Con esta herramienta te facilitamos un acceso a todas las ofertas y demandas de tecnología europeas y a búsquedas de socios para participar en propuestas europeas de I+D publicadas en la red Enterprise Europe Network, pudiendo filtrar los resultados para facilitar las búsquedas más acordes con tus necesidades.

¿Quieres recibir estos listados de oportunidades de colaboración en tu correo de forma periódica y personalizada? Date de alta en nuestro Boletín

Para optimizar los resultados de la búsqueda, se recomienda utilizar términos en inglés.

Solución de detección de anomalías basada en aprendizaje profundo

Resumen

Tipo:
Oferta Tecnológica
Referencia:
TOKR20181004003
Publicado:
01/11/2018
Caducidad:
02/11/2019
Resumen:
Una pyme coreana ha desarrollado una solución de detección de anomalías que emite alertas en tiempo real al reconocer un patrón anormal. Esta solución, que utiliza varias fuentes de datos y un modelo basado en una red neuronal de aprendizaje profundo, identifica patrones anómalos y también hace uso de métodos basados en reglas. La empresa busca socios con el fin de establecer acuerdos de comercialización con asistencia técnica y licencia.

Details

Tittle:
Anomaly Detection Solution based on Deep Learning
Summary:
The Korean SME has developed an anomaly detection solution which provides alerts in real-time when it recognizes an abnormal pattern. It uses various types of data streams to a model based on deep learning neural network. The technology identifies the anomalous patterns by also leveraging on rule-based methods.

Therefore, the cooperation form sought is a commercial agreement with technical assistance, a license agreement.
Description:
The Korean SME has developed is an anomaly detection solution which provides alerts in real-time, when it recognizes an abnormal pattern. It uses various types of data streams to a model based on deep learning neural network. The technology identifies the anomalous patterns by also leveraging on rule-based methods.

The disadvantages of existing competing technologies are:
· Other rule-based methods require specific domain experts to develop rule sets and are not robust but fragile and unable to identify slightly different patterns
· Data-driven machine learning approaches require vectorization of data records and require the total data set to be stored if upgrades are carried out after deployment from the first if want to upgrade after deployment

System and method for the embodiment of this technology applying the neural network based method and rule-based approach, for example, the deformation of the biometric action knowledge space (Hierarchical Behavior Knowledge Space: HBKS) method and sensing the ideal pattern to the hybrid form can be provided.

Ideal pattern sensing system and method for processing data which the embodiment of this technology does not create from the digitization processing method (Unseen) adapting to the word embedding method can be provided.

The SME is seeking partners to conclude license agreement and commercial agreement to enter the international market. The company is open to all the type and size of partners.
Advantages and Innovations:
· Data Digitization: Convert non-digital data fields to digital vectors
· Time-series Modeling: Applying a neural network model reflecting time-series characteristics
· Hierarchical Behavioral Knowledge Space (HBKS): Storing the anomalous patterns identified by the administrator and applying them in real time. By storing the causes identified by the administrators, it becomes possible to explain the cause of similar phenomena in the future
· Combining a deep neural network and a rule-based model
· Not required labeling for learning data
· Supporting autolearning
Stage of Development:
Available for demonstration
IPs:
Patents granted

Partner sought

Type and Role of Partner Sought:
Type of partner sought
- SME, larger company, research institutions
Specific area of activity of the partner
- Artificial intelligence
Tasks to be performed by the partner sought
- commercial agreement with technical assistance, license agreement

Client

Type and Size of Client:
Industry SME 11-49
Already Engaged in Trans-National Cooperation:
No
Languages Spoken:
English

Keywords

Technology Keywords:
01003003 Artificial Intelligence (AI)