scholarly journals DeepLink: A novel link prediction framework based on deep learning

2019 ◽  
pp. 016555151989134 ◽  
Author(s):  
Mohammad Mehdi Keikha ◽  
Maseud Rahgozar ◽  
Masoud Asadpour
Keyword(s):  
Deep Learning ◽  
Structural Feature ◽  
Network Topology ◽  
Link Prediction ◽  
Feature Learning ◽  
Structural Features ◽  
Feature Engineering ◽  
Hybrid Approaches ◽  
Learning Techniques ◽  
Content Information

Recently, link prediction has attracted more attention from various disciplines such as computer science, bioinformatics and economics. In link prediction, numerous information such as network topology, profile information and user-generated contents are considered to discover missing links between nodes. Whereas numerous previous researches had focused on the structural features of the networks for link prediction, recent studies have shown more interest in profile and content information, too. So, some of these researches combine structural and content information. However, some issues such as scalability and feature engineering need to be investigated to solve a few remaining problems. Moreover, most of the previous researches are presented only for undirected and unweighted networks. In this article, a novel link prediction framework named ‘DeepLink’ is presented, which is based on deep learning techniques. While deep learning has the advantage of extracting automatically the best features for link prediction, many other link prediction algorithms need manual feature engineering. Moreover, in the proposed framework, both structural and content information are employed. The framework is capable of using different structural feature vectors that are prepared by various link prediction methods. It learns all proximity orders that are presented on a network during the structural feature learning. We have evaluated the effectiveness of DeepLink on two real social network datasets, Telegram and irBlogs. On both datasets, the proposed framework outperforms several other structural and hybrid approaches for link prediction.

scholarly journals Link Prediction in Facebook using Web Scrapping and Deep Learning Techniques

2021 ◽  
Vol 10 (1) ◽  
pp. 194-197
Keyword(s):  
Social Networks ◽  
Deep Learning ◽  
Link Prediction ◽  
Machine Learning Techniques ◽  
Feature Engineering ◽  
Internet Technologies ◽  
Learning Techniques ◽  
The Social ◽  
Feature Based ◽  
Day By Day

As Internet technologies develop continuously social networks are getting more popular day by day. People are connected with each other via virtual applications. Using the Link Prediction in social networks more people get connected, may be they are friends, may be work together at the same workplace and may be their education are. Machine learning techniques are used to analyze the link between the nodes of the network and also create a better link prediction model through deep learning. The objective of this research is to measure the performance using the different techniques to predict link between the social networks. Using deep learning, feature engineering can be reduced for link prediction. In this research, the feature based learning is used to predict the link for better performance. Dataset is obtained by scraping the profile of Facebook users and they are used along with the random forest and graph convolution neural network to measure the performance of link prediction in social networks.

scholarly journals DeepOSN: Bringing deep learning as malicious detection scheme in online social network

2020 ◽  
Vol 9 (1) ◽  
pp. 146
Author(s):  
Putra Wanda ◽  
Marselina Endah Hiswati ◽  
Huang J. Jie
Keyword(s):  
Social Networks ◽  
Computer Vision ◽  
Deep Learning ◽  
Online Social Networks ◽  
Link Prediction ◽  
Online Social Network ◽  
Detection Scheme ◽  
Malicious Activity ◽  
Manual Analysis ◽  
Learning Techniques

Manual analysis for malicious prediction in Online Social Networks (OSN) is time-consuming and costly. With growing users within the environment, it becomes one of the main obstacles. Deep learning is growing algorithm that gains a big success in computer vision problem. Currently, many research communities have proposed deep learning techniques to automate security tasks, including anomalous detection, malicious link prediction, and intrusion detection in OSN. Notably, this article describes how deep learning makes the OSN security technique more intelligent for detecting malicious activity by establishing a classifier model.

Deep Learning Roles based Approach to Link Prediction in Networks

2020 ◽  
Author(s):  
Aman Gupta ◽  
Yadul Raghav
Keyword(s):  
Deep Learning ◽  
Link Prediction ◽  
Information Science ◽  
Structural Information ◽  
Structural Features ◽  
Similarity Score ◽  
Node Attribute ◽  
Depth Analysis ◽  
Real World Datasets ◽  
Better Than

The problem of predicting links has gained much attention in recent years due to its vast application in various domains such as sociology, network analysis, information science, etc. Many methods have been proposed for link prediction such as RA, AA, CCLP, etc. These methods required hand-crafted structural features to calculate the similarity scores between a pair of nodes in a network. Some methods use local structural information while others use global information of a graph. These methods do not tell which properties are better than others. With an in-depth analysis of these methods, we understand that one way to overcome this problem is to consider network structure and node attribute information to capture the discriminative features for link prediction tasks. We proposed a deep learning Autoencoder based Link Prediction (ALP) architecture for the latent representation of a graph, unified with non-negative matrix factorization to automatically determine the underlying roles in a network, after that assigning a mixed-membership of these roles to each node in the network. The idea is to transfer these roles as a feature vector for the link prediction task in the network. Further, cosine similarity is applied after getting the required features to compute the pairwise similarity score between the nodes. We present the performance of the algorithm on the real-world datasets, where it gives the competitive result compared to other algorithms.

