Gansu Academy of Sciences

Music emotion recognition and generation play a vital role in creating emotionally resonant experiences in human-computer interaction. Deep reinforcement learning (DRL) offers promising capabilities for dynamically modeling and generating music aligned with human emotional states. However, existing methods often struggle with rigid emotional mapping, a lack of real-time adaptability, and limited generalization across diverse musical contexts. To address these limitations, this study proposes an Emotion-Conditioned Deep Reinforcement Learning (EC-DRL) framework that integrates emotion-aware representations into the reward mechanism of a DRL agent. The system employs deep neural networks to extract high-level audio features and map them onto valence-arousal emotion space, guiding the music generation process through a reinforcement learning policy optimized for emotional congruence. This framework is applied in adaptive soundtrack generation for interactive applications such as video games, where music responds dynamically to emotional cues derived from gameplay and user interactions. Experimental results demonstrate that the EC-DRL framework significantly improves emotional accuracy, coherence, and user satisfaction compared to traditional sequence-based generation models. The proposed system shows the potential for creating emotionally intelligent music systems that can adapt in real-time and produce expressive musical output. EC-DRL achieves the mapping accuracy by 98%, emotional congruence score by 0.9%, real-time responsiveness by 280 ms, reward function optimization by 9.5%, audio feature extraction quality by 86%, policy convergence rate by 0.8%, user satisfaction score by 8.9%, and cross-domain generalization by 88%.

Abstract High-volume-fraction SiCp/6092Al composites exhibit significant potential for applications in aerospace, automotive manufacturing, and precision instrumentation, attributable to their exceptional lightweight characteristics, high strength, excellent thermal conductivity, and wear resistance. This study systematically examines the tribological behavior and surface damage evolution mechanisms of a 55% volume fraction SiCp/6092Al composite under loads ranging from 20 N to 50 N. The results demonstrate that the friction coefficient increases markedly from 0.388 to 0.475 as the load rises from 20 N to 30 N, stabilizing thereafter. The wear volume displays a linear relationship with load, peaking at 0.033 mm 3 at 50 N. Microstructural analysis indicates that, at a low load of 20 N, the wear scar surface remains relatively smooth, exhibiting only minor scratches. In contrast, at a load of 50 N, the wear depth and width increase by 3 times and 1.6 times, respectively, compared to the 20 N condition, signifying accelerated surface damage. At the high load of 50 N, the wear scar area reveals numerous deep grooves and material spalling. This study elucidates the critical load effect and the evolution of tribological properties in high-volume-fraction SiCp/6092Al composites, thereby providing essential theoretical foundations and practical guidance for the design and engineering of new high-performance aluminum-matrix composites.

BackgroundRhizosphere microorganisms play a critical role in plant growth and medicinal quality, yet their altitudinal patterns and interactions with soil nutrients and bioactive compounds in Angelica sinensis (A. sinensis) remain poorly understood.MethodsUsing Illumina MiSeq sequencing, we analyzed bacterial, fungal, arbuscular mycorrhizal (AM) fungal, and archaeal diversity across an altitudinal gradient, alongside soil physicochemical characteristics and bioactive components.ResultsAs cultivation elevation increased, bacterial and fungal diversity initially increased significantly and then stabilized (p < 0.05). In contrast, AM fungal and archaeal communities remained relatively stable. Bacterial communities varied significantly across altitudes (stress < 0.1, p = 0.001), as did soil nutrients and enzyme activities (p < 0.05). Bioactive components, except for ferulic acid, varied significantly with altitude. Redundancy analysis (RDA) confirmed that altitude and soil factors are key drivers of microbial community assembly. Mantel tests and structural equation modeling (SEM) demonstrated significant correlations between soil properties, microbial diversity, and medicinal properties of A. sinensis (p < 0.05).ConclusionThe mid-to high elevation zone (2520–2717 m) was identified as optimal for both yield and bioactive compound accumulation. These findings deepen the understanding of how microbes adapt to different altitudes in medicinal plants and offer a framework for precise cultivation of A. sinensis, thereby supporting the high-altitude symbiosis theory.