• Journal of the Semiconductor & Display Technology
• /
• v.21 no.2
• /
• pp.117-122
• /
• 2022

This paper proposes a method for evaluating the work of manufacturing workers using MediaPipe as a risk factor for musculoskeletal diseases. Recently, musculoskeletal disorders (MSDs) caused by repeated working attitudes in industrial sites have emerged as one of the biggest problems in the industrial health field while increasing public interest. The Korea Occupational Safety and Health Agency presents tools such as NIOSH Lifting Equations (NIOSH), OWAS (Ovako Working-posture Analysis System), Rapid Upper Limb Assessment (RULA), and Rapid Entertainment Assessment (REBA) as ways to quantitatively calculate the risk of musculoskeletal diseases that can occur due to workers' repeated working attitudes. To compensate for these shortcomings, the system proposed in this study obtains the position of the joint by estimating the posture of the worker using the posture estimation learning model of MediaPipe. The position of the joint is calculated using inverse kinetics to obtain an angle and substitute it into the REBA equation to calculate the load level of the working posture. The calculated result was compared to the expert's image-based REBA evaluation result, and if there was a result with a large error, feedback was conducted with the expert again.

• Journal of Positioning, Navigation, and Timing
• /
• v.12 no.1
• /
• pp.1-9
• /
• 2023

The problem of classifying a non-line-of-sight (NLOS) signal in a multipath channel is important to improve global navigation satellite system (GNSS) positioning accuracy in urban areas. Conventional deep learning-based NLOS signal classifiers use GNSS satellite measurements such as the carrier-to-noise-density ratio (CN_0), pseudorange, and elevation angle as inputs. However, there is a computational inefficiency with use of these measurements and the NLOS signal features expressed by the measurements are limited. In this paper, we propose a Convolutional Neural Network (CNN)-based NLOS signal classifier that receives successive Auto-correlation function (ACF) outputs according to a time-series, which is the most primitive output of GNSS signal processing. We compared the proposed classifier to other DL-based NLOS signal classifiers such as a multi-layer perceptron (MLP) and Gated Recurrent Unit (GRU) to show the superiority of the proposed classifier. The results show the proposed classifier does not require the navigation data extraction stage to classify the NLOS signals, and it has been verified that it has the best detection performance among all compared classifiers, with an accuracy of up to 97%.

• Geomechanics and Engineering
• /
• v.31 no.5
• /
• pp.453-460
• /
• 2022

It is essential for geotechnical engineers to conduct studies and make predictions about the stability of slopes, since collapse of a slope may result in catastrophic events. The Gaussian process regression (GPR) approach was carried out for the purpose of predicting the factor of safety (FOS) of the slopes in the study that was presented here. The model makes use of a total of 327 slope cases from Iran, each of which has a unique combination of geometric and shear strength parameters that were analyzed by PLAXIS software in order to determine their FOS. The K-fold (K = 5) technique of cross-validation (CV) was used in order to conduct an analysis of the accuracy of the models' predictions. In conclusion, the GPR model showed excellent ability in the prediction of FOS of slope stability, with an R² value of 0.8355, RMSE value of 0.1372, and MAPE value of 6.6389%, respectively. According to the results of the sensitivity analysis, the characteristics (friction angle) and (unit weight) are, in descending order, the most effective, the next most effective, and the least effective parameters for determining slope stability.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.31-33
• /
• 2021

In this paper, a dataset was designed and built to improve the accuracy of finger direction detection using an object detection algorithm based on You Only Look Once (YOLO). In order to improve the object detection performance, about 200 finger image data sets were trained, and to confirm that the detection accuracy differs from each other according to the angle of the palm, 50 comparison groups of different angles were configured and tested. As a result of the experiment, it was confirmed that the detection accuracy of palm located in a direction close to 90° is higher than that of other angles.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.516-518
• /
• 2022

In this paper, we introduce a dependence of number of nodes of hidden-layer in fall detection system using Long Short-Term Memory that can detect falls. Its training is carried out using the parameter theta(θ), which indicates the angle formed by the x, y, and z-axis data for the direction of gravity using a 3-axis acceleration sensor. In its learning, validation is performed and divided into training data and test data in a ratio of 8:2, and training is performed by changing the number of nodes in the hidden layer to increase efficiency. When the number of nodes is 128, the best accuracy is shown with Accuracy = 99.82%, Specificity = 99.58%, and Sensitivity = 100%.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.294-296
• /
• 2022

Atherosclerosis is a chronic vascular inflammatory disease in which plaque builds up in the arteries and impairs blood flow. This can lead to heart disease and stroke. Since most people do not have any symptoms until the artery is severely narrowed, early detection of atherosclerosis is critical. In this paper, in order to effectively detect atherosclerotic lesions in tube-shaped blood vessels, polar conversion is applied to MRI images based on the vessel center. We then propose a SE-LSTMNet model using continuous signal information for each angle of a polar coordinate image. The trained model showed classification performance of 0.9194 accuracy, 0.9370 sensitivity, 0.8796 specificity, 0.8700 F1 score, and 0.9719 AUC on the validation data.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.191-192
• /
• 2024

