• Korean Journal of Artificial Intelligence
• /
• v.9 no.1
• /
• pp.1-7
• /
• 2021

In this paper, We focused the issue of creating a socially problematic nurse schedule. The nurse schedule should be prepared in consideration of three shifts, appropriate placement of experienced workers, the fairness of work assignment, and legal work standards. Because of the complex structure of the nurse schedule, which must reflect various requirements, in most hospitals, the nurse in charge writes it by hand with a lot of time and effort. This study attempted to automatically create an optimized nurse schedule based on legal labor standards and fairness. We developed an I/O Q-Learning algorithm-based model based on Python and Web Application for automatic nurse schedule. The model was trained to converge to 100 by creating an Fairness Indicator Score(FIS) that considers Labor Standards Act, Work equity, Work preference. Manual nurse schedules and this model are compared with FIS. This model showed a higher work equity index of 13.31 points, work preference index of 1.52 points, and FIS of 16.38 points. This study was able to automatically generate nurse schedule based on reinforcement Learning. In addition, as a result of creating the nurse schedule of E hospital using this model, it was possible to reduce the time required from 88 hours to 3 hours. If additional supplementation of FIS and reinforcement Learning techniques such as DQN, CNN, Monte Carlo Simulation and AlphaZero additionally utilize a more an optimized model can be developed.

• International Journal of Computer Science & Network Security
• /
• v.24 no.7
• /
• pp.108-117
• /
• 2024

The selection and recommendation of a suitable job applicant from the pool of thousands of applications are often daunting jobs for an employer. The recommendation and selection process significantly increases the workload of the concerned department of an employer. Thus, Resume Classification System using the Natural Language Processing (NLP) and Machine Learning (ML) techniques could automate this tedious process and ease the job of an employer. Moreover, the automation of this process can significantly expedite and transparent the applicants' selection process with mere human involvement. Nevertheless, various Machine Learning approaches have been proposed to develop Resume Classification Systems. However, this study presents an automated NLP and ML-based system that classifies the Resumes according to job categories with performance guarantees. This study employs various ML algorithms and NLP techniques to measure the accuracy of Resume Classification Systems and proposes a solution with better accuracy and reliability in different settings. To demonstrate the significance of NLP & ML techniques for processing & classification of Resumes, the extracted features were tested on nine machine learning models Support Vector Machine - SVM (Linear, SGD, SVC & NuSVC), Naïve Bayes (Bernoulli, Multinomial & Gaussian), K-Nearest Neighbor (KNN) and Logistic Regression (LR). The Term-Frequency Inverse Document (TF-IDF) feature representation scheme proven suitable for Resume Classification Task. The developed models were evaluated using F-Score_M, Recall_M, Precission_M, and overall Accuracy. The experimental results indicate that using the One-Vs-Rest-Classification strategy for this multi-class Resume Classification task, the SVM class of Machine Learning algorithms performed better on the study dataset with over 96% overall accuracy. The promising results suggest that NLP & ML techniques employed in this study could be used for the Resume Classification task.

• Journal of Engineering Education Research
• /
• v.14 no.4
• /
• pp.11-19
• /
• 2011

The purpose of this study was to identify learning strategies by learning style of first-year engineering students in order to find implications for teaching and learning strategies in engineering education. This study was conducted with 273 first-year students in two universities in Korea. Following were the results: First, there were Sensing learners(72.2%), Visual learners(84.6%), Reflective learners(64.8%), and Sequential learners(58.2%) and the level of learning strategies was 3.28(SD=0.38). Secondly, the finding revealed that there was only significant difference in learning strategies on Information processing dimension and Active students demonstrated higher level of learning strategies than Reflective students. To be more specific, there were significant differences in cognitive, meta-cognitive, and internal and external management. For engineering education, implications for teaching strategies in classroom and self-regulated learning strategies were discussed.

