Earticle

On the knowledge based society is demanding for competent subjects who can create new knowledge and apply it as well as possess self-directed learning abilities. Even when it comes to instructing underachievers, changes in the systematic education program is being required. Underachievers show difference in learning ability with other students as their grade level increases and this leads to a decline in understanding about what is learned during class. Accordingly, this results in the loss of the desire to learn and is causing underachievement to become more serious. In this paper, arithmetic section was selected amongst all the other sections in an elementary mathematics textbook. In order to minimize the learning deficit of underachievers, recomposition was made with contents and stages appropriate for the instruction of underachievers to develop a self-directed learning model and implement the Scratch game program. As a result of applying the program of this study on underachievers who are in third grade of elementary school, it was analyzed that their competence of arithmetic operation was enhanced and that it also increased their level of interest about learning.

다른 사람에게 학습 자료를 가르치는 것의 이점은 학업 성취도에서 나타났다. 불안은 학습을 방해하는 요인 중 하나이고 수학 불안은 수학 성취도와 밀접한 관련이 있음이 밝혀졌다. 따라서 본 연구의 목적은 대학생들이 통계를 학습할 때 다른 사람을 가르치는 것이 수학 불안에 도움을 주는지 알아보는 것이다. 통계수업에 등록한 학생들 59명이 참여했고 30명의 학생은 그룹 안에서 다른 학생을 가르치는 그룹 과제를 수행했고, 29명의 학생은 수행하지 않았다. 그룹 과제를 제외하고 강사, 강의, 문제 풀이 과제와 시험은 모두 동일했다. 그 결과, 가르치는 그룹 과제를 수행한 학생들의 수학 불안은 학기 말에 감소하였다. 수학 불안이 증가하면 통계 학습에 대한 태도가 부정적으로 나타나고 그 결과 학습 성취도가 저하되었다. 또한, 수학 불안과 통계 학습에 대한 태도의 관계는 다른 사람을 가르치는 것으로 조절되었다. 이러한 결과는 가르치기는 수학 불안을 감소시키는 데 영향을 미쳐 지속적인 학습 이득을 얻을 수 있음을 시사한다.

The benefits of teaching learning materials to others have been shown on learning achievement. Anxiety is one of the obstacles in learning and it has been shown that math anxiety is strongly associated with math achievement. Thus, the aim of this study was to investigate whether teaching others benefits math anxiety when university students learn statistics. 59 students who enrolled in statistics class participated and 30 students performed group assignment of teaching peer in a group and 29 students did not. Other than group assignments, the instructor, lectures, assignment of solving the problems, and exams were all the same. The results showed that the math anxiety of students who did group assignments of teaching was decreased at the end the semester. Increased math anxiety yielded negative attitudes toward learning statistics, resulting in poor learning performance. Furthermore, the relationship between math anxiety and the attitudes toward leaning statistics was moderated by teaching others. The results suggest that teaching others has an effect on reducing math anxiety and thus, possibly yield persistent learning gains.

이 연구는 우즈벡 한국어 학습자들의 한국어 학습 실태와 관련하여 한국어 학습 목적, 학습 방법, 학습 과 정에서 나타나는 어려움, 개별적인 한국어 학습 방법, 한국어 분야 중 가장 중요하게 학습하는 분야 등에 대해 설문 조사하여 그 내용을 기반으로 우즈벡 한국어 학습자들이 좀 더 효율적으로 한국어 학습할 수 있는 여건 을 마련하고자 하였다. 우즈벡 한국어 학습자들의 한국어 학습 목적은 주로 한국 내 취업과 한국문화에 대한 관심이 많았다. 한국어 학습 방법으로는 교재와 대중 매체를 이용한다는 의견이 많았는데, 이는 앞으로 대중 매체를 통한 한국어교육이 필요하다는 것을 보여주는 결과이다. 한국어 학습에서 어려움을 주는 부분에 대해 발음이 가장 어렵다고 하였으며, 교실에서 쓰는 언어는 우즈벡어를 쓰는 것이 효과적이라 하였다. 우즈벡 학습 자들 개인의 한국어 학습 방법으로는 한국인과의 사교와 유튜브였다. 현재 한국어에서 중점적으로 학습하는 분야는 어휘이며, 가장 중요하게 생각하는 분야는 말하기, 듣기 등이었다. 이러한 결과는 우즈벡 한국어 학습 자들의 한국어 교육에서 교육 내용 구성이나 교육 과정의 설계 등의 측면에서는 반드시 고려해 보아야 할 부분이다.

