# kusuma86/machine-learning-2026 architecture

> Architecture diagram of the GitHub repository kusuma86/machine-learning-2026, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-11-17). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/kusuma86/machine-learning-2026
- Repository: https://github.com/kusuma86/machine-learning-2026

## Overview

This is a teaching-resource repository for a Machine Learning course, not a single runnable application. Its principal learning workflow runs from data exploration and preprocessing through modeling, evaluation, deployment, real-time inference, and decisions/actions. The README also documents neural-network, Raspberry Pi, sensor-integration, TinyML, and end-to-end topics. The graph maps these stages to representative materials; most relationships are course-level documentation rather than inspected runtime calls. The two sampled logger scripts show the sensor-acquisition path directly.

Main entry points: [`README.md`](https://github.com/kusuma86/machine-learning-2026/blob/main/README.md) (Edge deployment), [`PRAKTIKUM-02/loggerLaptop.py`](https://github.com/kusuma86/machine-learning-2026/blob/main/PRAKTIKUM-02/loggerLaptop.py) (Laptop logger), [`Classification_Metrics_Mission_05.md`](https://github.com/kusuma86/machine-learning-2026/blob/main/Classification_Metrics_Mission_05.md) (Model evaluation), [`Pertemuan2-EksplorasiData.ipynb`](https://github.com/kusuma86/machine-learning-2026/blob/main/Pertemuan2-EksplorasiData.ipynb) (Data exploration)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_learning["Course workflow"]
  node_exploration["Data exploration"]
  node_preprocessing["Preprocessing"]
  node_feature["Feature engineering<br/>[README.md]"]
end

subgraph group_models["Modeling and evaluation"]
  node_regression["Regression"]
  node_classification["Classification"]
  node_evaluation["Model evaluation"]
  node_improvement["Model improvement<br/>[README.md]"]
  node_neuralnet["Neural networks"]
  node_training["Neural-network training"]
end

subgraph group_embedded["Embedded systems"]
  node_deployment["Edge deployment<br/>[README.md]"]
  node_inference["Real-time inference<br/>[README.md]"]
  node_tinyml["TinyML"]
  node_decision["Decision and action<br/>[README.md]"]
end

subgraph group_acquisition["Sensor acquisition"]
  node_laptop["Laptop logger<br/>[loggerLaptop.py]"]
  node_esp32["ESP32 acquisition<br/>[loggerMPU6050.py]"]
  node_mpu["MPU6050 sensor"]
  node_csv["Captured CSV<br/>[loggerLaptop.py]"]
end

node_student(("Student"))

node_student -->|"studies"| node_exploration
node_exploration -->|"then preprocesses"| node_preprocessing
node_preprocessing -->|"then engineers features"| node_feature
node_feature -->|"models with"| node_regression
node_feature -->|"models with"| node_classification
node_regression -->|"evaluates models"| node_evaluation
node_classification -->|"evaluates models"| node_evaluation
node_evaluation -->|"improves models"| node_improvement
node_improvement -->|"advances to"| node_neuralnet
node_neuralnet -->|"trains through"| node_training
node_training -->|"prepares for"| node_deployment
node_deployment -->|"deploys for"| node_inference
node_inference -->|"informs"| node_decision
node_decision -->|"can trigger action"| node_deployment
node_student -->|"records data with"| node_laptop
node_laptop -->|"commands over serial"| node_esp32
node_esp32 -->|"reads samples from"| node_mpu
node_laptop -->|"writes samples to"| node_csv
node_tinyml -->|"implements edge ML"| node_deployment
node_inference -->|"integrates sensors"| node_mpu

