Abstract: Provided are a neural network device and method for rapidly finding a solution to a quadratic assignment problem (QAP). The neural network device includes a memory and a processor configured to generate logits for locations and facilities on the basis of a QAP instance stored in the memory, generate assignment matrices for the locations and the facilities through deep learning-based parallel processing of the generated logits, and find a solution to the QAP by calculating costs on the basis of the generated assignment matrices.

Abstract: Provided is a system for predicting disease based on biosignal data and medical knowledge base convergence. The system includes a first system unit configured to receive, from a user terminal, biosignal data collected from at least one sensor for sensing a biosignal, and calculate a disease score from the biosignal data based on a pre-trained prediction model, a second system unit configured to provide medical knowledge data for the first system unit, analyze a query input from the user terminal to provide a corresponding response, and augment the medical knowledge data based on the query and response; and a unified distributed repository that includes a database for enqueuing the biosignal data, a manager database for storing additional information of a user, and a medical knowledge base for storing predetermined medical knowledge data.

Abstract: A method of calculating a comprehensive disease index (CDI) is disclosed. The method includes analyzing pieces of medical data to calculate a disease risk value, analyzing pieces of vital data and vital data mapped to standard clinic guideline data among the pieces of vital data to calculate a disease severity value, and analyzing the disease risk value, the disease severity value, and medical knowledge information obtained from a medical knowledge base to calculate the CDI.

Abstract: Provided is a system for predicting disease based on biosignal data and medical knowledge base convergence. The system includes a first system unit configured to receive, from a user terminal, biosignal data collected from at least one sensor for sensing a biosignal, and calculate a disease score from the biosignal data based on a pre-trained prediction model, a second system unit configured to provide medical knowledge data for the first system unit, analyze a query input from the user terminal to provide a corresponding response, and augment the medical knowledge data based on the query and response; and a unified distributed repository that includes a database for enqueuing the biosignal data, a manager database for storing additional information of a user, and a medical knowledge base for storing predetermined medical knowledge data.

Abstract: Provided are an infrastructure apparatus and method of providing collaboration between thing devices. Since a plurality of thing devices located in a specific space share an experience where the plurality of thing devices have performed a collaboration service, each of the thing devices may search for peripheral thing devices for performing the collaboration service without intervention of a center server and may generate a collaboration group including the found thing devices, and tasks for performing through negotiation may be autonomously distributed to the thing devices included in the collaboration group, thereby providing autonomous collaboration between the thing devices.

Abstract: Provided is an apparatus and method for hierarchically providing a context-aware service by real-time user behavior analysis, autonomously collecting information required for the context-aware service using a smart device, and autonomously configuring the service. The apparatus for hierarchical context awareness and device autonomous configuration through a real-time user behavior analysis includes a fast context aware engine configured to receive user data, infer a context, and provide a primary response context aware service, and a fine context aware engine configured to provide a secondary response context aware service using context information inferred by the fast context aware engine and machine learning prediction data, wherein the fast context aware engine reconfigures a resource of a smart device to suit a service.

Abstract: According to a sensor network system and a method for processing sensor data, a sink node collects sensor data from sensor nodes, performs a prediction algorithm which is the same as a prediction algorithm performed in the sensor node to obtain a prediction value, when a sensing value is received from the sensor node, updates the prediction value to the sensing value, stores the sensing value as sensor data, determines whether the sensor node is a representative node when the sensing value is not received from the sensor node, and stores the prediction value as sensor data if the sensor node is the representative node, and corrects the prediction value based on the sensing value of a representative node and stores the corrected prediction value as sensor data if the sensor node is not the representative node.

Abstract: Provided are an infrastructure apparatus and method of providing collaboration between thing devices. Since a plurality of thing devices located in a specific space share an experience where the plurality of thing devices have performed a collaboration service, each of the thing devices may search for peripheral thing devices for performing the collaboration service without intervention of a center server and may generate a collaboration group including the found thing devices, and tasks for performing through negotiation may be autonomously distributed to the thing devices included in the collaboration group, thereby providing autonomous collaboration between the thing devices.

Abstract: A device and method for controlling lighting based on an illuminance model. The method for controlling lighting based on an illuminance model includes modeling actual illuminance measured by one or more illuminance measurement devices; generating a lighting profile based on the illuminance model; and controlling one or more lighting devices for each lighting scene according to the generated lighting profile.

Abstract: A device and method for controlling lighting based on an illuminance model. The method for controlling lighting based on an illuminance model includes modeling actual illuminance measured by one or more illuminance measurement devices; generating a lighting profile based on the illuminance model; and controlling one or more lighting devices for each lighting scene according to the generated lighting profile.

