• International Journal of Computer Science & Network Security
• /
• 제24권1호
• /
• pp.71-84
• /
• 2024

This paper presents a critical analysis of the current application of big data in higher education and how Learning Analytics (LA), and Educational Data Mining (EDM) are helping to shape learning in higher education institutions that have applied the concepts successfully. An extensive literature review of Learning Analytics, Educational Data Mining, Learning Management Systems, Informal Learning and Online Social Networks are presented to understand their usage and trends in higher education pedagogy taking advantage of 21st century educational technologies and platforms. The roles of and benefits of these technologies in teaching and learning are critically examined. Imperatively, this study provides vital information for education stakeholders on the significance of establishing a teaching and learning agenda that takes advantage of today's educational relevant technologies to promote teaching and learning while also acknowledging the difficulties of 21st-century learning. Aside from the roles and benefits of these technologies, the review highlights major challenges and research needs apparent in the use and application of these technologies. It appears that there is lack of research understanding in the challenges and utilization of data effectively for learning analytics, despite the massive educational data generated by high institutions. Also due to the growing importance of LA, there appears to be a serious lack of academic research that explore the application and impact of LA in high institution, especially in the context of informal online social network learning. In addition, high institution managers seem not to understand the emerging trends of LA which could be useful in the running of higher education. Though LA is viewed as a complex and expensive technology that will culturally change the future of high institution, the question that comes to mind is whether the use of LA in relation to informal learning in online social network is really what is expected? A study to analyze and evaluate the elements that influence high usage of OSN is also needed in the African context. It is high time African Universities paid attention to the application and use of these technologies to create a simplified learning approach occasioned by the use of these technologies.

• 한국멀티미디어학회논문지
• /
• 제23권3호
• /
• pp.447-459
• /
• 2020

The Internet of Things(IoT) paradigm is flourishing strenuously for the last two decades. Researchers around the globe have their dreams to transmute every real-world object to the virtual object. Consequently, IoT devices are escalating exponentially. The abrupt evolution of these IoT devices has caused a major challenge i.e. object classification. In order to classify devices comprehensively and accurately, this paper proposes a context-aware based multi-classification model for devices, which classifies the smart devices according to people's contexts. However, the classification features of contextual data of different contexts are difficult to extract. The deep learning algorithm has the capability to solve this problem. This paper proposes a context-aware based multi-classification model of devices, which classifies the smart devices according to people's contexts.

• 음성과학
• /
• 제10권1호
• /
• pp.71-84
• /
• 2003

In the acoustic modeling for large vocabulary speech recognition, a sparse data problem caused by a huge number of context-dependent (CD) models usually leads the estimated models to being unreliable. In this paper, we develop a new clustering method based on the C45 decision-tree learning algorithm that effectively encapsulates the CD modeling. The proposed scheme essentially constructs a supervised decision rule and applies over the pre-clustered triphones using the C45 algorithm, which is known to effectively search through the attributes of the training instances and extract the attribute that best separates the given examples. In particular, the data driven method is used as a clustering algorithm while its result is used as the learning target of the C45 algorithm. This scheme has been shown to be effective particularly over the database of low unknown-context ratio in terms of recognition performance. For speaker-independent, task-independent continuous speech recognition task, the proposed method reduced the percent accuracy WER by 3.93% compared to the existing rule-based methods.

• 한국멀티미디어학회논문지
• /
• 제20권8호
• /
• pp.1282-1290
• /
• 2017

Since the mitigation of fear of crime significantly enhances the consumptions in a city, studies focusing on urban safety analysis have received much attention as means of revitalizing the local economy. In addition, with the development of computer vision and machine learning technologies, efficient and automated analysis methods have been developed. Previous studies have used global features to predict the safety of cities, yet this method has limited ability in accurately predicting abstract information such as safety assessments. Therefore we used a Convolutional Context Neural Network (CCNN) that considered "context" as a decision criterion to accurately predict safety of cities. CCNN model is constructed by combining a stacked auto encoder with a fully connected network to find the context and use it in the CNN model to predict the score. We analyzed the RMSE and correlation of SVR, Alexnet, and Sharing models to compare with the performance of CCNN model. Our results indicate that our model has much better RMSE and Pearson/Spearman correlation coefficient.

• Educational Technology International
• /
• 제11권1호
• /
• pp.47-68
• /
• 2010

The purpose of this study was to analyze majors trends and issues of e-Learning curriculum for human resource development in the corporate context. The e-Learning curriculum was chosen as the subject of research consists of 2,710 lectures that were given from 2007 to July 2009 for the recent three years by providing at Ministry of Labor and Korea Research Institute for Vocational Education & Training. In order to investigate trends and issues, it was employed theme analysis which is one of the types of document analysis that approach a qualitative research methodology. As a result of this research, 7 major trends and issues in e-Learning curriculum for HRD in the field of corporate education were drawn; ① Strengthening expertise through learning of job related professional knowledge, ② Cultivation of common & essential knowledge for a job to increase work performance efficiency ③ Organizational management strategy for improving performance, ④ Organizational management and operational strategy for actively responding to environmental changes, ⑤ Leadership as a strategy for cultivating core personnel and field-centered practical leadership. ⑥ Creating a happy workplace through the work-life balance, ⑦ Strengthening global communication skill. Based on these analysis, practicals and theoretical implications of e-Learning professionals and HR researchers for HRD were suggested.

