MULTIPLE-ACCESS CODE GENERATION

Patent №

US 7,587,660

Granted

2009-09-08

Filed 2005

Owner

KANSAS STATE UNIVERSITY RESEARCH FOUNDATION

Lab

AI components

2

ml · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

11112249

Multiple-access codes are generated using an asymptotically optimal decoding algorithm, such as the Viterbi algorithm. A trellis may be constructed using a number of desired users, at least one code length, and a number of code-chip parameters. A fitness function is derived from a mathematical relationship between the multiple-access codes, and may include some measure of correlation of the codes. The multiple-access codes correspond to paths having optimal path metrics derived from the fitness function. Multiple iterations through the trellis may be performed to refine a selection of multiple-access codes.

Machine learningAI hardwareH04L 5/026H03M 13/41H04J 13/10

AI classification

Machine learning1.00
AI hardware0.97
Evolutionary computation0.30
Speech0.20
Planning0.09
Vision0.02
Knowledge representation0.00
Natural language0.00

Ownership

KANSAS STATE UNIVERSITY RESEARCH FOUNDATION

assignment · 224910673

Assignors

DYER, JUSTIN, NATARAJAN, BALASUBRAMIUM

On an employer assignment, the assignors are typically the inventors.

© 2026 NYSGPT2525 LLC