• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권6호
• /
• pp.2709-2729
• /
• 2016

Representation based classification, kernel method and sparse representation have received much attention in the field of face recognition. In this paper, we proposed an improved kernel principal component analysis method based on sparse representation to improve the accuracy and robustness for face recognition. First, the distances between the test sample and all training samples in kernel space are estimated based on collaborative representation. Second, S training samples with the smallest distances are selected, and Kernel Principal Component Analysis (KPCA) is used to extract the features that are exploited for classification. The proposed method implements the sparse representation under ℓ₂ regularization and performs feature extraction twice to improve the robustness. Also, we investigate the relationship between the accuracy and the sparseness coefficient, the relationship between the accuracy and the dimensionality respectively. The comparative experiments are conducted on the ORL, the GT and the UMIST face database. The experimental results show that the proposed method is more effective and robust than several state-of-the-art methods including Sparse Representation based Classification (SRC), Collaborative Representation based Classification (CRC), KCRC and Two Phase Test samples Sparse Representation (TPTSR).

• International journal of advanced smart convergence
• /
• 제12권2호
• /
• pp.56-66
• /
• 2023

The goal of deep learning is to extract complex features from multidimensional data use the features to create models that connect input and output. Deep learning is a process of learning nonlinear features and functions from complex data, and the user data that is employed to train deep learning models has become the focus of privacy concerns. Companies that collect user's sensitive personal information, such as users' images and voices, own this data for indefinite period of times. Users cannot delete their personal information, and they cannot limit the purposes for which the data is used. The study has designed a deep learning method that employs privacy protection technology that uses distributed collaborative learning so that multiple participants can use neural network models collaboratively without sharing the input datasets. To prevent direct leaks of personal information, participants are not shown the training datasets during the model training process, unlike traditional deep learning so that the personal information in the data can be protected. The study used a method that can selectively share subsets via an optimization algorithm that is based on modified distributed stochastic gradient descent, and the result showed that it was possible to learn with improved learning accuracy while protecting personal information.

• 한국산학기술학회논문지
• /
• 제20권11호
• /
• pp.361-367
• /
• 2019

본 연구의 목적은 전문대학 교수의 산업체 연수를 활성화 할 수 있는 방안을 탐색하는 것이다. 이를 위해 본 연구에서는 전문대학 유아교육과 교수가 협력적 실행연구를 활용하여 어떻게 산업체 연수를 진행하였는지에 대한 실제 사례를 제시하였다. 본 연구는 D시에 소재한 어린이집 만5세 학급에서 연구자가 산업체 연수기간 동안 학급 담당 교사와의 협력적 실행연구를 실시한 내용에 관한 것이다. 본 연구 진행을 위해 연구자와 교사는 협력적 실행연구 4단계를 거쳤고, 최종적으로 유아에게 적합한 기본운동기술이 포함된 구조화된 리듬동작 프로그램을 개발하였다. 본 연구진행을 위해 진행된 4단계는 다음과 같다. 첫 번째, 실천단계 1에서 교사와 연구자는 문제해결을 위한 상호집단을 형성하였다. 두 번째, 실천단계 2에서 교사와 연구자는 상호 호혜적 관계에서 교사의 문제를 파악하였다. 세 번째, 실천단계 3에서 교사와 연구자는 문제해결에 필요한 문헌연구를 하였다. 네 번째, 실천단계 4에서는 문제해결을 하였다. 이러한 산업체 연수 실천 사례로 얻어진 시사점으로는 첫 번째, 산업체 연수를 통하여 연구자는 실제와 이론을 강화할 수 있는 기회가 주어졌다는 것이고 두 번째, 산업체 연수 기간 동안 담당 학급 교사의 전문성도 함께 증진될 수 있었다는 것이다. 이러한 시사점은 연구자이며 직업교육자이기도 한 전문대학 교수의 다양한 산업체 연수방안이 어떻게 모색되어야 하는지에 대한 단초를 제공해 준다는데 그 의미가 있다.

• 한국CDE학회논문집
• /
• 제9권3호
• /
• pp.260-265
• /
• 2004

This paper proposed a Web-based training service for product data management by supporting an integrated product data management system, various technical documents. and efficient communication systems. It also supports a general product development process and a consistent product data model that enable participants to experience management of consistent product information during the product development life cycle. The Web based environment of the service also provides participants with a collaborative workplace with other participants and a Web portal for all the components of the service.

• Journal of Information Technology Applications and Management
• /
• 제29권3호
• /
• pp.43-55
• /
• 2022

In this study, with the goal of developing a deep learning-based product recommendation model for effective matching of influencers and products, a deep learning model with a collaborative filtering model combined with generalized matrix decomposition(GMF), a collaborative filtering model based on multi-layer perceptron (MLP), and neural collaborative filtering and generalized matrix Factorization (NeuMF), a hybrid model combining GMP and MLP was developed and tested. In particular, we utilize one-class problem free boosting (OCF-B) method to solve the one-class problem that occurs when training is performed only on positive cases using implicit feedback in the deep learning-based collaborative filtering recommendation model. In relation to model selection based on overall experimental results, the MLP model showed highest performance with weighted average precision, weighted average recall, and f1 score were 0.85 in the model (n=3,000, term=15). This study is meaningful in practice as it attempted to commercialize a deep learning-based recommendation system where influencer's promotion data is being accumulated, pactical personalized recommendation service is not yet commercially applied yet.

