Abstract: Disclosed are a system and method for training and managing a prediction model, and a master apparatus and a slave apparatus for the same. there is provided a system for training and managing a prediction model, the system including a master apparatus configured to generate a prediction model, train the prediction model, and obtain the trained prediction model; and a slave apparatus configured to collect data, transmit the data to the master apparatus, receive the prediction model or the trained prediction model from the master apparatus, and operate based on the prediction model or the trained prediction model. The master apparatus is further configured to generate the prediction model or train the prediction model based on the data transmitted from the slave apparatus.

Abstract: Provided are an energy management method in a self-powered network, and an energy management apparatus and an energy management system to perform the method. The energy management system includes a first energy management unit and at least one second energy management unit configured to be communicable with the first energy management unit. Here, the at least one second energy management unit may acquire observation data using collected data and may transmit the acquired observation data to the first energy management unit, the first energy management unit may acquire a global neural network parameter by performing learning based on the observation data and may transfer the neural network parameter to the second energy management unit, and the at least one second energy management unit may determine an energy dispatch by performing learning using the neural network parameter and the collected data.

Abstract: According to a technical aspect of the invention, there is provided a multiple unmanned aerial vehicles navigation optimization method is performed at a ground base station which operates in conjunction with unmanned aerial vehicles-base stations which are driven by a battery to move and cover a given trajectory point set, the multiple unmanned aerial vehicles navigation optimization method including: calculating an age-of-information metric by receiving an information update from the unmanned aerial vehicles-base stations through communication, when the ground base station is present within a transmission range of the unmanned aerial vehicles-base stations; setting conditions of a trajectory, energy efficiency, and age of information of each of the unmanned aerial vehicles-base stations; and executing Q-learning for finding a trajectory path policy of each of the unmanned aerial vehicles-base stations, so as to maximize total energy efficiency of an unmanned aerial vehicles-base station relay network to whic

Abstract: The present disclosure relates to a maritime communication system based on low earth orbit satellites and an unmanned aerial vehicle. The maritime communication system according to one embodiment may include one or more maritime users, one or more satellites connected to a network operator, and an unmanned aerial vehicle (UAV) for relaying communication between the maritime users and the satellites.

Abstract: The invention relates to a UAV arrangement device based on machine learning for maximizing communication throughput, the UAV arrangement device including: a communication module unit that receives location information and communication demand information of a user and transmits UAV arrangement information; a user information unit that stores and analyzes the location information and the communication demand information of the user; a UAV information unit that stores basic UAV information including UAV communication throughput; and a clustering algorithm modeling unit that calculates a location at which communication throughput is maximized, with a clustering algorithm based on the location information and the communication demand information of the user.

Abstract: The present disclosure relates to a technical idea for managing radio and computing resources in coexistence edge computing. A method of allocating radio and computing resources in coexistence edge computing according to one embodiment may include a step of formulating a resource allocation problem for two different entities with conflicting relationships in minimizing latency as a generalized Nash equilibrium problem (GNEP), a step of converting the formulated GNEP into a Nash equilibrium problem (NEP), and a step of allocating resources on a penalty basis for the converted NEP.

Abstract: Provided are an energy management method in a self-powered network, and an energy management apparatus and an energy management system to perform the method. The energy management system includes a first energy management unit and at least one second energy management unit configured to be communicable with the first energy management unit. Here, the at least one second energy management unit may acquire observation data using collected data and may transmit the acquired observation data to the first energy management unit, the first energy management unit may acquire a global neural network parameter by performing learning based on the observation data and may transfer the neural network parameter to the second energy management unit, and the at least one second energy management unit may determine an energy dispatch by performing learning using the neural network parameter and the collected data.

Abstract: Provided is an evolving symptom-disease prediction system for a smart healthcare decision support system according to the present disclosure. The symptom-disease prediction system may include a client configured to transmit data related to symptom information; and a server configured to detect and predict a disease based on the data related to the symptom information. The server may include a processor configured to, when a disease predicted based on a machine learning model is determined as an existing predicted disease and a new disease, update the machine learning model by aggregating the machine learning model with other models through a model aggregation process shared with other medical institutions.

Abstract: Disclosed is a technical idea of constructing energy-efficient communication and computation resource allocation framework for Enhanced Mobile Broadband (eMBB) and Ultra-Reliable Low-Latency Communication (URLLC) in 5G or higher networks. More particularly, the present disclosure relates to a technology of constructing social block coordinate descent (BCD)-based energy-efficient communication and computation resource allocation framework to address optimization problems related to restriction of eMBB users, reliability of URLLC traffic, and resource block allocation for eMBB user restriction.

