Techniques such as the protein folding approach have been demonstrated to be promising in predicting the core areas of proteins - α-helices and β-strands. However, loops that contain no regular units of secondary structure elements remain the most difficult regions for prediction. The protein loop prediction problem is to predict the spatial structure of a loop given the primary sequence of a protein and the spatial structures of all the other regions. There are two major approaches used to conduct loop prediction – the ab initio folding and database searching methods. The loop prediction accuracy is unsatisfactory because of the hypervariable property of the loops. The key contribution proposed by this thesis is a novel fragment assembly algorithm using branch-and-cut to tackle the loop prediction problem. We present various pruning rules to reduce the search space and to speed up the finding of good loop candidates. The algorithm has the advantages of the database-search approach and ensures that the predicted loops are physically reasonable. The algorithm also benefits from ab initio folding since it enumerates all the possible loops in the discrete approximation of the conformation space. We implemented the proposed algorithm as a protein loop prediction tool named LoopLocker. A test set from CASP6, the world wide protein structure prediction competition, was used to evaluate the performance of LoopLocker. Experimental results showed that LoopLocker is capable of predicting loops of 4, 8, 11-12, 13-15 residues with average RMSD errors of 0.452, 1.410, 1.741 and 1.895 A respectively. In the PDB, more than 90% loops are fewer than 15 residues. This concludes that our fragment assembly algorithm is successful in tackling the loop prediction problem.

Epilepsy is a nervous system disorder which affects approximately 1% of the world's population. Nearly 25% of people who have epilepsy are resistant to traditional treatments such as medication and are not candidates for surgery [32]. A new form of treatment has emerged that attempts to disrupt epileptic activity in the brain by electrically stimulating neural tissue. However, the nature of this treatment requires that it is able to accurately predict the onset of a seizure in order to time the intervention correctly. Recent studies suggest that EEG recordings may be generated by a low dimensional nonlinear process [35] [36] [6]. This paper will investigate nonlinearity tests, as well as the use of methods from the theory of nonlinear dynamical systems in the prediction of seizures or seizure like events (SLEs) from complex time series. To do this data is generated from a nonlinear dynamical system with a stochastic time dependent parameter, which attempts to emulate the different states of an epileptic brain. Two kinds of nonlinearity tests were used in simulations, one which specifies a model in the alternative hypothesis (Keenans test) and one which simply states that the process is `not linear' (Surrogate data test). The tests were applied to the generated data, as well as a short EEG recording from a person with epilepsy and a simple nonstationary example. Both tests were able to correctly identify the model as nonlinear, neither test identified the EEG data as nonlinear and there were contradicting results when the tests were applied to nonstationary data. Estimates of the correlation dimension and Lyapunov exponent were then used to classify the preictal state of the model data. Correlation dimensions showed the best ability to classify states, so they were used in the prediction algorithm. The results of the simulation was that the correlation dimension was able to successfully predict half of the SLEs, however there was an alarmingly high false prediction rate. These results suggest that even though a complicated model may fit the data better, when dealing with prediction it is usually best to use a simple model. A simpler approach with better understood statistical properties may be able to improve on the prediction of SLEs as well as reduce the computational cost of performing them.

If the primary sequence of a protein is known, what is its three-dimensional structure? This is one of the most challenging problems in molecular biology and has many applications in proteomics. During the last three decades, this issue has been extensively researched. Techniques such as the protein folding approach have been demonstrated to be promising in predicting the core areas of proteins - α-helices and β-strands. However, loops that contain no regular units of secondary structure elements remain the most difficult regions for prediction. The protein loop prediction problem is to predict the spatial structure of a loop given the primary sequence of a protein and the spatial structures of all the other regions. There are two major approaches used to conduct loop prediction – the ab initio folding and database searching methods. The loop prediction accuracy is unsatisfactory because of the hypervariable property of the loops. The key contribution proposed by this thesis is a novel fragment assembly algorithm using branch-and-cut to tackle the loop prediction problem. We present various pruning rules to reduce the search space and to speed up the finding of good loop candidates. The algorithm has the advantages of the database-search approach and ensures that the predicted loops are physically reasonable. The algorithm also benefits from ab initio folding since it enumerates all the possible loops in the discrete approximation of the conformation space. We implemented the proposed algorithm as a protein loop prediction tool named LoopLocker. A test set from CASP6, the world wide protein structure prediction competition, was used to evaluate the performance of LoopLocker. Experimental results showed that LoopLocker is capable of predicting loops of 4, 8, 11-12, 13-15 residues with average RMSD errors of 0.452, 1.410, 1.741 and 1.895 A respectively. In the PDB, more than 90% loops are fewer than 15 residues. This concludes that our fragment assembly algorithm is successful in tackling the loop prediction problem.

Epilepsy is a nervous system disorder which affects approximately 1% of the world's population. Nearly 25% of people who have epilepsy are resistant to traditional treatments such as medication and are not candidates for surgery [32]. A new form of treatment has emerged that attempts to disrupt epileptic activity in the brain by electrically stimulating neural tissue. However, the nature of this treatment requires that it is able to accurately predict the onset of a seizure in order to time the intervention correctly. Recent studies suggest that EEG recordings may be generated by a low dimensional nonlinear process [35] [36] [6]. This paper will investigate nonlinearity tests, as well as the use of methods from the theory of nonlinear dynamical systems in the prediction of seizures or seizure like events (SLEs) from complex time series. To do this data is generated from a nonlinear dynamical system with a stochastic time dependent parameter, which attempts to emulate the different states of an epileptic brain. Two kinds of nonlinearity tests were used in simulations, one which specifies a model in the alternative hypothesis (Keenans test) and one which simply states that the process is `not linear' (Surrogate data test). The tests were applied to the generated data, as well as a short EEG recording from a person with epilepsy and a simple nonstationary example. Both tests were able to correctly identify the model as nonlinear, neither test identified the EEG data as nonlinear and there were contradicting results when the tests were applied to nonstationary data. Estimates of the correlation dimension and Lyapunov exponent were then used to classify the preictal state of the model data. Correlation dimensions showed the best ability to classify states, so they were used in the prediction algorithm. The results of the simulation was that the correlation dimension was able to successfully predict half of the SLEs, however there was an alarmingly high false prediction rate. These results suggest that even though a complicated model may fit the data better, when dealing with prediction it is usually best to use a simple model. A simpler approach with better understood statistical properties may be able to improve on the prediction of SLEs as well as reduce the computational cost of performing them.