Self-supervised pretraining and transfer learning enable\titlebreak flu and covid-19 predictions in small mobile sensing datasets

MA Merrill, T Althoff - Conference on Health, Inference, and …, 2023 - proceedings.mlr.press
Detailed mobile sensing data from phones and fitness trackers offer an opportunity to
quantify previously unmeasurable behavioral changes to improve individual health and …

Is sustained participation a myth in crowdsourcing? A review

H Humayun, M Ghazali, MN Malik - European Journal of Innovation …, 2023 - emerald.com
Purpose The motivation to participate in crowdsourcing (CS) platforms is an emerging
challenge. Although researchers and practitioners have focused on crowd motivation in the …

Intersection of machine learning and mobile crowdsourcing: a systematic topic-driven review

W Chen, W Hussain, I Al-Qudah, G Al-Naymat… - Personal and Ubiquitous …, 2024 - Springer
During the past decade of the big data era, mobile crowdsourcing has emerged as a popular
research area, leveraging the collective intelligence and engagement of a vast number of …

Predicting performance improvement of human activity recognition model by additional data collection

K Tanigaki, TC Teoh, N Yoshimura… - Proceedings of the …, 2022 - dl.acm.org
The development of a machine-learning-based human activity recognition (HAR) system
using body-worn sensors is mainly composed of three phases: data collection, model …

Urban-scale poi updating with crowd intelligence

Z Hong, H Wang, W Lyu, H Wang, Y Liu… - Proceedings of the …, 2023 - dl.acm.org
Points of Interest (POIs), such as entertainment, dining, and living, are crucial for urban
planning and location-based services. However, the high dynamics and expensive updating …

Homekit2020: A benchmark for time series classification on a large mobile sensing dataset with laboratory tested ground truth of influenza infections

MA Merrill, E Safranchik… - … on Health, Inference …, 2023 - proceedings.mlr.press
Despite increased interest in wearables as tools for detecting various health conditions,
there are not as of yet any large public benchmarks for such mobile sensing data. The few …

A stacked CNN and random forest ensemble architecture for complex nursing activity recognition and nurse identification

A Rahman, N Nahid, B Schuller, MAR Ahad - Scientific Reports, 2024 - nature.com
Nursing activity recognition has immense importance in the development of smart
healthcare management and is an extremely challenging area of research in human activity …

CrossHAR: Generalizing Cross-dataset Human Activity Recognition via Hierarchical Self-Supervised Pretraining

Z Hong, Z Li, S Zhong, W Lyu, H Wang, Y Ding… - Proceedings of the …, 2024 - dl.acm.org
The increasing availability of low-cost wearable devices and smartphones has significantly
advanced the field of sensor-based human activity recognition (HAR), attracting …

Human-centred design on crowdsourcing annotation towards improving active learning model performance

J Dong, Y Kang, J Liu, C Sun, S Fan… - Journal of …, 2023 - journals.sagepub.com
Active learning in machine learning is an effective approach to reducing the cost of human
efforts for generating labels. The iterative process of active learning involves a human …

Analysis of Motivational Theories in Crowdsourcing Using Long Tail Theory: A Systematic Literature Review

H Humayun, MN Malik… - International Journal of …, 2024 - ieeexplore.ieee.org
Motivational theories have been extensively studied in a wide range of fields, such as
medical sciences, business, management, physiology, sociology, and particularly in the …