AppliedML-Refrigerator_Fault_Detection

Work for discipline INE410146 - Applied Machine Learning for Graduate Program in Computer Science (PPGCC) - Federal University of Santa Catarina

Objective:

Design and build a machine learning pipeline to classify faults of a refrigerator

Motivation:

No fault found (NFF) accounts for about 30-70% of the returned faulty products. Also, the investigation into the diagnosis of household anomalous appliances has not been decently taken into consideration \cite{Hosseini2020}. In the end, that means that home appliance manufacturing companies need to spend a large amount of capital caused by an imprecise or incorrect fault detection done by the maintenance engineer or by a misperception of the user. Such a fault can be identified by classifying the multivariate time series (MTS).The present work shows a machine learning pipeline that can receive an MTS from a refrigerator and classify that product as not having fault or having some fault on which the model was trained on.

Applied Machine Learning for Graduate Program in Computer Science (PPGCC)

Related tags

Overview

AppliedML-Refrigerator_Fault_Detection

Objective:

Motivation:

Owner

Jônatas Negri Grandini

scikit-learn models hyperparameters tuning and feature selection, using evolutionary algorithms.

Scikit learn library models to account for data and concept drift.

Bayesian optimization in JAX

Data Efficient Decision Making

Evidently helps analyze machine learning models during validation or production monitoring

PyNNDescent is a Python nearest neighbor descent for approximate nearest neighbors.

Avocado hass time series vs predict price

Python library which makes it possible to dynamically mask/anonymize data using JSON string or python dict rules in a PySpark environment.

A repository of PyBullet utility functions for robotic motion planning, manipulation planning, and task and motion planning

Compare MLOps Platforms. Breakdowns of SageMaker, VertexAI, AzureML, Dataiku, Databricks, h2o, kubeflow, mlflow...

Confidence intervals for scikit-learn forest algorithms

Required for a machine learning pipeline data preprocessing and variable engineering script needs to be prepared

Tools for diffing and merging of Jupyter notebooks.

Massively parallel self-organizing maps: accelerate training on multicore CPUs, GPUs, and clusters

Practical Time-Series Analysis, published by Packt

Python 3.6+ toolbox for submitting jobs to Slurm

Predico Disease Prediction system based on symptoms provided by patient- using Python-Django & Machine Learning

A Pythonic framework for threat modeling

SIMD-accelerated bitwise hamming distance Python module for hexidecimal strings

Xeasy-ml is a packaged machine learning framework.