Abstract: An apparatus and method for processing a path management packet is provided, the method including determining whether a router for processing a received path management packet is a storing node, and when the router is determined to be a storing node, controlling the path management packet to be stored in a routing table, or when the router is determined to be a non-storing node, failing to store the path management packet in the routing table and controlling the path management packet to be transmitted to a subsequent node.

Abstract: According to a sensor network system and a method for processing sensor data, a sink node collects sensor data from sensor nodes, performs a prediction algorithm which is the same as a prediction algorithm performed in the sensor node to obtain a prediction value, when a sensing value is received from the sensor node, updates the prediction value to the sensing value, stores the sensing value as sensor data, determines whether the sensor node is a representative node when the sensing value is not received from the sensor node, and stores the prediction value as sensor data if the sensor node is the representative node, and corrects the prediction value based on the sensing value of a representative node and stores the corrected prediction value as sensor data if the sensor node is not the representative node.

Abstract: An apparatus and method for processing a path management packet is provided, the method including determining whether a router for processing a received path management packet is a storing node, and when the router is determined to be a storing node, controlling the path management packet to be stored in a routing table, or when the router is determined to be a non-storing node, failing to store the path management packet in the routing table and controlling the path management packet to be transmitted to a subsequent node.

Abstract: Provided are a communication method and system for sensor network. In reporting event occurrence in a real-time sensor network application, a cycle time is divided into an event announcement period and a data transmission period to provide real-time transmission performance and energy efficiency. Each of the periods is again divided into the number of slots equal to the maximum depth of a network. Respective nodes sequentially operate according to their depths in a routing tree during the event announcement period to receive the signal transmitted from the lower node. To remove sleep delay, a slot next to the signal reception slot becomes a signal transmission slot. A node sensed an event transmits a signal informing event occurrence during its signal transmission slot, and this signal includes only the address of the transmission node. When a signal does not exist in the event announcement period, no traffic occurs in the data transmission period and the upper nodes maintain a sleep state.

Abstract: Provided are an energy-efficient communication method in a group information-based sensor network and a sensor network system using the method. A group exchanges group information and data with another group in order to provide an application service through inter-group cooperation in a sensor network. In this process, a target group is discovered, a communication path is established, and inter-group communication cycle information for energy-efficient communication is transmitted. On the basis of the group information and the communication cycle information, it is possible to minimize the network resource consumption and provide an energy-efficient inter-group communication method.

Abstract: An energy control apparatus and method using a usage property of an electronic device. The energy control method may include: setting a total power consumption to be less than a predetermined threshold; verifying a usage property for each electronic device when a collected total power consumption exceeds the threshold; calculating a scheduled end time based on the average usage time of each remaining electronic device excluding, from among operating devices, an electronic device of which power-off is unavailable; verifying a remaining electronic device excluding an electronic device of which scheduled end time is less than the threshold; controlling a temporarily stoppable electronic device to be temporarily stopped; controlling a power adjustable electronic device to decrease a power consumption when the total power consumption exceeds the threshold; and starting the temporarily stopped electronic device at a point in time when the total power consumption decreases to be less than the threshold.

Abstract: The present invention relates to a method and system for communication in an application field that may communicate with a sensor or a computer incorporated in an object or an environment to collect information about an object or an environment associated with the object, or process the information to semantic information to be shared and provided to a user or the object, and may recognize and determine a surrounding circumstance independently and without a command from an external source, thereby providing an intended application service.

Abstract: A reception station and a method for operating the reception station that may receive data using a multicast address from a transmission station are provided. The reception station may include an interface to receive a data packet including a multicast address from a transmission station, and a processor to distinguish a group address and a service address from the multicast address, and to maintain a reception of the data packet when a group address and a service address that are respectively identical to the distinguished group address and the distinguished service address are found from a database.

Abstract: Provided is an apparatus and method for managing a power equipment in an advanced metering infrastructure (AMI) network included in a smart grid network. According to an aspect of the present invention, an apparatus and method for managing a power equipment in an AMI network may provide a load control environment enabling a power equipment to declare an opt-out when another power equipment declares an opt-out by providing a list of power equipments included in a load control group in response to a power equipment declaring an opt-out of the load control group so as to process an opt-out of a power equipment selected from the list.

Abstract: Provided are an AMI gateway apparatus and method for processing large AMI data and an application profile. The AMI gateway apparatus and method are associated with collecting meter data of smart meters measuring the amount of electricity or the like and transmitting the meter data to an AMI server. Disclosed is a method of reducing an ID type and a method of minimizing meter data to reduce the transmission rate of large AMI data including an ID value and meter data. A method of setting a gateway ID value according to locations and zones is also provided. Those three methods achieve the efficient transmission of large AMI data to an AMI server and is applicable to various gateway apparatuses processing various application profiles such as an HA profile controlling and sensing home appliances, an SE profile providing an AMI service, a TA profile providing mobile services or the like.