Search engines and social media keep trace of profile-and behavioral-based distinct signals of their users, to provide them personalized and recommended content. Here, we focus on the level of web search personalization, to estimate the risk of trapping the user into so called Filter Bubbles. Our experimentation has been carried out on news, specifically investigating the Google News platform. Our results are in line with existing literature and call for further analyses on which kind of users are the target of specific recommendations by Google.

No abstract

Major search engines deploy personalized Web results to enhance users' experience, by showing them data supposed to be relevant to their interests. Even if this process may bring benefits to users while browsing, it also raises concerns on the selection of the search results. In particular, users may be unknowingly trapped by search engines in protective information bubbles, called "filter bubbles", which can have the undesired effect of separating users from information that does not fit their preferences. This paper moves from early results on quantification of personalization over Google search query results. Inspired by previous works, we have carried out some experiments consisting of search queries performed by a battery of Google accounts with differently prepared profiles. Matching query results, we quantify the level of personalization, according to topics of the queries and the profile of the accounts. This work reports initial results and it is a first step a for more extensive investigation to measure Web search personalization.

When pet's owners take care of their pets, it sparks the need to know about the well-being of their pets. This requires the ability to monitor the animals' activities in order to recognize unexpected behavior of the pets. Such monitoring systems are also useful for pet training purposes, which could be extended to more intelligent systems used to encourage specific behavior of pets. In order to do so, this study aims to develop a system that can keep track and record of such data of pets (e.g. movements, body temperature). The proposed ecosystem includes a collar affixed to the pet, interacting with a mobile application, a cloud data storage and processing platform as well as other toys to communicate with. This system is designed to be easily extended with new toys. It also can interact with smart voice assistant systems such as Apple Siri or Amazon Alexa. In addition, it has light weight so it can be affixed to small dogs or cats.

Localization is one of the most important functions for autonomous mobile robots (AMRs). For indoor applications, the localization problem faces some difficulties such as lightning variation, dynamic objects or highly reflective surfaces that generate measurement noises for the perceptive sensor systems. Recently, tags-based pose estimation has become a popular and efficient solution for AMRs. In this article, we also ultilize ceiling mounted AprilTags for our AMR application in indoor environment. The advantage of AprilTags is their invariance to uncertainty of the environment such as lightning conditions, providing robust pose measurements with a fairly large range of measuring distances from the camera to fiducial markers. By integrating AprilTags in the SLAM package, we have solved several problems such as robot pose-recovery problem and improving the accuracy of the robot localization. Experiments with an AMR robotic system, the Vibot-2 robot, are carried out in two cases: under day-light condition and night-time condition to verify the accuracy of the method. In addition, we also discuss our solution of tag positioning in order to increase the stability of the robot navigation in global map. Experiment results show that the accuracy in pose estimation is less than 20 cm in terms of position and less than 5° in terms of heading angle. Furthermore, the pose measurements from the camera are quite stable under different lightning conditions.