On the effectiveness of early life cycle defect prediction with Bayesian Nets

Standard practice in building models in software engineering normally involves three steps: collecting domain knowledge (previous results, expert knowledge); building a skeleton of the model based on step 1 including as yet unknown parameters; estimating the model parameters using historical data. Our experience shows that it is extremely difficult to obtain reliable data of the required granularity, or of the required volume with which we could later generalize our conclusions. Therefore, in searching for a method for building a model we cannot consider methods requiring large volumes of data. This paper discusses an experiment to develop a causal model (Bayesian net) for predicting the number of residual defects that are likely to be found during independent testing or operational usage. The approach supports (1) and (2), does not require (3), yet still makes accurate defect predictions (an R ² of 0.93 between predicted and actual defects). Since our method does not require detailed domain knowledge it can be applied very early in the process life cycle. The model incorporates a set of quantitative and qualitative factors describing a project and its development process, which are inputs to the model. The model variables, as well as the relationships between them, were identified as part of a major collaborative project. A dataset, elicited from 31 completed software projects in the consumer electronics industry, was gathered using a questionnaire distributed to managers of recent projects. We used this dataset to validate the model by analyzing several popular evaluation measures (R ², measures based on the relative error and Pred). The validation results also confirm the need for using the qualitative factors in the model. The dataset may be of interest to other researchers evaluating models with similar aims. Based on some typical scenarios we demonstrate how the model can be used for better decision support in operational environments. We also performed sensitivity analysis in which we identified the most influential variables on the number of residual defects. This showed that the project size, scale of distributed communication and the project complexity cause the most of variation in number of defects in our model. We make both the dataset and causal model available for research use.     

Thermal convection in a horizontal porous layer with spatially periodic boundary temperatures: small Ra flow

This study considers a small Rayleigh number thermal convection in a fluid-saturated porous medium between two infinite-horizontal walls. The lower and upper walls have sinusoidal temperature distributions with a wave number and a phase difference, and the effect of the parameters on the flow and heat transfer characteristics is investigated. For a given wave number, an out-of-phase configuration yields minimum heat transfer at the walls. Maximum heat transfer occurs at the wave number of 2.286 with an in-phase configuration.     

"The association between emotional upset and cardiac arrhythmia during daily life": Correction to Carels et al. (2003).

Reports an error in the original article by R. A. Carels et al (Journal of Consulting & Clinical Psychology, 2003[Jun], Vol 71[3], 613-618). On page 615, Lines 18, 20, 22, of Table 1, the data in the rows that read "Tachycardia in min per hr," "Repetitive PVCs per hr," and "PVCs per hr" are incorrectly reported in the n and % columns. They should have been reported in the M and SD columns. The corrected table is provided. (The following abstract of this article originally appeared in record 2003-00756-023.) Ventricular arrhythmia exhibits considerable within-subject variability that cannot be attributed to clinical status alone. This investigation examined the extent to which cardiac arrhythmia was associated with psychological and physical factors assessed during the hour preceding arrhythmic or nonarrhythmic activity. Approximately twice hourly, 46 patients randomly completed a diary assessing mood and physical symptoms during 24-hr electrocardiographic monitoring. Greater negative emotion was associated with increased arrhythmia. Additionally, greater negative emotion was significantly associated with increased arrhythmia among participants in a low left ventricular ejection fraction group (LVEF). However, this relationship between negative emotion and arrhythmia was not... (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Flavor Fade in Peanuts During Short-term Storage

ABSTRACT: Flavor characteristics of roasted peanuts over short-term storage were explored through sensory and chemical analyses. The volatiles from freshly roasted peanuts were evaluated over short-time (21 d) storage using gas chromatography, chemosensory techniques, and a sensory panel to quantify and identify pyrazines and hexanal over a 21-d storage period. A significant decrease ( P < 0.05) was noted in 2,3-diethylpyrazine, 2-methoxypyrazine, 2,3-dimethylpyrazine, 2-ethyl-3-methylpyrazine, and 2,3,5-trimethylpyrazine concentrations over a 21-d period. No significant difference ( P > 0.05) was noted in the 2-methylpyrazine and 2-ethylpyrazine concentrations. The hexanal concentration significantly increased ( P < 0.05) over the 21-d period. The peroxide values and sensory analysis agreed with these results. A significant increase ( P < 0.05) in peroxide value was seen at days 14 and 21, and a significant decrease ( P < 0.05) in fresh roasted peanuty flavor from day 0 to 21 and significant increases ( P < 0.05) in painty, cardboardy, and bitter flavors from day 7 to 21 with the sensory analysis. The electronic nose successfully separated day 0 and 21 samples from day 7 and 14 samples, which were also separated but with some overlap.     

Mathematical Relationship Between Surface Emission and Diffusion Coefficients

This naver analvzes the surface emission coefficient corresponding to anv diffusion coefficient expressed as an exponential function of the concentration diffusing substance in capillary porous solids. Theoretical equations for surface emission coefficient for both sorption and desorption are presented. Procedures to derive the diffusion coefficient and to verify the corresponding surface emission coefficient are made using experimental sorption data of aspen (Populur sp.) wood. It is of interest to note that the theoretical models for diffusion and surface emission coefficients can be established and/or evaluated using the same set of experimental dara.     

Trimethylpentanediol dibenzoate: New plasticizer for plastisol screen ink

Trimethylpentane diol (TMPD) dibenzoate use in vinyl as a plasticizer is not well recognized, and little has been published on vinyl performance characteristics. To assess new applications for vinyl, a basic evaluation was conducted. Based on the results of the screen and other considerations an evaluation for utility in plastisol silk screen ink was conducted. The results indicated that the TMPD dibenzoate performed very well in white ink, requiring good fabric dye bleed resistance compared to polymeric and phthalates currently being used for non-bleed ink. Non-bleed characteristics are important for colored tee shirt printing. The benzoate is a good solvator and has excellent extraction resistance.     

Valid parameter range analyses for chemical reaction kinetic models

The present work quantifies the relations between the structure of a chemical reaction kinetic model, its valid parameter range, and the truncation error tolerance of the model. General methods are presented to solve the three important problems of valid parameter range analysis: (1) identification of the valid parameter range of a kinetic model, (2) estimation of the error tolerance required when applying a kinetic model over a specified parameter range, and (3) improvement of existing model generation algorithms to construct more robust models. Finally, the relationship between a model's structure, its valid parameter range, and the truncation error tolerance are illustrated by the flexibility-tolerance-model graph. The new methods are applied to pyrolysis of methane/ethane mixtures.