• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.4 no.5
• /
• pp.859-876
• /
• 2010

In this paper, we propose a hierarchical application traffic classification system as an alternative means to overcome the limitations of the port number and payload based methodologies, which are traditionally considered traffic classification methods. The proposed system is a new classification model that hierarchically combines a binary classifier SVM and Support Vector Data Descriptions (SVDDs). The proposed system selects an optimal attribute subset from the bi-directional traffic flows generated by our traffic analysis system (KU-MON) that enables real-time collection and analysis of campus traffic. The system is composed of three layers: The first layer is a binary classifier SVM that performs rapid classification between P2P and non-P2P traffic. The second layer classifies P2P traffic into file-sharing, messenger and TV, based on three SVDDs. The third layer performs specialized classification of all individual application traffic types. Since the proposed system enables both coarse- and fine-grained classification, it can guarantee efficient resource management, such as a stable network environment, seamless bandwidth guarantee and appropriate QoS. Moreover, even when a new application emerges, it can be easily adapted for incremental updating and scaling. Only additional training for the new part of the application traffic is needed instead of retraining the entire system. The performance of the proposed system is validated via experiments which confirm that its recall and precision measures are satisfactory.

• The Journal of Asian Finance, Economics and Business
• /
• v.7 no.8
• /
• pp.425-433
• /
• 2020

This paper aims to develop a conceptual framework for evaluating the impact of motivational factors on the work results of lecturers at Vietnam National University, Hanoi (VNU), one of two leading multidisciplinary and multi-sectoral national universities in Vietnam. This study has considered wages and other benefits (WB), training and development (TD), working environment (WE) and working motivation (WM) as motivational factors, and proposed a structural model of the impact of motivational factors on the work results of lecturers at VNU. The empirical analysis used data from the survey data of 321 university lecturers. Comprehensive, valid, and reliable tools (SPSS 26 and SmartPLS 3.0 software) are used to evaluate rigorous statistical tests including convergence validity, discriminatory validity, reliability, and average variance extracted to analyze and verify the gathered data, and the hypotheses developed. The result of path analysis shows that four motivational factors constitute a structured system with different degrees of influence on the work results of lecturers. There is also a positive relationship between the motivational factors and the work results of lecturers. As a result, it can be concluded that all hypotheses developed are supported. Several recommendations are further suggested to improve the performance of lecturers at VNU.

• Journal of Digital Contents Society
• /
• v.19 no.1
• /
• pp.35-41
• /
• 2018

The Q-learning algorithm based on reinforcement learning is useful for learning the goal for one behavior at a time, using a combination of discrete states and actions. In order to learn multiple actions, applying a behavior-based architecture and using an appropriate behavior adjustment method can make a robot perform fast and reliable actions. Q-learning is a popular reinforcement learning method, and is used much for robot learning for its characteristics which are simple, convergent and little affected by the training environment (off-policy). In this paper, Q-learning algorithm is applied to a lamp robot to learn multiple behaviors (human recognition, desk object recognition). As the learning rate of Q-learning may affect the performance of the robot at the learning stage of multiple behaviors, we present the optimal multiple behaviors learning model by changing learning rate.

• The Journal of Industrial Distribution & Business
• /
• v.5 no.4
• /
• pp.31-42
• /
• 2014

Purpose - According to the applied studies knowledge, management implementation can improve organizational performance. The main objective of this study is to develop an understanding of critical success factors that enhance the successful implementation of knowledge management. Research design, data, and methodology - This study used Analytical Hierarchy Procedure (AHP), which is a multi-criteria decision making model that works on fuzzy logic. Using this method, researchers can find the proportion of success due to the contribution of the critical success factors (CSFs). Results - The results show that more than 70% of respondents indicate the possibility of success in knowledge management implementation. Further, the results show that top management support has the greatest relationship with the success of knowledge management implementation. This was followed by information technology, performance measurement, and culture, which had a high relation with knowledge management success. Process and activities have a moderate positive relation, while education and training has a low relation with success. Because of an inappropriate p-value, knowledge management strategies show no relation to the success of knowledge management in the Iranian health Industry. Conclusions - This study was conducted because of a critical issue in the Iranian health industry that indicated that a significant portion of the workforce would retire in 5 to 10 years. Most highly experienced and knowledge oriented employees would become eligible for retirement. Therefore, knowledge management is presented as a complete solution in the Iranian health sector.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.3
• /
• pp.333-340
• /
• 2022

The COVID-19 has made everyone anxious and people need to keep their distance. It is necessary to conduct collective assessment and screening of college students' mental health in the opening season of every year. This study uses and trains a multi-layer perceptron neural network model for deep learning to identify facial emotions. After the training, real pictures and videos were input for face detection. After detecting the positions of faces in the samples, emotions were classified, and the predicted emotional results of the samples were sent back and displayed on the pictures. The results show that the accuracy is 93.2% in the test set and 95.57% in practice. The recognition rate of Anger is 95%, Disgust is 97%, Happiness is 96%, Fear is 96%, Sadness is 97%, Surprise is 95%, Neutral is 93%, such efficient emotion recognition can provide objective data support for capturing negative. Deep learning emotion recognition system can cooperate with traditional psychological activities to provide more dimensions of psychological indicators for health.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.203-214
• /
• 2023

