scholarly journals Event Prediction in Complex Social Graphs using One-Dimensional Convolutional Neural Network

Author(s):  
Bonaventure Molokwu

Social network graphs possess apparent and latent knowledge about their respective actors and links which may be exploited, using effective and efficient techniques, for predicting events within the social graphs. Understanding the intrinsic relationship patterns among spatial social actors and their respective properties are crucial factors to be taken into consideration in event prediction within social networks. My research work proposes a unique approach for predicting events in social networks by learning the context of each actor/vertex using neighboring actors in a given social graph with the goal of generating vector-space embeddings for each vertex. Our methodology introduces a pre-convolution layer which is essentially a set of feature-extraction operations aimed at reducing the graph's dimensionality to aid knowledge extraction from its complex structure. Consequently, the low-dimensional node embeddings are introduced as input features to a one-dimensional ConvNet model for event prediction about the given social graph. Training and evaluation of this proposed approach have been done on datasets (compiled: November, 2017) extracted from real world social networks with respect to 3 European countries. Each dataset comprises an average of 280,000 links and 48,000 actors.

Materials ◽  
2021 ◽  
Vol 14 (18) ◽  
pp. 5139
Author(s):  
Weronika Smok ◽  
Tomasz Tański

The growing scientific interest in one-dimensional (1D) nanostructures based on metal-oxide semiconductors (MOS) resulted in the analysis of their structure, properties and fabrication methods being the subject of many research projects and publications all over the world, including in Poland. The application of the method of electrospinning with subsequent calcination for the production of these materials is currently very popular, which results from its simplicity and the possibility to control the properties of the obtained materials. The growing trend of industrial application of electrospun 1D MOS and the progress in modern technologies of nanomaterials properties investigations indicate the necessity to maintain the high level of research and development activities related to the structure and properties analysis of low-dimensional nanomaterials. Therefore, this review perfectly fits both the global trends and is a summary of many years of research work in the field of electrospinning carried out in many research units, especially in the Department of Engineering Materials and Biomaterials of the Faculty of Mechanical Engineering and Technology of Silesian University of Technology, as well as an announcement of further activities in this field.


Info ◽  
2015 ◽  
Vol 17 (6) ◽  
pp. 50-71 ◽  
Author(s):  
Natali Helberger ◽  
Katharina Kleinen-von Königslöw ◽  
Rob van der Noll

Purpose – The purposes of this paper are to deal with the questions: because search engines, social networks and app-stores are often referred to as gatekeepers to diverse information access, what is the evidence to substantiate these gatekeeper concerns, and to what extent are existing regulatory solutions to control gatekeeper control suitable at all to address new diversity concerns? It will also map the different gatekeeper concerns about media diversity as evidenced in existing research before the background of network gatekeeping theory critically analyses some of the currently discussed regulatory approaches and develops the contours of a more user-centric approach towards approaching gatekeeper control and media diversity. Design/methodology/approach – This is a conceptual research work based on desk research into the relevant and communications science, economic and legal academic literature and the relevant laws and public policy documents. Based on the existing evidence as well as on applying the insights from network gatekeeping theory, this paper then critically reviews the existing legal/policy discourse and identifies elements for an alternative approach. Findings – This paper finds that when looking at search engines, social networks and app stores, many concerns about the influence of the new information intermediaries on media diversity have not so much their source in the control over critical resources or access to information, as the traditional gatekeepers do. Instead, the real bottleneck is access to the user, and the way the relationship between social network, search engine or app platforms and users is given form. Based on this observation, the paper concludes that regulatory initiatives in this area would need to pay more attention to the dynamic relationship between gatekeeper and gated. Research limitations/implications – Because this is a conceptual piece based on desk-research, meaning that our assumptions and conclusions have not been validated by own empirical research. Also, although the authors have conducted to their best knowledge the literature review as broad and as concise as possible, seeing the breadth of the issue and the diversity of research outlets, it cannot be excluded that we have overlooked one or the other publication. Practical implications – This paper makes a number of very concrete suggestions of how to approach potential challenges from the new information intermediaries to media diversity. Social implications – The societal implications of search engines, social networks and app stores for media diversity cannot be overestimated. And yet, it is the position of users, and their exposure to diverse information that is often neglected in the current dialogue. By drawing attention to the dynamic relationship between gatekeeper and gated, this paper highlights the importance of this relationship for diverse exposure to information. Originality/value – While there is currently much discussion about the possible challenges from search engines, social networks and app-stores for media diversity, a comprehensive overview in the scholarly literature on the evidence that actually exists is still lacking. And while most of the regulatory solutions still depart from a more pre-networked, static understanding of “gatekeeper”, we develop our analysis on the basis for a more dynamic approach that takes into account the fluid and interactive relationship between the roles of “gatekeepers” and “gated”. Seen from this perspective, the regulatory solutions discussed so far appear in a very different light.