The study was designed to create an environment in which Uzbekistan's Korean learners can learn Korean more efficiently by conducting questionnaires on the purpose of learning Korean, the methods of learning Korean, and the most important areas of learning. Uzbekistan's Korean learners were mainly interested in Korean culture and employment in Korea. There were many opinions that the Korean language learning method should be through teaching materials and media, but this is a result that shows the need for Korean language education through the media in the future. He said that pronunciation is the most difficult part of learning Korean, and that Uzbekistan is the most effective language for the classroom. Uzbekistani learners learn Korean individually by socializing with Koreans and using YouTube. Currently, vocabulary is the most important field of study in Korean, and conversation and listening are the most important. Such a result is something that must be considered in terms of the composition of the Korean language education and the design of the curriculum for Uzbekistani language learners.

A transmission delay is a critical metric when dealing with ad hoc networks in 5G, particularly for real-time applications and multimedia. In this paper, we describe the challenge of managing mobile ad-hoc networks (MANET) based on multi-hop time-slotted time-division multiple access (TDMA) under routing delay minimization with heterogeneous traffic flows. In particular, we consider the challenge of request scheduling and power control in TDMA, for minimizing the overall weighted end-to-end packet delay when the weights are determined according to the priorities of the requests. A delay minimization network that uses deep learning is also introduced (DMNet). Simulations show that DMNet outperforms other state-of-art methods. Our approach is one of the first to utilize a DNN to solve end-to-end delay minimization through scheduling and power control.

The decision-making by agents in games is commonly based on reinforcement learning. To improve the quality of agents, it is necessary to solve the problems of the time and state space that are required for learning. Such problems can be solved by Macro-Actions, which are defined and executed by a sequence of primitive actions. In this line of research, the learning time is reduced by cutting down the number of policy decisions by agents. Macro-Actions were originally defined as combinations of the same primitive actions. Based on studies that showed the generation of Macro-Actions by learning, Macro-Actions are now thought to consist of diverse kinds of primitive actions. However an enormous amount of learning time and state space are required to generate Macro-Actions. To resolve these issues, we can apply insights from studies on the learning of tasks through Programming by Demonstration (PbD) to generate Macro-Actions that reduce the learning time and state space. In this paper, we propose a method to define and execute Macro-Actions. Macro-Actions are learned from a human subject via PbD and a policy is learned by reinforcement learning. In an experiment, the proposed method was applied to a car simulation to verify the scalability of the proposed method. Data was collected from the driving control of a human subject, and then the Macro-Actions that are required for running a car were generated. Furthermore, the policy that is necessary for driving on a track was learned. The acquisition of Macro-Actions by PbD reduced the driving time by about 16% compared to the case in which Macro-Actions were directly defined by a human subject. In addition, the learning time was also reduced by a faster convergence of the optimum policies.

In modern society, user privacy is emerging as an important issue as closed-circuit television (CCTV) systems increase rapidly in various public and private spaces. If CCTV cameras monitor sensitive areas or personal spaces, they can infringe on personal privacy. Someone's behavior patterns, sensitive information, residence, etc. can be exposed, and if the image data collected from CCTV is not properly protected, there can be a risk of data leakage by hackers or illegal accessors. This paper presents an innovative approach to "machine learning based reversible chaotic masking method for user privacy protection in CCTV environment." The proposed method was developed to protect an individual's identity within CCTV images while maintaining the usefulness of the data for surveillance and analysis purposes. This method utilizes a two-step process for user privacy. First, machine learning models are trained to accurately detect and locate human subjects within the CCTV frame. This model is designed to identify individuals accurately and robustly by leveraging state-of-the-art object detection techniques. When an individual is detected, reversible chaos masking technology is applied. This masking technique uses chaos maps to create complex patterns to hide individual facial features and identifiable characteristics. Above all, the generated mask can be reversibly applied and removed, allowing authorized users to access the original unmasking image.

This paper presents a novel method to construct a personalized e-Learning system based on dynamic estimations of item parameters and learners' abilities, where the learning content objects are of the same intrinsic quality or homogeneously distributed and the estimations are carried out using IRT(Item Response Theory). The system dynamically connects the test and the corresponding learning procedures. Test results are directly applied to estimate examinee's ability and are used to modify the item parameters and the difficulties of learning content objects during the learning procedure is being operated. We define the learning unit 'Node' as an amount of learning objects operated so that new parameters can be re-estimated. There are various content objects in a Node and the parameters estimated at the end of current Node are directly applied to the next Node. We offer the most appropriate learning Node for a person's ability throughout the estimation processes of IRT. As a result, this scheme improves learning efficiency in web-base e-Learning environments offering the most appropriate learning objects and items to the individual students according to their estimated abilities. This scheme can be applied to any e-Learning subject having homogeneous learning objects and unidimensional test items. In order to construct the system, we present an operation scenario using the proposed system architecture with the essential databases and agents.

