# swandip7/5gnr-snr-estimation-cef architecture

> Architecture diagram of the GitHub repository swandip7/5gnr-snr-estimation-cef, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-07). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/swandip7/5gnr-snr-estimation-cef
- Repository: https://github.com/swandip7/5gnr-snr-estimation-cef

## Overview

This repository provides synthetic 5G NR SNR-estimation datasets, MATLAB generation scripts, and a Python model-training and evaluation pipeline. The principal workflow generates channel samples and receiver-side measurements, stores features, labels, and estimator metadata in CSVs, then trains and evaluates fusion and baseline models. The README documents generator stages and capabilities; the sampled Python excerpt shows dataset loading and training components, but not the MATLAB internals or all training steps.

Main entry points: [`python/train_cef.py`](https://github.com/swandip7/5gnr-snr-estimation-cef/blob/main/python/train_cef.py) (Training Pipeline), [`matlab/generate_dataset.m`](https://github.com/swandip7/5gnr-snr-estimation-cef/blob/main/matlab/generate_dataset.m) (RF Impairments), [`data/Enhanced_5G_Dataset_OOD_5K_v311.csv`](https://github.com/swandip7/5gnr-snr-estimation-cef/blob/main/data/Enhanced_5G_Dataset_OOD_5K_v311.csv) (OOD Dataset), [`data/Enhanced_5G_Dataset_100K_v311.csv`](https://github.com/swandip7/5gnr-snr-estimation-cef/blob/main/data/Enhanced_5G_Dataset_100K_v311.csv) (Main Dataset)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_generation["Dataset Generation"]
  node_setup["System Setup<br/>[generate_dataset.m]"]
  node_scenario["Scenario Selection<br/>[generate_dataset.m]"]
  node_channel["CDL Channel<br/>[generate_dataset.m]"]
  node_mimo["MIMO Propagation<br/>[generate_dataset.m]"]
  node_impairments["RF Impairments<br/>[generate_dataset.m]"]
  node_receiver["Receiver Processing<br/>[generate_dataset.m]"]
  node_features["Feature Extraction<br/>[generate_dataset.m]"]
  node_estimators["Classical Estimators<br/>[generate_dataset.m]"]
end

subgraph group_datasets["Datasets"]
  node_main_data[("Main Dataset")]
  node_main_metadata[("Main Metadata")]
  node_ood_data[("OOD Dataset")]
  node_ood_metadata[("OOD Metadata")]
end

subgraph group_modeling["Training and Evaluation"]
  node_training["Training Pipeline<br/>[train_cef.py]"]
  node_models["Model Architectures<br/>[train_cef.py]"]
  node_evaluation["Evaluation and Ablations<br/>[train_cef.py]"]
end

node_researcher(("Researcher"))

node_researcher -->|"generates data"| node_setup
node_setup -->|"sets parameters"| node_scenario
node_scenario -->|"selects profile"| node_channel
node_channel -->|"propagates signal"| node_mimo
node_mimo -->|"adds impairments"| node_impairments
node_impairments -->|"feeds receiver"| node_receiver
node_receiver -->|"derives features"| node_features
node_receiver -->|"computes estimates"| node_estimators
node_features -->|"stores samples"| node_main_data
node_estimators -->|"stores estimates"| node_main_metadata
node_researcher -->|"trains models"| node_training
node_main_data -->|"loads samples"| node_training
node_ood_data -->|"loads OOD samples"| node_training
node_training -->|"fits models"| node_models
node_training -->|"evaluates results"| node_evaluation
node_researcher -->|"generates OOD set"| node_ood_data
node_impairments -->|"shifts severity"| node_ood_data
node_estimators -->|"stores estimates"| node_ood_metadata

