论文标题
AI机械师：声载体表征神经网络
The AI Mechanic: Acoustic Vehicle Characterization Neural Networks
论文作者
论文摘要
在一个越来越依赖基于道路的运输的世界中，必须了解车辆。我们介绍了AI Mechanic，一种声音车辆表征深度学习系统，作为一种使用从移动设备捕获的声音来提高透明度和对车辆的理解及其对非专家用户的状况的集成方法。我们开发并实施了新颖的级联体系结构，以进行车辆理解，并将其定义为处理原始音频以提取高粒度见解的顺序，条件，多级网络。为了展示级联体系结构的生存能力，我们构建了一个多任务卷积神经网络，该网络可预测和级联车辆属性以增强故障检测。我们在综合数据集上训练和测试这些模型，该数据集反映了超过40个小时的增强音频，并在属性（燃料类型，发动机配置，圆柱体计数和吸气类型）上实现> 92％的验证设置精度。我们的级联体系结构还获得了93.6％的验证和86.8％的测试集准确性，这表明比幼稚和平行基线提高了16.4％ / 7.8％ / 7.8％和4.2％ / 1.5％的利润率。我们探讨了侧重于声学特征，数据增强，特征融合和数据可靠性的实验研究。最后，我们在讨论了这项工作的更广泛的含义，未来的方向和应用领域的讨论中结束。
In a world increasingly dependent on road-based transportation, it is essential to understand vehicles. We introduce the AI mechanic, an acoustic vehicle characterization deep learning system, as an integrated approach using sound captured from mobile devices to enhance transparency and understanding of vehicles and their condition for non-expert users. We develop and implement novel cascading architectures for vehicle understanding, which we define as sequential, conditional, multi-level networks that process raw audio to extract highly-granular insights. To showcase the viability of cascading architectures, we build a multi-task convolutional neural network that predicts and cascades vehicle attributes to enhance fault detection. We train and test these models on a synthesized dataset reflecting more than 40 hours of augmented audio and achieve >92% validation set accuracy on attributes (fuel type, engine configuration, cylinder count and aspiration type). Our cascading architecture additionally achieved 93.6% validation and 86.8% test set accuracy on misfire fault prediction, demonstrating margins of 16.4% / 7.8% and 4.2% / 1.5% improvement over naïve and parallel baselines. We explore experimental studies focused on acoustic features, data augmentation, feature fusion, and data reliability. Finally, we conclude with a discussion of broader implications, future directions, and application areas for this work.
