A fabric-based hydrovoltaic electricity generator with multi-component carbon black for sustainable energy output.

Water evaporation-induced electricity generators are considered a promising green energy-harvesting technology to alleviate the increasingly serious fossil energy crisis. Previous water evaporation-induced electricity generators mainly focused on single component carbon black, limiting the improvements in energy output. At present, there are relatively few studies on multi-component carbon black for improving electricity-generation performance. Herein, inspired by plant transpiration, we designed a fabric-based water evaporation-induced electricity generator (FWEG) based on multi-component carbon black, which can maintain a voltage of 0.65 V for more than 48 h. Through the synergistic effect of multi-component carbon black-enhanced oxygen-containing functional density, the FWEG can generate an enhanced output current of 61.61 µA without any additional energy input. Moreover, we show that the FWEG can be integrated readily to charge commercial capacitors or directly power LED lights and calculators for a long time. This work provides new insights for designing high-performance hydrovoltaic electricity generators for sustainable green energy harvesting.

Dual-Tower Counterfactual Session-Aware Recommender System.

In the complex dynamics of modern information systems such as e-commerce and streaming services, managing uncertainty and leveraging information theory are crucial in enhancing session-aware recommender systems (SARSs). This paper presents an innovative approach to SARSs that combines static long-term and dynamic short-term preferences within a counterfactual causal framework. Our method addresses the shortcomings of current prediction models that tend to capture spurious correlations, leading to biased recommendations. By incorporating a counterfactual viewpoint, we aim to elucidate the causal influences of static long-term preferences on next-item selections and enhance the overall robustness of predictive models. We introduce a dual-tower architecture with a novel data augmentation process and a self-supervised training strategy, tailored to tackle inherent biases and unreliable correlations. Extensive experiments demonstrate the effectiveness of our approach, outperforming existing benchmarks and paving the way for more accurate and reliable session-based recommendations.