MTSA (Multiple Time Series Analysis)
MTSA is a unified framework for anomaly detection in multiple time series, designed to facilitate the replication and development of state-of-the-art anomaly detection approaches. The framework is particularly focused on handling acoustic data from industrial machinery, such as valves, pumps, fans, and slide rails.
Table of Contents
Introduction
Anomaly detection is a crucial technique for identifying unusual patterns in data, which can indicate malfunctions or other significant events. In industrial settings, detecting anomalies in machinery data can enable predictive maintenance and reduce downtime.
MTSA (Multiple Time Series Analysis) is a framework designed to simplify the implementation and replication of anomaly detection approaches, particularly for acoustic data. The framework provides a structured environment for developing, testing, and comparing different anomaly detection models, with a focus on replicability and ease of use.
Features
- Unified Framework: MTSA provides a modular and extensible structure for developing and testing anomaly detection models on multiple time series.
- State-of-the-Art Implementations: The framework includes implementations of three state-of-the-art anomaly detection approaches: Hitachi, RANSynCoders, and GANF.
- Enhanced Pipelines: RANSynCoders and GANF pipelines have been enhanced with feature extraction based on Mel-Frequency Cepstral Coefficients (MFCC), improving their performance on acoustic data.
- Comparative Analysis: MTSA enables easy comparison of different approaches, with a focus on acoustic data from industrial machinery.
Installation
To install MTSA, clone the repository and install the necessary dependencies:
git clone https://github.com/your-username/MTSA.git
cd MTSA
pip install -r requirements.txt
Usage
MTSA can be used to run anomaly detection models on acoustic data from industrial machines. Find an example here.
if you have problems with google colab please try running it:
%pip install --upgrade google-colab
Implemented Approaches
MTSA includes the following anomaly detection approaches:
- Hitachi: A robust approach tailored for industrial anomaly detection.
- RANSynCoders: A state-of-the-art model enhanced with MFCC for better performance on acoustic data.
- GANF: A generative adversarial network approach, also enhanced with MFCC.
- Isolation Forest: An approach using ITrees to isolate anomalies, also enhanced with MFCC.
Metadata
Release files for mtsa 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| mtsa-0.1.0.tar.gz | 40.1 kB | With provenance | Details for mtsa-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| mtsa-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for mtsa-0.1.0-py3-none-any.whl |
Total release size: 92.6 kB
Release files / mtsa-0.1.0.tar.gz
| Download URL | mtsa-0.1.0.tar.gz |
|---|---|
| Size | 40.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
b075e6a10f671814cca2d5816615dc6dcb2935d3f44b63b2341283f5560c314a
|
|
BLAKE2b-256 checksum How to use checksums |
79cbcdc0e0f63a967975e631d3fc88f4406c5c2cee516655d03f3a649c0eb445
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Feb 21, 2025.
Transparency logRelease files / mtsa-0.1.0-py3-none-any.whl
| Download URL | mtsa-0.1.0-py3-none-any.whl |
|---|---|
| Size | 52.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
c1bfec7c2405689ca505c68ee72c84ac74b0ac38ef9debc2c531a9a9c3216b67
|
|
BLAKE2b-256 checksum How to use checksums |
1dee3906bfcc040790cce5d7f705906397892bd93b84481373fb0fde0bf71d82
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Feb 21, 2025.
Transparency logSecurity for mtsa 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
Both files in this release have been uploaded with provenance metadata.
Attestation for mtsa-0.1.0.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Feb 21, 2025.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.