• 한국수학교육학회지시리즈E:수학교육논문집
• /
• 제34권3호
• /
• pp.393-419
• /
• 2020

삼각법은 수학의 유용성을 인식하도록 하며 삼각함수와의 연계를 통해 고등 수학 개념의 기반을 다진다. 본 연구는 호주와 핀란드를 비교 대상 국가로 정하여 Charalambous 외(2010)가 제시한 수평적 및 수직적 분석을 통해 교육과정과 교과서를 분석하였다. 세 국가가 삼각비에서 다루는 각을 확장한 학습 순서가 유사하며 삼각함수의 도입 시기 및 학습의 연속성에 차이가 있다. 삼각비의 정의 방법에 대한 학습경로는 공통적으로 삼각형 방법, 단위원 방법, 삼각함수 순서로 나타났는데 우리나라는 제 1사분면의 단위원에서 삼각비를 정의한 후 바로 일반각과 삼각함수가 전개된다는 차이점이 나타났다. 위장 맥락 문제와 인위적 맥락 문제는 우리나라가 호주나 핀란드에 비해 높은 비율을 보였다. 이를 통해 우리나라의 학습경로에서 생략되었던 단위원 방법을 제시하는 것, 실생활 맥락을 강조하는 문제를 제시하고 공학적 도구를 활용할 것, 삼각법을 다루는 교육과정 방식과 영역에 대해 재고할 것을 제안한다.

• 대한수학교육학회지:학교수학
• /
• 제4권1호
• /
• pp.79-95
• /
• 2002

This paper is to make strides toward an enriched understanding of student learning and performance in mathematics that acknowledges the roles social and cultural contexts play in what students learn as well as what we are able to team about student learning. A student's mathematical practice over a year and a half is presented in detail in order to explore the relationships between classroom contexts and student performance. This study was situated at a K-4 urban elementary school in the United States. The data used for this study included classroom observations, interviews with the teachers and the student, and document collection. The data were analyzed by characterizing each classroom context and exploring the student's practice both in the classrooms and in the interviews. Despite the student's ongoing status as a struggling student, there were tremendous changes in his level of engagement in and persistence with mathematical tasks. The student was substantially more engaged in and enthusiastic about the daily mathematics lessons in third grade than he had been in second. However, we found little improvement in his mathematical understanding and performance during class or in the interviews. This highlights that increased engagement in the mathematical tasks does not necessarily signal increased learning. This paper discusses several issues of learning and performance raised by the student, looking at the relationship between classroom context and student performance. This paper also considers implications for how students' performances are interpreted and how learning is assessed.

• Journal of Information Processing Systems
• /
• 제16권3호
• /
• pp.612-628
• /
• 2020

This paper presents a new approach for detecting abnormal behaviors in complex surveillance scenes where anomalies are subtle and difficult to distinguish due to the intricate correlations among multiple objects' behaviors. Specifically, a cascaded probabilistic topic model was put forward for learning the spatial context of local behavior and the temporal context of global behavior in two different stages. In the first stage of topic modeling, unlike the existing approaches using either optical flows or complete trajectories, spatio-temporal correlations between the trajectory fragments in video clips were modeled by the latent Dirichlet allocation (LDA) topic model based on Markov random fields to obtain the spatial context of local behavior in each video clip. The local behavior topic categories were then obtained by exploiting the spectral clustering algorithm. Based on the construction of a dictionary through the process of local behavior topic clustering, the second phase of the LDA topic model learns the correlations of global behaviors and temporal context. In particular, an abnormal behavior recognition method was developed based on the learned spatio-temporal context of behaviors. The specific identification method adopts a top-down strategy and consists of two stages: anomaly recognition of video clip and anomalous behavior recognition within each video clip. Evaluation was performed using the validity of spatio-temporal context learning for local behavior topics and abnormal behavior recognition. Furthermore, the performance of the proposed approach in abnormal behavior recognition improved effectively and significantly in complex surveillance scenes.

• 영어어문교육
• /
• 제10권1호
• /
• pp.23-52
• /
• 2004

This paper investigated students' and teachers' attitudes toward L2 grammar in EFL learning context. In a study in which attitude was viewed as consisting of three different components such as cognitive, affective, and behavioral, questionnaire developed on the basis of such a view of attitude was used as a data collection method. The results of the study indicated that in general, both students and teachers were similar to each other in their attitude toward L2 grammar. Among the findings, most important, two groups were shown to fully understand the important role of grammar in L2 learning. Another finding was that despite the 6th national curriculum for English education, our English class was still dominated by grammar-centered instruction. Also it was shown that the way teachers had been taught L2 grammar had a considerable effect on the way they would instruct it in their future classes. Based on these findings, some suggestions were offered for effective grammar pedagogy in EFL context.

• 한국IT서비스학회지
• /
• 제13권1호
• /
• pp.197-207
• /
• 2014

With the recent advance in smartphones, users are allowed to use mobile applications anytime anywhere, and change their way to interact with smart environment and people. As a result, the need for developing context-aware applications on smartphones has a great attention from users and developers. This paper proposes a context-aware framework for supporting UI/UX of smartphones. The proposed framework collects a wide range of sensory data from smartphones and allows developers to analyze and model context models for their desired apps. In addition, it also supports real-time inference within the apps to make them to adapt to context. In order to show effectiveness of the proposed framework, we introduce two smartphone apps: context-aware home screen and automatic detection of smartphone problem use. Therefore, we expect that the proposed framework will help developers easily implement their apps with respect to context-awareness.