首页> 外文会议>IEEE Global Conference on Consumer Electronics >Boat Noise Detection Using a Gated Recurrent Unit for Boat Notification System
【24h】

Boat Noise Detection Using a Gated Recurrent Unit for Boat Notification System

机译:船舶噪声检测使用Gated Recurrent单元进行船舶通知系统

获取原文

摘要

We aim to use machine learning to provide information on approaching noisy boats for people living near canals. Accordingly, we have studied boat noise detection using convolutional neural network (CNNs) and long short-term memory (LSTM) recurrent neural networks (RNN) models. The LSTM unit in the model has a complicated internal structure for time processing but a simpler alternative is the gated recurrent unit. Here, a GRU-RNN model classified boat noise (analysis time: 1 s) with accuracy of 0.935, which is 0.02 lower than that of the LSTM-RNN model and 0.01 higher than that of the than CNN model.
机译:我们的目标是使用机器学习,提供有关在运河附近的人们接近嘈杂船的信息。因此,我们研究了使用卷积神经网络(CNNS)和长短期存储器(LSTM)经常性神经网络(RNN)模型的船噪声检测。模型中的LSTM单元具有复杂的内部结构,用于时间处理,但更简单的替代方案是门控复发单元。这里,GRU-RNN模型分类船噪声(分析时间:1 s),精度为0.935,比LSTM-RNN模型低0.02,比比CNN模型高0.01。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号