• Journal of Digital Contents Society
• /
• v.18 no.3
• /
• pp.559-565
• /
• 2017

A lot of studies have been conducted to recognize the motion state or behavior of the user using the acceleration sensor built in the smartphone. In this paper, we applied the neural networks to the 3-axis acceleration information of smartphone to study human behavior. There are performance issues in applying time series data to neural networks. We proposed a multi-temporal neural networks which have trained three neural networks with different time windows for feature extraction and uses the output of these neural networks as input to the new neural network. The proposed method showed better performance than other methods like SVM, AdaBoot and IBk classifier for real acceleration data.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.5
• /
• pp.755-765
• /
• 2015

This paper is concerned with Interval Type-2 Radial Basis Function Neural Network classifier realized with the aid of Census Transform(CT) and (2D)2LDA methods. CT is considered to improve performance of face recognition in a variety of illumination variations. (2D)2LDA is applied to transform high dimensional image into low-dimensional image which is used as input data to the proposed pattern classifier. Receptive fields in hidden layer are formed as interval type-2 membership function. We use the coefficients of linear polynomial function as the connection weights of the proposed networks, and the coefficients and their ensuing spreads are learned through Conjugate Gradient Method(CGM). Moreover, the parameters such as fuzzification coefficient and the number of input variables are optimized by Artificial Bee Colony(ABC). In order to evaluate the performance of the proposed classifier, Yale B dataset which consists of images obtained under diverse state of illumination environment is applied. We show that the results of the proposed model have much more superb performance and robust characteristic than those reported in the previous studies.

• Journal of Korea Game Society
• /
• v.19 no.3
• /
• pp.87-100
• /
• 2019

Serious games based on VR(Virtual Reality) and motion recognition technologies have been studied in physical therapy and have shown significant positive effects. These existing systems have focused on measuring performance for the general public rather than patients which need rehabilitation. In the paper, We propose a serious game of self-rehabilitation that measures the patient's current physical state to generate appropriate difficulty levels to aid patients with shoulder injury.

• Journal of the Korea Convergence Society
• /
• v.10 no.6
• /
• pp.235-242
• /
• 2019

Recently, the use of artificial intelligence technology including deep learning has become active in various fields. In particular, several algorithms showing superior performance in object recognition and detection based on deep learning technology have been presented. In this paper, we propose the proper direction for the implementation of mobile healthcare application that user's convenience is effectively reflected. By effectively analyzing the current state of use satisfaction research for the existing fitness applications and the current status of mobile healthcare applications, we attempt to secure survival and superiority in the fitness application market, and, at the same time, to maintain and expand the existing user base.

• Journal of The Korean Society of Integrative Medicine
• /
• v.8 no.4
• /
• pp.49-58
• /
• 2020

Purpose : This study examined the effect of a home visit cognitive training program that uses a tablet-based digital recognition rehabilitation application, Brain Doctor, on local elderly people's cognitive function and depression. Methods : This study featured 20 elderly people living in Busan Metropolitan City, South Korea, who received a voucher for a home visit service to prevent dementia. The subjects were evenly divided into an intervention group provided with Brain Doctor and a control group provided with a conventional cognitive training program. Korean version of Mini Mental State Examination (MMSE-K) and Korean version of Montreal Cognitive Assessment (K-MoCA) were used to assess cognitive function in each group. Patient Health Questionnaire-9 (PHQ-9) was used to evaluate the depression levels. Results : The intervention group showed a significant change in cognitive function and depression after the intervention (p<.05). There was a statistically significant change in cognitive function and depression between the intervention and control groups (p<.05). Conclusion : This study confirmed that Brain Doctor had a positive effect on the cognitive function and depression of elderly people in the local community. It is expected to become a useful home visit program for dementia prevention in the future.

• Korean Journal of Pharmacognosy
• /
• v.51 no.4
• /
• pp.310-316
• /
• 2020

Kyung-Ok-Go (KOK) is a traditional prescription used for debilitating natural aging and post-illness debilitation. KOK has been used in a variety of ways because it strengthens immunity, prevents illness, and helps recovery in case of illness. In particular, recent research has revealed that KOK helps improve memory and cognition. Therefore, in this study, we investigated whether KOK was effective in improving memory decline and depression-state observed during menopause. In the present study, we employed ovariectomized mouse as an animal model for measuring menopausal syndrome. The administration of KOK for 8 weeks, the object recognition memory and working memory were improved in novel object recognition test and Y-maze test. And in the forced swimming test, the immobility time were decreased. Additionally, the expression level of mature brain derived neurotropic factor (mBDNF) was increased by KOK administration in ovariectomized mouse hippocampus. These results suggested that KOK could improve cognitive decline and depression during menopausal period, and it might be come from enhancing expression level of mBDNF in hippocampus.

