RESUMO
As computer image processing and digital technologies advance, creating an efficient method for classifying sports images is crucial for the rapid retrieval and management of large image datasets. Traditional manual methods for classifying sports images are impractical for large-scale data and often inaccurate when distinguishing similar images. This paper introduces an SE module that adaptively adjusts the weights of input feature mapping channels, and a Res module that excels in deep feature extraction, preventing gradient vanishing, multi-scale processing, and enhancing generalization in image recognition. Through extensive experimentation on network structure adjustments, the SE-RES-CNN neural network model is applied to sports image classification. The model is trained on a sports image classification dataset from Kaggle, alongside VGG-16 and ResNet50 models. Training results show that the proposed SE-RES-CNN model improves classification accuracy by approximately 5% compared to VGG-16 and ResNet50 models. Testing revealed that the SE-RES-CNN model classifies 100 out of 500 sports images in 6 s, achieving an accuracy rate of up to 98% and a single prediction time of 0.012 s. This validates the model's accuracy and effectiveness, significantly enhancing sports image retrieval and classification efficiency. This validates the model's accuracy and effectiveness, significantly enhancing sports image retrieval and classification efficiency.
RESUMO
With the rapid development of computer technology, artificial intelligence and big data technology have undergone a qualitative leap, permeating into various industries. In order to fully harness the role of artificial intelligence in the field of nuclear engineering, we propose to use the LSTM algorithm in deep learning to model the BEAVRS (Benchmark for Evaluation And Validation of Reactor Simulations) core first cycle loading. The BEAVRS core is simulated by DRAGON and DONJON, the training set and the test set are arranged in a sequential fashion according to the evolution of time, and the LSTM model is constructed by changing a number of hyperparameters. In addition to this, the training set and the test set are retained in a chronological order that is different from one another throughout the whole process. Additionally, there is a significant pattern that is followed when subsetting both the training set and the test set. This pattern applies to both sets. The steps in this design are very carefully arranged. The findings of the experiments suggest that the model can be altered by making use of the appropriate hyperparameters in such a way as to bring the maximum error of the effective multiplication factor keff prediction of the core within 2.5 pcm (10-5), and the average error within 0.5266 pcm, which validated the successful application of machine learning to transport equations.
RESUMO
BACKGROUND: Acupotomy was used to treat tenosynovitis of hand flexor tendons (THFT) in China. But it's uncertain about the efficacy of acupotomy for THFT. We plan to evaluate the efficacy and safety about acupotomy therapy in the treatment of THFT through this review. METHODS: The protocol about this review was registered in PROSPERO (registration number: CRD42022330568). We searched 6 databases from their respective inception dates to January 11, 2022. Studies searched was screened by our reviewers, and then the raw data was filtered out. We used RevMan 5.3 software to perform statistical analysis. RESULTS: 11 studies involving 828 patients were shortlisted. The experimental group showed obvious advantages compared with the control group, such as effective rate (odds ratio [OR]â =â 6.77, 95% CI [confidence intervals]â =â [3.89, 11.77], Pâ <â .00001), cure rate (ORâ =â 3.32, 95% CIâ =â [1.81, 6.11], Pâ =â .0001) and Vas score (MDâ =â -1.21, 95% CIâ =â [-2.00, -0.42], Zâ =â 3.01, Pâ <â .003). CONCLUSIONS: According to the above results, Acupotomy is an effective and safe treatment for THFT. So it should be recommended for the treatment of THFT patients.
Assuntos
Terapia por Acupuntura , Tenossinovite , Humanos , Tenossinovite/terapia , Terapia por Acupuntura/métodos , Projetos de Pesquisa , Tendões , ChinaRESUMO
PURPOSE: Factors influencing responsiveness to warfarin at treatment onset time were not well identified in Chinese patients undergoing heart valve replacement. We sought to select the most relevant factors that associated with patient response to warfarin early after heart valve surgery. METHODS: In this observational study, 289 patients starting warfarin therapy early after heart valve replacement surgery were enrolled. CYP2C9 *1, *2, *3, and *5; VKORC1-1639 G>A, CYP4F2 V433M, and GGCX rs11676382 genotypes; clinical characteristics, response to therapy, and bleeding and thrombosis events were collected. The primary outcomes were the time to the first INR equal to or more than lower limit of therapeutic range and the warfarin dose requirements. Stepwise multiple linear regression was performed to develop a dosing algorithm to predict the warfarin dose requirements. RESULTS: The results of univariate analysis showed lone VKORC1-1639 G>A, CYP2C9 *1/*3, cefazolin, cefoperazone-sulbactam, increased BMI, Δhemoglobin, and white blood cell count could significantly affect patient responsiveness to warfarin in the initial period of anticoagulation. Multivariate analysis resulted in an equation: Accumulated warfarin doses (mg) = 17.068 VKORC1-1639 G>A - 4.261 hypertension + 0.593 BMI - 0.115 age - 4.852 CYP2C9 *1/*3 - 2.617 cefazolin - 4.902 cefoperazone-sulbactam - 4.537, which could explain 40.2% of the variability in warfarin dose needed to reach the first INR equal to or more than lower limit of therapeutic range. CONCLUSIONS: Both genetic and clinical factors contributed to anticoagulation effect of warfarin in the initial period of treatment. Our findings could provide a basis for the personalized management of warfarin use in the early stage of anticoagulation in northern Chinese patients.