scholarly journals SA-HAVE: A Self-Attention based Hierarchical VAEs Network for Abstractive Summarization

2021 ◽  
Vol 2078 (1) ◽  
pp. 012073
Author(s):  
Xia Wan ◽  
Shenggen Ju
Keyword(s):  
Short Term Memory ◽  
Deep Structure ◽  
Research Direction ◽  
Superior Performance ◽  
Sentence Structure ◽  
Automatic Summarization ◽  
Daily Mail ◽  
Structure Information ◽  
Abstractive Summarization ◽  
Important Research Direction

Abstract The abstractive automatic summarization task is to summarize the main content of the article with short sentences, which is an important research direction in natural language generation. Most abstractive summarization models are based on sequence-to-sequence neural networks. Specifically, they encode input text sequences by Bi-directional Long Short-Term Memory (bi-LSTM), and decode summaries word-by-word by LSTM. However, existing models usually did not consider both the self-attention dependence during the encoding process using bi-LSTM, and deep potential sentence structure information for the decoding process. To tackle these limitations, we propose a Self-Attention based word embedding and Hierarchical Variational AutoEncoders (SA-HVAE) model. The model first introduces self-attention into LSTM to alleviate information decay of encoding, and accomplish summarization with deep structure information inference through hierarchical VAEs. The experimental results on the Gigaword and CNN/Daily Mail datasets validate the superior performance of SA-HVAE, and our model has a significant improvement over the baseline model.

scholarly journals 2D and 3D Palmprint and Palm Vein Recognition Based on Neural Architecture Search

2021 ◽  
Author(s):  
Wei Jia ◽  
Wei Xia ◽  
Yang Zhao ◽  
Hai Min ◽  
Yan-Xiang Chen
Keyword(s):  
Deep Learning ◽  
Recognition Performance ◽  
Research Direction ◽  
Palmprint Recognition ◽  
Neural Architecture ◽  
Development Direction ◽  
Vein Recognition ◽  
Palm Vein ◽  
2D And 3D ◽  
Important Research Direction

AbstractPalmprint recognition and palm vein recognition are two emerging biometrics technologies. In the past two decades, many traditional methods have been proposed for palmprint recognition and palm vein recognition and have achieved impressive results. In recent years, in the field of artificial intelligence, deep learning has gradually become the mainstream recognition technology because of its excellent recognition performance. Some researchers have tried to use convolutional neural networks (CNNs) for palmprint recognition and palm vein recognition. However, the architectures of these CNNs have mostly been developed manually by human experts, which is a time-consuming and error-prone process. In order to overcome some shortcomings of manually designed CNN, neural architecture search (NAS) technology has become an important research direction of deep learning. The significance of NAS is to solve the deep learning model’s parameter adjustment problem, which is a cross-study combining optimization and machine learning. NAS technology represents the future development direction of deep learning. However, up to now, NAS technology has not been well studied for palmprint recognition and palm vein recognition. In this paper, in order to investigate the problem of NAS-based 2D and 3D palmprint recognition and palm vein recognition in-depth, we conduct a performance evaluation of twenty representative NAS methods on five 2D palmprint databases, two palm vein databases, and one 3D palmprint database. Experimental results show that some NAS methods can achieve promising recognition results. Remarkably, among different evaluated NAS methods, ProxylessNAS achieves the best recognition performance.

Towards effective link prediction: A hybrid similarity model

2020 ◽  
pp. 1-14
Author(s):  
Longjie Li ◽  
Lu Wang ◽  
Hongsheng Luo ◽  
Xiaoyun Chen
Keyword(s):  
Link Prediction ◽  
Structural Similarity ◽  
Research Direction ◽  
Structural Features ◽  
Proposed Model ◽  
Similarity Model ◽  
Weight Calculation ◽  
Stable Performance ◽  
Grey Relation ◽  
Important Research Direction

