AutoDefect: Defect text classification in residential buildings using a multi-task channel attention network

Yang, Donghwa; Kim, Byeol; Lee, Sang Hyo; Ahn, Yong Han; Kim, Ha Young

doi:10.1016/j.scs.2022.103803

Cited by 13 publications

(2 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Stitini et al [ 20 ] conclude that the linkage between contextual information and classification enhances and improves the recommendation results. Yang et al [ 21 ] proposed a new automated defect text classification system (AutoDefect) based on a convolutional neural network (CNN) and natural language processing (NLP) using hierarchical two-stage encoders. Ma et al [ 22 ] presented a level-by-level HMTC approach based on the bidirectional gated recurrent unit network model together with hybrid embedding used to learn the representation of the text level-by-level.…”

Section: Related Workmentioning

confidence: 99%

A Multimodel-Based Deep Learning Framework for Short Text Multiclass Classification with the Imbalanced and Extremely Small Data Set

Tong¹,

Wang²,

Rui³

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Text classification plays an important role in many practical applications. In the real world, there are extremely small datasets. Most existing methods adopt pretrained neural network models to handle this kind of dataset. However, these methods are either difficult to deploy on mobile devices because of their large output size or cannot fully extract the deep semantic information between phrases and clauses. This paper proposes a multimodel-based deep learning framework for short-text multiclass classification with an imbalanced and extremely small dataset. Our framework mainly includes five layers: the encoder layer, the word-level LSTM network layer, the sentence-level LSTM network layer, the max-pooling layer, and the SoftMax layer. The encoder layer uses DistilBERT to obtain context-sensitive dynamic word vectors that are difficult to represent in traditional feature engineering methods. Since the transformer part of this layer is distilled, our framework is compressed. Then, we use the next two layers to extract deep semantic information. The output of the encoder layer is sent to a bidirectional LSTM network, and the feature matrix is extracted hierarchically through the LSTM at the word and sentence level to obtain the fine-grained semantic representation. After that, the max-pooling layer converts the feature matrix into a lower-dimensional matrix, preserving only the obvious features. Finally, the feature matrix is taken as the input of a fully connected SoftMax layer, which contains a function that can convert the predicted linear vector into the output value as the probability of the text in each classification. Extensive experiments on two public benchmarks demonstrate the effectiveness of our proposed approach on an extremely small dataset. It retains the state-of-the-art baseline performance in terms of precision, recall, accuracy, and F1 score, and through the model size, training time, and convergence epoch, we can conclude that our method can be deployed faster and lighter on mobile devices.

show abstract

Section: Related Workmentioning

confidence: 99%

A Multimodel-Based Deep Learning Framework for Short Text Multiclass Classification with the Imbalanced and Extremely Small Data Set

Tong¹,

Wang²,

Rui³

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…To resolve this issue, text classification was applied to categorize Khmer news articles. Text classification has been used in various languages, such as English (Luo, 2021), Arabic (Alsaleh & Larabi-Marie-Sainte, 2021), Chinese (Li, 2022), Khmer (Buoy et al, 2021;Jiang et al, 2022), Korean (Yang et al, 2022) and Spanish (Trigueros et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

Multi-Class Text Classification on Khmer News Using Ensemble Method in Machine Learning Algorithms

Phann¹,

Soomlek²,

Seresangtakul³

2023

AIP

View full text Add to dashboard Cite

The research herein applies text classification with which to categorize Khmer news articles. News articles were collected from three online websites through web scraping and grouped into nine categories. After text preprocessing, the dataset was split into training and testing sets. We then evaluated the performance of the ensemble learning method via machine learning classifiers with kfold validation. Various machine learning classifiers were employed, namely logistic regression, Complement Naive Bayes, Bernoulli Naive Bayes, k-nearest neighbours, perceptron, support vector machines, stochastic gradient descent, AdaBoost, decision tree, and random forest were employed. Accuracy was improved for the categorization of Khmer news articles, in which Grid Search CV was used to find the optimal hyperparameters for each machine learning classifier with feature extraction TF-IDF and Delta TF-IDF. The results determined that the highest accuracy was achieved through the ensemble learning method in the support vector machine with the optimal hyperparameters (C = 10, kernel = rbf), using feature extraction TF-IDF and Delta TF-IDF, at 83.47% and 83.40%, respectively. The model establishes that Khmer news articles can be accurately categorized.

show abstract

Calculation Procedure for Court Injunctions Due to Flaws in Continuous and Discontinuous Cladding

Carretero-Ayuso

Antón

Fernández-Tapia

et al. 2023

Lecture Notes in Civil Engineering

View full text Add to dashboard Cite

AutoDefect: Defect text classification in residential buildings using a multi-task channel attention network

Cited by 13 publications

References 47 publications

A Multimodel-Based Deep Learning Framework for Short Text Multiclass Classification with the Imbalanced and Extremely Small Data Set

A Multimodel-Based Deep Learning Framework for Short Text Multiclass Classification with the Imbalanced and Extremely Small Data Set

Multi-Class Text Classification on Khmer News Using Ensemble Method in Machine Learning Algorithms

Calculation Procedure for Court Injunctions Due to Flaws in Continuous and Discontinuous Cladding

Contact Info

Product

Resources

About