Data Technologies and Applications最新文献

Purpose

Intent detection (ID) and slot filling (SF) are two important tasks in natural language understanding. ID is to identify the main intent of a paragraph of text. The goal of SF is to extract the information that is important to the intent from the input sentence. However, most of the existing methods use sentence-level intention recognition, which has the risk of error propagation, and the relationship between intention recognition and SF is not explicitly modeled. Aiming at this problem, this paper proposes a collaborative model of ID and SF for intelligent spoken language understanding called ID-SF-Fusion.

Design/methodology/approach

ID-SF-Fusion uses Bidirectional Encoder Representation from Transformers (BERT) and Bidirectional Long Short-Term Memory (BiLSTM) to extract effective word embedding and context vectors containing the whole sentence information respectively. Fusion layer is used to provide intent–slot fusion information for SF task. In this way, the relationship between ID and SF task is fully explicitly modeled. This layer takes the result of ID and slot context vectors as input to obtain the fusion information which contains both ID result and slot information. Meanwhile, to further reduce error propagation, we use word-level ID for the ID-SF-Fusion model. Finally, two tasks of ID and SF are realized by joint optimization training.

Findings

We conducted experiments on two public datasets, Airline Travel Information Systems (ATIS) and Snips. The results show that the Intent ACC score and Slot F1 score of ID-SF-Fusion on ATIS and Snips are 98.0 per cent and 95.8 per cent, respectively, and the two indicators on Snips dataset are 98.6 per cent and 96.7 per cent, respectively. These models are superior to slot-gated, SF-ID NetWork, stack-Prop and other models. In addition, ablation experiments were performed to further analyze and discuss the proposed model.

Originality/value

This paper uses word-level intent recognition and introduces intent information into the SF process, which is a significant improvement on both data sets.

Purpose

Coal is a critical global energy source, and fluctuations in its price significantly impact related enterprises' profitability. This study aims to develop a robust model for predicting the coal price index to enhance coal purchase strategies for coal-consuming enterprises and provide crucial information for global carbon emission reduction.

Design/methodology/approach

The proposed coal price forecasting system combines data decomposition, semi-supervised feature engineering, ensemble learning and deep learning. It addresses the challenge of merging low-resolution and high-resolution data by adaptively combining both types of data and filling in missing gaps through interpolation for internal missing data and self-supervision for initiate/terminal missing data. The system employs self-supervised learning to complete the filling of complex missing data.

Findings

The ensemble model, which combines long short-term memory, XGBoost and support vector regression, demonstrated the best prediction performance among the tested models. It exhibited superior accuracy and stability across multiple indices in two datasets, namely the Bohai-Rim steam-coal price index and coal daily settlement price.

Originality/value

The proposed coal price forecasting system stands out as it integrates data decomposition, semi-supervised feature engineering, ensemble learning and deep learning. Moreover, the system pioneers the use of self-supervised learning for filling in complex missing data, contributing to its originality and effectiveness.

Purpose

Sleep arousal detection is an important factor to monitor the sleep disorder.

Design/methodology/approach

Thus, a unique nth layer one-dimensional (1D) convolutional neural network-based U-Net model for automatic sleep arousal identification has been proposed.

Findings

The proposed method has achieved area under the precision–recall curve performance score of 0.498 and area under the receiver operating characteristics performance score of 0.946.

Originality/value

No other researchers have suggested U-Net-based detection of sleep arousal.

Research limitations/implications

From the experimental results, it has been found that U-Net performs better accuracy as compared to the state-of-the-art methods.

Practical implications

Sleep arousal detection is an important factor to monitor the sleep disorder. Objective of the work is to detect the sleep arousal using different physiological channels of human body.

Social implications

It will help in improving mental health by monitoring a person's sleep.

Purpose

COVID-19 continues to spread, and cause increasing deaths. Physicians diagnose COVID-19 using not only real-time polymerase chain reaction but also the computed tomography (CT) and chest x-ray (CXR) modalities, depending on the stage of infection. However, with so many patients and so few doctors, it has become difficult to keep abreast of the disease. Deep learning models have been developed in order to assist in this respect, and vision transformers are currently state-of-the-art methods, but most techniques currently focus only on one modality (CXR).

Design/methodology/approach

This work aims to leverage the benefits of both CT and CXR to improve COVID-19 diagnosis. This paper studies the differences between using convolutional MobileNetV2, ViT DeiT and Swin Transformer models when training from scratch and pretraining on the MedNIST medical dataset rather than the ImageNet dataset of natural images. The comparison is made by reporting six performance metrics, the Scott–Knott Effect Size Difference, Wilcoxon statistical test and the Borda Count method. We also use the Grad-CAM algorithm to study the model's interpretability. Finally, the model's robustness is tested by evaluating it on Gaussian noised images.

Findings

Although pretrained MobileNetV2 was the best model in terms of performance, the best model in terms of performance, interpretability, and robustness to noise is the trained from scratch Swin Transformer using the CXR (accuracy = 93.21 per cent) and CT (accuracy = 94.14 per cent) modalities.

