Machine Learning

This dataset contains 3D models of 5 objects and numerous scenes where the objects are placed randomly creating occlusions and cluttered scenes. The 3D models are to be used to find them in the scene (object recognition) and segment them as well.

eLearning, or online learning, has reached every corner of the globe in this era of digitization. As a result of the COVID-19 pandemic, the value of eLearning has increased substantially. In eLearning recommendation systems, information overload, personalised suggestion, sparsity, and accuracy are all major problems. The correct eLearning Recommendation System is necessary to tailor the course recommendation according to the user's needs. To create this model, dataset of the User Profile and User Rating is needed.

CAD-EdgeTune dataset is acquired using a Husarion ROSbot 2.0 and ROSbot 2.0 Pro with the collection speed set to 5 frames per second from a suburban university environment. We may split the information into subgroups for noon, dusk, and dawn in order to depict our surroundings under various lighting situations. We have assembled 17 sequences totaling 8080 frames, of which 1619 have been manually analyzed using an open-source pixel annotation program. Since nearby photographs are highly similar to one another, we decide to annotate every five images.

We collected data to train the ML module to determine the user’s device's location based on beacon frame characteristics and RSSI values from Wi-Fi APs. To collect the data, we defined a threshold distance of 7 feet as the maximum allowable distance between the user’s devices. We then collected two datasets: one with data collected while the two Raspberry Pis were within 7 feet or less of each other named ”authentic”, and another with data collected while the distance between the two Raspberry Pis was over 7 feet named ”unauthorized”.