Existing Learning Methods Research Articles

Association Between Pandemic-Related Instructional Delivery Modifications and Emergency Medical Technician (EMT) First Attempt Pass Rates

Background: The COVID-19 pandemic represents a sentinel event for healthcare and healthcare education alike. Mandatory shutdowns of educational institutions, combined with increased demand for skilled healthcare personnel, highlighted pre-existing challenges surrounding how to maintain a stable workforce. To ensure continuity of educational opportunities, many emergency medical services (EMS) educational institutions were forced to modify existing learning method to digital learning formats. This emergent transition unearthed concerns regarding the impacts alternative learning methods would have on entry-level EMS providers' learning outcomes and overall competency levels. The objective of this study was to investigate the impact of alternative instructional methods used for EMT education during the COVID-19 pandemic. Methods: The study is a retrospective review of prospectively collected data for EMT candidates from a single community college-based EMT program who completed a first attempt of the National Registry EMS Certification examination for EMT candidates from course sections ending between January 1, 2019, and December 31, 2020. Historical pre-COVID first attempt exam outcomes were compared to the first attempt outcomes of two alternative instructional methods –Emergency Remote (ER) and COVID Distance Learning Hybrid (DL). Results: The outcomes of 237 EMT students were evaluated. Remote and COVID Hybrid DL models compared to the traditional pre-COVID learning format. There was no significant difference in first attempt pass rates between students who participated in traditional learning, the Emergency Remote model (1.53 odds ratio), or the Distance Learning model (2.98 odds ratio). Conclusions: This study suggests that virtual learning is at least as effective as traditional formats in preparing students for the NREMT examination. Additional research is warranted regarding best practices for applying virtual learning modalities in EMS education.

The Role of Tahfidz Al-Quran Learning in Assisting Religious Studies

Background. Islamic religious learning in schools generally focuses on the discussion of Qur'anic verses. However, many students have difficulty in reading the Qur'an correctly and precisely, even more so in memorizing these verses. This raises questions about the effectiveness of existing learning methods and the potential role of learning tahfidz Al-Qur'an in helping religious lessons. Purpose. This study aims to determine the role of learning tahfidz Al-Qur'an in helping religious lessons, especially in the context of learning Al-Qur'an Hadith. Method. The research uses a qualitative descriptive method. Sampling was carried out by the purposive method, with the key informants being class teachers and students of SDIT Nurul 'Ilmi Tenggarong. Data collection techniques include observation, interviews, and documentation. Results. The results of the study show that the learning of tahfidz Al-Qur'an has a very important position in helping religious learning, especially the learning of the Qur'an Hadith. Al-Qur'an tahfidz activities have a positive influence on students' learning of the Qur'an Hadith. Students who are diligent in reading and memorizing the Qur'an tend to have better learning activity. Conclusion. Learning tahfidz Al-Qur'an plays an important role in improving students' abilities in learning Al-Qur'an Hadith. Discipline in reading and memorizing the Qur'an is positively correlated with learning discipline, which ultimately improves the learning outcomes of the Qur'an Hadith subject. This research highlights the importance of integrating tahfidz Al-Qur'an learning in the Islamic religious education curriculum to improve students' understanding and skills in understanding and practicing Islamic teachings.

Adding immersive virtual reality laboratory simulations to traditional teaching methods enhances biotechnology learning outcomes