2021 ◽  
Vol 50 (1) ◽  
pp. 138-152
Author(s):  
Mujeeb Ur Rehman ◽  
Dost Muhammad Khan

Recently, anomaly detection has acquired a realistic response from data mining scientists as a graph of its reputation has increased smoothly in various practical domains like product marketing, fraud detection, medical diagnosis, fault detection and so many other fields. High dimensional data subjected to outlier detection poses exceptional challenges for data mining experts and it is because of natural problems of the curse of dimensionality and resemblance of distant and adjoining points. Traditional algorithms and techniques were experimented on full feature space regarding outlier detection. Customary methodologies concentrate largely on low dimensional data and hence show ineffectiveness while discovering anomalies in a data set comprised of a high number of dimensions. It becomes a very difficult and tiresome job to dig out anomalies present in high dimensional data set when all subsets of projections need to be explored. All data points in high dimensional data behave like similar observations because of its intrinsic feature i.e., the distance between observations approaches to zero as the number of dimensions extends towards infinity. This research work proposes a novel technique that explores deviation among all data points and embeds its findings inside well established density-based techniques. This is a state of art technique as it gives a new breadth of research towards resolving inherent problems of high dimensional data where outliers reside within clusters having different densities. A high dimensional dataset from UCI Machine Learning Repository is chosen to test the proposed technique and then its results are compared with that of density-based techniques to evaluate its efficiency.


2021 ◽  
Author(s):  
Shunning Li ◽  
Zhefeng Chen ◽  
Zhi Wang ◽  
Mouyi Weng ◽  
Jianyuan Li ◽  
...  

Abstract The past decades have witnessed an exponential growth in the discovery of functional materials, benefited from our unprecedented capabilities in characterizing their structure, chemistry, and morphology with the aid of advanced imaging, spectroscopic and computational techniques. Among these materials, atomic-scale low-dimensional compounds, as represented by the two-dimensional (2D) atomic layers, one-dimensional (1D) atomic chains and zero-dimensional (0D) atomic clusters, have long captivated scientific interest due to their unique topological motifs and exceptional properties. Their tremendous potentials in various applications make it a pressing urgency to establish a complete database of their structural information, especially for the underexplored 1D species. Here we apply graph theory in combination with first-principles high-throughput calculations to identify atomic-scale 1D materials that can be conceptually isolated from their parent bulk crystals. In total, two hundred and fifty 1D atomic chains are shown to be potentially exfoliable. We demonstrate how the lone electron pairs on cations interact with the p-orbitals of anions and hence stabilize their edge sites. Data analysis of the 2D and 1D materials also reveals the dependence of electronic band gap on the cationic percolation network determined by graph theory. The library of 1D compounds systematically identified in this work will pave the way for the predictive discovery of material systems for quantum engineering, and can serve as a source of stimuli for future data-driven design and understanding of functional materials with reduced dimensionality.


