Share This Author
ContextVP: Fully Context-Aware Video Prediction
This work introduces a fully context-aware architecture that captures the entire available past context for each pixel using Parallel Multi-Dimensional LSTM units and aggregates it using blending units and yields state-of-the-art performance for next step prediction on three challenging real-world video datasets.
Short-Term Load Forecasting With Deep Residual Networks
- Kunjin Chen, Kunlong Chen, Qin Wang, Ziyu He, Jun Hu, Jinliang He
- Computer ScienceIEEE Transactions on Smart Grid
- 30 May 2018
The proposed model is able to integrate domain knowledge and researchers’ understanding of the task by virtue of different neural network building blocks and has high generalization capability.
Domain Adaptive Transfer Learning for Fault Diagnosis
- Qin Wang, Gabriel Michau, Olga Fink
- Computer SciencePrognostics and System Health Management…
- 1 May 2019
Inspired by its successful implementation in computer vision, Domain-Adversarial Neural Networks (DANN) is introduced to this context, along with two other popular methods existing in previous fault diagnosis research, and a unified experimental protocol is offered for a fair comparison between domain adaptation methods for fault diagnosis problems.
Convolutional Sequence to Sequence Non-intrusive Load Monitoring
- Kunjin Chen, Qin Wang, Ziyu He, Kunlong Chen, Jun Hu, Jinliang He
- Computer ScienceThe Journal of Engineering
- 6 June 2018
The proposed convolutional sequence to sequence non-intrusive load monitoring model is applied to the REDD dataset and results show that the proposed model is able to give satisfactory disaggregation performance for appliances with varied characteristics.
Semi-Supervised Learning by Augmented Distribution Alignment
This work reveals that an essential sampling bias exists in semi-supervised learning due to the limited number of labeled samples, which often leads to a considerable empirical distribution mismatch between labeled data and unlabeled data and proposes an adversarial training strategy to minimize the distribution distance.
The combined value of wind and solar power forecasting improvements and electricity storage
Scale- and Context-Aware Convolutional Non-Intrusive Load Monitoring
- Kunjin Chen, Yu Zhang, Qin Wang, Jun Hu, Hang Fan, Jinliang He
- Computer ScienceIEEE Transactions on Power Systems
- 17 November 2019
This paper boosts the accuracy of energy disaggregation with a novel neural network structure named scale- and context-aware network, which exploits multi-scale features and contextual information.
A review of plug-in electric vehicles as distributed energy storages in smart grid
- Xianjun Zhang, Qin Wang, G. Xu, Ziping Wu
- EngineeringIEEE PES Innovative Smart Grid Technologies…
- 1 October 2014
The growing regulatory environment and security concerns about fossil fuels are driving the research and development of new technologies that can contribute significantly to sustainable and resilient…
Reliability of Non-Contact Infrared Thermometers for Fever Screening Under COVID-19
NECK temperature had the highest accuracy among the four NCIT temperature measurement sites, with an optimum fever diagnostic threshold of 37.35°C, and is recommended as the fever screening standard for COVID-19.
Supplementary Material for Semi-Supervised Learning by Augmented Distribution Alignment
It will be shown that the empirical distribution mismatch still exists for state-of-the-art SSL models like the VAT model, and the proposed Augmented Distribution Alignment is able to boost the VAT models by addressing the empirical Distribution mismatch of labeled and unlabeled samples.