Search

Grape leaf disease is a primary factor affecting grape yield and impeding the growth of the industrial economy. Currently, high-quality datasets are required for deep recognition models to effectively identify grape leaf diseases. In reality, the acquired image inevitably has the appearance of being low quality and unclear due to the influence of equipment and environment. The super-resolution method is an effective way to solve the problem. However, due to the complex model structure and learning strategies, existing super-resolution methods are computationally expensive and neglect the balance between global and local feature extraction. In this paper, a novel multiple attention transformer super-resolution (MATSR) method is proposed to solve these problems. Specifically, the method uses convolution to extract low-level features, which are then fed into the multiple attention shuffle transformer (MAST) module. The module consists of the shuffle transformer for global feature extraction, the constructed channel spatial attention block (CSAB) for local feature extraction, and the built reduisal feature block (RFB) for aggregating these two features. Meanwhile, considering the importance of the balance of global and local features for grape leaf disease recognition, a dynamic learning strategy is designed to balance these two features. Further, the abstract feature extraction layer combined the learned features with the low-level features. Finally, these abstracted features are fed into the pixels shuffle layer for super-resolution upsampling. Numerous comparative experiments are carried out on the collected high-resolution grape leaf disease images as well as the apple leaf pathological images. The results demonstrate the proposed method achieved the best PSNR of 38.152 dB and SSIM of 0.96 at scale ×2, and 35.896 dB and SSIM of 0.934 at scale ×3, respectively. Furthermore, four recognition models are experimented on the super-resolution grape disease dataset, among which ShuffleNet and Inception achieve the best accuracy of 98.28 % and 98.53 %, respectively. Therefore, this study can effectively aid grape growers in accurately identifying diseases and taking proactive measures. [ABSTRACT FROM AUTHOR]

Univariate time series forecasting is still an important but challenging task. Considering the wide application of temporal data, adaptive predictors are needed to study historical behavior and forecast future state in various scenarios. In this paper, inspired by human attention mechanism and decomposition and reconstruction framework, we proposed a convolution-based dual-stage attention (CDA) architecture combined with Long Short-Term Memory networks (LSTM) for univariate time series forecasting. Specifically, we first use the decomposition algorithm to generate derived variables from target series. Input variables are then fed into the CDA-LSTM machine for further forecasting. In the Encoder–Decoder phase, for the first stage, attention operation is combined with the LSTM acting as an encoder, which could adaptively learn the relevant derived series to the target. In the second stage, the temporal attention mechanism is integrated with decoder aiming to automatically select the relevant encoder hidden states across all time steps. A convolution phase is concatenated parallelly to the Encoder–Decoder phase to reuse the historical information of the target and extract the mutation features. The experimental results demonstrate the proposed method could be adopted as expert systems for forecasting in multiple scenarios, and the superiority is verified by comparing with twelve baseline models on ten datasets. The practicability of different decomposition algorithms and convolution architectures is also discussed by extensive experiment. Overall, our work carries a significant value not merely in adaptive modeling of deep learning in time series issues, but also in the field of univariate data processing and prediction. [ABSTRACT FROM AUTHOR]

The aim of the present study was to investigate the effect of Lidocaine on hypoxia-induced injury in cardiomyoblasts whilst exploring the associated molecular mechanism. In the present study, hypoxia was induced in H9c2 cells to establish an in vitro model of myocardial infarction. The cells were treated with lidocaine (0.5, 1, 5, 10 mM) for 48 h under hypoxic conditions. Cell viability and apoptosis levels were determined by MTT assay and flow cytometry, and ELISA was used to measure the levels of inflammatory cytokines released. A creatine kinase isoenzyme/cardiac troponin I detection kit was used to show that lidocaine significantly reduced hypoxia-induced cardiac troponin 1 and creatine kinase-muscle/brain release in a dose-dependent manner. Mitochondrial viability staining suggested that lidocaine significantly enhanced mitochondrial viability under hypoxic conditions. Lidocaine also significantly reduced hypoxia-induced apoptosis and increased H9c2 viability in a dose-dependent manner. Additionally, under hypoxic conditions, lidocaine dose-dependently promoted Bcl-2 expression, while decreasing Bax and caspase-3 expression in H9c2 cells. ELISA and reverse transcription quantitative PCR were used to detect the levels of tumor necrosis factor (TNF-α), interleukin (IL)-1β and IL-6 released by H9c2 cells. Results showed that lidocaine markedly reduced the hypoxia-induced expression levels of IL-1β, TNF-α and IL-6 in a dose-dependent manner. In addition, protein levels of phosphorylated (p)-ERK1/2 and NF-κB p-p65 were analyzed by western blotting, and results indicated that lidocaine significantly increased the protein levels of p-ERK1/2 and decreased the protein level of NF-κB p-p65 in a dose-dependent manner under hypoxic conditions. These data suggested that lidocaine might protect cardiomyoblasts from hypoxia-induced injury via activation of the mitogen activated protein kinase/ERK/NF-κB signaling pathway. [ABSTRACT FROM AUTHOR]