Author(s):  
Sovan Samanta ◽  
Madhumangal Pal

Social network is a topic of current research. Relations are broken and new relations are increased. This chapter will discuss the scope or predictions of new links in social networks. Here different approaches for link predictions are described. Among them friend recommendation model is latest. There are some other methods like common neighborhood method which is also analyzed here. The comparison among them to predict links in social networks is described. The significance of this research work is to find strong dense networks in future.


Author(s):  
Raúl Terol Bolinches ◽  
Nadia Alonso-López

Let the world listen to your best. The chapter discusses how the podcast can help to make academic research work more visible. Nowadays, professors can carry out a research and disseminate it among the academic community through creation of a podcast dedicated to the content of the research activity and they can share it through social networks. Creating a podcast is quite easy by following some small recommendations and using few technical resources, just an App for your smartphone and a USB microphone to get started. The chapter includes some examples how researchers can do their own podcast or can contribute to specific podcast about academic research. The chapter includes some examples of podcasts on academic dissemination and how they use social networks to share this content. Reports, interviews, and other radio genres help to spread the research that has been carried out. In this chapter, the author offers an overview of podcasts which can help you approach your audience and become more visible on the internet using the appropriate strategies.


Author(s):  
Maryam Qamar ◽  
Mehwish Malik ◽  
Saadia Batool ◽  
Sidra Mehmood ◽  
Asad W. Malik ◽  
...  

This work covers the research work on decentralization of Online Social Networks (OSNs), issues with centralized design are studied with possible decentralized solutions. Centralized architecture is prone to privacy breach, p2p architecture for data and thus authority decentralization with encryption seems a possible solution. OSNs' users grow exponentially causing scalability issue, a natural solution is decentralization where users bring resources with them via personal machines or paid services. Also centralized services are not available unremittingly, to this end decentralization proposes replication. Decentralized solutions are also proposed for reliability issues arising in centralized systems and the potential threat of a central authority. Yet key to all problems isn't found, metadata may be enough for inferences about data and network traffic flow can lead to information on users' relationships. First issue can be mitigated by data padding or splitting in uniform blocks. Caching, dummy traffic or routing through a mix of nodes can be some possible solutions to the second.


Author(s):  
Mark Alan Underwood

Intranets are almost as old as the concept of a web site. More than twenty-five years ago the text Business Data Communications closed with a discussion of intranets (Stallings, 1990). Underlying technology improvements in intranets have been incremental; intranets were never seen as killer developments. Yet the popularity of Online Social Networks (OSNs) has led to increased interest in the part OSNs play – or could play – in using intranets to foster knowledge management. This chapter reviews research into how social graphs for an enterprise, team or other collaboration group interacts with the ways intranets have been used to display, collect, curate and disseminate information over the knowledge life cycle. Future roles that OSN-aware intranets could play in emerging technologies, such as process mining, elicitation methods, domain-specific intelligent agents, big data, and just-in-time learning are examined.


2019 ◽  
Vol 33 (02) ◽  
pp. 1950012 ◽  
Author(s):  
Yu-Qing Wang ◽  
Zi-Huan Zhang

In the area of statistical physics, totally asymmetric simple exclusion process (TASEP) is treated as one of the most important driven-diffusive systems. It contains profound non-equilibrium statistical physics mechanisms due to being the paradigm model like Ising model. Different with previous work, a one-dimensional TASEP coupled with inner interactions and Langmuir dynamics is taken into account. Weak coupled binding and unbinding rates are introduced in the proposed model. Bond breaking and making mechanisms of self-driven particles illustrating the unidirectional movement of protein motors are investigated by means of performing cluster mean-field analyses. Dynamics in the proposed system dominated by the competition between the attraction effect and the repulsion one are found to depend on the specific value of the interaction energy of these active particles. The research work will be helpful for understanding non-equilibrium statistical behaviors of interacting particle systems.


Sign in / Sign up

Export Citation Format

Share Document