• Journal of KIISE:Software and Applications
• /
• v.31 no.4
• /
• pp.467-477
• /
• 2004

While recommender systems were used by a few E-commerce sites former days, they are now becoming serious business tools that are re-shaping the world of I-commerce. And collaborative filtering has been a very successful recommendation technique in both research and practice. But there are two problems in personalized recommender systems, it is First-Rating problem and Sparsity problem. In this paper, we solve these problems using the associative relation clustering and “Lift” of association rules. We produce “Lift” between items using user's rating data. And we apply Threshold by -cut to the association between items. To make an efficiency of associative relation cluster higher, we use not only the existing Hypergraph Clique Clustering algorithm but also the suggested Split Cluster method. If the cluster is completed, we calculate a similarity iten in each inner cluster. And the index is saved in the database for the fast access. We apply the creating index to predict the preference for new items. To estimate the Performance, the suggested method is compared with existing collaborative filtering techniques. As a result, the proposed method is efficient for improving the accuracy of prediction through solving problems of existing collaborative filtering techniques.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.5
• /
• pp.331-337
• /
• 2023

In this paper, we propose a deep learning model to detect lumbar 3 (L3) CT images to determine the occurrence and degree of sarcopenia. In addition, we would like to propose an optimization technique that uses oversampling ratio and class weight as design parameters to address the problem of performance degradation due to data imbalance between L3 level and non-L3 level portions of CT data. In order to train and test the model, a total of 150 whole-body CT images of 104 prostate cancer patients and 46 bladder cancer patients who visited Gangneung Asan Medical Center were used. The deep learning model used ResNet50, and the design parameters of the optimization technique were selected as six types of model hyperparameters, data augmentation ratio, and class weight. It was confirmed that the proposed optimization-based L3 level extraction model reduced the median L3 error by about 1.0 slices compared to the control model (a model that optimized only 5 types of hyperparameters). Through the results of this study, accurate L3 slice detection was possible, and additionally, we were able to present the possibility of effectively solving the data imbalance problem through oversampling through data augmentation and class weight adjustment.

• Education of Primary School Mathematics
• /
• v.26 no.4
• /
• pp.333-348
• /
• 2023

Clear analysis and diagnosis of various characteristic factors of individual students is the most important in order to realize individual customized teaching and learning, which is considered the most essential function of math artificial intelligence-based digital textbooks. In this study, analysis factors and tools for individual customized learning diagnosis and construction models for data collection and analysis were derived from mathematical AI digital textbooks. To this end, according to the Ministry of Education's recent plan to apply AI digital textbooks, the demand for AI digital textbooks in mathematics, personalized learning and prior research on data for it, and factors for learner analysis in mathematics digital platforms were reviewed. As a result of the study, the researcher summarized the factors for learning analysis as factors for learning readiness, process and performance, achievement, weakness, and propensity analysis as factors for learning duration, problem solving time, concentration, math learning habits, and emotional analysis as factors for confidence, interest, anxiety, learning motivation, value perception, and attitude analysis as factors for learning analysis. In addition, the researcher proposed noon data on the problem, learning progress rate, screen recording data on student activities, event data, eye tracking device, and self-response questionnaires as data collection tools for these factors. Finally, a data collection model was proposed that time-series these factors before, during, and after learning.

• Journal of KIISE:Computer Systems and Theory
• /
• v.35 no.9_10
• /
• pp.485-496
• /
• 2008

As the complexity of SoC (System-on-Chip) design increases dramatically. traditional system performance analysis and verification methods based on RTL (Register Transfer Level) are no more valid for increasing time-to-market pressure. Therefore a new design methodology is desperately required for system verification in early design stages. and hardware software (HW-SW) cosimulation at TLM (Transaction Level Modeling) level has been researched widely for solving this problem. However, most of HW-SW cosimulators support few restricted ion levels only, which makes it difficult to integrate HW-SW cosimulators with different ion levels. To overcome this difficulty, this paper proposes a multipurpose framework for HW SW cosimulation to provide systematic SoC design flow starting from software application design. It supports various design techniques flexibly for each design step, and various HW-SW cosimulators. Since a platform design is possible independently of ion levels and description languages, it allows us to generate simulation models with various ion levels. We verified the proposed framework to model a commercial SoC platform based on an ARM9 processor. It was also proved that this framework could be used for the performance optimization of an MJPEG example up to 44% successfully.

• Journal of Korea Multimedia Society
• /
• v.13 no.8
• /
• pp.1154-1162
• /
• 2010

Because it is easy to implement the scalar quantizer, it is used in various video coding systems. Although the scalar quantizer with a large quantization stepsize can reduce the amount of data, it has disadvantage that the reconstructed picture quality is poor. In this paper, we propose an efficient method which improves the coding performance by maintaining original quantization stepsize and increasing the number of quantization reconstruction levels. Simultaneously, for the purpose of solving the problem of transmitting the added symbol informations which is used to indicate the region of quantizer reconstruction level as the number of quantizer reconstruction level is increased, we also suggest the method to reduce the added informations. Therefore, for the intra-coded picture of H.264 video coding system, we generate the huffman codes for the symbol informations of quantization reconstruction regions by 4${\times}$4(horizontal 4 pixels, vertical pixels) block unit. Furthermore, for the inter-coded picture, we also generate the huffman codes for the symbol informations of quantization reconstruction regions by 8${\times}$8 blocks and 4${\times}$4 blocks within a macroblock. Adopting this method of reducing the added information by increasing the number of quantization reconstruction region, It is shown that the coding performance can be improved at the same bitrate.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.3
• /
• pp.122-126
• /
• 2017