In an increasingly competitive market, predicting the customer's consumption behavior has a vital role in customer relationship management. In this study, a new classifier for customer consumption behavior prediction is proposed. The proposed methods are as follows: (i) A feature selection method based on least absolute shrinkage and selection operator (Lasso) and Principal Component Analysis (PCA), to achieve efficient feature selection and eliminate correlations between variables. (ii) An improved genetic-eXtreme Gradient Boosting (XGBoost) for customer consumption behavior prediction, to improve the accuracy of prediction. Furthermore, the global search ability and flexibility of the genetic mechanism are used to optimize the XGBoost parameters, which avoids inaccurate parameter settings by manual experience. The adaptive crossover and mutation probabilities are designed to prevent the population from falling into the local extremum. Moreover, the grape-customer consumption behavior dataset is employed to compare the six Lasso-based models from the original, normalized and standardized data sources with the Isometric Mapping, Locally Linear Embedding, Multidimensional Scaling, PCA and Kernel Principal Component Analysis methods. The improved genetic-XGBoost is compared with several well-known parameter optimization algorithms and state-of-the-art classification approaches. Furthermore, experiments are conducted on the University of California Irvine datasets to verify the improved genetic-XGBoost algorithm. All results show that the proposed methods outperform the existing ones. The prediction results provide the decision-making basis for enterprises to formulate better marketing strategies. [ABSTRACT FROM AUTHOR]

Grape leaf diseases seriously affect grape yield and directly lead to the loss of the industrial economy. An accurate diagnosis is crucial for effective spraying and control. Presently, the combination of image blending and a deep recognition model is the most effective method for accurately identifying grape leaf diseases. Existing methods of image blending depend primarily on single-channel and multi-scale channel blending, computing and optimizing the Poisson equation, and the iterative optimization of learning-based methods for simple composite results. Although these methods have had some success, they are not able to simultaneously address lesion and leaf gap size, color bleeding, and edge smoothness. In this paper, we propose a novel image blending method named cascade wavelet attention network (CWAN). Specifically, CWAN consists of a cascade wavelet attention (CWA) and a blending autoencoder. First, we build a CWA to decompose the image into a multi-level and multi-scale frequency domain image. Then, the detailed features of the source and target domains are extracted, and the edges are smoothed. Following this, a shared decoder is designed to fuse these features in the corresponding frequency-domain layers, and the result serves as the attention feature. Finally, we design a blending autoencoder with a feature fusion mechanism to seamlessly blend lesions and leaves enhanced by CWA. We also construct a weighted blended loss function to avoid leaf color infiltration into the lesion in the blended image. Comprehensive experiments on two grape leaf disease datasets. Qualitative and quantitative results demonstrate the superiority and effectiveness of our model. • A novel method called CWAN for data enhancement of grape leaf disease is proposed. • The CWA is designed to enhance the textures and smooth the edge of blending. • The blending autoencoder with feature fusion mechanism can seamlessly blend images. • An unpaired image composition dataset is created for grape leaf disease blending. • The image shows superior performance on the texture and seam transition. [ABSTRACT FROM AUTHOR]

