• 한국멀티미디어학회논문지
• /
• 제24권7호
• /
• pp.913-921
• /
• 2021

After arranging the general usability evaluation criteria of existing VUI researchers, this study verified how appropriate these criteria are for AI VUI specialized in navigation and the priority of their suitability. The VUI used in this study was analyzed through a survey from a total of 195 Chinese users after analyzing the navigation VUI used in China. As a result of the analysis, the usability evaluation criteria of the navigation VUI were extracted from three sub-factors of 'task accuracy', 'function satisfaction', and 'information reliability' in verifying conformance with general VUI evaluation criteria. With the recent advent of self-driving cars, safety and response speed are becoming very important, so Chinese users also ranked responsiveness as the top priority in VUI design, and the importance was also found to be high. Also, both men and women have the highest reactivity and the lowest multiplicity. VUI requires a convenient and natural interface to understand the intention between two objects through usability evaluation and verification in order to have effective interaction between humans and machines.

• 한국컴퓨터그래픽스학회논문지
• /
• 제27권5호
• /
• pp.73-79
• /
• 2021

최근 컴퓨터 애니메이션 분야에서는 기존의 유한상태기계나 그래프 기반의 방식들에서 벗어나 딥러닝을 이용한 동작 생성 방식이 많이 연구되고있다. 동작 학습에 요구되는 네트워크의 표현력은 학습해야하는 동작의 단순한 길이보다는 그 안에 포함된 동작의 다양성에 더 큰 영향을 받는다. 본 연구는 이처럼 학습해야하는 동작의 종류가 다양한 경우에 효율적인 네트워크 구조를 찾는것을 목표로 한다. 기본적인 fully-connected 구조, 여러개의 fully-connected 레이어를 병렬적으로 사용하는 mixture of experts구조, seq2seq처리에 널리 사용되는 순환신경망(RNN), 그리고 최근 시퀀스 형태의 데이터 처리를 위해 자연어 처리 분야에서 사용되고있는 transformer구조의 네트워크들을 각각 학습하고 비교한다.

• International Journal of Computer Science & Network Security
• /
• 제23권9호
• /
• pp.192-198
• /
• 2023

Cyberbullying is a growing problem among adolescents and can have serious psychological and emotional consequences for the victims. In recent years, machine learning techniques have emerged as promising approach for detecting instances of cyberbullying in online communication. This research paper focuses on developing a machine learning models that are able to detect cyberbullying including support vector machines, naïve bayes, and random forests. The study uses a dataset of real-world examples of cyberbullying collected from Twitter and extracts features that represents the ideational metafunction, then evaluates the performance of each algorithm before and after considering the theory of systemic functional linguistics in terms of precision, recall, and F1-score. The result indicates that all three algorithms are effective at detecting cyberbullying with 92% for naïve bayes and an accuracy of 93% for both SVM and random forests. However, the study also highlights the challenges of accurately detecting cyberbullying, particularly given the nuanced and context-dependent nature of online communication. This paper concludes by discussing the implications of these findings for future research and the development of practical tool for cyberbullying prevention and intervention.

• Asia pacific journal of information systems
• /
• 제29권4호
• /
• pp.771-788
• /
• 2019

Deep learning techniques such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) show superior performance in text classification than traditional approaches such as Support Vector Machines (SVMs) and Naïve Bayesian approaches. When using CNNs for text classification tasks, word embedding or character embedding is a step to transform words or characters to fixed size vectors before feeding them into convolutional layers. In this paper, we propose a parallel word-level and character-level embedding approach in CNNs for text classification. The proposed approach can capture word-level and character-level patterns concurrently in CNNs. To show the usefulness of proposed approach, we perform experiments with two English and three Korean text datasets. The experimental results show that character-level embedding works better in Korean and word-level embedding performs well in English. Also the experimental results reveal that the proposed approach provides better performance than traditional CNNs with word-level embedding or character-level embedding in both Korean and English documents. From more detail investigation, we find that the proposed approach tends to perform better when there is relatively small amount of data comparing to the traditional embedding approaches.

• Smart Structures and Systems
• /
• 제22권5호
• /
• pp.561-574
• /
• 2018

In this paper, for efficiently reducing the computational cost of the model updating during the optimization process of damage detection, the structural response is evaluated using properly trained surrogate model. Furthermore, in practice uncertainties in the FE model parameters and modelling errors are inevitable. Hence, an efficient approach based on Monte Carlo simulation is proposed to take into account the effect of uncertainties in developing a surrogate model. The probability of damage existence (PDE) is calculated based on the probability density function of the existence of undamaged and damaged states. The current work builds a framework for Probability Based Damage Detection (PBDD) of structures based on the best combination of metaheuristic optimization algorithm and surrogate models. To reach this goal, three popular metamodeling techniques including Cascade Feed Forward Neural Network (CFNN), Least Square Support Vector Machines (LS-SVMs) and Kriging are constructed, trained and tested in order to inspect features and faults of each algorithm. Furthermore, three wellknown optimization algorithms including Ideal Gas Molecular Movement (IGMM), Particle Swarm Optimization (PSO) and Bat Algorithm (BA) are utilized and the comparative results are presented accordingly. Furthermore, efficient schemes are implemented on these algorithms to improve their performance in handling problems with a large number of variables. By considering various indices for measuring the accuracy and computational time of PBDD process, the results indicate that combination of LS-SVM surrogate model by IGMM optimization algorithm have better performance in predicting the of damage compared with other methods.

