scholarly journals Phonetics and Ambiguity Comprehension Gated Attention Network for Humor Recognition

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-9 ◽  
Author(s):  
Xiaochao Fan ◽  
Hongfei Lin ◽  
Liang Yang ◽  
Yufeng Diao ◽  
Chen Shen ◽  
...  
Keyword(s):  
Neural Network ◽  
Semantic Information ◽  
Semantic Representation ◽  
Research Attention ◽  
Attention Network ◽  
Phonetic Information ◽  
The Neural Network ◽  
Ambiguous Words ◽  
Public Datasets

Humor refers to the quality of being amusing. With the development of artificial intelligence, humor recognition is attracting a lot of research attention. Although phonetics and ambiguity have been introduced by previous studies, existing recognition methods still lack suitable feature design for neural networks. In this paper, we illustrate that phonetics structure and ambiguity associated with confusing words need to be learned for their own representations via the neural network. Then, we propose the Phonetics and Ambiguity Comprehension Gated Attention network (PACGA) to learn phonetic structures and semantic representation for humor recognition. The PACGA model can well represent phonetic information and semantic information with ambiguous words, which is of great benefit to humor recognition. Experimental results on two public datasets demonstrate the effectiveness of our model.

scholarly journals Extended Feature Pyramid Network with Adaptive Scale Training Strategy and Anchors for Object Detection in Aerial Images

2020 ◽  
Vol 12 (5) ◽  
pp. 784 ◽  
Author(s):  
Wei Guo ◽  
Weihong Li ◽  
Weiguo Gong ◽  
Jinkai Cui
Keyword(s):  
Neural Network ◽  
Object Detection ◽  
Semantic Information ◽  
Aerial Images ◽  
Training Strategy ◽  
The Public ◽  
Multi Scale ◽  
Shallow Layer ◽  
The Neural Network ◽  
Feature Pyramid

Multi-scale object detection is a basic challenge in computer vision. Although many advanced methods based on convolutional neural networks have succeeded in natural images, the progress in aerial images has been relatively slow mainly due to the considerably huge scale variations of objects and many densely distributed small objects. In this paper, considering that the semantic information of the small objects may be weakened or even disappear in the deeper layers of neural network, we propose a new detection framework called Extended Feature Pyramid Network (EFPN) for strengthening the information extraction ability of the neural network. In the EFPN, we first design the multi-branched dilated bottleneck (MBDB) module in the lateral connections to capture much more semantic information. Then, we further devise an attention pathway for better locating the objects. Finally, an augmented bottom-up pathway is conducted for making shallow layer information easier to spread and further improving performance. Moreover, we present an adaptive scale training strategy to enable the network to better recognize multi-scale objects. Meanwhile, we present a novel clustering method to achieve adaptive anchors and make the neural network better learn data features. Experiments on the public aerial datasets indicate that the presented method obtain state-of-the-art performance.

Depth Image Compression and Error Concealment for 3D Video Communication

2015 ◽  
Vol 764-765 ◽  
pp. 863-867
Author(s):  
Yih Chuan Lin ◽  
Pu Jian Hsu
Keyword(s):  
Neural Network ◽  
Communication Channel ◽  
Error Concealment ◽  
3D Video ◽  
Depth Image ◽  
Noisy Channel ◽  
The Neural Network ◽  
Processing Ability ◽  
Data Volume

In this paper, an error concealment scheme for neural-network based compression of depth image in 3D videos is proposed. In the neural-network based compression, each depth image is represented by one or more neural networks. The advantage of neural-network based compression lies in the parallel processing ability of multiple neurons, which can handle the massive data volume of 3D videos. The similarity of neuron weights of neighboring nodes is exploited to recover the loss neuron weights when transmitting with an error-prone communication channel. With a simulated noisy channel, the quality of compressed 3D video, which is reconstructed undergoing the noisy channel, can be recovered well by the proposed error concealment scheme.

scholarly journals An Enhancement for the Consistent Depth Estimation of Monocular Videos using Lightweight Network

2021 ◽  
Vol 8 (3) ◽  
pp. 15-27
Author(s):  
Mohamed N. Sweilam ◽  
Nikolay Tolstokulakov
Keyword(s):  
Neural Network ◽  
Computer Vision ◽  
Mobile Phones ◽  
Depth Estimation ◽  
The Neural Network ◽  
Monocular Video ◽  
Great Progress ◽  
Run Time

