Improve Learning Efficiency Research Articles

A Personalized Learning Service Compatible with Moodle E-Learning Management System

Among the numerous learning management platforms, Moodle is free, open-source software supporting expanding and modularized system functions and services to facilitate online courses or online resources and interactive activities. This study enhanced a personalized learning service for the Moodle e-learning management system, which synchronizes the user’s identity according to the user information database of the third-party user management platform system. According to the user’s demand to provide a personalized e-course, including personalized learning process, e-materials, and learning path to improve learning efficiency. This study adopted the pre-test and post-test achievement to compare the benefit of the personalized e-learning platform. Research samples were students in the “programming” course at the Technology University in central Taiwan. The experiment results indicate: (i) The average post-test result after using the proposed platform was higher than the average pre-test result (before using the proposed platform). (ii) The learning effect gap in the post-test between students was less than in the pre-test result. Hence, the proposed personalized e-learning platform was beneficial.

Teaching and Curriculum of the Preschool Physical Education Major Direction in Colleges and Universities under Virtual Reality Technology.

The present work aims to study the influence of virtual reality (VR) technology on the teaching and curriculum of preschool physical education in colleges and universities and establish a virtual teaching model suitable for the college teaching system. The classroom teaching situation of using VR technology in physical training of preschool education major direction in colleges and universities is investigated using the questionnaire survey and teaching experiment. Firstly, the feasibility of applying VR technology to teaching is proved by analyzing the relevant education theories. Secondly, the experimental research method is designed to verify the application effect of VR technology in teaching behavior. Finally, the collected data is sorted out to judge the method's feasibility. The experimental results demonstrate that 88.0% of the respondents are curious about the application of VR, and 88.6% of the respondents can accept the application of VR in sports dance teaching. Besides, 89.1% claimed that VR technology could enhance students' understanding of knowledge, and 93.0% thought that VR applications would not interfere with teachers' explanations. In addition, 80.0% thought that virtual teaching could stimulate students' interest in learning, 75.0% said that VR application could attract students' attention, and 63.0% believed that VR application could improve learning efficiency. The preliminary investigation suggests that introducing VR technology can reduce the work intensity of teachers, and the students participating in the survey are optimistic about the application of VR technology in preschool physical education. The formal test based on a t-test indicates that the average score of the experimental group is 3.18 points higher than that of the control group, and there are significant differences in technology between the control group and the experimental group. VR technology can improve students' technical level, enhance self-confidence, and improve students' grades. To sum up, this study provides a reference for developing virtual teaching mode and applying VR technology to physical education.

When Optimization Meets Machine Learning: The Case of IRS-Assisted Wireless Networks

Performance optimization of wireless networks is typically complicated because of high computational complexity and dynamic channel conditions. Considering a specific case, the recent introduction of intelligent reflecting surface (IRS) can reshape the wireless channels by controlling the scattering elements' phase shifts, namely, passive beamforming. However, due to the large size of scattering elements, the IRS's beamforming optimization becomes intractable. In this article, we focus on machine learning (ML) approaches for complex optimization problems in wireless networks. ML approaches can provide flexibility and robustness against uncertain and dynamic systems. However, practical challenges still remain due to slow convergence in offline training or online learning. This motivated us to design a novel optimization-driven ML framework that exploits the efficiency of model-based optimization and the robustness of model-free ML approaches. Splitting the control variables into two parts allows one part to be updated by the outer loop ML approach while the other part is solved by the inner loop optimization. The case study in IRS-assisted wireless networks confirms that the optimization-driven ML framework can improve learning efficiency and the reward performance significantly compared to conventional model-free ML approaches.

