• Journal of Korea Multimedia Society
• /
• v.23 no.12
• /
• pp.1540-1551
• /
• 2020

Aiming at the problem that the existing human behavior recognition algorithm cannot fully utilize the multi-level spatio-temporal information of the network, a human behavior recognition algorithm based on a dense three-dimensional residual network is proposed. First, the proposed algorithm uses a dense block of three-dimensional residuals as the basic module of the network. The module extracts the hierarchical features of human behavior through densely connected convolutional layers; Secondly, the local feature aggregation adaptive method is used to learn the local dense features of human behavior; Then, the residual connection module is applied to promote the flow of feature information and reduced the difficulty of training; Finally, the multi-layer local feature extraction of the network is realized by cascading multiple three-dimensional residual dense blocks, and use the global feature aggregation adaptive method to learn the features of all network layers to realize human behavior recognition. A large number of experimental results on benchmark datasets KTH show that the recognition rate (top-l accuracy) of the proposed algorithm reaches 93.52%. Compared with the three-dimensional convolutional neural network (C3D) algorithm, it has improved by 3.93 percentage points. The proposed algorithm framework has good robustness and transfer learning ability, and can effectively handle a variety of video behavior recognition tasks.

• Journal of the Korean Institute of Educational Facilities
• /
• v.19 no.2
• /
• pp.59-66
• /
• 2012

Community design education has covered the worldview dimension of the collaborative courses for sustainability draws on the architectural expertise developed in a network of community projects and therefore case studies of design education by the collaborative project-based learning in terms of participants, students, teachers and architects, such as 'Learning By Design' for the K-12 comprehensive program in Massachusetts addresses how a local society can make its community sustainable by both design and education. To understand that community design and education can provide professional development in all levels of skills and knowledge across disciplines and opportunities for collaborative learning and problem-solving, this research consists of case studies of the community design education including social systems that assist in organizing the local educational program as well as promoting the programs with public awareness of the community. It covers the UNESCO-UIA agenda of the community design and education that is to enhance the physical environment relating to human interaction by developing innovative alternatives of existing community and contributing voluntarily to neighborhoods through design. As the community design collaborative of design professionals and users is a structural approach to assess design quality, the cases address how to set up the architectural program in order to share pro bono design service and provide high-quality design resources available for sustainable environment.

• Korean Journal of Human Ecology
• /
• v.19 no.3
• /
• pp.471-485
• /
• 2010

This qualitative study explores how volunteering to help in early childhood education is conceptualized from the perspectives of three parties involved; university students, university professors, and principals as well as teachers, and children‘s mothers from a local daycare center and a kindergarten. Data was collected through journals, interviews, and several other artifacts, such as student portfolios, and letters from mothers. Findings were as follows: firstly, preservice early childhood teachers defined voluntary activity in early childhood education as a service that requires motivation and responsibility, and as an activity that helps to establish their identities as teachers. Secondly, university professors constructed the system for service learning activities and helped preservice early childhood teachers’ change the view from volunteering activity to volunteering learning. Thirdly, the local community referred to these activities in terms of the partnerships made for children‘s education and the possibility of cooperative childcare. The findings of this study describe the perspectives of parties involved and may be helpful in planning and executing specialized volunteer projects as well as in understanding volunteer behavior.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.3
• /
• pp.521-526
• /
• 2020

This paper presents an improved HOLP neural network that adds 25 average values to a typical HOLP neural network using 25 feature vector values as input values by applying high-order local autocorrelation function, which is excellent for extracting immutable feature values of iris images. Compared with deep learning structures with different types, we compared the recognition rate of iris recognition using Back-Propagation neural network, which shows excellent performance in voice and image field, and synthetic product neural network that integrates feature extractor and classifier.

