top of page

Based on Machine Learning
Anomaly
Detection

Welcome to the registration page of the upcoming webinar of KONsys Kft.

Let's discover how the latest machine learning-based solutions help in the effective identification and management of various anomalies occurring in energy supply systems.

Anomália detektáció 1.png

April 11

10:00 a.m

What the show is about:

We present how the latest machine learning-based solutions help in the effective identification and management of various anomalies and errors occurring in energy supply systems. We will learn how to predict energy consumption problems, minimize breakdowns and optimize operational efficiency by continuously analyzing the data.

Agenda

Duration: 60 minutes

1. Norbert Kovács: Introduction (5 minutes)

Welcome and greeting participants

A brief overview of the purpose and structure of the webinar

Brief introduction of the speakers and participants

2. Attila Baracskai: Anomalies occurring in energy supply systems (15 minutes)

The concept and importance of anomaly detection

Types and frequency of anomalies in energy supply systems

The impact and dangers of anomalies

3. Péter Forró: Operating principle of anomaly detection (10 minutes)

Data types and sources for analyzing anomalies in power supply systems

Basic methods and techniques for recognizing and detecting anomalies

4. Ádám Varga: Examples and practical approaches (15 minutes)

Presentation on a live system

Ways to detect anomalies

Methods of constructing anomaly models

5. Questions and answers (10 minutes)

6. Norbert Kovács: Conclusion and thanks (5 minutes)

Acknowledgment of participants and speakers

Mention of final thoughts and further actions

Our speakers

Atti_edited.jpg

Attila Baracskai

KONsys Kft
Executive responsible for software development

Péter Forró.jpg

Hot Peter

Moana Software
Software development engineer

Adam.jpg

Adam Varga

KONsys Kft

Software development and testing engineer

Sikeres regisztráció

Legal information:

KONsys Kft. - All rights reserved © 2024, Tax number: 13477266-2-08, Company registration number: 08 09 012984

bottom of page