IP Library Granted Patent US 11,310,802
Granted Patent B2
US 11,310,802 · App. 16/790,772 · Granted Apr 19, 2022

Method, system and apparatus for network adaptation via learning based terrain sensing

Inventor: Sreenath Ramanath (Bengaluru, IN)
H04W72/048G06N5/04G06N20/00H04W88/06
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,310,802
App. No.
16/790,772
Granted
Apr 19, 2022
Kind
B2
Abstract

According to an aspect, a mobile device capable of communicating with a base station using a communication mode from plurality of communication modes comprising, a set of sensors configured to provide a data representing a terrain condition of the mobile device, a distributed machine learning engine determining a first terrain state at regular interval based on a current data and a past data received from the set of sensors, and an inference unit determining a second terrain state of the mobile device from the current data and the first terrain state, wherein, the base station allocating the communication mode from plurality of communication modes based on the second terrain state.

Claims (9)

1. A mobile device capable of communicating with a base station using a communication mode from plurality of communication modes comprising:

a set of sensors configured to provide a data representing a terrain condition of the mobile device;

a distributed machine learning engine determining a first terrain state at regular interval based on a current data and a past data received from the set of sensors; and

an inference unit determining a second terrain state of the mobile device from the current data and the first terrain state,

wherein, the base station allocating the communication mode from plurality of communication modes based on the second terrain state.

2. The mobile device of claim 1 , wherein the set of sensor comprising a camera providing a sequence of images, a audio sensor providing sound information, a signal measurement device providing signal strength information, a position sensor providing a geographical position information and a geo data providing map information, in that distributed machine learning engine employing the sequence of images, sound information and position information to determine the terrain state.

3. The mobile device of claim 2 , wherein the distributed machine learning engine is configured to operate in two phases, a training and a prediction phase, wherein in the training phase a known terrain and a known sequence of images, a known sound information and a known position information are provided to generate a set of inference rule and a set of classification labels, and the distributed machine learning engine configured to apply the set of inference rule and the set of classification labels to a sequence of images, a sound information and a position information to determine the terrain state in the prediction phase.

4. The mobile device of claim 3 , wherein the communication mode comprising a first frequency and a second frequency resources.

5. The mobile device of claim 4 , wherein the communication mode further comprising a selection mode may comprises various transmission modes including, SISO, transmit diversity, Open-loop and closed-loop spatial multiplexing, MU-MIMO, pre-coding and a beam forming.

Continuity (1)
Related Publication 20200267717A1 · Aug 20, 2020