Link prediction is an important research direction in complex network analysis and has drawn increasing attention from researchers in various fields. So far, a plethora of structural similarity-based methods have been proposed to solve the link prediction problem. To achieve stable performance on different networks, this paper proposes a hybrid similarity model to conduct link prediction. In the proposed model, the Grey Relation Analysis (GRA) approach is employed to integrate four carefully selected similarity indexes, which are designed according to different structural features. In addition, to adaptively estimate the weight for each index based on the observed network structures, a new weight calculation method is presented by considering the distribution of similarity scores. Due to taking separate similarity indexes into account, the proposed method is applicable to multiple different types of network. Experimental results show that the proposed method outperforms other prediction methods in terms of accuracy and stableness on 10 benchmark networks.

Knowledge Enhanced LSTM for Coreference Resolution on Biomedical Texts

2021 ◽  
Author(s):  
Yufei Li ◽  
Xiaoyong Ma ◽  
Xiangyu Zhou ◽  
Pengzhen Cheng ◽  
Kai He ◽  
...  
Keyword(s):  
Information Integration ◽  
Short Term Memory ◽  
Superior Performance ◽  
Supplementary Information ◽  
Specific Information ◽  
Coreference Resolution ◽  
Fine Grained ◽  
Domain Specific ◽  
Memory Network ◽  
Biomedical Texts

Abstract Motivation Bio-entity Coreference Resolution focuses on identifying the coreferential links in biomedical texts, which is crucial to complete bio-events’ attributes and interconnect events into bio-networks. Previously, as one of the most powerful tools, deep neural network-based general domain systems are applied to the biomedical domain with domain-specific information integration. However, such methods may raise much noise due to its insufficiency of combining context and complex domain-specific information. Results In this paper, we explore how to leverage the external knowledge base in a fine-grained way to better resolve coreference by introducing a knowledge-enhanced Long Short Term Memory network (LSTM), which is more flexible to encode the knowledge information inside the LSTM. Moreover, we further propose a knowledge attention module to extract informative knowledge effectively based on contexts. The experimental results on the BioNLP and CRAFT datasets achieve state-of-the-art performance, with a gain of 7.5 F1 on BioNLP and 10.6 F1 on CRAFT. Additional experiments also demonstrate superior performance on the cross-sentence coreferences. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals FetNet: a recurrent convolutional network for occlusion identification in fetoscopic videos

2020 ◽  
Vol 15 (5) ◽  
pp. 791-801 ◽  
Author(s):  
Sophia Bano ◽  
Francisco Vasconcelos ◽  
Emmanuel Vander Poorten ◽  
Tom Vercauteren ◽  
Sebastien Ourselin ◽  
...  
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Laser Photocoagulation ◽  
Short Term Memory ◽  
Total Duration ◽  
Frame Rate ◽  
Superior Performance ◽  
Computer Assisted ◽  
Convolutional Network ◽  
Spatio Temporal

Abstract Purpose Fetoscopic laser photocoagulation is a minimally invasive surgery for the treatment of twin-to-twin transfusion syndrome (TTTS). By using a lens/fibre-optic scope, inserted into the amniotic cavity, the abnormal placental vascular anastomoses are identified and ablated to regulate blood flow to both fetuses. Limited field-of-view, occlusions due to fetus presence and low visibility make it difficult to identify all vascular anastomoses. Automatic computer-assisted techniques may provide better understanding of the anatomical structure during surgery for risk-free laser photocoagulation and may facilitate in improving mosaics from fetoscopic videos. Methods We propose FetNet, a combined convolutional neural network (CNN) and long short-term memory (LSTM) recurrent neural network architecture for the spatio-temporal identification of fetoscopic events. We adapt an existing CNN architecture for spatial feature extraction and integrated it with the LSTM network for end-to-end spatio-temporal inference. We introduce differential learning rates during the model training to effectively utilising the pre-trained CNN weights. This may support computer-assisted interventions (CAI) during fetoscopic laser photocoagulation. Results We perform quantitative evaluation of our method using 7 in vivo fetoscopic videos captured from different human TTTS cases. The total duration of these videos was 5551 s (138,780 frames). To test the robustness of the proposed approach, we perform 7-fold cross-validation where each video is treated as a hold-out or test set and training is performed using the remaining videos. Conclusion FetNet achieved superior performance compared to the existing CNN-based methods and provided improved inference because of the spatio-temporal information modelling. Online testing of FetNet, using a Tesla V100-DGXS-32GB GPU, achieved a frame rate of 114 fps. These results show that our method could potentially provide a real-time solution for CAI and automating occlusion and photocoagulation identification during fetoscopic procedures.

