• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.9 no.3
• /
• pp.249-256
• /
• 2016

Recently, a number of techniques to ensure the free walking for the visually impaired and transportation vulnerable have been studied. As a device for free walking, there are such as a smart cane and smart glasses to use the computer vision, ultrasonic sensor, acceleration sensor technology. In a typical technique, such as techniques for finds object and detect obstacles and walking area and recognizes the symbol information for notice environment information. In this paper, we studied recognization algorithm of the selected symbols that are required to visually impaired, with the deep learning algorithm. As a results, Use CNN(Convolutional Nueral Network) technique used in the field of deep-learning image processing, and analyzed by comparing through experimentation with various deep learning architectures.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.9
• /
• pp.1279-1292
• /
• 2022

This study proposes a non-contact input method based on face recognition and Pyautogui mouse control as a system that can help users who have difficulty using input devices such as conventional mouse due to physical discomfort. This study includes features that help web surfing more conveniently, especially screen zoom, scroll function, and also solves the problem of eye fatigue, which has been suggested as a limitation in existing non-contact input systems. In addition, various set values can be adjusted in consideration of individual physical differences and Internet usage habits. Furthermore, no high-performance CPU or GPU environment is required, and no separate tracker devices or high-performance cameras are required. Through these studies, we intended to contribute to the realization of barrier-free access by increasing the web accessibility of the disabled and the elderly who find it difficult to use web content.

• Design Convergence Study
• /
• v.15 no.3
• /
• pp.117-131
• /
• 2016

The introduction of comprehensive programming channels has led to a diversity in the viewers' tastes and excessive competition between TV channels. Demand for channels on well-being is also increasing, due to the well-being and green consumption trends. This study conducted a case study on domestic and international channel branding strategies as well as an analysis on Korean channels focusing on well-being and lifestyle and found that there are no TV channels which provides comprehensive well-being information on food, clothing and housing at the moment in Korea. This study further discovered that information on such topics are currently provided in a tidbit fashion via educational or entertainment programs. Therefore, this study presented strategies for a well-being lifestyle channel brand and designed the brand mark and a station ID for the channel. This study conducted a survey targeting 50 men and women over 20 who have participated in environment-related projects for an objective verification of the channel brand strategies and design. The survey showed that the respondents were generally positive towards the necessity of the channel and of the content presented by this researcher. Some of the respondents, however, pointed out that the readability of the brand mark needs to be improved. This was reflected in the improved design and a survey comparing the two designs showed positive results. The results of this study will contribute to the launch of a well-being lifestyle channel targeting green consumers in the future.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.44 no.10
• /
• pp.1567-1582
• /
• 2015

The purpose of this study was to examine the status of environmentally-friendly ingredients and dietitians' perceptions toward them in order to find for improvement. Data was collected from questionnaires completed by 202 school dietitians and nutrition teachers in Chungbuk, and this data was analyzed utilizing the SPSS 20.0 program. The results obtained from this study were as follows: 'mixed grains (58.9%)' and 'eggs (36.6%)' were found to be the most used environmentally-friendly ingredients. 81.7% of the respondents said they 'never used' marine products, whereas 'fruits (43.6%)', 'pork (40.8%)', and 'fish (54.5%)' were the most preferred ingredients. Dietitians and nutrition teachers used environmentally-friendly marine products less than other ingredients, had a poor understanding about environmentally-friendly marine products, and demonstrated low reliability and belief in the necessity of the system. In order to verify the environmentally-friendly status of the ingredients, marks on the product and documents of certification were mostly used. In order to improve the supply system, a more strict tracking system in the distribution process by securing more reliable suppliers is required.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.5
• /
• pp.447-453
• /
• 2020

In this paper, we propose a system to extract effective speaker representations from a speech signal using a deep learning method. Based on the fact that speech signal contains identity unrelated information such as text content, emotion, background noise, and so on, we perform a training such that the extracted features only represent speaker-related information but do not represent speaker-unrelated information. Specifically, we propose an auto-encoder based disentanglement method that outputs both speaker-related and speaker-unrelated embeddings using effective loss functions. To further improve the reconstruction performance in the decoding process, we also introduce a discriminator popularly used in Generative Adversarial Network (GAN) structure. Since improving the decoding capability is helpful for preserving speaker information and disentanglement, it results in the improvement of speaker verification performance. Experimental results demonstrate the effectiveness of our proposed method by improving Equal Error Rate (EER) on benchmark dataset, Voxceleb1.