Immersive virtual reality (VR) simulations are increasingly being used in diverse educational and training contexts to supplement traditional learning methods. The high versatility of virtual laboratories allows students to take advantage of many benefits, like experiencing dangerous reactions, time-consuming protocols, or expensive equipment without the necessity of a real science laboratory. However, little research is currently available to support the efficacy and efficiency of this new learning tool. In this context, the main objective of this study was to assess the influence of biotechnology training by using immersive VR technologies on the student’s motivational and learning outcomes as compared with learning with conventional methods only. To this aim we tested two diverse strategies, respectively VR simulations were used in place of or in addition to the teacher’s introductory lesson of a hands-on laboratory experience. Aligned questionaries were administered before and after the proposed activities to assess theoretical knowledge, self-efficacy, interest in biotechnology, and engagement of the participants. We found that when the introductory lesson to a biotechnology hands-on laboratory is replaced with an equivalent immersive VR simulation, the student’s learning outcomes are lower with respect to the traditional approach. On the contrary, when VR simulations are integrated as an additional tool to the existing learning methods, higher learning outcomes were observed demonstrating a deeper understanding of the learning contents. Furthermore, our study showed that learning with immersive VR simulations motivates students more than the traditional methods, thus, using this new technology in addition to the existing educational methods in biotechnology could be considered as a win-win strategy to raise the attention of the students while increasing the learning outcomes.

Alzheimer’s disease diagnosis from multi-modal data via feature inductive learning and dual multilevel graph neural network

Multi-modal data can provide complementary information of Alzheimer’s disease (AD) and its development from different perspectives. Such information is closely related to the diagnosis, prevention, and treatment of AD, and hence it is necessary and critical to study AD through multi-modal data. Existing learning methods, however, usually ignore the influence of feature heterogeneity and directly fuse features in the last stages. Furthermore, most of these methods only focus on local fusion features or global fusion features, neglecting the complementariness of features at different levels and thus not sufficiently leveraging information embedded in multi-modal data. To overcome these shortcomings, we propose a novel framework for AD diagnosis that fuses gene, imaging, protein, and clinical data. Our framework learns feature representations under the same feature space for different modalities through a feature induction learning (FIL) module, thereby alleviating the impact of feature heterogeneity. Furthermore, in our framework, local and global salient multi-modal feature interaction information at different levels is extracted through a novel dual multilevel graph neural network (DMGNN). We extensively validate the proposed method on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset and experimental results demonstrate our method consistently outperforms other state-of-the-art multi-modal fusion methods. The code is publicly available on the GitHub website. (https://github.com/xiankantingqianxue/MIA-code.git)

Extracting roads from satellite images via enhancing road feature investigation in learning

AbstractIt is a hot topic to extract road maps from satellite images. However, it is still very challenging with existing methods to achieve high‐quality results, because the regions covered by satellite images are very large and the roads are slender, complex and only take up a small part of a satellite image, making it difficult to distinguish roads from the background in satellite images. In this article, we address this challenge by presenting two modules to more effectively learn road features, and so improving road extraction. The first module exploits the differences between the patches containing roads and the patches containing no road to exclude the background regions as many as possible, by which the small part containing roads can be more specifically investigated for improvement. The second module enhances feature alignment in decoding feature maps by using strip convolution in combination with the attention mechanism. These two modules can be easily integrated into the networks of existing learning methods for improvement. Experimental results show that our modules can help existing methods to achieve high‐quality results, superior to the state‐of‐the‐art methods.

Learning Methods According to Modern Obaidat

Method is a way used to achieve certain goals. This method greatly affects students in receiving the knowledge delivered. The purpose of this research is to find out the learning method according to Obaidat. To achieve the research objectives, the author uses the type of library research by using written materials that have been published in the form of books and journals. There are 11 learning methods according to Obaidat, namely, lecture method, discussion method, brainstorming method, story method, problem solving method, project method, assignment method, field trip method, survey method, concept map method, and play while learning method. Remedial learning with the problem solving method is learning that is dominated by student activeness, so the success in overcoming student difficulties is higher than remedial learning with conventional methods that involve less student activeness. From the many existing learning methods, it can be concluded that students can use any method, as long as learning can take place optimally and students can understand the material presented. With the right learning method, it can encourage the growth of students' enjoyment of lessons, foster and increase motivation in doing assignments, make it easier to understand lessons, thus enabling students to achieve better learning outcomes.