• 한국생산제조학회지
• /
• 제26권1호
• /
• pp.130-136
• /
• 2017

The three-wheel pitching machine is a device that throws balls automatically instead of a pitcher and is used chiefly to train baseball players. The machine is abundantly used by people in indoor baseball grounds for baseball games. However, in Korea, foreign products are more popular because the efficiency of domestic products is poor as compared to that of the foreign ones. Therefore, a miniature pitching machine was manufactured to analyze and solve the problems of the existing machine. We added a feeder device to insert the balls in the machine and developed a smart phone application. The machine is easily controlled by a smart phone with bluetooth. While manufacturing the miniature, the existing problems were mitigated and the machine was redesigned for mass production. This study attempted to render the pitching machine more convenient and safer as a substitute for foreign pitching machines.

• 대한안전경영과학회지
• /
• 제12권1호
• /
• pp.27-33
• /
• 2010

This study surveyed the reading discomforts and the reasons for discomfortable reading of the safety and health information (texts and icons) presented on the agricultural vehicles/machines, pesticides, fertilizers, and feeds. Eighty seven people residing in rural area participated in the survey interview. Questionnaire survey showed that the most discomfortable product in reading the texts was pesticides. Forty three (49%) among participants had very-discomfortable or discomfortable in reading the texts used in the label of pesticides, and the main reason for the discomfort was small text size. The reading discomforts in reading the texts (varied from 4 point to 19 point and presented in 50 cm reading distance) showed different pattern according to the age groups. Three age groups (50s, 60s and older than 70s) showed a similar discomfort pattern, but different from the group of 30s and 40s. Forty four people (51%) had a problem in understanding the meaning of the icons and the main reasons were the small size and the difficulty in inferring the meaning of the icons. Thus, the more detailed and practical guidelines for the presentation format, particularly about the text heights and the size of icons, are required. Also, more comprehensive research is needed to investigate the readability and legibility of texts and icons.

• 한국정밀공학회지
• /
• 제31권12호
• /
• pp.1101-1106
• /
• 2014

Hybrid manufacturing technology has been advanced to overcome limitations due to traditional fabrication methods. To fabricate a micro/nano-scale structure, various manufacturing technologies such as lithography and etching were attempted. Since these manufacturing processes are limited by their materials, temperature and features, it is necessary to develop a new three-dimensional (3D) printing method. A novel nano-scale 3D printing system was developed consisting of the Nano-Particle Deposition System (NPDS) and the Focused Ion Beam (FIB) to overcome these limitations. By repeating deposition and machining processes, it was possible to fabricate micro/nano-scale 3D structures with various metals and ceramics. Since each process works in different chambers, a transfer process is required. In this research, nanoscale 3D printing system was briefly explained and an alignment algorithm for nano-scale 3D printing system was developed. Implementing the algorithm leads to an accepted error margin of 0.5% by compensating error in rotational, horizontal, and vertical axes.

• The Korean Journal of Pain
• /
• 제24권4호
• /
• pp.205-215
• /
• 2011

Background: Interventional pain management (IPM) is a branch of medical science that deals with management of painful medical conditions using specially equipped X-ray machines and anatomical landmarks. Interventional physiatry is a branch of physical medicine and rehabilitation that treats painful conditions through intervention in peripheral joints, the spine, and soft tissues. Methods: A cross-sectional study was conducted using three years of hospital records (2006 to 2008) from the Physical Medicine and Rehabilitation Department at Chittagong Medical College Hospital in Bangladesh, with a view toward highlighting current interventional pain practice in a tertiary medical college hospital. Result: The maximum amount of intervention was done in degenerative peripheral joint disorders (600, 46.0%), followed by inflammatory joint diseases (300, 23.0%), soft tissue rheumatism (300, 23.0%), and radicular or referred lower back conditions (100, 8.0%). Of the peripheral joints, the knee was the most common site of intervention. Motor stimulation-guided intralesional injection of methylprednisolone into the piriformis muscle was given in 10 cases of piriformis syndrome refractory to both oral medications and therapeutic exercises. Soft tissue rheumatism of unknown etiology was most common in the form of adhesive capsulitis (90, 64.3%), and is discussed separately. Epidural steroid injection was practiced for various causes of lumbar radiculopathy, with the exception of infective discitis. Conclusion: All procedures were performed using anatomical landmarks, as there were no facilities for the C-arm/diagnostic ultrasound required for accurate and safe intervention. A dedicated IPM setup should be a requirement in all PMR departments, to provide better pain management and to reduce the burden on other specialties.

• 한국산학기술학회논문지
• /
• 제14권9호
• /
• pp.4124-4129
• /
• 2013

본 연구는 무한궤도와 엔진 및 유압장치를 두어서 독립적으로 구동할 수 있는 탈곡기를 3차원 설계후 시제품을 제작하는 데 목적을 두었다. 탈곡기의 기능을 충실히 수행하기 위해서 탈곡통에 칼날을 나선형으로 배치하여 탈곡성능이 향상되게 하였다. 또한 뒤쪽에 배출구를 두어서 잔여부산물들이 적채되는 기존의 탈곡기 문제를 해결하였다. 부산물들이 콩과 섞여서 배출되지 않게 하려고 경사진 벨트를 내부에 두어 부산물들만 직접 송풍하도록 설계하였다. 완전히 정선된 콩만이 스크류 축을 통해서 통에 적재되면 송풍팬을 통해 배출관 파이프를 따라 이동하여 최종적으로 포장자루에 바로 담을 수 있도록 편의성을 고려하여 설계하였다. 본 독립구동방식의 콩 탈곡기 시스템은 산학협력을 통하여 국산화한 기술로서 국내 최초의 독립구동 방식의 자주형 콩 탈곡기 시스템이다.