The reliability of the insulator has directly affected the stable operation of electric power system. The detection of defective insulators has always been an important issue in smart grid systems. However, the traditional transmission line detection method has low accuracy and poor real-time performance. We present an insulator defect detection method based on CenterNet. In order to improve detection efficiency, we simplified the backbone network. In addition, an attention mechanism is utilized to suppress useless information and improve the accuracy of network detection. In image preprocessing, the blurring of some detected images results in the samples being discarded, so we use super-resolution reconstruction algorithm to reconstruct the blurred images to enhance the dataset. The results show that the AP of the proposed method reaches 96.16% and the reasoning speed reaches 30FPS under the test condition of NVIDIA GTX 1080 test conditions. Compared with Faster R-CNN, YOLOV3, RetinaNet and FSAF, the detection accuracy of proposed method is greatly improved, which fully proves the effectiveness of the proposed method.
Download full-text PDF |
Source |
---|---|
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8320933 | PMC |
http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0255135 | PLOS |
Biometrics
October 2024
RAND Corporation, Pittsburgh, PA 15213, United States.
Health care decisions are increasingly informed by clinical decision support algorithms, but these algorithms may perpetuate or increase racial and ethnic disparities in access to and quality of health care. Further complicating the problem, clinical data often have missing or poor quality racial and ethnic information, which can lead to misleading assessments of algorithmic bias. We present novel statistical methods that allow for the use of probabilities of racial/ethnic group membership in assessments of algorithm performance and quantify the statistical bias that results from error in these imputed group probabilities.
View Article and Find Full Text PDFJ Morphol
January 2025
Dpto. de Medicina Interna, Hospital Universitario de Canarias, Universidad de La Laguna, La Laguna, Spain.
Anatomical variants can be used effectively to identify relationships between individuals in kinship analysis and they may be useful during surgical procedures. These procedures can be better implemented when the cause, appearance and location are understood. Clear representations and definitions of anatomical traits are necessary.
View Article and Find Full Text PDFChemistry
December 2024
East China University of Science and Technology, School of Materials Science and Engineering, meilong Road, 200237, shanghai, CHINA.
Perovskite-based photodetectors (PDs) are broadly utilized in optical communication, non-destructive testing, and smart wearable devices due to their ability to convert light into electrical signals. However, toxicity and instability hold back their mass production and commercialization. The lead-free Cs2AgBiBr6 double perovskite film, promised to be an alternative, is fabricated by electrophoretic deposition (EPD), which compromises film quality.
View Article and Find Full Text PDFJ Oral Implantol
December 2024
Department of Post-Graduation, Latin American Institute of Dental Research and Education (ILAPEO), Curitiba, Paraná, Brazil.
Full-arch implant rehabilitation in extremely atrophic edentulous mandibles is still challenging due to the high risk of fracture and the limited bone availability. The approach proposes using short implants with immediate loading for final prostheses as a treatment option, which offers shorter treatment times and fewer invasive procedures. A 66-year-old female patient with an edentulous mandible and severe alveolar bone resorption was treated with four short implants in the interforaminal area.
View Article and Find Full Text PDFNord J Psychiatry
December 2024
Department of Psychiatry, Psychiatric Centre Copenhagen, Copenhagen, Denmark.
Background: Reliable gender-sensitive normative data is needed to facilitate mental health research and clinical utility of commonly used symptoms scales. This study establishes Danish gender-stratified norms for the 53-item and 18-item Brief Symptom Inventory (BSI-53, BSI-18), proposed attention deficit hyperactivity disorder (ADHD) symptomatology scales from the BSI-53, and the 10-item Symptom Checklist (SCL-10). This study also examines gender-differences in symptom reporting of the ADHD and SCL-10 scales, and assesses potential bias in recent SCL-10 norms.
View Article and Find Full Text PDFEnter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!