Depth estimation has made great progress in the last few years due to its applications in robotics science and computer vision. Various methods have been implemented and enhanced to estimate the depth without flickers and missing holes. Despite this progress, it is still one of the main challenges for researchers, especially for the video applications which have more complexity of the neural network which af ects the run time. Moreover to use such input like monocular video for depth estimation is considered an attractive idea, particularly for hand-held devices such as mobile phones, they are very popular for capturing pictures and videos, in addition to having a limited amount of RAM. Here in this work, we focus on enhancing the existing consistent depth estimation for monocular videos approach to be with less usage of RAM and with using less number of parameters without having a significant reduction in the quality of the depth estimation.

scholarly journals Using high-performance deep learning platform to accelerate object detection

2019 ◽  
pp. 354-360 ◽  
Author(s):  
S O Stepanenko ◽  
P Y Yakimov
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Image Processing ◽  
Processing Speed ◽  
High Performance ◽  
Object Classification ◽  
High Accuracy ◽  
Learning Platform ◽  
The Neural Network

Object classification with use of neural networks is extremely current today. YOLO is one of the most often used frameworks for object classification. It produces high accuracy but the processing speed is not high enough especially in conditions of limited performance of a computer. This article researches use of a framework called NVIDIA TensorRT to optimize YOLO with the aim of increasing the image processing speed. Saving efficiency and quality of the neural network work TensorRT allows us to increase the processing speed using an optimization of the architecture and an optimization of calculations on a GPU.

scholarly journals Improved Docking of Protein Models by a Combination of Alphafold2 and ClusPro

2021 ◽  
Author(s):  
Usman Ghani ◽  
Israel Desta ◽  
Akhil Jindal ◽  
Omeir Khan ◽  
George Jones ◽  
...  
Keyword(s):  
Neural Network ◽  
Success Rate ◽  
Protein Docking ◽  
Additional Step ◽  
The Neural Network ◽  
Docking Program ◽  
Protein Models ◽  
Docking Benchmark ◽  
Benchmark Sets

AbstractIt has been demonstrated earlier that the neural network based program AlphaFold2 can be used to dock proteins given the two sequences separated by a gap as the input. The protocol presented here combines AlphaFold2 with the physics based docking program ClusPro. The monomers of the model generated by AlphaFold2 are separated, re-docked using ClusPro, and the resulting 10 models are refined by AlphaFold2. Finally, the five original AlphaFold2 models are added to the 10 AlphaFold2 refined ClusPro models, and the 15 models are ranked by their predicted aligned error (PAE) values obtained by AlphaFold2. The protocol is applied to two benchmark sets of complexes, the first based on the established protein-protein docking benchmark, and the second consisting of only structures released after May 2018, the cut-off date for training AlphaFold2. It is shown that the quality of the initial AlphaFold2 models improves with each additional step of the protocol. In particular, adding the AlphaFold2 refined ClusPro models to the AlphaFold2 models increases the success rate by 23% in the top 5 predictions, whereas considering the 10 models obtained by the combined protocol increases the success rate to close to 40%. The improvement is similar for the second benchmark that includes only complexes distinct from the proteins used for training the neural network.

scholarly journals Identification of Rice Variety Using Geometric Features and Neural Network

2019 ◽  
Vol 13 (3) ◽  
pp. 301
Author(s):  
Wahyu Srimulyani ◽  
Aina Musdholifah
Keyword(s):  
Neural Network ◽  
Rice Variety ◽  
Physical Characteristics ◽  
Training Data ◽  
Test Results ◽  
Trial And Error ◽  
Rice Varieties ◽  
Segmentation Evaluation ◽  
The Neural Network

 Indonesia has many food varieties, one of which is rice varieties. Each rice variety has physical characteristics that can be recognized through color, texture, and shape. Based on these physical characteristics, rice can be identified using the Neural Network. Research using 12 features has not optimal results. This study proposes the addition of geometry features with Learning Vector Quantization and Backpropagation algorithms that are used separately.The trial uses data from 9 rice varieties taken from several regions in Yogyakarta. The acquisition of rice was carried out using a camera Canon D700 with a kit lens and maximum magnification, 55 mm. Data sharing is carried out for training and testing, and the training data was sharing with the quality of the rice. Preprocessing of data was carried out before feature extraction with the trial and error thresholding process of segmentation. Evaluation is done by comparing the results of the addition of 6 geometry features and before adding geometry features.The test results show that the addition of 6 geometry features gives an increase in the value of accuracy. This is evidenced by the Backpropagation algorithm resulting in increased accuracy of 100% and 5.2% the result of the LVQ algorithm.

