Hierarchical multi-view aggregation network for sensor-based human activity recognition.

08:00 EDT 12th September 2019 | BioPortfolio

Summary of "Hierarchical multi-view aggregation network for sensor-based human activity recognition."

Sensor-based human activity recognition aims at detecting various physical activities performed by people with ubiquitous sensors. Different from existing deep learning-based method which mainly extracting black-box features from the raw sensor data, we propose a hierarchical multi-view aggregation network based on multi-view feature spaces. Specifically, we first construct various views of feature spaces for each individual sensor in terms of white-box features and black-box features. Then our model learns a unified representation for multi-view features by aggregating views in a hierarchical context from the aspect of feature level, position level and modality level. We design three aggregation modules corresponding to each level aggregation respectively. Based on the idea of non-local operation and attention, our fusion method is able to capture the correlation between features and leverage the relationship across different sensor position and modality. We comprehensively evaluate our method on 12 human activity benchmark datasets and the resulting accuracy outperforms the state-of-the-art approaches.


Journal Details

This article was published in the following journal.

Name: PloS one
ISSN: 1932-6203
Pages: e0221390


DeepDyve research library

PubMed Articles [33086 Associated PubMed Articles listed on BioPortfolio]

Multi-angle-view monocular camera using a polarization image sensor.

A wide-angle view can be conventionally acquired with a monocular camera by means of a fish-eye lens. However, the acquired image using the fish-eye lens is generally distorted with a view angle of le...

oComm: Overlapping Community Detection in Multi-view Brain Network.

Many efforts have been made on developing multi-view network community detection approaches. However, most of them can only reveal non-overlapping community structure. In this paper, we propose a nove...

Multi-view Linear Discriminant Analysis Network.

In many real-world applications, an object can be described from multiple views or styles, leading to the emerging multi-view analysis. To eliminate the complicated (usually highly nonlinear) view dis...

Deep multi-view feature learning for EEG-based epileptic seizure detection.

Epilepsy is a neurological illness caused by abnormal discharge of brain neurons, where epileptic seizure can lead to life-threatening emergencies. By analyzing the encephalogram (EEG) signals of pati...

Hierarchical complexity of the adult human structural connectome.

The structural network of the human brain has a rich topology which many have sought to characterise using standard network science measures and concepts. However, this characterisation remains incomp...

Clinical Trials [11713 Associated Clinical Trials listed on BioPortfolio]

Sensor-supported Classification of Gait Patterns in Everyday Movement of Patients With Parkinson's Disease

Within this study we conduct long-term measurements on Parkinson patients using a three sensor IMU setup: one sensor is located at the wrist, one sensor at the belt/ in the pocket and one ...

Human CNS Tau Kinetics in Tauopathies

The goal of this study is to characterize tau kinetics and tau aggregation in the human CNS and to test the hypothesis that tau kinetics are altered (i.e. increased production, decreased c...

A New Optical Sweat Test Method Based on a Citric Acid-derived Multi-halide Sensor

Cystic Fibrosis (CF) is a hereditary multi-system disease affecting approximately 30,000n children and adults in the USA. The diagnosis of CF requires biochemical confirmation (either abno...

Pivot Breath Sensor Human Factors and Usability Study

Prospective, observational open label, single center study enrolling up to 15 subjects to evaluate human factors and usability of the Pivot Breath Sensor.

An Inpatient Evaluation of Six-Day Subcutaneous Glucose Sensor Performance

The purpose of this study is to assess the performance of the subcutaneous glucose sensor over an extended sensor life. The sensor is currently approved for 3 days of use and this study wi...

Medical and Biotech [MESH] Definitions

A view of the world and the individual's environment as comprehensible, manageable, and meaningful, claiming that the way people view their life has a positive influence on their health.

The difference between two images on the retina when looking at a visual stimulus. This occurs since the two retinas do not have the same view of the stimulus because of the location of our eyes. Thus the left eye does not get exactly the same view as the right eye.

A multi- and interdisciplinary field concerned with improving health and achieving equity in health for all people. It transcends national boundaries, promotes cooperation and collaboration within and beyond health science fields, and combines population-based disease prevention with individually-based patient care.

A broad category of multi-ingredient preparations that are marketed for the relief of upper respiratory symptoms resulting from the COMMON COLD; ALLERGIES; or HUMAN INFLUENZA. While the majority of these medications are available as OVER-THE-COUNTER DRUGS some of them contain ingredients that require them to be sold as PRESCRIPTION DRUGS or as BEHIND-THE COUNTER DRUGS.

The formation of clumps of RED BLOOD CELLS under low or non-flow conditions, resulting from the attraction forces between the red blood cells. The cells adhere to each other in rouleaux aggregates. Slight mechanical force, such as occurs in the circulation, is enough to disperse these aggregates. Stronger or weaker than normal aggregation may result from a variety of effects in the ERYTHROCYTE MEMBRANE or in BLOOD PLASMA. The degree of aggregation is affected by ERYTHROCYTE DEFORMABILITY, erythrocyte membrane sialylation, masking of negative surface charge by plasma proteins, etc. BLOOD VISCOSITY and the ERYTHROCYTE SEDIMENTATION RATE are affected by the amount of erythrocyte aggregation and are parameters used to measure the aggregation.

Quick Search

DeepDyve research library

Relevant Topic

Antiretroviral therapy
Standard antiretroviral therapy (ART) consists of the combination of at least three antiretroviral (ARV) drugs to maximally suppress the HIV virus and stop the progression of HIV disease. Huge reductions have been seen in rates of death and suffering whe...

Searches Linking to this Article