The aim of this study was to develop a device for solving the heating problem of living space using heated air, utilizing a simple air heater type collector for solar energy. At the present time, this study assessed the possibility of a development system through theoretical calculations for the amount of available energy according to the size change of the air-heated solar energy collector. To produce and supply hot water using the heat energy of the sun, hot water at $100^{\circ}C$ or less was produced using a flat or vacuum tube type collector. The purpose of this study was to research the air heating type solar collector that utilizes heating energy with heating air above $75^{\circ}C$, by designing and manufacturing an air piping type solar collector that is a simpler type than a conventional solar collector system. The analysis results were obtained for the generated air temperature ($^{\circ}C$) and the production of air (kg/h) to determine the performance of air heating by an air-heated solar collector according to the heat transfer characteristics in the collector of the model when a specified amount of heat flux was dropped into a solar collector of a certain size using PHOENICS, which is a heat flow analysis program applying the Finite Volume Method. From the analysis result, the temperature of the air obtained was approximately $40.5^{\circ}C$, which could be heated using an air heating tube with an inner diameter of 0.1m made of aluminum in a collector with a size of $1.2m{\times}1.1m{\times}0.19m$. The production of air was approximately 161 m3/h. This device can be applied to maintain a suitable environment for human activity using the heat energy of the sun.

• Journal of The Korean Association of Information Education
• /
• v.18 no.2
• /
• pp.225-234
• /
• 2014

Robot programming allows students to plan an algorithm in order to solve a task, implement the algorithm, easily confirm the results of the implementation with a robot, and correct errors. Thus, robot programming is a problem solving process based on reflective thinking, and is closely related to students' metacognition. On this point, this research is conducted to develop a robot programming instructional model for tile enhancement of students' metacognition. The instructional processes of robot programming are divided into 5 stages (i.e., 'exploration of learning tasks', 'a teacher's modeling', 'preparation of a plan for task performance along with the visualization of the plan', 'task performance', and 'self-evaluation and self-reinforcement'), and core strategies of metacognition (i.e., planning, monitering, regulating, and evaluating) are suggested for students' activities in each stage. Also, in order to support students' programming activities and the use of metacognition, instructional strategies based on cognitive apprenticeship (i.e. modeling, coaching and scaffolding) are suggested in relation to the instructional model. In addition, in order to support students' metacognitive activities. the model is designed to use self-questioning, and questions that students can use at each stage of the model are presented.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.5
• /
• pp.548-556
• /
• 2016

Cognitive-linguistic changes that normally accompany aging are often simply an annoyance, but in some instances they may herald a more perilous course of decline to a state of neurological disease. This study investigated the correlation between subjective and objective tests on cognitive-linguistic abilities in older adults and the predictors of objective performances. Healthy elders over 65 years of age (n=63) and their informants (n=63) completed the subjective and objective cognitive-linguistic tests (ISCOLE and CAPTBI) from July of 2015 to February of 2016. The main findings were as follows: performance on the self-report test was not significantly different from that on the informant-report test. Additionally, eight domains in older adults group and 15 domains in the informants group were significantly associated with performance on the objective test. Finally, language on the informant-report test was a predictor of several abilities including problem solving and memory on the informant-report test predicted executive function and language. The present study demonstrates that two groups have significant differences in correlation between subjective and objective tests on the cognitive-linguistic abilities, and there are more relevant domains in rating by informants. These findings have implications for the use of cognitive-linguistic evaluation and preventive intervention in clinical settings.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.10
• /
• pp.29-41
• /
• 2022

Recently, with the development of deep learning technology, a variety of huge models with excellent performance have been devised by pre-training massive amounts of text data. However, in order for such a model to be applied to real-life services, the inference speed must be fast and the amount of computation must be low, so the technology for model compression is attracting attention. Knowledge distillation, a representative model compression, is attracting attention as it can be used in a variety of ways as a method of transferring the knowledge already learned by the teacher model to a relatively small-sized student model. However, knowledge distillation has a limitation in that it is difficult to solve problems with low similarity to previously learned data because only knowledge necessary for solving a given problem is learned in a teacher model and knowledge distillation to a student model is performed from the same point of view. Therefore, we propose a heterogeneous knowledge distillation method in which the teacher model learns a higher-level concept rather than the knowledge required for the task that the student model needs to solve, and the teacher model distills this knowledge to the student model. In addition, through classification experiments on about 18,000 documents, we confirmed that the heterogeneous knowledge distillation method showed superior performance in all aspects of learning efficiency and accuracy compared to the traditional knowledge distillation.

• Information Systems Review
• /
• v.21 no.4
• /
• pp.69-97
• /
• 2019

Knowledge service firms are able to have higher 'Organizational Performance (OP)' by improving efficiency in management processes on customer problem solving. This study explores the role of inefficiency that has been overlooked up to now compared to the management process efficiency. We also suggest in this study 'Hierarchical Culture (HC)' and 'IT Relatedness (IR)' as the factors influencing the inefficiency of management processes, and propose the moderating effect of 'Task Difficulty (TD)' on the relationship between independent factors and 'Inefficiency of Business Process(IP)'. The results of analysis show that 'HC' has a positive effect on 'IP', and 'IR' has a negative effect on 'IP'. 'TD' was significant moderator of between independent variables and 'IP'. 'IP' was shown to play a full mediating role between independent factors and 'OP'. In conclusion, knowledge service firms are desired to reduce 'HC' and enhance 'IR' by minimizing unnecessary formal procedures, securing flexibility in decision making through appropriate empowerment, creating a smooth flow of knowledge, and enhancing the level of IT resource management and utilization. In addition, in order to effectively reduce 'IP', it is required that a company with a high degree of 'TD' to more reduce a 'HC' and a company with a low degree of 'TD' to more enhance a 'IR'.