Considering factors such as illumination, camera quality variations, and background-specific variations, identifying a face using a smartphone-based facial image capture application is challenging. Face Image Quality Assessment refers to the process of taking a face image as input and producing some form of "quality" estimate as an output. Typically, quality assessment techniques use deep learning methods to categorize images. The models used in deep learning are shown as black boxes. This raises the question of the trustworthiness of the models. Several explainability techniques have gained importance in building this trust. Explainability techniques provide visual evidence of the active regions within an image on which the deep learning model makes a prediction. Here, we developed a technique for reliable prediction of facial images before medical analysis and security operations. A combination of gradient-weighted class activation mapping and local interpretable model-agnostic explanations were used to explain the model. This approach has been implemented in the preselection of facial images for skin feature extraction, which is important in critical medical science applications. We demonstrate that the use of combined explanations provides better visual explanations for the model, where both the saliency map and perturbation-based explainability techniques verify predictions.

Micro ribonucleic acids (miRNAs) can regulate the protein expression levels of genes in the human body and have recently been reported to be closely related to the cause of disease. Determining the genes related to miRNAs will aid in understanding the mechanisms underlying complex miRNAs. However, the identification of miRNA-related genes through wet experiments (in vivo, traditional methods are time- and cost-consuming). To overcome these problems, recent studies have investigated the prediction of miRNA relevance using deep learning models. This study presents a method for predicting the relationships between miRNAs and genes. First, we reconstruct a negative dataset using the proposed method. We then extracted the feature using an autoencoder, after which the feature vector was concatenated with the original data. Thereafter, the concatenated data were used to train a long short-term memory model. Our model exhibited an area under the curve of 0.9609, outperforming previously reported models trained using the same dataset.

Recently, extensive studies have been conducted to apply deep learning to reinforcement learning to solve the state-space problem. If the state-space problem was solved, reinforcement learning would become applicable in various fields. For example, users can utilize dance-tutorial systems to learn how to dance by watching and imitating a virtual instructor. The instructor can perform the optimal dance to the music, to which reinforcement learning is applied. In this study, we propose a method of reinforcement learning in which the action space is dynamically adjusted. Because actions that are not performed or are unlikely to be optimal are not learned, and the state space is not allocated, the learning time can be shortened, and the state space can be reduced. In an experiment, the proposed method shows results similar to those of traditional Q-learning even when the state space of the proposed method is reduced to approximately 0.33% of that of Q-learning. Consequently, the proposed method reduces the cost and time required for learning. Traditional Q-learning requires 6 million state spaces for learning 100,000 times. In contrast, the proposed method requires only 20,000 state spaces. A higher winning rate can be achieved in a shorter period of time by retrieving 20,000 state spaces instead of 6 million.

In fine-tuning-based transfer learning, the size of the dataset may affect learning accuracy. When a dataset scale is small, fine-tuning-based transfer-learning methods use high computing costs, similar to a large-scale dataset. We propose a mid-level feature extractor that retrains only the mid-level convolutional layers, resulting in increased efficiency and reduced computing costs. This mid-level feature extractor is likely to provide an effective alternative in training a small-scale medical image dataset. The performance of the mid-level feature extractor is compared with the performance of low- and high-level feature extractors, as well as the fine-tuning method. First, the mid-level feature extractor takes a shorter time to converge than other methods do. Second, it shows good accuracy in validation loss evaluation. Third, it obtains an area under the ROC curve (AUC) of 0.87 in an untrained test dataset that is very different from the training dataset. Fourth, it extracts more clear feature maps about shape and part of the chest in the X-ray than fine-tuning method.