scholarly journals Comparison of Feature Extraction Methods for Physiological Signals for Heat-Based Pain Recognition

Sensors ◽  
2021 ◽  
Vol 21 (14) ◽  
pp. 4838
Author(s):  
Philip Gouverneur ◽  
Frédéric Li ◽  
Wacław M. Adamczyk ◽  
Tibor M. Szikszay ◽  
Kerstin Luedtke ◽  
...  
Keyword(s):  
Machine Learning ◽  
Feature Extraction ◽  
Deep Learning ◽  
Feature Learning ◽  
Recognition System ◽  
Extraction Methods ◽  
Feature Engineering ◽  
Learning Approaches ◽  
Physiological Sensors ◽  
Pain Recognition

While even the most common definition of pain is under debate, pain assessment has remained the same for decades. But the paramount importance of precise pain management for successful healthcare has encouraged initiatives to improve the way pain is assessed. Recent approaches have proposed automatic pain evaluation systems using machine learning models trained with data coming from behavioural or physiological sensors. Although yielding promising results, machine learning studies for sensor-based pain recognition remain scattered and not necessarily easy to compare to each other. In particular, the important process of extracting features is usually optimised towards specific datasets. We thus introduce a comparison of feature extraction methods for pain recognition based on physiological sensors in this paper. In addition, the PainMonit Database (PMDB), a new dataset including both objective and subjective annotations for heat-induced pain in 52 subjects, is introduced. In total, five different approaches including techniques based on feature engineering and feature learning with deep learning are evaluated on the BioVid and PMDB datasets. Our studies highlight the following insights: (1) Simple feature engineering approaches can still compete with deep learning approaches in terms of performance. (2) More complex deep learning architectures do not yield better performance compared to simpler ones. (3) Subjective self-reports by subjects can be used instead of objective temperature-based annotations to build a robust pain recognition system.

scholarly journals A Survey on Software Defect Prediction Using Deep Learning

Mathematics ◽  
2021 ◽  
Vol 9 (11) ◽  
pp. 1180
Author(s):  
Elena N. Akimova ◽  
Alexander Yu. Bersenev ◽  
Artem A. Deikov ◽  
Konstantin S. Kobylkin ◽  
Anton V. Konygin ◽  
...  
Keyword(s):  
Deep Learning ◽  
Structural Features ◽  
Learning Technologies ◽  
Fault Prediction ◽  
Defect Prediction ◽  
Open Problems ◽  
Software Defect ◽  
Learning Techniques ◽  
Language Research ◽  
Recent Trends

Defect prediction is one of the key challenges in software development and programming language research for improving software quality and reliability. The problem in this area is to properly identify the defective source code with high accuracy. Developing a fault prediction model is a challenging problem, and many approaches have been proposed throughout history. The recent breakthrough in machine learning technologies, especially the development of deep learning techniques, has led to many problems being solved by these methods. Our survey focuses on the deep learning techniques for defect prediction. We analyse the recent works on the topic, study the methods for automatic learning of the semantic and structural features from the code, discuss the open problems and present the recent trends in the field.

scholarly journals Deep Cross-Corpus Speech Emotion Recognition: Recent Advances and Perspectives

2021 ◽  
Vol 15 ◽  
Author(s):  
Shiqing Zhang ◽  
Ruixin Liu ◽  
Xin Tao ◽  
Xiaoming Zhao
Keyword(s):  
Deep Learning ◽  
Emotion Recognition ◽  
Feature Learning ◽  
Learning Ability ◽  
Speech Emotion Recognition ◽  
Practical Applications ◽  
Learning Techniques ◽  
Challenges And Opportunities ◽  
Comprehensive Survey ◽  
Cross Language

Automatic speech emotion recognition (SER) is a challenging component of human-computer interaction (HCI). Existing literatures mainly focus on evaluating the SER performance by means of training and testing on a single corpus with a single language setting. However, in many practical applications, there are great differences between the training corpus and testing corpus. Due to the diversity of different speech emotional corpus or languages, most previous SER methods do not perform well when applied in real-world cross-corpus or cross-language scenarios. Inspired by the powerful feature learning ability of recently-emerged deep learning techniques, various advanced deep learning models have increasingly been adopted for cross-corpus SER. This paper aims to provide an up-to-date and comprehensive survey of cross-corpus SER, especially for various deep learning techniques associated with supervised, unsupervised and semi-supervised learning in this area. In addition, this paper also highlights different challenges and opportunities on cross-corpus SER tasks, and points out its future trends.