• The KIPS Transactions:PartB
• /
• v.14B no.3 s.113
• /
• pp.183-190
• /
• 2007

VoiceXML is new markup language which is designed for web resource navigation via voice based on XML. An application using VoiceXML is classified into mutual-controlled and machine-controlled form dialog structure. Such dialog structures can't construct service which provide free navigation of web resource by user because a scenario is decided by application developer. In this paper, we propose VoiceXML application structure using user-controlled form dialog system which decide service scenario according to user's intention. The proposed application automatically detects recognition candidates from requested information by user, and then system uses recognition candidate as voice-anchor. Also, system connects each voice-anchor with new voice-node. An example of proposed system, we implement news service with IT term dictionary, and we confirm detection and registration of voice-anchor and make an estimate of hit rate about measurement of an successive offer from information according to user's intention and response speed. As the experiment result, we confirmed possibility which is more freely navigation of web resource than existing VoiceXML form dialog systems.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.7
• /
• pp.1759-1769
• /
• 1997

The Error BackPropagation (EBP) algorithm for multi-layered neural networks is widely used in various areas such as associative memory, speech recognition, pattern recognition and robotics, etc. Nevertheless, many researchers have continuously published papers about improvements over the original EBP algorithm. The main reason for this research activity is that EBP is exceeding slow when the number of neurons and the size of training set is large. In this study, we developed new learning speed acceleration methods using variable learning rate, variable momentum rate and variable slope for the sigmoid function. During the learning process, these parameters should be adjusted continuously according to the total error of network, and it has been shown that these methods significantly reduced learning time over the original EBP. In order to show the efficiency of the proposed methods, first we have used binary data which are made by random number generator and showed the vast improvements in terms of epoch. Also, we have applied our methods to the binary-valued Monk's data, 4, 5, 6, 7-bit parity checker and real-valued Iris data which are famous benchmark training sets for machine learning.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.12
• /
• pp.509-516
• /
• 2022

Accurate pose prediction of objects in 3D space is an important visual recognition technique widely used in many applications such as scene understanding in both indoor and outdoor environments, robotic object manipulation, autonomous driving, and augmented reality. Most previous works for object pose estimation have the limitation that they require an exact 3D CAD model for each object. Unlike such previous works, this paper proposes a novel neural network model that can predict the poses of unknown objects based on only their RGB color images without the corresponding 3D CAD models. The proposed model can obtain depth maps required for unknown object pose prediction by using an adaptive depth estimator, AdaBins,. In this paper, we evaluate the usefulness and the performance of the proposed model through experiments using benchmark datasets.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.9
• /
• pp.913-917
• /
• 2010

To inspect the defects of printed markings on the surface of IC package, the OCV (Optical Character Verification) method based on NCC (Normalized Correlation Coefficient) pattern matching is widely used. In order to detect the micro pattern defects appearing on the small portion of the markings, a Partitioned NCC pattern matching method was proposed to overcome the limitation of the NCC pattern matching. In this method, the reference pattern is first partitioned into several blocks and the NCC values are computed and are combined in these small partitioned blocks, rather than just using the NCC value for the whole reference pattern. In this paper, we proposed a method to decide the proper number of partition blocks and a method to inspect and combine the NCC values of each partitioned block to identify the defective markings.

• Proceedings of the KIEE Conference
• /
• 2008.11a
• /
• pp.302-304
• /
• 2008

2003년 8월 미국 북미지역과 동년 9월 이태리, 스웨던/덴마크에서 발생한 광역정전과 더불어 영국과 말레시아, 이태리에서도 대규모 정전이 발생하여 지진, 태풍에 의한 자연재해에 버금가는 엄청난 사회적 혼란과 더불어 막대한 경제적 손실을 초래했던 사실은, 이제 전력공급의 중단(정전)이란 결코 용인될 수 없는 사회적 실정에 이르렀음을 극명히 보여준 사례라 할 수 있다. 또한, 북미와 유럽의 대규모 광역정전 발생의 원인 중에서 계통운영자의 부적절한 상황인식과 지휘체제 혼란으로 신속하게 대처하지 못한 점이 주된 원인중의 하나로 지적되면서, 전력계통 운영의 현업에 종사하고 있는 계통운영자의 막중하고 중대한 소임을 다시 한번 자각시켜 주는 계기가 되었다. 이러한 맥락으로 미국을 중심, 전세계적으로 대규모 전력계통 운영환경하에서 계통운영자에게 방대한 정보를 신속하고 효과적으로 제공해야 할 시각화의 필요성이 대두되는 계기가 되었다. 본 논문은 전력계통 데이터의 시각화 기법에 있어 해외기술동향을 살펴보고, 전력거래소의 시각화 화면의 개발 사례 및 향후계획 등에 대해 소개하고자 한다.