Electronics and Telecommunications Research Institute

Myung Eun Kim

Jin Chul Choi

Sang Yeoun Lee

Hyunseok Kim

Young Sung Son

Seonghyun Kim

Soonyong Song

Donghun Lee

Jongkwon Son

Ingook Jang

Hwan Mook Kim

Tae Joon Park

Kang Bok Lee

Jong Hyun Park

Hoe Sung Yang

Sang Gi Hong

Hyo Chan Bang

Dong Beom Shin

Dong Il Seo

Myung Nam Bae

Sun Jin Kim

Ji Hun Jeon

Hye Sun Lee

Provided is a Bluetooth Low Energy (BLE) communication module that supports a dynamic multi-link to configure a wireless ad hoc network. The BLE communication module includes a master configured to scan an advertising message transmitted from a slave of another BLE communication module and a slave connected to the master through an internal interface and configured to receive a scan message transmitted from a master of the other BLE communication module and transmit an advertising message corresponding to the scan message. Each of the master and the slave has a predetermined multi-port and a routing table for processing transmitted or received data.

BLE communication module and unmanned moving object supporting dynamic multi-link to configure wireless ad hoc network, and method thereof

A method and an apparatus for exclusive reinforcement learning are provided, comprising: collecting information of states of an environment through the communication interface and performing a statistical analysis on the states using the collected information; determining a first state value of a first state among the states in a training phase and a second state value of a second state among the states in an inference phase based on analysis results of the statistical analysis; performing reinforcement learning by using one reinforcement learning unit of a plurality of reinforcement learning unit which performs reinforcement learnings from different perspectives according to the first state value; and selecting one of actions determined by the plurality of reinforcement learning unit based on the second state value and applying selected action to the environment.

Method and apparatus for reinforcement machine learning

An apparatus and method for abnormal situation detection are disclosed. An abnormal situation detection apparatus can map first sensor data among sensor data transmitted from a plurality of sensors into a vector value, convert it into first situation information in the form of an image pattern, and generate a learning model using the first situation information and an abnormal situation reference range. In addition, the abnormal situation detection apparatus can convert second sensor data among sensor data transmitted from a plurality of sensors into a form that can be input to the learning model, and determine whether an abnormal situation occurs by applying the converted second data to the learning model.

Apparatus and method for abnormal situation detection

A mobile ad-hoc routing apparatus includes a first communication module and a second communication module configured to transmit and receive data through a first communication band and a second communication band, respectively, a memory configured to store a program for transmitting and receiving the data, and a processor configured to execute the program stored in the memory, wherein when the program is executed, the processor receives first control information broadcast by one or more neighboring nodes via the first communication module and stores the first control information in the memory, wherein the first control information includes current position and communication status information of the neighboring node, the processor updates information on the neighboring node on the basis of the first control information, generates packet forwarding information which includes information on a node which currently allows packet data to be transmitted based on the updated information on the neighboring node, and stores the generated packet forwarding information in the memory, and the processor determines a subsequent node which allows the packet data to be transmitted to a destination node on the basis of the packet forwarding information and transmits the packet data to the subsequent node via the second communication module.

Mobile ad-hoc routing apparatus and method

Provided are a system and method for coping with encrypted harmful traffic in hybrid IPv4/IPv6 networks. The system includes: an encryption key manager collecting encryption key information from a user terminal connected to the hybrid IPv4/IPv6 networks, and storing and managing the information in an encryption key database; an encryption traffic collector collecting encrypted traffic from traffic in the hybrid IPv4/IPv6 networks; an encryption key searcher searching for an encryption key used to decrypt the encrypted traffic from the encryption key database using a source IP address and a destination IP address of the encrypted traffic; a harmful traffic determiner decrypting the encrypted traffic using the encryption key and determining whether the decrypted traffic is harmful traffic; and an encryption traffic processor, if the decrypted traffic is determined to be harmful traffic, blocking the harmful traffic and, if the decrypted traffic is determined to be normal traffic, encrypting the normal traffic, and transferring the encrypted traffic to a user terminal corresponding to the destination IP address, thereby detecting and blocking an attack pattern using the encrypted harmful traffic in hybrid IPv4/IPv6 networks which cannot be detected by a conventional firewall system and more effectively protecting the networks.

System and method for coping with encrypted harmful traffic in hybrid IPv4/IPv6 networks

Growing community of inventors

Daejeon, South Korea

Myung Eun Kim