• The KIPS Transactions:PartA
• /
• v.11A no.6
• /
• pp.425-432
• /
• 2004

Traditional applications are executed using the restricted resources of a single computer, do not consider contextual information, and can not support mobile users. However, ubiquitous applications provide optimal services for mobile users using the various resources of computers and the contextual information around users and devices. Thus, ubiquitous applications need to have the functionality of context awareness, user mobility and QoS adaptability. This paper design the CMQ(Context-aware, Mobility-aware, QoS-aware) middleware framework for ubiquitous applications and implement the middleware framework using Jini and Java. The implemented middleware system can process various contexts, provide the session handoff for a mobile user, and allow applications to adjust its QoS dynamically.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.357-359
• /
• 2023

This paper proposes a hybrid recommendation system (RS) model that overcomes the limitations of traditional approaches such as data sparsity, cold start, and scalability by combining collaborative filtering and context-aware techniques. The objective of this model is to enhance the accuracy of recommendations and provide personalized suggestions by leveraging the strengths of collaborative filtering and incorporating user context features to capture their preferences and behavior more effectively. The approach utilizes a novel method that combines contextual attributes with the original user-item rating matrix of CF-based algorithms. Furthermore, we integrate k-mean++ clustering to group users with similar preferences and finally recommend items that have highly rated by other users in the same cluster. The process of partitioning is the use of the rating matrix into clusters based on contextual information offers several advantages. First, it bypasses of the computations over the entire data, reducing runtime and improving scalability. Second, the partitioned clusters hold similar ratings, which can produce greater impacts on each other, leading to more accurate recommendations and providing flexibility in the clustering process. keywords: Context-aware Recommendation, Collaborative Filtering, Kmean++ Clustering.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.2
• /
• pp.79-86
• /
• 2024

In this paper, a novel visual tracking method which can utilize the context of object regions is presented. Conventional methods have the inherent problem of treating all candidate regions independently, where the tracker could not successfully discriminate regions with similar appearances. This was due to lack of contextual modeling in a given scene, where all candidate object regions should be taken into consideration when choosing a single region. The goal of the proposed method is to encourage feature exchange between candidate regions to improve the discriminability between similar regions. It improves upon conventional methods that only consider a single region, and is implemented by employing the MLP-Mixer model for enhanced feature exchange between regions. By implementing channel-wise, inter-region interaction operation between candidate features, contextual information of regions can be embedded into the individual feature representations. To evaluate the performance of the proposed tracker, the large-scale LaSOT dataset is used, and the experimental results show a competitive AUC performance of 0.560 while running at a real-time speed of 65 fps.

• Asia pacific journal of information systems
• /
• v.10 no.3
• /
• pp.41-59
• /
• 2000

The role of information systems(IS) is far more important in business operations today. Managers recognize information as a major resource of the organization, and non-expert end users positively participate in information system development processes. This phenomenon is considered user-led information system development(ULD), where users define the information requirements, oversee system testing, manage system development, and lead the overall project. Based on a socio-technical approach, this study examines the impact of ULD on IS success. This paper also investigates the moderating effects of various contextual factors on the relationships between ULD and the success. The questionnaire was developed and the data was collected from the end users who participated in implementing ERP systems. The results showed that ULD positively affects the success. For the moderating variables, IT complexity was found to have a strong effect on the relationship between ULD and the success while business complexity and top management support have partial effects. Surprisingly, resource adequacy was not found to have the effect. This study provides academia and practitioners with a number of implications and guidelines regarding why and when to introduce ULD in their IS development initiatives.

