Automatically analyzing panoramic dental X-rays through AI-based approaches has attracted attention and concern among dentists with the recent advancement of AI techniques. Recent studies have shown that these approaches have achieved high accuracy in recognizing and numbering teeth. However, the datasets utilized in such studies contain only a small proportion of panoramic X-rays that include missing teeth, despite such X-rays often being observed in actual diagnosis. Accordingly, the suitability of these approaches for practical panoramic X-rays remains unconfirmed. This study verifies the efficacy of three powerful and efficient object detection models for tooth numbering on panoramic X-rays with varying numbers of missing teeth. The experimental results indicate that the performance of AI models is affected by the existing tooth count appearing in panoramic X-ray dataset images, and images with a lower tooth count tend to exhibit a lower tooth-numbering accuracy that reaches a precision of 62.2%. Additionally, our study highlights the features in low tooth-count images that influence this accuracy. Our results thus also verify the unsuitability of AI models in numbering on panoramic X-ray images with a low tooth count. Importantly, this study suggests that disclosing the tooth count distribution of datasets is indispensable for proving the effectiveness of AI-based approaches in the tooth numbering task.
As the number of edge devices rapidly multiplies into the millions in the post-5G era, there is a simultaneous surge in demand for job execution driven by the data generated by these devices. Ultra-distributed computing systems have emerged to support this notable proliferation of interconnected devices and in addressing the unprecedented data generated over low-latency networks. To ensure the high availability and reliability of these systems, an efficient job scheduling method is required to schedule jobs across available resources. However, there are currently no large-scale benchmarks available to evaluate job scheduling methods. This paper introduces large-scale benchmarks of up to one million devices for job shop scheduling problems. We evaluate the makespan reduction of widely used combinatorial optimizations on these benchmarks, including simulated annealing, ant colony, tree Parzen search, particle swarm, artificial bee colony, cuckoo search, whale, grey wolf, firefly, and bat optimizations. We investigate the impact of execution time on finding the optimal makespan of job shop scheduling for each method. The experimental results can be used to guide the selection of a job scheduling method for particular applications.
Text-to-image models such as Stable Diffusion (SD) require comprehensive, fine-grained, and high-precision methods for evaluating text–image alignment. A prior method, the text–image alignment metric (TIAM), employs a template-based approach for fine-grained, high-precision evaluation; however, it is restricted to objects and colors, limiting its comprehensiveness. This study extends the TIAM by incorporating attention maps and vision–language models to deliver a fine-grained and high-precision evaluation framework that goes beyond colors and objects to include attributes, actions, and positions. In our experiments, we analyze the evaluation scores of images generated by the proposed method and compare them with human judgments. The results demonstrate that the proposed method outperforms existing methods, exhibiting a stronger correlation with human judgments (r = 0.853, ). In addition, we applied the proposed method to evaluate the generation abilities of three SD models (i.e., SD1.4, SD2, and SD3.5). Each experiment used over 900 images, totaling 9858 images across all experiments to ensure statistical significance. The results indicate that SD3.5 exhibits superior expressiveness compared with SD1.4 and SD2. Nevertheless, for more complex tasks such as multi-attribute generation or multi-action generation, limitations in text–image alignment remain evident.