Efficient Learning Research Articles

How does the use of modern technologies affect students’ perception of information? The effectiveness of holographic projection technology in music education

ABSTRACT The article studies the holographic projection technology in an innovative music classroom during full-time education. The study addresses the influence of this technology on the effectiveness and efficiency of learning, as well as on the perception and memorisation of educational material by students. It describes an innovative music classroom with equipment for using a 3D Hologram (3DH) for face-to-face lectures. An educational experiment was conducted within a three-month course. The experiment enrolled 111 foreign students in the first year of studying at higher educational institutions in China. The evaluation of the emotional background of the learning environment in the innovative music classroom indicates a positive attitude of students towards educational activities. The activities aroused their interest, admiration and trust; the environment was friendly and joyful. The findings can facilitate the search for innovative solutions to improve pedagogical activity or foster the introduction of holographic innovations into teaching practice.

Energy efficient deep reinforcement learning approach to control the traffic flow in iot networks for smart city

Energy efficient deep reinforcement learning approach to control the traffic flow in iot networks for smart city

Enhancing motor skill learning through multiple sessions of online high-definition transcranial direct current stimulation in healthy adults: insights from EEG power spectrum.

The purpose of this study was to evaluate the influence of high-definition transcranial direct current stimulation (HD-tDCS) on finger motor skill acquisition. Thirty-one healthy adult males were randomly assigned to one of three groups: online HD-tDCS (administered during motor skill learning), offline HD-tDCS (delivered before motor skill learning), and a sham group. Participants engaged in a visual isometric pinch task for three consecutive days. Overall motor skill learning and speed-accuracy tradeoff function were used to evaluate the efficacy of tDCS. Electroencephalography was recorded and power spectral density was calculated. Both online and offline HD-tDCS total motor skill acquisition was significantly higher than the sham group (P < 0.001 and P < 0.05, respectively). Motor skill acquisition in the online group was higher than offline (P = 0.132, Cohen's d =1.46). Speed-accuracy tradeoff function in the online group was higher than both offline and sham groups in the post-test. The online group exhibited significantly lower electroencephalography activity in the frontal, fronto-central, and centro-parietal alpha band regions compared to the sham (P < 0.05). The findings suggest that HD-tDCS application can boost finger motor skill acquisition, with online HD-tDCS displaying superior facilitation. Furthermore, online HD-tDCS reduces the power of alpha rhythms during motor skill execution, enhancing information processing and skill learning efficiency.

A path planning method based on deep reinforcement learning for AUV in complex marine environment

The potential of autonomous underwater vehicle (AUV) on future applications is significant due to advancements in autonomy and intelligence. Path planning is a critical technology for AUV to perform operational missions in complex marine environments. To this end, this paper proposes a path planning method for AUV based on deep reinforcement learning. Initially, considering actual requirements, a complex marine environment model containing underwater terrain, sonobuoy detection, and ocean currents is established. Subsequently, the corresponding state space, action space, and reward function are formulated. Furthermore, to address the inherent limitations of existing deep reinforcement learning algorithms in terms of training efficiency, a mixed experience replay (MER) strategy is proposed. This strategy aims to enhance the efficiency of sample learning by integrating prior knowledge and exploration experience. Lastly, a novel HMER-SAC algorithm for AUV path planning is proposed by integrating the Soft Actor–Critic (SAC) algorithm with the hierarchical reinforcement learning strategy and the MER strategy. The results of the simulation and experiment demonstrate that the method is capable of efficiently planning executable paths in complex marine environments and exhibits superior training efficiency, stability, and performance.