Reinforcement learning based sliding mode control for two-time-scale multi-agent systems with malicious attacks

The optimal consensus problem for linear two-time-scale multi-agent systems under malicious attacks is studied in this paper. Firstly, an integral sliding mode function is devised to guide the system trajectory towards the sliding mode surface and the impact of attacks can be eliminated. Then, the optional consensus problem is reformulated as a zero-sum game problem between each agent and its neighbouring agents. Thus, the game algebraic Riccati equation with singularly perturbed parameter is formulated. Furthermore, to avoid the requirement of the system dynamics information, an integral reinforcement learning algorithm is presented to obtain the optimal control policy for multi-agent systems. Compared with existing learning methods, the obtained reinforcement learning algorithm is devoid of potential calculation error issues from singularly perturbed parameter. Meanwhile, the convergence of the proposed algorithm is verified. Finally, a simulation example is provided to demonstrate the efficacy of the proposed control method.

RTHEN: Unsupervised deep homography estimation based on dynamic attention for repetitive texture image stitching

Homography estimation is regarded as one of the key challenges in image alignment, where the goal is to estimate the projective transformation between two images on the same plane. Unsupervised learning methods are gradually becoming popular due to their excellent performance and lack of need for labeled data. However, in regional scenes with repeated textures, there may be ambiguity in the correspondence between local features, affecting homography estimation accuracy. This paper proposes a new unsupervised deep homography method RTHEN to solve such problems. In order to effectively obtain repeated texture features, a multi-scale Feature pyramid Siamese network (FPSN) is designed. Specifically, we dynamically allocate the weights of recited texture features through a dynamic attention module and introduce a channel attention module to provide rich contextual information for repeated texture areas. We propose a hard triplet loss function based on overlap constraints to optimize the matching results. At the same time, we collected a repetitive texture image dataset (RTID) for homography estimation training and evaluation. Experimental results show that our method outperforms existing learning methods in repetitive texture scenes and offers competitive performance with state-of-the-art traditional methods.

Training multi-layer spiking neural networks with plastic synaptic weights and delays.

Spiking neural networks are usually considered as the third generation of neural networks, which hold the potential of ultra-low power consumption on corresponding hardware platforms and are very suitable for temporal information processing. However, how to efficiently train the spiking neural networks remains an open question, and most existing learning methods only consider the plasticity of synaptic weights. In this paper, we proposed a new supervised learning algorithm for multiple-layer spiking neural networks based on the typical SpikeProp method. In the proposed method, both the synaptic weights and delays are considered as adjustable parameters to improve both the biological plausibility and the learning performance. In addition, the proposed method inherits the advantages of SpikeProp, which can make full use of the temporal information of spikes. Various experiments are conducted to verify the performance of the proposed method, and the results demonstrate that the proposed method achieves a competitive learning performance compared with the existing related works. Finally, the differences between the proposed method and the existing mainstream multi-layer training algorithms are discussed.

Action Research on Improving Students’ Conceptual Understanding in the “Force and Energy” Unit through Semantic Mapping

This study was aimed to eliminate the difficulties in teaching the concepts and the students' conceptual understanding in the “Force and Energy” unit through semantic mapping. The study was conducted using the action research method. This study was conducted in the control group, using the existing learning method in the science curriculum, while in the experimental group, homework practices with semantic maps were added. The study sample comprised 49 students studying in the seventh grade of a public middle school affiliated with the Republic of Turkey Ministry of National Education [MoNE] in the 2021–2022 academic year. Data collection tools in this study were administered “New Force and Energy Unit Conceptual Understanding Test”, “Semantic Mapping Evaluation Rubric”, and “Implementation Interview Form”. The study findings determined that the semantic mapping practice, applied to improve the conceptual understanding of the seventh grade middle school students focused on the concepts within the scope of the “Force and Energy” unit, had positive effects on the students. The results of the structured interview form to obtain the views of the seventh grade students participating in this study on the semantic mapping practice indicate that the students reinforced the subject, demonstrating more effective learning. Another result revealed that students had more fun and were more enthusiastic as they actively participated in the process. Our study results reveal that semantic mapping positively affects student performance and attitudes. From this perspective, the use of semantic mapping in the science education process can be expanded.

