Published papers

As a growing proportion of road bridges continue to age, the demand for automated crack inspection is becoming increasingly urgent. However, in automated crack detection for concrete bridge decks, reducing false negatives often leads to an increase in false positives, whereas suppressing false positives tends to increase the risk of missed detections. In addition, surface-specific noise in real inspection environments, such as color irregularities, structural boundaries, and efflorescence, frequently triggers spurious detections, making it difficult to achieve a level of performance suitable for field deployment. To address this challenge, this study proposes a two-stage penalty learning framework for semantic segmentation, in which false negatives (FNs) are heavily penalized during the early stage of training, followed by the introduction of Online Hard Negative Mining (OHNM) to suppress false positives. Comparative experiments using images acquired from actual bridge decks showed that the proposed method improved both IoU and F1 score. Furthermore, paired t-tests with Holm correction confirmed that these improvements were statistically significant. The proposed approach can therefore be regarded as a promising learning strategy for practical crack detection systems that must simultaneously cope with missed detections and false alarms.

In deep-learning-based concrete crack detection, degraded generalization on unseen bridges due to domain shift remains a major practical challenge. This study compares two robust training-data selection strategies: target-specific sampling, which prioritizes images with textures similar to the inference target, and cluster-balanced sampling, which ensures coverage of diverse background patterns through feature clustering. Bridge-wise cross-validation on real bridge-deck datasets revealed that target-specific sampling overfits to particular background features, leading to both missed detections (false negatives) and over-detections (false positives). In contrast, cluster-balanced sampling reduces reliance on specific textures by learning diverse background patterns, thereby suppressing missed detections and maintaining generalization performance on unseen bridges. These findings provide practical guidelines for constructing training datasets that enhance the reliability of AI models for infrastructure inspection.

Nowadays there is increased need for utilizing big data efficiently. In addition to using data to provide new information, combining various data sources can help create value-added information which provides new insights. In medical safety, there is increased attention for big data applications in healthcare and medical safety. Medical safety is supported by applying big data to the medical research fields. After considering the overall configuration of current system different applications were proposed. Because the database environment is not in place, authors could not consider the system in operational use, however researchers examined each application and formulated future policy.

Public services, for example Railroad service and hospital service, have carried out safety activities to provide safety service for users aiming “accident zero”. However, safety activities can’t go well in the actual enterprises. For the reason why safe activity can’t work, it is caused by the fact that employees’ motivation to safety activities decreases. However, the safe managers misunderstand it caused by a lowering of the safe consciousness of the employees and perform activity for the purpose of the improvement of the safe consciousness. Therefore, the safe activity in the actual enterprises cannot be readily activated by employees because of the gap of the recognition of the safe managers. We suggest that managers should evaluate the safety of the public service by an enhancement degree of the safety activity instead of employee’s safe consciousness in the enterprise. And, this study shows that the safe managers should expand new explanation to employees when I they teach how to do safety activities.

超音波探傷試験におけるヒューマンエラーと作業姿勢との関係を明らかにし、望ましい作業姿勢の提案を図った

非破壊検査の一つである超音波探傷試験におけるヒューマンエラーと作業者の上腕部との関係を明らかにした