• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.5
• /
• pp.134-140
• /
• 1994

In this paper, an algorithm of CBAM(Combination Bidirectional Associative Memory) model proposes, analyzes and tests CBAM model `s performancess by simulating with recalls and recognitions of patterns. In learning-procedure each correlation matrix of training patterns is obtained. As each correlation matrix's some elements correspond to juxtaposition, all correlation matrices are merged into one matrix (Combination Correlation Matrix, CCM). In recall-procedure, CCM is decomposed into a number of correlation matrices by spiliting its elements into the number of elements corresponding to all training patterns. Recalled patterns are obtained by multiplying input pattern with all correlation matrices and selecting a pattern which has the smallest value of energy function. By using a CBAM model, we have some advantages. First, all pattern having less than 20% of noise can be recalled. Second, memory capacity of CBAM model, can be further increased to include English alphabets or patterns. Third, learning time of CBAM model can be reduced greatly because of operation to make CCM.

• School Mathematics
• /
• v.2 no.2
• /
• pp.489-508
• /
• 2000

With the increased use of computational technology, many educators question about spending large amount of class time for dealing with computational algorithms in elementary school math classroom at the expense of more holistic aspects of mathematics such as number sense, spatial sense, problem solving and data management. This paper introduce the new method for learning addition and subtraction so called ‘Mrs. Weill’s Hill’, which is believed as a suitable remedial method for children with mathematical learning disabilities, with perceptual problems, or with limited working memory capacities. This method provides children with external memory strategies by allowing them to solve the addition and subtraction problems in a stage by stage fashion with as many steps as they require. It also gives the child greater flexibility in the solution process and thus helps reduce anxiety.

• Korean Journal of Agricultural Science
• /
• v.46 no.1
• /
• pp.67-78
• /
• 2019

The purpose of this study was to predict the water quality using the RNN (recurrent neutral network) and LSTM (long short-term memory). These are advanced forms of machine learning algorithms that are better suited for time series learning compared to artificial neural networks; however, they have not been investigated before for water quality prediction. Three water quality indexes, the BOD (biochemical oxygen demand), COD (chemical oxygen demand), and SS (suspended solids) are predicted by the RNN and LSTM. TensorFlow, an open source library developed by Google, was used to implement the machine learning algorithm. The Okcheon observation point in the Geum River basin in the Republic of Korea was selected as the target point for the prediction of the water quality. Ten years of daily observed meteorological (daily temperature and daily wind speed) and hydrological (water level and flow discharge) data were used as the inputs, and irregularly observed water quality (BOD, COD, and SS) data were used as the learning materials. The irregularly observed water quality data were converted into daily data with the linear interpolation method. The water quality after one day was predicted by the machine learning algorithm, and it was found that a water quality prediction is possible with high accuracy compared to existing physical modeling results in the prediction of the BOD, COD, and SS, which are very non-linear. The sequence length and iteration were changed to compare the performances of the algorithms.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.17 no.30
• /
• pp.25-34
• /
• 1994

Mental workload has a improtant place in modern work environment such as human-computer interaction. Designing man-machine system requires knowledge and evaluation of the human cognitive process which controls information flow during our works. Many studies estimate reaction time as a index of menatal workload. This paper investigates what reflacts the workload of human information handling when the informations grow its degree. Experiment result introuce the memory time that explain the information-load more sensitive than react time. And react time shows learning effect but memory time does'nt show that effect So it can be concluded that cognitive learning or work schema needs more time to achieve dexterity than motor skill.

• The Journal of the Korea Contents Association
• /
• v.15 no.8
• /
• pp.625-641
• /
• 2015

Recent research shows that emotion is closely related to memory and learning. Although a growing number of educators have high interest in affective aspects of learning processes and outcomes, there are few studies to investigate systematically instructional strategies and learning environments based on learners' emotion. Despite the efforts to understand the role of emotion and to facilitate positive emotion for meaningful learning in face-to-face and online environments, it is still a challenging issue to measure emotion in a valid and reliable way. To implement emotion-based education, it is essential to overcome the limitation of self-report surveys on emotion, which rely on the memory of learners. The current study surveyed emotion measurement tools, which are recently developed in education and other domains, in terms of self-report, neurophysiology, and behavioral responses. This study also discussed how emotion measurement tools can be used in authentic learning and teaching situations. Particularly, this study focused on cutting-edge technologies that would enable educators to collect and analyze learners' emotion easily in real-world contexts. This study will contribute to the research about the role of emotion in education and the design of adaptive learning environments that consider the change of learners' emotion.