Preparation and Properties of Alginate Fibre

2011 ◽  
Vol 335-336 ◽  
pp. 419-422 ◽  
Author(s):  
Yuan Lian ◽  
Jian Yi Wu ◽  
Da Peng Zhou ◽  
Hong Mei Wang ◽  
Dian Wu Huang ◽  
...  
Keyword(s):  
Research Direction ◽  
Biological Properties ◽  
Wet Spinning ◽  
Structure And Properties ◽  
Important Research ◽  
Preparation Technology ◽  
Thermal Gravimetric Analyzer ◽  
Infrared Spectrometer ◽  
Medical Materials ◽  
Important Research Direction

Alginate fibre has attracted great attention in the area of biological medical materials due to its unique biological properties. But its low tenacity greatly hinders its application area. Therefore, the preparation technology of alginate fibre has been as an important research direction in this area in recent years. The purpose of this article is to prepare the calcium alginate fibre with good properties by wet spinning. The structure and properties of this fibre are analyzed by scanning electron microscope，infrared spectrometer，thermal gravimetric analyzer and DSC.

scholarly journals A Pointer Generator Network Model to Automatic Text Summarization and Headline Generation

2019 ◽  
Vol 8 (5S3) ◽  
pp. 447-451
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Recurrent Neural Network ◽  
Text Summarization ◽  
Daily Mail ◽  
Automatic Text Summarization ◽  
Generator Model ◽  
Abstractive Summarization ◽  
Automatic Text

In a world where information is growing rapidly every single day, we need tools to generate summary and headlines from text which is accurate as well as short and precise. In this paper, we have described a method for generating headlines from article. This is done by using hybrid pointer-generator network with attention distribution and coverage mechanism on article which generates abstractive summarization followed by the application of encoder-decoder recurrent neural network with LSTM unit to generate headlines from the summary. Hybrid pointer generator model helps in removing inaccuracy as well as repetitions. We have used CNN / Daily Mail as our dataset.

scholarly journals Comparison of ARIMA, ANN and LSTM for Stock Price Prediction

2020 ◽  
Vol 218 ◽  
pp. 01026
Author(s):  
Qihang Ma
Keyword(s):  
Stock Prices ◽  
Stock Price ◽  
Short Term Memory ◽  
Moving Average ◽  
Arima Model ◽  
Predictive Ability ◽  
Research Direction ◽  
Ann Model ◽  
Advantages And Disadvantages ◽  
Stock Price Prediction

The prediction of stock prices has always been a hot topic of research. However, the autoregressive integrated moving average (ARIMA) model commonly used and artificial neural networks (ANN) still have their own advantages and disadvantages. The use of long short-term memory (LSTM) networks model for prediction also shows interesting possibilities. This article compares three models specifically through the analysis of the principles of the three models and the prediction results. In the end, it is believed that the LSTM model may have the best predictive ability, but it is greatly affected by the data processing. The ANN model performs better than that of the ARIMA model. The combination of time series and external factors may be a worthy research direction.

