• Journal of Computing Science and Engineering
• /
• v.10 no.3
• /
• pp.95-101
• /
• 2016

In this study, we propose a new system for constructing parallel corpora for sign languages, which are generally under-resourced in comparison to spoken languages. In order to achieve scalability and accessibility regarding data collection and corpus construction, our system utilizes deep learning-based techniques and predicts depth information to perform pose estimation on hand information obtainable from video recordings by a single RGB camera. These estimated poses are then transcribed into expressions in SignWriting. We evaluate the accuracy of hand tracking and hand pose estimation modules of our system quantitatively, using the American Sign Language Image Dataset and the American Sign Language Lexicon Video Dataset. The evaluation results show that our transcription system has a high potential to be successfully employed in constructing a sizable sign language corpus using various types of video resources.

• Journal of Internet Computing and Services
• /
• v.8 no.3
• /
• pp.85-98
• /
• 2007

In distributed computing paradigm, mobile surrogate systems have not gained wide acceptance because of security concerns that have not been suitably addressed yet. Currently even the widely used Grid middleware, Globus, does not have a host authentication mechanism, which makes it hard to provide high performance Grid computing capabilities to mobile clients. In this paper, a mobile Grid service framework is designed and implemented in order to provide Grid services to mobile host such as PDA. The surrogate host-based system allows mobile hosts to be provided with Grid services while moving. The implemented mobile Grid services system has been applied to mobile healthcare system which utilizes Grid computing for ECG signal processing. The presented system framework can be used as a secure enterprise mobile healthcare system for hospital physicians.

• Journal of KIISE:Computer Systems and Theory
• /
• v.32 no.11_12
• /
• pp.566-577
• /
• 2005

A ubiquitous computing system could be constructed not only with one computer but with networks of computers (or ether devices with computing power) embedded in everyday objects. For this, dependability must be guaranteed for each single component of a system and for the whole system which might be more than just a sum of its components. This paper proposes an autonomic self-management mechanism that ran operate for 24 hours/day with the minimum human intervention. In addition, we validate the autonomic fault management scheme based on a workload model derived from the system log analysis.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.2
• /
• pp.658-661
• /
• 2005

Internet-based client/server architecture of Contents Delivery System suffers from frequent disconnections and security treats caused by dependency of the server or overload. But, We reached the limit to the increase of the server because a contents quality enhance and Internet user explosively increase. Therefore, a P2P based computing methods are used for sloving these issues. In this paper, We implement and design the Education Content Delivery System for cyber education system using idle Computing Power in P2P computing to share computing resources. We implement not only Internet infrastructure but also satellite infrastructure system, and designed to transfer real-time or non real-time contents.

• Journal of the Semiconductor & Display Technology
• /
• v.23 no.1
• /
• pp.1-6
• /
• 2024

Recently, artificial neural networks have been playing a crucial role and advancing across various fields. Artificial neural networks are typically categorized into feedforward neural networks and recurrent neural networks. However, feedforward neural networks are primarily used for processing static spatial patterns such as image recognition and object detection. They are not suitable for handling temporal signals. Recurrent neural networks, on the other hand, face the challenges of complex training procedures and requiring significant computational power. In this paper, we propose memristors suitable for an advanced form of recurrent neural networks called reservoir computing systems, utilizing a mask processor. Using the characteristic equations of Ti/TiOx/TaOy/Pt, Pt/TiOx/Pt, and Ag/ZnO-NW/Pt memristors, we generated current-voltage curves to verify their memristive behavior through the confirmation of hysteresis. Subsequently, we trained and inferred reservoir computing systems using these memristors with the NIST TI-46 database. Among these systems, the accuracy of the reservoir computing system based on Ti/TiOx/TaOy/Pt memristors reached 99%, confirming the Ti/TiOx/TaOy/Pt memristor structure's suitability for inferring speech recognition tasks.

• Journal of Internet Computing and Services
• /
• v.6 no.5
• /
• pp.155-166
• /
• 2005

Currently, almost of all the Internet users have as many IDs as the number of sites they have subscribed for, The users should memorize and input every independent ID and password whenever they want to login to the system. Although ID management system is used to solve this problem, 10 and password management will become more complicated in the forthcoming ubiquitous computing environments because so many computers will be interconnected on various kinds of wired and wireless networks, Furthermore, it is not enough to use the existing single Circle of Trust (COT) ID management system for the forthcoming computing environments. To solve this problem, the paper proposes ID federation models in multiple COT domain and implements an ID federation system that can be scaled to mobile computing environment as well as wired computing environment. The proposed ID federation models has been verified to operate with no problem between the systems in different trust domains by doing the ID scaability test.

