# US 11,309,991 B2 · Wireless receiver apparatus

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

- Number: US 11,309,991 B2
- Document ID: US11309991B2
- Status: Granted
- Kind: B2
- Application number: 17/230,323
- Filed: 2021-04-14
- Published: 2021-10-14
- Granted: 2022-04-19
- Earliest claimed: 2020-04-14
- Assignees: NEC Corporation; Osaka University; The Doshisha
- Applicants: NEC Corporation; Osaka University; The Doshisha
- Inventors: Kazushi Muraoka; Naoto Ishii; Takumi Takahashi; Seiichi Sampei; Shinsuke Ibi
- Web page: https://patentgrep.com/patent/US11309991B2

## CPC

- H04L 1/0045: {Arrangements at the receiver end}
- H04L 25/03165: {using neural networks}
- H03M 13/1111: {Soft-decision decoding, e.g. by means of message passing or belief propagation algorithms}
- H04L 1/0057: {Block codes (H04L1/0061, H04L1/0064 take precedence)}
- H04L 25/0328: {with interference cancellation circuitry (adaptations for interference cancellation within a sequence estimator H04L25/03305; interference related aspects of direct sequence spread spectrum H04B1/7097; interference related aspects of frequency hopping spread spectrum H04B1/715; see also H04B1/10)}
- H04L 2025/03611: {Iterative algorithms}
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- H03M: CODING; DECODING; CODE CONVERSION IN GENERAL (using fluidic means F15C4/00; optical analogue/digital converters G02F7/00; coding, decoding or code conversion, specially adapted for particular applications, see the relevant subclasses, e.g. G01D, G01R, G06F, G06T, G09G, G10L, G11B, G11C, H04B, H04L, H04M, H04N; ciphering or deciphering for cryptography or other purposes involving the need for secrecy G09C)

## Abstract

A BP detector of a wireless receiver apparatus reads a first parameter set or a second parameter set. The first parameter set includes a plurality of scaling factors and a plurality of damping factors learned together using a deep learning technique. The second parameter set includes a plurality of scaling factors and a plurality of node selection factors learned together using a deep learning technique from a memory. The BP detector executes an iterative BP algorithm that uses the first parameter set or the second parameter set in order to perform multi-user detection.

## Claims

### Claim 1

A wireless receiver apparatus comprising:
at least one memory configured to store a first parameter set or a second parameter set, the first parameter set including a plurality of scaling factors and a plurality of damping factors learned together using a deep learning technique, the second parameter set including a plurality of scaling factors and a plurality of node selection factors learned together using a deep learning technique; and
a BP detector configured to execute an iterative Belief Propagation (BP) algorithm that uses the first parameter set or the second parameter set in order to perform multi-user detection.

### Claim 2 (depends on 1)

The wireless receiver apparatus according to claim 1, wherein
the BP detector is configured to use the scaling factors in different respective iterations of the iterative BP algorithm, and
the BP detector is configured to use the damping factors, or the node selection factors, in the different respective iterations of the iterative BP algorithm.

### Claim 3 (depends on 1)

The wireless receiver apparatus according to claim 1, wherein
the first parameter set, or the second parameter set, comprises a plurality of subsets that correspond to different total numbers of iterations, and
the BP detector is configured to use in the iterative BP algorithm a subset that corresponds to a configured number of iterations.

### Claim 4 (depends on 1)

The wireless receiver apparatus according to claim 1, wherein
the BP detector is configured to use the second parameter set in the iterative BP algorithm, and
each of the node selection factors is a real number value between 0 and 1.

### Claim 5 (depends on 1)

The wireless receiver apparatus according to claim 1, wherein the BP detector comprises:
an interference canceller configured to use replicas of all transmitted signals, excluding an m-th transmitted signal, generated in a (t−1)-th iteration and subtract components of all the transmitted signals, excluding a component of the m-th transmitted signal, from an n-th received signal among a plurality of received signals, thereby generating a post-cancellation n-th received signal;
a belief generator configured to generate a belief associated with the n-th received signal at least based on the damping factor or the node selection factor and based on the post-cancellation n-th received signal; and
a replica generator configured to generate a replica of the m-th transmitted signal in a t-th iteration at least based on the scaling factor and the belief.

### Claim 6

A method performed by a wireless receiver apparatus, the method comprising:
reading a first parameter set or a second parameter set from a memory, the first parameter set including a plurality of scaling factors and a plurality of damping factors learned together using a deep learning technique, the second parameter set including a plurality of scaling factors and a plurality of node selection factors learned together using a deep learning technique; and
executing an iterative Belief Propagation (BP) algorithm that uses the first parameter set or the second parameter set in order to perform multi-user detection.

### Claim 7 (depends on 6)

The method according to claim 6, wherein the executing comprises:
using the scaling factors in different respective iterations of the iterative BP algorithm; and
using the damping factors, or the node selection factors, in the different respective iterations of the iterative BP algorithm.

### Claim 8 (depends on 6)

The method according to claim 6, wherein
the first parameter set, or the second parameter set, comprises a plurality of subsets that correspond to different total numbers of iterations, and
the executing comprises using in the iterative BP algorithm a subset that corresponds to a configured number of iterations.

### Claim 9 (depends on 6)

The method according to claim 6, wherein
the executing comprises using the second parameter set in the iterative BP algorithm, and
each of the node selection factors is a real number value between 0 and 1.

### Claim 10

A non-transitory computer readable medium storing a program comprising instructions, which when executed on a processor of a wireless receiver apparatus causes the processor to:
read a first parameter set or a second parameter set from a memory, the first parameter set including a plurality of scaling factors and a plurality of damping factors learned together using a deep learning technique, the second parameter set including a plurality of scaling factors and a plurality of node selection factors learned together using a deep learning technique; and
execute an iterative Belief Propagation (BP) algorithm that uses the first parameter set or the second parameter set in order to perform multi-user detection.

### Claim 11 (depends on 10)

The non-transitory computer readable medium according to claim 10, wherein the executing comprises:
using the scaling factors in different respective iterations of the iterative BP algorithm; and
using the damping factors, or the node selection factors, in the different respective iterations of the iterative BP algorithm.

### Claim 12 (depends on 10)

The non-transitory computer readable medium according to claim 10, wherein
the first parameter set, or the second parameter set, comprises a plurality of subsets that correspond to different total numbers of iterations, and
the executing comprises using in the iterative BP algorithm a subset that corresponds to a configured number of iterations.

### Claim 13 (depends on 10)

The non-transitory computer readable medium according to claim 10, wherein
the executing comprises using the second parameter set in the iterative BP algorithm, and
each of the node selection factors is a real number value between 0 and 1.