scholarly journals Deep Image Understanding Using Multilayered Contexts

2018 ◽  
Vol 2018 ◽  
pp. 1-11 ◽  
Author(s):  
Donghyeop Shin ◽  
Incheol Kim
Keyword(s):  
Natural Language ◽  
High Performance ◽  
Lower Layer ◽  
Image Understanding ◽  
Performance Comparison ◽  
Context Information ◽  
Data Set ◽  
Ongoing Research ◽  
Proposed Model ◽  
Deep Image

Generation of scene graphs and natural language captions from images for deep image understanding is an ongoing research problem. Scene graphs and natural language captions have a common characteristic in that they are generated by considering the objects in the images and the relationships between the objects. This study proposes a deep neural network model named the Context-based Captioning and Scene Graph Generation Network (C2SGNet), which simultaneously generates scene graphs and natural language captions from images. The proposed model generates results through communication of context information between these two tasks. For effective communication of context information, the two tasks are structured into three layers: the object detection, relationship detection, and caption generation layers. Each layer receives related context information from the lower layer. In this study, the proposed model was experimentally assessed using the Visual Genome benchmark data set. The performance improvement effect of the context information was verified through various experiments. Further, the high performance of the proposed model was confirmed through performance comparison with existing models.

An Efficient Time Series Forecasting Method Exploiting Fuzziness and Turbulences in Data

2018 ◽  
pp. 1773-1791 ◽  
Author(s):  
Prateek Pandey ◽  
Shishir Kumar ◽  
Sandeep Shrivastava
Keyword(s):  
Time Series ◽  
Performance Comparison ◽  
Time Series Forecasting ◽  
Fuzzy Time Series ◽  
Data Set ◽  
Common Trend ◽  
Proposed Model ◽  
Forecasting Method ◽  
High Degree ◽  
Degree Of Instability

In recent years, there has been a growing interest in Time Series forecasting. A number of time series forecasting methods have been proposed by various researchers. However, a common trend found in these methods is that they all underperform on a data set that exhibit uneven ups and downs (turbulences). In this paper, a new method based on fuzzy time-series (henceforth FTS) to forecast on the fundament of turbulences in the data set is proposed. The results show that the turbulence based fuzzy time series forecasting is effective, especially, when the available data indicate a high degree of instability. A few benchmark FTS methods are identified from the literature, their limitations and gaps are discussed and it is observed that the proposed method successfully overcome their deficiencies to produce better results. In order to validate the proposed model, a performance comparison with various conventional time series models is also presented.

Parsing Noun Phrases in the Penn Treebank

2011 ◽  
Vol 37 (4) ◽  
pp. 753-809 ◽  
Author(s):  
David Vadas ◽  
James R. Curran
Keyword(s):  
Natural Language ◽  
Language Processing ◽  
Gold Standard ◽  
High Performance ◽  
Large Scale ◽  
Complex Structure ◽  
Noun Phrases ◽  
Simple Task ◽  
Data Set ◽  
Lexical Information

Noun phrases (nps) are a crucial part of natural language, and can have a very complex structure. However, this np structure is largely ignored by the statistical parsing field, as the most widely used corpus is not annotated with it. This lack of gold-standard data has restricted previous efforts to parse nps, making it impossible to perform the supervised experiments that have achieved high performance in so many Natural Language Processing (nlp) tasks. We comprehensively solve this problem by manually annotating np structure for the entire Wall Street Journal section of the Penn Treebank. The inter-annotator agreement scores that we attain dispel the belief that the task is too difficult, and demonstrate that consistent np annotation is possible. Our gold-standard np data is now available for use in all parsers. We experiment with this new data, applying the Collins (2003) parsing model, and find that its recovery of np structure is significantly worse than its overall performance. The parser's F-score is up to 5.69% lower than a baseline that uses deterministic rules. Through much experimentation, we determine that this result is primarily caused by a lack of lexical information. To solve this problem we construct a wide-coverage, large-scale np Bracketing system. With our Penn Treebank data set, which is orders of magnitude larger than those used previously, we build a supervised model that achieves excellent results. Our model performs at 93.8% F-score on the simple task that most previous work has undertaken, and extends to bracket longer, more complex nps that are rarely dealt with in the literature. We attain 89.14% F-score on this much more difficult task. Finally, we implement a post-processing module that brackets nps identified by the Bikel (2004) parser. Our np Bracketing model includes a wide variety of features that provide the lexical information that was missing during the parser experiments, and as a result, we outperform the parser's F-score by 9.04%. These experiments demonstrate the utility of the corpus, and show that many nlp applications can now make use of np structure.

