window.dataLayer = window.dataLayer || []; function gtag(){dataLayer.push(arguments);} gtag('js', new Date()); gtag('config', 'UA-115625534-1');
List

A Comprehensive Survey 

Human Activity Recognition Research Paper [link]

Nowadays, the aging population is becoming one of the world’s primary concerns. It is estimated that the population aged over 65 will increase from 461 million to 2 billion by 2050. Such a substantial increase in the elderly population will have significant social and health care consequences. To monitor older adults’ physical, functional, and cognitive health in their homes, Human Activity Recognition (HAR) is emerging as a powerful tool.  

Workflow showing daily environment sensors, preprocessing steps, pattern recognition techniques, and evaluation.

HAR’s goal is to recognize human activities of daily life (for example, walking, standing, sleeping, running, repose, watching TV, cooking, etc.) in controlled and uncontrolled settings.  

i-Heal’s lab director, Dr. Parisa Rashidi, teamed up with Dr. Florenc Demrozi and Dr. Graziano Pravadelli from University of Verona, Italy and Dr. Azra Bihorac from UF Prisma-P to review the latest advancements in HAR. 

This paper provides an in-depth systematic review of the state-of-the-art in HAR approaches, published from January 2015 to September 2019, based on Classic Machine Learning and Deep Learning, which make use of data collected by sensors (inertial or physiological), embedded into wearables or environment. 

Overview of the proposed survey structure on sensor-based
HAR research results from 2015 to 2019.

We surveyed methodologies based on sensor type, device type (smartphone, smartwatch, or standalone), preprocessing step (noise removal or feature extraction technique), and finally, their Deep Learning or Classic Machine Learning model. The results are presented in terms of a) average activity recognition accuracy, b) the average number of studied activities, and c) the average number of datasets used to test the methodology. 

We presented results both from the point of view of quality (accuracy) and quantity (number of recognized activities). We concluded that HAR researchers still prefer Classic Machine Learning models, mainly because they require a smaller amount of data and less computational power than Deep Learning models. However, the Deep Learning models have shown higher capacity in recognizing many complex activities.  

Future work in Human Activity Recognition applications should focus on developing more advanced generalization capabilities and recognition of more complex activities. 

Read the full research paper here.

  Category: Paper Release

10 posts
February 4th, 2021

Human Activity Recognition Using Inertial, Physiological and Environmental Sensors

A Comprehensive Survey  Human Activity Recognition Research Paper [link] Nowadays, the aging population is becoming one of the world’s primary […]

February 19th, 2019

News Coverage in UFHealth News

n a hospital’s intensive care unit, doctors get a cascade of data about each patient’s condition that can be challenging […]

August 29th, 2018

Survey on EHR Deep learning available on IEEE JBHI

Our survey paper on deep learning for EHR will appear in the September Issue of IEEE JBHI: Link  

April 30th, 2018

Intelligent ICU paper available on arXiv

Currently, many critical care indices are repetitively assessed and recorded by overburdened nurses, e.g. physical function or facial pain expressions […]

April 16th, 2018

CVPR Workshop paper accepted

CVPR workshop paper on activity recognition in the ICU is accepted. Congratulations to Anis and Kumar!   Patients staying in […]

April 16th, 2018

EMBC Paper accepted

Our EMBC paper is accepted, congratulations to Anis, Raha, and Paul!   Physiological timeseries such as vital signs contain important […]

March 13th, 2018

Paper on surgical team network structure is online

We examined the structure of intra- and postoperative case-collaboration networks among the surgical service providers in a quaternary-care academic medical […]

March 12th, 2018

Paper on the cover of IEEE JBHI

The prevalence of time-series data within the healthcare field necessitates the development of methods that can analyze the data in […]

March 12th, 2018

DeepSOFA beats your old SOFA score

Traditional methods for assessing illness severity and predicting in-hospital mortality among critically ill patients require manual, time-consuming, and error-prone calculations […]

March 10th, 2018

Paper available for open peer review

Chronic pain, including arthritis, affects about 100 million adults in the United States. Complexity and diversity of pain experience across […]