With the proliferation and rapid evolution of new psychoactive substances (NPSs), traditional database-based search methods face increasing challenges in identifying NPS seizures with complex compositions, thereby complicating their regulation and early warning. To address this issue, CBMAFF-Net (CNN BiLSTM Multistep Attentional Feature Fusion Network) is proposed as an intelligent screening method to rapidly classify unknown confiscated substances using ¹³C nuclear magnetic resonance (NMR) and ¹H NMR data. Initially, we utilize the synergy of a convolutional neural network (CNN) and bidirectional long short-term memory network (BiLSTM) to extract the global and local features of the NMR data. These features are sequentially fused through a weighted approach guided by an attention mechanism, thoroughly capturing the essential NPS information. We evaluated the model on a generated simulated data set, where it performed with 99.8% accuracy and a 99.8% F1 score. Additionally, testing on 42 actual seizure cases yielded a recognition accuracy of 97.6%, significantly surpassing the performance of conventional database-based similarity search algorithms. These findings suggest that the proposed method holds substantial promise for the rapid screening and classification of NPSs.

中文翻译：

---

CBMAFF-Net：一种基于智能 NMR 的新型精神活性物质非靶向筛选方法


随着新精神活性物质 （NPS） 的扩散和快速进化，传统的基于数据库的搜索方法在识别成分复杂的 NPS 癫痫发作方面面临越来越大的挑战，从而使它们的监管和早期预警复杂化。针对这一问题，提出了一种智能筛选方法CBMAFF-Net（CNN BiLSTM Multistep Attentional Feature Fusion Network），利用¹³C核磁共振（NMR）和¹H NMR数据对未知没收物质进行快速分类。最初，我们利用卷积神经网络 （CNN） 和双向长短期记忆网络 （BiLSTM） 的协同作用来提取 NMR 数据的全局和局部特征。这些特征通过由注意力机制指导的加权方法依次融合，彻底捕获基本的 NPS 信息。我们在生成的模拟数据集上评估了该模型，其性能准确率为 99.8%，F1 得分为 99.8%。此外，对 42 个实际查获案例的测试产生了 97.6% 的识别准确率，大大超过了传统的基于数据库的相似性搜索算法的性能。这些发现表明，所提出的方法为 NPS 的快速筛选和分类具有重大前景。