On the Personalization of Classification Models for Human Activity Recognition

Ferrari, Anna; Micucci, Daniela; Mobilio, Marco; Napoletano, Paolo

doi:10.1109/access.2020.2973425

Cited by 106 publications

(76 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our analysis in Section 3 , we construct a separate dictionary for each subject using their own personal training data. Previous studies have found that using a personalized classifier model for each given subject, which could be built using their personal data (as we do in our analysis) or by leveraging data of other subjects who are similar to them, can improve classification accuracy [ 20 , 27 , 28 ].…”

Section: Methodsmentioning

confidence: 99%

Augmented Movelet Method for Activity Classification Using Smartphone Gyroscope and Accelerometer Data

Huang

Onnela

2020

Sensors

View full text Add to dashboard Cite

Physical activity, such as walking and ascending stairs, is commonly used in biomedical settings as an outcome or covariate. Researchers have traditionally relied on surveys to quantify activity levels of subjects in both research and clinical settings, but surveys are subjective in nature and have known limitations, such as recall bias. Smartphones provide an opportunity for unobtrusive objective measurement of physical activity in naturalistic settings, but their data tends to be noisy and needs to be analyzed with care. We explored the potential of smartphone accelerometer and gyroscope data to distinguish between walking, sitting, standing, ascending stairs, and descending stairs. We conducted a study in which four participants followed a study protocol and performed a sequence of activities with one phone in their front pocket and another phone in their back pocket. The subjects were filmed throughout, and the obtained footage was annotated to establish moment-by-moment ground truth activity. We introduce a modified version of the so-called movelet method to classify activity type and to quantify the uncertainty present in that classification. Our results demonstrate the promise of smartphones for activity recognition in naturalistic settings, but they also highlight challenges in this field of research.

show abstract

Section: Methodsmentioning

confidence: 99%

Augmented Movelet Method for Activity Classification Using Smartphone Gyroscope and Accelerometer Data

Huang

Onnela

2020

Sensors

View full text Add to dashboard Cite

show abstract

“…For that reason, they cannot be generalized to every kind of user, so there has not been a real transition to real-life, yet. Presently, personalization of AI models in HAR for large numbers of people is still an active research topic [5,6], despite being actively researched for nearly a decade [7,8].…”

Section: Introductionmentioning

confidence: 99%

A Public Domain Dataset for Real-Life Human Activity Recognition Using Smartphone Sensors

García-González

Rivero

Fernández-Blanco

et al. 2020

Sensors

108

View full text Add to dashboard Cite

In recent years, human activity recognition has become a hot topic inside the scientific community. The reason to be under the spotlight is its direct application in multiple domains, like healthcare or fitness. Additionally, the current worldwide use of smartphones makes it particularly easy to get this kind of data from people in a non-intrusive and cheaper way, without the need for other wearables. In this paper, we introduce our orientation-independent, placement-independent and subject-independent human activity recognition dataset. The information in this dataset is the measurements from the accelerometer, gyroscope, magnetometer, and GPS of the smartphone. Additionally, each measure is associated with one of the four possible registered activities: inactive, active, walking and driving. This work also proposes asupport vector machine (SVM) model to perform some preliminary experiments on the dataset. Considering that this dataset was taken from smartphones in their actual use, unlike other datasets, the development of a good model on such data is an open problem and a challenge for researchers. By doing so, we would be able to close the gap between the model and a real-life application.

show abstract

“…Physical characteristics, health state, lifestyle, moving style, and gender are parameters that can be highly personalized. Therefore, in order to consider generalization of prediction or classification models, the data should be labeled personally, and the focus of research should be more on personalized analysis [ 42 , 43 ]. One way to personalize data is automatic identification of human activities and consequently labeling data based on different activities.…”

Section: Discussionmentioning

confidence: 99%

Deep Learning–Based Multimodal Data Fusion: Case Study in Food Intake Episodes Detection Using Wearable Sensors

Bahador¹,

Ferreira²,

Tamminen³

et al. 2021

JMIR Mhealth Uhealth

View full text Add to dashboard Cite

Background Multimodal wearable technologies have brought forward wide possibilities in human activity recognition, and more specifically personalized monitoring of eating habits. The emerging challenge now is the selection of most discriminative information from high-dimensional data collected from multiple sources. The available fusion algorithms with their complex structure are poorly adopted to the computationally constrained environment which requires integrating information directly at the source. As a result, more simple low-level fusion methods are needed. Objective In the absence of a data combining process, the cost of directly applying high-dimensional raw data to a deep classifier would be computationally expensive with regard to the response time, energy consumption, and memory requirement. Taking this into account, we aimed to develop a data fusion technique in a computationally efficient way to achieve a more comprehensive insight of human activity dynamics in a lower dimension. The major objective was considering statistical dependency of multisensory data and exploring intermodality correlation patterns for different activities. Methods In this technique, the information in time (regardless of the number of sources) is transformed into a 2D space that facilitates classification of eating episodes from others. This is based on a hypothesis that data captured by various sensors are statistically associated with each other and the covariance matrix of all these signals has a unique distribution correlated with each activity which can be encoded on a contour representation. These representations are then used as input of a deep model to learn specific patterns associated with specific activity. Results In order to show the generalizability of the proposed fusion algorithm, 2 different scenarios were taken into account. These scenarios were different in terms of temporal segment size, type of activity, wearable device, subjects, and deep learning architecture. The first scenario used a data set in which a single participant performed a limited number of activities while wearing the Empatica E4 wristband. In the second scenario, a data set related to the activities of daily living was used where 10 different participants wore inertial measurement units while performing a more complex set of activities. The precision metric obtained from leave-one-subject-out cross-validation for the second scenario reached 0.803. The impact of missing data on performance degradation was also evaluated. Conclusions To conclude, the proposed fusion technique provides the possibility of embedding joint variability information over different modalities in just a single 2D representation which results in obtaining a more global view of different aspects of daily human activities at hand, and yet preserving the desired performance level in activity recognition.

show abstract

On the Personalization of Classification Models for Human Activity Recognition

Cited by 106 publications

References 57 publications

Augmented Movelet Method for Activity Classification Using Smartphone Gyroscope and Accelerometer Data

Augmented Movelet Method for Activity Classification Using Smartphone Gyroscope and Accelerometer Data

A Public Domain Dataset for Real-Life Human Activity Recognition Using Smartphone Sensors

Deep Learning–Based Multimodal Data Fusion: Case Study in Food Intake Episodes Detection Using Wearable Sensors

Contact Info

Product

Resources

About