Guojian Wang

A fragment-based encryption and compression scheme for secure air-to-ground data transmission

Guojian Wang, Jianwei Tao

With the rapid development of civil aviation digitalization and the increasing demand for real-time communication between airborne systems and ground control stations, the security and efficiency of air-to-ground (ATG) data transmission has become a critical issue. Traditional data transmission frameworks are often …

cn (code pays fourni par la source)

Probing the dark ages and cosmic dawn with 21 cm global spectrum in the DSL mission

Yidong Xu, Chuang Xu, Yuewei Wen, Junqing Xia et autres

探索宇宙黑暗时代和黎明是鸿蒙项目的重要科学目标，这主要是通过对宇宙黑暗时代和黎明时代中性氢 产生的21cm全天平均频谱（又称21cm整体谱）进行探测。利用月球轨道的优越条件，鸿蒙计划的低频子星和高频子星将分别对0.1-30MHz、30-120MHz频段的全天平均谱进行测量，而避免电离层、电磁干扰、地面反射等地面实验的常见系统误差。本文介绍了标准宇宙学模型中宇宙黑暗时代和黎明时代各种物理过程对21cm全天平均频谱形状的影响，指出可以根据测得的21cm全天平均频谱获得关于宇宙演化的重要信息。同时，也指出由于不同宇宙模型参数以及前景辐射参数的简并性，单从21cm全天平均谱观测数据对宇宙学模型的辨别能力还是有限的，需综合多种观测手段，才能获得对宇宙早期演化历史的准确认识。

cn, Afrique du Sud (code pays fourni par la source)

Target-Aligned Fusion for Decision-Sequence Learning under Dynamics Shift

Guojian Wang, Quinson Hon, Xuyang Chen, Lin Zhao

External trajectories can improve offline decision-sequence learning, but dynamics shift may make some source subsequences inconsistent with the target environment. We study how to fuse such trajectories with limited target data for Decision Transformer learning under dynamics shift. We propose Target-Aligned Fusion …

Rapid trajectory planning under multiple constraints in unknown environments

Chenghong Xu, Wenjie Qi, Zhigang Zhang, Shuaishuai Ge et autres

cn (code pays fourni par la source)

Secure Transmission Technology Based on Air-to-Ground Aviation Networks

Guojian Wang, G. F. Xu, Zhiming Zheng, Jianping Li

In air-to-ground aviation networks, the high mobility of aircraft during flight and the uncertainty in the distribution of ground stations make communication links between the air and ground highly susceptible to interference and attacks. Therefore, designing an efficient and secure encryption and …

cn (code pays fourni par la source)

Uncertainty modified policy for multi-agent reinforcement learning

Xinyu Zhao, Jianxiang Liu, Faguo Wu, Xiao Zhang et autres

cn (code pays fourni par la source)

[Baroreflex failure syndrome after the resection of complex paragangliomas of head and neck: a case report].

Nan Wu, Guojian Wang, Weidong Shen, Pu Dai et autres

Protection of cranial nerves is one of the major challenges in the resection of paragangliomas of head and neck, especially in complex paragangliomas. We report a case of bilateral jugular tumor with unilateral carotid body tumor. Baroreflex failure syndrome（BFS） occurred after staged …

cn, us, my (code pays fourni par la source)

Preference-Guided Reinforcement Learning for Efficient Exploration

Guojian Wang, Faguo Wu, Xiao Zhang, Tianyuan Chen et autres

In this paper, we investigate preference-based reinforcement learning (PbRL), which enables reinforcement learning (RL) agents to learn from human feedback. This is particularly valuable when defining a fine-grain reward function is not feasible. However, this approach is inefficient and impractical for promoting …

CMBFSCNN: Cosmic Microwave Background Polarization Foreground Subtraction with Convolutional Neural Network

Ye-Peng Yan, Siyu Li, Guojian Wang, Zirui Zhang et autres

In our previous study, we introduced a machine-learning technique, namely CMBFSCNN, for the removal of foreground contamination in cosmic microwave background (CMB) polarization data. This method was successfully employed on actual observational data from the Planck mission. In this study, we extend …

Rapid trajectory planning under multiple constraints in unknown environment

Chenghong Xu, Wenjie Qi, Zhigang Zhang, Shuaishuai Ge et autres

Abstract In this work, we propose a rapid trajectory planning method based on robotic kinematic constraints, specifically applied to ground-based robot navigation in unknown environments. We address this by formulating a Quadratically Constrained Quadratic Program problem, integrating third-order polynomials and multiple motion …

cn (code pays fourni par la source)

Trajectory-Oriented Policy Optimization with Sparse Rewards

Guojian Wang, Faguo Wu, Xiao Zhang

The mastery of deep reinforcement learning (DRL) proves challenging when the environmental reward signals are sparse. These limited rewards indicate whether the task has been partially or entirely accomplished, and the agent must conduct various exploration actions before the agent receives meaningful …

cn (code pays fourni par la source)

Clinical Application of the 4K-3D Exoscope System in Cochlear Implantation

Honglei Zhang, Guojian Wang, Xin Zhang, Wei Liu et autres

PURPOSE: To evaluate a system for otomicrosurgery based on 4K three-dimensional (3D) exoscope technology and apply it to cochlear implantation. METHODS: An open stereoscopic vision-based surgical system, which differs from traditional surgical microscopes, was created by utilizing 4K stereo imaging technology and …

cn, us (code pays fourni par la source)