Konsep Metode Diskusi dalam Meningkatkan Motivasi Belajar Peserta Didik pada Pelajaran Fiqih

The aim of this study is to describe the implementation of discussion methods in improving the learning motivation of students in fiqih lessons at Nurul Hikmah MA as well as the supporting and inhibiting factors in using the discussion method. The research method used is a qualitative approach through descriptive methods. This research uses many data collection techniques such as interviews, observations, and documentation. The results of this study show that the concept of discussion method on fiqih lessons in Nurul Hikmah MA uses the division of students into groups to be able to collaborate and engage in discussion. This method significantly increases the motivation of students to learn through the enthusiasm of students. However, in implementing the discussion method there are some supportive and inhibitor factors so that educators can study and review the various existing learning methods. Because not all lessons are suitable for implementation with discussion methods so educators need to have the right learning strategies to facilitate the learning process

Unsupervised learning of stationary and switching dynamical system models from Poisson observations

Objective. Investigating neural population dynamics underlying behavior requires learning accurate models of the recorded spiking activity, which can be modeled with a Poisson observation distribution. Switching dynamical system models can offer both explanatory power and interpretability by piecing together successive regimes of simpler dynamics to capture more complex ones. However, in many cases, reliable regime labels are not available, thus demanding accurate unsupervised learning methods for Poisson observations. Existing learning methods, however, rely on inference of latent states in neural activity using the Laplace approximation, which may not capture the broader properties of densities and may lead to inaccurate learning. Thus, there is a need for new inference methods that can enable accurate model learning. Approach. To achieve accurate model learning, we derive a novel inference method based on deterministic sampling for Poisson observations called the Poisson Cubature Filter (PCF) and embed it in an unsupervised learning framework. This method takes a minimum mean squared error approach to estimation. Terms that are difficult to find analytically for Poisson observations are approximated in a novel way with deterministic sampling based on numerical integration and cubature rules. Main results. PCF enabled accurate unsupervised learning in both stationary and switching dynamical systems and largely outperformed prior Laplace approximation-based learning methods in both simulations and motor cortical spiking data recorded during a reaching task. These improvements were larger for smaller data sizes, showing that PCF-based learning was more data efficient and enabled more reliable regime identification. In experimental data and unsupervised with respect to behavior, PCF-based learning uncovered interpretable behavior-relevant regimes unlike prior learning methods. Significance. The developed unsupervised learning methods for switching dynamical systems can accurately uncover latent regimes and states in population spiking activity, with important applications in both basic neuroscience and neurotechnology.

Latent Dirichlet Allocation Utilization as a Text Mining Method to Elaborate Learning Effectiveness

Learning method is a way to explain the lesson materials to students so that the learning process can occur in students as an effort to achieve the goals. Learning methods can be said to be a success if students are active, both physically, mentally, and socially in the learning process, in addition to showing high enthusiasm for learning and having self-confidence. The purpose of this study is to classify the opinions of Indonesian students regarding the existing learning methods and what learning methods they expected. In order to evaluate existing learning methods using the latent dirichlet allocation method. The data used comes from tweets of Twitter users within the range of January to March 2022. The data is taken using the scrapping method through the help of the python twisel library and totaled to 3778 data, then preprocessed through the nltk and Sastrawi libraries. The results of this analysis stated that student opinions can be classified into 3 major topics which state students' opinions regarding effective learning methods, student difficulties in applicable learning methods, and high cross-departmental interest.