The Korea Customs Service is efficiently handling business with an electronic customs system that can effectively handle one-stop business. This is the case and a more effective method is needed. Import and export require HS Code (Harmonized System Code) for classification and tax rate application for all goods, and item classification that classifies the HS Code is a highly difficult task that requires specialized knowledge and experience and is an important part of customs clearance procedures. Therefore, this study uses various types of data information such as product name, product description, and product image in the item classification request form to learn and develop a deep learning model to reflect information well based on Multimodal representation learning. It is expected to reduce the burden of customs duties by classifying and recommending HS Codes and help with customs procedures by promptly classifying items.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.2
• /
• pp.389-396
• /
• 2024

Generative AI has recently been utilized across all fields, achieving expert-level advancements in deep data analysis. However, identifying regional names in scientific literature remains a challenge due to insufficient training data and limited AI application. This study developed a standardized dataset for effectively classifying regional names using address data from Korean institution-affiliated authors listed in the Web of Science. It tested and evaluated the applicability of machine learning and deep learning models in real-world problems. The BERT model showed superior performance, with a precision of 98.41%, recall of 98.2%, and F1 score of 98.31% for metropolitan areas, and a precision of 91.79%, recall of 88.32%, and F1 score of 89.54% for city classifications. These findings offer a valuable data foundation for future research on regional R&D status, researcher mobility, collaboration status, and so on.

• Resources Recycling
• /
• v.27 no.1
• /
• pp.84-91
• /
• 2018

In this study, a novel soft information based most probable classification scheme is proposed for sorting recyclable metal alloys with laser induced breakdown spectroscopy (LIBS). Regression analysis with LIBS captured spectrums for estimating concentrations of common elements can be efficient for classifying unknown arbitrary metal alloys, even when that particular alloy is not included for training. Therefore, partial least square regression (PLSR) is employed in the proposed scheme, where spectrums of the certified reference materials (CRMs) are used for training. With the PLSR model, the concentrations of the test spectrum are estimated independently and are compared to those of CRMs for finding out the most probable class. Then, joint soft information can be obtained by assuming multi-variate normal (MVN) distribution, which enables to account the probability measure or a prior information and improves classification performance. For evaluating the proposed schemes, MVN soft information is evaluated based on PLSR of LIBS captured spectrums of 9 metal CRMs, and tested for classifying unknown metal alloys. Furthermore, the likelihood is evaluated with the radar chart to effectively visualize and search the most probable class among the candidates. By the leave-one-out cross validation tests, the proposed scheme is not only showing improved classification accuracies but also helpful for adaptive post-processing to correct the mis-classifications.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.9
• /
• pp.387-396
• /
• 2020

The purpose of this study is to identify the variables of metropolitan and provincial offices of education that affect the academic achievement of unit schools, and to predict how academic achievements dynamically change with the support of offices of education. The results of academic achievement of 606 general high schools in 16 metropolitan and provincial offices of education(rates of attaining more than normal education in Korean, English, and mathematics subjects) were analyzed using a multi-level model and system dynamics. As a result of the analysis, it was confirmed that the provincial and provincial offices of education's efforts to increase the efficiency of local education finance, the efforts to reduce teacher administration, and the facilitation of faculty training were the variables of the provincial and provincial offices of education. In addition, through policy experiments, efforts to revitalize teacher training were the most influential factors in academic achievement of unit schools, followed by efforts to streamline local education finances and to reduce the administrative work of teachers. In order to improve the academic achievement of unit schools, the functions of the metropolitan and provincial offices of education should be strengthened based on the education accountability, and policies need to be established in the mid- to long-term perspective.

• Journal of Radiation Protection and Research
• /
• v.40 no.1
• /
• pp.55-64
• /
• 2015

Dose calculations which are a crucial requirement for radiotherapy treatment planning systems require accuracy and rapid calculations. The conventional radiotherapy treatment planning dose algorithms are rapid but lack precision. Monte Carlo methods are time consuming but the most accurate. The new combined system that Monte Carlo methods calculate part of interesting domain and the rest is calculated by neural can calculate the dose distribution rapidly and accurately. The preliminary study showed that neural networks can map functions which contain discontinuous points and inflection points which the dose distributions in inhomogeneous media also have. Performance results between scaled conjugated gradient algorithm and Levenberg-Marquardt algorithm which are used for training the neural network with a different number of neurons were compared. Finally, the dose distributions of homogeneous phantom calculated by a commercialized treatment planning system were used as training data of the neural network. In the case of homogeneous phantom;the mean squared error of percent depth dose was 0.00214. Further works are programmed to develop the neural network model for 3-dimensinal dose calculations in homogeneous phantoms and inhomogeneous phantoms.