Accurate quantification of the citrus dropped number plays a vital role in evaluating the disaster resistance capabilities of citrus varieties and selecting superior cultivars. However, research in this critical area remains notably insufficient. To bridge this gap, we conducted in-depth experiments using a custom dataset of 1200 citrus images and proposed a lightweight YOLO-MECD model that is built upon the YOLOv11s architecture. Firstly, the EMA attention mechanism was introduced as a replacement for the traditional C2PSA attention mechanism. This modification not only enhances feature extraction capabilities and detection accuracy for citrus fruits but also achieves a significant reduction in model parameters. Secondly, we implemented a CSPPC module based on partial convolution to replace the original C3K2 module, effectively reducing both parameter count and computational complexity while maintaining mAP values. At last, the MPDIoU loss function was employed, resulting in improved bounding box detection accuracy and accelerated model convergence. Notably, our research reveals that reducing convolution operations in the backbone architecture substantially enhances small object detection capabilities and significantly decreases model parameters, proving more effective than the addition of small object detection heads. The experimental results and comparative analysis with similar network models indicate that the YOLO-MECD model has achieved significant improvements in both detection performance and computational efficiency. This model demonstrates excellent comprehensive performance in citrus object detection tasks, with a precision (P) of 84.4%, a recall rate (R) of 73.3%, and an elevated mean average precision (mAP) of 81.6%. Compared to the baseline, YOLO-MECD has improved by 0.2, 4.1, and 3.9 percentage points in detection precision, recall rate, and mAP value, respectively. Furthermore, the number of model parameters has been substantially reduced from 9,413,574 in YOLOv11s to 2,297,334 (a decrease of 75.6%), and the model size has been compressed from 18.2 MB to 4.66 MB (a reduction of 74.4%). Moreover, YOLO-MECD also demonstrates superior performance against contemporary models, with mAP improvements of 3.8%, 3.2%, and 5.5% compared to YOLOv8s, YOLOv9s, and YOLOv10s, respectively. The model’s versatility is evidenced by its excellent detection performance across various citrus fruits, including pomelos and kumquats. These achievements establish YOLO-MECD as a robust technical foundation for advancing citrus fruit detection systems and the development of smart orchards.

Accurate determination of the number and location of immature small yellow peaches is crucial for bagging, thinning, and estimating yield in modern orchards. However, traditional methods have faced challenges in accurately distinguishing immature yellow peaches due to their resemblance to leaves and susceptibility to variations in shooting angles and distance. To address these issues, we proposed an improved target-detection model (EMA-YOLO) based on YOLOv8. Firstly, the sample space was enhanced algorithmically to improve the diversity of samples. Secondly, an EMA attention-mechanism module was introduced to encode global information; this module could further aggregate pixel-level features through dimensional interaction and strengthen small-target-detection capability by incorporating a 160 × 160 detection head. Finally, EIoU was utilized as a loss function to reduce the incidence of missed detections and false detections of the target small yellow peaches under the condition of high density of yellow peaches. Experimental results show that compared with the original YOLOv8n model, the EMA-YOLO model improves mAP by 4.2%, Furthermore, compared with SDD, Objectbox, YOLOv5n, and YOLOv7n, this model’s mAP was improved by 30.1%, 14.2%,15.6%, and 7.2%, respectively. In addition, the EMA-YOLO model achieved good results under different conditions of illumination and shooting distance and significantly reduced the number of missed detections. Therefore, this method can provide technical support for smart management of yellow-peach orchards.

The large-scale production of edible mushrooms typically requires the use of greenhouses, as the greenhouse environment significantly affects the growth of edible mushrooms. It is crucial to effectively predict the temperature, humidity, and carbon dioxide fluctuations within the mushroom greenhouse for determining the environmental stress and pre-regulation of edible mushrooms. To address the nonlinearity, temporal dynamics, and strong coupling of the edible mushroom greenhouse environment, a temperature, humidity, and carbon dioxide prediction model based on the combination of the attention mechanism, the convolutional neural network, and the long short-term memory neural network (A-CNN-LSTM) is proposed. Experimental data were collected from both the inside and outside of the greenhouse, including environmental data and the on–off data of environmental control devices. After completing missing data using linear interpolation, denoising with Kalman filtering, and normalization, the recurrent neural network (RNN) model, long short-term memory (LSTM) model, and A-CNN-LSTM model were trained and tested on the time series data. These models were used to predict the environmental changes in temperature, humidity, and carbon dioxide inside the greenhouse. The results indicate that the A-CNN-LSTM model outperforms the other two models in terms of denoising, non-denoising, and different prediction time steps. The proposed method accurately predicts temperature, humidity, and carbon dioxide levels with errors of 0.17 °C (R² = 0.974), 2.06% (R² = 0.804), and 8.367 ppm (R² = 0.993), respectively. These results indicate improved prediction accuracy for temperature, humidity, and carbon dioxide values inside the edible mushroom greenhouse. The findings provide a decision basis for the precise control of the greenhouse environment.

Using object detection techniques on immature fruits to find out their quantity and position is a crucial step for intelligent orchard management. A yellow peach target detection model (YOLOv7-Peach) based on the improved YOLOv7 was proposed to address the problem of immature yellow peach fruits in natural scenes that are similar in color to the leaves but have small sizes and are easily obscured, leading to low detection accuracy. First, the anchor frame information from the original YOLOv7 model was updated by the K-means clustering algorithm in order to generate anchor frame sizes and proportions suitable for the yellow peach dataset; second, the CA (coordinate attention) module was embedded into the backbone network of YOLOv7 so as to enhance the network’s feature extraction for yellow peaches and to improve the detection accuracy; then, we accelerated the regression convergence process of the prediction box by replacing the object detection regression loss function with EIoU. Finally, the head structure of YOLOv7 added the P2 module for shallow downsampling, and the P5 module for deep downsampling was removed, effectively improving the detection of small targets. Experiments showed that the YOLOv7-Peach model had a 3.5% improvement in mAp (mean average precision) over the original one, much higher than that of SSD, Objectbox, and other target detection models in the YOLO series, and achieved better results under different weather conditions and a detection speed of up to 21 fps, suitable for real-time detection of yellow peaches. This method could provide technical support for yield estimation in the intelligent management of yellow peach orchards and also provide ideas for the real-time and accurate detection of small fruits with near background colors.

Electrocardiogram (ECG) is nowadays an important technology to be applied in the clinical diagnosis for the detection of the heart disease. But the large storage and high-burden transmission of the ECG data is a challenge. Therefore, the compressive sensing (CS) is appropriate to deal with those signals for it can compress and sample the signal at the same time. In order to get rid of the constraints in the traditional CS methods, we propose a compressive sensing framework based on multiscale feature fusion and SE block.In the compression process we use sequential convolutional layers instead of the traditional compressive sensing using measurement matrix projection for ECG signals. In the reconstruction process, the multi-scale feature fusion method is first used to fuse multiple feature maps output from the convolution layer to better extract signal features. Subsequently, Squeeze-and-Excitation (SE) block is used to further enhance the feature representation. Finally, sequence modeling of the ECG signal is performed using LSTM to obtain the reconstructed signal. The results show that the proposed method performs well on various datasets and evaluation metrics, in the case of SR=0.4, the PRD and SNR of the experiments on the MIT-BIH Arrhythmia database are 1.55% and 37.66dB, respectively.The PRD and SNR of the experiments on the Non-Invasive Fetal ECG Arrhythmia Database were 2.48% and 34.57dB, respectively, which were the lowest among all the comparison methods, indicating that the proposed method has good ECG signal processing capability.