Attention-based Unsupervised Keyphrase Extraction and Phrase Graph for COVID-19 Medical Literature Retrieval

Searching, reading, and finding information from the massive medical text collections are challenging. A typical biomedical search engine is not feasible to navigate each article to find critical information or keyphrases. Moreover, few tools provide a visualization of the relevant phrases to the query. However, there is a need to extract the keyphrases from each document for indexing and efficient search. The transformer-based neural networks—BERT has been used for various natural language processing tasks. The built-in self-attention mechanism can capture the associations between words and phrases in a sentence. This research investigates whether the self-attentions can be utilized to extract keyphrases from a document in an unsupervised manner and identify relevancy between phrases to construct a query relevancy phrase graph to visualize the search corpus phrases on their relevancy and importance. The comparison with six baseline methods shows that the self-attention-based unsupervised keyphrase extraction works well on a medical literature dataset. This unsupervised keyphrase extraction model can also be applied to other text data. The query relevancy graph model is applied to the COVID-19 literature dataset and to demonstrate that the attention-based phrase graph can successfully identify the medical phrases relevant to the query terms.

Inhibition of RANKL and Sema4d Improves Residual Ridge Resorption in Mice.

Residual ridge resorption (RRR) is a chronic and progressive bone resorption following tooth loss. It causes deterioration of the oral environments and leads to the pathogenesis of various systemic diseases. However, the molecular mechanisms and risk factors for RRR progression are still unclear and controversial. In this study, we developed a tooth extraction model using mice for analyzing long-term morphological and gene expression changes in the alveolar bone. We further applied ovariectomy to this model to elucidate the effects of osteoporosis on RRR progression. As a result, the alveolar bone loss was biphasic and consisted of rapid loss in the early stages and subsequently slow and sustained bone loss over a long period. Gene expression analysis indicated that ovariectomy increased the expression of pro-inflammatory cytokines in the alveolar bone and prolonged the activation of osteoclasts same as histological analysis. Furthermore, the expressions of Tnfsf11 and Sema4d kept increasing for a long time in OVX mice. Administration of neutralization antibodies for receptor activator of NF-κB ligand (RANKL) effectively suppressed RRR. Similarly, inhibition of Semaphorin 4d (Sema4d) also improved alveolar bone loss. This study demonstrated that osteoporosis is a risk factor for RRR and that RANKL and Sema4d suppression are potential treatments.

Sentiment-Target Word Pair Extraction Model Using Statistical Analysis of Sentence Structures

Product information has been propagated online via forums and social media. Lots of merchandise are recommended via an expert system method and is considered for purchase by online comments or product reviews. For predicting people’s opinions on products, studying people’s thoughts via extracting information in documents is referred to as sentiment analysis. Finding sentiment-target word pairs is an important sentiment mining research issue. With the Korean language, as the predicate appears at the very end, it is not easy to find the exact word pairs without first identifying the syntactic structure of the sentence. In this study, we propose a model that parses sentence structures and extracts sentiment-target word pairs from the parse tree. The proposed model extracts the sentiment-target word pairs that appear in the sentence by using parsing and statistical methods. For extracting sentiment-target word pairs, this model uses a sentiment word extractor and a target word extractor. After testing data from 4000 movie reviews, the applicable model showed high performance in both accuracy 93.25 (+14.45) and F1-score 82.29 (+3.31) compared with others. However, improvements in the recall rate (−0.35) are needed and computational costs must be reduced.

Reinforcement Learning Approach for Adaptive e-Learning Based on Multiple Learner Characteristics

We introduce a novel three stepwise model of adaptive e-learning using multiple learner characteristics. We design a model of a learner attributes enlisting the study domain, summary details of the student and the requirements of the student. We include the theories of learning style to categorize and identify specific individuals so as to improve their experience on the online learning platform and apply it in the model. The affective state extraction model which extracts learner emotions from text inputs during the platform interactions. We finally pass the system extracted information the adaptivity domain which uses the off-policy Q-learning model free algorithm (Jang et al., 2019) to structure the learning path into tutorials, lectures and workshops depending on predefined constraints of learning. Simulated results show better adaptivity incases of multiple characteristics as opposed to single learner characteristics. Further research to include more than three characteristics as in this research.

