• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.9
• /
• pp.2109-2116
• /
• 2014

This paper presents the implementation and design of the advanced WI-FI systems with beam-forming antenna that radiate their power to the direction of user equipment to improve the overall throughput, contrast to the general WI-FI systems equipped with omni-antenna. The system consists of patch array antenna, DSP, FPGA, and Qualcomm's commercial chip. The beam-forming system on the FPGA utilizes the packet information from Qualcomm's commercial chip to control the phase shifters and attenuators of the patch array antenna. The PCI express interface has been used to maximize the communication speed between DSP and FPGA. The directions of arrival of users are managed using the database, and each user is distinguished by the MAC address given from the packet information. When the system wants to transmit a packet to one user, it forms beams to the direction of arrival of the corresponding user stored in the database to maximize the throughput. Directions of arrival of users are estimated using the received preamble in the packet to make its SINR as high as possible. The proposed beam-forming system was implemented using an FPGA and Qualcommm's commercial chip together. The implemented system showed considerable throughput improvement over the existing general AP system with omni-directional antenna in the multi-user communication environment.

• Journal of Broadcast Engineering
• /
• v.24 no.3
• /
• pp.495-505
• /
• 2019

Typical algorithms of deep learning include CNN(Convolutional Neural Networks), which are mainly used for image recognition, and RNN(Recurrent Neural Networks), which are used mainly for speech recognition and natural language processing. Among them, CNN is able to learn from filters that generate feature maps with algorithms that automatically learn features from data, making it mainstream with excellent performance in image recognition. Since then, various algorithms such as R-CNN and others have appeared in object detection to improve performance of CNN, and algorithms such as YOLO(You Only Look Once) and SSD(Single Shot Multi-box Detector) have been proposed recently. However, since these deep learning-based detection algorithms determine the success of the detection in the still images, stable object tracking and detection in the video requires separate tracking capabilities. Therefore, this paper proposes a method of combining Kalman filters into deep learning-based detection networks for improved object tracking and detection performance in the video. The detection network used YOLO v2, which is capable of real-time processing, and the proposed method resulted in 7.7% IoU performance improvement over the existing YOLO v2 network and 20 fps processing speed in FHD images.

• Journal of Korean Neurosurgical Society
• /
• v.64 no.1
• /
• pp.125-135
• /
• 2021

Objective : This study aimed to validate the Korean version of the Repeatable Battery for the Assessment of Neuropsychological Status Update (K-RBANS). Methods : We performed a retrospective analysis of 283 psychiatric and neurosurgery patients. To investigate the convergent validity of the K-RBANS, correlation analyses were performed for other intelligence and neuropsychological test results. Confirmatory factor analysis was used to test a series of alternative plausible models of the K-RBANS. To analyze the various capabilities of the K-RBANS, we compared the area under the receiver operating characteristic (ROC) curves (AUC). Results : Significant correlations were observed, confirming the convergent validity of the K-RBANS among the Total Scale Index (TSI) and indices of the K-RBANS and indices of intelligence (r=0.47-0.81; p<0.001) and other neuropsychological tests at moderate and above significance (r=0.41-0.63; p<0.001). Additionally, the results testing the construct validity of the K-RBANS showed that the second-order factor structure model (model 2, similar to an original factor structure of RBANS), which includes a first-order factor comprising five index scores (immediate memory, visuospatial capacity, language, attention, delayed memory) and one higher-order factor (TSI), was statistically acceptable. The comparative fit index (CFI) (CFI, 0.949) values and the goodness of fit index (GFI) (GFI, 0.942) values higher than 0.90 indicated an excellent fit. The root mean squared error of approximation (RMSEA) (RMSEA, 0.082) was considered an acceptable fit. Additionally, the factor structure of model 2 was found to be better and more valid than the other model in χ2 values (Δχ2=7.69, p<0.05). In the ROC analysis, the AUCs of the TSI and five indices were 0.716-0.837, and the AUC of TSI (AUC, 0.837; 95% confidence interval, 0.760-0.896) was higher than the AUCs of the other indices. The sensitivity and specificity of TSI were 77.66% and 78.12%, respectively. Conclusion : The overall results of this study suggest that the K-RBANS may be used as a valid tool for the brief screening of neuropsychological patients in Korea.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.6
• /
• pp.489-495
• /
• 2020

