Learning Step Research Articles

The Development of Online Lessons for Promoting Piano Playing Skills for Non-piano Playing Background Students

This study explores the process of developing online courses to improve the piano-playing skills of students with no piano-playing experience, designs and develops practical online piano courses for students and evaluates the effectiveness and practicality of the developed online courses in enhancing students' piano skills. This is research and development approach collecting data from 35 students. This study uses four tools: course plans and expert validation forms, interview and questionnaire forms, and pretest and post-test evaluations of piano performance skills. Data were analyzed by statistical and content analysis. The findings reveal that online piano lesson assessment step involves expert validation and trials to evaluate the online piano lesson design outcomes. The expert validation of the online piano lesson design and tools, including lesson plans, learning implementation observation sheets, and student response sheets. The expert assessment of the online piano lesson design encompasses the evaluation of several components, such as the correctness of the information provided on the rationale for developing online piano lessons, the theoretical foundations underlying the lessons, and the different learning components included (including learning steps, social systems, reaction principles, and support systems). The online piano lessons in the study were convenient, with an average learning implementation score of 4.20 out of a possible score of 5. Beginners have significantly improved their piano playing skills in various dimensions. These improvements were reflected in the mastery of basic playing skills and the flexible use of complex rhythms and chords. The course design emphasizes training in two-handed coordination, touch techniques, and rhythm. The successful development of the course has provided a flexible and efficient learning path for students with no prior piano playing background and has demonstrated the significant educational value and prospects for the promotion of online piano teaching in developing the skills of beginning piano students

Optimizing Amazon Reviews Using Principal Component Analysis, Feature Selection On Random Forest Classifier

Dataset optimization is an important step in machine learning to improve model performance. This review discusses the use of Random Forest, Principal Component Analysis (PCA), and Feature Selection algorithms to optimize datasets. Based on this review, the combination of Random Forest, PCA, and Feature Selection is proven to be effective in improving machine learning model performance. This combination can help reduce overfitting, improve prediction accuracy, and speed up the model training process. In our experiments with the Amazon Reviews dataset, this optimized approach achieved an impressive accuracy of 91%, demonstrating a significant improvement over baseline models.

Unsupervised data imputation with multiple importance sampling variational autoencoders

Recently, deep latent variable models have made significant progress in dealing with missing data problems, benefiting from their ability to capture intricate and non-linear relationships within the data. In this work, we further investigate the potential of Variational Autoencoders (VAEs) in addressing the uncertainty associated with missing data via a multiple importance sampling strategy. We propose a Missing data Multiple Importance Sampling Variational Auto-Encoder (MMISVAE) method to effectively model incomplete data. Our approach consists of a learning step and an imputation step. During the learning step, the mixture components are represented by multiple separate encoder networks, which are later combined through simple averaging to enhance the latent representation capabilities of the VAEs when dealing with incomplete data. The statistical model and variational distributions are iteratively updated by maximizing the Multiple Importance Sampling Evidence Lower Bound (MISELBO) on the joint log-likelihood. In the imputation step, missing data is estimated using conditional expectation through multiple importance resampling. We propose an efficient imputation algorithm that broadens the scope of Missing data Importance Weighted Auto-Encoder (MIWAE) by incorporating multiple proposal probability distributions and the resampling schema. One notable characteristic of our method is the complete unsupervised nature of both the learning and imputation processes. Through comprehensive experimental analysis, we present evidence of the effectiveness of our method in improving the imputation accuracy of incomplete data when compared to current state-of-the-art VAEs-based methods.

The Development of Self-Directed Learning in Online English Reading of Thai Students Attending a CALL Learner Training

This research studied self-directed learning in online English reading of seven secondary school students who attended a ten-week Computer-Assisted Language Learning (CALL) learner training. The CALL learner training was sequenced using Knowles’s (1975) six steps of self-directed learning, which were setting climate, analyzing needs, setting goals, choosing materials, using strategies, and evaluating the outcomes. Each training session covered three components: pedagogical, strategic, and technical training. The training was conducted over ten weeks and included three required sessions and seven optional consultation sessions. During the training, the learners conducted three weeks of self-learning independently. Three sources of qualitative data, including learners’ learning logs, consultation recordings, and interviews, were used to examine the development of learners’ self-directed learning throughout the training. Overall, all participants showed improvement in their self-directed learning in online English reading after the training. However, goal setting and material selection seemed to be the main challenges for most participants. The findings suggested that more research on using CALL learner training should introduce more technology for different online reading tasks since the current study only presented limited tools.

