Times-series data augmentation and deep learning for construction equipment activity recognition

KM Rashid, J Louis - Advanced Engineering Informatics, 2019 - Elsevier
Automated, real-time, and reliable equipment activity recognition on construction sites can
help to minimize idle time, improve operational efficiency, and reduce emissions. Previous …

DAGA: Data augmentation with a generation approach for low-resource tagging tasks

B Ding, L Liu, L Bing, C Kruengkrai, TH Nguyen… - ar**_A_Time_Series_Data_Augmentation_of_IMU_Data_for_Construction_Equipment_Activity_Identification/links/5d153b7d299bf1547c8420d2/Time-War**-A-Time-Series-Data-Augmentation-of-IMU-Data-for-Construction-Equipment-Activity-Identification.pdf" data-clk="hl=en&sa=T&oi=gga&ct=gga&cd=4&d=264249991791950277&ei=pQm4Z6DPBqq0ieoP69fV6Q4" data-clk-atid="xbmorPfNqgMJ" target="_blank">[PDF] researchgate.net

[PDF][PDF] Window-war**: A time series data augmentation of IMU data for construction equipment activity identification

KM Rashid, J Louis - … symposium on automation and robotics in …, 2019 - researchgate.net
Automated, real-time, and reliable equipment activity identification on construction sites can
help to minimize idle times, improve operational efficiencies, and reduce emissions. Many …

A case study of the augmentation and evaluation of training data for deep learning

J Ding, X Li, X Kang, VN Gudivada - Journal of Data and Information …, 2019 - dl.acm.org
Deep learning has been widely used for extracting values from big data. As many other
machine learning algorithms, deep learning requires significant training data. Experiments …

A general domain specific feature transfer framework for hybrid domain adaptation

P Wei, Y Ke, CK Goh - IEEE Transactions on Knowledge and …, 2018 - ieeexplore.ieee.org
Heterogeneous domain adaptation needs supplementary information to link up different
domains. However, such supplementary information may not always be available in real …

Adversarial discriminative sim-to-real transfer of visuo-motor policies

F Zhang, J Leitner, Z Ge, M Milford… - … International Journal of …, 2019 - journals.sagepub.com
Various approaches have been proposed to learn visuo-motor policies for real-world robotic
applications. One solution is first learning in simulation then transferring to the real world. In …

Modular deep q networks for sim-to-real transfer of visuo-motor policies

F Zhang, J Leitner, M Milford, P Corke - arxiv preprint arxiv:1610.06781, 2016 - arxiv.org
While deep learning has had significant successes in computer vision thanks to the
abundance of visual data, collecting sufficiently large real-world datasets for robot learning …

[PDF][PDF] Sim-to-real transfer of visuo-motor policies for reaching in clutter: Domain randomization and adaptation with modular networks

F Zhang, J Leitner, M Milford, P Corke - world, 2017 - researchgate.net
A modular method is proposed to learn and transfer visuo-motor policies from simulation to
the real world in an efficient manner by combining domain randomization and adaptation …