• Journal of Korea Multimedia Society
• /
• v.6 no.5
• /
• pp.824-830
• /
• 2003

RPA (Recursive Partition Averaging) method was proposed in order to improve the storage requirement and classification rate of the Memory Based Reasoning. That algorithm worked well in many areas, however, the major drawbacks of RPA are it's pattern averaging mechanism. We propose an adaptive OHC algorithm which uses the FPD(Feature-based Population Densimeter) to increase the classification rate of RPA. The proposed algorithm required only approximately 40% of memory space that is needed in k-NN classifier, and showed a superior classification performance to the RPA. Also, by reducing the number of stored patterns, it showed a excellent results in terms of classification when we compare it to the k-NN.

• Proceedings of the KIEE Conference
• /
• 1993.07a
• /
• pp.492-494
• /
• 1993

CMAC (Cerebeller Model Articulation Controller) is kind of Neural Networks that imitate the human cerebellum. For storage and retrieval of learned data, the input of CMAC is used as a key to determine the memory location. he learned information is distributively stored in physical memory. The learning of CMAC is very fast and converged well, therefore, it effects the application of Pattern Recognition. Through the our experiment of Pattern Recognition, we will prove that CMAC is very suitable for On-line real time processing and incremental learning of Neural Networks.

• ETRI Journal
• /
• v.44 no.3
• /
• pp.438-449
• /
• 2022

This study proposes a dependency grammar-based self-attention multilayered bidirectional long short-term memory (DG-M-Bi-LSTM) model for subject-predicate-object (SPO) tuple recognition from natural language (NL) sentences. To add recent knowledge to the knowledge base autonomously, it is essential to extract knowledge from numerous NL data. Therefore, this study proposes a high-accuracy SPO tuple recognition model that requires a small amount of learning data to extract knowledge from NL sentences. The accuracy of SPO tuple recognition using DG-M-Bi-LSTM is compared with that using NL-based self-attention multilayered bidirectional LSTM, DG-based bidirectional encoder representations from transformers (BERT), and NL-based BERT to evaluate its effectiveness. The DG-M-Bi-LSTM model achieves the best results in terms of recognition accuracy for extracting SPO tuples from NL sentences even if it has fewer deep neural network (DNN) parameters than BERT. In particular, its accuracy is better than that of BERT when the learning data are limited. Additionally, its pretrained DNN parameters can be applied to other domains because it learns the structural relations in NL sentences.

• The Journal of Korean society of community based occupational therapy
• /
• v.3 no.1
• /
• pp.67-75
• /
• 2013

Objective : The purpose of study was to visual scanning program on the effect of visual memory in stroke patients. Method : A single subject experimental research with ABA design was employed in this study. The experiment composed of 15 sessions in total: 5 sessions for baseline, 7 session for visual scanning program, and 3 sessions for the second baseline. Each session for intervention took 30 minutes daily. MVPT, CNT(visual span test, visual learning test) were used for assessment visual perception, visual memory. Result : After visual scanning program, changing faster processing time MVPT 5.5 seconds to 4.5 seconds. Also all itme raw score changes of CNT visual span test, visual learning test. Conclusion : Visual scanning program in stroke patients give a positive impact on the visual memory. To improve stroke patients' perception visual scanning program utilizing visual perception research as well as training programs for a variety of looks forward to being developed.

• KIISE Transactions on Computing Practices
• /
• v.23 no.7
• /
• pp.417-423
• /
• 2017

Recently, many embedded devices that have the computing capability required for deep learning have become available; hence, many new applications using these devices are emerging. However, these embedded devices have an architecture different from that of PCs and high-performance servers. In this paper, we propose a method that improves the performance of deep-learning framework by considering the architecture of an embedded device that shares memory between the CPU and the GPU. The proposed method is implemented in Caffe, an open-source deep-learning framework, and is evaluated on an NVIDIA Jetson TK1 embedded device. In the experiment, we investigate the image recognition performance of several state-of-the-art deep-learning networks, including AlexNet, VGGNet, and GoogLeNet. Our results show that the proposed method can achieve significant performance gain. For instance, in AlexNet, we could reduce image recognition latency by about 33% and energy consumption by about 50%.