From Pixels to Precision: Techniques for Image Dataset Refinement

Preparing and processing image datasets is a crucial step in deep learning and computer vision applications. However, many challenges arise in creating high-quality image datasets that can make deep learning models more accurate and generic. We provide a thorough review of best practices in this document for preparing and processing image datasets, from raw data collection to final dataset creation. We discuss various techniques and tools that can be used to enhance image quality, reduce noise, and address issues such as class imbalance and bias. Additionally, we provide practical tips for data cleaning, normalization, and augmentation, which are essential for improving the accuracy and robustness of machine learning procedures. Consequently, we demonstrate the effectiveness of our approach by applying it to real-time images and converting them to datasets suitable for several computer vision applications, such as object detection and classification.

Penerapan Model PBL Berbasis Literasi Berbantuan Media Flinola (Flipbook Inovatif Pancasila) Upaya Peningkatan Pemahaman Nilai-Nilai Pancasila Kelas 2 Sekolah Dasar

Literacy skills significantly influence the learning process and outcomes, making it imperative for teachers to cultivate literacy habits among students. A solid grasp of literacy, coupled with the selection of appropriate learning models and media, is essential for fostering an understanding of Pancasila values. This research aimed to describe the implementation steps of a literacy-based Problem-Based Learning (PBL) model using Flinola (an innovative Pancasila flipbook) and to assess its effectiveness in enhancing second-grade students' comprehension of Pancasila values at SDN Wates 01. A mixed-methods research design was employed. The implementation of the literacy-based PBL model using Flinola was achieved through pre-learning literacy activities and the five phases of PBL. The analysis results indicated that this learning approach was effective in improving students' understanding of Pancasila values, as evidenced by a significant increase in the average score from 56 to 85.2, and a substantial increase in the mastery rate from 16% to 92%. Furthermore, the n-gain analysis revealed a moderate increase in understanding with a value of 0.6953.

Open distance and e-learning (ODeL) assessment indicators for quality learning

This paper is aimed at identifying indicators of open distance and e-learning (ODeL) assessment for quality learning in higher education. The demand for university education in higher learning institutions has continued to grow and hence there has been a phenomenal expansion in enrolments that are not matching with the expansion of facilities. As institutions of higher learning step up to offer their academic programmes by ODeL mode of instructional delivery, there are concerns from stakeholders about the quality of the certificates and degree awards. This can be attributed to inadequate quality assurance standards to assess the quality and value of ODeL academic programmes. The concept of quality, in general, is debated to a high extent, even though it is a common word, it is not a well-understood concept and is defined differently by different individuals in different contexts at different points in time. The implications of poorly assessed students in most cases result in half-baked graduates who may fail to grasp the concepts, skills and knowledge in their area of specialization. On the same score, it is envisaged that the process of assessment requires students’ full engagement with clearly explained criteria that includes peer-reviewing of each other’s work and the necessary support that is provided to the students on the programme. The process of assessment is an iterative process and benefits both the lecturers and students. Although assessment demands a synergetic approach by all the players in the delivery of a programme, there are other critical indicators of assessment that promote quality teaching, and these must be taken into serious considerations. Therefore, the paper contends that there are various indicators of ODeL assessment for quality learning. Additionally, the paper presents Evans’ assessment tool (EAT framework) that could be used to improve quality e-assessment feedback of ODeL and move away from the more traditional methods of providing feedback to the learners under this mode.