click node_exploration "https://github.com/kusuma86/machine-learning-2026/blob/main/Pertemuan2-EksplorasiData.ipynb"
click node_preprocessing "https://github.com/kusuma86/machine-learning-2026/blob/main/Pertemuan3-DataPreprocessing.ipynb"
click node_feature "https://github.com/kusuma86/machine-learning-2026/blob/main/README.md"
click node_regression "https://github.com/kusuma86/machine-learning-2026/blob/main/LAB01/Lab01-Multiple_Regression.md"
click node_classification "https://github.com/kusuma86/machine-learning-2026/blob/main/LAB01/Lab01-KNN_classification.md"
click node_evaluation "https://github.com/kusuma86/machine-learning-2026/blob/main/Classification_Metrics_Mission_05.md"
click node_improvement "https://github.com/kusuma86/machine-learning-2026/blob/main/README.md"
click node_neuralnet "https://github.com/kusuma86/machine-learning-2026/blob/main/TensorFlow%20-%20Dense%20Layer%20Intro/Motor_Condition.ipynb"
click node_training "https://github.com/kusuma86/machine-learning-2026/blob/main/TensorFlow%20-%20Dense%20Layer%20Intro/Panduan_Motor_Condition_Dense.md"
click node_deployment "https://github.com/kusuma86/machine-learning-2026/blob/main/README.md"
click node_inference "https://github.com/kusuma86/machine-learning-2026/blob/main/README.md"
click node_tinyml "https://github.com/kusuma86/machine-learning-2026/blob/main/PRAKTIKUM-03/Praktikum_TinyML_Klasifikasi_Getaran_Kompresor.ipynb"
click node_decision "https://github.com/kusuma86/machine-learning-2026/blob/main/README.md"
click node_laptop "https://github.com/kusuma86/machine-learning-2026/blob/main/PRAKTIKUM-02/loggerLaptop.py"
click node_esp32 "https://github.com/kusuma86/machine-learning-2026/blob/main/PRAKTIKUM-02/loggerMPU6050.py"
click node_csv "https://github.com/kusuma86/machine-learning-2026/blob/main/PRAKTIKUM-02/loggerLaptop.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_exploration,node_preprocessing,node_feature toneBlue
class node_regression,node_classification,node_evaluation,node_improvement,node_neuralnet,node_training toneAmber
class node_deployment,node_inference,node_tinyml,node_decision toneMint
class node_laptop,node_esp32,node_mpu,node_csv toneRose
class node_student toneIndigo
```

## Components

### Course workflow

- [Data exploration](https://github.com/kusuma86/machine-learning-2026/blob/main/Pertemuan2-EksplorasiData.ipynb): `Pertemuan2-EksplorasiData.ipynb`
- [Preprocessing](https://github.com/kusuma86/machine-learning-2026/blob/main/Pertemuan3-DataPreprocessing.ipynb): `Pertemuan3-DataPreprocessing.ipynb`
- [Feature engineering](https://github.com/kusuma86/machine-learning-2026/blob/main/README.md): `README.md`

### Modeling and evaluation

- [Regression](https://github.com/kusuma86/machine-learning-2026/blob/main/LAB01/Lab01-Multiple_Regression.md): `LAB01/Lab01-Multiple_Regression.md`
- [Classification](https://github.com/kusuma86/machine-learning-2026/blob/main/LAB01/Lab01-KNN_classification.md): `LAB01/Lab01-KNN_classification.md`
- [Model evaluation](https://github.com/kusuma86/machine-learning-2026/blob/main/Classification_Metrics_Mission_05.md): `Classification_Metrics_Mission_05.md`
- [Model improvement](https://github.com/kusuma86/machine-learning-2026/blob/main/README.md): `README.md`
- [Neural networks](https://github.com/kusuma86/machine-learning-2026/blob/main/TensorFlow%20-%20Dense%20Layer%20Intro/Motor_Condition.ipynb): `TensorFlow - Dense Layer Intro/Motor_Condition.ipynb`
- [Neural-network training](https://github.com/kusuma86/machine-learning-2026/blob/main/TensorFlow%20-%20Dense%20Layer%20Intro/Panduan_Motor_Condition_Dense.md): `TensorFlow - Dense Layer Intro/Panduan_Motor_Condition_Dense.md`

### Embedded systems

- [Edge deployment](https://github.com/kusuma86/machine-learning-2026/blob/main/README.md): `README.md`
- [Real-time inference](https://github.com/kusuma86/machine-learning-2026/blob/main/README.md): `README.md`
- [TinyML](https://github.com/kusuma86/machine-learning-2026/blob/main/PRAKTIKUM-03/Praktikum_TinyML_Klasifikasi_Getaran_Kompresor.ipynb): `PRAKTIKUM-03/Praktikum_TinyML_Klasifikasi_Getaran_Kompresor.ipynb`
- [Decision and action](https://github.com/kusuma86/machine-learning-2026/blob/main/README.md): `README.md`

### Sensor acquisition

- [Laptop logger](https://github.com/kusuma86/machine-learning-2026/blob/main/PRAKTIKUM-02/loggerLaptop.py): `PRAKTIKUM-02/loggerLaptop.py`
- [ESP32 acquisition](https://github.com/kusuma86/machine-learning-2026/blob/main/PRAKTIKUM-02/loggerMPU6050.py): `PRAKTIKUM-02/loggerMPU6050.py`
- **MPU6050 sensor**
- [Captured CSV](https://github.com/kusuma86/machine-learning-2026/blob/main/PRAKTIKUM-02/loggerLaptop.py): `PRAKTIKUM-02/loggerLaptop.py`

### Other components

- **Student**

## Connections

- Student → Data exploration: studies (evidence: `README.md`)
- Data exploration → Preprocessing: then preprocesses (evidence: `README.md`)
- Preprocessing → Feature engineering: then engineers features (evidence: `README.md`)
- Feature engineering → Regression: models with (evidence: `README.md`)
- Feature engineering → Classification: models with (evidence: `README.md`)
- Regression → Model evaluation: evaluates models (evidence: `README.md`)
- Classification → Model evaluation: evaluates models (evidence: `README.md`)
- Model evaluation → Model improvement: improves models (evidence: `README.md`)
- Model improvement → Neural networks: advances to (evidence: `README.md`)
- Neural networks → Neural-network training: trains through (evidence: `README.md`)
- Neural-network training → Edge deployment: prepares for (evidence: `README.md`)
- Edge deployment → Real-time inference: deploys for (evidence: `README.md`)
- Real-time inference → Decision and action: informs (evidence: `README.md`)
- Decision and action → Edge deployment: can trigger action (evidence: `README.md`)
- Student → Laptop logger: records data with (evidence: `README.md`)
- Laptop logger → ESP32 acquisition: commands over serial (evidence: `PRAKTIKUM-02/loggerLaptop.py`)
- ESP32 acquisition → MPU6050 sensor: reads samples from (evidence: `PRAKTIKUM-02/loggerMPU6050.py`)
- Laptop logger → Captured CSV: writes samples to (evidence: `PRAKTIKUM-02/loggerLaptop.py`)
- TinyML → Edge deployment: implements edge ML (evidence: `README.md`)
- Real-time inference → MPU6050 sensor: integrates sensors (evidence: `README.md`)
