Many systems in our daily lives control physical processes, which are parametrized and adapted, such as heating systems in buildings. Faults and non-optimized settings lead to a high energy demand and, therefore, need to be detected as early as possible. Unfortunately, due to specific adaptations, only the basic principles remain the same, but not the concrete implementations, making the use of techniques like machine learning difficult. Therefore, we suggest using abstract models that cover the basic behavior in a way that allows us to reuse the models in different installations. In particular, we discuss the application of qualitative simulation for fault detection and introduce a formal definition of conformance between the results of qualitative simulation and the monitored behavior. We discuss arising difficulties and provide a basis for further research and applications.

Improving sustainability in the building sector requires more efficient operation of energy-intensive systems such as Heating, Ventilation, and Air Conditioning (HVAC). We present a novel diagnostic framework for HVAC systems that integrates Answer Set Programming (ASP) with Functional Event Calculus (FEC). Our approach exploits the declarative nature of ASP for modeling and incorporates FEC to capture temporal system dynamics. We demonstrate the feasibility of our approach through a case study on a real-world heating system, where we model key components and system constraints. Our evaluation on nominal and faulty traces shows that exploiting ASP in combination with FEC can identify plausible diagnoses. Moreover, we explore the difference between static and rolling-window strategies and provide insights into runtime versus soundness on those variants. Our work provides a step toward the practical application of ASP-based temporal reasoning in building diagnostics.

Peer code review is a key practice in professional software development, and its integration into computer science education can provide valuable learning experiences for students. However, few reports compare different peer code review methods within a single educational context. This experience report shares insights from implementing various review types-individual, team, and pair code reviews-in a first-year Data Structures and Algorithms course in a bachelor's degree program. Throughout the semester, students took an active role in their learning by completing three programming assignments, each followed by a different peer review method. Feedback was collected through questionnaires to capture the students' perceptions of their data structure knowledge, programming skills, and overall learning experience. Our report outlines the design of the different review learning activities, provides insights into the students' opinions on the review techniques, and reflects on the challenges and successes we encountered. As each method offers unique benefits, we believe that incorporating a variety of peer code review methods can enhance the overall learning experience in computer science courses.

Visualizations in teaching have become a common practice as they effectively convey theoretical concepts. Compiler construction, a heavily theory-based subject in computer science education, is particularly challenging for students to understand. While many tools simulate a compiler's front end, or analysis phase, applications that focus on the back end, or synthesis phase, are scarce. This paper describes VisOpt, a web-based visualization tool designed for a master's level Compiler Construction course. VisOptfocuses on the synthesis phase, i.e., code optimization and code generation. Its primary objective is to help students comprehend various local compiler optimizations, which can be visualized on the original code, an intermediate representation, or an assembler-like target code. A quasi-experiment with a pre-test-post-test design revealed that students who used VisOpt reported higher self-efficacy compared to those who did not. Although no significant improvement in learning outcomes was observed overall, we propose VisOpt as an engaging pedagogical tool that effectively complements traditional methods for teaching the synthesis phase of compilers.

Abstract As software projects evolve and grow in size and complexity, so do their test suites. Test suite reduction (TSR) aims at reducing the size of a test suite by removing redundant and obsolete test cases based on a coverage metric while preserving its fault detection capabilities. The contributions of this paper are twofold: (1) We examine a lesser‐known coverage criterion, that is, checked coverage. Checked coverage not only investigates if a part of the code was executed but also if it was checked by a test oracle. In an empirical evaluation, we performed TSR based on different reduction algorithms, coverage metrics, and open‐source Java projects with our own TSR tool to determine the most effective and efficient combination of metric and method. (2) Given the results of the first evaluation, we further investigate the potential of parameter optimization in regard to a genetic reduction algorithm. In particular, we focus on finding a general setting for the parameters crossover rate and mutation rate such that test suites can be reduced in a reasonable time while maintaining a high fault detection power.

As the size of software projects increases, their test suites usually grow accordingly. Test suite size, however, has a direct impact on the efficiency of software testing. Hence, test suite reduction (TSR) procedures aim at removing redundant test cases while maintaining the suites fault detection capabilities (FDC). This paper explores checked coverage as a coverage metric for TSR; checked coverage not only investigates if a part of code was executed but also if it was checked by a test oracle. Previously, this metric has been applied successfully as an indicator for oracle quality. To assess how suitable checked coverage is in comparison to traditional metrics, such as line or method coverage, we developed a TSR tool for Java programs. In an empirical evaluation, we performed TSR based on different reduction algorithms, coverage metrics, and open-source Java projects. Our study investigates both the efficiency of the TSR as well as effectiveness in regard to the FDC and size of the reduced test suites.

Abstract Abductive inference derives explanations for encountered anomalies and thus embodies a natural approach for diagnostic reasoning. Yet its computational complexity, which is inherent to the expressiveness of the underlying theory, remains a disadvantage. Even when restricting the representation to Horn formulae the problem is NP-complete. Hence, finding procedures that can efficiently solve abductive diagnosis problems is of particular interest from a research as well as practical point of view. In this paper, we aim at providing guidance on choosing an algorithm or tool when confronted with the issue of computing explanations in propositional logic-based abduction. Our focus lies on Horn representations, which provide a suitable language to describe most diagnostic scenarios. We illustrate abduction via two contrasting problem formulations: direct proof methods and conflict-driven techniques. While the former is based on determining logical consequences, the later searches for suitable refutations involving possible causes. To reveal runtime performance trends we conducted a case study, in which we compared publicly available general purpose tools, established Horn reasoning engines, as well as new variations of known methods as a means for abduction.

The complexity of technical systems requires increasingly advanced fault diagnosis methods to ensure safety and reliability during operation. Particularly in domains where maintenance constitutes an extensive portion of the entire operation cost, efficient and effective failure identification holds the potential to provide large economic value. Abduction offers an intuitive concept for diagnostic reasoning relying on the notion of logical entailment. Nevertheless, abductive reasoning is an intractable problem and computing solutions for instances of reasonable size and complexity persists to pose a challenge. In this paper, we investigate algorithm selection as a mechanism to predict the “best” performing technique for a specific abduction scenario within the framework of model-based diagnosis. Based on a set of structural attributes extracted from the system models, our meta-approach trains a machine learning classifier that forecasts the most runtime efficient abduction technique given a new diagnosis problem. To assess the predictor’s selection capabilities and the suitability of the meta-approach in general, we conducted an empirical analysis featuring seven abductive reasoning approaches. The results obtained indicate that applying algorithm selection is competitive in comparison to always choosing a single abductive reasoning method.