Automatic Relationship Construction in Domain Ontology Engineering using Semantic and Thematic Graph Generation Process and Convolution Neural Network

Facts can be exchanged in multiple fields with the help of disease-specific ontologies. A range of diverse values can be produced by mining ontological approaches for demonstrating disease mechanisms. Alzheimer’s disease (AD) is an incurable neurological brain illness. An early diagnosis of AD can be helpful for better treatment and the prevention of brain tissue destruction. Researchers have used machine learning techniques to predict the early detection of AD. However, Alzheimer’s disorders are still underexplored in the knowledge domain. In the biomedical field, the illustration of terminologies and notions is essential. Multiple methods are adopted to represent these notions, but ontologies are the most frequent and accurate. Ontology construction is a complex and time-consuming process. The designed ontology relies on Disease Ontology (DO), which is considered the benchmark in medical practice. Ontology reasoning mechanisms can be adopted for AD identification. In this paper, a deep convolutional neural network-based approach is proposed to diagnose Alzheimer’s disease, using an AD dataset acquired from Kaggle. Machine learning-based approaches (logistic regression, gradient boosting, XGB, SGD, MLP, SVM, KNN, random forest) are also used for a fair comparison. The simulation results are generated using three strategies (default parameters, 10-cross validation, and grid search), and MLP provides superior results on a default parameter strategy with an accuracy of 92.12%. Furthermore, the deep learning-based approach convolutional neural network (CNN) achieved an accuracy of 94.61%. The experimental results indicate that the construction of ontology, with the help of deep learning knowledge, can produce better results where the robustness and scalability can be enhanced. In comparisons to other methods, the CNN results are excellent and encouraging.

show abstract

“…Additionally, data mining techniques are used to present knowledge and to demonstrate the accuracy of information retrieval [2].…”

Section: Introductionmentioning

confidence: 99%

Constructing Domain Ontology for Alzheimer Disease Using Deep Learning Based Approach

Bangyal¹,

Rehman

Nawaz

et al. 2022

Electronics

View full text Add to dashboard Cite

show abstract

“…Related studies by Wang et al [110], Kim et al [111], and Bangyal et al [112] all used CNN models to classify text. CNNs are multi-layer networks with convolutional and subsampling layers of multiple 2D layers and fully connected hidden layers [113]. In particular, CNN has an input layer that directly receives two-dimensional objects, a feature extraction process done through convolution, and the subsampling layer implemented using multiple fully connected hidden layers as shown in Figure 16.…”

Section: Relation Discovery In Ontology Learning Involves Attribute O...mentioning

confidence: 99%

“…In particular, CNN has an input layer that directly receives two-dimensional objects, a feature extraction process done through convolution, and the subsampling layer implemented using multiple fully connected hidden layers as shown in Figure 16. It is reported that [113], correct hyperparameters setting improves performance during training. For instance, Guruvayur et al [113] developed a 6-step CNN algorithm for the classification of text and explained that, given a batch size of 50, running for 50 epochs, and A convolution operation uses a filter, called w, to create a new feature based on a window of h words in a word vector [114].…”

Section: Relation Discovery In Ontology Learning Involves Attribute O...mentioning

confidence: 99%

“…It is reported that [113], correct hyperparameters setting improves performance during training. For instance, Guruvayur et al [113] developed a 6-step CNN algorithm for the classification of text and explained that, given a batch size of 50, running for 50 epochs, and A convolution operation uses a filter, called w, to create a new feature based on a window of h words in a word vector [114]. Using a window of words x i:i+h−1 , a feature c i can be created, as in Equation 22.…”

Section: Relation Discovery In Ontology Learning Involves Attribute O...mentioning

confidence: 99%

See 1 more Smart Citation

A Review of State of the Art Deep Learning Models for Ontology Construction

Zengeya,

Vincent Fonou-Dombeu

2024

IEEE Access

View full text Add to dashboard Cite

ABSRTACT Researchers are working towards automation of ontology construction to manage the evergrowing data on the web. Currently, there is a shift from the use of machine learning techniques towards exploration of deep learning models for ontology construction. Deep learning model are capable of extracting terms, entities, relations, and classifications, and perform axiom learning from the underutilized richness of web-based knowledge. There has been remarkable progress in automatic ontology creation using deep learning models since they can perform word embedding, long-term dependency acquisition, concept extraction from large corpora, and inference of abstracted relationships based on broad corpora. Despite their emerging importance, deep learning models remain underutilized in ontology construction, and there is no comprehensive review of their application in ontology learning. This paper presents a comprehensive review of existing deep-learning models for the construction of ontologies, the strength and the weaknesses presented by the deep learning models for ontology learning as well as promising directions to achieve a more robust deep learning models. The Deep Learning models reviewed include Recurrent Neural Networks (RNNs), Convolutional Neural Networks (CNNs), Long-Short Term Memory (LSTMs), and Gated Recurrent Unit (GRU) as well as their ensembles. While these traditional deep learning models have achieved great success, one of their limitations is that they struggle to understand the meaning and order of data in sequences. CNNs and RNN-based models such as LSTMs and GRUs can be computationally expensive due to their large number of parameters or complex gating mechanisms. Furthermore, RNN models suffer from vanishing gradients, making it difficult to learn long-term relationships in sequences. Additionally, RNN-based models process information sequentially, limiting their ability to take advantage of powerful parallel computing hardware, slowing down training and inference, especially for long sequences. Consequently, there has been a shift towards Generative Pre-Trained (GPT) models and Bidirectional Encoder Representations from Transformers (BERT) models. This paper also reviewed the GPT-3, GPT-4, and the BERT models for extracting terms, entities, relations, and classifications. While GPT models excel in contextual understanding and flexibility, they fall short when handling domain-specific terminology and disambiguating complex relationships. Fine-tuning and domain-specific training data could minimize these shortcomings, and further enhance the performance of GPT in term and relation extraction tasks. On the other hand, the BERT models excel in comprehending context-heavy texts, but struggles with higher-level abstraction and inference tasks due to a lack of explicit semantic knowledge, thus necessitating inference for unspecified relationships. The paper recommends further research on deep learning models for ontology alignment and merging. Also, the ensembling of deep learning models and the u...

show abstract

Automatic Relationship Construction in Domain Ontology Engineering using Semantic and Thematic Graph Generation Process and Convolution Neural Network

Cited by 2 publications

References 26 publications

Constructing Domain Ontology for Alzheimer Disease Using Deep Learning Based Approach

Constructing Domain Ontology for Alzheimer Disease Using Deep Learning Based Approach

A Review of State of the Art Deep Learning Models for Ontology Construction

Contact Info

Product

Resources

About