Patrick Mäder

Software traceability: trends and future directions

Software traceability is a sought-after, yet often elusive quality in software-intensive systems. Required in safety-critical systems by many certifying bodies, such as the USA Federal Aviation Authority, software traceability is an essential element of the software development process. In practice, traceability is often conducted in an ad-hoc, after-the-fact manner and, therefore, its benefits are not always fully realized. Over the past decade, researchers have focused on specific areas of the traceability problem, developing more sophisticated tooling, promoting strategic planning, applying information retrieval techniques capable of semi-automating the trace creation and maintenance process, developing new trace query languages and visualization techniques that use trace links, and applying traceability in specific domains such as Model Driven Development, product line systems, and agile project environments. In this paper, we build upon a prior body of work to highlight the state-of-the-art in software traceability, and to present compelling areas of research that need to be addressed.

Motivation Matters in the Traceability Trenches

Reports from the field are few and far between when it comes to traceability. As a community, we know little more about the traceability practice in companies today than we did a decade ago. This paper reports on findings from a practitioner survey designed to get a high-level update on traceability practice and problems. What emerges is the importance of the prevailing motivation underlying traceability adoption in an organization and we characterize this in four ways. We use these perspectives to discuss our findings and their implications.

Mind the gap: assessing the conformance of software traceability to relevant guidelines

Many guidelines for safety-critical industries such as aeronautics, medical devices, and railway communications, specify that traceability must be used to demonstrate that a rigorous process has been followed and to provide evidence that the system is safe for use. In practice, there is a gap between what is prescribed by guidelines and what is implemented in practice, making it difficult for organizations and certifiers to fully evaluate the safety of the software system. In this paper we present an approach, which parses a guideline to extract a Traceability Model depicting software artifact types and their prescribed traces. It then analyzes the traceability data within a project to identify areas of traceability failure. Missing traceability paths, redundant and/or inconsistent data, and other problems are highlighted. We used our approach to evaluate the traceability of seven safety-critical software systems and found that none of the evaluated projects contained traceability that fully conformed to its relevant guidelines.

Enabling Automated Traceability Maintenance through the Upkeep of Traceability Relations

Traceability is demanded within mature development processes and offers a wide range of advantages. Nevertheless, there are deterrents to establishing traceability: it can be painstaking to achieve initially and then subject to almost instantaneous decay. To be effective, this is clearly an investment that should be retained. We therefore focus on reducing the manual effort incurred in performing traceability maintenance tasks. We propose an approach to recognize those changes to structural UML models that impact existing traceability relations and, based upon this knowledge, we provide a mix of automated and semi-automated strategies to update these relations. This paper provides technical details on the update process; it builds upon a previous publication that details how triggers for these updates can be recognized in an automated manner. The overall approach is supported by a prototype tool and empirical results on the effectiveness of tool-supported traceability maintenance are provided.

Enabling Automated Traceability Maintenance by Recognizing Development Activities Applied to Models

For anything but the simplest of software systems, the ease and costs associated with change management can become critical to the success of a project. Establishing traceability initially can demand questionable effort, but sustaining this traceability as changes occur can be a neglected matter altogether. Without conscious effort, traceability relations become increasingly inaccurate and irrelevant as the artifacts they associate evolve. Based upon the observation that there are finite types of development activity that appear to impact traceability when software development proceeds through the construction and refinement of UML models, we have developed an approach to automate traceability maintenance in such contexts. Within this paper, we describe the technical details behind the recognition of these development activities, a task upon which our automated approach depends, and we discuss how we have validated this aspect of the work to date.

Rule-Based Maintenance of Post-Requirements Traceability Relations

An accurate set of traceability relations between software development artifacts is desirable to support evolutionary development. However, even where an initial set of traceability relations has been established, their maintenance during subsequent development activities is time consuming and error prone, which results in traceability decay. This paper focuses solely on the problem of maintaining a set of traceability relations in the face of evolutionary change, irrespective of whether generated manually or via automated techniques, and it limits its scope to UML-driven development activities post-requirements specification. The paper proposes an approach for the automated update of existing traceability relations after changes have been made to UML analysis and design models. The update is based upon predefined rules that recognize elementary change events as constituent steps of broader development activities. A prototype traceMaintainer has been developed to demonstrate the approach. Currently, traceMaintainer can be used with two commercial software development tools to maintain their traceability relations. The prototype has been used in two experiments. The results are discussed and our ongoing work is summarized.