A generic neural network model to estimate populational neural activity for robust neural decoding

BackgroundRobust and continuous neural decoding is crucial for reliable and intuitive neural-machine interactions. This study developed a novel generic neural network model that can continuously predict finger forces based on decoded populational motoneuron firing activities. MethodWe implemented convolutional neural networks (CNNs) to learn the mapping from high-density electromyogram (HD-EMG) signals of forearm muscles to populational motoneuron firing frequency. We first extracted the spatiotemporal features of EMG energy and frequency maps to improve learning efficiency, given that EMG signals are intrinsically stochastic. We then established a generic neural network model by training on the populational neuron firing activities of multiple participants. Using a regression model, we continuously predicted individual finger forces in real-time. We compared the force prediction performance with two state-of-the-art approaches: a neuron-decomposition method and a classic EMG-amplitude method. ResultsOur results showed that the generic CNN model outperformed the subject-specific neuron-decomposition method and the EMG-amplitude method, as demonstrated by a higher correlation coefficient between the measured and predicted forces, and a lower force prediction error. In addition, the CNN model revealed more stable force prediction performance over time. ConclusionsOverall, our approach provides a generic and efficient continuous neural decoding approach for real-time and robust human-robot interactions.

The Influence of Different Learning Strategies on Pupils' Learning Motivation: Is Augmented Reality Multimedia Learning Consistent With Traditional Text Learning?

How to reduce pupils’ burden and improve learning efficiency? Research shows that non-intelligence factors and learning strategies are the key factors in the effective learning process, and external intervention can play a greater role in these two aspects. The purpose of this study is to explore the effects of different learning strategies on learning motivation under the presentation of augmented reality (AR) multimedia or traditional text learning. Sixty third-grade pupils in Hebei Province were selected, and 2 (learning materials: AR materials and text materials) × 3 (learning strategies: restudying strategies, retrieval practicing strategies, and self-generated drawing strategies) between-subjects design was adopted. The dependent variable is learning motivation, which includes three dimensions: surface motivation, deep motivation and achievement motivation. The results showed that (1) Learning strategies had a significant impact on deep motivation. The deep motivation aroused by retrieval practicing strategies was significantly higher than that aroused by restudying strategies and self-generated drawing strategies. (2) The interaction between learning materials and learning strategies was marginally significant. When learning with AR materials, the achievement motivation of pupils in the restudying strategy group was higher (marginal significant) than that in the retrieval practicing strategy group. Retrieval practicing strategies have positive significance in cultivating deep motivation. The combination of different learning modes and learning strategies will impact achievement motivation.

Проблемный метод обучения в формировании профессиональной компетентности будущих бакалавров техносферной безопасности

Technosphere safety is a complex issue that depends directly on the level of professional competence of the people involved. The present research featured the problem-based method of teaching technogenic safety to Bachelor's Degree students. It involved a detailed analysis of the professionally-oriented training of technosphere safety bachelors. The analysis revealed some reasons behind the low efficiency of the current approach. The problem method is a promising resource for improving learning efficiency. The article introduces the content and application conditions of the problem method. The new approach was tested as part of lectures on Reliability of Technical Systems and Technogenic Risk. The problem method proved effective and improved the motivation of the future bachelors of technosphere safety.

Ingame Worked Examples Support as an Alternative to Textual Instructions in Serious Games About Programming

Serious games are considered an effective method to engage students in programming education and have been increasingly used in classrooms. An important part of the learning process with serious games involves the presentation of the new concepts and the provided support to encounter student difficulties. Although the most common approach is the use of instructional text, it comes with some drawbacks. This paper proposes an alternative method for user support in serious games about programming which mitigates current problems and provides improved learning efficiency. An experiment was conducted ( N = 291) to test textual instructions learning efficiency compared to in-game worked examples. Two randomly assigned groups used different types of support in a block-based game, developed for the study. Our implementation provided support through a non-player character who executed worked examples inside the game world. The analysis showed a significant statistical difference in score performance between the two supports on both novice and experienced students. The results point to increased learning efficiency by students, when in-game worked examples and problem-solving are combined. We further argue that the Cognitive load theory can provide adequate justification for the outcomes.