Wireless networks have become integral to society as they provide mobility and scalability advantages. However, their disadvantage is that they cannot control the media, which makes them vulnerable to various types of attacks. One example of such attacks is the evil twin access point (AP) attack, in which an authorized AP is impersonated by mimicking its service set identifier (SSID) and media access control (MAC) address. Evil twin APs are a major source of deception in wireless networks, facilitating message forgery and eavesdropping. Hence, it is necessary to detect them rapidly. To this end, numerous methods using clock skew have been proposed for evil twin AP detection. However, clock skew is difficult to calculate precisely because wireless networks are vulnerable to noise. This paper proposes an evil twin AP detection method that uses a multiple-feature-based machine learning classification algorithm. The features used in the proposed method are clock skew, channel, received signal strength, and duration. The results of experiments conducted indicate that the proposed method has an evil twin AP detection accuracy of 100% using the random forest algorithm.

Objective To present new classification methods of knee osteoarthritis (KOA) using machine learning and compare its performance with conventional statistical methods as classification techniques using machine learning have recently been developed. Methods A total of 84 KOA patients and 97 normal participants were recruited. KOA patients were clustered into three groups according to the Kellgren-Lawrence (K-L) grading system. All subjects completed gait trials under the same experimental conditions. Machine learning-based classification using the support vector machine (SVM) classifier was performed to classify KOA patients and the severity of KOA. Logistic regression analysis was also performed to compare the results in classifying KOA patients with machine learning method. Results In the classification between KOA patients and normal subjects, the accuracy of classification was higher in machine learning method than in logistic regression analysis. In the classification of KOA severity, accuracy was enhanced through the feature selection process in the machine learning method. The most significant gait feature for classification was flexion and extension of the knee in the swing phase in the machine learning method. Conclusion The machine learning method is thought to be a new approach to complement conventional logistic regression analysis in the classification of KOA patients. It can be clinically used for diagnosis and gait correction of KOA patients.

This paper proposes a novel image classification method based on few-shot learning, which is mainly used to solve model overfitting and non-convergence in image classification tasks of small datasets and improve the accuracy of classification. This method uses model structure optimization to extend the basic convolutional neural network (CNN) model and extracts more image features by adding convolutional layers, thereby improving the classification accuracy. We incorporated certain measures to improve the performance of the model. First, we used general methods such as setting a lower learning rate and shuffling to promote the rapid convergence of the model. Second, we used the data expansion technology to preprocess small datasets to increase the number of training data sets and suppress over-fitting. We applied the model to 10 monkey species and achieved outstanding performances. Experiments indicated that our proposed method achieved an accuracy of 87.92%, which is 26.1% higher than that of the traditional CNN method and 1.1% higher than that of the deep convolutional neural network ResNet50.

5G-based MANET has received a lot of attention recently. Its fundamental feature is that nodes are constantly subjected to high traffic loads, while QoS requirements are extremely stringent. When applied to 5G-based MANETs, existing routing protocols have shown drawbacks. In this paper, we propose an enhanced AODV protocol solution for 5G-based MANETs. Using reinforcement learning, each node updates a state information database of intermediate nodes along routes to destinations. This database is used by the routing algorithm to find guaranteed QoS routes. Our solution is highly efficient in terms of throughput, end-to-end delay, and SNR, according to the simulation results.

Sign-in point of interest (POI) are extremely sparse in location-based social networks, hindering recommendation systems from capturing users' deep-level preferences. To solve this problem, we propose a content-aware POI recommendation algorithm based on a convolutional neural network. First, using convolutional neural networks to process comment text information, we model location POI and user latent factors. Subsequently, the objective function is constructed by fusing users' geographical information and obtaining the emotional category information. In addition, the objective function comprises matrix decomposition and maximisation of the probability objective function. Finally, we solve the objective function efficiently. The prediction rate and F1 value on the Instagram-NewYork dataset are 78.32% and 76.37%, respectively, and those on the Instagram-Chicago dataset are 85.16% and 83.29%, respectively. Comparative experiments show that the proposed method can obtain a higher precision rate than several other newer recommended methods.

Purpose: This study aimed to investigate the factors affecting nursing students' learning flow in COVID- 19 pandemic situations through mixed-method research. Method: Of the 245 nursing students participating in the survey, 20 participated in a focus group interview. Quantitative data were analyzed using stepwise multiple regression analysis. Qualitative data were analyzed using content analysis. Results: The factors affecting the learning flow of nursing students during the COVID-19 pandemic were their self-regulated learning ability (b ¼ .24, p ¼ .001); learning motivation (b ¼ .23, p ¼ .001); selfefficacy in clinical practice (b ¼ .14, p ¼ .014); and lecture type, or a mixture of recorded and realtime video lectures (b ¼ .13, p ¼ .022). As a result of the qualitative study, eight categories and 22 subcategories were derived. The eight categories are: a lack of preparation in the starting of virtual classes, adapting and growing in a new learning environment, enhancing nursing knowledge and skills through virtual clinical training, self-regulation difficulties when studying alone due to social distancing, difficulty concentrating when learning online, disadvantages of virtual learning, concerns about academic performance, and missing opportunities to enjoy college life. Conclusion: Students attempted to discover their own learning expertise through virtual learning while concerned that they would be unable to fully establish their competence to work as actual hospital nurses due to a lack of clinical practice. In such a learning environment, systematic support and strategies are needed to increase the learning flow of nursing students.