Ethnoscience Learning Ideas Oriented to Outcome Base Education (OBE) to Foster Entrepreneurial Competency

This study recommends OBE-oriented ethnoscience learning to foster entrepreneurial competence carried out with 6 stages of learning namely ethnoscience observation activities. ethnoscience analysis, product ideas, production trials, production cost analysis and product presentation/presentation. This learning model is further introduced by the author as ethnoedusciencepreneurship. This learning step is relevant to the main outputs/outcomes of science learning, namely Content Knowledge (HBS1): Inquiry Skills and Scientific Processes (HBS2): Laboratory Engineering and Safety (HBS3): Science Communication (HBS4): Critical Thinking and Problem Solving (HBS5): Scientific Literacy and Ethical Considerations (HBS6): Lifelong Learning and Scientific Investigation (HBS7). The learning step can accommodate the needs of developing entrepreneurial competencies in students referring to SKKNI Number 53 of 2014 concerning Industrial Entrepreneurship.

Conceptual Innovative Arabic Language Lesson Plan Based on 21st Century Skills

The learning implementation design or called RPP is an important component in manifesting the form of teaching and learning activities. The design of the implementation of integral learning is the design of the implementation of learning that involves different processes to get good results. This requires special attention that the design of the implementation of learning has a very large effect on teacher performance and the quality of students. Plus the phenomenon that is increasingly happening in the 21st century is the absolute need for students to have qualified skills that become an important standard in the life of globalization. This is something that the teacher must respond to quickly in his expertise in creating the concept of an innovative Arabic language learning implementation design that is oriented towards 21st century skills. However, the problem is that it is difficult for teachers to formulate learning objectives, develop unique 21st century learning steps including strategies, models, methods and their development in the field due to lack of education about understanding the process of preparing innovative 21st century skills-based RPP with an insufficient period of time. Thus the challenges of teachers will be even greater, new innovations will continue to be generated. On that basis, this study aims to understand and know more clearly the conceptual design of the implementation of innovative Arabic learning based on 21st century skills. This study uses a qualitative method with the type of library research (library research), which is to obtain correct and good information on research criteria from all reading and recording activities. in the form of books, journals, articles, survey results, seminar materials and other research results.

The Qur'anic Education Strategies for the Indonesian Context: An investigation of the Halaqah of the Qur’an in Mecca and Medina

This paper aims to provide a comprehensive perspective on strategies for promoting Qur'anic education in the Indonesian context. The study examines the halaqah of the Quran in Mecca and Medina within the strategic framework of the Qur'anic teaching-learning process. The study begins by highlighting the miserable fact that the current young Muslim generation in Indonesia lacks an interest in the Qur'an. This condition leads not only to the absence of Qur'anic spiritual values in their lives but also to the loss of the tradition of studying the Quran in Muslim societies. This research employs a combined research model that involves a literature review and field research. This study concludes by identifying three key strategies for improving Qur'anic education in Indonesia. First, by using a dialogical approach, the tradition of the halaqah of the Qur'an can be employed as a model for developing the tradition of learning the Qur'an in Indonesia. Second, to develop Qur'anic education in Indonesia, three fundamental components are critical, namely: developing learning spirit and motivation; extending time flexibility and learning innovation; and achieving external support. Third, the learning steps are addressed systematically as part of the integrated contextual learning approach. It covers facilitating a collaborative, supportive, and interactive learning environment. By integrating these elements, it is hoped that Qur'anic education in Indonesia can develop properly and reach a high level of productivity.

An efficient unsupervised classification model for galaxy morphology: Voting clustering based on coding from ConvNeXt large model

By combining unsupervised and supervised machine learning methods, we have proposed a framework, called USmorph to carry out automatic classifications of galaxy morphologies. In this work, we update the unsupervised machine learning (UML) step by proposing an algorithm based on ConvNeXt large model coding to improve the efficiency of unlabeled galaxy morphology classifications. The method can be summarized into three key aspects as follows: (1) a convolutional autoencoder is used for image denoising and reconstruction and the rotational invariance of the model is improved by polar coordinate extension; (2) utilizing a pre-trained convolutional neural network (CNN) named ConvNeXt for encoding the image data. The features were further compressed via a principal component analysis (PCA) dimensionality reduction; (3) adopting a bagging-based multi-model voting classification algorithm to enhance robustness. We applied this model to I-band images of a galaxy sample with $I_ mag < 25$ in the COSMOS field. Compared to the original unsupervised method, the number of clustering groups required by the new method is reduced from 100 to 20. Finally, we managed to classify about 53<!PCT!> galaxies, significantly improving the classification efficiency. To verify the validity of the morphological classification, we selected massive galaxies with $M_ M_ sun $ for morphological parameter tests. The corresponding rules between the classification results and the physical properties of galaxies on multiple parameter surfaces are consistent with the existing evolution model. Our method has demonstrated the feasibility of using large model encoding to classify galaxy morphology, which not only improves the efficiency of galaxy morphology classification, but also saves time and manpower. Furthermore, in comparison to the original UML model, the enhanced classification performance is more evident in qualitative analysis and has successfully surpassed a greater number of parameter tests. The enhanced UML method will support the Chinese space station telescope in the future.

