Classification of Research Papers on Radio Frequency Electromagnetic Field (RF-EMF) Using Graph Neural Networks (GNN)
This study compares the performance of graph convolutional neural network (GCN) models with conventional natural language processing (NLP) models for classifying scientific literature related to radio frequency electromagnetic field (RF-EMF). Specifically, the study examines two GCN models: BertGCN...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/7/4614 |
| _version_ | 1797608292440080384 |
|---|---|
| author | Youngsun Jang Kwanghee Won Hyung-do Choi Sung Y. Shin |
| author_facet | Youngsun Jang Kwanghee Won Hyung-do Choi Sung Y. Shin |
| author_sort | Youngsun Jang |
| collection | DOAJ |
| description | This study compares the performance of graph convolutional neural network (GCN) models with conventional natural language processing (NLP) models for classifying scientific literature related to radio frequency electromagnetic field (RF-EMF). Specifically, the study examines two GCN models: BertGCN and the citation-based GCN. The study concludes that the model achieves consistently good performance when the input text is long enough, based on the attention mechanism of BERT. When the input sequence is short, the composition parameter <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi>λ</mi></semantics></math></inline-formula>, which combines output values of the two subnetworks of BertGCN, plays a crucial role in achieving high classification accuracy. As the value of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi>λ</mi></semantics></math></inline-formula> increases, the classification accuracy also increases. The study also proposes and tests a simplified variant of BertGCN, revealing performance differences among the models under two different data conditions by the existence of keywords. This study has two main contributions: (1) the implementation and testing of a variant of BertGCN and citation-based GCN for document classification tasks related to radio frequency electromagnetic fields publications, and (2) the confirmation of the impact of model conditions, such as the existence of keywords and input sequence length, in the original BertGCN. Although this study focused on a specific domain, our approaches have broader implications that extend beyond scientific publications to general text classification. |
| first_indexed | 2024-03-11T05:42:23Z |
| format | Article |
| id | doaj.art-f26f005c409540a79658f083e850306f |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T05:42:23Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-f26f005c409540a79658f083e850306f2023-11-17T16:23:06ZengMDPI AGApplied Sciences2076-34172023-04-01137461410.3390/app13074614Classification of Research Papers on Radio Frequency Electromagnetic Field (RF-EMF) Using Graph Neural Networks (GNN)Youngsun Jang0Kwanghee Won1Hyung-do Choi2Sung Y. Shin3Electrical Engineering and Computer Science Department, South Dakota State University, Brookings, SD 57007, USAElectrical Engineering and Computer Science Department, South Dakota State University, Brookings, SD 57007, USARadio Research Division, Electronics and Telecom Research Institute, Daejeon 34129, Republic of KoreaElectrical Engineering and Computer Science Department, South Dakota State University, Brookings, SD 57007, USAThis study compares the performance of graph convolutional neural network (GCN) models with conventional natural language processing (NLP) models for classifying scientific literature related to radio frequency electromagnetic field (RF-EMF). Specifically, the study examines two GCN models: BertGCN and the citation-based GCN. The study concludes that the model achieves consistently good performance when the input text is long enough, based on the attention mechanism of BERT. When the input sequence is short, the composition parameter <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi>λ</mi></semantics></math></inline-formula>, which combines output values of the two subnetworks of BertGCN, plays a crucial role in achieving high classification accuracy. As the value of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi>λ</mi></semantics></math></inline-formula> increases, the classification accuracy also increases. The study also proposes and tests a simplified variant of BertGCN, revealing performance differences among the models under two different data conditions by the existence of keywords. This study has two main contributions: (1) the implementation and testing of a variant of BertGCN and citation-based GCN for document classification tasks related to radio frequency electromagnetic fields publications, and (2) the confirmation of the impact of model conditions, such as the existence of keywords and input sequence length, in the original BertGCN. Although this study focused on a specific domain, our approaches have broader implications that extend beyond scientific publications to general text classification.https://www.mdpi.com/2076-3417/13/7/4614document classificationBERTgraph convolution neural networkelectromagnetic fields |
| spellingShingle | Youngsun Jang Kwanghee Won Hyung-do Choi Sung Y. Shin Classification of Research Papers on Radio Frequency Electromagnetic Field (RF-EMF) Using Graph Neural Networks (GNN) Applied Sciences document classification BERT graph convolution neural network electromagnetic fields |
| title | Classification of Research Papers on Radio Frequency Electromagnetic Field (RF-EMF) Using Graph Neural Networks (GNN) |
| title_full | Classification of Research Papers on Radio Frequency Electromagnetic Field (RF-EMF) Using Graph Neural Networks (GNN) |
| title_fullStr | Classification of Research Papers on Radio Frequency Electromagnetic Field (RF-EMF) Using Graph Neural Networks (GNN) |
| title_full_unstemmed | Classification of Research Papers on Radio Frequency Electromagnetic Field (RF-EMF) Using Graph Neural Networks (GNN) |
| title_short | Classification of Research Papers on Radio Frequency Electromagnetic Field (RF-EMF) Using Graph Neural Networks (GNN) |
| title_sort | classification of research papers on radio frequency electromagnetic field rf emf using graph neural networks gnn |
| topic | document classification BERT graph convolution neural network electromagnetic fields |
| url | https://www.mdpi.com/2076-3417/13/7/4614 |
| work_keys_str_mv | AT youngsunjang classificationofresearchpapersonradiofrequencyelectromagneticfieldrfemfusinggraphneuralnetworksgnn AT kwangheewon classificationofresearchpapersonradiofrequencyelectromagneticfieldrfemfusinggraphneuralnetworksgnn AT hyungdochoi classificationofresearchpapersonradiofrequencyelectromagneticfieldrfemfusinggraphneuralnetworksgnn AT sungyshin classificationofresearchpapersonradiofrequencyelectromagneticfieldrfemfusinggraphneuralnetworksgnn |