Smart Healthcare for ECG Telemonitoring System

2021 ◽  
Vol 2 (2) ◽  
Author(s):  
Jwan Najeeb Saeed ◽  
◽  
Siddeeq Y. Ameen ◽  
Keyword(s):  
Health Care ◽  
Deep Learning ◽  
Activity Recognition ◽  
Human Activity ◽  
Health Monitoring ◽  
Feature Learning ◽  
Human Activity Recognition ◽  
Smart Healthcare ◽  
Learning Techniques ◽  
Smart Health

Cardiovascular disorders are one of the major causes of sad death among older and middle-aged people. Over the past two decades, health monitoring services have evolved quickly and had the ability to change the way health care is currently provided. However, the most challenging aspect of the mobile and wearable sensor-based human activity recognition pipeline is the extraction of the related features. Feature extraction decreases both computational complexity and time. Deep learning techniques are used for automatic feature learning in a variety of fields, including health, image classification, and, most recently, for the extraction and classification of complex and straightforward human activity recognition in smart health care. This paper reviews the recent state of the art in electrocardiogram (ECG) smart health monitoring systems based on the Internet of things with the machine and deep learning techniques. Moreover, the paper provided possible research and challenges that can help researchers advance state of art in future work.

Deep Learning for Feature Engineering-Based Improved Weather Prediction

2021 ◽  
pp. 195-217
Author(s):  
Partha Sarathi Mishra ◽  
Debabrata Nandi
Keyword(s):  
Deep Learning ◽  
Time Series Data ◽  
Weather Prediction ◽  
Model Development ◽  
Model Complexity ◽  
Daily Maximum ◽  
Feature Engineering ◽  
Learning Models ◽  
Computationally Efficient ◽  
Learning Techniques

Weather prediction has gained a point of attraction for many researchers of variant research communities. The emerging deep learning techniques have motivated many researches to explore hidden hierarchical pattern in the great mass of weather dataset for weather prediction. In this chapter, four different categories of computationally efficient deep learning models—CNN, LSTM, CNN-LSTM, and ConvLSTM—have been critically examined for improved weather prediction. Here, emphasis has been given on supervised learning techniques for model development by considering the importance of feature engineering. Feature engineering plays a vital role in reducing dimension, decreasing model complexity as well as handling the noise and corrupted data. Using daily maximum temperature, this chapter investigates the performance of different deep learning models for improved predictions. The results obtained from different experiments conducted ensures that the feature engineering based deep learning study for the purpose of predictive modeling using time series data is really an encouraging approach.

scholarly journals An experimental study on feature engineering and learning approaches for aggression detection in social media

2019 ◽  
Vol 22 (63) ◽  
pp. 81-100 ◽  
Author(s):  
Antonela Tommasel ◽  
Juan Manuel Rodriguez ◽  
Daniela Godoy
Keyword(s):  
Social Media ◽  
Deep Learning ◽  
Social Relations ◽  
Large Scale ◽  
Well Being ◽  
Feature Engineering ◽  
Learning Approaches ◽  
Social Media Networks ◽  
Online Social Media ◽  
Learning Techniques

With the widespread of modern technologies and social media networks, a new form of bullying occurring anytime and anywhere has emerged. This new phenomenon, known as cyberaggression or cyberbullying, refers to aggressive and intentional acts aiming at repeatedly causing harm to other person involving rude, insulting, offensive, teasing or demoralising comments through online social media. As these aggressions represent a threatening experience to Internet users, especially kids and teens who are still shaping their identities, social relations and well-being, it is crucial to understand how cyberbullying occurs to prevent it from escalating. Considering the massive information on the Web, the developing of intelligent techniques for automatically detecting harmful content is gaining importance, allowing the monitoring of large-scale social media and the early detection of unwanted and aggressive situations. Even though several approaches have been developed over the last few years based both on traditional and deep learning techniques, several concerns arise over the duplication of research and the difficulty of comparing results. Moreover, there is no agreement regarding neither which type of technique is better suited for the task, nor the type of features in which learning should be based. The goal of this work is to shed some light on the effects of learning paradigms and feature engineering approaches for detecting aggressions in social media texts. In this context, this work provides an evaluation of diverse traditional and deep learning techniques based on diverse sets of features, across multiple social media sites. 

scholarly journals p1-FP: Extraction, Classification, and Prediction of Website Fingerprints with Deep Learning

2019 ◽  
Vol 2019 (3) ◽  
pp. 191-209 ◽  
Author(s):  
Se Eun Oh ◽  
Saikrishna Sunkam ◽  
Nicholas Hopper
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Deep Neural Network ◽  
State Of The Art ◽  
Machine Learning Techniques ◽  
Feature Engineering ◽  
Engineering Process ◽  
Learning Techniques ◽  
Wide Range

Abstract Recent advances in Deep Neural Network (DNN) architectures have received a great deal of attention due to their ability to outperform state-of-the-art machine learning techniques across a wide range of application, as well as automating the feature engineering process. In this paper, we broadly study the applicability of deep learning to website fingerprinting. First, we show that unsupervised DNNs can generate lowdimensional informative features that improve the performance of state-of-the-art website fingerprinting attacks. Second, when used as classifiers, we show that they can exceed performance of existing attacks across a range of application scenarios, including fingerprinting Tor website traces, fingerprinting search engine queries over Tor, defeating fingerprinting defenses, and fingerprinting TLS-encrypted websites. Finally, we investigate which site-level features of a website influence its fingerprintability by DNNs.

Sign in / Sign up

Export Citation Format

Share Document