Penerapan Strategi True Or False Mata Pelajaran Fiqih Untuk Meningkatkan Hasil Belajar Siswa Kelas VII MTs Al-Ikhwan Serapuh ABC

This research was motivated by the lack of creativity of fiqh teachers in class VII MTs Al-Ikhwan Sefragile ABC so far in exploring learning designs that can be used for monotonous fiqh subjects so that students tend to feel bored, for this reason there needs to be a paradigm shift in reviewing teaching and learning strategies and regulating teacher and student interactions, applying true or false strategies in the fiqh learning process in class VII MTs Al-Ikhwan Sefragile ABC is One way to improve existing learning methods. This study is intended to answer the problem: Can the True or False strategy improve student learning outcomes on halal and haram food materials in class VII MITs Al-Ikhwan Sefragile ABC? These quentions were discussed in two cycles of classroom behavioral reseacrh. The sequence of stages includes plan, act, observe, and consider. The results show that: Can the True or False strategy improve student learning outcomes on halal and haram food materials in class VII MTs Al-Ikhwan Sefragile ABC? These problems are discussed through classroom action research carried out through 2 cycles with each cycle of stages being planning, action, observation, and reflection. The results are as follows. In Class VII MTs, correct or incorrect strategies can improve students' learning outcomes on halal and haram ingredients. Al Ifwan Sephrazir ABC. Cycle students only 53.1% Cycle I 65.3%, Cycle II 85.6%.

Design of progressive fuzzy polynomial neural networks through gated recurrent unit structure and correlation/probabilistic selection strategies

This study focuses on two critical design aspects of a progressive fuzzy polynomial neural network (PFPNN): the influence of the gated recurrent unit (GRU) structure and the implementation of fitness-based candidate neuron selection (FCNS) through two probabilistic strategies. The primary objectives are to enhance modeling accuracy and to reduce the computational load associated with nonlinear regression tasks. Compared with the existing fuzzy rule-based modeling architecture, the proposed dynamic model consists of the GRU structure and the hybrid fuzzy polynomial architecture. In the initial two layers of the PFPNN, we introduce three types of polynomial and fuzzy rules into the GRU neurons (GNs) and fuzzy polynomial neurons (FPNs), which can effectively reveal potential complex relationships in the data space. The synergy of the FCNS strategies and the ℓ2 regularization learning method is to design a progressive regression model adept at melding the GRU structure with a self-organizing architecture. The proposed GRU structure and polynomial-based neurons significantly improve the modeling accuracy for time-series datasets. The rational utilization of FCNS strategies can reinforce the network structure and discover the potential performance of neurons of the network. Furthermore, the inclusion of ℓ2 norm regularization provides additional stability to the proposed model and mitigates the overfitting issue commonly encountered in many existing learning methods. We validated the proposed neural networks using six time-series, four machine learning, and two real-world datasets. The PFPNN outperformed other models in the comparison studies in 83.3% of the datasets, emphasizing its superiority in terms of developing a stable deep structure from diverse candidate neurons and reducing computational overhead.

Point2MM: Learning medial mesh from point clouds

Medial mesh is the most commonly used representation of medial axis transform (MAT) which is a high-fidelity compact representation of 3D shape. Existing learning methods of extracting medial mesh from point clouds either have strict requirements of supervising training data, or are incapable of learning the complete form of medial mesh, leading to large reconstruction error. We introduce Point2MM, an unsupervised method for learning a complete medial mesh from point clouds. Our key idea is to use the envelop geometry of medial primitives – spheres, cones, and slabs – to capture the intrinsic geometry of shape, and the connectivity of medial mesh to capture the topology of shape. We firstly predict initial medial spheres by learning the geometric transformation of point clouds, then construct an initial connectivity of the medial spheres by learning the probability of medial cones and medial slabs with a novel unsupervised formulation. Finally we propose an iterative strategy for fine-tuning medial primitives. Extensive evaluations and comparisons show our method has superior accuracy and robustness in learning medial mesh from point clouds. In addition, the excessive training time is also a concern for our research, and it is a limitation where we need to make improvements in our future work.

