Contrastive Self-Supervised Representation Learning for Sensing Signals from the Time-Frequency Perspective

计算机科学 人工智能 深度学习 卷积神经网络 特征学习 机器学习 监督学习 代表(政治) 人工神经网络 政治学 政治 法学
作者
Dongxin Liu,Tianshi Wang,Shengzhong Liu,Ruijie Wang,Shuochao Yao,Tarek Abdelzaher
出处
期刊:International Conference on Computer Communications and Networks 卷期号:: 1-10 被引量:28
标识
DOI:10.1109/icccn52240.2021.9522151
摘要

This paper presents a contrastive self-supervised representation learning framework that is new in being designed specifically for deep learning from frequency domain data. Contrastive self-supervised representation learning trains neural networks using mostly unlabeled data. It is motivated by the need to reduce the labeling burden of deep learning. In this paper, we are specifically interested in applying this approach to physical sensing scenarios, such as those arising in Internet-of-Things (IoT) applications. Deep neural networks have been widely utilized in IoT applications, but the performance of such models largely depends on the availability of large labeled datasets, which in turn entails significant training costs. Motivated by the success of contrastive self-supervised representation learning at substantially reducing the need for labeled data (mostly in areas of computer vision and natural language processing), there is growing interest in customizing the contrastive learning framework to IoT applications. Most existing work in that space approaches the problem from a time-domain perspective. However, IoT applications often measure physical phenomena, where the underlying processes (such as acceleration, vibration, or wireless signal propagation) are fundamentally a function of signal frequencies and thus have sparser and more compact representations in the frequency domain. Recently, this observation motivated the development of Short-Time Fourier Neural Networks (STFNets) that learn directly in the frequency domain, and were shown to offer large performance gains compared to Convolutional Neural Networks (CNNs) when designing supervised learning models for IoT tasks. Hence, in this paper, we introduce an STFNet-based Contrastive Self-supervised representation Learning framework (STF-CSL). STF-CSL takes both time-domain and frequency-domain features into consideration. We build the encoder using STFNet as the fundamental building block. We also apply both time-domain data augmentation and frequency-domain data augmentation during the self-supervised training process. We evaluate the resulting performance of STF-CSL on various human activity recognition tasks. The evaluation results demonstrate that STF-CSL significantly outperforms the time-domain based self-supervised approaches thereby substantially enhancing our ability to train deep neural networks from unlabeled data in IoT contexts.

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
东方自远完成签到,获得积分10
刚刚
1秒前
Orange的应助被659采纳,获得10
1秒前
求求完成签到,获得积分10
1秒前
传奇3的应助被yu采纳,获得10
1秒前
乐乐的应助被洋小忆采纳,获得10
2秒前
ding的应助被huifeideyu采纳,获得10
2秒前
宛若晴空完成签到 ,获得积分10
3秒前
ZM完成签到 ,获得积分10
3秒前
英姑的应助被科研通管家采纳,获得10
3秒前
慕青的应助被科研通管家采纳,获得10
3秒前
打打的应助被科研通管家采纳,获得10
4秒前
菜鸟完成签到,获得积分10
4秒前
Orange的应助被科研通管家采纳,获得10
4秒前
完美世界的应助被科研通管家采纳,获得10
4秒前
小马甲的应助被科研通管家采纳,获得10
4秒前
爆米花的应助被科研通管家采纳,获得10
4秒前
4秒前
嘻嘻哈哈的应助被科研通管家采纳,获得10
4秒前
4秒前
脑洞疼的应助被科研通管家采纳,获得10
5秒前
5秒前
null的应助被科研通管家采纳,获得10
5秒前
彭于晏的应助被小太阳采纳,获得10
5秒前
5秒前
在水一方的应助被科研通管家采纳,获得20
5秒前
科目三的应助被科研通管家采纳,获得10
5秒前
大模型的应助被xi采纳,获得10
5秒前
bkagyin的应助被科研通管家采纳,获得10
5秒前
情怀的应助被科研通管家采纳,获得10
5秒前
xiangrug发布了新的文献求助10
6秒前
诚心逍遥发布了新的文献求助10
6秒前
Jun的应助被科研通管家采纳,获得20
6秒前
田様的应助被科研通管家采纳,获得10
6秒前
Ava的应助被科研通管家采纳,获得10
6秒前
嘻嘻哈哈的应助被科研通管家采纳,获得10
6秒前
大个的应助被科研通管家采纳,获得10
6秒前
zyl完成签到,获得积分10
6秒前
6秒前
null的应助被科研通管家采纳,获得10
6秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
Grapes 1000
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8178521
求助须知:如何正确求助?哪些是违规求助? 9569377
关于积分的说明 21803750
捐赠科研通 7773465
什么是DOI,文献DOI怎么找? 3432844
关于科研通互助平台的介绍 2556838
邀请新用户注册赠送积分活动 2478444