• Journal of Positioning, Navigation, and Timing
• /
• v.11 no.3
• /
• pp.163-172
• /
• 2022

Typical anti-jamming technologies based on array antennas, Space Time Adaptive Process (STAP) & Space Frequency Adaptive Process (SFAP), are very effective algorithms to perform nulling and beamforming. However, it does not perform equally well for all types of jamming signals. If the anti-jamming algorithm is not optimized for each signal type, anti-jamming performance deteriorates and the operation stability of the system become worse by unnecessary computation. Therefore, jamming classification technique is required to obtain optimal anti-jamming performance. Machine learning, which has recently been in the spotlight, can be considered to classify jamming signal. In general, performing supervised learning for classification requires a huge amount of data and new learning for unfamiliar signal. In the case of jamming signal classification, it is difficult to obtain large amount of data because outdoor jamming signal reception environment is difficult to configure and the signal type of attacker is unknown. Therefore, this paper proposes few-shot jamming signal classification technique using meta-learning and transfer-learning to train the model using a small amount of data. A training dataset is constructed by anti-jamming algorithm input data within the GNSS receiver when jamming signals are applied. For meta-learning, Model-Agnostic Meta-Learning (MAML) algorithm with a general Convolution Neural Networks (CNN) model is used, and the same CNN model is used for transfer-learning. They are trained through episodic training using training datasets on developed our Python-based simulator. The results show both algorithms can be trained with less data and immediately respond to new signal types. Also, the performances of two algorithms are compared to determine which algorithm is more suitable for classifying jamming signals.

• Journal of the Korean Society for Library and Information Science
• /
• v.44 no.1
• /
• pp.29-51
• /
• 2010

A knowledge-based society values creative and independent individuals. This study depicts operational approaches to the effective utilization of school libraries as teaching/learning media center in order to support independent learning in relation to the way in which constructivist teaching-learning(CTL) improves learners' self-learning abilities. The result of this study seems to imply that self-learning based on constructivism is possible only when school libraries are managed as teaching/learning media centers and that the more variety there is in learning materials and when more direct interaction exists, there is more creativity and self-learning abilities are achieved in the learning process.

• Journal of Oriental Neuropsychiatry
• /
• v.25 no.4
• /
• pp.333-350
• /
• 2014

Objectives: The purpose of this study was to research learning based on brain science and the learning methodology of Korean Medicine according to disparity of age. Through this, the study aimed to provide a guideline to related Korean Medicine treatments as well as the common nurturing/educational institutions. Methods: All journals and dissertations on brain science based learning methods studied in Korea to date that could be found in the National Assembly Library and the RISS were implemented in the analysis. The terminology used for search was as follows: 1st search, 'Brain'; 2nd search, 'Learning', 'Education'; 3rd search, 'Baby, 'Infant', 'Child'. For the learning methodology of Korean Medicine according to disparity of age, the related contents were extracted from Donguibogam and Liuyi, Sasang constitutional medicine. Results: A total of 30 studies, were collected as data. In the baby stage, the development and myelination of brain neurons are accelerated by experience and learning, highly influenced by social, cognitive and emotional movement. In infancy, the frontal lobe actively develops, so education for development of the prefrontal cortex is suggested. The brain of the infant at this stage can be developed by arts and physical education. In the child stage, the parietal and temporal lobe develop actively. Thus, programs to stimulate brain activity including brain respiration would be helpful in enhancing learning ability, concentration, etc. As evidence for learning and nurturing methodology according to disparity of age from Korean Medicine prospective, the following are listed: Location and time for sexual intercourse before pregnancy, stabilization during pregnancy, baby nurturing methods for nurturing from Donguibogam. Also Liuyi and Sasanag constitutional medicine can be the learning methodology according to disparity of age. And there are acupuncture points on each head section according to age in Donguibogam. Conclusions: Studies on 'brain-science based learning' are continuously being conducted. Based on these studies, diverse new brain-science based learning will be developed in the future. There is also a need to develop the learning methodology of Korean Medicine according to disparity of age in a more systematic and diverse way.

