International Business Machines Corporation

Maletsabisa Molapo

Hyman David Chantz

Toby Kurien

Richard Allen Young

Enas Ahmed Zaki

Vishnupriya Muthukesavaraj

Ismail Yunus Akhalwaya

Naweed Aghmad Khan

Darlington Shingirirai Mapiye

Sibusisiwe Audrey Makhanya

Joan Byamugisha

Chane Simone Moodley

A method includes: receiving, by a computer device, an association of a prescribed treatment to a user; receiving, by the computer device, an image of the user; receiving, by the computer device, an image of treatment adherence by the user; determining, by the computer device, adherence to the prescribed treatment by analyzing the image of treatment adherence; and generating, by the computer device, a personalized visualization illustrating the determined adherence to the prescribed treatment by modifying the image of the user.

Treatment adherence systems and processes

Method, systems, and apparatus to facilitate navigation in a known environment. Communication and tracking between a receiver device and one or more beacons are provided to identify a current position of the receiver device. A direction to a next waypoint of a current path is determined based on the identified current position and a haptic feedback system is signaled to provide continuous haptic feedback to orient a user in the identified direction.

Spatial guidance system for visually impaired individuals

Method and systems for identifying dangers in an accessible environment. Computer vision and video analysis is performed on one or more images and/or video of the accessible environment to generate a series of still frames for a database of training images and natural language processing (NLP) is performed on one or more written reports to generate textual parameters. An online image similarity search is performed using the textual parameters to generate additional images for the database of training images and a risk/danger prediction model is generated based on the database of training images. One or more potential dangers are identified, and one or more warnings are generated using the risk/danger prediction model.

Contextual safety assessment, recommendations, provisioning and monitoring

Language models may be run with an input set of words in a given sentence. Each of the language models can predict a set of next candidate words to follow the input set or words. Based on the sets of next candidate words predicted by the language models and an actual next word, language guidance can be provided.

Automated feedback in online language exercises

Summarizing contents displayed on a screen of a device based on scroll speed of a user to decrease eye strain of a user by providing a summarization of the content being actively scrolled.

Growing community of inventors

Pretoria, South Africa

Maletsabisa Molapo