Abstract:
The present invention relates to a deep-learning-based intrusion detection method, a system and a computer program for web applications, and more particularly, to a method, a system and a computer program for detecting whether the traffic is a hacker attack, based on an output from a deep neural network (DNN) model after setting network traffic flowing into a server farm as an input of the model. The present invention provides an effective intrusion detection system by utilizing deep neural networks in the form of complicated messages of the Web service protocol (hypertext transfer protocol (HTTP)), which is most general and representative for a company, among various application-layered services. In particular, the present invention provides a web application threat detection method, a system and a computer program implementing the same that are configured to determine security threats bypassing and intruding the detection scheme of the signature-based security system.
Abstract:
The present invention relates to underwater communication and, more particularly to a signal transmission method and device which configure and transmit physical channel information such that low-power control is performed in underwater communication. The present invention configures the physical channel information such that a reception node side can check through a combination of preambles whether a signal is provided to itself, when forward direction communication is performed in a centralized underwater communication network. Therefore, the present invention performs the control such that only a relevant reception node requiring data reception performs a demodulation operation, without requiring all reception nodes to always perform demodulation in a forward direction communication process. Through this process, many reception nodes do not perform unnecessary demodulation operations in the forward direction communication process, thereby providing an effect of preventing unnecessary power consumption.
Abstract:
The present invention provides an underwater communication system capable of efficiently communicating with a plurality of sensor nodes by using a limited frequency in the water. The present invention has a hierarchical structure in which one underwater base station control station manages a plurality of underwater base stations in the water, and each underwater base station within a plurality of underwater base stations centrally manages a plurality of underwater sensor nodes. Furthermore, the present invention enables efficient underwater communication the underwater environment by using different frequencies, when the underwater base station control station performs the underwater communication with the plurality of underwater base stations, and when the underwater base stations perform the underwater communication with the plurality of underwater sensor nodes.
Abstract:
The present invention relates to an underwater communication method capable of communicating with a plurality of sensor nodes within a limited frequency band. Underwater information communication of the present invention allocates an appropriate frequency to each sensor node according to the distance between a central node and the plurality of sensor nodes, and then, controls underwater communication between the central node and the plurality of sensor nodes using the allocated frequency. By virtue of such control, the present invention prevents the occurrence of an unusable sensor node which cannot smoothly perform underwater communication when the allocated frequency is unreasonable. Therefore, the present invention has the effect of enabling efficient underwater communication between a plurality of sensor nodes and a central node.
Abstract:
Provided are a three-dimensional mouse device using several body parts, and a marionette control system using the same. The three-dimensional mouse device includes: a support member that is worn on at least one of a head, a face, an arm, and a foot among body parts; an action recognition module that is mounted on the support member; and an action recognition module that is attached to the support member to sense a motion of the body parts and output a sensing signal to the action recognition module.