Search Results for author: Thomas Ploetz

Found 20 papers, 5 papers with code

Transfer Learning in Human Activity Recognition: A Survey

no code implementations18 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.

Human Activity Recognition Transfer Learning

Cross-Domain HAR: Few Shot Transfer Learning for Human Activity Recognition

no code implementations22 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.

Human Activity Recognition Transfer Learning

Towards Learning Discrete Representations via Self-Supervision for Wearables-Based Human Activity Recognition

no code implementations1 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.

Human Activity Recognition Quantization

ConvBoost: Boosting ConvNets for Sensor-based Activity Recognition

1 code implementation22 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.

Data Augmentation Human Activity Recognition

Simple Yet Surprisingly Effective Training Strategies for LSTMs in Sensor-Based Human Activity Recognition

no code implementations23 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.

Human Activity Recognition Time Series Analysis

Investigating Enhancements to Contrastive Predictive Coding for Human Activity Recognition

1 code implementation11 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.

Human Activity Recognition Time Series +1

Finding Islands of Predictability in Action Forecasting

no code implementations13 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.

Ubi-SleepNet: Advanced Multimodal Fusion Techniques for Three-stage Sleep Classification Using Ubiquitous Sensing

1 code implementation19 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.

Open-Ended Question Answering

Explainable Activity Recognition for Smart Home Systems

no code implementations20 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.

Activity Recognition Explainable artificial intelligence +1

Contrastive Predictive Coding for Human Activity Recognition

no code implementations9 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.

Human Activity Recognition

Transfer Learning for Activity Recognition in Mobile Health

1 code implementation12 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.

Activity Recognition Transfer Learning

IMUTube: Automatic Extraction of Virtual on-body Accelerometry from Video for Human Activity Recognition

no code implementations29 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).

Human Activity Recognition

Towards Reliable, Automated General Movement Assessment for Perinatal Stroke Screening in Infants Using Wearable Accelerometers

no code implementations21 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).

Robust Cross-View Gait Recognition with Evidence: A Discriminant Gait GAN (DiGGAN) Approach

1 code implementation26 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.

Gait Identification Gait Recognition +1

On Attention Models for Human Activity Recognition

no code implementations19 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.

Human Activity Recognition Time Series +1

Ensembles of Deep LSTM Learners for Activity Recognition using Wearables

no code implementations28 Mar 2017 Yu Guan, Thomas Ploetz

We demonstrate, both formally and empirically, that Ensembles of deep LSTM learners outperform the individual LSTM networks.

Human Activity Recognition

Deep, Convolutional, and Recurrent Models for Human Activity Recognition using Wearables

no code implementations29 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.

Human Activity Recognition

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