Abstract: Provided are a method and a system for determining a model output direction on the basis of heat dissipation characteristic analysis for stabilizing output of metal 3D printing.

Abstract: A thermal-analysis-based output stabilization method and system for improving 3D printing output reliability are provided. The thermal-analysis-based output stabilization method according to an embodiment of the present invention comprises steps in which: an output stabilization system performs first stacking thermal analysis on a plurality of residual heat quantity review specimens for which a process range corresponding to normal output quality is set; the output stabilization system performs second stacking thermal analysis on an actual stacked product on the basis of the first stacking thermal analysis result in the same manner as the first stacking thermal analysis method; and the output stabilization system performs stability review on the stacking result of the stacked product on the basis of the second stacking thermal analysis result.

Abstract: Provided is a deep learning-based panoptic segmentation accelerated processing technique using a complexity-based RPN skip method. An image segmentation system includes: a first processing unit configured to extract dynamic objects in an instance segmentation method by using an extracted feature; a calculation unit configured to control to skip some areas of the feature extracted at the network by the first processing unit, on the basis of complexity of the input image; a second processing unit configured to extract static objects in a semantic segmentation method by using the feature extracted at the network; and a fusion unit configured to fuse a result of extracting by the first processing unit and a result of extracting by the second processing unit. Accordingly, the panoptic segmentation method can be easily performed even in an embedded environment by reducing complexity for panoptic segmentation processing by reducing a calculation burden.

Abstract: A system evaluates residential satisfaction of residents living in a building, based on preferred sections of the residents predicted using personal tendencies of the residents and sensing data collected through sensors in the building. The system may include a server that evaluates the residential satisfaction of the residents by analyzing a correlation between the sensing data and residential satisfaction information obtained from the survey conducted through a communication manner including the user terminals, and controls an air conditioning system in the building of a control target by predicting a feature-based preferred section of the users through random forest model learning.

Abstract: A haptic effect transmission method for providing real-time immersive content according to the present invention includes executing participatory content in which one or more users participate, collecting motion information of the users participating in the participatory content through a haptic device, multiplexing the motion information with video and audio files of the participatory content to obtain a multiplexed file, and demultiplexing the multiplexed file and providing the demultiplexed file to a display device and a haptic device of a client terminal.

Abstract: Provided are a method for segmenting sign language into morphemes, a method for predicting morpheme positions, and a method for augmenting data. A system for analyzing sign language according to an embodiment of the present invention comprises: a recognition unit which recognizes key points of a speaker from a sign language video; and a prediction unit which inputs the recognized key points into an artificial intelligence model, segments the sign language into morphemes, and predicts position information of the segmented morphemes. Accordingly, by recognizing the morphemes of the sign language video frame by frame on the basis of a skeletal model and thereby segmenting the sign language into morphemes and predicting morpheme positions, it is possible to lay the foundations for accurate sign language translation.

Abstract: A film for wrapping including a heat shrinkable film shrinkable when the heat shrinkable film reaches a predetermined temperature, and a capsule layer formed at one surface of the heat shrinkable film while including a plurality of microcapsules is disclosed. Electrophoretic particles are included in the microcapsules. Accordingly, a color or text represented at the film for wrapping is variable.

Abstract: An energy harvesting system includes a plurality of energy converters connected to multiple ambient energy sources, respectively, receiving energy from the multiple ambient energy sources, and converting the received energy into electrical energy. The system also includes an electrical energy buffer receiving and collecting electrical energy from the energy converters, and combining the collected electrical energy to have a predetermined power level and a constant voltage converter receiving the combined electrical energy from the electrical energy buffer, and converting the received electrical energy into driving power of a power level usable by a load. The system further includes an electrical energy storage receiving the driving power from the constant voltage converter, storing the received driving power, and providing the stored driving power to the load.

Abstract: Provided is a switch having a structure having an excellent isolation characteristic even without a limiter in an ultrahigh frequency hand used for a military component. A switch according to an embodiment of the present invention comprises: multiple transistors which are connected in parallel to a path from an input terminal toward an output terminal and perform switching; and a first transmission line provided between the input terminal and a node on a path to which a first transistor is connected. By the present invention, switching can be performed in an ultrahigh frequency such as W-band while a GaN transistor is used, an insertion loss is low, an isolation characteristic is excellent, and eventually efficiency of an ultrahigh frequency circuit can be further enhanced.

Abstract: There are provided a system and a method for setting a synchronization agent. A system for setting an optimal synchronization agent according to a workload according to an embodiment includes: a data integration device configured to integrate and store data which is collected through a collection agent; an agent management server configured to manage the collection agent that periodically polls data from a data source and transmits the data to the data integration device; and an agent setting automation device configured to set an optimal agent set value related to collection and transmission of data of the collection agent.

Abstract: There are provided a method and a system for selecting an optimal synchronization broker for each workload. A system for selecting an optimal synchronization broker for each workload according to an embodiment includes: a storage unit including a database that contains specialist recommendation information including information on a correct protocol that is recommended by a specialist with respect to a service specification and data transmission requirements; and a processor configured to determine an optimal in-bound protocol and an optimal out-bound protocol according to the data transmission requirements through a decision tree model that is trained by using the specialist recommendation information as training data.