click node_setup "https://github.com/swandip7/5gnr-snr-estimation-cef/blob/main/matlab/generate_dataset.m"
click node_scenario "https://github.com/swandip7/5gnr-snr-estimation-cef/blob/main/matlab/generate_dataset.m"
click node_channel "https://github.com/swandip7/5gnr-snr-estimation-cef/blob/main/matlab/generate_dataset.m"
click node_mimo "https://github.com/swandip7/5gnr-snr-estimation-cef/blob/main/matlab/generate_dataset.m"
click node_impairments "https://github.com/swandip7/5gnr-snr-estimation-cef/blob/main/matlab/generate_dataset.m"
click node_receiver "https://github.com/swandip7/5gnr-snr-estimation-cef/blob/main/matlab/generate_dataset.m"
click node_features "https://github.com/swandip7/5gnr-snr-estimation-cef/blob/main/matlab/generate_dataset.m"
click node_estimators "https://github.com/swandip7/5gnr-snr-estimation-cef/blob/main/matlab/generate_dataset.m"
click node_main_data "https://github.com/swandip7/5gnr-snr-estimation-cef/blob/main/data/Enhanced_5G_Dataset_100K_v311.csv"
click node_main_metadata "https://github.com/swandip7/5gnr-snr-estimation-cef/blob/main/data/Enhanced_5G_Dataset_100K_v3_metadata11.csv"
click node_ood_data "https://github.com/swandip7/5gnr-snr-estimation-cef/blob/main/data/Enhanced_5G_Dataset_OOD_5K_v311.csv"
click node_ood_metadata "https://github.com/swandip7/5gnr-snr-estimation-cef/blob/main/data/Enhanced_5G_Dataset_OOD_5K_v311_metadata.csv"
click node_training "https://github.com/swandip7/5gnr-snr-estimation-cef/blob/main/python/train_cef.py"
click node_models "https://github.com/swandip7/5gnr-snr-estimation-cef/blob/main/python/train_cef.py"
click node_evaluation "https://github.com/swandip7/5gnr-snr-estimation-cef/blob/main/python/train_cef.py"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_setup,node_scenario,node_channel,node_mimo,node_impairments,node_receiver,node_features,node_estimators toneBlue
class node_main_data,node_main_metadata,node_ood_data,node_ood_metadata toneAmber
class node_training,node_models,node_evaluation toneMint
class node_researcher toneIndigo
```

## Components

### Dataset Generation

- [System Setup](https://github.com/swandip7/5gnr-snr-estimation-cef/blob/main/matlab/generate_dataset.m): `matlab/generate_dataset.m`
- [Scenario Selection](https://github.com/swandip7/5gnr-snr-estimation-cef/blob/main/matlab/generate_dataset.m): `matlab/generate_dataset.m`
- [CDL Channel](https://github.com/swandip7/5gnr-snr-estimation-cef/blob/main/matlab/generate_dataset.m): `matlab/generate_dataset.m`
- [MIMO Propagation](https://github.com/swandip7/5gnr-snr-estimation-cef/blob/main/matlab/generate_dataset.m): `matlab/generate_dataset.m`
- [RF Impairments](https://github.com/swandip7/5gnr-snr-estimation-cef/blob/main/matlab/generate_dataset.m): `matlab/generate_dataset.m`
- [Receiver Processing](https://github.com/swandip7/5gnr-snr-estimation-cef/blob/main/matlab/generate_dataset.m): `matlab/generate_dataset.m`
- [Feature Extraction](https://github.com/swandip7/5gnr-snr-estimation-cef/blob/main/matlab/generate_dataset.m): `matlab/generate_dataset.m`
- [Classical Estimators](https://github.com/swandip7/5gnr-snr-estimation-cef/blob/main/matlab/generate_dataset.m): `matlab/generate_dataset.m`

### Datasets

- [Main Dataset](https://github.com/swandip7/5gnr-snr-estimation-cef/blob/main/data/Enhanced_5G_Dataset_100K_v311.csv): `data/Enhanced_5G_Dataset_100K_v311.csv`
- [Main Metadata](https://github.com/swandip7/5gnr-snr-estimation-cef/blob/main/data/Enhanced_5G_Dataset_100K_v3_metadata11.csv): `data/Enhanced_5G_Dataset_100K_v3_metadata11.csv`
- [OOD Dataset](https://github.com/swandip7/5gnr-snr-estimation-cef/blob/main/data/Enhanced_5G_Dataset_OOD_5K_v311.csv): `data/Enhanced_5G_Dataset_OOD_5K_v311.csv`
- [OOD Metadata](https://github.com/swandip7/5gnr-snr-estimation-cef/blob/main/data/Enhanced_5G_Dataset_OOD_5K_v311_metadata.csv): `data/Enhanced_5G_Dataset_OOD_5K_v311_metadata.csv`

### Training and Evaluation

- [Training Pipeline](https://github.com/swandip7/5gnr-snr-estimation-cef/blob/main/python/train_cef.py): `python/train_cef.py`
- [Model Architectures](https://github.com/swandip7/5gnr-snr-estimation-cef/blob/main/python/train_cef.py): `python/train_cef.py`
- [Evaluation and Ablations](https://github.com/swandip7/5gnr-snr-estimation-cef/blob/main/python/train_cef.py): `python/train_cef.py`

### Other components

- **Researcher**

## Connections

- Researcher → System Setup: generates data (evidence: `README.md`)
- System Setup → Scenario Selection: sets parameters (evidence: `README.md`)
- Scenario Selection → CDL Channel: selects profile (evidence: `README.md`)
- CDL Channel → MIMO Propagation: propagates signal (evidence: `README.md`)
- MIMO Propagation → RF Impairments: adds impairments (evidence: `README.md`)
- RF Impairments → Receiver Processing: feeds receiver (evidence: `README.md`)
- Receiver Processing → Feature Extraction: derives features (evidence: `README.md`)
- Receiver Processing → Classical Estimators: computes estimates (evidence: `README.md`)
- Feature Extraction → Main Dataset: stores samples (evidence: `README.md`)
- Classical Estimators → Main Metadata: stores estimates (evidence: `README.md`)
- Researcher → Training Pipeline: trains models (evidence: `README.md`)
- Main Dataset → Training Pipeline: loads samples (evidence: `python/train_cef.py`)
- OOD Dataset → Training Pipeline: loads OOD samples (evidence: `python/train_cef.py`)
- Training Pipeline → Model Architectures: fits models (evidence: `python/train_cef.py`)
- Training Pipeline → Evaluation and Ablations: evaluates results (evidence: `python/train_cef.py`)
- Researcher → OOD Dataset: generates OOD set (evidence: `README.md`)
- RF Impairments → OOD Dataset: shifts severity (evidence: `README.md`)
- Classical Estimators → OOD Metadata: stores estimates (evidence: `README.md`)
