This paper focuses on the robust beamforming for space-air-ground integrated networks (SAGIN) under uncertain channel state information (CSI). In SAGIN, uncertain CSI undermines the precise adjustment of beamforming, posing a major challenge to meeting users’ quality of service (QoS) requirements. To address this challenge, we first formulate the optimization problem as a quadratic program, which ensures a specified outage probability to maintain QoS. We then propose a multiple kernel-based machine learning method to model the uncertain CSI as an asymmetric convex polyhedron set. Leveraging semidefinite relaxation, the quadratic objective function is transformed into a linear function composed of beamforming matrix traces. Under the constructed CSI uncertainty set, a general robust transformation method is developed to linearly approximate the original probability constraints. Finally, we reformulate the joint optimization problem as a standard semidefinite program (SDP) and design an adaptive robust strategy to find its optimal solution. Simulation results show that our proposed method outperforms traditional robust and non-robust methods, effectively addressing limitations in existing SAGIN-related research.
Currently, recognition and assessment of human posture have become significant topics of interest, particularly through the use of visual sensor systems. These approaches can effectively address the drawbacks associated with traditional manual assessments, which include fatigue, variations in experience, and inconsistent judgment criteria. However, systems based on visual sensors encounter substantial implementation challenges when a large number of such sensors are used. To address these issues, we propose a human posture recognition and assessment system architecture, which comprises four distinct subsystems. Specifically, these subsystems include a Visual Sensor Subsystem (VSS), a Posture Assessment Subsystem (PAS), a Control-Display Subsystem, and a Storage Management Subsystem. Through the cooperation of subsystems, the architecture has achieved support for parallel data processing. Furthermore, the proposed architecture has been implemented by building an experimental testbed, which effectively verifies the rationality and feasibility of this architecture. In the experiments, the proposed architecture was evaluated by using pull-up and push-up exercises. The results demonstrate that the proposed architecture achieves an overall accuracy exceeding 96%, while exhibiting excellent real-time performance and scalability in different assessment scenarios.
Currently, recognition and assessment of human posture has become significant topics of interest, particularly through the use of visual sensor systems. These approaches can effectively address the drawbacks associated with traditional manual assessments, which include fatigue, variations in experience, and inconsistent judgment criteria. However, systems based on visual sensors encounter substantial implementation challenges when a large number of such sensors are used. To address these issues, we propose a human posture recognition and assessment system architecture, which comprises four distinct subsystems. Specifically, these subsystems include a Visual Sensor Subsystem (VSS), a Posture Assessment Subsystem (PAS), a Control-Display Subsystem, and a Storage Management Subsystem. Through the cooperation of subsystems, the architecture has achieved support for parallel data processing. Furthermore, the proposed architecture has been implemented by building an experimental testbed, which effectively verifies the rationality and feasibility of this architecture. In the experiments, the proposed architecture was evaluated by using pull-up and push-up exercises. The results demonstrate that the proposed architecture achieves an overall accuracy exceeding 96%, while exhibiting excellent real-time performance and scalability in different assessment scenarios.