no code implementations • 18 Jan 2024 • Sourish Gunesh Dhekane, Thomas Ploetz
In this survey, we focus on these transfer learning methods in the application domains of smart home and wearables-based HAR.
no code implementations • 22 Oct 2023 • Megha Thukral, Harish Haresamudram, Thomas Ploetz
Yet they can fail when the differences between source and target conditions are too large and/ or only few samples from a target application domain are available, each of which are typical challenges in real-world human activity recognition scenarios.
no code implementations • 1 Jun 2023 • Harish Haresamudram, Irfan Essa, Thomas Ploetz
Based on an extensive experimental evaluation on a suite of wearables-based benchmark HAR tasks, we demonstrate the potential of our learned discretization scheme and discuss how discretized sensor data analysis can lead to substantial changes in HAR.
1 code implementation • 22 May 2023 • Shuai Shao, Yu Guan, Bing Zhai, Paolo Missier, Thomas Ploetz
Specifically, with the introduction of three conceptual layers--Sampling Layer, Data Augmentation Layer, and Resilient Layer -- we develop three "boosters" -- R-Frame, Mix-up, and C-Drop -- to enrich the per-epoch training data by dense-sampling, synthesizing, and simulating, respectively.
no code implementations • 23 Dec 2022 • Shuai Shao, Yu Guan, Xin Guan, Paolo Missier, Thomas Ploetz
What remains a major challenge though is the sporadic activity recognition (SAR) problem, where activities of interest tend to be non periodic, and occur less frequently when compared with the often large amount of irrelevant background activities.
1 code implementation • 11 Nov 2022 • Harish Haresamudram, Irfan Essa, Thomas Ploetz
The dichotomy between the challenging nature of obtaining annotations for activities, and the more straightforward nature of data collection from wearables, has resulted in significant interest in the development of techniques that utilize large quantities of unlabeled data for learning representations.
no code implementations • 13 Oct 2022 • Daniel Scarafoni, Irfan Essa, Thomas Ploetz
We address dense action forecasting: the problem of predicting future action sequence over long durations based on partial observation.
1 code implementation • 19 Nov 2021 • Bing Zhai, Yu Guan, Michael Catt, Thomas Ploetz
Experimental results demonstrate important evidence that three-stage sleep can be reliably classified by fusing cardiac/movement sensing modalities, which may potentially become a practical tool to conduct large-scale sleep stage assessment studies or long-term self-tracking on sleep.
no code implementations • 20 May 2021 • Devleena Das, Yasutaka Nishimura, Rajan P. Vivek, Naoto Takeda, Sean T. Fish, Thomas Ploetz, Sonia Chernova
In this work, we build on insights from Explainable Artificial Intelligence (XAI) techniques and introduce an explainable activity recognition framework in which we leverage leading XAI methods to generate natural language explanations that explain what about an activity led to the given classification.
no code implementations • 29 Mar 2021 • Dan Scarafoni, Irfan Essa, Thomas Ploetz
Action prediction focuses on anticipating actions before they happen.
no code implementations • 9 Dec 2020 • Harish Haresamudram, Irfan Essa, Thomas Ploetz
Our work focuses on effective use of small amounts of labeled data and the opportunistic exploitation of unlabeled data that are straightforward to collect in mobile and ubiquitous computing scenarios.
1 code implementation • 12 Jul 2020 • Yuchao Ma, Andrew T. Campbell, Diane J. Cook, John Lach, Shwetak N. Patel, Thomas Ploetz, Majid Sarrafzadeh, Donna Spruijt-Metz, Hassan Ghasemzadeh
While activity recognition from inertial sensors holds potential for mobile health, differences in sensing platforms and user movement patterns cause performance degradation.
no code implementations • 29 May 2020 • Hyeokhyen Kwon, Catherine Tong, Harish Haresamudram, Yan Gao, Gregory D. Abowd, Nicholas D. Lane, Thomas Ploetz
The lack of large-scale, labeled data sets impedes progress in developing robust and generalized predictive models for on-body sensor-based human activity recognition (HAR).
no code implementations • 21 Feb 2019 • Yan Gao, Yang Long, Yu Guan, Anna Basu, Jessica Baggaley, Thomas Ploetz
We demonstrate the effectiveness of our approach in a study with 34 newborns (21 typically developing infants and 13 PS infants with abnormal movements).
1 code implementation • 26 Nov 2018 • BingZhang Hu, Yu Guan, Yan Gao, Yang Long, Nicholas Lane, Thomas Ploetz
Gait as a biometric trait has attracted much attention in many security and privacy applications such as identity recognition and authentication, during the last few decades.
no code implementations • 19 May 2018 • Vishvak S Murahari, Thomas Ploetz
Most approaches that model time-series data in human activity recognition based on body-worn sensing (HAR) use a fixed size temporal context to represent different activities.
no code implementations • 28 Mar 2017 • Yu Guan, Thomas Ploetz
We demonstrate, both formally and empirically, that Ensembles of deep LSTM learners outperform the individual LSTM networks.
no code implementations • 29 Apr 2016 • Nils Y. Hammerla, Shane Halloran, Thomas Ploetz
Human activity recognition (HAR) in ubiquitous computing is beginning to adopt deep learning to substitute for well-established analysis techniques that rely on hand-crafted feature extraction and classification techniques.