An Efficient Time Series Forecasting Method Exploiting Fuzziness and Turbulences in Data

2017 ◽  
Vol 6 (4) ◽  
pp. 83-98 ◽  
Author(s):  
Prateek Pandey ◽  
Shishir Kumar ◽  
Sandeep Shrivastava
Keyword(s):  
Time Series ◽  
Performance Comparison ◽  
Time Series Forecasting ◽  
Fuzzy Time Series ◽  
Time Series Models ◽  
Data Set ◽  
Common Trend ◽  
Proposed Model ◽  
Forecasting Method ◽  
High Degree

In recent years, there has been a growing interest in Time Series forecasting. A number of time series forecasting methods have been proposed by various researchers. However, a common trend found in these methods is that they all underperform on a data set that exhibit uneven ups and downs (turbulences). In this paper, a new method based on fuzzy time-series (henceforth FTS) to forecast on the fundament of turbulences in the data set is proposed. The results show that the turbulence based fuzzy time series forecasting is effective, especially, when the available data indicate a high degree of instability. A few benchmark FTS methods are identified from the literature, their limitations and gaps are discussed and it is observed that the proposed method successfully overcome their deficiencies to produce better results. In order to validate the proposed model, a performance comparison with various conventional time series models is also presented.

A Review and evaluation of Machine Translation methods for Lumasaaba

2020 ◽  
pp. 3-17
Author(s):  
Peter Nabende
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Machine Translation ◽  
Language Processing ◽  
Research Area ◽  
Data Driven ◽  
East African ◽  
Data Set ◽  
African Languages ◽  
Translation Methods

Natural Language Processing for under-resourced languages is now a mainstream research area. However, there are limited studies on Natural Language Processing applications for many indigenous East African languages. As a contribution to covering the current gap of knowledge, this paper focuses on evaluating the application of well-established machine translation methods for one heavily under-resourced indigenous East African language called Lumasaaba. Specifically, we review the most common machine translation methods in the context of Lumasaaba including both rule-based and data-driven methods. Then we apply a state of the art data-driven machine translation method to learn models for automating translation between Lumasaaba and English using a very limited data set of parallel sentences. Automatic evaluation results show that a transformer-based Neural Machine Translation model architecture leads to consistently better BLEU scores than the recurrent neural network-based models. Moreover, the automatically generated translations can be comprehended to a reasonable extent and are usually associated with the source language input.

EXPONENTIATED HALF-LOGISTIC LOMAX DISTRIBUTION WITH PROPERTIES AND APPLICATION

2019 ◽  
Vol XVI (2) ◽  
pp. 1-11
Author(s):  
Farrukh Jamal ◽  
Hesham Mohammed Reyad ◽  
Soha Othman Ahmed ◽  
Muhammad Akbar Ali Shah ◽  
Emrah Altun
Keyword(s):  
Real Data ◽  
Continuous Model ◽  
Model Parameters ◽  
Data Set ◽  
Lomax Distribution ◽  
Mathematical Properties ◽  
Proposed Model ◽  
Probability Weighted Moment ◽  
Record Statistics ◽  
Maximum Likelihood Criterion

A new three-parameter continuous model called the exponentiated half-logistic Lomax distribution is introduced in this paper. Basic mathematical properties for the proposed model were investigated which include raw and incomplete moments, skewness, kurtosis, generating functions, Rényi entropy, Lorenz, Bonferroni and Zenga curves, probability weighted moment, stress strength model, order statistics, and record statistics. The model parameters were estimated by using the maximum likelihood criterion and the behaviours of these estimates were examined by conducting a simulation study. The applicability of the new model is illustrated by applying it on a real data set.