고령 인구의 지속적인 증가로 인해 고령자의 안전과 관련된 문제는 주요한 관심사 중 하나로 부상하고 있다. 특히, 고령자들 사이에서 자주 발생하는 낙상 사고는 심각한 건강 문제를 일으킬 수 있으며, 이를 예방하고 대응하는 것은 고령 인구의 삶의 질을 향상하는 데 중요한 역할을 한다. 본 연구는 8대의 카메라로 촬영된 영상과 센서 데이터를 통합한 낙상 감지 기법을 제안한다. 제안한 기법은 MediaPipe를 활용하여 Skeleton Keypoint를 추출하는 이미지 인식 기법과 센서 데이터에서 얻은 특징을 활용하는 센서 기반 기술을 결합하여 낙상 사고의 발생 및 방향을 효과적으로 감지할 수 있다. 이러한 결과를 바탕으로 본 연구는 향후 고령자들의 생활 안전성과 의료 시스템의 효율성을 높이는 데 이바지할 수 있을 것으로 기대한다.

• Wind and Structures
• /
• v.38 no.4
• /
• pp.231-244
• /
• 2024

As wind farms expand into low wind speed areas, an increasing number are being established in mountainous regions. To fully utilize wind energy resources, it is essential to understand the details of mountain flow fields. Reconstructing the wind speed field in complex terrain is crucial for planning, designing, operation of wind farms, which impacts the wind farm's profits throughout its life cycle. Currently, wind speed reconstruction is primarily achieved through physical and machine learning methods. However, physical methods often require significant computational costs. Therefore, we propose a Full Convolutional Neural Network (FCNN)-based reconstruction method for mountain wind velocity fields to evaluate wind resources more accurately and efficiently. This method establishes the mapping relation between terrain, wind angle, height, and corresponding velocity fields of three velocity components within a specific terrain range. Guided by this mapping relation, wind velocity fields of three components at different terrains, wind angles, and heights can be generated. The effectiveness of this method was demonstrated by reconstructing the wind speed field of complex terrain in Beijing.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.4
• /
• pp.153-163
• /
• 2017

This research is based on the previous research that personally preferred safe distance, rotating angle and speed are differentiated. Thus, we use machine learning model for recognizing maneuvering modes trained per personal or per similar driving pattern groups, and we evaluate automatic driving according to maneuvering modes. By utilizing driving knowledge, we subdivided 8 kinds of longitudinal modes and 4 kinds of lateral modes, and by combining the longitudinal and lateral modes, we build 21 kinds of maneuvering modes. we train the labeled data set per time stamp through RNN, LSTM and Bi-LSTM models by the trips of drivers, which are supervised deep learning models, and evaluate the maneuvering modes of automatic driving for the test data set. The evaluation dataset is aggregated of living trips of 3,000 populations by VTTI in USA for 3 years and we use 1500 trips of 22 people and training, validation and test dataset ratio is 80%, 10% and 10%, respectively. For recognizing longitudinal 8 kinds of maneuvering modes, RNN achieves better accuracy compared to LSTM, Bi-LSTM. However, Bi-LSTM improves the accuracy in recognizing 21 kinds of longitudinal and lateral maneuvering modes in comparison with RNN and LSTM as 1.54% and 0.47%, respectively.

• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.408-415
• /
• 2022

In this paper, we propose a 3D point cloud reconstruction technique from 2D images using efficient feature map extraction network. The originality of the method proposed in this paper is as follows. First, we use a new feature map extraction network that is about 27% efficient than existing techniques in terms of memory. The proposed network does not reduce the size to the middle of the deep learning network, so important information required for 3D point cloud reconstruction is not lost. We solved the memory increase problem caused by the non-reduced image size by reducing the number of channels and by efficiently configuring the deep learning network to be shallow. Second, by preserving the high-resolution features of the 2D image, the accuracy can be further improved than that of the conventional technique. The feature map extracted from the non-reduced image contains more detailed information than the existing method, which can further improve the reconstruction accuracy of the 3D point cloud. Third, we use a divergence loss that does not require shooting information. The fact that not only the 2D image but also the shooting angle is required for learning, the dataset must contain detailed information and it is a disadvantage that makes it difficult to construct the dataset. In this paper, the accuracy of the reconstruction of the 3D point cloud can be increased by increasing the diversity of information through randomness without additional shooting information. In order to objectively evaluate the performance of the proposed method, using the ShapeNet dataset and using the same method as in the comparative papers, the CD value of the method proposed in this paper is 5.87, the EMD value is 5.81, and the FLOPs value is 2.9G. It was calculated. On the other hand, the lower the CD and EMD values, the better the accuracy of the reconstructed 3D point cloud approaches the original. In addition, the lower the number of FLOPs, the less memory is required for the deep learning network. Therefore, the CD, EMD, and FLOPs performance evaluation results of the proposed method showed about 27% improvement in memory and 6.3% in terms of accuracy compared to the methods in other papers, demonstrating objective performance.