paper-with-me

홈 › Papers

ShortFuse: Biomedical Time Series Representations in the Presence of Structured Information

2017-05-13 · Madalina Fiterau, Suvrat Bhooshan, Jason Fries, Charles Bournhonesque, Jennifer Hicks, Eni Halilaj, Christopher Ré, Scott Delp

In healthcare applications, temporal variables that encode movement, health status and longitudinal patient evolution are often accompanied by rich structured information such as demographics, diagnostics and medical exam data. However, current methods do not jointly optimize over structured covariates and time series in the feature extraction process. We present ShortFuse, a method that boosts the accuracy of deep learning models for time series by explicitly modeling temporal interactions and dependencies with structured covariates. ShortFuse introduces hybrid convolutional and LSTM cells that incorporate the covariates via weights that are shared across the temporal domain. ShortFuse outperforms competing models by 3% on two biomedical applications, forecasting osteoarthritis-related cartilage degeneration and predicting surgical outcomes for cerebral palsy patients, matching or exceeding the accuracy of models that use features engineered by domain experts.

📄 PDF Abstract BibTeX arXiv:1705.04790

Code (4)

Jungguchoi/Hybrid_CNN_with_1DCAE pytorch
MindSpore-scientific/code-8/tree/main/ShortFuse-Biomedical-Time-Series mindspore
pwc-1/Paper-9/tree/main/4/ShortFuse-Biomedical-Time-Series mindspore
pwc-1/Paper-9/tree/main/7/ShortFuse-Biomedical-Time-Series mindspore

Tasks

Time SeriesTime Series Analysis

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

Multi-Scale and Multi-Modal Contrastive Learning Network for Biomedical Time Series

2023-12-06 · Hongbo Guo, Xinzi Xu, Hao Wu, Guoxing Wang

Multi-modal biomedical time series (MBTS) data offers a holistic view of the physiological state, holding significant importance in various bio-medical applications. Owing to inherent noise and distribution gaps across d…

Activity RecognitionContrastive LearningHuman Activity RecognitionRepresentation Learning+1

Forecasting-based Biomedical Time-series Data Synthesis for Open Data and Robust AI

2025-10-06 · Youngjoon Lee, Seongmin Cho, Yehhyun Jo, Jinu Gong 외 arxiv

The limited data availability due to strict privacy regulations and significant resource demands severely constrains biomedical time-series AI development, which creates a critical gap between data requirements and acces…

Synthetic Data Generation

Learning compressed representations of blood samples time series with missing data

2017-10-20 · Filippo Maria Bianchi, Karl Øyvind Mikalsen, Robert Jenssen

Clinical measurements collected over time are naturally represented as multivariate time series (MTS), which often contain missing data. An autoencoder can learn low dimensional vectorial representations of MTS that pres…

General ClassificationMissing ValuesTime SeriesTime Series Analysis

SigTime: Learning and Visually Explaining Time Series Signatures

2025-12-12 · Yu-Chia Huang, Juntong Chen, Dongyu Liu, Kwan-Liu Ma arxiv

Understanding and distinguishing temporal patterns in time series data is essential for scientific discovery and decision-making. For example, in biomedical research, uncovering meaningful patterns in physiological signa…

Feature Engineering

BioFormer: Rethinking Cross-Subject Generalization via Spectral Structural Alignment in Biomedical Time-Series

2026-05-21 · Guikang Du, Haoran Li, Xinyu Liu, Zhibo Zhang 외 arxiv

Cross-subject generalization in biomedical time-series refers to training on data from some subjects and testing on unseen subjects.The key challenge is to suppress subject specific variability in BTS representations.Mos…