• Journal of Information Technology Applications and Management
• /
• 제29권6호
• /
• pp.81-93
• /
• 2022

As deep learning technology in natural language and visual processing has rapidly developed, collaborative filtering-based recommendation systems using deep learning technology are being actively introduced in the recommendation field. In this study, OCF-GAN, a hybrid collaborative filtering model using GAN, was proposed to solve the one-class and cold-start problems, and its usefulness was verified through performance evaluation. OCF-GAN based on conditional GAN consists of a generator that generates a pattern similar to the actual user preference pattern and a discriminator that tries to distinguish the actual preference pattern from the generated preference pattern. When the training is completed, user preference vectors are generated based on the actual distribution of preferred items. In addition, the cold-start problem was solved by using a hybrid collaborative filtering recommendation method that additionally utilizes user and item profiles. As a result of the performance evaluation, it was found that the performance of the OCF-GAN with additional information was superior in all indicators of the Top 5 and Top 20 recommendations compared to the existing GAN-based recommender. This phenomenon was more clearly revealed in experiments with cold-start users and items.

• 산업경영시스템학회지
• /
• 제40권4호
• /
• pp.154-163
• /
• 2017

Collaborative filtering, one of the most widely used techniques to build recommender systems, is based on the idea that users with similar preferences can help one another find useful items. Credit card user behavior analytics show that most customers hold three or less credit cards without duplicates. This behavior is one of the most influential factors to data sparsity. The 'cold-start' problem caused by data sparsity prevents recommender system from providing recommendation properly in the personalized credit card recommendation scenario. We propose a personalized credit card recommender system to address the cold-start problem, using multiple user profiles. The proposed system consists of a training process and an application process using five user profiles. In the training process, the five user profiles are transformed to five user networks based on the cosine similarity, and an integrated user network is derived by weighted sum of each user network. The application process selects k-nearest neighbors (users) from the integrated user network derived in the training process, and recommends three of the most frequently used credit card by the k-nearest neighbors. In order to demonstrate the performance of the proposed system, we conducted experiments with real credit card user data and calculated the F1 Values. The F1 value of the proposed system was compared with that of the existing recommendation techniques. The results show that the proposed system provides better recommendation than the existing techniques. This paper not only contributes to solving the cold start problem that may occur in the personalized credit card recommendation scenario, but also is expected for financial companies to improve customer satisfactions and increase corporate profits by providing recommendation properly.

• 한국인터넷방송통신학회논문지
• /
• 제18권6호
• /
• pp.259-268
• /
• 2018

본 연구의 목적은 인지기능 훈련 콘텐츠들을 사용하는 동안 사용자들의 흥미와 몰입도를 높이기 위하여 인지 능력 수준에 맞춘 훈련 방법을 제시하는 것이다. 사용자의 인지 능력 수준은 K-means 알고리즘을 적용한 협업 필터링을 사용하여 사용자들의 정보와 한국형 아동 간이 정신 상태 검사 점수를 기반으로 군집화한 결과를 바탕으로 이루어졌다. 이 결과를 구현된 인지기능 훈련 통합 시스템에 적용하여 사용자의 인지 능력 수준에 알맞은 인지기능 훈련 영역 별 콘텐츠 순서와 난이도를 추천하였다. 특히 콘텐츠 난이도 조절은 사용자들이 긴장감과 편안함을 반복적으로 느낄 수 있도록 제안한 '몰입이론' 방법을 적용하여 높은 몰입감을 주고자 하였다. 결론적으로 본 논문에서 제안한 사용자 맞춤형 인지기능 훈련 방법은 기존의 치료사가 콘텐츠 순서와 난이도를 주관적으로 설정하는 것보다 더욱 효과적이고 재활 결과를 기대할 수 있을 것이다.

• Journal of Information Technology Applications and Management
• /
• 제23권4호
• /
• pp.55-70
• /
• 2016

Recently, development of indoor positioning system and IoT such as beacon makes it possible to collect and analyze each customer's shopping behavior in off-line shopping malls. In this study, we propose a realtime brand recommendation scheme based on each customer's brand visiting history for off-line shopping mall with indoor positioning system. The proposed scheme, which apply collaborative filtering to off-line shopping mall, is composed of training and apply process. The training process is designed to make the base brand network (BBN) using historical transaction data. Then, the scheme yields recommended brands for shopping customers based on their behaviors and BBN in the apply process. In order to verify the performance of the proposed scheme, simulation was conducted using purchase history data from a department store in Korea. Then, the results was compared to the previous scheme. Experimental results showd that the proposed scheme performs brand recommendation effectively in off-line shopping mall.

• 한국멀티미디어학회논문지
• /
• 제6권4호
• /
• pp.685-697
• /
• 2003

The Web based multimedia programmes/courses are becoming widely available in recent years. Most of these courses focus on Behaviorist way of learning, which does not promote deep learning in any way. For Adults this approach further incapacitated, as it does not satisfy Andragogical needs. The search for Constructivist way of learning through the web applied to Indian conditions led to need for developing a curriculum development approach that would promote construction of knowledge through web based collaboration. This paper attempts to reengineer existing curriculum development processes and lays out a framework of‘Problem Based Online Learning (PBOL)’curriculum design. In this context, entire curriculum development life cycle is evolved and explained. This is a part of doctoral work (Ph.D), which is in progress and being undertaken by K.James Mathai, and guided of Dr.D.S.Karaulia.