Locally linear reconstruction for instance-based learning

Instance-based learning (IBL), so called memory-based reasoning (MBR), is a commonly used non-parametric learning algorithm. k-nearest neighbor (k-NN) learning is the most popular realization of IBL. Due to its usability and adaptability, k-NN has been successfully applied to a wide range of applications. However, in practice, one has to set important model parameters only empirically: the number of neighbors (k) and weights to those neighbors. In this paper, we propose structured ways to set these parameters, based on locally linear reconstruction (LLR). We then employed sequential minimal optimization (SMO) for solving quadratic programming step involved in LLR for classification to reduce the computational complexity. Experimental results from 11 classification and eight regression tasks were promising enough to merit further investigation: not only did LLR outperform the conventional weight allocation methods without much additional computational cost, but also LLR was found to be robust to the change of k.     

A superscalar simulation employing poisson distributed stalls

This paper presents a statistical approach to estimating the performance of a superscalar processor. Traditional trace-driven simulators can take a large amount time to conduct a performance evaluation of a machine, especially as the number of instructions increases. The result of this type of simulation is typically tied to the particular trace that was run. Elements such as dependencies, delays, and stalls are all a direct result of the particular trace being run, and can differ from trace to trace. This paper describes a model designed to separate simulation results from a specific trace. Rather than running a trace-driven simulation, a statistical model is employed, more specifically a Poisson distribution, to predict how these types of delay affects performance. Through the use of this statistical model, a performance evaluation can be conducted using a general code model, with specific stall rates, rather than a particular code trace. This model allows simulations to quickly run tens of millions of instructions and evaluate the performance of a particular micro-architecture while at the same time, allowing the flexibility to change the structure of the architecture.     

Web proxy cache replacement scheme based on back-propagation neural network

Web proxy caches are used to reduce the strain of contemporary web traffic on web servers and network bandwidth providers. In this research, a novel approach to web proxy cache replacement which utilizes neural networks for replacement decisions is developed and analyzed. Neural networks are trained to classify cacheable objects from real world data sets using information known to be important in web proxy caching, such as frequency and recency. Correct classification ratios between 0.85 and 0.88 are obtained both for data used for training and data not used for training. Our approach is compared with Least Recently Used (LRU), Least Frequently Used (LFU) and the optimal case which always rates an object with the number of future requests. Performance is evaluated in simulation for various neural network structures and cache conditions. The final neural networks achieve hit rates that are 86.60% of the optimal in the worst case and 100% of the optimal in the best case. Byte-hit rates are 93.36% of the optimal in the worst case and 99.92% of the optimal in the best case. We examine the input-to-output mappings of individual neural networks and analyze the resulting caching strategy with respect to specific cache conditions.     

Distributing test cases more evenly in adaptive random testing

Adaptive random testing (ART) has recently been proposed to enhance the failure-detection capability of random testing. In ART, test cases are not only randomly generated, but also evenly spread over the input domain. Various ART algorithms have been developed to evenly spread test cases in different ways. Previous studies have shown that some ART algorithms prefer to select test cases from the edge part of the input domain rather than from the centre part, that is, inputs do not have equal chance to be selected as test cases. Since we do not know where the failure-causing inputs are prior to testing, it is not desirable for inputs to have different chances of being selected as test cases. Therefore, in this paper, we investigate how to enhance some ART algorithms by offsetting the edge preference, and propose a new family of ART algorithms. A series of simulations have been conducted and it is shown that these new algorithms not only select test cases more evenly, but also have better failure detection capabilities.     

The effectiveness of software metrics in identifying error-prone classes in post-release software evolution process

Many empirical studies have found that software metrics can predict class error proneness and the prediction can be used to accurately group error-prone classes. Recent empirical studies have used open source systems. These studies, however, focused on the relationship between software metrics and class error proneness during the development phase of software projects. Whether software metrics can still predict class error proneness in a system’s post-release evolution is still a question to be answered. This study examined three releases of the Eclipse project and found that although some metrics can still predict class error proneness in three error-severity categories, the accuracy of the prediction decreased from release to release. Furthermore, we found that the prediction cannot be used to build a metrics model to identify error-prone classes with acceptable accuracy. These findings suggest that as a system evolves, the use of some commonly used metrics to identify which classes are more prone to errors becomes increasingly difficult and we should seek alternative methods (to the metric-prediction models) to locate error-prone classes if we want high accuracy.     

Analyzing clusters of class characteristics in OO applications

The transition from Java 1.4 to Java 1.5 has provided the programmer with more flexibility due to the inclusion of several new language constructs, such as parameterized types. This transition is expected to increase the number of class clusters exhibiting different combinations of class characteristics. In this paper we investigate how the number and distribution of clusters are expected to change during this transition. We present the results of an empirical study were we analyzed applications written in both Java 1.4 and 1.5. In addition, we show how the variability of the combinations of class characteristics may affect the testing of class members.     

Segmented software cost estimation models based on fuzzy clustering

Parametric software cost estimation models are based on mathematical relations, obtained from the study of historical software projects databases, that intend to be useful to estimate the effort and time required to develop a software product. Those databases often integrate data coming from projects of a heterogeneous nature. This entails that it is difficult to obtain a reasonably reliable single parametric model for the range of diverging project sizes and characteristics. A solution proposed elsewhere for that problem was the use of segmented models in which several models combined into a single one contribute to the estimates depending on the concrete characteristic of the inputs. However, a second problem arises with the use of segmented models, since the belonging of concrete projects to segments or clusters is subject to a degree of fuzziness, i.e. a given project can be considered to belong to several segments with different degrees.This paper reports the first exploration of a possible solution for both problems together, using a segmented model based on fuzzy clusters of the project space. The use of fuzzy clustering allows obtaining different mathematical models for each cluster and also allows the items of a project database to contribute to more than one cluster, while preserving constant time execution of the estimation process. The results of an evaluation of a concrete model using the ISBSG 8 project database are reported, yielding better figures of adjustment than its crisp counterpart.     

Examining the significance of high-level programming features in source code author classification

The use of Source Code Author Profiles (SCAP) represents a new, highly accurate approach to source code authorship identification that is, unlike previous methods, language independent. While accuracy is clearly a crucial requirement of any author identification method, in cases of litigation regarding authorship, plagiarism, and so on, there is also a need to know why it is claimed that a piece of code is written by a particular author. What is it about that piece of code that suggests a particular author? What features in the code make one author more likely than another? In this study, we describe a means of identifying the high-level features that contribute to source code authorship identification using as a tool the SCAP method. A variety of features are considered for Java and Common Lisp and the importance of each feature in determining authorship is measured through a sequence of experiments in which we remove one feature at a time. The results show that, for these programs, comments, layout features and package-related naming influence classification accuracy whereas user-defined naming, an obvious programmer related feature, does not appear to influence accuracy. A comparison is also made between the relative feature contributions in programs written in the two languages.     

Avoiding semantic and temporal gaps in developing software intensive systems

Development of software intensive systems (systems) in practice involves a series of self-contained phases for the lifecycle of a system. Semantic and temporal gaps, which occur among phases and among developer disciplines within and across phases, hinder the ongoing development of a system because of the interdependencies among phases and among disciplines. Such gaps are magnified among systems that are developed at different times by different development teams, which may limit reuse of artifacts of systems development and interoperability among the systems. This article discusses such gaps and a systems development process for avoiding them.