Search

TensorFlow is an open source deep learning framework developed at Google that enables developers to conceive a wide variety of applications based on artificial intelligence principles. In this paper, we employ such software resources towards the development of a computer vision system for people with visual impairments. We propose a wearable assistive technology solution consisting of a single board computer connected to a camera mounted on the user's glasses. A TensorFlow based software runs on the board in order to real time classify the images captured by the camera, while a text to speech process vocalizes the still's content for the blind person. In this way, the system provides an audio description of the objects in the user's surrounding environment and it may help these people to better detect the things around them. [ABSTRACT FROM AUTHOR]

The relationship of the teenagers with the new technologies is very complex and it is the center of attention today for the schools. Everyone is always connected: some searches show that the teenagers under 18 spend online about ten hours every day and are connected also for 24 hours with mobile devices and thanks to free wi-fi. Pair programming is a collaboration paradigm that has been strongly adopted in particular in the computer science education. In fact, Pair Programming has demonstrated benefits for many aspects in education, but unique concerns of mobile software design raise questions about the effectiveness of Pair Programming in this evolving field. This paper probes unique challenges for Pair Programming when used in mobile software design classes, focusing on four mobile design topics: dealing with interface and data management, recording and playing audio via mobile device and App Inventor components, using sensors and collecting GPS data from mobile device, using a TinyBD component of App Inventor for storage data. The paper highlights successes and challenges for Pair Programming and mobile applications, concluding with recommendations on building assignments. [ABSTRACT FROM AUTHOR]