The amount of data is increasing through various IT devices in a hyper-connected society where the 4th revolution is progressing, and new value can be created by analyzing that data. This paper was collected total 1,526 articles from 2017 to 2019 in central magazines, economic magazines, regional associations, and major broadcasting companies with the keyword "(East Coast Tourism or East Coast Travel) and Gangwon-do" through Bigkinds. It was performed the topic modeling using LDA algorithm implemented in the R language to analyze the collected 1,526 articles. It was extracted keywords for each year from 2017 to 2019, and classified and compared keywords with high frequency for each year. It was setted the optimal number of topics to 8 using Log Likelihood and Perplexity, and then inferred 8 topics using the Gibbs Sampling method. The inferred topics were Gangneung and Beach, Goseong and Mt.Geumgang, KTX and Donghae-Bukbu line, weekend sea tour, Sokcho and Unification Observatory, Yangyang and Surfing, experience tour, and transportation network infra. The changes of articles on East coast tourism was was analyzed using the proportion of the inferred eight topics. As the result, the proportion of Unification Observatory and Mt. Geumgang showed no significant change, the proportion of KTX and experience tour increased, and the proportion of other topics decreased in 2018 compared to 2017. In 2019, the proportion of KTX and experience tour decreased, but the proportion of other topics showed no significant change.

• Phonetics and Speech Sciences
• /
• v.13 no.2
• /
• pp.57-66
• /
• 2021

This study focuses on the issue of automatic severity classification of dysarthric speakers based on speech intelligibility. Speech intelligibility is a complex measure that is affected by the features of multiple speech dimensions. However, most previous studies are restricted to using features from a single speech dimension. To effectively capture the characteristics of the speech disorder, we extracted features of multiple speech dimensions: voice quality, prosody, and pronunciation. Voice quality consists of jitter, shimmer, Harmonic to Noise Ratio (HNR), number of voice breaks, and degree of voice breaks. Prosody includes speech rate (total duration, speech duration, speaking rate, articulation rate), pitch (F0 mean/std/min/max/med/25quartile/75 quartile), and rhythm (%V, deltas, Varcos, rPVIs, nPVIs). Pronunciation contains Percentage of Correct Phonemes (Percentage of Correct Consonants/Vowels/Total phonemes) and degree of vowel distortion (Vowel Space Area, Formant Centralized Ratio, Vowel Articulatory Index, F2-Ratio). Experiments were conducted using various feature combinations. The experimental results indicate that using features from all three speech dimensions gives the best result, with a 80.15 F1-score, compared to using features from just one or two speech dimensions. The result implies voice quality, prosody, and pronunciation features should all be considered in automatic severity classification of dysarthria.

• Journal of Industrial Convergence
• /
• v.19 no.6
• /
• pp.11-19
• /
• 2021

The purpose of this study is to explore trends in research at home and abroad related to "Sport Facilities", and seek the direction of further research. 1,801 abstracts of papers including "Sport Facilities" were collected from the SCOPUS DB from 2016 to 2020. Topic modeling techniques based on Latent Dirichlet Allocation (LDA) algorithm implemented in R language, TD-IDF techniques, and word cluds using Tagxedo was conducted to analyze the data. As a result, 8 topics were optimally determined, and "sports", "facilities", "health", "physical", "data", and "using" were derived as the main keywords for topics. This results indicated that studies on physical activity, health and using facilities regarding sports facilities at home and abroad have been actively carried out in recent years. This indicates that papers in SCOPUS DB are paying attention to the instrumental value of sport facilities, such as health promotion and improving the quality of life. Therefore, various studies that help participants who use sport facilities for a healthy life should be continuously conducted in the future.

• Therapeutic Science for Rehabilitation
• /
• v.10 no.4
• /
• pp.81-94
• /
• 2021

Objective : Response time plays a prominent part in research on cognitive ability and the aging effect. This study aimed to identify the impact of cognitive ability on information processing by conducting cognitive response time (CRT) using a computer program. Methods : This study was conducted in 30 normal elderly (NE) and 30 elderly with amnestic MCI (aMCI), aged 65-79 years old living in Daegu and Gyeongbuk. The results were analyzed using the statistical analysis program R 4.0.2 (University of Auckland, New Zealand). Results : In the three sub-areas of CRT, the total response time showed a significant difference depending on group or age, and the error rate showed a significant difference depending on age or group in some sub-areas. In the aMCI group, the performance of CRT significantly correlated with that of the overall cognition and memory test. Conclusion : Information processing depending on aging or cognitive ability and the differential performance of processing speed could be observed through CRT. The performance of this test was found to be significantly correlated with that of the overall cognition and memory test. Therefore, CRT could be used meaningfully as a simplified tool to predict the initial cognitive disorder of the elderly in the community.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.31-31
• /
• 2023

