Yimei Yang

Many occluded and ambiguous ground truths exist in object detection, making detectors unable to obtain optimal training samples. In this article, we revisit the suboptimal sample issue in label assignment for object detection and propose a novel detector-agnostic strategy, termed FSS, to address it. FSS reformulates label assignment as the process of selecting high-quality sub-optimal samples and progressively transforming them into optimal ones. Specifically, for each candidate, we estimate the probability of being an optimal sample by jointly considering localization quality and classification confidence, thereby constructing an instance-wise probability matrix. Based on the spatial distribution of potentially optimal samples, we introduce a Gaussian prior to adaptively determine the number of sub-optimal samples per instance. We then assign weights to these sub-optimal samples according to their optimality probabilities, enforcing consistent ranking between classification and localization and promoting the emergence of truly optimal samples. Extensive experiments on MS-COCO demonstrate the effectiveness and plug-and-play nature of FSS: when integrated into a modern one-stage detector, FSS achieves 50.8 AP under single-model, single-scale testing, without introducing any additional inference overhead.

This study, based on engineering education accreditation standards, addresses the supply–demand imbalance in China’s cybersecurity talent cultivation by constructing a sustainable “education-industry-society” collaborative model. Through case studies at Huaihua University and other institutions, employing methods such as literature analysis, field research, and empirical investigation, we systematically explore reform pathways for an innovative cybersecurity talent development system. The research proposes a “three-platform, four-module” practical teaching framework, where the coordinated operation of the basic skills training platform, comprehensive ability development platform, and innovation enhancement platform significantly improves students’ engineering competencies (practical courses account for 41.6% of the curriculum). Findings demonstrate that eight industry-academia practice bases established through deep collaboration effectively align teaching content with industry needs, substantially enhancing students’ innovative and practical abilities (172 national awards, 649 provincial awards). Additionally, the multi-dimensional evaluation mechanism developed in this study enables a comprehensive assessment of students’ professional skills, practical capabilities, and innovative thinking. These reforms have increased the employment rate of cybersecurity graduates to over 90%, providing a replicable solution to China’s talent shortage. The research outcomes offer valuable insights for discipline development under engineering education accreditation and contribute to implementing sustainable development concepts in higher education.

Temperature prediction plays a crucial role across various sectors, including agriculture and climate research. Understanding weather patterns, seasonal shifts, and climate dynamics heavily relies on accurate temperature forecasts. This paper presents an innovative hybrid method, EEMD-LR, that combines ensemble empirical mode decomposition (EEMD) with linear regression (LR) for temperature prediction. EEMD is used to decompose temperature signals into stable sub-signals, enhancing their predictability. LR is then applied to forecast each sub-signal, and the resulting predictions are integrated to obtain the final temperature forecast. The proposed EEMD-LR model achieved RMSE, MAE, and R² values of 0.000027, 0.000021, and 1.000000, respectively, on the sine simulation time-series data used in this study. For actual temperature time-series data, the model achieved RMSE, MAE, and R² values of 0.713150, 0.512700, and 0.994749, respectively. The experimental results on these two datasets indicate that the EEMD-LR model demonstrates superior predictive performance compared to alternative methods.

In view of the problems that the current rural land data detection is not timely, the degree of intelligence is backward, and the risk discovery and prediction is not timely, the smart "farmer" rural land risk prediction system is developed through the modern technology of Big data, artificial intelligence, agricultural Internet of Things and modern sensing equipment. Based on the Spring Boot framework, the system mainly realizes the functions of viewing rural land data and risk prediction. Through the innovation of visualization technology in the intelligent "farmer" rural land risk prediction system and the application of deep learning technology in artificial intelligence, it is possible to better display the current data situation of rural land intuitively, achieve more timely real-time supervision, and make timely adjustments and repairs based on the predicted risk information of the system. This helps to make rural land and planting more intelligent, scientific, and systematic, improving the control of land and crop information, which is of great research and development significance for the intelligent development of modern rural land.