• Phonetics and Speech Sciences
• /
• v.14 no.4
• /
• pp.57-66
• /
• 2022

In this study, the definition of "digital therapeutics" was clarified by examining related studies, and the development trend of digital therapeutics at the domestic level was investigated. Further, research data and technologies applied to various communication disorders since 2015 were analyzed. From all these, digital therapeutics can be defined as software that can support evidence-based treatment when used on patients to prevent, manage, and treat disorders With huge investments and research efforts increasingly made in the field of digital therapeutics, 17 of the 22 studies examined were on digital therapeutics applied in the treatment of language disorders. In the research papers examined, the technologies applied were virtual reality and augmented reality, with augmented reality used in most cases. The effects of applying digital treatment were positive, and most studies focused on content development in relation to the development of digital treatment, although one study was conducted for app development. Future studies could examine the application of digital therapeutics to more diverse communication disorder subjects. Active government support is expected in developing more sophisticated software that can be applied using a wider range of technologies in the field of digital therapeutics to treat more communication disorders.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.6
• /
• pp.381-389
• /
• 2023

One of the crucial components in building information modeling (BIM) is data. To systematically manage these data, various research studies have focused on the creation of object breakdown structures and property sets. Specifically, crucial data for managing programs and payments involves work breakdown structures (WBSs) and cost breakdown structures (CBSs), which are indispensable for mapping BIM objects. Achieving this requires disassembling CBS quantities based on 3D objects and WBS. However, this task is highly tedious owing to the large volume of CBS and divergent coding practices employed by different organizations. Manual processes, such as those based on Excel, become nearly impossible for such extensive tasks. In response to the challenge of computing quantities that are difficult to derive from BIM objects, this study presents methods for disassembling length-based quantities, incorporating significant portions of the bill of quantities (BOQs). The proposed approach recommends suitable CBS by leveraging the accumulated history of WBS-CBS mapping databases. Additionally, it establishes a unified CBS code, facilitating the effective operation of CBS databases.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.6
• /
• pp.525-530
• /
• 2023

Digital drawing subjects require the subdivision of evaluation elements and the graduality of evaluation according to the recent movement of the innovative curriculum. The purpose of this paper is to present the criteria for evaluating the drawing and to propose it as a rubric evaluation. In the text, criteria for beginner evaluation were technical skills such as the accuracy and consistency of the line, the ratio and balance of the picture, and the ability to effectively utilize various brushes and tools at the intermediate levels. In the advanced evaluation section, it is a part of a new perspective or originality centered on creativity and originality, and a unique perspective or interpretation of a given subject. In addition, as an understanding of design principles, the evaluation of completeness was derived focusing on the ability to actively utilize various functions of digital drawing software through design principles such as placement, color, and shape. The importance of introducing rubric evaluation is to allow instructors to make objective and consistent evaluations, and the key to research in rubric evaluation in these art subjects is to help learners clearly grasp their strengths and weaknesses, and learners can identify what needs to be improved and develop better drawing skills accordingly through feedback on each item.

• International Journal of Internet, Broadcasting and Communication
• /
• v.12 no.1
• /
• pp.67-72
• /
• 2020

The fifth generation (5G) mobile communication has an impact on the human life over the whole world, nowadays, through the artificial intelligence (AI) and the internet of things (IoT). The low latency of the 5G new radio (NR) access is implemented by the state-of-the art technologies, such as non-orthogonal multiple access (NOMA). This paper investigates a practical issue that in NOMA, for the practical channel models, such as fading channel environments, the successive interference cancellation (SIC) should be performed on the stronger channel users with low power allocation. Only if the SIC is performed on the user with the stronger channel gain, NOMA performs better than orthogonal multiple access (OMA). Otherwise, NOMA performs worse than OMA. Such the superiority requirement can be easily implemented for the channel being static or slow varying, compared to the block interval time. However, most mobile channels experience fading. And symbol by symbol channel estimations and in turn each symbol time, selections of the SIC-performing user look infeasible in the practical environments. Then practically the block of symbols uses the single channel estimation, which is obtained by the training sequence at the head of the block. In this case, not all the symbol times the SIC is performed on the stronger channel user. Sometimes, we do perform the SIC on the weaker channel user; such cases, NOMA performs worse than OMA. Thus, we can say that by what percent NOMA is better than OMA. This paper calculates analytically the percentage by which NOMA performs better than OMA in the practical mobile communication systems. We show analytically that the percentage for NOMA being better than OMA is only the function of the ratio of the stronger channel gain variance to weaker. In result, not always, but almost time, NOMA could perform better than OMA.

• Journal of the Korean association of regional geographers
• /
• v.1 no.1
• /
• pp.61-68
• /
• 1995

The writers study on the development and the prospect of computer map based on the most recent computer mapping technical aspects. We also study domestic prospect of computer map in connection with the present condition of domestic GIS. The main results are as follows: (1) Computer map has rapidly developed in spite of its short history. We expect that computer map will be improved more in the future owing to the development of computer hardware and software. Most mapping processes will be possible sooner or later owing to Artificial Intelligence(AI) and more improved scanner without human effort. (2) Computer map can be used for various industrial fields and its development can give a great help for technical advance in correlated industries. (3) Computer map has really developed in the country since 1980, when GIS was introduced. Especially, government planned to digitalize all the basic topographical maps covering the whole country between 1996-1998. We think that there is an epoch-making change in the development history of computer map in the future. (4) The development of GIS is closely connected with one of computer map, but the recent technical levels of GIS is not perfect. So there is an urgent need for technical supplement to produce good computer maps. (5) The government had better construct GIS database in order to cut down expenses derived from overlapping input of data by individual users and there is a need for data standard.