Abstract: A method and a system for providing a domain-based process framework are provided. The method for providing a domain-specific process framework, according to one embodiment of the present invention, comprises steps in which: a process framework provision system generates a process model on the basis of a pre-stored meta-model (primitive) and a relationship model (relation); and the process framework provision system distributes the generated process model. Therefore, a process framework capable of reflecting domain knowledge is introduced so that different business processes between companies can be normalized by domain.

Abstract: There is provided a cooperative driving control method based on a vehicle security status. The cooperative driving method according to an embodiment includes: identifying a security status of a cooperative driving target vehicle; determining a cooperative driving strategy according to the identified security status; and controlling driving according to the determined cooperative driving strategy. Accordingly, cooperative driving may be performed or excluded based on a security status of a target vehicle, so that an accident may be prevented from being caused by cooperative driving with a problematic vehicle, and safety of a driver and an occupant may be guaranteed.

Abstract: There are provided a method and an apparatus for cloud management, which selects optimal resources based on graphic processing unit (GPU) resource analysis in a large-scale container platform environment. According to an embodiment, a GPU bottleneck phenomenon occurring in an application of a large-scale container environment may be reduced by processing partitioned allocation of GPU resources, rather than existing 1:1 allocation, through real-time GPU data analysis (application of a threshold) and synthetic analysis of GPU performance degrading factors.

Abstract: There are provided an apparatus and a method for reconstructing a 3D human object based on a monocular image through depth image-based implicit function learning. A 3D human object reconstruction method according to an embodiment includes: predicting a double-sided orthographic depth map from a front perspective color image of a human object; predicting a signed distance (SD) regarding points on a 3D space from the predicted double-sided orthographic depth map; and reconstructing a 3D human object by using the predicted SD. Accordingly, a human object and details can be naturally reconstructed with respect to not only an area visible through a front perspective color image of the human object but also an invisible area.

Abstract: Provided is a power transmission and reception system and a power transmission and reception system method capable of simultaneously transmitting/receiving data and power and including an array antenna including a plurality of antennas, a radio frequency (RF) unit and a baseband unit provided for data transmission and reception, a slot allocation unit configured to allocate a channel for power transfer and a slot for data transmission in a Contention Access Period (CAP) section, and allocate a slot for power transfer in consideration of whether to perform cooperative charging with a nearby another Simultaneous Wireless Information and Power Transfer (SWIPT) power transfer system, and a power supply and beamforming control unit configured to adjust the array antenna such that a power signal to be transmitted is beamformed according to a positioning beacon from a power receiving unit (PRU).

Abstract: There is provided an emotion prediction method based on virtual facial expression image augmentation. The emotion prediction method may acquire a user facial image, may extract a facial expression feature from the acquired user facial image, and may predict a user emotion from the extracted facial expression feature. The emotion prediction method may extract the facial expression feature by using a facial expression recognition network, the facial expression recognition network being an AI model that is trained to receive a user facial image and to extract a facial expression feature. The facial expression recognition network is retrained with virtual facial images which are augmented from a facial image that causes a failure in emotion recognition. Accordingly, by augmenting features of a facial expression image that causes a failure in prediction through error feedback, facial expression recognition performance can be enhanced.

Abstract: There is provided a depth estimation method for a small baseline-stereo camera through LiDAR sensor fusion. A depth map estimation method according to an embodiment may estimate a high-resolution depth map from a small baseline-stereo image based on deep learning, by using transfer learning from a deep learning network that is trained to estimate a depth map from a wide baseline-stereo image. Accordingly, in a device which has a small baseline-stereo camera installed therein due to structural constraints, such as a smartphone, a wearable AR/VR device, a drone, 3D image quality can be enhanced. In addition, according to embodiments, pseudo-LiDAR data may be generated by using a depth map estimated from a small baseline-stereo image, and may be used for replacing or reinforcing LiDAR data.

Abstract: The present invention provides a method for manufacturing a high frequency capacitor, including preparing a substrate for formation of the capacitor, forming a dielectric layer at an upper surface of the substrate, forming an upper electrode at an upper surface of the dielectric layer, and removing a portion of a lower surface of the substrate, to expose a lower surface of the dielectric layer, and forming a lower electrode at the lower surface of the dielectric layer. The high frequency capacitor includes a dielectric layer having a uniform surface, a thick upper electrode, and a thick lower electrode and, as such, exhibits high quality factor (Q) even at a high frequency.

Abstract: Provided is a method for inserting a copyright information indication as a means for protecting the copyright of LF content which can be played back as multi-viewpoint images, wherein the copyright information indication is only inserted in images of a specific viewpoint. A method for generating multi-viewpoint images according to an embodiment of the present invention includes the steps of: generating multi-viewpoint images; inserting a specific information indication in images of a specific viewpoint among the generated multi-viewpoint images; and storing the multi-viewpoint images in which the specific information indication has been inserted. Accordingly, the copyright of LF content, which are expensive multi-viewpoint images, can be protected by inserting the copyright information indication only in the images of the specific viewpoint.