Related papers: Resource-Efficient Wearable Computing for Real-Tim…
Unlike images or videos data which can be easily labeled by human being, sensor data annotation is a time-consuming process. However, traditional methods of human activity recognition require a large amount of such strictly labeled data for…
Motor imagery brain--machine interfaces enable us to control machines by merely thinking of performing a motor action. Practical use cases require a wearable solution where the classification of the brain signals is done locally near the…
Wearable devices are transforming computing and the human-computer interaction and they are a primary means for motion recognition of reflexive systems. We review basic wearable deployments and their open wireless communications. An…
Cascading multiple pre-trained models is an effective way to compose an end-to-end system. However, fine-tuning the full cascaded model is parameter and memory inefficient and our observations reveal that only applying adapter modules on…
We propose a tree-based algorithm for classification and regression problems in the context of functional data analysis, which allows to leverage representation learning and multiple splitting rules at the node level, reducing…
Training multimodal networks requires a vast amount of data due to their larger parameter space compared to unimodal networks. Active learning is a widely used technique for reducing data annotation costs by selecting only those samples…
We consider human activity recognition (HAR) from wearable sensor data in manual-work processes, like warehouse order-picking. Such structured domains can often be partitioned into distinct process steps, e.g., packaging or transporting.…
While neural network binary classifiers are often evaluated on metrics such as Accuracy and $F_1$-Score, they are commonly trained with a cross-entropy objective. How can this training-evaluation gap be addressed? While specific techniques…
Vision-based human activity recognition has emerged as one of the essential research areas in video analytics domain. Over the last decade, numerous advanced deep learning algorithms have been introduced to recognize complex human actions…
Classification methods based on sparse estimation have drawn much attention recently, due to their effectiveness in processing high-dimensional data such as images. In this paper, a method to improve the performance of a sparse…
Human activity recognition has become an attractive research area with the development of on-body wearable sensing technology. With comfortable electronic-textiles, sensors can be embedded into clothing so that it is possible to record…
Face masks have long been used in many areas of everyday life to protect against the inhalation of hazardous fumes and particles. They also offer an effective solution in healthcare for bi-directional protection against air-borne diseases.…
Industrial cyber physical systems operate under heterogeneous sensing, stochastic dynamics, and shifting process conditions, producing data that are often incomplete, unlabeled, imbalanced, and domain shifted. High-fidelity datasets remain…
The problem of human activity recognition is central for understanding and predicting the human behavior, in particular in a prospective of assistive services to humans, such as health monitoring, well being, security, etc. There is…
Supervised machine learning-based medical image computing applications necessitate expert label curation, while unlabelled image data might be relatively abundant. Active learning methods aim to prioritise a subset of available image data…
Mobile platforms must satisfy the contradictory requirements of fast response time and minimum energy consumption as a function of dynamically changing applications. To address this need, system-on-chips (SoC) that are at the heart of these…
In the realm of smart sensing with the Internet of Things, earable devices are empowered with the capability of multi-modality sensing and intelligence of context-aware computing, leading to its wide usage in Human Activity Recognition…
Recent advances in Tiny Machine Learning (TinyML) empower low-footprint embedded devices for real-time on-device Machine Learning. While many acknowledge the potential benefits of TinyML, its practical implementation presents unique…
The limited and dynamically varied resources on edge devices motivate us to deploy an optimized deep neural network that can adapt its sub-networks to fit in different resource constraints. However, existing works often build sub-networks…
Heterogeneity is a ubiquitous property of many biological systems and has profound implications for computation. While it is conceivable to optimize neuronal and synaptic heterogeneity for a specific task, such top-down optimization is…