scholarly journals DEVELOPMENT OF ALGORITHMIC SUPPORT AND A DEDICATED DEVICE FOR IMAGING THE INTERNAL ORGANS OF THE PATIENT ACCORDING TO MRI AND CT SCANNERS

2019 ◽  
Vol 22 (6) ◽  
pp. 189-197
Author(s):  
E. S. Sirota ◽  
M. I. Truphanov
Keyword(s):  
Neural Network ◽  
Three Dimensional ◽  
Color Difference ◽  
Learning Criterion ◽  
Average Value ◽  
Advantages And Disadvantages ◽  
The Neural Network ◽  
Training Stage ◽  
Algorithmic Support

In work the algorithm of restoration of the images damaged as a result of influence of noise of various nature is considered. The advantages and disadvantages of the existing approaches, as well as the prospects of using artificial neural networks, are noted. A double-layer neural network is used as an image restoration tool, and it is assumed that the location of the damaged pixels is known. A neuron is represented as a 3x3 array, where each element of the array has a pixel color value that corresponds to the value of that color in the palette. The neural network is trained on intact images, while the color difference of pixels acts as a learning criterion. For a more accurate restoration, it is recommended at the training stage to select images similar in color to damaged ones. At the recovery stage, neurons (3x3) are formed around the damaged pixels, so that the damaged pixel is located in the middle of the neuron data array. The damaged pixel is assigned a neuron value depending on the average value of the weights matrix. An algorithm for the restoration of pixels, as well as its software implementation. The simulation was carried out in the RGB palette separately for each channel. To assess the quality of the recovery were selected groups of images with varying degrees of damage. Unlike existing solutions, the algorithm has the simplicity of implementation. The  research results show that regardless of the degree of damage (within 50%), about 70% of damaged pixels are restored. Further studies suggest a modification of the algorithm to restore images with enlarged areas of damage, as well as adapting it to restore three-dimensional images.

scholarly journals System of providing sustainability of tower cranes from overturn in extreme wind loads

2018 ◽  
Vol 224 ◽  
pp. 02086
Author(s):  
Pavel Sorokin ◽  
Alexey Mishin ◽  
Vitaliy Antsev ◽  
Alexey Red’kin
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Network Models ◽  
Wind Loads ◽  
Neural Network Models ◽  
Quality Of Work ◽  
Development Stages ◽  
The Neural Network ◽  
Extreme Wind

The article is devoted to the issues of ensuring stability of tower cranes from overturn. The development stages of devices for ensuring tower cranes safety are examined and their shortcomings are revealed. The system consisting of subsystems and drives is proposed and their interaction is presented. The article deals with a subsystem based on artificial intelligence methods. The neural network models of forecasting wind parameters are developed. The quality of work of neural network models is estimated. The ways of further topic development are suggested.

USING OF LSTM NETWORKS IN SENTIMENT ANALYSIS OF DOCUMENTS IN KAZAKH LANGUAGE

2020 ◽  
Vol 69 (1) ◽  
pp. 366-370
Author(s):  
N.K. Kadyrbek ◽  
◽  
М.Е. Mansurova ◽  
М.Е. Kyrgyzbayeva ◽  
◽  
...  
Keyword(s):  
Neural Network ◽  
Social Networks ◽  
Social Media ◽  
Sentiment Analysis ◽  
Mobile Phones ◽  
User Reviews ◽  
Average Value ◽  
First Case ◽  
The Neural Network

Due to the growing trust in information in social media resources, interest in the field of sentiment analysis is growing. Because sentiment analysis is one of the main technologies for monitoring the opinions of millions of users of social networks. The article discusses the use of LSTM networks in the analysis of the tonality of texts in the Kazakh language. For training the neural network, 1000 user reviews of mobile phones were used. The experiments were carried out in two ways: in the first case, preprocessing of the analyzed reviews was carried out, in the second case, the preprocessing was not carried out. The average value of the metric for assessing the quality of the pre-processed model reached 80%. This indicator is 11% higher than for a model trained on data without preprocessing. The results of the study allowed us to conclude that the preprocessing of the texts improves the quality of the model.

Sign in / Sign up

Export Citation Format

Share Document