Feature Allocation for Semantic Communication with Space-Time Importance Awareness
In the realm of semantic communication, the significance of encoded features can vary, while wireless channels are known to exhibit fluctuations across multiple subchannels in different domains. Consequently, critical features may traverse subchannels with poor states, resulting in performance degradation. To tackle this challenge, we introduce a framework called Feature Allocation for Semantic Transmission (FAST), which offers adaptability to channel fluctuations across both spatial and temporal domains. In particular, an importance evaluator is first developed to assess the importance of various features. In the temporal domain, channel prediction is utilized to estimate future channel state information (CSI). Subsequently, feature allocation is implemented by assigning suitable transmission time slots to different features. Furthermore, we extend FAST to the space-time domain, considering two common scenarios: precoding-free and precoding-based multiple-input multiple-output (MIMO) systems. An important attribute of FAST is its versatility, requiring no intricate fine-tuning. Simulation results demonstrate that this approach significantly enhances the performance of semantic communication systems in image transmission. It retains its superiority even when faced with substantial changes in system configuration.
Code (0)
등록된 구현이 없습니다.
Tasks
AttributeSemantic CommunicationSimilar Papers 제목 키워드 기반
Resource allocation for text semantic communications
Semantic communications have shown its great potential to improve the transmission reliability, especially in the low signal-to-noise regime. However, resource allocation for semantic communications still remains unexplo…
Semantic CommunicationOFDM-Based Digital Semantic Communication with Importance Awareness
Semantic communication (SemCom) has received considerable attention for its ability to reduce data transmission size while maintaining task performance. However, existing works mainly focus on analog SemCom with simple c…
Deep Reinforcement LearningSemantic CommunicationIRS-Enhanced Secure Semantic Communication Networks: Cross-Layer and Context-Awared Resource Allocation
Learning-task oriented semantic communication is pivotal in optimizing transmission efficiency by extracting and conveying essential semantics tailored to specific tasks, such as image reconstruction and classification. …
Deep Reinforcement LearningImage ReconstructionSemantic CommunicationAdaptive Resource Allocation for Semantic Communication Networks
Semantic communication, recognized as a promising technology for future intelligent applications, has received widespread research attention. Despite the potential of semantic communication to enhance transmission reliab…
Deep Reinforcement LearningQuantizationSemantic CommunicationVision Transformer-based Semantic Communications With Importance-Aware Quantization
Semantic communications provide significant performance gains over traditional communications by transmitting task-relevant semantic features through wireless channels. However, most existing studies rely on end-to-end (…
image-classificationImage ClassificationImage CompressionQuantization+1