Implementasi Kegiatan Pembelajaran Bahasa Arab Pada Boarding School SMA Muhammadiyah 2 Sidoarjo

This research discusses the implementation of Arabic language learning using the boarding school system at SMA Muhammadiyah Sidoarjo, which discusses learning planning, namely an Arabic learning plan including activities to develop learning objectives and planning the flow of lessons for learning Arabic, implementation of learning, namely learning plans. that have been developed, as well as a continuous process of teaching and learning activities that focus on school activities to achieve educational goals, learning evaluation is one of the important stage activities that educators must carry out to determine the effectiveness and efficiency of learning. In the Arabic language learning planning at Muhammadiyah Sidoarjo High School, currently there is a learning curriculum, learning tools and an Arabic language competency skills upgrading program implemented for teachers and students. In the learning implementation there is formal and non-formal learning. Evening diniyah formal learning. Meanwhile, non-formal learning takes the form of giving mufrodat, muhadoroh, and language drama. In learning evaluation there are 3 assessment components, namely daily assessment, daily test assessment and final pre-school assessment which are test and non-test based.

Utilizing Big Data to Create Educational Information Systems

Background and Aims: Using big data to create educational information systems is critical for customizing learning experiences for individual students while also improving overall educational outcomes. Using data-driven insights, educators and administrators can make informed decisions to improve teaching strategies, predict student performance, and streamline operations, resulting in a more effective and personalized educational experience. The purpose of this paper is to investigate the use of Big Data to create Educational Information Systems. Methodology: The methodology calls for the use of a variety of data sources, including academic journals and case studies, as well as a structured literature review protocol to ensure comprehensive coverage. Data is collected and analyzed thematically to identify key trends, applications, and challenges in big data utilization in education, resulting in a comprehensive overview of its impact. Results: The study discovered that the review emphasizes big data's transformative potential in educational information systems, specifically its ability to improve personalized learning, predictive analytics, curriculum development, and administrative efficiency. Successful implementations, such as those at Georgia State University and Purdue University, highlight the significant benefits of using big data while emphasizing the importance of addressing ethical and privacy concerns. The future of big data in education promises even greater advances thanks to technologies like AI and real-time analytics, but it also necessitates ongoing research into ethical frameworks and their impact on educational equity. Balancing innovation with privacy and ethical concerns will be critical as educational institutions, administrators, and policymakers navigate these changes, allowing big data to reach its full potential while maintaining equitable and effective educational practices. Conclusion: The article emphasizes big data's potential to transform educational systems through personalized learning, predictive analytics, curriculum development, and administrative efficiency. Moving forward, it is critical to strike a balance between technological advancements and ethical and privacy concerns to ensure that big data innovations are used effectively and fairly in education.

The most efficient machine learning algorithms in stroke prediction: A systematic review.

Stroke is one of the most common causes of death worldwide, leading to numerous complications and significantly diminishing the quality of life for those affected. The purpose of this study is to systematically review published papers on stroke prediction using machine learning algorithms and introduce the most efficient machine learning algorithms and compare their performance. The papers have published in period from 2019 to August 2023. The authors conducted a systematic search in PubMed, Scopus, Web of Science, and IEEE using the keywords "Artificial Intelligence," "Predictive Modeling," "Machine Learning," "Stroke," and "Cerebrovascular Accident" from 2019 to August 2023. Twenty articles were included based on the inclusion criteria. The Random Forest (RF) algorithm was introduced as the best and most efficient stroke ML algorithm in 25% of the articles (n = 5). In addition, in other articles, Support Vector Machines (SVM), Stacking and XGBOOST, DSGD, COX& GBT, ANN, NB, and RXLM algorithms were introduced as the best and most efficient ML algorithms in stroke prediction. This research has shown a rapid increase in using ML algorithms to predict stroke, with significant improvements in model accuracy in recent years. However, no model has reached 100% accuracy or is entirely error-free. Variations in algorithm efficiency and accuracy stem from differences in sample sizes, datasets, and data types. Further studies should focus on consistent datasets, sample sizes, and data types for more reliable outcomes.

Application of Facial Analysis Based on Convolutional Neural Network and Iterative Decision Tree for Teaching Evaluation in Smart Classrrom

The creation of intelligent classrooms has been expedited by the rapid advancement of the Internet and computer vision, and intelligent teaching has increased the interactivity and effectiveness of learning. Teachers’ teaching and students’ classroom learning state ultimately affect the teaching effect. Students’ facial expressions during class can reflect emotional changes and the current learning state. The computer camera in the smart classroom collects students’ face image data, uses texture-based information, edge-based information, geometric information, and global and local feature extraction to identify and analyze and process the students’ facial expressions. Research has shown that the combination of expression recognition and an intelligent teaching classroom can accurately identify and analyze students’ emotions and learning status, and can effectively evaluate the teaching effect of the intelligent classroom, which helps to improve teaching quality and learning efficiency. Therefore, applying facial expression recognition in the intelligent teaching classroom has far-reaching significance.

