• Journal of Korea Multimedia Society
• /
• v.24 no.5
• /
• pp.659-666
• /
• 2021

With the continuous development of deep learning, human behavior recognition algorithms have achieved good results. However, in a multi-person recognition environment, the complex behavior environment poses a great challenge to the efficiency of recognition. To this end, this paper proposes a multi-person pose estimation model. First of all, the human detectors in the top-down framework mostly use the two-stage target detection model, which runs slow down. The single-stage YOLOv3 target detection model is used to effectively improve the running speed and the generalization of the model. Depth separable convolution, which further improves the speed of target detection and improves the model's ability to extract target proposed regions; Secondly, based on the feature pyramid network combined with context semantic information in the pose estimation model, the OHEM algorithm is used to solve difficult key point detection problems, and the accuracy of multi-person pose estimation is improved; Finally, the Euclidean distance is used to calculate the spatial distance between key points, to determine the similarity of postures in the frame, and to eliminate redundant postures.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.2
• /
• pp.68-73
• /
• 2022

In this study, we produced the surface defect detection model to automatically detect defect bone plates using a deep learning algorithm. Bone plates with a width and a length of 50 mm are most used for fracture treatment. Normal bone plates and defective bone plates were printed on the 3d printer. Normal bone plates and defective bone plates were photographed with 1,080 pixels using the webcam. The total quantity of collected images was 500. 300 images were used to learn the defect detection model. 200 images were used to test the defect detection model. The mAP(Mean Average Precision) method was used to evaluate the performance of the surface defect detection model. As the result of confirming the performance of the surface defect detection model, the detection accuracy was 96.3 %.

• Wind and Structures
• /
• v.37 no.5
• /
• pp.383-397
• /
• 2023

In the Structural Health Monitoring (SHM) system of civil engineering, data missing inevitably occurs during the data acquisition and transmission process, which brings great difficulties to data analysis and poses challenges to structural health monitoring. In this paper, Convolution Neural Network (CNN) is used to recover the nonstationary wind speed data missing randomly at sampling points. Given the technical constraints and financial implications, field monitoring data samples are often insufficient to train a deep learning model for the task at hand. Thus, simulation combined transfer learning strategy is proposed to address issues of overfitting and instability of the deep learning model caused by the paucity of training samples. According to a portion of target data samples, a substantial quantity of simulated data consistent with the characteristics of target data can be obtained by nonstationary wind-field simulation and are subsequently deployed for training an auxiliary CNN model. Afterwards, parameters of the pretrained auxiliary model are transferred to the target model as initial parameters, greatly enhancing training efficiency for the target task. Simulation synergy strategy effectively promotes the accuracy and stability of the target model to a great extent. Finally, the structural dynamic response analysis verifies the efficiency of the simulation synergy strategy.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.5 no.4
• /
• pp.27-38
• /
• 2001

A mechanical lumped parameter model is proposed for the dynamic modeling of a semi-infinite reservoir. A semi-analytic transmitting boundary is derived for a semi-infinite 2-D reservoir of constant depth. The characteristics of the solution are examined in both frequency and time domains. Mass, damping and spring coefficients of the mechanical model are obtained to preserve the major features of the solution such as eigenfrequencies and the shapes of Bessel functions that appear as kernels in the convolution integrals. The lumped parameter model in its final form consists of two masses, a spring and two dampers for each eigenfrequency. Application examples demonstrated that the new lumped parameter model could be used for the time domain analysis of dam-reservoir systems.

• Proceedings of the KIEE Conference
• /
• 2001.05a
• /
• pp.112-115
• /
• 2001

This paper illustrates a new nodal effective load model for nodal probabilistic production cost simulation of the load point in a composite power system. The new effective load model includes capacities and uncertainties of generators as well as transmission lines. The CMELDC based on the new effective load model at HLII has been developed also. The CMELDC can be obtain from convolution integral processing of the outage capacity probabilistic distribution function of the fictitious generator and the original load duration curve given at the load point. It is expected that the new model for the CMELDC proposed. In this study will provide some solutions to many problems based on nodal and decentralized operation and control of an electric power systems under competition environment in future. The CMELDC based on the new model at HLII will extend the application areas of nodal probabilistic production cost simulation, outage cost assessment and reliability evaluation etc. at load points. The characteristics and effectiveness of this new model are illustrated by a case study of a test system.