Integrating Hawgent Dynamic Mathematics Software into Cone Volume Geometry Learning in Elementary School

The aim of this research is to integrate Hawgent dynamic mathematics software into geometry learning to help teachers explain concepts and students understand the basic concept of volume of cone in 6th grade of elementary school. The research was conducted at Ningcheng Third Experimental Primary School with the population being all 6th grade students of the 2021/2022 school year. Sampling with a cluster random sampling technique and selected 40 students of 6th grade as the sampling class. In this teaching experiment research, the researcher was using a BOPPPS model based on the APOS theory. The research results showed that 79.49% of the students agree that the integrating Hawgent dynamic mathematics software into cone volume geometry learning process can help them understand the concept of cone volume. Integrating Hawgent dynamic mathematics software improves their interest in learning, the basis of in-depth understanding of knowledge, and the accuracy of the problem. In addition, information, communication and technology is highly integrated with classroom teaching, which can enrich classroom content and improve learning efficiency.

Students Sense of Belonging and Academic Performance via Online PBL: A Case Study of a University in Hong Kong during Quarantine.

Innovative educational adaptations have been essential during the COVID-19 pandemic. Against the backdrop of school closures in Hong Kong resulting from unrest and COVID-19, this study proposed using problem-based learning (PBL) in online courses and empirically examined the influence of the PBL learning methodology on online learners’ sense of classroom belonging and academic performance. A total of 44 sophomores pursuing electrical and electronic engineering majors and taking “Practical Chinese for engineering students” as a compulsory course at the University of Hong Kong participated in the study. They were divided evenly between the experimental group C1 and the control group C2 (22 in each). We implemented online PBL learning for the experimental group, C1, and traditional online learning for the control group, C2. Quantitative data were collected via an achievement test and a scale on sense of classroom community. Qualitative data were obtained through a semi-structured focus group discussion. The quantitative results showed that the students who received the PBL learning method scored higher on tests, experienced a stronger sense of classroom belonging, and had closer connections with each other. A content analysis of student interviews revealed that implementation of the PBL learning method in online teaching could strengthen students’ classroom interactions and that the enhancement of their mutual connections could stimulate learning and improve learning efficiency. Overall, this study finds that the PBL learning method is effective in promoting students’ deep active learning and sense of community in the online environment.

Application of Six Sigma Management-based Teaching Method in Financial Management Course Online Teaching

Driven by huge demand for talents in the market, economics major in colleges and universities need to take the initiative to reform the teaching of finance specialty in accordance with the demand for finance talents in the era of big data, cultivate versatile innovative competent talents, and output high-quality talents for social enterprises, satisfy enterprises’ needs of recruiting financial talents, and give full play to the social education value of university finance specialty. Financial management is the core of economic organization, and the management effectiveness affects the overall operational feasibility of the organization. In order to promote the high-quality development of the market economy, universities should devote greater effort to the teaching reform of financial management, enhance talent cultivation conversion efficiency, and give full play to the value of the financial specialty in colleges and universities. However, the existing course teaching can hardly achieve the expected goals due to insufficient monitoring of financial management teaching process, insufficient self-learning resources, and defective student learning support service, imperfect teacher's training, single assessment method, and small proportion of practical teaching, etc. In view of the current status, this paper innovatively introduced six sigma management theory to improve the online teaching of financial management courses. Firstly, the teaching process involving five stages of define-measure-analyze-improve-control was designed according to the course characteristics of financial management and at the same time, the financial management teaching model was improved by online and offline inquiry-based teaching method. In order to improve the application effectiveness of financial management online teaching resources, a precise teaching resource push system was established using Web data mining so as to achieve the goal of recommending different teaching resources to different students. It was proved by the teaching practice that the new teaching method proposed in this study can help students improve learning efficiency and enhance their problem-solving ability. Thus, this teaching model is worthy of application and promotion in courses of finance specialty.

The Impact of Serious Game on the Nursing Students' Learning, Behavioral Engagement, and Motivation