Real-Time Detection of IoT Anomalies and Intrusion Data in Smart Cities Using Multi-Agent System.

Analyzing IoT data is an important challenge in the smart cities domain due to the complexity of network traffic generated by a large number of interconnected devices: smart cameras, light bulbs, motion sensors, voice assistants, and so on. To overcome this issue, a multi-agent system is proposed to deal with all machine learning steps, from preprocessing and labeling data to discovering the most suitable model for the analyzed dataset. This paper shows that dividing the work into different tasks, managed by specialized agents, and evaluating the discovered models by an Expert System Agent leads to better results in the learning process.

Combining climate models and observations to predict the time remaining until regional warming thresholds are reached

Abstract The importance of climate change for driving adverse climate impacts has motivated substantial effort to understand the rate and magnitude of regional climate change in different parts of the world. However, despite decades of research, there is substantial uncertainty in the time remaining until specific regional temperature thresholds are reached, with climate models often disagreeing both on the warming that has occurred to-date, as well as the warming that might be experienced in the next few decades. Here, we adapt a recent machine learning approach to train a convolutional neural network to predict the time (and its uncertainty) until different regional warming thresholds are reached based on the current state of the climate system. In addition to predicting regional rather than global warming thresholds, we include a transfer learning step in which the climate-model-trained network is fine-tuned with limited observations, which further improves predictions of the real world. Using observed 2023 temperature anomalies to define the current climate state, our method yields a central estimate of 2040 or earlier for reaching the 1.5 °C threshold for all regions where transfer learning is possible, and a central estimate of 2040 or earlier for reaching the 2.0 °C threshold for 31 out of 34 regions. For 3.0 °C, 26 °C out of 34 regions are predicted to reach the threshold by 2060. Our results highlight the power of transfer learning as a tool to combine a suite of climate model projections with observations to produce constrained predictions of future temperatures based on the current climate.

Interrelated dynamic biased feature selection and classification model using enhanced gorilla troops optimizer for intrusion detection

An Intrusion Detection System (IDS) is a valuable tool for network security since it can identify attacks, intrusions, and other types of illegal access. Excessive and irrelevant data slows down the classification process and eventually weakens the system's capacity to make informed decisions when IDS is monitoring a huge volume of network traffic. Innovative approaches are utilized to create large amounts of data and a lot of network traffic in order to test its effectiveness. A vital step in machine learning is feature selection. By determining which features are most essential for describing the dataset and its initial attributes, feature selection seeks to improve intrusion prediction performance while simultaneously delving deeper into the stored data. Making a feature selection is similar to fixing an optimization problem without a clear definition when users don't know where to begin. Finding the fewest characteristics required to describe the dataset, the original features, and to conduct classification is the primary purpose of feature selection, which also aims to improve prediction performance and acquire a deeper understanding of the stored data. As a result, researchers have been focusing on feature-selection issues recently, especially in light of the massive growth in available databases. Metaheuristic algorithms using a learning model have been the subject of studies to optimize feature selection difficulties. This research uses Enhanced Gorilla Troops Optimizer (EGTO), for enhancing the feature selection process and then performing classification. This research presents a Interrelated Dynamic Biased Feature Selection Model using Enhanced Gorilla Troops Optimizer (IDBFS-EGTO) for generation of feature vector set for intrusion detection. Despite its apparent success in handling a wide range of practical problems, it risks getting mired in local optima and premature convergence when faced with more difficult optimization challenges that is overcome with EGTO. The EGTO approach, which uses a collection of operators to strike a more steady equilibrium between exploitation and exploration. The proposed model generates relevant feature subset for machine learning model for accurate detection and classification of intrusions in the network. The proposed model achieved 98.4 % accuracy in intrusion detection and 98.6 % accuracy in EGTO optimization classification. The proposed model is improved by 3.8 % in feature weight allocation accuracy and 1.2 % in detection accuracy levels. The proposed model is compared with the traditional models and the results represent that the proposed model performance is high.