• International Journal of Computer Science & Network Security
• /
• v.22 no.7
• /
• pp.220-228
• /
• 2022

Image always carry useful information, detecting a text from scene images is imperative. The proposed work's purpose is to recognize scene text image, example boarding image kept on highways. Scene text detection on highways boarding's plays a vital role in road safety measures. At initial stage applying preprocessing techniques to the image is to sharpen and improve the features exist in the image. Likely, morphological operator were applied on images to remove the close gaps exists between objects. Here we proposed a two phase algorithm for extracting and recognizing text from scene images. In phase I text from scenery image is extracted by applying various image preprocessing techniques like blurring, erosion, tophat followed by applying thresholding, morphological gradient and by fixing kernel sizes, then canny edge detector is applied to detect the text contained in the scene images. In phase II text from scenery image recognized using MSER (Maximally Stable Extremal Region) and OCR; Proposed work aimed to detect the text contained in the scenery images from popular dataset repositories SVT, ICDAR 2003, MSRA-TD 500; these images were captured at various illumination and angles. Proposed algorithm produces higher accuracy in minimal execution time compared with state-of-the-art methodologies.

• ETRI Journal
• /
• v.44 no.5
• /
• pp.794-804
• /
• 2022

Transformer models have had a great impact on natural language processing (NLP) in recent years by realizing outstanding and efficient contextualized language models. Recent studies have used transformer-based language models for various NLP tasks, including Persian named entity recognition (NER). However, in complex tasks, for example, NER, it is difficult to determine which contextualized embedding will produce the best representation for the tasks. Considering the lack of comparative studies to investigate the use of different contextualized pretrained models with sequence modeling classifiers, we conducted a comparative study about using different classifiers and embedding models. In this paper, we use different transformer-based language models tuned with different classifiers, and we evaluate these models on the Persian NER task. We perform a comparative analysis to assess the impact of text representation and text classification methods on Persian NER performance. We train and evaluate the models on three different Persian NER datasets, that is, MoNa, Peyma, and Arman. Experimental results demonstrate that XLM-R with a linear layer and conditional random field (CRF) layer exhibited the best performance. This model achieved phrase-based F-measures of 70.04, 86.37, and 79.25 and word-based F scores of 78, 84.02, and 89.73 on the MoNa, Peyma, and Arman datasets, respectively. These results represent state-of-the-art performance on the Persian NER task.

• ETRI Journal
• /
• v.44 no.4
• /
• pp.672-685
• /
• 2022

This article proposes a subject-independent application of brain-computer interfacing (BCI). A 32-channel Electroencephalography (EEG) device is used to measure imagined speech (SI) of four words (sos, stop, medicine, washroom) and one phrase (come-here) across 13 subjects. A deep long short-term memory (LSTM) network has been adopted to recognize the above signals in seven EEG frequency bands individually in nine major regions of the brain. The results show a maximum accuracy of 73.56% and a network prediction time (NPT) of 0.14 s which are superior to other state-of-the-art techniques in the literature. Our analysis reveals that the alpha band can recognize SI better than other EEG frequencies. To reinforce our findings, the above work has been compared by models based on the gated recurrent unit (GRU), convolutional neural network (CNN), and six conventional classifiers. The results show that the LSTM model has 46.86% more average accuracy in the alpha band and 74.54% less average NPT than CNN. The maximum accuracy of GRU was 8.34% less than the LSTM network. Deep networks performed better than traditional classifiers.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.3991-4007
• /
• 2022

In the public healthcare, a computational system that can automatically and efficiently detect and classify falls from a video sequence has significant potential. With the advancement of deep learning, which can extract temporal and spatial information, has become more widespread. However, traditional 3D CNNs that usually adopt shallow networks cannot obtain higher recognition accuracy than deeper networks. Additionally, some experiences of neural network show that the problem of gradient explosions occurs with increasing the network layers. As a result, an enhanced three-dimensional ResNet-based method for fall detection (3D-ERes-FD) is proposed to directly extract spatio-temporal features to address these issues. In our method, a 50-layer 3D residual network is used to deepen the network for improving fall recognition accuracy. Furthermore, enhanced residual units with four convolutional layers are developed to efficiently reduce the number of parameters and increase the depth of the network. According to the experimental results, the proposed method outperformed several state-of-the-art methods.