• Journal of Digital Convergence
• /
• v.8 no.4
• /
• pp.151-164
• /
• 2010

This study utilized SPSS and AMOS program to research a process of learning satisfaction of learners, who used Ubiquitous Living English Experience Learning Center. The following results were found ; First, there was a positive correlation between learning setting and learning interest, between learning setting and learning satisfaction, between confidence and learning interest, between confidence and learning satisfaction, and between learning interest and learning satisfaction. Second, the process of the research model was meaningful in various ways: learning setting ${\rightarrow}$ confidence, learning setting ${\rightarrow}$ learning interest, learning setting ${\rightarrow}$ learning satisfaction, confidence ${\rightarrow}$ learning satisfaction, learning interest ${\rightarrow}$ learning satisfaction. Finally, learning setting had a direct influence upon learning interest and learning satisfaction.

• Journal of the Korean Society of Radiology
• /
• v.83 no.6
• /
• pp.1259-1272
• /
• 2022

Purpose As part of ongoing efforts to improve the current e-learning center, a survey was conducted regarding user experience and satisfaction to identify areas of improvement. Materials and Methods Radiologists (n = 454/617) and radiology residents (n = 163/617) of the Korean Society of Radiology were asked to answer a survey via email. The questionnaire asked for basic user information as well as user experiences relating to the e-learning center, such as workplace, frequency of use, overall satisfaction levels, reasons for satisfaction or dissatisfaction, and other suggestions for improvement. Results Annual members and all members of the e-learning center reported above average satisfaction levels of 67% and 42%, respectively. Approximately 30% of respondents viewed e-learning center lectures more than 5 times a month, with residents having a particularly high usage frequency. There was a high demand for additional lectures covering more diverse specialties (e-learning for annual members only: n = 28/97, e-learning for all members: n = 72/166), a smoother and more convenient searching platform/interface (n = 37/97 and n = 58/166, respectively), and regular content updates. In addition, many of the members suggested the addition of user-friendly functions such as playback speed control, a way to save viewing history, as well as requests for improved system stability. Conclusion Based on survey results, the educational committee plans to continue its efforts to improve the e-learning center by increasing the quality and quantity of available lectures, and increasing technical support to improve the stability and convenience of the e-learning digital system.

• Journal of Oriental Neuropsychiatry
• /
• v.24 no.4
• /
• pp.393-402
• /
• 2013

Objectives: This study is a clinical report of a patient with ADHD and learning disorders who is being treated with hyperbaric oxygen, scalp acupuncture, cognitive enhancement therapy and speech-language therapy. Methods: The BASA-R, BASA-M and REVT tests were used for the diagnosis of learning disorders. For the treatment, hyperbaric oxygen therapy, scalp acupuncture, cognitive enhancement therapy and speech-language therapy were all being used. The Raven's matrix tests were compared for between before and after the abovementioned therapies. Results: After the treatment, Raven's matrix test grade improved from 4 to 5. The improvement of the patient's concentration, communication, motion, confidence, and sleep conditions were observed. Conclusions: These therapies including the hyperbaric oxygen therapy are efficient for the treatment of ADHD and learning disorders.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.6
• /
• pp.1743-1758
• /
• 2023

Automatic modulation classification is a critical algorithm for non-cooperative communication systems. This paper addresses the challenging problem of closed-set and open-set signal modulation classification in complex channels. We propose a novel approach that incorporates a self-learning filter and center-loss in Deep Residual Shrinking Networks (DRSN) for closed-set modulation classification, and the Opendistance method for open-set modulation classification. Our approach achieves better performance than existing methods in both closed-set and open-set recognition. In closed-set recognition, the self-learning filter and center-loss combination improves recognition performance, with a maximum accuracy of over 92.18%. In open-set recognition, the use of a self-learning filter and center-loss provide an effective feature vector for open-set recognition, and the Opendistance method outperforms SoftMax and OpenMax in F1 scores and mean average accuracy under high openness. Overall, our proposed approach demonstrates promising results for automatic modulation classification, providing better performance in non-cooperative communication systems.