Anomalies in time series, also called “discord,” are the abnormal subsequences. The occurrence of anomalies in time series may indicate that some faults or disease will occur soon. Therefore, development of novel computational approaches for anomaly detection (discord search) in time series is of great significance for state monitoring and early warning of real-time system. Previous studies show that many algorithms were successfully developed and were used for anomaly classification, e.g., health monitoring, traffic detection, and intrusion detection. However, the anomaly detection of time series was not well studied. In this paper, we proposed a long short-term memory- (LSTM-) based anomaly detection method (LSTMAD) for discord search from univariate time series data. LSTMAD learns the structural features from normal (nonanomalous) training data and then performs anomaly detection via a statistical strategy based on the prediction error for observed data. In our experimental evaluation using public ECG datasets and real-world datasets, LSTMAD detects anomalies more accurately than other existing approaches in comparison.

Stomata play a crucial role in plant immune responses, with their morphological characteristics closely linked to disease resistance. Accurate detection and analysis of stomatal phenotypic parameters are essential for soybean disease resistance research and variety breeding. However, traditional stoma detection methods are challenged by complex backgrounds and leaf vein structures in soybean images. To address these issues, we proposed a Soybean Stoma-YOLO (You Only Look Once) model (SS-YOLO) by incorporating large separable kernel attention (LSKA) in the Spatial Pyramid Pooling-Fast (SPPF) module of YOLOv8 and Deformable Large Kernel Attention (DLKA) in the Neck part. These architectural modifications enhanced YOLOV8′s ability to extract multi-scale and irregular stomatal features, thus improving detection accuracy. Experimental results showed that SS-YOLO achieved a detection accuracy of 98.7%. SS-YOLO can effectively extract the stomatal features (e.g., length, width, area, and orientation) and calculate related indices (e.g., density, area ratio, variance, and distribution). Across different soybean rust disease stages, the variety Dandou21 (DD21) exhibited less variation in length, width, area, and orientation compared with Fudou9 (FD9) and Huaixian5 (HX5). Furthermore, DD21 demonstrated greater uniformity in stomatal distribution (SEve: 1.02–1.08) and a stable stomatal area ratio (0.06–0.09). The analysis results indicate that DD21 maintained stable stomatal morphology with rust disease resistance. This study demonstrates that SS-YOLO significantly improved stoma detection and provided valuable insights into the relationship between stomatal characteristics and soybean disease resistance, offering a novel approach for breeding and plant disease resistance research.

Soybean rust is a widespread and rapidly spreading fungal disease that poses a serious threat to both the yield and quality of soybeans. Traditional vegetation indices struggle to effectively assess disease severity across different infection stages, particularly during early or mild stages, due to weak spectral responses. In this study, we propose a soybean rust resistance identification model, RustNet-3D (Soybean Rust Disease Diagnosis Network-3D), which integrates a 3D deformable convolution module and a spectral dilated convolution module to achieve accurate classification of different disease severity levels. We further introduce a spectral feature band extraction module, iBSAM (improved Band Selection and Attention Module), which employs a modified depthwise separable convolution architecture. iBSAM incorporates bandwise independent convolution to enable individualized modeling of each spectral band. It also applies a hard thresholding strategy to remove redundant information, and integrates a channel attention mechanism to reinforce the model’s sensitivity to discriminative wavelengths. By modeling the temporal hyperspectral data of soybean rust, five highly sensitive spectral bands—581 nm, 605 nm, 596 nm, 609 nm, and 628 nm—are identified and subsequently used to construct the Soybean Rust Spectral Index (SRSI). Experimental results demonstrate that the RustNet-3D model achieves an overall accuracy (OA) of 92.74%, and the correlation coefficient between SRSI and disease severity reaches 0.89, validating the effectiveness of the selected spectral features. This study provides a rapid and accurate solution for soybean rust severity evaluation, offering a high-efficiency and automated approach for resistance identification and intelligent breeding.