• Journal of the Society of Naval Architects of Korea
• /
• v.56 no.3
• /
• pp.217-230
• /
• 2019

In this study, a fatigue damage estimation for an ice-going vessel navigating through broken ice fields was carried out. A numerical model to simulate the interaction between ice and structure developed using the finite element method was introduced. Time series of stresses calculated by the proposed model and the corresponding fatigue analysis results are presented. The numerical model enables the long time analysis through an efficient interaction model, the application of the periodic media analysis and the convolution integral, and it allows the stress time history to be extracted directly using the finite element method. To describe the probability distribution of stress amplitudes, the 2-parameter Weibull model was applied to the calculated stress time history, and the fatigue damage was calculated using the Palmgren-Miner rule. Finally, the fatigue damage considering the ice conditions of the Baltic Sea was calculated using the proposed method and LR method, and the results were compared to each other.

• International Journal of Computer Science & Network Security
• /
• v.21 no.8
• /
• pp.238-246
• /
• 2021

The rapid rise of the Internet and social media has resulted in a large number of text-based reviews being placed on sites such as social media. In the age of social media, utilizing machine learning technologies to analyze the emotional context of comments aids in the understanding of QoS for any product or service. The classification and analysis of user reviews aids in the improvement of QoS. (Quality of Services). Machine Learning algorithms have evolved into a powerful tool for analyzing user sentiment. Unlike traditional categorization models, which are based on a set of rules. In sentiment categorization, Bidirectional Long Short-Term Memory (BiLSTM) has shown significant results, and Convolution Neural Network (CNN) has shown promising results. Using convolutions and pooling layers, CNN can successfully extract local information. BiLSTM uses dual LSTM orientations to increase the amount of background knowledge available to deep learning models. The suggested hybrid model combines the benefits of these two deep learning-based algorithms. The data source for analysis and classification was user reviews of Indian Railway Services on Twitter. The suggested hybrid model uses the Keras Embedding technique as an input source. The suggested model takes in data and generates lower-dimensional characteristics that result in a categorization result. The suggested hybrid model's performance was compared using Keras and Word2Vec, and the proposed model showed a significant improvement in response with an accuracy of 95.19 percent.

• Nuclear Engineering and Technology
• /
• v.55 no.1
• /
• pp.100-108
• /
• 2023

In this study, a neural network model inspired by a one-dimensional convolution U-net is developed to automatically accelerate edge localized mode (ELM) detection from big diagnostic data of fusion devices and increase the detection accuracy regardless of the hyperparameter setting. This model recognizes the input signal patterns and overcomes the problems of existing detection algorithms, such as the prominence algorithm and those of differential methods with high sensitivity for the threshold and signal intensity. To train the model, 10 sets of discharge radiation data from the KSTAR are used and sliced into 11091 inputs of length 12 ms, of which 20% are used for validation. According to the receiver operating characteristic curves, our model shows a positive prediction rate and a true prediction rate of approximately 90% each, which is comparable to the best detection performance afforded by other algorithms using their optimized hyperparameters. The accurate and automatic ELM-burst detection methodology used in our model can be beneficial for determining plasma properties, such as the ELM frequency from big data measured in multiple experiments using machines from the KSTAR device and ITER. Additionally, it is applicable to feature detection in the time-series data of other engineering fields.

• Interaction and multiscale mechanics
• /
• v.3 no.3
• /
• pp.267-276
• /
• 2010

A nonlocal finite element model is developed for solving elasto-static frictional contact problems of nanostructures and nanoscale devices. A two dimensional Eringen-type nonlocal elasticity model is adopted. The material is characterized by a stress-strain constitutive relation of a convolution integral form whose kernel is capable to take into account both the diffusion process of nonlocal elasticity and the scale ratio effects. The incremental convex programming procedure is exploited as a solver. Two examples of different nature are presented, the first one presents the behavior of a nanoscale contacting system and the second example discusses the nano-indentation problem.

• International journal of advanced smart convergence
• /
• v.7 no.2
• /
• pp.95-100
• /
• 2018

In this paper, we propose a binarized multi-scale module to accelerate the speed of the pose estimating deep neural network. Recently, deep learning is also used for fine-tuned tasks such as pose estimation. One of the best performing pose estimation methods is based on the usage of two neural networks where one computes the heat maps of the body parts and the other computes the part affinity fields between the body parts. However, the convolution filtering with a large kernel filter takes much time in this model. To accelerate the speed in this model, we propose to change the large kernel filters with binarized multi-scale modules. The large receptive field is captured by the multi-scale structure which also prevents the dropdown of the accuracy in the binarized module. The computation cost and number of parameters becomes small which results in increased speed performance.