Sugarcane is an important raw material for sugar and chemical production. However, in recent years, various sugarcane diseases have emerged, severely impacting the national economy. To address the issue of identifying diseases in sugarcane leaf sections, this paper proposes the SE-VIT hybrid network. Unlike traditional methods that directly use models for classification, this paper compares threshold, K-means, and support vector machine (SVM) algorithms for extracting leaf lesions from images. Due to SVM’s ability to accurately segment these lesions, it is ultimately selected for the task. The paper introduces the SE attention module into ResNet-18 (CNN), enhancing the learning of inter-channel weights. After the pooling layer, multi-head self-attention (MHSA) is incorporated. Finally, with the inclusion of 2D relative positional encoding, the accuracy is improved by 5.1%, precision by 3.23%, and recall by 5.17%. The SE-VIT hybrid network model achieves an accuracy of 97.26% on the PlantVillage dataset. Additionally, when compared to four existing classical neural network models, SE-VIT demonstrates significantly higher accuracy and precision, reaching 89.57% accuracy. Therefore, the method proposed in this paper can provide technical support for intelligent management of sugarcane plantations and offer insights for addressing plant diseases with limited datasets.
Separating plasma or serum from blood is essential for precise testing. However, extracting precise plasma quantities outside the laboratory poses challenges. A recent study has introduced a capillary force-driven membrane filtration technique to accurately separate small plasma volumes. This method efficiently isolates 100–200 L of pure human whole blood with a 48% hematocrit, resulting in 5–30 L of plasma with less than a 10% margin of error. The entire process is completed within 20 min, offering a simple and cost-effective approach to blood separation. This study has successfully addressed the bottleneck in self-service POCT, ensuring testing accuracy. This innovative method shows promise for clinical diagnostics and point-of-care testing.
The color and texture characteristics of crops can reflect their nitrogen (N) nutrient status and help optimize N fertilizer management. This study conducted a one-year field experiment to collect sugarcane leaf images at tillering and elongation stages using a commercial digital camera and extract leaf image color feature (CF) and texture feature (TF) parameters using digital image processing techniques. By analyzing the correlation between leaf N content and feature parameters, feature dimensionality reduction was performed using principal component analysis (PCA), and three regression methods (multiple linear regression; MLR, random forest regression; RF, stacking fusion model; SFM) were used to construct N content estimation models based on different image feature parameters. All models were built using five-fold cross-validation and grid search to verify the model performance and stability. The results showed that the models based on color-texture integrated principal component features (C-T-PCA) outperformed the single-feature models based on CF or TF. Among them, SFM had the highest accuracy for the validation dataset with the model coefficient of determination (R2) of 0.9264 for the tillering stage and 0.9111 for the elongation stage, with the maximum improvement of 9.85% and 8.91%, respectively, compared with the other tested models. In conclusion, the SFM framework based on C-T-PCA combines the advantages of multiple models to enhance the model performance while enhancing the anti-interference and generalization capabilities. Combining digital image processing techniques and machine learning facilitates fast and nondestructive estimation of crop N-substance nutrition.
Automated weeding equipment is urgently needed to deal with weeds in farmlands in the context of the rapid development of Intelligent Agriculture. A system for accurately identifying crops and weeds in images is crucial component of automated weeding equipment. However, in the field environment, crops and weeds grow intertwined, and weeds are very similar to sugarcane leaves, making it difficult to accurately segment crops, weeds, and their boundaries from images. In this paper, we proposed a novel network that fully utilizes low-level semantic information to accurately segment crops and weeds in images, improving the accuracy of crop and weed segmentation while reducing the need for training weight parameters and improving speed in the prediction stage. Specifically, we made three important modifications for crop and weed identification. First, a Multi-scale Feature Extraction and Fusion module (MFEF) was designed to capture abundant low-level semantic feature information. Afterward, we introduce a Global Response Normalization (GRN) block to select more useful feature information. Finally, a series of residual attention transformer layers are designed to transmit the long-range dependency information extracted between layers. Numerous experimental results confirmed that our proposed network achieved excellent performance in segmenting sugarcane and weed images. Specifically, (1) the mean accuracy and, Mean Intersection of Union (MIoU) reached 96.97% and 94.13%, respectively, (2) the training parameters of the model have been reduced by more than 25%, improving the Frames Per Second (FPS) value of the prediction process, and (3) is also effective on the publicly available BoniRob Dataset, indicating that the proposed model has considerable generalization ability. This study provides an accurate weed identification map and has reference significance for subsequent systems as mechanical weeding equipment.