Digital Music Waveform Analysis and Retrieval Based on Feature Extraction Algorithm

In order to improve the feature extraction effect of digital music and improve the efficiency of music retrieval, this paper combines digital technology to analyze music waveforms, extract music features, and realize digital processing of music features. Taking the extraction of waveform music file features as the starting point, this paper combines the digital music feature extraction algorithm to build a music feature extraction model and conducts an in-depth analysis of the digital music waveform extraction process. In addition, by setting the threshold, the linear difference between the sampling points on both sides of the threshold on the leading edge of the waveform is used to obtain the overthreshold time. From the experimental research results, it can be seen that the music feature extraction model based on digital music waveform analysis proposed in this paper has good results.

Synergistic Use of Geospatial Data for Water Body Extraction from Sentinel-1 Images for Operational Flood Monitoring across Southeast Asia Using Deep Neural Networks

Deep learning is a promising method for image classification, including satellite images acquired by various sensors. However, the synergistic use of geospatial data for water body extraction from Sentinel-1 data using deep learning and the applicability of existing deep learning models have not been thoroughly tested for operational flood monitoring. Here, we present a novel water body extraction model based on a deep neural network that exploits Sentinel-1 data and flood-related geospatial datasets. For the model, the U-Net was customised and optimised to utilise Sentinel-1 data and other flood-related geospatial data, including digital elevation model (DEM), Slope, Aspect, Profile Curvature (PC), Topographic Wetness Index (TWI), Terrain Ruggedness Index (TRI), and Buffer for the Southeast Asia region. Testing and validation of the water body extraction model was applied to three Sentinel-1 images for Vietnam, Myanmar, and Bangladesh. By segmenting 384 Sentinel-1 images, model performance and segmentation accuracy for all of the 128 cases that the combination of stacked layers had determined were evaluated following the types of combined input layers. Of the 128 cases, 31 cases showed improvement in Overall Accuracy (OA), and 19 cases showed improvement in both averaged intersection over union (IOU) and F1 score for the three Sentinel-1 images segmented for water body extraction. The averaged OA, IOU, and F1 scores of the ‘Sentinel-1 VV’ band are 95.77, 80.35, and 88.85, respectively, whereas those of ‘band combination VV, Slope, PC, and TRI’ are 96.73, 85.42, and 92.08, showing improvement by exploiting geospatial data. Such improvement was further verified with water body extraction results for the Chindwin river basin, and quantitative analysis of ‘band combination VV, Slope, PC, and TRI’ showed an improvement of the F1 score by 7.68 percent compared to the segmentation output of the ‘Sentinel-1 VV’ band. Through this research, it was demonstrated that the accuracy of deep learning-based water body extraction from Sentinel-1 images can be improved up to 7.68 percent by employing geospatial data. To the best of our knowledge, this is the first work of research that demonstrates the synergistic use of geospatial data in deep learning-based water body extraction over wide areas. It is anticipated that the results of this research could be a valuable reference when deep neural networks are applied for satellite image segmentation for operational flood monitoring and when geospatial layers are employed to improve the accuracy of deep learning-based image segmentation.

A Novel Hybrid Method Based on Three-Stage Extraction and DEA-CCR Models for Selecting the Optimal Conditions for Citronella Oil Extraction

In citronella oil extraction process by steam distillation, inefficient use of steam is the main cause of excessive energy consumption that affects energy cost and oil yield. This research is aimed to reduce the energy cost and increase the oil yield by studying the steam used in the process. The proposed method is the three-stage extraction model combined with the Data Envelopment Analysis developed by Charnes, Cooper and Rhodes (DEA-CCR model). Although the three-stage extraction model has been widely used, there is no research integrate this model with DEA-CCR model. It is well known that DEA-CCR model is an effective tool to evaluate efficiency of decision making units/alternatives. The advantages of this research were presented as the calculation of the optimum distillation conditions, including the steam flow rate and the distillation time, were achieved as discussed in this article. The study was comprised of 3 parts. Firstly, the three-stage extraction model for citronella oil was formulated. Secondly, the results of the proposed model were calculated under different conditions, classified by steam flow rates from 5,000 to 60,000 cm3/min for the distillation period of 15–180 min. Finally, the DEA-CCR model was utilized to evaluate and rank alternatives. The results expressed that the best condition for producing citronella oil was at the steam flow rate of 40,000 cm3/min and the distillation time of 60 min. The optimal energy cost and percentage of oil yield were equal to 0.440 kWh/mL and 0.7%, respectively. When comparing to the experimental results, the percentage error of optimal energy cost and oil yield were slightly different, with a value of 0.98% and 0.85%, respectively. Moreover, the energy consumption was also reduced by 34.6% compared to the traditional operating conditions.