• 한국정보교육학회:학술대회논문집
• /
• 2011.01a
• /
• pp.139-146
• /
• 2011

The present study proposes an innovative approach to develop educational contents for the field trip with creative activities. In the study, the field trip with creative activities extends students' learning spaces from not only the classroom but also social circumstances. With the use of the Creative Resource Map (CRM) for students' field trip, students can approach to rich contents whenever and wherever they want. For this, it is necessary to have a variety of curriculum-related contents. For the content development, it is important to enhance mutual cooperation between school and local community as well as to create local capacity for the development of the u-learning contents with smart devices.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.10 no.7
• /
• pp.807-812
• /
• 2015

Lifelong education is a periodic keyword. For a lifelong learner friendly education, university should provide the adult learners with the efficient academic administrative service. A university should support them in learning a series of graded lifelong study and come up with the convenience of continuous learning, maintaining the educational operation as a lifelong education university. A local government induces the regional economy reinvigoration from setting the lifelong learning conditions of the city. In this paper, I suggest a policy management scheme for opening training courses of 3D printing and CAD professionals training module as a non-degree reeducation programs for the lifelong learners that reflects the industrial milieu of the local community.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.9 no.5
• /
• pp.490-495
• /
• 1999

In this paper. a learning method VoD-EBP for neural networks is proposed, which learn patterns by error back propagation. Based on Voronoi diagram, the method initializes the weights of the neural networks systematically, wh~ch results in faster learning speed and alleviated local optimum problem. The method also shows better the reliability of the design of neural network because proper number of hidden nodes are determined from the analysis of Voronoi diagram. For testing the performance, this paper shows the results of solving the XOR problem and the parity problem. The results were showed faster learning speed than ordinary error back propagation algorithm. In solving the problem, local optimum problems have not been observed.

• Journal of Information Processing Systems
• /
• v.19 no.6
• /
• pp.842-857
• /
• 2023

Currently, most sentiment classification models on microblogging platforms analyze sentence parts of speech and emoticons without comprehending users' emotional inclinations and grasping moral nuances. This study proposes a hybrid sentiment analysis model. Given the distinct nature of microblog comments, the model employs a combined stop-word list and word2vec for word vectorization. To mitigate local information loss, the TextCNN model, devoid of pooling layers, is employed for local feature extraction, while BiLSTM is utilized for contextual feature extraction in deep learning. Subsequently, microblog comment sentiments are categorized using a classification layer. Given the binary classification task at the output layer and the numerous hidden layers within BiLSTM, the Tanh activation function is adopted in this model. Experimental findings demonstrate that the enhanced TextCNN-BiLSTM model attains a precision of 94.75%. This represents a 1.21%, 1.25%, and 1.25% enhancement in precision, recall, and F1 values, respectively, in comparison to the individual deep learning models TextCNN. Furthermore, it outperforms BiLSTM by 0.78%, 0.9%, and 0.9% in precision, recall, and F1 values.

• The Korean Journal of Community Living Science
• /
• v.17 no.4
• /
• pp.67-80
• /
• 2006

This study conducted research on the actual state of community-oriented services for elderly rural inhabitants and their desire related to them to develop a local community service network model suitable to the characteristics of rural longevity villages. The research was conducted on 906 elderly people over 65 living in 20 rural longevity villages through questionnaires assessing filming and economy, economic activity, health care, learning and leisure activities as well as asking their wants and needs relative to local community services. As a result, it was found rural elderly people showed a high desire for local community services such as health, transportation and economy activity. In addition, they were mainly cultivating farm products as their economic activity and showed a high demand in the future as well. Most were found to take a walk in the healthcare field and showed a high demand for health examinations, health education, health consulting, hot spring bathing and basking in the woods. Respecting learning, social and leisure activities, they were mostly found to watch TV and do house chores, and showed a high desire for village environment repair, traditional farm music, visiting and tourism. With the above results, it is expected that the desire of rural elderly for such services can be satisfied, and the development of a local community service network model suitable to the characteristic of a local community is recommended.

• Journal of the Korean association of regional geographers
• /
• v.11 no.2
• /
• pp.233-246
• /
• 2005

This paper aims to explore the innovation milieu of red-pepper agro-industry in Bonghwa County, in the northern part of Gyeongbuk Province, and suggest policy recommendations for bringing up local agro-industry from a cluster perspective. It turns out that the capabilities of Bonghwa red-pepper agro-industry to innovate are remarkably weak let alone soft infrastructures such as learning networks between innovation agents and social capital. In this sense Bonghwa red-pepper agro-industry can be viewed as an agricultural area simply specialized in production sector rather than a kind of agro-industry cluster. For moving up Bonghwa red pepper industry into an innovative cluster, the paper suggests that the policy makers need to focus on cultivating local learning communities, building a region-wide incorporated brand, promoting the local agricultural technology centre as a network hub of cluster and fostering the functional links between universities and local innovation agents, covering farmers, agricultural organizations, agro-food producers and the local government.