1 code implementation • 26 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.
no code implementations • 20 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.
1 code implementation • 22 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.
no code implementations • 22 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.
no code implementations • 25 Jun 2021 • Bishal Lamichhane, Dror Ben-Zeev, Andrew Campbell, Tanzeem Choudhury, Marta Hauser, John Kane, Mikio Obuchi, Emily Scherer, Megan Walsh, Rui Wang, Weichen Wang, Akane Sano
In this work, we investigated a machine learning based schizophrenia relapse prediction model using mobile sensing data to characterize behavioral features.
1 code implementation • 19 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.
1 code implementation • 16 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.
no code implementations • 22 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.
no code implementations • 24 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.
no code implementations • 12 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.
no code implementations • 7 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.
1 code implementation • 13 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.
no code implementations • 13 Oct 2022 • Han Yu, Huiyuan Yang, Akane Sano
But the view-learning method is not well developed for time-series data.
no code implementations • 21 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.
no code implementations • 17 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.
1 code implementation • 18 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.
no code implementations • 1 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.
no code implementations • 20 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.
no code implementations • 12 Apr 2024 • Zeyu Yang, Peikun Guo, Khadija Zanna, Akane Sano
Diffusion models have emerged as a robust framework for various generative tasks, such as image and audio synthesis, and have also demonstrated a remarkable ability to generate mixed-type tabular data comprising both continuous and discrete variables.
no code implementations • 12 Apr 2024 • Khadija Zanna, Akane Sano
To address these issues, we propose a bias mitigation method based on multi-task learning, utilizing the concept of Monte-Carlo dropout and Pareto optimality from multi-objective optimization.