首页 > AI前沿 > HeteroWear: Sensor-Aware Self-Supervised Learning for Heterogeneous Wearable Activity Recognition

HeteroWear: Sensor-Aware Self-Supervised Learning for Heterogeneous Wearable Activity Recognition

arXiv机器学习 2026-11-14 07:58 15 阅读 查看原文
用户现在需要把给定的新闻正文排版成语义化HTML片段,首先看内容,都是学术类的段落,没有列表、引用、代码这些,首先第一部分是背景介绍,然后是提出HeteroWear,然后是技术细节,然后是实验结果,首先得划分小节吧?不对,先看内容结构,开头是背景,然后介绍框架,然后技术方法,然后实验评估,然后消融实验?首先,先想,首先,开头的背景可以作为引言?不对,按照规则,长文用h2/h3划分小节,首先,先确定几个小节:首先背景与问题,然后HeteroWear框架介绍,然后训练方法,然后实验评估,然后消融分析?不对,等下要保留所有信息,不能增删改。等下,先看原文的段落,原文是一整段?不对,原文的内容是连贯的,首先,先把内容拆分,首先,第一句是背景:Self-supervised learning for wearable sensing is usually confined to a single dataset or device family, leaving open whether representations transfer across heterogeneous sensor configurations and whether gains come from pretraining rather than architecture or richer sensor input. 这部分可以作为引言,然后

核心框架HeteroWear

,然后下一句We present HeteroWear...这部分是介绍框架的。然后

技术架构设计

,然后HeteroWear separates...这部分。然后

训练策略

,然后Training combines...这部分。然后

实验评估

,然后Under leave-one-dataset-out...这部分,还有Held-out-device...还有Under 50% test-time...。然后

消融分析

,然后Ablations show...这部分。不对,等下要准确,不要自己加内容?不对,标题的措辞不能改变原文内容哦?哦不对,规则是不能增删改内容,那h2/h3的标题是划分小节,内容都是原文的,不能改原文的文字,所以h2/h3的标题应该是用原文里的关键表述?不对,等下,不对,规则4是保留原文所有信息,不得增删改内容,所以不能自己编造标题内容?哦,不对,等下,我想想,比如,原文的结构和内容,首先,第一个自然段(背景)用p?不对,或者,正确的拆分: 首先,开头的背景部分是一个p?不对,再理清楚原文的内容分层: 1. 研究背景与现存问题:Self-supervised learning for wearable sensing is usually confined to a single dataset or device family, leaving open whether representations transfer across heterogeneous sensor configurations and whether gains come from pretraining rather than architecture or richer sensor input. 2. 提出的框架介绍:We present HeteroWear, a sensor-aware self-supervised framework pretrained on an eight-dataset wearable corpus (173 subjects, 358,261 windows) spanning inertial and physiological signals across body locations, devices, and sampling rates. 3. 技术架构:HeteroWear separates within-sensor temporal modeling from cross-sensor relational modeling using sensor-context embeddings, temporal and cross-sensor Transformers, and latent cross-attention fusion. 4. 训练方法:Training combines structured sensor dropout, cross-configuration consistency, and per-axis masked sensor modeling; missing sensors are omitted rather than reconstructed. 5. 实验结果(基准评估):Under leave-one-dataset-out pretraining and subject-disjoint evaluation on PAMAP2, WISDM, HHAR, HARTH, and UCI-HAR, HeteroWear improves mean macro-F1 from 0.688 to 0.724 over the identical architecture trained from scratch, with the largest gain on HHAR (0.823 versus 0.741), and achieves the highest macro-F1 on four of five benchmarks relative to single-accelerometer supervised baselines. 6. 跨设备评估:Held-out-device evaluation yields a mean +0.066 macro-F1 improvement. 7. 通道缺失鲁棒性评估:Under 50% test-time channel removal, HeteroWear retains 73.8% of full-channel performance versus 64.1% for the same architecture trained from scratch without sensor dropout. 8. 消融结果:Ablations show that structured sensor dropout primarily drives robustness, while cross-configuration consistency and sensor-context encoding contribute to transfer. 不对,但是h2/h3的标题需要是合理的,而且不能改变原文内容,哦不对,等下,规则里说长文用h2/h3划分小节,那标题的内容应该是对小节内容的概括,但是不能增删改原文的信息?不对,规则4是保留原文所有信息,不得增删改内容,就是说原文的文字不能改,不能加原文没有的信息,也不能删掉原文的信息。那h2/h3的标题是结构划分,应该用原文里的关键词?比如: 首先,开头的背景部分用

研究背景

?不对,会不会不符合?不对,等下,再看规则,规则3里的重要句子可以用strong,那重要的术语比如HeteroWear可以加strong?对哦,规则3说重要句子可用。 等下,重新来,正确的HTML结构: 首先,第一个部分是研究背景,作为第一个小节?

研究背景与问题

Self-supervised learning for wearable sensing is usually confined to a single dataset or device family, leaving open whether representations transfer across heterogeneous sensor configurations and whether gains come from pretraining rather than architecture or richer sensor input.

然后下一个小节是框架介绍:

核心框架HeteroWear

We present HeteroWear, a sensor-aware self-supervised framework pretrained on an eight-dataset wearable corpus (173 subjects, 358,261 windows) spanning inertial and physiological signals across body locations, devices, and sampling rates.

技术架构设计

HeteroWear separates within-sensor temporal modeling from cross-sensor relational modeling using sensor-context embeddings, temporal and cross-sensor Transformers, and latent cross-attention fusion.

训练策略

Training combines structured sensor dropout, cross-configuration consistency, and per-axis masked sensor modeling; missing sensors are omitted rather than reconstructed.

然后是实验评估的小节:

实验评估结果

Under leave-one-dataset-out pretraining and subject-disjoint evaluation on PAMAP2, WISDM, HHAR, HARTH, and UCI-HAR, HeteroWear improves mean macro-F1 from 0.688 to 0.724 over the identical architecture trained from scratch, with the largest gain on HHAR (0.823 versus 0.741), and achieves the highest macro-F1 on four of five benchmarks relative to single-accelerometer supervised baselines.

Held-out-device evaluation yields a mean +0.066 macro-F1 improvement.

Under 50% test-time channel removal, HeteroWear retains 73.8% of full-channel performance versus 64.1% for the same architecture trained from scratch without sensor dropout.

然后是消融分析的小节:

消融分析结论

Ablations show that structured sensor dropout primarily drives robustness, while cross-configuration consistency and sensor-context encoding contribute to transfer.

等下,会不会标题是我自己加的内容?不对,规则说不得增删改内容,那标题的概括算不算增改?哦,不对,等下,原文是一整段的学术文本,可能不需要硬加标题?不对,规则说长文用h2/h3划分小节,那原文的内容是长文,所以需要划分。等下,再仔细看规则4:“保留原文所有信息,不得增删改内容”,意思是原文的文字内容不能改动,不能增加原文没有的事实信息,但是结构划分的标签是排版用的,标题是对各部分内容的提炼,只要是准确的,不改变原意,不增加信息,是可以的?不对,或者,有没有可能,不需要加标题?不对,规则2说“长文用

/

划分小节”,所以这个文本是长文,需要划分。 等下,再调整,确保原文的每一个字都没有改,只是加了标签,重要的术语加strong,标题是合理的结构划分,