Social Network Analysis With Data Fusion

Farasat, Alireza; Gross, Geoffrey; Nagi, Rakesh; Nikolaev, Alexander G.

doi:10.1109/tcss.2016.2613563

Cited by 30 publications

(8 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Design. As two very similar research fields, expression recognition and face recognition have many commonalities, making many theories and techniques about the face recognition field be directly applied to the field of facial expression analysis [21]. e difference between the two is that face recognition mainly identifies who the person is and recognizes a larger number of categories, while expression recognition recognizes human emotions and recognizes fewer categories, and the current expression analysis categories are mainly six types of expressions, so the classifier selection of the two has a large difference and the feature extraction is also different.…”

Section: Face Recognition and Emotion Recognition Algorithmmentioning

confidence: 99%

Emotion Monitoring for Preschool Children Based on Face Recognition and Emotion Recognition Algorithms

2021

Complexity

View full text Add to dashboard Cite

In this paper, we study the face recognition and emotion recognition algorithms to monitor the emotions of preschool children. For previous emotion recognition focusing on faces, we propose to obtain more comprehensive information from faces, gestures, and contexts. Using the deep learning approach, we design a more lightweight network structure to reduce the number of parameters and save computational resources. There are not only innovations in applications, but also algorithmic enhancements. And face annotation is performed on the dataset, while a hierarchical sampling method is designed to alleviate the data imbalance phenomenon that exists in the dataset. A new feature descriptor, called “oriented gradient histogram from three orthogonal planes,” is proposed to characterize facial appearance variations. A new efficient geometric feature is also proposed to capture facial contour variations, and the role of audio methods in emotion recognition is explored. Multifeature fusion can be used to optimally combine different features. The experimental results show that the method is very effective compared to other recent methods in dealing with facial expression recognition problems about videos in both laboratory-controlled environments and outdoor environments. The method performed experiments on expression detection in a facial expression database. The experimental results are compared with data from previous studies and demonstrate the effectiveness of the proposed new method.

show abstract

Section: Face Recognition and Emotion Recognition Algorithmmentioning

confidence: 99%

Emotion Monitoring for Preschool Children Based on Face Recognition and Emotion Recognition Algorithms

2021

Complexity

View full text Add to dashboard Cite

show abstract

“…In [6] author offered a parallel computing based method to extract a social network individuals from fused data, by using cumulative association Data Graph. They implemented a supervised learning framework to parameterize the extraction algorithms.…”

Section: Related Workmentioning

confidence: 99%

Developing a Framework for Analyzing Heterogeneous Data from Social Networks

Paul¹,

Shamsul²,

Karim³

2019

ijacsa

View full text Add to dashboard Cite

Due to the rapid growth of internet technologies, at present online social networks have become a part of people's everyday life. People shares their thoughts, feelings, likings, disliking and many other issues at social networks by posting messages, videos, images and commenting on these. It is a great source of heterogeneous data. Heterogeneous data is a kind of unstructured data which comes in a variety of forms with an uncertain speed. In this paper, we develop a framework to collect and analyze a significant amount of heterogeneous data obtained from the social network to understand the behavioural patterns of the people at the social networks. In our framework, at first we crawl data from a well-known social network through Graph API that contains post, comments, images and videos. We compute keywords from the users' comments and posts and separate keywords as noun, verb, and adjective with the help of an XML based parts of speech tagger. We analyze images related to each user to find out how a user like to move. For this purpose, we count the number of users in an image using frontal face detection classifier. We also analyze video files of the users to find the categories of videos. For this purpose, we divide each video into frames and measure the RGB properties, speed, duration, frame's height and width. Finally, for each user we combine information from text, images and videos and based on the combined information we develop the profile of the user. Then, we generate recommendations for each user based on activities of the user and cosine similarity between users. We perform several experiments to show the effectiveness of our developed system. From the experimental evaluation, we can say that our framework can generate results up to a satisfactory level.

show abstract

“…is series of intelligent video surveillance content can be divided into three major modules and motion target detection and identification, target tracking technology is the basic module of intelligent video surveillance, and the technology in the basic module is mostly derived from image processing [5]. e research in this direction improves the performance of moving target detection and tracking algorithms in video sequences in various aspects, such as robustness and real-time performance [6].…”

Section: Introductionmentioning

confidence: 99%

Machine Learning‐Based Multitarget Tracking of Motion in Sports Video

Zhang¹,

Yang

2021

Complexity

View full text Add to dashboard Cite

In this paper, we track the motion of multiple targets in sports videos by a machine learning algorithm and study its tracking technique in depth. In terms of moving target detection, the traditional detection algorithms are analysed theoretically as well as implemented algorithmically, based on which a fusion algorithm of four interframe difference method and background averaging method is proposed for the shortcomings of interframe difference method and background difference method. The fusion algorithm uses the learning rate to update the background in real time and combines morphological processing to correct the foreground, which can effectively cope with the slow change of the background. According to the requirements of real time, accuracy, and occupying less video memory space in intelligent video surveillance systems, this paper improves the streamlined version of the algorithm. The experimental results show that the improved multitarget tracking algorithm effectively improves the Kalman filter-based algorithm to meet the real-time and accuracy requirements in intelligent video surveillance scenarios.

show abstract

Social Network Analysis With Data Fusion

Cited by 30 publications

References 27 publications

Emotion Monitoring for Preschool Children Based on Face Recognition and Emotion Recognition Algorithms

Emotion Monitoring for Preschool Children Based on Face Recognition and Emotion Recognition Algorithms

Developing a Framework for Analyzing Heterogeneous Data from Social Networks

Machine Learning‐Based Multitarget Tracking of Motion in Sports Video

Contact Info

Product

Resources

About