• The Journal of Bigdata
• /
• v.4 no.2
• /
• pp.115-126
• /
• 2019

There have been many discussions on export indices in trade exports, but there is no definite trade export index which can be explained by objective indicators. Korea International Trade Association (KITA), Korea Trade-Investment Promotion Agency (KOTRA), etc., but we are currently in the process of thinking about ways to express the capabilities of exporting companies. In this study, we constructed the AI data sets by setting the activity indicators such as the size of the company and the credit score, the number of transaction customers, the number of transactions, the number of items, the transaction volume, and the transaction period as features, Lightgbm. Using the Graph Neural Network as an industrial cluster classification model, the export live index which expresses the exportable capacity among companies, items, and business groups was calculated. This includes the past activity of the company from the current calculating index Objectivity.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.3
• /
• pp.1-8
• /
• 2022

Recently, Google MedeiaPipe presents a novel approach for neural network-based hair segmentation from a single camera input specifically designed for real-time, mobile application. Though neural network related to hair segmentation is relatively small size, it produces a high-quality hair segmentation mask that is well suited for AR effects such as a realistic hair recoloring. However, it has undesirable segmentation effects according to hair styles or in case of containing noises and holes. In this study, the energy function of the test image is constructed according to the estimated prior distributions of hair location and hair color likelihood function. It is further optimized according to graph cuts algorithm and initial hair region is obtained. Finally, clustering algorithm and image post-processing techniques are applied to the initial hair region so that the final hair region can be segmented precisely. The proposed method is applied to MediaPipe hair segmentation pipeline.

• Genomics & Informatics
• /
• v.17 no.2
• /
• pp.15.1-15.7
• /
• 2019

Automatically detecting mentions of pharmaceutical drugs and chemical substances is key for the subsequent extraction of relations of chemicals with other biomedical entities such as genes, proteins, diseases, adverse reactions or symptoms. The identification of drug mentions is also a prior step for complex event types such as drug dosage recognition, duration of medical treatments or drug repurposing. Formally, this task is known as named entity recognition (NER), meaning automatically identifying mentions of predefined entities of interest in running text. In the domain of medical texts, for chemical entity recognition (CER), techniques based on hand-crafted rules and graph-based models can provide adequate performance. In the recent years, the field of natural language processing has mainly pivoted to deep learning and state-of-the-art results for most tasks involving natural language are usually obtained with artificial neural networks. Competitive resources for drug name recognition in English medical texts are already available and heavily used, while for other languages such as Spanish these tools, although clearly needed were missing. In this work, we adapt an existing neural NER system, NeuroNER, to the particular domain of Spanish clinical case texts, and extend the neural network to be able to take into account additional features apart from the plain text. NeuroNER can be considered a competitive baseline system for Spanish drug and CER promoted by the Spanish national plan for the advancement of language technologies (Plan TL).

• Fibers and Polymers
• /
• v.7 no.4
• /
• pp.404-413
• /
• 2006

This study examines multiple quality optimization of the injection molding for Polyether Ether Ketone (PEEK). It also looks into the dimensional deviation and strength of screws that are reduced and improved for the molding quality, respectively. This study applies the Taguchi method to cut down on the number of experiments and combines grey relational analysis to determine the optimal processing parameters for multiple quality characteristics. The quality characteristics of this experiment are the screws' outer diameter, tensile strength and twisting strength. First, one should determine the processing parameters that may affect the injection molding with the $L_{18}(2^1{\times}3^7)$ orthogonal, including mold temperature, pre-plasticity amount, injection pressure, injection speed, screw speed, packing pressure, packing time and cooling time. Then, the grey relational analysis, whose response table and response graph indicate the optimum processing parameters for multiple quality characteristics, is applied to resolve this drawback. The Taguchi method only takes a single quality characteristic into consideration. Finally, a processing parameter prediction system is established by using the back-propagation neural network. The percentage errors all fall within 2%, between the predicted values and the target values. This reveals that the prediction system established in this study produces excellent results.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.11
• /
• pp.2427-2432
• /
• 2009

This paper proposes an monitoring system of elder and feeble person's motion activity using an object's motion activity data. The proposed system used wireless 3-axis sensor module, product by Freescale(Wireless Sensing Triple Axis Reference Design Board (ZSTAR)). We distribute sensing data into three classes using Neural Network System SVM. We find performance of proposed system that simulate some case about walk, past walk, fallen. Classify result data and graph of sensing data present succes rate 80%.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.5
• /
• pp.463-468
• /
• 2010