Do developers benefit from requirements traceability when evolving and maintaining a software system

Software traceability is a required component of many software development processes. Advocates of requirements traceability cite advantages like easier program comprehension and support for software maintenance (i.e., software change). However, despite its growing popularity, there exists no published evaluation about the usefulness of requirements traceability. It is important, if not crucial, to investigate whether the use of requirements traceability can significantly support development tasks to eventually justify its costs. We thus conducted a controlled experiment with 71 subjects re-performing real maintenance tasks on two third-party development projects: half of the tasks with and the other half without traceability. Subjects sketched their task solutions on paper to focus on the their ability to solving the problems rather than their programming skills. Our findings show that subjects with traceability performed on average 24 % faster on a given task and created on average 50 % more correct solutions—suggesting that traceability not only saves effort but can profoundly improve software maintenance quality.

Design pattern recovery based on annotations

Design patterns have been widely used for developing flexible, extensible and perceptible applications to produce effective, reliable, verifiable and easily maintained software systems. The main advantage of using patterns is to take the edge of using best practices and experiences of others in solving the challenging tasks. Patterns have been extensively tested in different applications and reusing them yields the quality software. In this paper, we present a design pattern recovery approach based on annotations, regular expressions and database queries. We define the varying features of patterns and apply rules to match these features with the source code elements. Our novel approach reduces the search space and time for detecting patterns by using appropriate semantics of annotations from large legacy systems. We have tested our approach as proof of concept on motivating examples, and the obtained results are very encouraging.

An empirical study on project-specific traceability strategies

Effective requirements traceability supports practitioners in reaching higher project maturity and better product quality. Researchers argue that effective traceability barely happens by chance or through ad-hoc efforts and that traceability should be explicitly defined upfront. However, in a previous study we found that practitioners rarely follow explicit traceability strategies. We were interested in the reason for this discrepancy. Are practitioners able to reach effective traceability without an explicit definition? More specifically, how suitable is requirements traceability that is not strategically planned in supporting a projects development process. Our interview study involved practitioners from 17 companies. These practitioners were familiar with the development process, the existing traceability and the goals of the project they reported about. For each project, we first modeled a traceability strategy based on the gathered information. Second, we examined and modeled the applied software engineering processes of each project. Thereby, we focused on executed tasks, involved actors, and pursued goals. Finally, we analyzed the quality and suitability of a projects traceability strategy. We report common problems across the analyzed traceability strategies and their possible causes. The overall quality and mismatch of analyzed traceability suggests that an upfront-defined traceability strategy is indeed required. Furthermore, we show that the decision for or against traceability relations between artifacts requires a detailed understanding of the projects engineering process and goals; emphasizing the need for a goal-oriented procedure to assess existing and define new traceability strategies.

Plant species classification using flower images—A comparative study of local feature representations

Steady improvements of image description methods induced a growing interest in image-based plant species classification, a task vital to the study of biodiversity and ecological sensitivity. Various techniques have been proposed for general object classification over the past years and several of them have already been studied for plant species classification. However, results of these studies are selective in the evaluated steps of a classification pipeline, in the utilized datasets for evaluation, and in the compared baseline methods. No study is available that evaluates the main competing methods for building an image representation on the same datasets allowing for generalized findings regarding flower-based plant species classification. The aim of this paper is to comparatively evaluate methods, method combinations, and their parameters towards classification accuracy. The investigated methods span from detection, extraction, fusion, pooling, to encoding of local features for quantifying shape and color information of flower images. We selected the flower image datasets Oxford Flower 17 and Oxford Flower 102 as well as our own Jena Flower 30 dataset for our experiments. Findings show large differences among the various studied techniques and that their wisely chosen orchestration allows for high accuracies in species classification. We further found that true local feature detectors in combination with advanced encoding methods yield higher classification results at lower computational costs compared to commonly used dense sampling and spatial pooling methods. Color was found to be an indispensable feature for high classification results, especially while preserving spatial correspondence to gray-level features. In result, our study provides a comprehensive overview of competing techniques and the implications of their main parameters for flower-based plant species classification.