Digital game-based learning is a ludic approach that has evolved through the development of information and communication technologies (ICT), making the learner an active participant in the virtual learning environment instead of a mere observer. It is an electronic simulation tool suitable for improving learning efficiency as well as learner engagement and motivation. The integration of this educational technology in the teaching and learning process can contribute to the construction of knowledge, the development of new skills and attitudes among students.
 The purpose of this study is to investigate the impact of serious game on the learning, behavioral engagement, and motivation of nursing students. To do this, we first conducted a study with a sample of 58 polyvalent nursing students divided into two groups; one experimental and the other as a control. Both groups benefited from the same content taught at a distance, however, the experimental group benefited from an online serious game after the course. By comparing the summative scores of the two groups using the Student's t-test, the results show that the serious game improved the students' clinical knowledge of pediatric nursing (t= -2.706,p=0.009). However, it did not have an effect on clinical skills (t= -0.373, p=0.711). As a second step, we have studied the impact of the game on the learners' behavioral engagement based on the analysis of the digital traces of the students' work. Meanwhile, the motivation is analyzed using a questionnaire developed from the ARCS scale of Killer (2010), which is distributed to the experimental group. By comparing the means and deviation standards, the results show that the students give the satisfaction factor the highest score (4.71±0.34) followed by the relevance, attention, and confidence factors.
 To obtain reliable results, however, it is necessary to repeat the serious game experience in several nursing modules. In addition, the impact of combining serious game with simulation on the learning of nursing students should be studied.

A Deep Reinforcement Learning Strategy Combining Expert Experience Guidance for a Fruit-Picking Manipulator

When using deep reinforcement learning algorithms for path planning of a multi-DOF fruit-picking manipulator in unstructured environments, it is much too difficult for the multi-DOF manipulator to obtain high-value samples at the beginning of training, resulting in low learning and convergence efficiency. Aiming to reduce the inefficient exploration in unstructured environments, a reinforcement learning strategy combining expert experience guidance was first proposed in this paper. The ratios of expert experience to newly generated samples and the frequency of return visits to expert experience were studied by the simulation experiments. Some conclusions were that the ratio of expert experience, which declined from 0.45 to 0.35, was more effective in improving learning efficiency of the model than the constant ratio. Compared to an expert experience ratio of 0.35, the success rate increased by 1.26%, and compared to an expert experience ratio of 0.45, the success rate increased by 20.37%. The highest success rate was achieved when the frequency of return visits was 15 in 50 episodes, an improvement of 31.77%. The results showed that the proposed method can effectively improve the model performance and enhance the learning efficiency at the beginning of training in unstructured environments. This training method has implications for the training process of reinforcement learning in other domains.

Application and Analysis of Education and Teaching Mode Based on 5G and Smart Technology

The development of information technology has brought tremendous changes to our country’s education. Based on the 5G + Internet, the article proposes a brand-new intelligent education model and proposes an ST analysis method, which mainly studies the teacher and students in the classroom. Class performance, based on Yebes network, proposed a learning decision method and application. The research results of the article show the following: (1) The article compares the monthly test scores of three variables under two different teaching modes. The results show that the performance of the online teaching mode is generally better than that of the traditional teaching mode, and the performance of the experimental class has increased more, with an average growth score of 4.83, indicating that there are significant differences in students’ learning and cognitive abilities under different teaching models. (2) The article compares the students’ knowledge mastery under two different teaching modes. The results show that under the traditional teaching mode, the students’ knowledge mastery is low, and the complete mastery rate is only 15%. In the network multimedia teaching mode, the students’ knowledge mastery rate has been greatly improved, the complete mastery rate is as high as 45%, and the students’ mastery of knowledge has been extremely improved, indicating that the network multimedia teaching mode can stimulate students’ learning interest more, improve learning efficiency. (3) Studying the differences in the source of curriculum resources of three different types of teachers, and the results show that the proportion of curriculum resources downloaded through the Internet is the largest; in the investigation of the impact of multimedia teaching on the classroom, the cooperation rate of students when multimedia teaching is not used, classroom practice accuracy and classroom completion rate are low, but after using multimedia teaching, students’ cooperation rate and classroom practice accuracy rate have been greatly improved, among which the accuracy rate of the experimental class is as high as 62.4%, and the students’ thinking ability is also good. Great improvement.

