Social media is one of the major outcomes of progressive changes in the world of technology. The various social webs and mobile technologies have accelerated the rate at which information sharing is done, how relationships developed, and influences are held. Social media is increasingly being used by the people to help and shape the world's events and cultures with the ability to share pictures, ideas, events, etc. Further, it has transformed the way the authors interpret life and the way business is done. This article presents a decision system for selecting an appropriate social media platform (such as Facebook or Twitter) to post content with the objective to maximize the reachability of the post. The decision is made considering the domain or subject of the post and retrieving data associated with it from the web at regular time intervals. The retrieved data has been trained using logistics and K-NN regression to classify a particular instance of data and identify the platform which can provide the most reachability. The system also suggests keywords related to the topic of the post which has been mostly used in recent times.
This paper considers the problem of cooperative localization of multiple robots under uncertainty, communicating over a partially connected, dynamic communication network and assisted by an agile landmark. Each robot owns an IMU and a relative pose sensing suite, which can get faulty due to system or environmental uncertainty, and therefore exhibit large bias in their estimation output. For the robots to localize accurately under sensor failure and system or environmental uncertainty, a novel Distributed Learning based Decentralized Cooperative Localization (DL-DCL) algorithm is proposed that involves real-time learning of an information fusion strategy by each robot for combining pose estimates from its own sensors as well as from those of its neighboring robots, and utilizing the moving landmark's pose information as a feedback to the learning process. Convergence analysis shows that the learning process converges exponentially under certain reasonable assumptions. Simulations involving sensor failures inducing around 40-60 times increase in the nominal bias show DL-DCL's estimation performance to be approximately 40% better than the well-known covariance-based estimate fusion methods. For the evaluation of DL-DCL's implementability and fault-tolerance capability in practice, a high-fidelity simulation is carried out in Gazebo with ROS2.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.