An obstacle avoidance method for a mobile robot is proposed in this paper. Our research was focused on the obstacles that can be found indoors since a robot is usually used within a building. It is necessary that the robot maintain the desired direction after successfully avoiding the obstacles to achieve a good autonomous navigation performance for the specified project mission. Sensors such as laser, ultrasound, and PSD (Position Sensitive Detector) can be used to detect and analyze the obstacles. A PSD sensor was used to detect and measure the height and width of the obstacles on the floor. The PSD sensor was carefully calibrated before measuring the obstacles to achieve better accuracy. Data obtained from the repeated experiments were used to plot an error graph which was fitted to a polynomial curve. The polynomial equation was used to navigate the robot. We also obtained a direction-error model of the robot after avoiding the obstacles. The prototypes for the obstacle and direction-error were modeled using a neural network whose inputs are the obstacle height, robot speed, direction of the wheels, and the error in direction. A mobile robot operated by a notebook computer was setup and the proposed algorithm was used to navigate the robot and avoid the obstacles. The results showed that our algorithm performed very well during the experiments.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.10
• /
• pp.1469-1476
• /
• 2022

Recently, many researches have been conducted to estimate blood pressure using ECG(Electrocardiogram) and PPG(Photoplentysmography) signals. In this paper, we designed and implemented a mobile system to monitor blood pressure in real time by using 1-D convolutional neural networks. The proposed model consists of deep 11 layers which can learn to extract various features of ECG and PPG signals. The simulation results show that the more the number of convolutional kernels the learned neural network has, the more detailed characteristics of ECG and PPG signals resulted in better performance with reduced mean square error compared to linear regression model. With receiving measurement signals from wearable ECG and PPG sensor devices attached to the body, the developed system receives measurement data transmitted through Bluetooth communication from the devices, estimates systolic and diastolic blood pressure values using a learned model and displays its graph in real time.

• Journal of Internet Computing and Services
• /
• v.22 no.5
• /
• pp.27-33
• /
• 2021

With the broad adoption of the Internet of Things (IoT) in a variety of scenarios and application services, management and orchestration entities require upgrading the traditional architecture and develop intelligent models with ultra-reliable methods. In a heterogeneous network environment, mission-critical IoT applications are significant to consider. With erroneous priorities and high failure rates, catastrophic losses in terms of human lives, great business assets, and privacy leakage will occur in emergent scenarios. In this paper, an efficient resource slicing scheme for optimizing federated learning in software-defined IoT (SDIoT) is proposed. The decentralized support vector regression (SVR) based controllers predict the IoT slices via packet inspection data during peak hour central congestion to achieve a time-sensitive condition. In off-peak hour intervals, a centralized deep neural networks (DNN) model is used within computation-intensive aspects on fine-grained slicing and remodified decentralized controller outputs. With known slice and prioritization, federated learning communications iteratively process through the adjusted resources by virtual network functions forwarding graph (VNFFG) descriptor set up in software-defined networking (SDN) and network functions virtualization (NFV) enabled architecture. To demonstrate the theoretical approach, Mininet emulator was conducted to evaluate between reference and proposed schemes by capturing the key Quality of Service (QoS) performance metrics.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.3
• /
• pp.227-237
• /
• 2022

The most critical factors for detecting changes in very high-resolution satellite images are building positional inconsistencies and relief displacements caused by satellite side-view. To resolve the above problems, additional processing using a digital elevation model and deep learning approach have been proposed. Unfortunately, these approaches are not sufficiently effective in solving these problems. This study proposed a change detection method that considers both positional and topology information of buildings. Mask R-CNN (Region-based Convolutional Neural Network) was trained on a SpaceNet building detection v2 dataset, and the central points of each building were extracted as building nodes. Then, triangulated irregular network graphs were created on building nodes from temporal images. To extract the area, where there is a structural difference between two graphs, a change index reflecting the similarity of the graphs and differences in the location of building nodes was proposed. Finally, newly changed or deleted buildings were detected by comparing the two graphs. Three pairs of test sites were selected to evaluate the proposed method's effectiveness, and the results showed that changed buildings were detected in the case of side-view satellite images with building positional inconsistencies.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.59 no.5
• /
• pp.93-99
• /
• 2017

A model was developed using Artificial Neural Networks (ANNs) based on Principal Component Analysis (PCA), to accurately predict the air humidity inside an experimental greenhouse located in Daegu (latitude $35.53^{\circ}N$, longitude $128.36^{\circ}E$, and altitude 48 m), South Korea. The weather parameters, air temperature, relative humidity, solar radiation, and carbon dioxide inside and outside the greenhouse were monitored and measured by mounted sensors. Through the PCA of the data samples, three main components were used as the input data, and the measured inside humidity was used as the output data for the ALYUDA forecaster software of the ANN model. The Nash-Sutcliff Model Efficiency Coefficient (NSE) was used to analyze the difference between the experimental and the simulated results, in order to determine the predictive power of the ANN software. The results obtained revealed the variables that affect the inside air humidity through a sensitivity analysis graph. The measured humidity agreed well with the predicted humidity, which signifies that the model has a very high accuracy and can be used for predictions based on the computed $R^2$ and NSE values for the training and validation samples.