Search Results for author: Akane Sano

Found 18 papers, 6 papers with code

SleepNet: Attention-Enhanced Robust Sleep Prediction using Dynamic Social Networks

no code implementations20 Jan 2024 Maryam Khalid, Elizabeth B. Klerman, Andrew W. McHill, Andrew J. K. Phillips, Akane Sano

Monitoring and predicting sleep behavior with ubiquitous sensors may therefore assist in both sleep management and tracking of related health conditions.


ECG-SL: Electrocardiogram(ECG) Segment Learning, a deep learning method for ECG signal

no code implementations1 Oct 2023 Han Yu, Huiyuan Yang, Akane Sano

In this work, we propose a novel ECG-Segment based Learning (ECG-SL) framework to explicitly model the periodic nature of ECG signals.

Attribute Self-Supervised Learning +1

Empirical Study of Mix-based Data Augmentation Methods in Physiological Time Series Data

1 code implementation18 Sep 2023 Peikun Guo, Huiyuan Yang, Akane Sano

In this study, we systematically review the mix-based augmentations, including mixup, cutmix, and manifold mixup, on six physiological datasets, evaluating their performance across different sensory data and classification tasks.

Data Augmentation Time Series +1

PiRL: Participant-Invariant Representation Learning for Healthcare Using Maximum Mean Discrepancy and Triplet Loss

no code implementations17 Feb 2023 Zhaoyang Cao, Han Yu, Huiyuan Yang, Akane Sano

Due to individual heterogeneity, person-specific models are usually achieving better performance than generic (one-size-fits-all) models in data-driven health applications.

Representation Learning

PiRL: Participant-Invariant Representation Learning for Healthcare

no code implementations21 Nov 2022 Zhaoyang Cao, Han Yu, Huiyuan Yang, Akane Sano

Due to individual heterogeneity, performance gaps are observed between generic (one-size-fits-all) models and person-specific models in data-driven health applications.

Representation Learning

Empirical Evaluation of Data Augmentations for Biobehavioral Time Series Data with Deep Learning

1 code implementation13 Oct 2022 Huiyuan Yang, Han Yu, Akane Sano

As an effective technique to increase the data variability and thus train deep models with better generalization, data augmentation (DA) is a critical step for the success of deep learning models on biobehavioral time series data.

Data Augmentation Time Series +1

Bias Reducing Multitask Learning on Mental Health Prediction

no code implementations7 Aug 2022 Khadija Zanna, Kusha Sridhar, Han Yu, Akane Sano

However, there is still a lack of standard in evaluating bias in such machine learning models in the field, which leads to challenges in providing reliable predictions and in addressing disparities.

Fairness Feature Importance +2

Exploiting Social Graph Networks for Emotion Prediction

no code implementations12 Jul 2022 Maryam Khalid, Akane Sano

To this end, we leverage phone data to construct social networks and develop a machine learning architecture that aggregates information from multiple users of the graph network and integrates it with the temporal dynamics of data to predict emotion for all the users.

Psychotic Relapse Prediction in Schizophrenia Patients using A Mobile Sensing-based Supervised Deep Learning Model

no code implementations24 May 2022 Bishal Lamichhane, Joanne Zhou, Akane Sano

The CrossCheck dataset consisting of continuous mobile sensing data obtained from 63 schizophrenia patients, each monitored for up to a year, was used for our evaluations.

Anomaly Detection

Semi-Supervised Learning and Data Augmentation in Wearable-based Momentary Stress Detection in the Wild

no code implementations22 Feb 2022 Han Yu, Akane Sano

We first applied data augmentation techniques on the physiological and behavioral data to improve the robustness of supervised stress detection models.

Data Augmentation

More to Less (M2L): Enhanced Health Recognition in the Wild with Reduced Modality of Wearable Sensors

1 code implementation16 Feb 2022 Huiyuan Yang, Han Yu, Kusha Sridhar, Thomas Vaessen, Inez Myin-Germeys, Akane Sano

For example, although combining bio-signals from multiple sensors (i. e., a chest pad sensor and a wrist wearable sensor) has been proved effective for improved performance, wearing multiple devices might be impractical in the free-living context.

Transfer Learning

Modality Fusion Network and Personalized Attention in Momentary Stress Detection in the Wild

1 code implementation19 Jul 2021 Han Yu, Thomas Vaessen, Inez Myin-Germeys, Akane Sano

Compared to the baseline method using the samples with complete modalities, the performance of the MFN improved by 1. 6% in f1-scores.

Transfer Learning

Forecasting Health and Wellbeing for Shift Workers Using Job-role Based Deep Neural Network

1 code implementation22 Jun 2021 Han Yu, Asami Itoh, Ryota Sakamoto, Motomu Shimaoka, Akane Sano

According to the differences in self-reported health and wellbeing labels between nurses and doctors, and the correlations among their labels, we proposed a job-role based multitask and multilabel deep learning model, where we modeled physiological and behavioral data for nurses and doctors simultaneously to predict participants' next day's multidimensional self-reported health and wellbeing status.

Routine Clustering of Mobile Sensor Data Facilitates Psychotic Relapse Prediction in Schizophrenia Patients

no code implementations22 Jun 2021 Joanne Zhou, Bishal Lamichhane, Dror Ben-Zeev, Andrew Campbell, Akane Sano

The clustering model based features, together with other features characterizing the mobile sensing data, resulted in an F2 score of 0. 24 for the relapse prediction task in a leave-one-patient-out evaluation setting.


Sensor-Based Estimation of Dim Light Melatonin Onset (DLMO) Using Features of Two Time Scales

no code implementations20 Aug 2019 Cheng Wan, Andrew W. McHill, Elizabeth Klerman, Akane Sano

The results using data from 207 undergraduates show that our two-step model with two time-scale features has statistically significantly lower root-mean-square errors than models that use either daily sampled data or frequently sampled data.

Multimodal Autoencoder: A Deep Learning Approach to Filling In Missing Sensor Data and Enabling Better Mood Prediction

1 code implementation26 Oct 2017 Natasha Jaques, Sara Taylor, Akane Sano, Rosalind W. Picard

To accomplish forecasting of mood in real-world situations, affective computing systems need to collect and learn from multimodal data collected over weeks or months of daily use.


Cannot find the paper you are looking for? You can Submit a new open access paper.