Signal Intelligence

Analyze large-scale time series data. Develop advanced analytics workflows with human in the loop. Transfer insights into actionable decisions.

Github Join Slack community

Analyze, Interact, Decide

The ecosystem of Sintel allows you to build advanced analytic workflows with human in the loop using the Machine Learning libraries,  RESTful APIs, and Visualization tools.

Code

from sigpro import SigPro
from sigpro.demo import (
  get_amplitude_demo,
  load_demo_primitives
)

data = get_amplitude_demo()

trans, aggre = load_demo_primitives()

sigpro = SigPro(
  transformations=trans,
  aggregations=aggre,
  keep_columns=True
)

sigpro.process_signal(data)

Code

from pyteller.data import load_data
from pyteller.core import Pyteller

train_data = load_data(
  'pyteller/data/AL_Weather_current.csv')
test_data = load_data(
  'pyteller/data/AL_Weather_input.csv')

pyteller = Pyteller(
  pipeline=('pyteller/pipelines/sandbox/'
            'LSTM/LSTM_offset.json'),
  pred_length=6, offset=1)

pyteller.fit(
  data=train_data,
  timestamp_col='valid', target_signal='tmpf',
  entity_col='station', entities='8A0')

pyteller.forecast(data=test_data)

Code

from orion.data import load_signal
from orion import Orion

train_data = load_signal('S-1-train')

orion = Orion(pipeline='lstm_dynamic_threshold')

orion.fit(train_data)

new_data = load_signal('S-1-new')

orion.detect(new_data)

Code

from draco.demo import load_demo
from draco.pipeline import DracoPipeline
from sklearn.model_selection import train_test_split

target_times, readings = load_demo()

train, test = train_test_split(
  target_times, test_size=0.25, random_state=0)

test_targets = test.pop('target')

draco = DracoPipeline(
  'classes.normalize_dfs_xgb_classifier')

draco.fit(train, readings)

draco.predict(test, readings)

Code

from orion.benchmark import benchmark

pipelines = [
  'arima',
  'lstm_dynamic_threshold'
]

signals = ['S-1', 'P-1']

metrics = ['f1', 'accuracy', 'recall', 'precision']

benchmark(
  pipelines=pipelines,
  datasets=signals,
  metrics=metrics,
  rank='f1'
)

Use Cases

Sintel have been demonstrated in the following application domains.

Satellite

Satellite

Monitor satellite telemetry and solve an unsupervised time series anomaly detection problem.

Wind Turbine

Wind Turbine

Monitor wind energy production systems and solve a time series classification problem.

Water

Water

Monitor water distribution and delivery networks and address time series classification and regression problems.

Open Source

Sintel is an ecosystem for time series processing, labeling, modeling, benchmarking, and user interactions. Explore the ecosystem of open source libraries supporting the Sintel. Each can be used as a standalone package for particular needs.

Draco

Draco

Classifies time series segments into particular categories.

gpe

gpe

Creates labeling functions to search occurrences of specific types of events in the past.

ml-stars

ml-stars

Stores a collection of pipelines that will be used by Orion, Draco, and Pyteller.

MTV

MTV

Integrates a suite of visualization techniques to support complex analytic workflow with human-in-the-loop

Orion

Orion

Identifies anomalous time series segments.

pyteller

pyteller

Predicts future values by analyzing past trends.

SigPro

SigPro

Featurizes time series with domain knowledge encoded for machine learning uses.

Sintel

Sintel

Enables your team to build human-in-the-loop analytics workflow with predefined RESTFul APIs and MongoDB Schema.

TSGym

TSGym

Benchmarks machine learning models for different tasks.

No results found

Sintel Research

Sintel: A Machine Learning Framework to Extract Insights from Signals

Sintel: A Machine Learning Framework to Extract Insights from Signals

Sarah Alnegheimish, Dongyu Liu, Carles Sala, Laure Berti-Équille, Kalyan Veeramachaneni

SIGMOD ACM SIGMOD/PODS International Conference on Management of Data, 2022

Download: [pdf] [bib] [code]

MTV: Visual Analytics for Detecting, Investigating, and Annotating Anomalies in Multivariate Time Series

MTV: Visual Analytics for Detecting, Investigating, and Annotating Anomalies in Multivariate Time Series

Dongyu Liu, Sarah Alnegheimish, Alexandra Zytek, Kalyan Veeramachaneni

CSCW The ACM Conference on Computer Supported Cooperative Work, 2022

Download: [pdf] [bib] [code] [video]

TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networks

TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networks

Alexander Geiger, Dongyu Liu, Sarah Alnegheimish, Alfredo Cuesta-Infante, Kalyan Veeramachaneni

BigData IEEE International Conference on BigData, 2020

Download: [pdf] [bib] [talk] [code] [news] [blog] | 🏆 GitHub stars > 600

Meet Our Team

Great things are never done by one person. They're done by a team of excellent people.

Dongyu Liu

Dongyu Liu

Postdoc (Project Lead)

DAI Lab, MIT

Sarah Alnegheimish

Sarah Alnegheimish

MS Student (Project Co-Lead)

DAI Lab, MIT

Kalyan Veeramachaneni

Kalyan Veeramachaneni

Principal Investigator

DAI Lab, MIT

Frances Hartwell

Frances Hartwell

MS Student

DAI Lab, MIT

Lawrence Wong

Lawrence Wong

MS Student

DAI Lab, MIT

Hugo Ramirez

Hugo Ramirez

UROP Student

DAI Lab, MIT

LAURE BERTI-ÉQUILLE

LAURE BERTI-ÉQUILLE

Visiting Professor

DAI Lab, MIT

Plamen Valentinov Kolev

Plamen Valentinov Kolev

Software Engineer

DAI Lab, MIT

Carles Sala

Carles Sala

Software Engineer

DAI Lab, MIT

Sergiu Ojoc

Sergiu Ojoc

Frontend Developer

Iulia Ionescu

Iulia Ionescu

UI/UX Designer

Arash Akhgari

Arash Akhgari

Animator & Graphic Designer

Alumni

MICHAELA HENRY

MICHAELA HENRY

Program Coordinator

DAI Lab, MIT

SKYLAR EISKOWITZ

SKYLAR EISKOWITZ

MS Student

DAI Lab, MIT

ALEX GEIGER

ALEX GEIGER

Visiting Student

DAI Lab, MIT

Our Sponsors


Address

Data to AI Lab
MIT Stata Center
32 Vassar St, Room 32-D712
Cambridge, MA 02139
Email
sintel@mit.edu