Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 

Saved Queries

Sign in to use this feature.

Search Filter Reset All

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
Add Subjects Reset
Select Subjects

Journals

remove_circle_outline
Add Journals Reset
Select Journals

Article Types

remove_circle_outline
Add Article Types Reset
Select Article Types

Countries / Regions

remove_circle_outline
remove_circle_outline
Add Countries / Regions Reset
Select Countries / Regions
Update Search
share announcement

Search Results (2)

Search Parameters:
Keywords = flat layer (FL)

Order results
Result details
Results per page
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
13 pages, 2303 KiB  
Article
Named Entity Identification in the Power Dispatch Domain Based on RoBERTa-Attention-FL Model
by Yan Chen, Dezhao Lin, Qi Meng, Zengfu Liang and Zhixiang Tan
Energies 2023, 16(12), 4654; https://doi.org/10.3390/en16124654 - 12 Jun 2023
Cited by 3 | Viewed by 1722
Abstract
Named entity identification is an important step in building a knowledge graph of the grid domain, which contains a certain number of nested entities. To address the issue of nested entities in the Chinese power dispatching domain’s named entity recognition, we propose a [...] Read more.
Named entity identification is an important step in building a knowledge graph of the grid domain, which contains a certain number of nested entities. To address the issue of nested entities in the Chinese power dispatching domain’s named entity recognition, we propose a RoBERTa-Attention-FL model. This model effectively recognizes nested entities using the span representation annotation method. We extract the output values from RoBERTa’s middle 4–10 layers, obtain syntactic information from the Transformer Encoder layers via the multi-head self-attention mechanism, and integrate it with deep semantic information output from RoBERTa’s last layer. During training, we use Focal Loss to mitigate the sample imbalance problem. To evaluate the model’s performance, we construct named entity recognition datasets for flat and nested entities in the power dispatching domain annotated with actual power operation data, and conduct experiments. The results indicate that compared to the baseline model, the RoBERTa-Attention-FL model significantly improves recognition performance, increasing the F1-score by 4.28% to 90.35%, with an accuracy rate of 92.53% and a recall rate of 88.12%. Full article
(This article belongs to the Special Issue Advanced Applications of Machine Learning and Artificial Intelligence in Smart Grids)
►▼ Show Figures

Figure 1

9 pages, 2438 KiB  
Article
Innovative Membrane Electrode Assembly (MEA) Fabrication for Proton Exchange Membrane Water Electrolysis
by Guo-Bin Jung, Shih-Hung Chan, Chun-Ju Lai, Chia-Chen Yeh and Jyun-Wei Yu
Energies 2019, 12(21), 4218; https://doi.org/10.3390/en12214218 - 5 Nov 2019
Cited by 14 | Viewed by 7465
Abstract
In order to increase the hydrogen production rate as well as ozone production at the anode side, increased voltage application and more catalyst utilization are necessary. The membrane electrode assembly (MEA) produces hydrogen/ozone via proton exchange membrane water electrolysis (PEMWE)s which gives priority [...] Read more.
In order to increase the hydrogen production rate as well as ozone production at the anode side, increased voltage application and more catalyst utilization are necessary. The membrane electrode assembly (MEA) produces hydrogen/ozone via proton exchange membrane water electrolysis (PEMWE)s which gives priority to a coating method (abbreviation: ML). However, coating takes more effort and is labor-consuming. This study will present an innovative preparation method, known as flat layer (FL), and compare it with ML. FL can significantly reduce efforts and largely improve MEA production. Additionally, MEA with the FL method is potentially durable compared to ML. Full article
(This article belongs to the Special Issue Hydrogen-Based Energy Conversion: Polymer Electrolyte Fuel Cells and Electrolysis)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying article 1-50 on page 1 of 1.
Back to TopTop