Ensemble Augmentation for Deep Neural Networks Using 1-D Time Series Vibration Data

稳健性(进化) 计算机科学 人工智能 模式识别(心理学) 人工神经网络 试验数据 集成学习 集合预报 训练集 机器学习 生物化学 基因 化学 程序设计语言
作者
Atik Faysal,Wai Keng Ngui,M. H. Lim,M. Salman Leong
出处
期刊:Journal of vibration engineering & technologies [Springer Science+Business Media]
卷期号:11 (5): 1987-2011 被引量:3
标识
DOI:10.1007/s42417-022-00683-w
摘要

Time-series data are one of the fundamental types of raw data representation used in data-driven techniques. In machine condition monitoring, time-series vibration data are overly used in data mining for deep neural networks. Typically, vibration data is converted into images for classification using Deep Neural Networks (DNNs), and scalograms are the most effective form of image representation. However, the DNN classifiers require huge labeled training samples to reach their optimum performance. So, many forms of data augmentation techniques are applied to the classifiers to compensate for the lack of training samples. However, the scalograms are graphical representations where the existing augmentation techniques suffer because they either change the graphical meaning or have too much noise in the samples that change the physical meaning. In this study, a data augmentation technique named ensemble augmentation is proposed to overcome this limitation. This augmentation method uses the power of white noise added in ensembles to the original samples to generate real-like samples. After averaging the signal with ensembles, a new signal is obtained that contains the characteristics of the original signal. The parameters for the ensemble augmentation are validated using a simulated signal. The proposed method is evaluated using 10 class bearing vibration data using three state-of-the-art Transfer Learning (TL) models, namely, Inception-V3, MobileNet-V2, and ResNet50. Augmented samples are generated in two increments: the first increment generates the same number of fake samples as the training samples, and in the second increment, the number of samples is increased gradually. The outputs from the proposed method are compared with no augmentation, augmentations using deep convolution generative adversarial network (DCGAN), and several geometric transformation-based augmentations...
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
保卫时光完成签到,获得积分10
刚刚
1秒前
过过关注了科研通微信公众号
1秒前
Akim应助张玉雪采纳,获得10
1秒前
封芷完成签到,获得积分10
1秒前
1秒前
剑指东方是为谁应助cc采纳,获得10
1秒前
2秒前
苗条砖家发布了新的文献求助10
2秒前
2秒前
balababa关注了科研通微信公众号
3秒前
zb发布了新的文献求助10
3秒前
3秒前
3秒前
5秒前
6秒前
6秒前
zho发布了新的文献求助10
6秒前
甜甜玫瑰应助战魂采纳,获得10
7秒前
7秒前
Ja完成签到,获得积分10
7秒前
7秒前
8秒前
852应助甜美的音响采纳,获得10
9秒前
顺心幻波完成签到,获得积分20
9秒前
快乐小霉完成签到,获得积分10
9秒前
9秒前
偶然的风41177完成签到,获得积分10
9秒前
酷波er应助科研通管家采纳,获得30
10秒前
CodeCraft应助科研通管家采纳,获得10
10秒前
科研通AI5应助科研通管家采纳,获得10
10秒前
科目三应助科研通管家采纳,获得10
10秒前
香蕉觅云应助科研通管家采纳,获得10
10秒前
天天快乐应助科研通管家采纳,获得10
10秒前
科研通AI5应助科研通管家采纳,获得30
10秒前
FashionBoy应助科研通管家采纳,获得10
10秒前
传奇3应助科研通管家采纳,获得10
10秒前
FashionBoy应助科研通管家采纳,获得10
10秒前
科研通AI5应助科研通管家采纳,获得10
10秒前
10秒前
高分求助中
Les Mantodea de Guyane Insecta, Polyneoptera 2500
Mobilization, center-periphery structures and nation-building 600
Technologies supporting mass customization of apparel: A pilot project 600
Introduction to Strong Mixing Conditions Volumes 1-3 500
China—Art—Modernity: A Critical Introduction to Chinese Visual Expression from the Beginning of the Twentieth Century to the Present Day 430
Multichannel rotary joints-How they work 400
Tip60 complex regulates eggshell formation and oviposition in the white-backed planthopper, providing effective targets for pest control 400
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 物理 生物化学 纳米技术 计算机科学 化学工程 内科学 复合材料 物理化学 电极 遗传学 量子力学 基因 冶金 催化作用
热门帖子
关注 科研通微信公众号,转发送积分 3796339
求助须知:如何正确求助?哪些是违规求助? 3341373
关于积分的说明 10306159
捐赠科研通 3057930
什么是DOI,文献DOI怎么找? 1677992
邀请新用户注册赠送积分活动 805746
科研通“疑难数据库(出版商)”最低求助积分说明 762775