More Like this

1. Model-Agnostic Structural Transfer Learning for Cross-Domain Autonomous Activity Recognition

   https://doi.org/10.3390/s23146337  

   Alinia, Parastoo; Arefeen, Asiful; Ashari, Zhila Esna; Mirzadeh, Seyed Iman; Ghasemzadeh, Hassan (July 2023, Sensors)

   Activity recognition using data collected with smart devices such as mobile and wearable sensors has become a critical component of many emerging applications ranging from behavioral medicine to gaming. However, an unprecedented increase in the diversity of smart devices in the internet-of-things era has limited the adoption of activity recognition models for use across different devices. This lack of cross-domain adaptation is particularly notable across sensors of different modalities where the mapping of the sensor data in the traditional feature level is highly challenging. To address this challenge, we propose ActiLabel, a combinatorial framework that learns structural similarities among the events that occur in a target domain and those of a source domain and identifies an optimal mapping between the two domains at their structural level. The structural similarities are captured through a graph model, referred to as the dependency graph, which abstracts details of activity patterns in low-level signal and feature space. The activity labels are then autonomously learned in the target domain by finding an optimal tiered mapping between the dependency graphs. We carry out an extensive set of experiments on three large datasets collected with wearable sensors involving human subjects. The results demonstrate the superiority of ActiLabel over state-of-the-art transfer learning and deep learning methods. In particular, ActiLabel outperforms such algorithms by average F1-scores of 36.3%, 32.7%, and 9.1% for cross-modality, cross-location, and cross-subject activity recognition, respectively. 

   more » « less
2. Multi-Modal Recognition of Worker Activity for Human-Centered Intelligent Manufacturing

   https://doi.org/10.1016/j.engappai.2020.103868  

   Tao, W.; Leu, M.; Yin, Z. (October 2020, Engineering applications of artificial intelligence)

   This study aims at sensing and understanding the worker’s activity in a human-centered intelligent manufacturing system. We propose a novel multi-modal approach for worker activity recognition by leveraging information from different sensors and in different modalities. Specifically, a smart armband and a visual camera are applied to capture Inertial Measurement Unit (IMU) signals and videos, respectively. For the IMU signals, we design two novel feature transform mechanisms, in both frequency and spatial domains, to assemble the captured IMU signals as images, which allow using convolutional neural networks to learn the most discriminative features. Along with the above two modalities, we propose two other modalities for the video data, i.e., at the video frame and video clip levels. Each of the four modalities returns a probability distribution on activity prediction. Then, these probability distributions are fused to output the worker activity classification result. A worker activity dataset is established, which at present contains 6 common activities in assembly tasks, i.e., grab a tool/part, hammer a nail, use a power-screwdriver, rest arms, turn a screwdriver, and use a wrench. The developed multi-modal approach is evaluated on this dataset and achieves recognition accuracies as high as 97% and 100% in the leave-one-out and half-half experiments, respectively. 

   more » « less
3. Prediction of fall risk among community-dwelling older adults using a wearable system

   https://doi.org/10.1038/s41598-021-00458-5  

   Lockhart, Thurmon E.; Soangra, Rahul; Yoon, Hyunsoo; Wu, Teresa; Frames, Christopher W.; Weaver, Raven; Roberto, Karen A. (December 2021, Scientific Reports)

   Abstract Falls are among the most common cause of decreased mobility and independence in older adults and rank as one of the most severe public health problems with frequent fatal consequences. In the present study, gait characteristics from 171 community-dwelling older adults were evaluated to determine their predictive ability for future falls using a wearable system. Participants wore a wearable sensor (inertial measurement unit, IMU) affixed to the sternum and performed a 10-m walking test. Measures of gait variability, complexity, and smoothness were extracted from each participant, and prospective fall incidence was evaluated over the following 6-months. Gait parameters were refined to better represent features for a random forest classifier for the fall-risk classification utilizing three experiments. The results show that the best-trained model for faller classification used both linear and nonlinear gait parameters and achieved an overall 81.6 ± 0.7% accuracy, 86.7 ± 0.5% sensitivity, 80.3 ± 0.2% specificity in the blind test. These findings augment the wearable sensor's potential as an ambulatory fall risk identification tool in community-dwelling settings. Furthermore, they highlight the importance of gait features that rely less on event detection methods, and more on time series analysis techniques. Fall prevention is a critical component in older individuals’ healthcare, and simple models based on gait-related tasks and a wearable IMU sensor can determine the risk of future falls. 

   more » « less
4. Classification of aortic stenosis using conventional machine learning and deep learning methods based on multi-dimensional cardio-mechanical signals

   https://doi.org/10.1038/s41598-020-74519-6  

   Yang, Chenxi; Ojha, Banish D.; Aranoff, Nicole D.; Green, Philip; Tavassolian, Negar (October 2020, Scientific Reports)

   Abstract This paper introduces a study on the classification of aortic stenosis (AS) based on cardio-mechanical signals collected using non-invasive wearable inertial sensors. Measurements were taken from 21 AS patients and 13 non-AS subjects. A feature analysis framework utilizing Elastic Net was implemented to reduce the features generated by continuous wavelet transform (CWT). Performance comparisons were conducted among several machine learning (ML) algorithms, including decision tree, random forest, multi-layer perceptron neural network, and extreme gradient boosting. In addition, a two-dimensional convolutional neural network (2D-CNN) was developed using the CWT coefficients as images. The 2D-CNN was made with a custom-built architecture and a CNN based on Mobile Net via transfer learning. After the reduction of features by 95.47%, the results obtained report 0.87 on accuracy by decision tree, 0.96 by random forest, 0.91 by simple neural network, and 0.95 by XGBoost. Via the 2D-CNN framework, the transfer learning of Mobile Net shows an accuracy of 0.91, while the custom-constructed classifier reveals an accuracy of 0.89. Our results validate the effectiveness of the feature selection and classification framework. They also show a promising potential for the implementation of deep learning tools on the classification of AS. 

   more » « less
5. Unsupervised Adversarial Domain Adaptation in Wearable Physiological Sensing for Construction Workers’ Health Monitoring Using Photoplethysmography

   https://doi.org/10.1061/9780784485262.035  

   Gautam, Yogesh; Liu, Yizhi; Jebelli, Houtan (March 2024, Construction Research Congress 2024)

   Recent advancements in wearable physiological sensing and artificial intelligence have made some remarkable progress in workers’ health monitoring in construction sites. However, the scalable application is still challenging. One of the major complications for deployment has been the distribution shift observed in the physiological data obtained through sensors. This study develops a deep adversarial domain adaptation framework to adapt to out-of-distribution data(ODD) in the wearable physiological device based on photoplethysmography (PPG). The domain adaptation framework is developed and validated with reference to the heart rate predictor based on PPG. A heart rate predictor module comprising feature generating encoder and predictor isinitially trained with data from a given training domain. An unsupervised adversarial domain adaptation method is then implemented for the test domain. In the domain adaptation process, the encoder network is adapted to generate domain invariant features for the test domain using discriminator-based adversarial optimization. The results demonstrate that this approach can effectively accomplish domain adaptation, as evidenced by a 27.68% reduction in heart rate prediction error for the test domain. The proposed framework offers potential for scaled adaptation in the jobsite by addressing the ODD problem. 

   more » « less