• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.6
• /
• pp.319-325
• /
• 2023

In this study, we proposed a method for hyperparameter optimization in the building and training of a deep learning model designed to process point cloud data collected by a millimeter-wave radar system. The primary aim of this study is to facilitate the deployment of a baseline model in resource-constrained IoT devices. We evaluated a RadHAR baseline deep learning model trained on a public dataset composed of point clouds representing five distinct human activities. Additionally, we introduced a coarse-to-fine hyperparameter optimization procedure, showing substantial potential to enhance model efficiency without compromising predictive performance. Experimental results show the feasibility of significantly reducing model size without adversely impacting performance. Specifically, the optimized model demonstrated a 3.3% improvement in classification accuracy despite a 16.8% reduction in number of parameters compared th the baseline model. In conclusion, this research offers valuable insights for the development of deep learning models for resource-constrained IoT devices, underscoring the potential of hyperparameter optimization and model size reduction strategies. This work contributes to enhancing the practicality and usability of deep learning models in real-world environments, where high levels of accuracy and efficiency in data processing and classification tasks are required.

• School Mathematics
• /
• v.15 no.2
• /
• pp.337-352
• /
• 2013

The purpose of this study is to evaluate the efficacy of teaching methods among elementary school math teachers in terms of student achievement in examinations. Results are based upon data from two elementary schools. The evaluation criteria of fifteen items was modified from Ryang's original MTEBI sixteen items to measure elementary school teachers' math teaching efficacy. The result of this study could be summarized as follows. The students were divided into two groups according to teaching efficiency: higher teaching efficiency and lower teaching efficiency. A comparison of math tests taken by students from these groups demonstrates a significant statistical difference. Students with teachers in the lower efficiency group are likely to under-perform. In consequence, teachers' self-efficiency in math is considered to affect students' learning achievement in mathematics.

• The Journal of Information Systems
• /
• v.29 no.3
• /
• pp.145-157
• /
• 2020

Purpose This study proposed an approach for predicting the efficiency rating of the cultural tourism festivals using DEA and machine learning techniques. The cultural tourism festivals are selected for the best festivals through peer reviews by tourism experts. However, only 10% of the festivals which are held in a year could be evaluated in the view of effectiveness without considering the efficiency of festivals. Design/methodology/approach Efficiency scores were derived from the results of DEA for the prediction of efficiency ratings. This study utilized BCC models to reflect the size effect of festivals and classified the festivals into four ratings according the efficiency scores. Multi-classification method were considered to build the prediction of four ratings for the festivals in this study. We utilized neural networks and SVMs with OAO(one-against-one), OAR(one-against-rest), C&S(crammer & singer) with Korea festival data from 2013 to 2018. Findings The number of total visitors in low efficient rating of DEA is more larger than the number of total visitors in high efficient ratings although the total expenditure of visitors is the highest in the most efficient rating when we analyzed the results of DEA for the characteristics of four ratings. SVM with OAO model showed the most superior performance in accuracy as SVM with OAR model was not trained well because of the imbalanced distribution between efficient rating and the other ratings. Our approach could predict the efficiency of festivals which were not included in the review process of culture tourism festivals without rebuilding DEA models each time. This enables us to manage the festivals efficiently with the proposed machine learning models.

• Cross-Cultural Studies
• /
• v.44
• /
• pp.283-314
• /
• 2016

The purpose of this study is to explore the diversity of French learning materials and suggest a learning method to increase the efficiency of learning. In the first part, we explore the linguistic characteristics of the proverb. In the second part, we present the examples that can be utilized in actual learning. In terms of teaching methods, sharing a common cultural consciousness is important for language and communication between interlocutors. In view of this point, the proverb has an extremely important value in the linguistic dimension. It means that the proverb can serve as a very useful material for the comparison of the morphology and phonetics of French. The efficiency of learning can be increased if we can apply an adequate learning plan using proverbs in accordance to the learner's level and the learning contents.

• Journal of Digital Convergence
• /
• v.7 no.3
• /
• pp.49-60
• /
• 2009

The aim of this study was to develop a model for teaching-teaming by applying Ubiquitous at a learning experience field, in which connect characteristics of both ubiquitous application learning and experience teaming, making use of them. A literature survey of concepts was conducted, with the main areas to find out relationships between ubiquitous application learning and experience learning. Experience learning by applying ubiquitous learning methods maximizes its efficiency of experience learning in considering ubiquitous learning methods's characteristics of dynamic, interaction, sharing. Also it makes communications through positive participation and active interaction, and leads to a process of internal examination. The research data suggests that critical factors of experiencing learning applying ubiquitous are acquiring information and memory, information integration and exquisiteness, emotional and social activity, producing activity, help activity.

• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 2004.06a
• /
• pp.41-46
• /
• 2004

e-learning을 통한 교육은 이제 대학 내뿐 만 아니라 중ㆍ고등학교나 기업체 등에서도 이루어지고 있는 것이 현실이다. 사교육비의 과대지출로 중ㆍ고등학교에서의 e-learning을 통한 교육은 이제 교육사업에 커다란 부분을 차지해 갈 것이 분명한 사실이다. 기업체 또한 기업 내 인력양성을 위한 모든 교육을 시간과 장소의 구애를 받지 않는 e-learning을 통한 교육으로의 전환이 이미 많이 이루어졌고 앞으로 더욱 많아지리라 생각된다. 하지만, 사교육이나 기업 내 추가적인 인력양성 교육에서의 e-learning의 도입을 통한 교육의 성과보다는 대학 내 e-learning을 통한 교육이 일반 대학생들이 오프라인 수업의 보조학습이 아닌 대체학습으로서 과연 대학 내 대표적인 e-learning 수업진행을 맡고 있는 OCU를 기본모델로 현재 e-learning을 통한 OCU수업을 듣고 있는 학생들을 대상으로 본 학습에 얼마나 많은 이해를 가지고 있는지를 알아보고자 한다. 또한 오프라인에서의 수업과 e-learning을 통한 수업의 이해도와 만족도에 얼마나 차이가 있는지 실증분석 해 보려 한다. 이 결과로 앞으로 대학 내 e-learning을 통한 학습에 문제점이 있다면 분석하여 오프라인의 보조학습이 아닌 대체학습으로 나아가는데 지식전달의 효율성 측면에서 나아갈 방안에 대해서 연구해 보려 한다.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.3
• /
• pp.753-761
• /
• 2023

This study investigates strategies to increase learning efficiency for programming subjects to which flipped learning teaching method is applied targeting non-major students. Design a learner-centered flipped learning-based programming class and get strategies for effective application methods for field application. Also, the purpose is to explore the efficient application of the flipped learning teaching method to the computational thinking subject of liberal arts classes at this university. By applying the flipped learning teaching method, one of the innovative teaching methods, we consider ways to improve the quality of programming subject classes, the efficiency of practical education, and the improvement of learner achievement. The purpose of this study is to design an efficient learning model for software education targeting non-majors by applying various teaching methods and learning design models convergence away from the traditional teaching method.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.9
• /
• pp.169-177
• /
• 2024

Industrial Wireless Sensor Network (IWSN) is a key feature of Industrial IoT that enables industrial automation through process monitoring and control by connecting industrial equipment such as sensors, robots, and machines wirelessly, and must support the strict requirements of modern industrial environments such as real-time, reliability, and energy efficiency. To achieve these goals, IWSN uses reliable communication methods such as multipath routing, fixed redundant resource allocation, and non-contention-based scheduling. However, the issue of wasting redundant resources that are not utilized for communication degrades not only the efficiency of limited radio resources but also the energy efficiency. In this paper, we propose a scheme that utilizes reinforcement learning in communication scheduling to periodically identify unused wireless resources and reallocate them to save energy consumption of the entire industrial network. The experimental performance evaluation shows that the proposed approach achieves about 30% improvement of resource efficiency in scheduling compared to the existing method while supporting high reliability. In addition, the energy efficiency and latency are improbed by more than 21% and 38%, respectively, by reducing unnecessary communication.

• The KIPS Transactions:PartA
• /
• v.13A no.6 s.103
• /
• pp.555-560
• /
• 2006

In contrast with the earlier remote education that simply recorded off-line classes, modern remote education emphasizes on offering additional functions that could maximize learning efficiency. Usage of such multimedia information as the texts, graphics, sounds, animations is considered fundamental element in offering the additional functions. This paper designs and implements an encoder/decoder that could accommodate the multimedia information with emphasis on demonstrating execution files. Instructors can demonstrate my type of execution files or application data files, and the remote learners can freely try running the corresponding execution files by themselves. Consequently, a high-level of learning efficiency can be achieved by the proposed encoder/decoder.

• Korean Journal of Construction Engineering and Management
• /
• v.24 no.5
• /
• pp.73-82
• /
• 2023

Optimization of Construction Site Layout Planning (CSLP) heavily relies on workers' travel paths. However, traditional path generation approaches predominantly focus on the shortest path, often neglecting critical variables such as individual wayfinding tendencies, the spatial arrangement of site objects, and potential hazards. These oversights can lead to compromised path simulations, resulting in less reliable site layout plans. While Deep Reinforcement Learning (DRL) has been proposed as a potential alternative to address these issues, it has shown limitations. Despite presenting more realistic travel paths by considering these variables, DRL often struggles with efficiency in complex environments, leading to extended learning times and potential failures. To overcome these challenges, this study introduces a refined model that enhances spatial navigation capabilities and learning performance by integrating workers' visibility into the reward functions. The proposed model demonstrated a 12.47% increase in the pathfinding success rate and notable improvements in the other two performance measures compared to the existing DRL framework. The adoption of this model could greatly enhance the reliability of the results, ultimately improving site operational efficiency and safety management such as by reducing site congestion and accidents. Future research could expand this study by simulating travel paths in dynamic, multi-agent environments that represent different stages of construction.