Toward Evolving Knowledge Ecosystems for Big Data Understanding

Ermolayev, Vadim; Terziyan, Vagan; Cochez, Michael

doi:10.1201/b16014-3

Cited by 10 publications

(16 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, knowledge evolves to support the intellectual activity of its owners, e.g., to interpret the information generated in event observations -handling the diversity and complexity of such information. Consequently, Ermolayev et al [1] hypothesize that the mechanisms of knowledge evolution are very similar to (and could be spotted from) the mechanisms of the evolution of humans. Apart from the societal aspects, these are appropriately described using the metaphor of biological evolution.…”

Section: Big Knowledge -Evolving Knowledge Ecosystemsmentioning

confidence: 99%

“…In this paper we use a highly scalable method to collect the increments of incoming knowledge using a 3F+3Co approach, which stand for Focusing, Filtering, and Forgetting + Contextualizing, Compressing, and Connecting (c.f. [1] and section 3.2).…”

Section: Efficiency Versus Effectivenessmentioning

confidence: 99%

“…Similarly, a knowledge ecosystem has to be introduced for enabling and managing the evolution of knowledge. As proposed in [1], such EKE should scale adequately to cope with realistic and increasing characteristics of data/information to be processed and balance the efficiency and effectiveness while extracting knowledge from information and triggering the changes in the available knowledge.…”

Section: Big Knowledge -Evolving Knowledge Ecosystemsmentioning

confidence: 99%

“…matching their genome noticeably. The nutrition is provided by Knowledge Extraction and Contextualization functionality of the ecosystem [1] in a form of knowledge tokens. Hence, several and possibly overlapping environmental contexts need to be regarded in a hierarchy which corresponds to several subject domains of interest and a foundational knowledge layer.…”

Section: Evolving Knowledge Ecosystemsmentioning

confidence: 99%

“…This problem becomes even more challenging given the explosion in the volumes, complexity, variety of the information available about the world, and the velocity of its change. Recently a conceptual approach to attack this challenging problem has been proposed [1]. The core of that proposal is the understanding that the mechanisms of knowledge evolution could be spotted from evolutionary biology.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Balanced Large Scale Knowledge Matching Using LSH Forest

Cochez

Terziyan

Ermolayev³

2015

Semantic Keyword-Based Search on Structured Data Sources

Self Cite

View full text Add to dashboard Cite

Section: Big Knowledge -Evolving Knowledge Ecosystemsmentioning

confidence: 99%

Section: Efficiency Versus Effectivenessmentioning

confidence: 99%

Section: Big Knowledge -Evolving Knowledge Ecosystemsmentioning

confidence: 99%

Section: Evolving Knowledge Ecosystemsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Balanced Large Scale Knowledge Matching Using LSH Forest

Cochez

Terziyan

Ermolayev³

2015

Semantic Keyword-Based Search on Structured Data Sources

Self Cite

View full text Add to dashboard Cite

Representational Quality Challenges of Big Data: Insights from Comparative Case Studies

Wahyudi

Pekkola

Janssen

2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Big data is said to provide many benefits. However, as data originates from multiple sources with different quality, big data is not easy to use. Representational quality refers to the concise and consistent representation of data to allow ease of understanding of the data and interpretability. In this paper, we investigate the challenges in creating representational quality of big data. Two case studies are investigated to understand the challenges emerging from big data. Our findings suggest that the veracity and velocity of big data makes interpretation more difficult. Our findings also suggest that decisions are made ad-hoc and decision-makers often are not able to understand the ins and outs. Sense-making is one of the main challenges in big data. Taking a naturalistic decision-making view can be used to understand the challenges of big data processing, interpretation and use in decision-making better. We recommend that big data research should focus more on easy interpretation of the data.

show abstract

Agile Deep Learning UAVs Operating in Smart Spaces: Collective Intelligence Versus “Mission-Impossible”

Cochez

Périaux

Terziyan

et al. 2017

Computational Methods and Models for Transport

Self Cite

View full text Add to dashboard Cite

The environments, in which we all live, are known to be complex and unpredictable. The complete discovery of these environments aiming to take full control over them is a "mission-impossible", however, still in our common agenda. People intend to make their living spaces smarter utilizing innovations from the Internet of Things and Artificial Intelligence. Unmanned aerial vehicles (UAVs) as very dynamic, autonomous and intelligent things capable to discover and control large areas are becoming important "inhabitants" within existing and future smart cities. Our concern in this paper is to challenge the potential of UAVs in situations, which are evolving fast in awayunseen before,e.g.,emergencysituations.Toaddresssuch challenges, UAVs have to be "intelligent" enough to be capable to autonomously and in near real-time evaluate the situation and its dynamics. Then, they have to discover their own missions and set-up suitable own configurations to perform it. This configuration is the result of flexible plans which are created in mutual collab oration . Finally, the UAVs execute the plans and learn from the new experiences for future reuse. However, if to take into account also the Big Data challenge, which is naturally associated with the smart cities, UAVs must be also "wise" in a sense that the process of making autonomous and responsible real-time decisions must include continuous search for a compromise between efficiency (acceptable time frame to get the decision and reasonable resources spent for that) and effectiveness (processing as much of important input information as possible and to improve the quality of the decisions). To address such a "skill" we propose to perform the required computations using Cloud Computing enhanced with Semantic Web technologies and potential tools ("agile" deep learning) for compromising, such as, e.g., focusing, filtering, forgetting, contextualizing, compressing and connecting.

show abstract

Toward Evolving Knowledge Ecosystems for Big Data Understanding

Cited by 10 publications

References 40 publications

Balanced Large Scale Knowledge Matching Using LSH Forest

Balanced Large Scale Knowledge Matching Using LSH Forest

Representational Quality Challenges of Big Data: Insights from Comparative Case Studies

Agile Deep Learning UAVs Operating in Smart Spaces: Collective Intelligence Versus “Mission-Impossible”

Contact Info

Product

Resources

About