Shouliang Li

Medical lesion segmentation remains challenging due to ambiguous boundaries, heterogeneous appearances, and the limited ability of visual features alone to capture clinically meaningful semantics. Existing vision-language segmentation methods have demonstrated the value of textual guidance, but they often rely on fixed or shared textual representations across different decoder stages, despite the fact that visual features progressively evolve from coarse semantic representations to finer spatial details. To address this stage-wise representation mismatch, we propose SAF-Net, a stage-aware vision-language segmentation framework that couples stage-specific semantic allocation with frequency-refined progressive decoding. Specifically, Adaptive Hierarchical Text Allocation (AHTA) retains the hidden representations from all layers of a frozen medical language encoder and learns independent layer-mixing distributions for different text-guided decoder stages, enabling stage-specific semantic guidance without manually predefined layer-to-stage correspondence. Meanwhile, Frequency-Gated Spatial-aware Channel Attention (FGSCA) refines the incoming decoder features through complementary frequency-aware spatial-channel modeling before cross-modal interaction. By coordinating hierarchical textual semantics with frequency-aware visual refinement across progressive decoding stages, SAF-Net allows the representations participating in multimodal interaction to better adapt to the changing requirements of hierarchical decoding. Extensive experiments on QaTa-COV19 and MosMedData+ demonstrate the effectiveness and competitiveness of the proposed framework.

Pseudo-random number generators (PRNGs) are important cornerstones of many fields, such as statistical analysis and cryptography, and the need for PRNGs for information security (in fields such as blockchain, big data, and artificial intelligence) is becoming increasingly prominent, resulting in a steadily growing demand for high-speed, high-quality random number generators. To meet this demand, the multiple deep-dynamic transformation (MDDT) algorithm is innovatively developed. This algorithm is incorporated into the skewed tent map, endowing it with more complex dynamical properties. The improved one-dimensional discrete chaotic mapping method is effectively realized on a field-programmable gate array (FPGA), specifically the Xilinx xc7k325tffg900-2 model. The proposed pseudo-random number generator (PRNG) successfully passes all evaluations of the National Institute of Standards and Technology (NIST) SP800-22, diehard, and TestU01 test suites. Additional experimental results show that the PRNG, possessing high novelty performance, operates efficiently at a clock frequency of 150 MHz, achieving a maximum throughput of 14.4 Gbps. This performance not only surpasses that of most related studies but also makes it exceptionally suitable for embedded applications.

Forest fires pose a catastrophic threat to Earth’s ecology as well as threaten human beings. Timely and accurate monitoring of forest fires can significantly reduce potential casualties and property damage. Thus, to address the aforementioned problems, this paper proposed an unmanned aerial vehicle (UAV) based on a lightweight forest fire recognition model, Fire-Net, which has a multi-stage structure and incorporates cross-channel attention following the fifth stage. This is to enable the model’s ability to perceive features at various scales, particularly small-scale fire sources in wild forest scenes. Through training and testing on a real-world dataset, various lightweight convolutional neural networks were evaluated on embedded devices. The experimental outcomes indicate that Fire-Net attained an accuracy of 98.18%, a precision of 99.14%, and a recall of 98.01%, surpassing the current leading methods. Furthermore, the model showcases an average inference time of 10 milliseconds per image and operates at 86 frames per second (FPS) on embedded devices.