• Journal of KIISE:Software and Applications
• /
• v.34 no.4
• /
• pp.342-358
• /
• 2007

Ubiquitous Computing System (UCS) is a system where the user can get information through computer network anytime and anywhere regardless of the places. Since UCS is a personalized system, it should interact with other systems. UCS will bring a remarkable change in production, consumption, politics, economy, community, culture, and other areas related to our daily life. That is, a high-quality UCS results in high-quality services provided to users. Hence, this paper proposes a systematic quality model based on ISO/lEC 9126 in order to evaluate the ubiquitous computing system, based on ISO/lEC 9126. And, we identify key characteristics of UCS and derive the set of quality attributes based on identified characteristics. We define metrics for each quality attribute and Ubiquitous Computing Quality Model CUCQM) so that we can evaluate overall environment and important characteristics of UCS.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.6
• /
• pp.115-121
• /
• 2007

Recently, Location Based Service including tracking and way-finding services has been activated rapidly in the ubiquitous computing environment. According as the ubiquitous computing environment is developed, various types of sensor to acquire various data including location of the moving object are used widely, and acquired sensor data becomes abundant. However, the existing location management system based on a single location sensor is difficult to support LBS efficiently in the ubiquitous computing environment. In this paper, therefore, we propose the location management system in the ubiquitous computing environment that can manage the location data and the various sensor data efficiently. In addition, the location management system adopts the core technology for efficiently storing and transferring a large-volume of various data such as location data and for efficiently processing the various requests from a variety of servers and sensors. Especially, our architecture that is presented in this paper can support context-aware services and autonomous services efficiently in the ubiquitous computing environment.

• Journal of Korea Society of Industrial Information Systems
• /
• v.11 no.5
• /
• pp.141-149
• /
• 2006

Ubiquitous computing environment means the computing environment that has taken its position so closely with the ordinary living so much like air or water. In building up the U-Korea, one of the important issues is the social issue from the drasticincrease of senior population. The contemporary society has its distinct trend in increase of senior household following the nuclear family orientation, increase of working parents with the advancement of women in society, unable to support seniors for long distance or short distance of business trip and other reasons that the need of senior welfare has been ever more felt. Accordingly, the Ministry of Government Affairs and Home Administration has developed the wireless paging system to make prompt response system for 119 Rescue when the single senior is encountered with emergency situation that is has been widely provided for the socially neglected people such as single senior, the disabled persons and others. Currently, the wireless paging system is operated as the sub-system for emergency rescue informationsystem, but due to the lack of reliability of product, problems of terminal portable transmitter, receptor and others, rejection of beneficiary and lack of knowledge in use, insufficient management and supervision of managing officers, the efficiency has been declined that there is a need of development for the system. Therefore, this study proposes the context aware information structure of the subject of ubiquitous wireless paging system required forthe development of the wireless paging system model of ubiquitous environment that improved the problems of currently operated wireless paging system.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.2
• /
• pp.43-50
• /
• 2018

Biometric information computing is greatly influencing both a computing system and Big-data system based on the bio-information system that combines bio-signal sensors and bio-information processing. Unlike conventional data formats such as text, images, and videos, biometric information is represented by text-based values that give meaning to a bio-signal, important event moments are stored in an image format, a complex data format such as a video format is constructed for data prediction and analysis through time series analysis. Such a complex data structure may be separately requested by text, image, video format depending on characteristics of data required by individual biometric information application services, or may request complex data formats simultaneously depending on the situation. Since previous bio-information processing computing systems depend on conventional computing component, computing structure, and data processing method, they have many inefficiencies in terms of data processing performance, transmission capability, storage efficiency, and system safety. In this study, we propose an improved biosensing converged big data computing architecture to build a platform that supports biometric information processing computing effectively. The proposed architecture effectively supports data storage and transmission efficiency, computing performance, and system stability. And, it can lay the foundation for system implementation and biometric information service optimization optimized for future biometric information computing.