Deep learning algorithms for human activity recognition using mobile and wearable sensor networks: State of the art and research challenges

HF Nweke, YW Teh, MA Al-Garadi, UR Alo - Expert Systems with …, 2018 - Elsevier
Human activity recognition systems are developed as part of a framework to enable
continuous monitoring of human behaviours in the area of ambient assisted living, sports …

Edge computing in smart health care systems: Review, challenges, and research directions

M Hartmann, US Hashmi… - Transactions on Emerging …, 2022 - Wiley Online Library
Today, patients are demanding a newer and more sophisticated health care system, one
that is more personalized and matches the speed of modern life. For the latency and energy …

Squeezing deep learning into mobile and embedded devices

ND Lane, S Bhattacharya, A Mathur… - IEEE Pervasive …, 2017 - ieeexplore.ieee.org
This department provides an overview the progress the authors have made to the emerging
area of embedded and mobile forms of on-device deep learning. Their work addresses two …

First person action recognition using deep learned descriptors

S Singh, C Arora, CV Jawahar - Proceedings of the IEEE …, 2016 - openaccess.thecvf.com
We focus on the problem of wearer's action recognition in first person aka egocentric videos.
This problem is more challenging than third person activity recognition due to unavailability …

Explainability scenarios: towards scenario-based XAI design

CT Wolf - Proceedings of the 24th International Conference on …, 2019 - dl.acm.org
Integral to the adoption and uptake of AI systems in real-world settings is the ability for
people to make sense of and evaluate such systems, a growing area of development and …

Eyemotion: Classifying facial expressions in VR using eye-tracking cameras

S Hickson, N Dufour, A Sud, V Kwatra… - 2019 IEEE winter …, 2019 - ieeexplore.ieee.org
One of the main challenges of social interaction in virtual reality settings is that head-
mounted displays occlude a large portion of the face, blocking facial expressions and …

Deepeye: Resource efficient local execution of multiple deep vision models using wearable commodity hardware

A Mathur, ND Lane, S Bhattacharya, A Boran… - Proceedings of the 15th …, 2017 - dl.acm.org
Wearable devices with built-in cameras present interesting opportunities for users to capture
various aspects of their daily life and are potentially also useful in supporting users with low …

A vision-based deep learning approach for the detection and prediction of occupancy heat emissions for demand-driven control solutions

PW Tien, S Wei, JK Calautit, J Darkwa, C Wood - Energy and Buildings, 2020 - Elsevier
This paper introduces a vision-based deep learning approach that enables the detection
and recognition of occupants' activities within building spaces. The data can feed into …

Deepcham: Collaborative edge-mediated adaptive deep learning for mobile object recognition

D Li, T Salonidis, NV Desai… - 2016 IEEE/ACM …, 2016 - ieeexplore.ieee.org
Deep learning techniques achieve state-of-the-art performance on many computer vision
related tasks, eg large-scale object recognition. In this paper we show that recognition …

Toward storytelling from visual lifelogging: An overview

M Bolanos, M Dimiccoli… - IEEE Transactions on …, 2016 - ieeexplore.ieee.org
Visual lifelogging consists of acquiring images that capture the daily experiences of the user
by wearing a camera over a long period of time. The pictures taken offer considerable …