Better Safe Than Sorry: Constructing Byzantine-Robust Federated Learning with Synthesized Trust

Byzantine-robust federated learning empowers the central server to acquire high-end global models amidst a restrictive set of malicious clients. The general idea of existing learning methods requires the central server to statistically analyze all local parameter (gradient or weight) updates, and to delete suspicious ones. The drawback of these approaches is that they lack a root of trust that would allow us to identify which local parameter updates are suspicious, which means that malicious clients can still disrupt the global model. The machine learning community has recently proposed a new method, FLTrust (NDSS’2021), where the server achieves robust aggregation by using a tiny, uncontaminated dataset (denoted as the root dataset) to generate the root of trust; however, the global model’s accuracy will significantly decline if the root dataset greatly deviates from the client’s dataset. To address the above problems, we propose FLEST: a Federated LEarning with Synthesized Trust method. Our method considers that trust and anomaly detection methods can complementarily solve their respective problems; therefore, we designed a new robust aggregation rule with synthesized trust scores (STS). Specifically, we propose the trust synthesizing mechanism, which can aggregate trust scores (TS) and confidence scores (CS) into STS through a dynamic trust ratio γ, and we use STS as the weight for aggregating the local parameter updates. Our experimental results demonstrated that FLEST is capable of resisting existing attacks, even when the root dataset distribution significantly differs from the total dataset distribution: for example, the global model trained by FLEST is 41% more accurate than FLTrust for adaptive attacks using the mnist-0.5 dataset with the bias probability set to 0.8.

A scalable graph reinforcement learning algorithm based stochastic dynamic dispatch of power system under high penetration of renewable energy

Due to the increasing penetration of renewable energy source, power system is facing significant uncertainties. How to fully consider those uncertainties in dynamic economic dispatch (DED) has become a crucial problem to the safe and economic operation of power system. Reinforcement learning (RL) based approaches can provide the dispatch policy in response to uncertainty. However, current RL uses traditional Euclidean data representation, which greatly reduces the scalability and computational efficiency of economic dispatch algorithms. To address such obstacle, this paper develops a novel graph reinforcement learning (GRL) method for DED of power system. Firstly, DED is formulated as a Markov decision process and formulated as a dynamic sequential decision problem. Secondly, a novel graph-based representation of system state is proposed. Using graph data to represent dispatch operation data with non-Euclidean characteristics can effectively capture the implicit correlation of the uncertainty corresponding to the system topology. Thirdly, a GRL algorithm is proposed to learn the optimal policy which maps graph represented system state to DED decision. Compared with the traditional deep reinforcement learning (DRL), the GRL proposed in this paper has certain generalization ability and scalability, and can achieve higher quality solutions in online operation. Case studies illustrate that the optimality of the proposed method is 98.04%, which is 15.13% higher than that of the existing learning methods. The algorithm is scalable and improves the sample efficiency.

MAGNET: A MODALITY-AGNOSTIC NETWORK FOR 3D MEDICAL IMAGE SEGMENTATION.

In this paper, we proposed MAGNET, a novel modality-agnostic network for 3D medical image segmentation. Different from existing learning methods, MAGNET is specifically designed to handle real medical situations where multiple modalities/sequences are available during model training, but fewer ones are available or used at time of clinical practice. Our results on multiple datasets show that MAGNET trained on multi-modality data has the unique ability to perform predictions using any subset of training imaging modalities. It outperforms individually trained uni-modality models while can further boost performance when more modalities are available at testing.

Smart pictorial dictionary via mobile augmented reality

Augmented reality (AR) technology offers many benefits for language teaching and learning. Using the AR technique in pedagogy attracts and engages children to learn and memorize easily, even in a short time. Visual representation learning method like a pictorial dictionary is one of the beginnings of learning for children. It helps children to visualize the object and memorize it in effective ways. Based on the survey conducted in one of the primary schools at Merlimau, Melaka, it was found that the children have difficulties in learning English. The development of pictorial dictionaries with the combination of AR technology in 3D that are presented in the form of mobile applications can be used to improve existing learning methods in English. The method used during the development of this application is the ADDIE model, which comes with five phases: analysis, design, development, implementation, and evaluation. The development of the ‘smart pictorial dictionary via mobile AR application has been done successfully and has received positive results. Based on the evaluation using the attention relevance confidence satisfaction (ARCS) model, the output has an overall mean of 4.58, which shows that using AR technology in early childhood learning makes children learn more.