An enhanced OCT image captioning system to assist ophthalmologists in detecting and classifying eye diseases

2020 ◽  
Vol 28 (5) ◽  
pp. 975-988
Author(s):  
Sivamurugan Vellakani ◽  
Indumathi Pushbam
Keyword(s):  
Short Term Memory ◽  
Clinical Decision ◽  
True Positive Rate ◽  
Eye Diseases ◽  
Age Related Macular Degeneration ◽  
Superior Performance ◽  
Image Captioning ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Age Related

Human eye is affected by the different eye diseases including choroidal neovascularization (CNV), diabetic macular edema (DME) and age-related macular degeneration (AMD). This work aims to design an artificial intelligence (AI) based clinical decision support system for eye disease detection and classification to assist the ophthalmologists more effectively detecting and classifying CNV, DME and drusen by using the Optical Coherence Tomography (OCT) images depicting different tissues. The methodology used for designing this system involves different deep learning convolutional neural network (CNN) models and long short-term memory networks (LSTM). The best image captioning model is selected after performance analysis by comparing nine different image captioning systems for assisting ophthalmologists to detect and classify eye diseases. The quantitative data analysis results obtained for the image captioning models designed using DenseNet201 with LSTM have superior performance in terms of overall accuracy of 0.969, positive predictive value of 0.972 and true-positive rate of 0.969using OCT images enhanced by the generative adversarial network (GAN). The corresponding performance values for the Xception with LSTM image captioning models are 0.969, 0.969 and 0.938, respectively. Thus, these two models yield superior performance and have potential to assist ophthalmologists in making optimal diagnostic decision.

scholarly journals Height Estimation of Target Objects Based on Structured Light

2018 ◽  
Vol 2018 ◽  
pp. 1-9
Author(s):  
Wei Liu ◽  
Yongsheng Zhao
Keyword(s):  
Simple Structure ◽  
Structured Light ◽  
Three Dimensional ◽  
Research Direction ◽  
Target Object ◽  
Height Estimation ◽  
Word Structure ◽  
Dimensional Reconstruction ◽  
Important Research Direction ◽  
Structure Light

The height estimation of the target object is an important research direction in the field of computer vision. The three-dimensional reconstruction of structured light has the characteristics of high precision, noncontact, and simple structure and is widely used in military simulation and cultural heritage protection. In this paper, the height of the target object is estimated by using the word structure light. According to the height dictionary, the height under the offset is estimated by the movement of the structured light to the object. In addition, by effectively preprocessing the captured structured light images, such as expansion, seeking skeleton, and other operations, the flexibility of estimating the height of different objects by structured light is increased, and the height of the target object can be estimated more accurately.

Hearing the Beat

2016 ◽  
Vol 34 (1) ◽  
pp. 56-70 ◽  
Author(s):  
Kathleen M. Einarson ◽  
Laurel J. Trainor
Keyword(s):  
Cognitive Skills ◽  
Short Term Memory ◽  
Superior Performance ◽  
Auditory Stimuli ◽  
Perceptual Sensitivity ◽  
Short Term ◽  
Term Memory ◽  
Phase Errors ◽  
The Relationship ◽  
Better Than

Adults can extract the underlying beat from music, and entrain their movements with that beat. Although infants and children are poor at synchronizing their movements to auditory stimuli, recent findings suggest they are perceptually sensitive to the beat. We examined five-year-old children’s perceptual sensitivity to musical beat alignment (adapting the adult task of Iversen & Patel, 2008). We also examined whether sensitivity is affected by metric complexity, and whether perceptual sensitivity correlates with cognitive skills. On each trial of the complex Beat Alignment Test (cBAT) children were presented with two successive videos of puppets drumming to music with simple or complex meter. One puppet’s drumming was synchronized with the beat of the music while the other had either incorrect tempo or incorrect phase, and children were asked to select the better drummer. In two experiments, five-year-olds were able to detect beat misalignments in simple meter music significantly better than beat misalignments in complex meter music for both phase errors and tempo errors, with performance for complex meter music at chance levels. Although cBAT performance correlated with short-term memory in Experiment One, the relationship held for both simple and complex meter, so cannot explain the superior performance for culturally typical meters.

Sign in / Sign up

Export Citation Format

Share Document