• A novel method for data enhancement of grape leaf disease images is proposed. • The proposed method relies on feature fusion mechanism and capsule structure. • GrapeGAN generates high quality images with full structure and a FID of 5.495. • The recognition accuracy of images generated by the GrapeGAN can reach 96.13%. Grape leaf disease seriously affects the yield and quality of grapes. Limited by actual conditions, collecting a large number of grape disease images is time-consuming and labor intensive, which makes it difficult to train grape disease identification models with excellent performance. Currently, using generative adversarial networks(GANs) to generate grape leaf images is a popular method. Unfortunately, the leaf disease images generated by conventional GANs are not clear enough and the structural integrity is insufficient. To address this problem, a novel architecture named GrapeGAN is proposed in this paper. First, suppress the loss of texture detail information during image generation, a U-Net-like generator is designed by integrating convolutions with residual blocks and reorganization (reorg) methods. Simultaneously, the concatenation (concat) method is used in the generator to retain more scale texture information. Then, to make the generated grape images structurally complete and avoid petiole and leaf structure misalignment, a discriminator is designed with a convolution block and capsule structure. Convolution is used to extract general features, and the capsule structure encodes the spatial information and the probability of the presence of spots. In subsequent experiments on the same raw data, GrapeGAN is compared to WGAN and DCGAN, and the results show that GrapeGAN outperforms the comparative models. Specifically, the Fréchet inception distance (FID) is 5.495, and the neural image assessment (NIMA) is 4.937 ± 1.515. Moreover, four convolutional neural network (CNN) recognition models are used to identify the generated grape leaf diseases. The results demonstrate that the recognition accuracy of grape leaf disease images generated by the GrapeGAN is higher than 86.36%, and the identification accuracy of VGG16 and InceptionV1 achieve 96.13%. In summary, the experimental results show the effectiveness of GrapeGAN, which proves that GrapeGAN can efficiently detect grape leaf disease detection. [ABSTRACT FROM AUTHOR]

• A high precision time delay calibration system based on optical fiber switches and fiber coils network for the satellite range measurement system is proposed. • The Phase Stabilized Optical Fiber (PSOF), is proposed to use as time delay component instead of the Single Mode Fiber (SMF) to minimize the temperature dependence of transmission delay time. • By using the PSOF, the temperature error can be decreased by 4.15 times compared with using the SMF. A high precision time delay calibration system based on optical fiber switches and fiber coils network for the satellite range measurement system is proposed in this paper. To reach the high time delay precision, the Phase Stabilized Optical Fiber (PSOF), is proposed to use as time delay component instead of the Single Mode Fiber (SMF) to minimize the temperature dependence of transmission delay time. In order to verify the time delay precision, a low coherence interferometry which contains a Michelson interferometer and a Mach-Zehnder interferometer is used to measure the thermal coefficient of delay of the PSOF compared with the SMF from −20 to 60℃. The result showed that by using the PSOF, the temperature error can be decreased by 4.15 times compared with using the standard SMF in the fiber based range measurement system. [ABSTRACT FROM AUTHOR]

• A new oversampling method is proposed to solve class imbalance in the real dataset. • A new classifier is proposed to improve the accuracy of consumer behavior prediction. • The hybrid kernel of the radial basis function neural network is designed. • The centers of the neural network are optimized by the immune algorithm. • All results show that the proposed two methods outperform existing models. In practical applications, imbalanced data has brought great challenges to classification problems. In this paper, we propose two new methods: (1) a new oversampling method, named Tomek-CASUWO, to address the issue of class imbalance; (2) a new classifier, named ILS-RBFNN, to increase the accuracy of prediction of customer consumption behavior. Since current ASUWO algorithm is easily affected by noise samples and fuzzy class boundaries, we propose Tomek-CASUWO to address these problems: (i) the Tomek links algorithm is used to filter noise samples; (ii) CASUWO is used to avoid overlapping class boundaries; (iii) Tomek-CASUWO is used to synthesize new samples. Also, we propose a new classifier based on RBFNN, named ILS-RBFNN, to improve the prediction accuracy: (i) the hybrid kernel is developed by combining Gaussian and Polynomial; (ii) an Immune Algorithm (IA) is used to optimize the centers of RBFNN; (iii) Least-Squares (LS) is used to calculate the biases and weights. Wine-consumer behavior data is used to compare our Tomek-CASUWO with other oversampling methods. We compare ILS-RBFNN with several well-known kernel functions and parameter update methods. The experimental results show that Tomek-CASUWO can significantly improve the prediction accuracy of a classifier, and ILS-RBFNN outperforms other classification methods. We also conduct experiments on the extended real-world dataset. Finally, the robustness and applicability of ILS-RBFNN are verified on the eleven UCI datasets. All results show that the proposed two methods outperform existing models. The experimental results also demonstrate the effectiveness and practicability of ILS-RBFNN for predicting customer behavior. [ABSTRACT FROM AUTHOR]