The efficient detection of grapes is a crucial technology for fruit-picking robots. To better identify grapes from branch shading that is similar to the fruit color and improve the detection accuracy of green grapes due to cluster adhesion, this study proposes a Shine-Muscat Grape Detection Model (S-MGDM) based on improved YOLOv3 for the ripening stage. DenseNet is fused in the backbone feature extraction network to extract richer underlying grape information; depth-separable convolution, CBAM, and SPPNet are added in the multi-scale detection module to increase the perceptual field of grape targets and reduce the model computation; meanwhile, PANet is combined with FPN to promote inter-network information flow and iteratively extract grape features. In addition, the CIOU regression loss function is used and the prior frame size is modified by the k-means algorithm to improve the accuracy of detection. The improved detection model achieves an AP value of 96.73% and an F1 value of 91% on the test set, which are 3.87% and 3% higher than the original network model, respectively; the average detection speed under GPU reaches 26.95 frames/s, which is 6.49 frames/s higher than the original model. The comparison results with several mainstream detection algorithms such as SSD and YOLO series show that the method has excellent detection accuracy and good real-time performance, which is an important reference value for the problem of accurate identification of Shine-Muscat grapes at maturity.
Crop diseases have an important impact on the safe production of food. Therefore, the automated identification of pre-crop diseases is very important for farmers to increase production and income. In this paper, a tomato leaf disease identification method based on the optimized MobileNetV2 model is proposed. A dataset of 20,400 tomato disease images was created based on tomato disease images taken from the greenhouse and obtained from the PlantVillage database. The optimized MobileNetV2 model was trained with the dataset to obtain a classification model for tomato leaf diseases. The average recognition accuracy of the model is 98.3% and the recall rate is 94.9%, which is 1.2% and 3.9% higher than the original model, respectively, after experimental validation. The average prediction speed of the model for a single image is about 76 ms, which is 2.94% better than the original model. To verify the performance of the optimized MobileNetV2 model, it was compared with the Xception, Inception, and VGG16 feature extraction network models using migration learning, respectively. The experimental results show that the average recognition accuracy of the model is 0.4 to 2.4 percentage points higher than that of the Xception, Inception, and VGG16 models. It can provide technical support for the identification of tomato diseases, and is also important for plant growth monitoring under precision agriculture.
The design of this paper is to draw lessons from and optimize the advanced design at home and abroad, and design a vegetable seeder that can better adapt to the actual complex sowing situation in China. This design uses air-suction metering device, which can accurately sow seeds and improve the production efficiency. This design improves the overall structure of the seeder to adapt to different sizes and rugged and complex land conditions, whether complex hilly or flat terrain, no matter how well the soil can adapt. The sowing amount, plant spacing and row spacing can be adjusted in a wide range to meet the different needs of sowing. With a small change in the structure, the actual production needs can be met.
ObjectiveThe aim of our study was to evaluate the prognostic value of gated SPECT MPI in non-obstructed coronary arteries (INOCA) patients, sought to stratify patients more accurately and thus derive more reliable prognostic information.Materials and methodsIn total, 167 patients with INOCA were enrolled. The patients were divided into two groups according to their SSS. Patients were followed-up regularly in terms of major adverse cardiovascular event (MACE), including cardiac death, nonfatal myocardial infarction, stroke, re-hospitalization with angina pectoris, and recurrent angina pectoris. Kaplan-Meier curves and Cox's proportional hazards models were used to analyze survival and identify predictive factors.ResultsAdverse cardiac events occurred in 33 cases (19.8%). The rate of MACE was higher in the summed stress score (SSS) ≥4 group than in the SSS 0–3 group (30.1% vs. 9.5%, respectively, P = 0.001) and MACE-free survival was lower (annual MACE-free rates of 87.5% vs. 96.2%, respectively, P = 0.003). Event-free survival was consistently higher in patients with normal arteries than in those with non-obstructive coronary artery disease (annual MACE-free rates of 96.1% and 88.4%, P = 0.035). When the SSS and the CAG results were combined, patients with normal coronary arteries (SSS 0–3) had the best prognosis and those with non-obstructive coronary artery stenosis (SSS ≥ 4) had the worst. However, the early prognosis of patients with non-obstructive coronary artery disease and SSS of 0–3 was comparable to that of patients with normal coronary arteries and SSS ≥ 4 (annual MACE-free rates of 100%, 94.6%, 93.1%, and 78.2%, respectively). Multivariate Cox's regression indicated that the SSS [hazard ratio (HR) = 1.126, 95% confidence interval (CI) 1.042–1.217, P = 0.003] and non-obstructive coronary artery disease (HR = 2.559, 95% CI 1.249–5.246, P = 0.01) were predictors of adverse cardiac events.ConclusionSPECT MPI data were prognostic for INOCA patients, thus identifying groups at high risk. The long-term predictive efficacy of such data exceeded that of CAG data. A combination of the two measures more accurately stratified INOCA patients in terms of risk.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.