THE ROLE OF NEUROPEDAGOGY IN TEACHING PRIMARY CLASS STUDENTS TO READ AND UNDERSTAND TEXT

This study explores the impact of neuropedagogy on reading and text comprehension among elementary school students. Neuropedagogy integrates insights from neuroscience with traditional educational practices, aiming to enhance cognitive engagement and learning efficiency. The research involved a controlled experimental design with two groups: one receiving traditional teaching methods and the other exposed to neuropedagogical strategies. Results indicate significant improvements in the neuropedagogy group, with enhanced reading speed, comprehension, and cognitive reflection. These findings suggest that tailored educational approaches that align with neurocognitive development can significantly improve elementary students' literacy skills.

Impact of ChatGPT on case creation efficiency and learning quality in case-based learning for undergraduate nursing students

Impact of ChatGPT on case creation efficiency and learning quality in case-based learning for undergraduate nursing students

Research on Cooperative Tracking of Multiple Agents on Heterogeneous Ground

Abstract Pursuit-evasion scenarios are typical and significant area of study multi-agent behaviours. While previous research has primarily focused on training pursuit strategies on idealized flat, this paper explores pursuit strategies on heterogeneous ground that rely on ground features from the effects of friction and viscous forces. Since agent interacts with heterogeneous ground and changes its acceleration, we perform multi-agent modelling. Aiming at the multi-agent deep deterministic policy gradient (MADDPG) algorithm’s low training efficiency and slow convergence speed in pursuit learning, we use the prioritized experience selection mechanism of MADDPG algorithm (PES-MADDPG) which improve the experience extraction mechanism based on the policy evaluation function error and the experience extraction training frequency. With this approach, the design of rewards results in faster convergence of reward values. The experimental findings confirm that the suggested method delivers better performance and effectiveness for pursuers and evaders on heterogeneous ground, and both can acquire the relevant movement strategies through training.

Relationship between autonomic nervous function and brain functions such as memory and attention

This study aimed to evaluate the relationship between autonomic nervous function (ANF) and cognitive abilities, such as memory and attention, using the Kana pick-out test (KPT). The participants were 11 female college students aged 21 years old. Each participant completed the KPT ten times, during which their ANF was assessed via heart rate variability analysis. During the KPT, participants circled Japanese vowels in a 400-character story written in hiragana. We measured attention using the KPT score and assessed memory using a memory score based on ten descriptive questions about the story. Statistical analysis revealed a significant positive correlation between higher KPT and memory scores, indicating a link between memory and attention. The parasympathetic sinus modulation marker, high-frequency component power (HF), decreased during the kana-picking task (Interval B) and recovered during the subsequent content verification task (Interval C). In Interval A (before the kana-picking task), the HF showed a positive correlation with both the KPT and memory scores. Additionally, a positive correlation was observed between HF and memory scores during interval B. Other autonomic nervous indices, including low-frequency component power (LF), total power (TP), and LF/HF ratio, also showed significant correlations with KPT and memory scores. Our findings strongly suggest that ANF is intricately connected to cognitive functions, such as memory and attention. This indicates that monitoring ANF could provide a novel methodology for assessing learning and occupational efficiency.

A multi-docking strategy for robotic LAR and deep pelvic surgery with the Hugo RAS system: experience from a tertiary referral center.

