• Journal of Korea Multimedia Society
• /
• v.19 no.8
• /
• pp.1498-1504
• /
• 2016

The progress of mobile computing technology is bringing a large amount of multimedia contents such as image. Thus, we need an image retrieval system which searches semantically relevant image. In this paper, we propose a semantic image annotation and retrieval in mobile environments. Previous mobile-based annotation approaches cannot fully express the semantics of image due to the limitation of current form (i.e., keyword tagging). Our approach allows mobile devices to annotate the image automatically using the context-aware information such as temporal and spatial data. In addition, since we annotate the image using RDF(Resource Description Framework) model, we are able to query SPARQL for semantic image retrieval. Our system implemented in android environment shows that it can more fully represent the semantics of image and retrieve the images semantically comparing with other image annotation systems.

• Journal of information and communication convergence engineering
• /
• v.19 no.3
• /
• pp.148-154
• /
• 2021

With the advent of context-aware computing, many attempts were made to understand emotions. Among these various attempts, Speech Emotion Recognition (SER) is a method of recognizing the speaker's emotions through speech information. The SER is successful in selecting distinctive 'features' and 'classifying' them in an appropriate way. In this paper, the performances of SER using neural network models (e.g., fully connected network (FCN), convolutional neural network (CNN)) with Mel-Frequency Cepstral Coefficients (MFCC) are examined in terms of the accuracy and distribution of emotion recognition. For Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) dataset, by tuning model parameters, a two-dimensional Convolutional Neural Network (2D-CNN) model with MFCC showed the best performance with an average accuracy of 88.54% for 5 emotions, anger, happiness, calm, fear, and sadness, of men and women. In addition, by examining the distribution of emotion recognition accuracies for neural network models, the 2D-CNN with MFCC can expect an overall accuracy of 75% or more.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.1305-1308
• /
• 2013

본 논문에서는 스마트폰 사용자의 실시간 상황 인식을 위한 효과적인 사운드 분류 시스템을 제안한다. 이 시스템에서는 PCM 형태의 사운드 입력 데이터에 대한 전처리를 통해 고요한 사운드와 화이트 노이즈를 학습 및 분류 단계 이전에 미리 여과함으로써, 계산 자원의 불필요한 소모를 막을 수 있다. 또한 에너지 레벨이 낮아 신호의 패턴을 파악하기 어려운 사운드 데이터는 증폭함으로써, 이들에 대한 분류 성능을 향상시킬 수 있다. 또, 제안하는 사운드 분류 시스템에서는 HMM 분류 모델의 효율적인 학습과 적용을 위해 k-평균 군집화를 이용하여 특징 벡터들에 대한 차원 축소와 이산화를 수행하고, 그 결과를 모아 일정한 길이의 시계열 데이터를 구성하였다. 대학 연구동내 다양한 일상생활 상황들에서 수집한 8가지 유형의 사운드 데이터 집합을 이용하여 성능 분석 실험을 수행하였고, 이를 통해 본 논문에서 제안하는 사운드 분류 시스템의 높은 성능을 확인할 수 있었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.11a
• /
• pp.1126-1129
• /
• 2010

클라우드 컴퓨팅 서비스 환경에서 인증 및 접근 제어와 같은 여러 보안 이슈가 발생하고 있다. 특히, 클라우드 컴퓨팅 환경에서 다양한 자원에 접속을 할 경우, 통합적으로 관리 및 제어가 가능한 인증 및 접근제어 모델이 필요하다. 이를 해결하기 위해서, 본 논문에서는 상황인식 기반의 통합 인증(SSO) 및 접근제어 모델을 제안하고, 이를 설계 및 구현함으로써, 클라우드 컴퓨팅 환경에서 유연하고, 편리한 보안 시스템을 검증하고자 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.05a
• /
• pp.714-717
• /
• 2008