Abstract: According to a technical aspect of the invention, there is provided a multiple unmanned aerial vehicles navigation optimization method is performed at a ground base station which operates in conjunction with unmanned aerial vehicles-base stations which are driven by a battery to move and cover a given trajectory point set, the multiple unmanned aerial vehicles navigation optimization method including: calculating an age-of-information metric by receiving an information update from the unmanned aerial vehicles-base stations through communication, when the ground base station is present within a transmission range of the unmanned aerial vehicles-base stations; setting conditions of a trajectory, energy efficiency, and age of information of each of the unmanned aerial vehicles-base stations; and executing Q-learning for finding a trajectory path policy of each of the unmanned aerial vehicles-base stations, so as to maximize total energy efficiency of an unmanned aerial vehicles-base station relay network to whic

Abstract: The invention relates to a UAV arrangement device based on machine learning for maximizing communication throughput, the UAV arrangement device including: a communication module unit that receives location information and communication demand information of a user and transmits UAV arrangement information; a user information unit that stores and analyzes the location information and the communication demand information of the user; a UAV information unit that stores basic UAV information including UAV communication throughput; and a clustering algorithm modeling unit that calculates a location at which communication throughput is maximized, with a clustering algorithm based on the location information and the communication demand information of the user.

Abstract: The present disclosure relates to a maritime communication system based on low earth orbit satellites and an unmanned aerial vehicle. The maritime communication system according to one embodiment may include one or more maritime users, one or more satellites connected to a network operator, and an unmanned aerial vehicle (UAV) for relaying communication between the maritime users and the satellites.

Abstract: The present disclosure relates to a technical idea for managing radio and computing resources in coexistence edge computing. A method of allocating radio and computing resources in coexistence edge computing according to one embodiment may include a step of formulating a resource allocation problem for two different entities with conflicting relationships in minimizing latency as a generalized Nash equilibrium problem (GNEP), a step of converting the formulated GNEP into a Nash equilibrium problem (NEP), and a step of allocating resources on a penalty basis for the converted NEP.

Abstract: Disclosed is a technical idea of constructing energy-efficient communication and computation resource allocation framework for Enhanced Mobile Broadband (eMBB) and Ultra-Reliable Low-Latency Communication (URLLC) in 5G or higher networks. More particularly, the present disclosure relates to a technology of constructing social block coordinate descent (BCD)-based energy-efficient communication and computation resource allocation framework to address optimization problems related to restriction of eMBB users, reliability of URLLC traffic, and resource block allocation for eMBB user restriction.

Abstract: The present disclosure relates to a method for generating an energy demand model by a multi-access edge server, the method including: a step a of receiving a task execution request signal including a bit value from a user; a step b of matching a task to one or more pre-classified groups using the bit value; a step c of extracting a feature of energy consumed to perform the task according to a criterion set differently for each group; a step of performing the steps a to c for one or more task execution request signals received from one or more users during a time period and generating an energy demand pattern for the time period using a feature of energy for one or more tasks performed during the time period; and a step of generating an energy demand model by time using one or more energy demand patterns by time and energy cost by time.

Abstract: The present invention relates to a delivery system, a delivery management system, a delivery management device, and a delivery management method, wherein the delivery system may comprise: a plurality of deliverer terminals corresponding to a plurality of deliverers, respectively; and a delivery management system which collects information required for delivery, and combines at least one of the plurality of deliverers on the basis of the information required for delivery to thereby determine an optimal route by which to deliver a parcel.

Abstract: Disclosed are an uplink resource allocation method and a cognitive small cell network system performing the method. In the method, a small cell manager collects an access request from a small cell user and forms a preference relationship for each small cell user. Then, sub-channel-specific transmission power for providing a maximum data transmission rate at the time of uplink transmission is calculated and the calculated sub-channel-specific transmission power information is transferred to the small cell user. Meanwhile, the small cell user forms all possible sub-channel-specific preference relations and thereafter, transmits the access request for each sub-channel having a maximum preference relationship to the small cell manager.

Abstract: The present invention relates to a method for transmitting content in a content-based network and, more particularly, to a content transmission method by which requested content is identified on the basis of a hash value of the requested content so as to be stored only in mapped routers, thereby preventing the same content from being duplicately stored in routers in a regional group such that various types of content can be distributed and stored, and a content request message is directly transmitted only to routers mapped to a hash value of requested content, on the basis of the hash value of the requested content, such that a traffic load, occurring due to the transmission of a content request message by a flooding scheme, can be reduced.

Abstract: A client and server system that performs a reinforcement learning-based encryption and decryption method according to an aspect of the present invention may include: a key management module configured to manage an encryption key required in performing an encryption and a decryption of data; a secret sharing module configured to perform a secret sharing of a threshold value for a lifetime and availability of the data; and a threshold estimation module configured to perform an estimation of the threshold value; and can improve the availability and security of data to satisfy user demands in a self-destructing environment for privacy protection.

Abstract: The present invention relates to a technology of forwarding interest parallel by adjusting a ratio of an interest packet requiring content depending upon a network state when a mobile device having a variety of interfaces is connected to various networks in a content-centric networking environment, thereby increasing a data transfer rate. An apparatus for controlling multipath interest forwarding according to an aspect of the present invention includes a weighted forwarding ratio administrator configured to generate an interest packet; a weighted forwarding ratio storage configured to record and maintain weighted forwarding ratios reflecting a transmission capacity of an interest packet per face; and a forwarding engine configured to control the generated interest packet to be transmitted via each of the faces based on the weighted forwarding ratios.