In June 2023, our institution adopted the Medtronic Hugo RAS system for colorectal procedures. This system's independent robotic arms enable personalized docking configurations. This study presents our refined multi-docking strategy for robotic low anterior resection (LAR) and deep pelvic procedures, designed to maximize the Hugo RAS system's potential in rectal surgery, and evaluates the associated learning curve. This retrospective analysis included 31 robotic LAR procedures performed with the Hugo RAS system using our novel multi-docking strategy. Docking times were the primary outcome. The Mann-Kendall test, Spearman's correlation, and cumulative sum (CUSUM) analysis were used to assess the learning curve and efficiency gains associated with the strategy. Docking times showed a significant negative trend (p < 0.01), indicating improved efficiency with experience. CUSUM analysis confirmed a distinct learning curve, with proficiency achieved around the 15th procedure. The median docking time was 6min, comparable to other robotic platforms after proficiency. This study demonstrates the feasibility and effectiveness of a multi-docking strategy in robotic LAR using the Hugo RAS system. Our personalized approach, capitalizing on the system's unique features, resulted in efficient docking times and streamlined surgical workflow. This approach may be particularly beneficial for surgeons transitioning from laparoscopic to robotic surgery, facilitating a smoother adoption of the new technology. Further research is needed to validate the generalizability of these findings across different surgical settings and experience levels.

Efficient Privacy-Preserving Machine Learning with Lightweight Trusted Hardware

In this paper, we propose a new secure machine learning inference platform assisted by a small dedicated security processor, which will be easier to protect and deploy compared to today's TEEs integrated into high-performance processors. Our platform provides three main advantages over the state-of-the-art: (i) We achieve significant performance improvements compared to state-of-the-art distributed Privacy-Preserving Machine Learning (PPML) protocols, with only a small security processor that is comparable to a discrete security chip such as the Trusted Platform Module (TPM) or on-chip security subsystems in SoCs similar to the Apple enclave processor. In the semi-honest setting with WAN/GPU, our scheme is 4X-63X faster than Falcon (PoPETs'21) and AriaNN (PoPETs'22) and 3.8X-12X more communication efficient. We achieve even higher performance improvements in the malicious setting. (ii) Our platform guarantees security with abort against malicious adversaries under honest majority assumption. (iii) Our technique is not limited by the size of secure memory in a TEE and can support high-capacity modern neural networks like ResNet18 and Transformer. While previous work investigated the use of high-performance TEEs in PPML, this work represents the first to show that even tiny secure hardware with very limited performance can be leveraged to significantly speed-up distributed PPML protocols if the protocol can be carefully designed for lightweight trusted hardware.

Efficient Hierarchical Reinforcement Learning for Mapless Navigation With Predictive Neighbouring Space Scoring

Efficient Hierarchical Reinforcement Learning for Mapless Navigation With Predictive Neighbouring Space Scoring

Delivery optimization for collaborative truck-drone routing problem considering vehicle obstacle avoidance

Drone participating in logistics delivery has gained much concern due to its potential superiority of operational efficiency and service costs. How to optimize the hybrid vehicle delivery trip is still a crucial issue. Besides, complex urban environment and regulatory no-through zones bring more rigorous challenges. The aim is to develop an efficient routing solution that considers obstacles encountered by the truck and drone, ensuring the timely delivery. This paper proposes an efficient deep reinforcement learning to optimize the collaborative truck-drone routing problem (C-TDRP) under vehicle obstacle avoidance trail. Specifically, the trucks deploy a fleet of drones to serve the random distributed consumers subject to minimum delivery cost. Homogeneous drones serve multiple demand nodes per trip with limited energy carrying capacity. We design the C-TDRP formulation with studying the feasibility of obstacle avoidance routing. Owing to the computational complexity of the proposed mathematical model, an intelligent optimization algorithm based on deep reinforcement learning is developed, named pointer network (Ptr-Net), which can capture the position weights associated with network sequence automatically. Through rigorous experimental validations, the results demonstrate that the vehicle energy consumption of final trajectory reduces by more than 42%, even for large-scale delivery scenarios. Our proposed method not only enhances the optimization performance but also lays the foundation for more intelligent and adaptable logistics delivery in complex urban environments.

