Research map / Time series / Foundation models for time series

Scalable Hierarchical Deep Neural Network for Time Series Analysis in Wearable Sensor-based Human Activity Recognition

AAAI 2025 · Time series › Foundation models for time series · approach: Time series classification · 2 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Doctoral-consortium style proposal for an adaptive hierarchical deep neural network with fuzzy logic and adaptive learning for interpretable, data-efficient time series classification and wearable-sensor human activity recognition.

Problem

Deep learning models for time series classification and HAR need large labeled datasets, substantial compute, and are hard to interpret; they also struggle with long-term dependencies and real-time deployment on wearables.

Approach

A multi-level hierarchical network processing time series at different temporal resolutions, combined with fuzzy logic rules and an adaptive learning module, aimed at reducing trainable parameters, data needs, and improving interpretability and noise robustness.

Key results

• No quantitative results are reported; the paper states only that a preliminary model is developed and that testing on real-world HAR datasets remains future work.

Limitations

• No experiments or quantitative results are presented.
• Adaptive learning module and extensive real-world testing are still unimplemented.
• Claims about convexity, noise robustness and data efficiency are asserted without evidence.

Experimental setup

Builds on: ResNet InceptionTime

Closest papers by meaning

• HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors (AAAI 2024 · similarity 0.85)
• Training Recurrent Neural Networks with Inherent Missing Data for Wearable Device Applications (Student Abstract) (AAAI 2025 · similarity 0.85)
• Scaling Wearable Foundation Models (ICLR 2025 · similarity 0.85)
• Hierarchical Classification Auxiliary Network for Time Series Forecasting (AAAI 2025 · similarity 0.84)
• MPTSNet: Integrating Multiscale Periodic Local Patterns and Global Dependencies for Multivariate Time Series Classification (AAAI 2025 · similarity 0.84)
• Generalizable Sensor-Based Activity Recognition via Categorical Concept Invariant Learning (AAAI 2025 · similarity 0.83)