Originality/value

Models compared are pretrained on MedNIST and leverage both the CT and CXR modalities.

Purpose

Advanced big data analysis and machine learning methods are concurrently used to unleash the value of the data generated by government hotline and help devise intelligent applications including automated process management, standard construction and more accurate dispatched orders to build high-quality government service platforms as more widely data-driven methods are in the process.

Design/methodology/approach

In this study, based on the influence of the record specifications of texts related to work orders generated by the government hotline, machine learning tools are implemented and compared to optimize classify dispatching tasks by performing exploratory studies on the hotline work order text, including linguistics analysis of text feature processing, new word discovery, text clustering and text classification.

Findings

The complexity of the content of the work order is reduced by applying more standardized writing specifications based on combining text grammar numerical features. So, order dispatch success prediction accuracy rate reaches 89.6 per cent after running the LSTM model.

Originality/value

The proposed method can help improve the current dispatching processes run by the government hotline, better guide staff to standardize the writing format of work orders, improve the accuracy of order dispatching and provide innovative support to the current mechanism.

Purpose

Aspect-based sentiment analysis (ASA) is a task of sentiment analysis that requires predicting aspect sentiment polarity for a given sentence. Many traditional techniques use graph-based mechanisms, which reduce prediction accuracy and introduce large amounts of noise. The other problem with graph-based mechanisms is that for some context words, the feelings change depending on the aspect, and therefore it is impossible to draw conclusions on their own. ASA is challenging because a given sentence can reveal complicated feelings about multiple aspects.

Design/methodology/approach

This research proposed an optimized attention-based DL model known as optimized aspect and self-attention aware long short-term memory for target-based semantic analysis (OAS-LSTM-TSA). The proposed model goes through three phases: preprocessing, aspect extraction and classification. Aspect extraction is done using a double-layered convolutional neural network (DL-CNN). The optimized aspect and self-attention embedded LSTM (OAS-LSTM) is used to classify aspect sentiment into three classes: positive, neutral and negative.

Findings

To detect and classify sentiment polarity of the aspect using the optimized aspect and self-attention embedded LSTM (OAS-LSTM) model. The results of the proposed method revealed that it achieves a high accuracy of 95.3 per cent for the restaurant dataset and 96.7 per cent for the laptop dataset.

Originality/value

The novelty of the research work is the addition of two effective attention layers in the network model, loss function reduction and accuracy enhancement, using a recent efficient optimization algorithm. The loss function in OAS-LSTM is minimized using the adaptive pelican optimization algorithm, thus increasing the accuracy rate. The performance of the proposed method is validated on four real-time datasets, Rest14, Lap14, Rest15 and Rest16, for various performance metrics.

Purpose

The purpose of this study is to investigate and demonstrate the advancements achieved in the field of chest X-ray image captioning through the utilization of dynamic convolutional encoder–decoder networks (DyCNN). Typical convolutional neural networks (CNNs) are unable to capture both local and global contextual information effectively and apply a uniform operation to all pixels in an image. To address this, we propose an innovative approach that integrates a dynamic convolution operation at the encoder stage, improving image encoding quality and disease detection. In addition, a decoder based on the gated recurrent unit (GRU) is used for language modeling, and an attention network is incorporated to enhance consistency. This novel combination allows for improved feature extraction, mimicking the expertise of radiologists by selectively focusing on important areas and producing coherent captions with valuable clinical information.

Design/methodology/approach

In this study, we have presented a new report generation approach that utilizes dynamic convolution applied Resnet-101 (DyCNN) as an encoder (Verelst and Tuytelaars, 2019) and GRU as a decoder (Dey and Salemt, 2017; Pan et al., 2020), along with an attention network (see Figure 1). This integration innovatively extends the capabilities of image encoding and sequential caption generation, representing a shift from conventional CNN architectures. With its ability to dynamically adapt receptive fields, the DyCNN excels at capturing features of varying scales within the CXR images. This dynamic adaptability significantly enhances the granularity of feature extraction, enabling precise representation of localized abnormalities and structural intricacies. By incorporating this flexibility into the encoding process, our model can distil meaningful and contextually rich features from the radiographic data. While the attention mechanism enables the model to selectively focus on different regions of the image during caption generation. The attention mechanism enhances the report generation process by allowing the model to assign different importance weights to different regions of the image, mimicking human perception. In parallel, the GRU-based decoder adds a critical dimension to the process by ensuring a smooth, sequential generation of captions.

Findings

The findings of this study highlight the significant advancements achieved in chest X-ray image captioning through the utilization of dynamic convolutional encoder–decoder networks (DyCNN). Experiments conducted using the IU-Chest X-ray datasets showed that the proposed model outperformed other state-of-the-art approaches. The model achieved notable scores, including a BLEU_1 score of 0.591, a BLEU_2 score of 0.347, a BLEU_3 score of 0.277 and a BLEU_4 score of 0.155. These results highlight the efficiency and efficacy of the model in producing pre