"id" |"create_date" |"modified_date" |"depositor" |"title" |"date_uploaded" |"date_modified"|"state"|"proxy_depositor"|"on_behalf_of"|"arkivo_checksum"|"owner"|"alternate_title"|"award"|"includes"|"advisor" |"advisor" |"sponsor" |"sponsor" |"center"|"year"|"funding"|"institute"|"school"|"major" |"sdg" |"note" |"alternative_title"|"label"|"relative_path"|"import_url"|"resource_type" |"creator" |"contributor"|"description" |"abstract"|"keyword" |"keyword" |"keyword" |"keyword" |"keyword" |"keyword" |"license"|"rights_notes"|"rights_statement" |"access_right"|"publisher" |"date_created"|"subject" |"subject" |"subject" |"subject" |"language"|"identifier" |"identifier"|"based_near"|"related_url"|"bibliographic_citation"|"source"|"version" |"permalink" "j3860b242"|"2022-02-21T15:04:16.520+00:00"|"2024-03-11T20:09:01.873+00:00"|"depositor@wpi.edu"|"IndexPen: Two-Finger Text Input with Millimeter-Wave Radar"|"2022-02-21T10:04:15.952-05:00"|"" |"" |"" |"" |"" |"" |"" |"" |"" |"Solovey, Erin"|"Pahlavan, Kaveh"|"Kaveh Pahlavan"|"Erin Solovey"|"" |"2021"|"" |"" |"" |"Electrical & Computer Engineering"|"09 - Industry, Innovation and Infrastructure"|"This report represents the work of one or more WPI undergraduate students submitted to the faculty as evidence of completion of a degree requirement. WPI routinely publishes these reports on its website without editorial or peer review."|"" |"" |"" |"" |"Major Qualifying Project"|"Wei, Haowen"|"" |"Recent work has shown that the mmWave radar sensors can track object motion in 3-dimensional space with high resolution, providing a new approach for humans to interact with electronic devices. Specifically, this emerging technology enables the close distance gesture motion detection and classification with high resolution, which has the potential to become a text input device that does not require physical contact from users. We develop an in-air real-time writing system via a deep learning approach with its high resolution and touch-free properties. In this project, we introduce IndexPen, a novel interaction technique for text input through two-finger in-air micro-gestures, enabling touch-free, effortless, tracking-based interaction, designed to mirror real-world writing. Our system is based on millimeter-wave radar sensing and does not require instrumentation on the user. IndexPen can successfully identify 30 distinct gestures, representing the letters A-Z, as well as Space, Backspace, Enter, and a special Activation gesture to prevent unintentional input. Additionally, we include a noise class to differentiate gesture and non-gesture noise. We present our system design, including the radio frequency (RF) processing pipeline, classification model, and real-time detection algorithms."|"" |"Real-time Signal Processing"|"Deep Learning"|"Transfer Learning"|"Mobile Computing and Human Computer Interaction"|"Radio Frequency(RF) signal"|"Embedded System"|"" |"" |"http://rightsstatements.org/vocab/InC/1.0/"|"" |"Worcester Polytechnic Institute"|"2021-11-17" |"Project-Based Learning"|"Computing"|"Industry"|"Innovation"|"" |"E-project-111721-144850"|"41536" |"" |"" |"" |"" |"W/"c601e09e613a08b92a24d039f5aa713d467ae706""|"https://digital.wpi.edu/show/j3860b242"