Methodology for Interactive Labeling of Patched Asphalt Pavement Images Based on U-Net Convolutional Neural Network

Image recognition based on deep learning generally demands a huge sample size for training, for which the image labeling becomes inevitably laborious and time-consuming. In the case of evaluating the pavement quality condition, many pavement distress patching images would need manual screening and labeling, meanwhile the subjectivity of the labeling personnel would greatly affect the accuracy of image labeling. In this study, in order for an accurate and efficient recognition of the pavement patching images, an interactive labeling method is proposed based on the U-Net convolutional neural network, using active learning combined with reverse and correction labeling. According to the calculation results in this paper, the sample size required by the interactive labeling is about half of the traditional labeling method for the same recognition precision. Meanwhile, the accuracy of interactive labeling method based on the mean intersection over union (mean_IOU) index is 6% higher than that of the traditional method using the same sample size and training epochs. In addition, the accuracy analysis of the noise and boundary of the prediction results shows that this method eliminates 92% of the noise in the predictions (the proportion of noise is reduced from 13.85% to 1.06%), and the image definition is improved by 14.1% in terms of the boundary gray area ratio. The interactive labeling is considered as a significantly valuable approach, as it reduces the sample size in each epoch of active learning, greatly alleviates the demand for manpower, and improves learning efficiency and accuracy.

Application of Virtual Reality Technology in Film and Television Animation Based on Artificial Intelligence Background

The application of artificial intelligence technology in the film and television field has profoundly changed the content and production methods of television programs and promoted the development and production of a new generation of artificial intelligence television. The popularization of artificial intelligence technology is conducive to improving the quality of television program content, innovating content categories, reducing television program production cost, and improving production efficiency. Due to the popularization and the use of virtual reality (VR) technology in scientific research and social life, the application of VR technology has been studied from the perspective of film and television animation (FTA) teaching, hoping to promote the development of FTA education. First, the existing dynamic environment modeling technology, real-time three-dimensional (3D) graphic generation technology, stereoscopic display, and sensor technology and other VR technologies are combined to carry out teaching design. In view of the current situation of the teaching process of FTA major, the research on these four aspects has been carried out. VR technology is used as an auxiliary teaching tool to complete the basic course teaching of FTA; the 3D animation course and VR technology are combined to improve the teaching effect of professional skill courses. Then, in the application effect, classroom satisfaction, comprehensive quality evaluation, and professional core curriculum effect are compared and analyzed. The results show that the students’ comprehensive quality evaluation in VR technology group is significantly improved, and the satisfaction of classroom atmosphere, teaching mode, and teaching facilities are 75%, 61%, and 81%, respectively. The students in this group can better integrate the new design method into the animation modeling and complete the course design task with high quality. Compared with the traditional teaching mode, the students’ satisfaction is higher and the harvest is greater. Therefore, the use of VR technology in FTA teaching can stimulate students’ interest in learning, improve learning efficiency, and promote the mastery of professional knowledge and skills. The application mode and effect analysis of the proposed VR technology provide a reference for the application of VR technology in FTA teaching.

Research on Teaching Resource Recommendation Algorithm Based on Deep Learning and Cognitive Diagnosis

With the increasing abundance of network teaching resources, the recommendation technology based on network is becoming more and more mature. There are differences in the effect of recommendation, which leads to great differences in the effect of recommendation algorithms for teaching resources. The existing teaching resource recommendation algorithm either takes insufficient consideration of the students' personality characteristics, cannot well distinguish the students' users through the students' personality, and pushes the same teaching resources or considers the student user personality not sufficient and cannot well meet the individualized learning needs of students. Therefore, in view of the above problem, combining TDINA model by the user for the students to build cognitive diagnosis model, we put forward a model based on convolution (CUPMF) joint probability matrix decomposition method of teaching resources to recommend the method combined with the history of the students answer, cognitive ability, knowledge to master the situation, and forgetting effect factors. At the same time, CNN is used to deeply excavate the test question resources in the teaching resources, and the nonlinear transformation of the test question resources output by CNN is carried out to integrate them into the joint probability matrix decomposition model to predict students' performance on the resources. Finally, the students' knowledge mastery matrix obtained by TDINA model is combined to recommend corresponding teaching resources to students, so as to improve learning efficiency and help students improve their performance.