Efficient Reinforcement Learning With Impaired Observability: Learning to Act With Delayed and Missing State Observations

Efficient Reinforcement Learning With Impaired Observability: Learning to Act With Delayed and Missing State Observations

One-Step Multiview Fuzzy Clustering With Collaborative Learning Between Common and Specific Hidden Space Information.

Multiview data are widespread in real-world applications, and multiview clustering is a commonly used technique to effectively mine the data. Most of the existing algorithms perform multiview clustering by mining the commonly hidden space between views. Although this strategy is effective, there are two challenges that still need to be addressed to further improve the performance. First, how to design an efficient hidden space learning method so that the learned hidden spaces contain both shared and specific information of multiview data. Second, how to design an efficient mechanism to make the learned hidden space more suitable for the clustering task. In this study, a novel one-step multiview fuzzy clustering (OMFC-CS) method is proposed to address the two challenges by collaborative learning between the common and specific space information. To tackle the first challenge, we propose a mechanism to extract the common and specific information simultaneously based on matrix factorization. For the second challenge, we design a one-step learning framework to integrate the learning of common and specific spaces and the learning of fuzzy partitions. The integration is achieved in the framework by performing the two learning processes alternately and thereby yielding mutual benefit. Furthermore, the Shannon entropy strategy is introduced to obtain the optimal views weight assignment during clustering. The experimental results based on benchmark multiview datasets demonstrate that the proposed OMFC-CS outperforms many existing methods.

Efficient Deep Learning Based Models for Rapid Prediction of RC Shear Wall Responses Under Monotonic and Cyclic Loading

The seismic response of reinforced concrete (RC) shear walls is of paramount importance in earthquake-resistant design. While traditional techniques such as finite-element-based modeling and experimental testing provide comprehensive insights into shear wall behavior, they often require significant computational resources and time. In response, this study investigates the efficacy of various Deep Neural Networks (DNNs), including Convolutional Neural Networks (CNNs), Bidirectional Long Short-Term Memory (Bi-LSTM) networks, and LSTM-Based Autoencoders, in predicting the behavior of RC shear walls under monotonic and cyclic loading conditions. Through training on a diverse dataset encompassing various geometric configurations, material properties, and loading scenarios, the proposed approach generalizes well to unseen cases, enabling rapid estimation of shear wall responses without extensive numerical simulations. This approach offers several advantages, including faster design iterations, improved assessment of existing structures, and potentially higher accuracy. Extensive comparative analyses against experimental tests and numerical simulations evaluate the performance of the deep learning models. Results demonstrate that the proposed approach achieves superior accuracy in prediction of hysteresis and pushover curves, effectively capturing the nonlinear structural behavior of RC shear walls subjected to static and cyclic loading conditions. Validation using a comprehensive experimental database of 160 specimens shows that the model achieves less than 10% error in maximum lateral load predictions for specimens within the training data range; while simultaneously reducing computational time Overall, this study contributes to the evolving landscape of structural engineering by showcasing the potential of DNNs as efficient tools for predicting the behavior of RC shear walls.

Efficient Multitask Reinforcement Learning Without Performance Loss.

We propose an iterative sparse Bayesian policy optimization (ISBPO) scheme as an efficient multitask reinforcement learning (RL) method for industrial control applications that require both high performance and cost-effective implementation. Under continual learning scenarios in which multiple control tasks are sequentially learned, the proposed ISBPO scheme preserves the previously learned knowledge without performance loss (PL), enables efficient resource use, and improves the sample efficiency of learning new tasks. Specifically, the proposed ISBPO scheme continually adds new tasks to a single policy neural network while completely preserving the control performance of previously learned tasks through an iterative pruning method. To create a free-weight space for adding new tasks, each task is learned through a pruning-aware policy optimization method called the sparse Bayesian policy optimization (SBPO), which ensures efficient allocation of limited policy network resources for multiple tasks. Furthermore, the weights allocated to the previous tasks are shared and reused in new task learning, thereby improving sample efficiency and the performance of new task learning. Simulations and practical experiments demonstrate that the proposed ISBPO scheme is highly suitable for sequentially learning multiple tasks in terms of performance conservation, efficient resource use, and sample efficiency.