# US 11,310,802 B2 · Method, system and apparatus for network adaptation via learning based terrain sensing

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 11,310,802 B2
- Document ID: US11310802B2
- Status: Granted
- Kind: B2
- Application number: 16/790,772
- Filed: 2020-02-14
- Published: 2020-08-20
- Granted: 2022-04-19
- Earliest claimed: 2020-02-14
- Applicants: Lekha Wireless Solutions Pvt Ltd
- Inventors: Sreenath Ramanath
- Web page: https://patentgrep.com/patent/US11310802B2

## CPC

- H04L 67/10: in which an application is distributed across nodes in the network (software deployment G06F8/60; multiprogramming arrangements G06F9/46)
- H04W 72/51: based on terminal or device properties
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
- G06N 3/0499: Feedforward networks
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06N 3/092: Reinforcement learning
- G06N 3/098: Distributed learning, e.g. federated learning
- G06N 5/04: Inference or reasoning models
- G06N 20/00: Machine learning
- H04L 67/12: specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- H04W 88/06: adapted for operation in multiple networks {or having at least two operational modes}, e.g. multi-mode terminals
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## 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

### Claim 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.

### Claim 2 (depends on 1)

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.

### Claim 3 (depends on 2)

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.

### Claim 4 (depends on 3)

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

### Claim 5 (depends on 4)

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.