A Review on Sentiment Classification: Natural Language Understanding

2019 ◽  
Vol 13 (1) ◽  
pp. 20-27 ◽  
Author(s):  
Srishty Jindal ◽  
Kamlesh Sharma
Keyword(s):  
Natural Language ◽  
Sentiment Analysis ◽  
Social Networking Sites ◽  
Natural Language Understanding ◽  
Business Analytics ◽  
Language Understanding ◽  
Text Data ◽  
Data Set ◽  
Market Positioning ◽  
Illegal Activities

Background: With the tremendous increase in the use of social networking sites for sharing the emotions, views, preferences etc. a huge volume of data and text is available on the internet, there comes the need for understanding the text and analysing the data to determine the exact intent behind the same for a greater good. This process of understanding the text and data involves loads of analytical methods, several phases and multiple techniques. Efficient use of these techniques is important for an effective and relevant understanding of the text/data. This analysis can in turn be very helpful in ecommerce for targeting audience, social media monitoring for anticipating the foul elements from society and take proactive actions to avoid unethical and illegal activities, business analytics, market positioning etc. Method: The goal is to understand the basic steps involved in analysing the text data which can be helpful in determining sentiments behind them. This review provides detailed description of steps involved in sentiment analysis with the recent research done. Patents related to sentiment analysis and classification are reviewed to throw some light in the work done related to the field. Results: Sentiment analysis determines the polarity behind the text data/review. This analysis helps in increasing the business revenue, e-health, or determining the behaviour of a person. Conclusion: This study helps in understanding the basic steps involved in natural language understanding. At each step there are multiple techniques that can be applied on data. Different classifiers provide variable accuracy depending upon the data set and classification technique used.

Human Activity Recognition using Fourier Transform Inspired Deep Learning Combination Model

2019 ◽  
Vol 9 (1) ◽  
pp. 16-31
Author(s):  
Kyungkoo Jun
Keyword(s):  
Fourier Transform ◽  
Deep Learning ◽  
Short Term Memory ◽  
Window Size ◽  
Sensor Data ◽  
Data Sets ◽  
Data Set ◽  
Proposed Model ◽  
Testing Data ◽  
Labeling Scheme

Background & Objective: This paper proposes a Fourier transform inspired method to classify human activities from time series sensor data. Methods: Our method begins by decomposing 1D input signal into 2D patterns, which is motivated by the Fourier conversion. The decomposition is helped by Long Short-Term Memory (LSTM) which captures the temporal dependency from the signal and then produces encoded sequences. The sequences, once arranged into the 2D array, can represent the fingerprints of the signals. The benefit of such transformation is that we can exploit the recent advances of the deep learning models for the image classification such as Convolutional Neural Network (CNN). Results: The proposed model, as a result, is the combination of LSTM and CNN. We evaluate the model over two data sets. For the first data set, which is more standardized than the other, our model outperforms previous works or at least equal. In the case of the second data set, we devise the schemes to generate training and testing data by changing the parameters of the window size, the sliding size, and the labeling scheme. Conclusion: The evaluation results show that the accuracy is over 95% for some cases. We also analyze the effect of the parameters on the performance.

AN EFFICIENT MACHINE LEARNING MODEL FOR PREDICTION OF ACUTE MYOCARDIAL INFARCTION

2020 ◽  
Vol 13 ◽  
Author(s):  
Dhilsath Fathima.M ◽  
S. Justin Samuel ◽  
R. Hari Haran
Keyword(s):  
Machine Learning ◽  
Myocardial Infarction ◽  
Acute Myocardial Infarction ◽  
Logistic Regression ◽  
Decision Tree ◽  
Learning Model ◽  
Training Dataset ◽  
Data Set ◽  
Machine Learning Model ◽  
Proposed Model

Aim: This proposed work is used to develop an improved and robust machine learning model for predicting Myocardial Infarction (MI) could have substantial clinical impact. Objectives: This paper explains how to build machine learning based computer-aided analysis system for an early and accurate prediction of Myocardial Infarction (MI) which utilizes framingham heart study dataset for validation and evaluation. This proposed computer-aided analysis model will support medical professionals to predict myocardial infarction proficiently. Methods: The proposed model utilize the mean imputation to remove the missing values from the data set, then applied principal component analysis to extract the optimal features from the data set to enhance the performance of the classifiers. After PCA, the reduced features are partitioned into training dataset and testing dataset where 70% of the training dataset are given as an input to the four well-liked classifiers as support vector machine, k-nearest neighbor, logistic regression and decision tree to train the classifiers and 30% of test dataset is used to evaluate an output of machine learning model using performance metrics as confusion matrix, classifier accuracy, precision, sensitivity, F1-score, AUC-ROC curve. Results: Output of the classifiers are evaluated using performance measures and we observed that logistic regression provides high accuracy than K-NN, SVM, decision tree classifiers and PCA performs sound as a good feature extraction method to enhance the performance of proposed model. From these analyses, we conclude that logistic regression having good mean accuracy level and standard deviation accuracy compared with the other three algorithms. AUC-ROC curve of the proposed classifiers is analyzed from the output figure.4, figure.5 that logistic regression exhibits good AUC-ROC score, i.e. around 70% compared to k-NN and decision tree algorithm. Conclusion: From the result analysis, we infer that this proposed machine learning model will act as an optimal decision making system to predict the acute myocardial infarction at an early stage than an existing machine learning based prediction models and it is capable to predict the presence of an acute myocardial Infarction with human using the heart disease risk factors, in order to decide when to start lifestyle modification and medical treatment to prevent the heart disease.