SEARCH ON TEACHING MODE AND EVALUATION OF FOREIGN LANGUAGE WISDOM EDUCATION BASED ON BIG DATA

The development of modern information technology and the deepening integration of education and teaching provide excellent support for the upgrading and popularization of foreign language wisdom education platform. The foreign language wisdom education platform based on the theoretical framework of foreign language educational technology conforms to the law of foreign language teaching, and provides teachers with an intelligent teaching assistant system based on big data analysis, so as to truly realize autonomous learning and improve learning efficiency; To provide big data decision analysis for teaching administrators, so as to truly realize intelligent teaching management and comprehensively improve teaching quality. Under the background of big data, the concept of wisdom education has brought systematic changes to foreign language education. Data mining and learning analysis technology are adopted to construct personalized learning content and multiinteractive teaching evaluation mechanism, so as to improve students' learning efficiency and learning autonomy, thus realizing intelligent and personalized education.

Teaching Method for Entity–Relationship Models Based on Semantic Network Theory

Students in database courses often have difficulty learning entity–relationship (ER) modeling. According to semantic network theory, learning to construct an ER diagram for a database problem requires complex semantic transformations between the problem and the diagram. Such complex transformation may require excessive mental effort by learners, jeopardizing their learning outcomes. A concept map is a learning tool that incorporates elements of both learning theory and semantic network theory. In this study, concept maps were used to describe the semantic transformation process to increase learner understanding of ER modeling. An empirical experiment was conducted on two database courses (one concept-map-based and one conventional course) to examine the effect of using concept maps on understanding ER modeling according to cognitive load theory. The experimental results revealed that the concept-map-based teaching method was superior to the conventional teaching method because it improved mental efficiency by reducing extraneous load while increasing germane load. Moreover, concept maps can be used as a medium to facilitate communication regarding ER modeling problems between learners and instructors, thereby improving learning efficiency. The results can help educators and researchers understand the effectiveness of concept maps for ER model learning, motivate them to resolve learning difficulties, and encourage them to develop improved teaching methods by using semantic network theory.

RF-UAVNet: High-Performance Convolutional Network for RF-Based Drone Surveillance Systems

In recent years, the increasing popularity of unmanned aerial vehicles (UAVs) has arisen from the emergence of cutting-edge technologies deployed in small and low-cost devices. With the great capability of friendly uses and wide applications for multiple purposes, amateur drones can be piloted to effortlessly access any geographical area. This poses some difficulties in monitoring and managing drones that may invade private or limited-access areas. In this paper, we propose a radio-frequency (RF)-based surveillance solution to effectively detect and classify drones, and recognize operations by leveraging a high-performance convolutional neural network. The proposed network, namely RF-UAVNet, is specified with grouped one-dimensional convolution to significantly reduce the network size and computational cost. Besides, a novel structure of multi-level skip-connection, for the preservation of gradient flow, incorporating multi-level pooling, for the collection of informative deep features, is proposed to achieve high accuracy via learning efficiency improvement. In the experiments, RF-UAVNet yields the accuracy of 99.85% for drone detection, 98.53% for drone classification, and 95.33% for operation mode recognition, numbers which outperform the current state-of-the-art deep learning-based methods on DroneRF, a publicly available dataset for RF-based drone surveillance systems.

An Effective Way of Teaching Fundamentals of Robotics to Undergraduate Students using RoboAnalyzer

Abstract: Robots are becoming increasingly important as the world continues to evolve. Robots are needed to achieve higher production rates and competitiveness. Many universities have already started to offer robotics courses in response to the growing demand for automation. However, in a traditional classroom teaching method, students find it challenging to apply pure mathematical algorithms in robotics. The lack of visualization of robot modelling affects the students learning interest. It becomes imperative to introduce simulation software in teaching the fundamental concepts of robotics. This paper presents the application of the RoboAnalyzer tool to teach the robotics course at the undergraduate level. The methodology was adopted to complement the theoretical concepts of robotics. In the present study, we collected feedback from the students about the method. The results show that around 76 % strongly agreed that the RoboAnalyzer tool improved learning efficiency, and 74 % strongly agreed that the combination of conventional teaching and the simulation tool is better than the traditional teaching method. RoboAnalyzer was implemented during the academic year 2019 – 2020 and received a positive response. Keywords: learning, modelling, RoboAnalyzer, robotics, simulation, undergraduate,