• Journal of Internet Computing and Services
• /
• v.22 no.3
• /
• pp.9-16
• /
• 2021

This study aims to develop a human activity recognition (HAR) system as a Deep-Learning (DL) classification model, distinguishing various human activities. We solely rely on the signals from a wristband accelerometer worn by a person for the user's convenience. 3-axis sequential acceleration signal data are gathered within a predefined time-window-slice, and they are used as input to the classification system. We are particularly interested in developing a Deep-Learning model that can outperform conventional machine learning classification performance. A total of 13 activities based on the laboratory experiments' data are used for the initial performance comparison. We have improved classification performance using the Convolutional Neural Network (CNN) combined with an auto-encoder feature reduction and parameter tuning. With various publically available HAR datasets, we could also achieve significant improvement in HAR classification. Our CNN model is also compared against Recurrent-Neural-Network(RNN) with Long Short-Term Memory(LSTM) to demonstrate its superiority. Noticeably, our model could distinguish both general activities and near-identical activities such as sitting down on the chair and floor, with almost perfect classification accuracy.

• Communications for Statistical Applications and Methods
• /
• v.30 no.3
• /
• pp.273-289
• /
• 2023

In this paper, we develop a new time series model for predicting IPO (initial public offering) data with non-negative integer value. The proposed model is based on integer-valued autoregressive (INAR) model with a Poisson thinning operator. Just as the heterogeneous autoregressive (HAR) model with daily, weekly and monthly averages in a form of cascade, the integer-valued heterogeneous autoregressive (INHAR) model is considered to reflect efficiently the long memory. The parameters of the INHAR model are estimated using the conditional least squares estimate and Yule-Walker estimate. Through simulations, bias and standard error are calculated to compare the performance of the estimates. Effects of model fitting to the Korea's IPO are evaluated using performance measures such as mean square error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE) etc. The results show that INHAR model provides better performance than traditional INAR model. The empirical analysis of the Korea's IPO indicates that our proposed model is efficient in forecasting monthly IPO volumes.

• Journal of Internet Computing and Services
• /
• v.21 no.4
• /
• pp.127-135
• /
• 2020

The purpose of this study is to develop a human activity recognition (HAR) system, which distinguishes 13 activities, including five activities commonly dealt with in conventional HAR researches and eight activities from the Eastern-Asian culture. The eight special activities include floor-sitting/standing, chair-sitting/standing, floor-lying/up, and bed-lying/up. We used a 3-axis accelerometer sensor on the wrist for data collection and designed a machine learning model for the activity classification. Data clustering through preprocessing and feature extraction/reduction is performed. We then tested six machine learning algorithms for recognition accuracy comparison. As a result, we have achieved an average accuracy of 99.7% for the 13 activities. This result is far better than the average accuracy of current HAR researches based on a smartwatch (89.4%). The superiority of the HAR system developed in this study is proven because we have achieved 98.7% accuracy with publically available 'pamap2' dataset of 12 activities, whose conventionally met the best accuracy is 96.6%.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.5
• /
• pp.177-183
• /
• 2022

Recently, interesting of home training is getting bigger due to COVID-19. Accordingly, research on applying HAR(human activity recognition) technology to home training has been conducted. However, existing paper of HAR proposed static activity instead of dynamic activity. In this paper, the deep learning model where dynamic exercise posture can be analyzed and the accuracy of the user's exercise posture can be shown is proposed. Fitness images of AI-hub are analyzed by blaze pose. The experiment is compared with three types of deep learning model: RNN(recurrent neural network), LSTM(long short-term memory), CNN(convolution neural network). In simulation results, it was shown that the f1-score of RNN, LSTM and CNN is 0.49, 0.87 and 0.98, respectively. It was confirmed that CNN is more suitable for human activity recognition than other models from simulation results. More exercise postures can be analyzed using a variety learning data.

• Bulletin of the Korean Chemical Society
• /
• v.29 no.3
• /
• pp.656-662
• /
• 2008

Antagonists of the d -opioid receptor are effective in overcoming resistance against analgesic drugs such as morphine. To identify novel antagonists of the d -opioid receptor that display high potency and low resistance, we performed 3D-QSAR analysis using chemical feature-based pharmacophore models. Chemical features for d -opioid receptor antagonists were generated using quantitative (Catalyst/HypoGen) and qualitative (Catalyst/HipHop) approaches. For HypoGen analysis, we collected 16 peptide and 16 non-peptide antagonists as the training set. The best-fit pharmacophore hypotheses of the two antagonist models comprised identical features, including a hydrophobic aromatic (HAR), a hydrophobic (HY), and a positive ionizable (PI) function. The training set of the HipHop model was constructed with three launched opioid drugs. The best hypothesis from HipHop included four features: an HAR, an HY, a hydrogen bond donor (HBD), and a PI function. Based on these results, we confirm that HY, HAR and PI features are essential for effective antagonism of the d -opioid receptor, and determine the appropriate pharmacophore to design such antagonists.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.6
• /
• pp.89-95
• /
• 2023