scholarly journals Hugoniot Data and Equation of State Parameters for an Ultra-High Performance Concrete

2021 ◽  
Author(s):  
C. Sauer ◽  
F. Bagusat ◽  
M.-L. Ruiz-Ripoll ◽  
C. Roller ◽  
M. Sauer ◽  
...  
Keyword(s):  
Equation Of State ◽  
High Performance ◽  
High Performance Concrete ◽  
Applied Pressure ◽  
High Strength ◽  
Parameter Study ◽  
Ultra High Performance Concrete ◽  
Data Set ◽  
Shock Response ◽  
Particle Velocities

AbstractThis work aims at the characterization of a modern concrete material. For this purpose, we perform two experimental series of inverse planar plate impact (PPI) tests with the ultra-high performance concrete B4Q, using two different witness plate materials. Hugoniot data in the range of particle velocities from 180 to 840 m/s and stresses from 1.1 to 7.5 GPa is derived from both series. Within the experimental accuracy, they can be seen as one consistent data set. Moreover, we conduct corresponding numerical simulations and find a reasonably good agreement between simulated and experimentally obtained curves. From the simulated curves, we derive numerical Hugoniot results that serve as a homogenized, mean shock response of B4Q and add further consistency to the data set. Additionally, the comparison of simulated and experimentally determined results allows us to identify experimental outliers. Furthermore, we perform a parameter study which shows that a significant influence of the applied pressure dependent strength model on the derived equation of state (EOS) parameters is unlikely. In order to compare the current results to our own partially reevaluated previous work and selected recent results from literature, we use simulations to numerically extrapolate the Hugoniot results. Considering their inhomogeneous nature, a consistent picture emerges for the shock response of the discussed concrete and high-strength mortar materials. Hugoniot results from this and earlier work are presented for further comparisons. In addition, a full parameter set for B4Q, including validated EOS parameters, is provided for the application in simulations of impact and blast scenarios.

An approach for document retrieval using cluster-based inverted indexing

2021 ◽  
pp. 016555152110184
Author(s):  
Gunjan Chandwani ◽  
Anil Ahlawat ◽  
Gaurav Dubey
Keyword(s):  
High Performance ◽  
Clustering Algorithm ◽  
Pearson Correlation ◽  
Relevant Information ◽  
Document Retrieval ◽  
Bhattacharyya Distance ◽  
Data Set ◽  
Query Matching ◽  
Inverted Indexing ◽  
Query Optimisation

Document retrieval plays an important role in knowledge management as it facilitates us to discover the relevant information from the existing data. This article proposes a cluster-based inverted indexing algorithm for document retrieval. First, the pre-processing is done to remove the unnecessary and redundant words from the documents. Then, the indexing of documents is done by the cluster-based inverted indexing algorithm, which is developed by integrating the piecewise fuzzy C-means (piFCM) clustering algorithm and inverted indexing. After providing the index to the documents, the query matching is performed for the user queries using the Bhattacharyya distance. Finally, the query optimisation is done by the Pearson correlation coefficient, and the relevant documents are retrieved. The performance of the proposed algorithm is analysed by the WebKB data set and Twenty Newsgroups data set. The analysis exposes that the proposed algorithm offers high performance with a precision of 1, recall of 0.70 and F-measure of 0.8235. The proposed document retrieval system retrieves the most relevant documents and speeds up the storing and retrieval of information.

Sign in / Sign up

Export Citation Format

Share Document