• Journal of Preventive Medicine and Public Health
• /
• v.38 no.3
• /
• pp.252-258
• /
• 2005

Major approaches of Social epidemiology; 1)holistic, ecological approach, 2)population based approach, 3)development and life-course approach, 4)contextual multi-level approach, have stressed the importance of not only social context of health and illness, but also the population based strategy in the health interventions. Ultimately, it provides the conceptual guidelines and methodological tools to lead toward the healthy public policies; integrated efforts to improve condition which people live: secure, safe, adequate, and sustainable livelihoods, lifestyles, and environments, including housing, education, nutrition, information exchange, child care, transportation, and necessary community and personal social and health services.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2003.04a
• /
• pp.9-14
• /
• 2003

본 연구에서는 원격탐사 화상의 분류를 목적으로 분광정보와 공간적 상관성의 반복적 결합방법을 제안하였다. 퍼지이론을 기반으로 공간적 상관성을 분류 과정에 적용하기 위하여 초기단계에서 정의된 소속 함수에 대해서 주변영역에 대한 필터링을 적용하였고, 특정 수렴 조건을 만족하는 단계까지 반복적 결합을 수행하였다. Landsat TM 화상에 적용한 결과, 향상된 분류정확도와 분광정보만으로 분류가 애매한 화소의 공간적 분포 양상을 확인할 수 있었다.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.16 no.5
• /
• pp.225-232
• /
• 2021

Deraining is one of the image restoration tasks and should consider a tradeoff between local details and broad contextual information while recovering images. Current studies adopt an attention mechanism which has been actively researched in natural language processing to deal with both global and local features. This paper classifies existing deraining methods and provides comparative analysis and performance comparison by using several datasets in terms of generalization.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.391-394
• /
• 2022

딥러닝을 통해 자연어처리 분야에서 대용량 정보를 기반으로 학습 할 수 있게 되었고 높은 성능을 얻을 수 있게 되었다. 본 논문에서는 학습에 포함되는 문맥 정보 중 분야 또는 데이터에 맞게 조절이 필요하다는 것을 주장하고, TACRED 데이터를 기반으로 문맥 정보 자질 선택에 따른 성능 변화를 확인하였다. 해당 데이터에서 엔터티와 연관된 문맥 정보를 사용함으로써 약 1.4%의 성능 보완을 이루었다.

• Proceedings of the KSRS Conference
• /
• 2002.10a
• /
• pp.382-387
• /
• 2002

In this paper, we propose a geostatistical approach incorporated to the Bayesian data fusion technique for supervised classification of multi-sensor remote sensing data. Traditional spectral based classification cannot account for the spatial information and may result in unrealistic classification results. To obtain accurate spatial/contextual information, the indicator kriging that allows one to estimate the probability of occurrence of classes on the basis of surrounding observations is incorporated into the Bayesian framework. This approach has its merit incorporating both the spectral information and spatial information and improves the confidence level in the final data fusion task. To illustrate the proposed scheme, supervised classification of multi-sensor test remote sensing data set was carried out.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.8
• /
• pp.727-739
• /
• 2003

In this paper, we propose a generation method of regression classes for adaptation in the HM-Net (Hidden Markov Network) system. The MLLR (Maximum Likelihood Linear Regression) adaptation approach is applied to the HM-Net speech recognition system for expressing the characteristics of speaker effectively and the use of HM-Net in various tasks. For the state level sharing, the context domain state splitting of PDT-SSS (Phonetic Decision Tree-based Successive State Splitting) algorithm, which has the contextual and time domain clustering, is adopted. In each state of contextual domain, the desired phoneme classes are determined by splitting the context information (classes) including target speaker's speech data. The number of adaptation parameters, such as means and variances, is autonomously controlled by contextual domain state splitting of PDT-SSS, depending on the context information and the amount of adaptation utterances from a new speaker. The experiments are performed to verify the effectiveness of the proposed method on the KLE (The center for Korean Language Engineering) 452 data and YNU (Yeungnam Dniv) 200 data. The experimental results show that the accuracies of phone, word, and sentence recognition system increased by 34∼37%, 9%, and 20%, respectively, Compared with performance according to the length of adaptation utterances, the performance are also significantly improved even in short adaptation utterances. Therefore, we can argue that the proposed regression class method is well applied to HM-Net speech recognition system employing MLLR speaker adaptation.