No abstract

No abstract

No abstract

With the success and ubiquity of large scale, social media networks comes the challenge of assessing the veracity of information shared across them that inform individuals about emerging real-world events and trends. We propose a veracityassessment model for information dissemination on social media networks that combines natural language processing and machine learning algorithms to mine textual content generated by each user. Large scale social media networks (such as Twitter and Facebook) are considered digital communication platforms, in which information can be quickly and easily exchanged, thereby expanding the breadth of knowledge across the globe. In this paper, four case studies spanning multiple geographic regions, threat scenarios and time frames are investigated, in order to demonstrate how real-world events impact the manner in which information/misinformation is communicated and spread through a social media network. Our results show that metadata associated with each user can provide significant insight on the social media network's users' tendency to accurately discuss a topic.

This paper presents a study of wide area agents based on communication for primary and backup coordinated protection. Agents are used to give each protection component control capacity as well as the ability to communicate with other agents. We feel that this method naturally points towards a new philosophy for primary and backup protection. Simulations are used to illustrate concepts, using a simulation engine named EPOCHS that combines the EMTDClPSCAD power simulator with the NS2 network communications simulator. Results illustrate the improved performance of our protection scheme, In this new protection system, agents were embedded in each of the conventional protection components to construct an IED relay (Intelligent Electronic Device). The agent searches for relevant information by communicating with other agents, Agent communications can take place at the same substation or at remote substations. This information can be used to detect primary and remote faults, relay misoperation, breaker failures, and to compensate such problems with much better performance than that can be done in traditional schemes. Preliminary results give us hope that the proposed protection scheme may be able to contribute towards the mitigation of wide-area disturbances and the power blackouts that frequently follow them. Index

No abstract

No abstract

In recent years, convolutional neural networks have achieved state-of-the-art performance in a number of computer vision problems such as image classification. Prior research has shown that a transfer learning technique known as parameter finetuning wherein a network is pre-trained on a different dataset can boost the performance of these networks. However, the topic of identifying the best source dataset and learning strategy for a given target domain is largely unexplored. Thus, this research presents and evaluates various transfer learning methods for fine-grained image classification as well as the effect on ensemble networks. The results clearly demonstrate the effectiveness of parameter fine-tuning over random initialization. We find that training should not be reduced after transferring weights, larger, more similar networks tend to be the best source task, and parameter fine-tuning can often outperform randomly initialized ensembles. The experimental framework and findings will help to train models with improved accuracy.