As Internet of Things (IoT) technology sees extensive adoption in smart agriculture, smart healthcare, and smart cities, emerging systems are increasingly confronted with complex and dynamic security threats. Intrusion Detection Systems (IDS), a key technology in network security, effectively enhance IoT system safety by detecting and monitoring anomalous activities. Nevertheless, IDS relying on traditional Machine Learning (ML) technologies demonstrate limited efficacy in classifying malicious traffic. In recent years, approaches that convert network security data into image sets and leverage Deep Transfer Learning (DTL) for classification have gained rapid popularity. While these methods substantially improve detection accuracy, they also lead to increased time and resource consumption during training. To balance high detection accuracy with reduced time consumption, this study introduces an efficient intrusion detection approach based on the Vision Transformer (ViT), utilizing its powerful feature extraction capabilities to enhance performance. The proposed High-performance ViT Intrusion Detection System (HiViT-IDS) begins by transforming one-dimensional network traffic data into RGB images and leverages the ViT model’s exceptional representational power for efficient classification. Experimental results on the ToN-IoT and Edge-IIoTset datasets reveal classification accuracies of 99.70% and 100%, respectively. In comparison to existing mainstream DTL approaches, the proposed model achieves considerable reductions in training time while sustaining high performance. The findings suggest that the HiViT-IDS offers superior potential and a competitive edge in adapting to complex and dynamic network environments.

In rice cultivation and breeding, obtaining accurate information on the quantity and spatial distribution of rice plants is crucial. However, traditional field sampling methods can only provide rough estimates of the plant count and fail to capture precise plant locations. To address these problems, this paper proposes P2PNet-EFF for the counting and localization of rice plants. Firstly, through the introduction of the enhanced feature fusion (EFF), the model improves its ability to integrate deep semantic information while preserving shallow spatial details. This allows the model to holistically analyze the morphology of plants rather than focusing solely on their central points, substantially reducing errors caused by leaf overlap. Secondly, by integrating efficient multi-scale attention (EMA) into the backbone, the model enhances its feature extraction capabilities and suppresses interference from similar backgrounds. Finally, to evaluate the effectiveness of the P2PNet-EFF method, we introduce the URCAL dataset for rice counting and localization, gathered using UAV. This dataset consists of 365 high-resolution images and 173,352 point annotations. Experimental results on the URCAL demonstrate that the proposed method achieves a 34.87% reduction in MAE and a 28.19% reduction in RMSE compared to the original P2PNet while increasing $R^2$ by 3.03%. Furthermore, we conducted extensive experiments on three frequently used plant counting datasets. The results demonstrate the excellent performance of the proposed method.

Wheat breeding heavily relies on the observation of various traits during the wheat growth process. Among all traits, wheat head density stands out as a particularly crucial characteristic. Despite the realization of high-throughput phenotypic data collection for wheat, the development of efficient and robust models for extracting traits from raw data remains a significant challenge. Numerous fully supervised target detection algorithms have been employed to address the wheat head detection problem. However, constrained by the exorbitant cost of dataset creation, especially the manual annotation cost, fully supervised target detection algorithms struggle to unleash their full potential. Semi-supervised training methods can leverage unlabeled data to enhance model performance, addressing the issue of insufficient labeled data. This paper introduces a one-stage anchor-based semi-supervised wheat head detector, named “Wheat Teacher”, which combines two semi-supervised methods, pseudo-labeling, and consistency regularization. Furthermore, two novel dynamic threshold components, Pseudo-label Dynamic Allocator and Loss Dynamic Threshold, are designed specifically for wheat head detection scenarios to allocate pseudo-labels and filter losses. We conducted detailed experiments on the largest wheat head public dataset, GWHD2021. Compared with various types of detectors, Wheat Teacher achieved a mAP0.5 of 92.8% with only 20% labeled data. This result surpassed the test outcomes of two fully supervised object detection models trained with 100% labeled data, and the difference with the other two fully supervised models trained with 100% labeled data was within 1%. Moreover, Wheat Teacher exhibits improvements of 2.1%, 3.6%, 5.1%, 37.7%, and 25.8% in mAP0.5 under different labeled data usage ratios of 20%, 10%, 5%, 2%, and 1%, respectively, validating the effectiveness of our semi-supervised approach. These experiments demonstrate the significant potential of Wheat Teacher in wheat head detection.