유비쿼터스 컴퓨팅(Ubiquitous Computing) 시대에 기업의 사무 환경은 다양한 정보들과 많은 사용자들이 유기적인 관계를 형성한다. 이러한 관계에서 접근 제어는 다양한 정보 객체에 허가된 사용자만이 접근할 수 있는 권한을 갖는 기능을 제공하는 것이고, 사무 환경에서 보안상 필수적이며 중요한 역할을 한다. 하지만 기존의 접근 제어 모델들은 상황 정보를 고려하지 않아 동적인 접근 제어를 하지 못하는 문제점을 가지고 있다. 본 논문은 워크플로우 기반의 오피스 환경에서 동적이고 능동적인 접근제어 관리를 제공하기 위한 상황 정보와 역할 기반의 워크플로우 데이터 접근제어 모델을 제안한다. 이 모델은 수많은 상황 정보 및 사무 정보와 사용자가 동적으로 변화하는 사무환경에서 사용자에게 접근을 제어하기 적합하다.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.13 no.2
• /
• pp.35-48
• /
• 2017

There are many and various devices like sensors, displays, smart phone, etc. in smart environment. And contents can be provided by using these devices. Vast amounts of contents are provided to users, but in most environments, there are no regard for user or some simple elements like location and time are regarded. So there's a limit to provide meaningful contents to users. In this paper, I suggest the contents recommendation system that can recommend contents to users by reasoning context of users, devices and contents. The contents recommendation system suggested in this paper recommend the contents by calculating the user preferences using the situation reasoned with the contextual data acquired from various devices and the user profile received from the user directly. To organize this process, the method on how to model ontology with domain knowledge and how to design and develop the contents recommendation system are discussed in this paper. And an application of the contents recommendation system in Centum City, Busan is introduced. Then, the evaluation methods how the contents recommendation system is evaluated are explained. The evaluation result shows that the mean absolute error is 0.8730, which shows the excellent performance of the proposed contents recommendation system.

• Proceedings of the Korea Society of Information Technology Applications Conference
• /
• 2005.11a
• /
• pp.55-60
• /
• 2005

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 drastic increase 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 information system, 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 for the development of the wireless paging system model of ubiquitous environment that improved the problems of currently operated wireless paging system.

• The KIPS Transactions:PartC
• /
• v.16C no.6
• /
• pp.691-698
• /
• 2009

A mobile communication device is a small size of portable computer which provides communication service, such as smart phone and PDA. Currently, one of the biggest barriers in developing the mobile communication device is security issue. Even though there are excellent security functions which can remove the security issues, there is a problem that the mobile communication device can not be loaded with all the functions because it has low storage, poor computational power, and inconvenient user interface, compared to the desktop personal computer. This paper proposes a context-aware security reconfiguration scheme for effective security management of the mobile communication device. The scheme can provide the mobile communication device with the optimized security service which is most adapted to its current security context. Through the prototype implementation and the experiments of the proposed scheme, we have confirmed that the proposed scheme is excellent in terms of computing resource efficiency and usability, without degrading security level.

• Journal of Intelligence and Information Systems
• /
• v.17 no.1
• /
• pp.1-16
• /
• 2011

The real-time ubiquitous environment is required to be able to process a series of sensor data within limited time. The whole sensor data processing consists of several phases : getting data out of sensor, acquiring context and responding to users. The ubiquitous computing middleware is aware of the context using the input sensor data and a series of data from database or knowledge-base, makes a decision suitable for the context and shows a response according to the decision. When the real-time ubiquitous environment gets a set of sensor data as its input, it needs to be able to estimate the delay-time of the sensor data considering the available resource and the priority of it for scheduling a series of sensor data. Also the sensor data of higher priority can stop the processing of proceeding sensor data. The research field for such a decision making is not yet vibrant. In this paper, we propose a queuing time computation algorithm for sensor data processing in real-time ubiquitous environment.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39C no.2
• /
• pp.151-163
• /
• 2014

The recent wearable device's applications concentrates on providing diverse services such as location based service, context aware service to the users. These various services are implemented by the interactions between the wearable device and the user. In the legacy system, the interaction requires certain explicit configuration from the user. If the user is unfamiliar with the IT technology, it will be impossible to get the wanted service. Therefore, a new autonomous communication concept among neighbor devices is essential for people who is unfamiliar with the IT technology. The implicit human computer interface enables the user to acquire the services, even though the user don't know the IT technology. In this paper, we propose two BLE based protocols (B-LIDx protocol, B-PniP). B-LIDx protocol is the protocol for locationing the mobile device in indoor. B-PniP is a zero-configure opportunistic direct M2M communication protocol between neighbor devices to achieve the autonomous communication concept with zero-configuration. The protocol's evaluations are performed by measuring the time for finding the location of a mobile device in actual environment and aligning the time spent in services using the B-PniP.