During December 2022, the northeast monsoon, which dominates the south and the Gulf of Thailand, had significant rainfall that impacted the lower southern region, causing flash floods, landslides, blustery winds, and the river exceeding its bank. The Golok River, located in Narathiwat, divides the border between Thailand and Malaysia was also affected by rainfall. In flood management, instruments for measuring precipitation and water level have become important for assessing and forecasting the trend of situations and areas of risk. However, such regions are international borders, so the installed measuring telemetry system cannot measure the rainfall and water level of the entire area. This study aims to predict 72 hours of water level and evaluate the situation as information to support the government in making water management decisions, publicizing them to relevant agencies, and warning citizens during crisis events. This research is applied to machine learning (ML) for water level prediction of the Golok River, Lan Tu Bridge area, Sungai Golok Subdistrict, Su-ngai Golok District, Narathiwat Province, which is one of the major monitored rivers. The eXtreme Gradient Boosting (XGBoost) algorithm, a tree-based ensemble machine learning algorithm, was exploited to predict hourly water levels through the R programming language. Model training and testing were carried out utilizing observed hourly rainfall from the STH010 station and hourly water level data from the X.119A station between 2020 and 2022 as main prediction inputs. Furthermore, this model applies hourly spatial rainfall forecasting data from Weather Research and Forecasting and Regional Ocean Model System models (WRF-ROMs) provided by Hydro-Informatics Institute (HII) as input, allowing the model to predict the hourly water level in the Golok River. The evaluation of the predicted performances using the statistical performance metrics, delivering an R-square of 0.96 can validate the results as robust forecasting outcomes. The result shows that the predicted water level at the X.119A telemetry station (Golok River) is in a steady decline, which relates to the input data of predicted 72-hour rainfall from WRF-ROMs having decreased. In short, the relationship between input and result can be used to evaluate flood situations. Here, the data is contributed to the Operational support to the Special Water Resources Management Operation Center in Southern Thailand for flood preparedness and response to make intelligent decisions on water management during crisis occurrences, as well as to be prepared and prevent loss and harm to citizens.

• The Journal of Bigdata
• /
• v.6 no.2
• /
• pp.71-84
• /
• 2021

Since small and medium-sized enterprises fell short of the securement of technological competitiveness in the field of big data and artificial intelligence (AI) field-core technologies of the Fourth Industrial Revolution, it is important to strengthen the competitiveness of the overall industry through technology commercialization. In this study, we aimed to propose a priority related to technology transfer and commercialization for practical use of public research results. We utilized public research performance information, improving missing values of 6T classification by deep learning model with an ensemble method. Then, we conducted topic modeling to derive the converging fields of big data and AI. We classified the technology fields into four different segments in the technology portfolio based on technology activity and technology efficiency, estimating the potential of technology commercialization for those fields. We proposed a priority of technology commercialization for 10 detailed technology fields that require long-term investment. Through systematic analysis, active utilization of technology, and efficient technology transfer and commercialization can be promoted.

• Information Systems Review
• /
• v.25 no.1
• /
• pp.93-110
• /
• 2023

Recently, attempts have been made to convert unstructured text into vectors and to analyze vast amounts of natural language for various purposes. In particular, the demand for analyzing texts in specialized domains is rapidly increasing. Therefore, studies are being conducted to analyze specialized and general-purpose documents simultaneously. To analyze specific terms with general terms, it is necessary to align the embedding space of the specific terms with the embedding space of the general terms. So far, attempts have been made to align the embedding of specific terms into the embedding space of general terms through a transformation matrix or mapping function. However, the linear transformation based on the transformation matrix showed a limitation in that it only works well in a local range. To overcome this limitation, various types of nonlinear vector alignment methods have been recently proposed. We propose a vector alignment model that matches the embedding space of specific terms to the embedding space of general terms through end-to-end learning that simultaneously learns the autoencoder and regression model. As a result of experiments with R&D documents in the "Healthcare" field, we confirmed the proposed methodology showed superior performance in terms of accuracy compared to the traditional model.