Convolutional Neural Networks For Apical Lesion Segmentation From Panoramic Radiographs

Convolutional neural networks (CNNs) have rapidly emerged as one of the most promising next-generation artificial intelligence (AI) in the field of medical and dental researches, which can further provide an effective diagnostic methodology allowing for detection of diseases at early age. This study was, thus, aimed to evaluate performances for apical lesion segmentation from panoramic radiographs using two CNN algorithms including U-Net and FPN. A total of 1000 panoramic radiographs showing apical lesions were separated into training (n = 800, 80%), validation (n = 100, 10%), and test (n = 100, 10%) dataset, respectively. These datasets were further incorporated to construct CNN models using two algorithms, respectively. The performances of identifying apical lesions were evaluated after calculating precision, recall, and F1-score from both CNN models. Both U-Net and FPN algorithms provided considerably good performances in identifying apical lesions in panoramic radiographs.

Aircraft system-level diagnosis with emphasis on maintenance decisions

This paper proposes a diagnostic technique that can predict component degradation for a number of complex systems. It improves and clarifies the capabilities of a previously proposed diagnostic approach, by identifying the degradation severity of the examined components, and uses a 3D Principal Component Analysis approach to provide an explanation for the observed diagnostic accuracy. The diagnostic results are then used, in a systematic way, to influence maintenance decisions. Having been developed for the Auxiliary Power Unit (APU), the flexibility and power of the diagnostic methodology is shown by applying it to a completely new system, the Environmental Control System (ECS). A major conclusion of this work is that the proposed diagnostic approach is able to correctly predict the health state of two aircraft systems, and potentially many more, even in cases where different fault combinations result in similar fault patterns. Based on the engineering simulation approach verified here, a diagnostic methodology suitable from aircraft conception to retirement is proposed.

Characteristics of pre-school children’s creative activity

The article deals with the problem of preschool children’ formation of the creative activity. The author understands creative activity as integrative, qualitative characteristic of personality, which includes a complex of motivational, creative, volitional components. According to the selected indicators, a diagnostic methodology for the three main blocks was constructed. All indicators were evaluated by a 3-point system, in which each score expressed the content of the existing level of formation of diagnosed indicators. Four levels of creative activity of older preschool children are distinguished: high (creative), middle (research), below average (imitative), low (performing). It is established that the most unformed components of creative activity in preschool age are creative and volitional. It is substantiated that development of speed, flexibility and originality of thinking, as well as stimulation of children’s initiative and independence will allow to increase the level of creative activity.