Clustering approach to solve hierarchical classification problem complexity
In a large domain of classification problems for real applications, like human activity
recognition, separable spaces between groups of concepts are easier to learn than each …
recognition, separable spaces between groups of concepts are easier to learn than each …
A wearable-HAR oriented sensory data generation method based on spatio-temporal reinforced conditional GANs
Human activity recognition based on wearable sensors plays an essential role in promoting
many practical applications, such as healthcare, motion monitoring, medical examination …
many practical applications, such as healthcare, motion monitoring, medical examination …
[HTML][HTML] Promoting fairness in activity recognition algorithms for patient's monitoring and evaluation systems in healthcare
C Mennella, M Esposito, G De Pietro… - Computers in Biology …, 2024 - Elsevier
Researchers face the challenge of defining subject selection criteria when training
algorithms for human activity recognition tasks. The ongoing uncertainty revolves around …
algorithms for human activity recognition tasks. The ongoing uncertainty revolves around …
Semantic Loss: A New Neuro-Symbolic Approach for Context-Aware Human Activity Recognition
Deep Learning models are a standard solution for sensor-based Human Activity
Recognition (HAR), but their deployment is often limited by labeled data scarcity and …
Recognition (HAR), but their deployment is often limited by labeled data scarcity and …
Reduction of the position bias via multi-level learning for activity recognition
The relative position of sensors placed on specific body parts generates two types of data
related to (1) the movement of the body part wrt the body and (2) the whole body wrt the …
related to (1) the movement of the body part wrt the body and (2) the whole body wrt the …
Context Abstraction to Improve Decentralized Machine Learning in Structured Sensing Environments
Abstract In Internet of Things applications, data generated from devices with different
characteristics and located at different positions are embedded into different contexts. This …
characteristics and located at different positions are embedded into different contexts. This …
On the Necessity of Metalearning: Learning Suitable Parameterizations for Learning Processes
In this paper we will discuss metalearning and how we can go beyond the current classical
learning paradigm. We will first address the importance of inductive biases in the learning …
learning paradigm. We will first address the importance of inductive biases in the learning …
Anthropometric ratios for lower-body detection based on deep learning and traditional methods
J Jaruenpunyasak, A García Seco de Herrera… - Applied Sciences, 2022 - mdpi.com
Lower-body detection can be useful in many applications, such as the detection of falling
and injuries during exercises. However, it can be challenging to detect the lower-body …
and injuries during exercises. However, it can be challenging to detect the lower-body …
Metalearning guided by domain knowledge in distributed and decentralized applications
M Hamidi - 2022 - theses.hal.science
This thesis is concerned with learning in distributed applications such as IoT, industry 4.0, or
connected health. We are interested in the different challenges, both theoretical and …
connected health. We are interested in the different challenges, both theoretical and …
Multiview Representation Learning for Human Activity Recognition
Over the years, multi-view representation learning has become widespread in machine
learning and deep learning due to the availability of extensive data and the contribution of …
learning and deep learning due to the availability of extensive data and the contribution of …