How kusuma86/machine-learning-2026 works
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 Edge deployment · loggerLaptop.py Laptop logger · Classification_Metrics_Mission_05.md Model evaluation · Pertemuan2-EksplorasiData.ipynb Data exploration
Components 18
Course workflow
- Data exploration
Pertemuan2-EksplorasiData.ipynb - Preprocessing
Pertemuan3-DataPreprocessing.ipynb - Feature engineering
README.md
Modeling and evaluation
- Regression
LAB01/Lab01-Multiple_Regression.md - Classification
LAB01/Lab01-KNN_classification.md - Model evaluation
Classification_Metrics_Mission_05.md - Model improvement
README.md - Neural networks
TensorFlow - Dense Layer Intro/Motor_Condition.ipynb - Neural-network training
TensorFlow - Dense Layer Intro/Panduan_Motor_Condition_Dense.md
Embedded systems
- Edge deployment
README.md - Real-time inference
README.md - TinyML
PRAKTIKUM-03/Praktikum_TinyML_Klasifikasi_Getaran_Kompresor.ipynb - Decision and action
README.md
Sensor acquisition
- Laptop logger
PRAKTIKUM-02/loggerLaptop.py - ESP32 acquisition
PRAKTIKUM-02/loggerMPU6050.py - MPU6050 sensor
- Captured CSV
PRAKTIKUM-02/loggerLaptop.py
Other components
- Student
Connections 20
- Student → Data exploration: studies
README.md - Data exploration → Preprocessing: then preprocesses
README.md - Preprocessing → Feature engineering: then engineers features
README.md - Feature engineering → Regression: models with
README.md - Feature engineering → Classification: models with
README.md - Regression → Model evaluation: evaluates models
README.md - Classification → Model evaluation: evaluates models
README.md - Model evaluation → Model improvement: improves models
README.md - Model improvement → Neural networks: advances to
README.md - Neural networks → Neural-network training: trains through
README.md - Neural-network training → Edge deployment: prepares for
README.md - Edge deployment → Real-time inference: deploys for
README.md - Real-time inference → Decision and action: informs
README.md - Decision and action → Edge deployment: can trigger action
README.md - Student → Laptop logger: records data with
README.md - Laptop logger → ESP32 acquisition: commands over serial
PRAKTIKUM-02/loggerLaptop.py - ESP32 acquisition → MPU6050 sensor: reads samples from
PRAKTIKUM-02/loggerMPU6050.py - Laptop logger → Captured CSV: writes samples to
PRAKTIKUM-02/loggerLaptop.py - TinyML → Edge deployment: implements edge ML
README.md - Real-time inference → MPU6050 sensor: integrates sensors
README.md