RESUMO
Recently, pressure-sensing mats have been widely used to capture static and dynamic pressure over sleep for posture recognition. Both a full-size mat with a low-density sensing array for figuring out the structure of the whole body and a miniature scale mat with a high-density sensing array for identifying the local characteristics around the chest have been investigated. However, both of the mat systems may face the challenge in the trade-off between the computational complexity (involving the size, density, etc. of the mat) and the performance of sleep posture recognition, where high performance may requires overcomplex computation and result in time latency in real-time sleep posture monitoring. In this paper, a lightweight neural network named ConcatNet, is proposed to realize sleep postures (supine, left, right, and prone) recognition in real time while maintaining a favorable performance. In ConcatNet, the inception module is proposed to extract the image features under multiple receptive fields, while the multi-layer feature fusion module is utilized to fuse deep and shallow features to enhance the model performance. To further improve the efficiency of the model, the depthwise convolution is adopoted. ConcatNet models in 3 different scales (ConcatNet-S, ConcatNet-M, and ConcatNet-L) are built to explore the impact of the sensor density on sleep posture recognition performance. Experimental results exhibit that ConcatNet-M corresponding to medium sensor density ( 16×16 ) achieved the best comprehensive performance, with short-term data cross-validation accuracy at 95.56% and overnight data testing accuracy at 94.68%. The model size is 7.91KB, FLOPs is 56.47K, and the inference time is only 0.38ms, which shows an outstanding performance of real-time sleep posture recognition with minimum consumption, indicating the potential to be deployed in mobile devices.
Assuntos
Algoritmos , Redes Neurais de Computação , Postura , Sono , Humanos , Postura/fisiologia , Sono/fisiologia , Masculino , Adulto , Pressão , Desenho de Equipamento , Feminino , Decúbito Dorsal/fisiologia , Decúbito Ventral/fisiologia , Adulto JovemRESUMO
Cervical cancer is one of the most common malignant tumours. Human papillomavirus (HPV) infection is the main cause of this cancer so that it could be prevented by screening and early treatment. Developing reginal screen protocols of maximum public health efficacy requires in-depth understandings of local HPV distribution and consequential cancer risks. Therefore, test results of HPV genotyping, cytology testing (TCT) and colposcopy inspection with biopsy were collected in this retrospective research. Data included by this research involved 63,906 women received screen related tests from Shenzhen Baoan Shiyan People's Hospital and the subsidiary institutes between 2017.01 and 2023.05. 10,238 colposcopies were performed in this period collecting 8,716 samples and 814 high-grade CIN were discovered. Within the 763 high-grade CIN cases with both TCT and HPV testing results, 232 were tested cytologically normal but only 30 were negative in HPV test. Besides, the rates of high-grade CIN observed in coinfection were all lower than the estimated rates generated from related single infection. HPV 52, 58 and 16 were found to be the most common types in Baoan, Shenzhen. The result also suggested that HPV coinfections should not increase risk for cervical cancers.
Assuntos
Coinfecção , Genótipo , Papillomaviridae , Infecções por Papillomavirus , Neoplasias do Colo do Útero , Humanos , Feminino , Infecções por Papillomavirus/virologia , Infecções por Papillomavirus/epidemiologia , Infecções por Papillomavirus/complicações , Neoplasias do Colo do Útero/virologia , Neoplasias do Colo do Útero/epidemiologia , China/epidemiologia , Coinfecção/virologia , Coinfecção/epidemiologia , Adulto , Estudos Retrospectivos , Papillomaviridae/genética , Papillomaviridae/isolamento & purificação , Papillomaviridae/classificação , Pessoa de Meia-Idade , Adulto Jovem , Displasia do Colo do Útero/virologia , Displasia do Colo do Útero/epidemiologia , Colposcopia , Detecção Precoce de Câncer , IdosoRESUMO
We described a novel approach for the C-H functionalization of 2,2'-bipyridine derivatives with alkynes. DFT calculations and experimental data showed a significant substituent effect at the 6-position of 2,2'-bipyridine, which weakened the adjacent N-Rh bond and provided the possibility of subsequent rollover cyclometalation, C-H activation, and functionalization.
RESUMO
The first example of pyrazole-directed rhodium(iii)-catalyzed unreactive C(sp3)-H alkenylation with alkynes has been described, which showed a relatively broad substrate scope with good functional group compatibility. Moreover, we demonstrated that the transitive coordinating center pyrazole could be easily removed under mild conditions.