• Journal of KIISE:Software and Applications
• /
• v.30 no.3_4
• /
• pp.251-258
• /
• 2003

A support vector machine (SVM) is supposed to provide a good generalization performance, but the actual performance of a actually implemented SVM is often far from the theoretically expected level. This is largely because the implementation is based on an approximated algorithm, due to the high complexity of time and space. To improve this limitation, we propose ensemble of SVMs by using Bagging (bootstrap aggregating) and Boosting. By a Bagging stage each individual SVM is trained independently using randomly chosen training samples via a bootstrap technique. By a Boosting stage an individual SVM is trained by choosing training samples according to their probability distribution. The probability distribution is updated by the error of independent classifiers, and the process is iterated. After the training stage, they are aggregated to make a collective decision in several ways, such ai majority voting, the LSE(least squares estimation) -based weighting, and double layer hierarchical combining. The simulation results for IRIS data classification, the hand-written digit recognition and Face detection show that the proposed SVM ensembles greatly outperforms a single SVM in terms of classification accuracy.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.11
• /
• pp.2167-2175
• /
• 2017

In recent years, an IoT is dramatically developing according to the enhancement of AI, the increase of connected devices, and the high-performance cloud systems. Huge data produced by many devices and sensors is expanding the scope of services, such as an intelligent diagnostics, a recommendation service, as well as a smart monitoring service. The studies of edge computing are limited as a role of small server system with high quality HW resources. However, there are specialized requirements in a smart factory domain needed edge computing. The edges are needed to pre-process containing tiny filtering, pre-formatting, as well as merging of group contexts and manage the regional rules. So, in this paper, we extract the features and requirements in a scope of efficiency and robustness. Our edge offers to decrease a network resource consumption and update rules and learning models. Moreover, we propose architecture of edge computing based on learning factors sharing with a cloud system in a smart factory.

• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1314-1320
• /
• 2019

In this paper, we propose a new method for optimizing bit operations and applying them to DNN(Deep Neural Network) in software environment. As a method for this, we propose a packing function for bitwise optimization and a masking matrix multiplication operation for application to DNN. The packing function converts 32-bit real value to 2-bit quantization value through threshold comparison operation. When this sequence is over, four 32-bit real values are changed to one 8-bit value. The masking matrix multiplication operation consists of a special operation for multiplying the packed weight value with the normal input value. And each operation was then processed in parallel using a GPU accelerator. As a result of this experiment, memory saved about 16 times than 32-bit DNN Model. Nevertheless, the accuracy was within 1%, similar to the 32-bit model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.8
• /
• pp.3567-3582
• /
• 2020

Human activities are often affected by weather conditions. Automatic weather recognition is meaningful to traffic alerting, driving assistance, and intelligent traffic. With the boost of deep learning and AI, deep convolutional neural networks (CNN) are utilized to identify weather situations. In this paper, a three-channel convolutional neural network (3C-CNN) model is proposed on the basis of ResNet50.The model extracts global weather features from the whole image through the ResNet50 branch, and extracts the sky and ground features from the top and bottom regions by two CNN5 branches. Then the global features and the local features are merged by the Concat function. Finally, the weather image is classified by Softmax classifier and the identification result is output. In addition, a medium-scale dataset containing 6,185 outdoor weather images named WeatherDataset-6 is established. 3C-CNN is used to train and test both on the Two-class Weather Images and WeatherDataset-6. The experimental results show that 3C-CNN achieves best on both datasets, with the average recognition accuracy up to 94.35% and 95.81% respectively, which is superior to other classic convolutional neural networks such as AlexNet, VGG16, and ResNet50. It is prospected that our method can also work well for images taken at night with further improvement.

• Journal of the East Asian Society of Dietary Life
• /
• v.24 no.1
• /
• pp.42-52
• /
• 2014

The aim of this investigation was to assess the relationship between food habits and nutrient intake in college female students. Nutrient intakes of 149 female subjects aged 19.3 y were determined by using 24-hr recall. The questionnaire included general characteristics and food habits (frequency of breakfast and fast food intake). Body composition was determined by bioim- pedance analysis. Nutrient analysis was performed with Can pro software. Statistics were generated using SAS 9.3 (SAS Institute, Cary, NC). Mean intake of energy, fiber, calcium, potassium. vitamin $B_2$ and vitamin C by the subjects ware below KDRIs. The nutrients for which the largest proportion of subjects showed inadequate intakes (less than the RI or AI) were potassium, calcium, vitamin C and fiber. Subjects that consumed fast food ${\leq}6$ times showed significantly lower intakes of calcium, potassium, fiber, vitamin A, vitamin $B_6$ and vitamin C. Subjects who skipped breakfast more frequently showed significantly lower intakes of energy, carbohydrate, fiber, calcium, iron, potassium, vitamin $B_2$ and vitamin C than subjects who ate breakfast more frequently. This is strong evidence that higher intakes of nutrients such as potassium, fiber, and calcium are associated with increased frequency of eating breakfast or decreased frequency of eating fast food. Low calcium, fiber, and potassium intakes may thus lead to chronic diseases. Nutrition education can be an important facilitator for improving nutrient intakes.