In the field of software development, debugging is a crucial yet challenging skill, particularly for novice programmers. This study evaluates the efficacy of systematic debugging education in enhancing students’ debugging skills through two experimental phases. The first experiment involved 31 CS II students tackling debugging problems without prior instruction. The second experiment involved a different group of 59 students who received structured debugging instruction before engaging with similar debugging problems. The research aims to address the differences in debugging performance before and after the introduction of systematic debugging strategies, and the specific challenges faced by novice programmers in identifying and fixing various types of bugs. The results indicate significant improvements post-instruction, with the median correctness level rising from 60% to 80% and the median time to complete tasks decreasing from 28.7 minutes to 10.7 minutes. Further analysis revealed that certain bugs, such as division by integers and misusing switch statements, posed greater challenges initially but showed marked improvement post-instruction. This study underscores the transformative impact of systematic debugging education on novice programmers, enhancing both their accuracy and efficiency in debugging tasks.

Metaheuristic methods have demonstrated their utility in tackling global optimization problems with and without constraints. However, existing state-of-the-art (SOTA) algorithms often suffer from limitations such as premature convergence, inefficient exploration-exploitation balance, and poor adaptability to complex discrete optimization problems like Team Formation (TF). The Golden Eagle Optimizer (GEO) algorithm is a promising metaheuristic that addresses some of these challenges by effectively managing its hunting spiral motion using two control parameters: cruise (exploration) and attack (exploitation). Despite its strengths, the standard GEO algorithm requires modifications to handle the discrete and multi-objective nature of the TF problem effectively. This paper proposes an amended version of GEO, called AGEO, which integrates specialized operators to enhance its performance in TF scenarios. A skillful TF aims to form teams of experts with complementary skills in social networks (SN) while optimizing multiple objectives, including minimizing communication costs, maximizing the similarity score between team members, and achieving minimal team cardinality. AGEO preserves GEO’s powerful exploitation and exploration mechanisms while introducing tailored operator strategies to overcome the challenges inherent in TF. The AGEO undergoes testing on several well-established benchmark datasets, including Universiti Malaysia Pahang (UMP), Internet Movie Database (IMDB), Association for Computing Machinery (ACM), and Database Systems & Logic Programming (DBLP). Additionally, a comparative study against SOTA metaheuristic algorithms such as Particle Swarm Optimization (PSO), Butterfly Optimization Algorithm (BOA), Crow Search Algorithm (CSA), and Jaya Algorithm demonstrates AGEO’s superior performance in forming highly optimized teams with the least communication cost, lowest team cardinality, and highest similarity score.

Building defect datasets are slow to assemble and expensive to label, and indoors there is the added problem of photographing people’s homes. Text-to-image models look like an easy way round this, but it has not been shown that a classifier trained on generated pictures will recognise defects in real ones. We repeated an earlier experiment on three moisture-related indoor defects (damp, mould and paint deterioration) in two arms. The same ImageNet pre-trained VGG-16 network, set up as in the earlier study apart from the number of epochs, was trained once on real, manually collected and labelled images and once on AI-generated images (Stable Diffusion XL 1.0). Tested on images from its own domain, the synthetic-trained model scored 91.7% accuracy (macro-F1 0.918, n = 303) and the real-trained model 83.2% (macro-F1 0.832, n = 559). That comparison is misleading: the test sets differ, and the synthetic test images share a generator with the synthetic training images. On a common set of 150 real photographs (50 per class), the real-trained model reached 82.0%, while the synthetic-trained model reached only 45.3% (95% confidence intervals 75.1–87.3% and 37.6–53.3%). Recall for damp fell to 8%; mould held at 92%. In the configuration we tested, AI-generated images did not work as a stand-alone replacement for real annotated images, and the apparent advantage over manual labelling disappeared on real photographs. We suggest treating synthetic images as a supplement to real data, and testing any synthetic-trained model on real images.