ANOMALY and EVENT DETECTION
without FALSE-Positives

We all love Watch-Dog systems,
but only when they bark on time.

About F-A-K-E tail

Fault-tolerAnt Kpi Evaluation (FAKE) is a generic detection system for anomaly detection and troubleshooting designed to minimize the number of false-positive alerts.

Long time ago, Aesop (Esopo) wrote the well-known fable called "The Boy Who Cried Wolf".
The story learns that if you make false claims, then they won't believe even if you tell the truth.

Img
Img

When KPI are still Raw-Data

Most companies define Key Performance Indicators (KPIs) for the analysis of processes. For example, a KPI might be the average number of requests to a service per user/hour.

KPIs are used to represent big-data in a compact and user-friendly manner, but most KPIs are still very similar to the original data and inherits its problems in terms of mathematical function behavior.

Application Scenarios

The FAKE project started from the background experience of the EVoKE project, an anomaly detection tool designed for wide 2G, 3G, 4G, 5G TLC networks.

FAKE extends the application scenario to different fields such as Computer/IoT networks, environmental monitoring (museums, smart-building, structural health), farming. Moreover, the false-positive reduction techniques have been improved.

Img

Key Features

FAKE is a general purpose system that can be customized and calibrated for specific application scenarios.
KPIs and business rules are defined by Domain experts.

Plug and Play

FAKE natively integrates Learn-By-Example techniques for simplifying the training (setup) phase.

Fast !

All components of FAKE system are designed to be (quasi) real-time.

Multiple Formats

Not only tabular data! FAKE-Imaging plugin allow to use images (e.g. from video cameras) as data-source.

Configurable

FAKE detection system is designed like an onion. User might customize or disable each detection layer.

Learn and Improve

FAKE exploits user-feedback (e.g. correct/wrong detection) for improving further analyses.

Extendible

Users might tune parameters of each detector, but also add new components written in Java, Scala or Python.

Scalable

The FAKE system can run on an isolated node or in a clustered/cloud environment both.

Easy Integration

It is very simple to connect FAKE to real-world data-source and HW processes to be monitored.

Alerts mean nothing when you can't trust them

The FAKE detection system is designed to minimize the number of false-positive detections.

go to top

Main Techniques

FAKE detection system is designed like an onion.
Each layer identifies, filters and characterizes events by applying many different algorithms at the same time.

Statistical Analysis

exploit robust indicators for outlier detection

Data Regression

exploit Support Vector Regression and Gaussian processes

Training Set optimization

exploit mathematical techniques to select and minimize training set without loosing information

Prediction

train multiple-input multiple-output prediction models (e.g., Kriging)

Recurrent Neural Networks

exploit RNN for time-series regression and characterization

Spiking Neural Networks

apply third-generation NN for detecting events in time and space

Compressive Sensing

apply CS techniques for lossless representation and compression of data streams

Reinforced Learning

the system keep learning and improving accuracy from live data and operators feedback