Knowledge creation and management are regarded as critical success factors for an organization's survival in the knowledge era. As a process of knowledge acquisition and sharing, organizational learning mechanisms (OLMs) guide the learning function of organizations represented by its different learning activities. We examined a variety of learning processes that constitute OLMs. In this study, we aimed to capture the process and framework of OLMs and knowledge sharing and acquisition. Factors facilitating OLMs were investigated at three levels: individual, group, and organizational. The concept of an OLM has received some attention in the field of organizational learning, however, the relationship among the factors generating OLMs has not been empirically tested. As part of the ongoing discussion, we attempted a systemic approach for OLMs. OLMs can be represented by factors that are inherent to the organization's system; therefore, prior to empirically testing the OLM generating factor(s), evaluation of its organizational integration is required to determine effective treatment of each factor. Thus, we developed a framework to manage knowledge and proposed a method to numerically evaluate factors influencing the OLMs. Specifically, composite importance (CI) of the Decision-Making Trial and Evaluation Laboratory (DEMATEL) method was applied to explore the interaction effect of these factors based on systemic approach. The augmented matrix thus generated is expected to serve as a stochastic matrix of an absorbing Markov chain.

EEG signals have been widely used in emotion recognition in recent years. However, a great challenge still exists for the practical applications of cross-subject emotion recognition. Inspired by recent neuroscience studies and the advantage of the DE feature applied in EEG emotion recognition, we proposed a combined DE feature and contrastive learning method to tackle the cross-subject emotion recognition problem. The proposed model can minimize the inter-subject differences by maximizing the similarity in EEG signal representations across subjects when they receive the same emotional stimuli in contrast to different ones and gain a better encoding. Finally, we conducted extensive experiments on SEED and SEED-IV. The cross-subject emotion recognition accuracy is 84.72 on the SEED and 69.24 on the SEED-IV. It experimentally verified the effectiveness of the model.

다른 장르의 게임에 비해 포커는 게이머의 심리적 요소가 많은 영향을 끼친다. 본 논문에서는 CNN과 SVM을 기반으로 온라인 포커 게임에 게이머와 아바타 간의 감성연결을 실현하기 위한 새로운 감성 인식방법을 제안한다. CNN모델을 이용하여 원래 얼굴 이미지의 특징을 추출하고, 다중 클래스 SVM분류기를 사용하여 목표 이미지를 인식하고 분류한다. FER-2013데이터베이스에서 이 방법은 감성인식률 68.79 %를 달성하였다. 기존의 다른 감성 인 식 모델과 비교하면, 이 모델은 뚜렷한 장점을 보일 수 있다. 본 게임은 Socket 통신방식을 통해 감성인식결과를 Seven Poker로 전송하여 아바타가 게이머와 같은 감성을 표현하도록 설계하였다. 온라인 포커 게임에 감성연결 기술을 이용하면 게임과 인간의 상호작용이 향상될 뿐 아니라 게 이머가 상대방의 심리적인 활동을 효과적으로 분석할 수 있다. 감성연결 기술은 게임에서 게이머 들에게 새로운 게임 경험을 제공할 수 있는 기술이라고 생각된다.

Compared to other types of games, poker game is a psychological game based on gamer's psychological activity. This paper proposes a method based on convolutional neural network (CNN) and support vector machine (SVM) to realize the emotion recognition to link the gamer and his avatar in online poker game. The CNN model is used to extract feature of the original face images, and the multi-class SVM classifier is used to classify the emotions. On the FER-2013 database, the proposed method achieves 68.79% emotion recognition rate, and has obvious advantages compared with most other emotion recognition methods. Next, through the socket communication, the result of the emotion recognition is transferred to the designed seven poker game to realize the emotion linkage between the gamer and his avatar. More importantly, the emotion linkage technology not only helps the gamer to analyze the opponent’s psychological state, but also enhances the interaction of the game. It is undoubtedly a new breakthrough in game play that will give gamers a whole new gaming experience.