In recent decades, human action recognition (HAR) has demonstrated potential applications in sports analysis, human-robot interaction, and large-scale signage content. In this paper, spatial temporal attention graph convolutional network (STAGCN)-based HAR system is proposed. Spatioal-temmporal features of skeleton sequences are assigned different weights by STAGCN, enabling the consideration of key joints and viewpoints. From simulation results, it has been shown that the performance of the proposed model can be improved in terms of classification accuracy in the NTU RGB+D dataset.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.4
• /
• pp.53-58
• /
• 2022

Shape changes of hard mask play a key role in the aspect ratio dependent etch (ARDE). For etch process using high density and energy ions, deformation of hard mask shape becomes more severe, and high aspect ratio (HAR) etch profile is distorted. In this study, polygonal geometric model for shape-deformation of amorphous carbon layered hard mask is suggested to control etch profile during the process. Mask shape is modeled with polygonal geometry consisting of trapezoids and rectangles, and it provides dynamic information about angles of facets and etched width and height of remained mask shape, providing important features for real-time HAR etch profiling.

• Proceedings of the Korean Society of Developmental Biology Conference
• /
• 2003.10a
• /
• pp.9-19
• /
• 2003

Pig organ is thought to be the most suitable nonhuman organ for xenotransplanstation. However, one of the major constraints to using pig organs for xenotransplantation is human natural antibody-mediated hyperacute rejection (HAR). Elimination of a(1,3) galactosyltransferase (GGTA1) from the pig is expected to be a solution to the problem of hyperacute rejection. Many efforts have made characterization of GGTA1 in structure and function, improvement in the technique of DNA transfection of somatic cells and advancement of the pig NT, a specific modification has been made to one copy of the GGTAl gene by Missouri group in 2002 To date because homozygousity of the genetic modification has been achieved in this gene, the role of gala(1,3) gal specific natural antibody in HAR and the efficacy of xenotransplantation in a nonhuman primate model will be addressed. Of other genes are found to be involved in rejection of pig donors by primates, the technology will be available to modify those genes so that rejection can be overcome.

• Proceedings of the Korean Society of Embryo Transfer Conference
• /
• 2003.10a
• /
• pp.9-19
• /
• 2003

Pig organ is thought to be the most suitable nonhuman organ for xenotransplanstation. However, one of the major constraints to using pig organs for xenotransplantation is human natural antibody-mediated hyperacute rejection (HAR). Elimination of a(1,3) galactosyltransferase (GGTA1) from the pig is expected to be a solution to the problem of hyperacute rejection. ry1any efforts have made characterization of GGTA1 in structure and function. improvement in the technique of DNA transfection of somatic cells and advancement of the pig NT, a specific modification has been made to one copy of the GGTA1 gene by Missouri group in 2002. To date because homozygousity of the genetic modification has been achieved in this gene, the role of gala(1,3) gal specific natural antibody in HAR and the efficacy of xenotransplantation in a nonhuman primate model will be addressed. If other genes are found to be involved in rejection of pig donors by primates, the technology will be available to modify those genes so that rejection can be overcome.

• Database Research
• /
• v.34 no.3
• /
• pp.137-147
• /
• 2018

A key to a well-performing human activity recognition (HAR) system through machine learning technique is the availability of a substantial amount of labeled data. Collecting sufficient labeled data is an expensive and time-consuming task. To build a HAR system in a new environment (i.e., the target domain) with very limited labeled data, it is unfavorable to naively exploit the data or trained classifier model from the existing environment (i.e., the source domain) as it is due to the domain difference. While traditional machine learning approaches are unable to address such distribution mismatch, transfer learning approach leverages the utilization of knowledge from existing well-established source domains that help to build an accurate classifier in the target domain. In this work, we propose a transfer learning approach to create an accurate HAR classifier with very limited data through the multitask neural network. The classifier loss function minimization for source and target domain are treated as two different tasks. The knowledge transfer is performed by simultaneously minimizing the loss function of both tasks using a single neural network model. Furthermore, we utilize the unlabeled data in an unsupervised manner to help the model training. The experiment result shows that the proposed work consistently outperforms existing approaches.