Diversivikasi Produk dan Pemasaran Berbasis IT untuk Meningkatkan Nilai Tambah Omzet Penjualan UMKM Tempe Bagong

Tempe Bagong UMKM is a business engaged in processing soybeans into traditional tempeh. The problems that occur in Tempe Bagong UMKM Partners include not having other tempeh product variations, tempeh bagong product packaging is still absent, and the marketing process is still being sold in small stalls around the village. The community service approach method used to help partner problems is Participatory Learning and Action (PLA). The steps of the Participatory Learning and Action (PLA) approach are characterized by socialization, discussion, and direct training practices. The stages of this community service activity are pre-training, education stage, practice stage, mentoring stage, and evaluation stage. Through this community service, diversification is produced in the form of tempeh bungkil which is a mixture of soybeans, soybean skin, copra, and peanuts. This product is packaged more attractively to increase its selling value. In addition, digital marketing is also carried out through digital marketing

Complexity, interpretability and robustness of GP-based feature engineering in remote sensing

Feature engineering is a crucial step in machine learning that provides better data for the learning algorithms to induce robust models, and this effort should be adapted to the capabilities of each algorithm. For example, classifiers that do not perform data transformations (e.g., cluster-based) perform better when the different classes are separated, typically requiring preprocessed data. Other models (e.g., decision trees) can perform several splits in the feature space, easily obtaining perfect results in training data, but have a higher risk of overfitting with unprocessed data. We use the rbd-GP and M3GP genetic programming algorithms to induce new features based on the original features, to be used by shallow and deep decision tree and random forest models. M3GP is wrapped around a learning algorithm, using its performance as fitness. This way, the induced features are adapted to the classifier, allowing us to compare the complexity of the features induced for the different classifiers. We measure the complexity of the induced features using several structural and functional complexity metrics found in the literature, also proposing a new metric that measures the separability of classes in the feature space. Like other authors, we use complexity as an interpretability metric, selecting three models to discuss and validate based on their performance and size. We apply these methods to remote sensing classification problems and solve two tasks that are hard due to the high similarity between the land cover classes: detecting cocoa agroforest and forecasting forest degradation up to one year in the future.

Implementasi Metode Takrir dalam Meningkatkan Hafalan Al-Qur’an Peserta Didik pada Mata Pelajaran Tahfizh Kelas VC MI Darul Qur’an Sawangan Depok

This study discusses the implementation of the takrir method in improving the memorization of the Qur'an among students of the VC class MI Darul Qur'an Sawangan, Depok. This study aims to find out the application of the takrir method in improving the memorization of the Qur'an among students of the VC MI Darul Qur'an class, the results of the application of the takrir method and its supporting and inhibiting factors. This study uses a descriptive qualitative approach with the type of field research. The data collection technique uses observation, interview, and documentation techniques, using data analysis, data reduction, data presentation, and conclusion. The results of this study show that the application of the takrir method in learning tahfizh in VC class in improving the memorization of the Qur'an has gone well and in accordance with the following learning steps: Bin-Nazhar, Talaqqi, Takrir, Tasmi'. Supporting factors in the application of this method include health, psychological, intelligence, motivation and age. The inhibiting factors are: the reading of the Qur'an is still not good, similar verses, few repetitions, and the absence of a guide.

Fitness and historical success information-assisted binary particle swarm optimization for feature selection

Feature selection is a critical preprocessing step in machine learning aimed at identifying the most relevant features or variables from a dataset. Although conventional particle swarm optimization (PSO) has shown efficiency for feature selection tasks, developing an effective PSO algorithm for this task is still challenging. This study proposes a fitness and historical success information-assisted binary particle swarm optimization, denoted by FPSO. The FPSO is developed by integrating different search strategies, including a weighted center-based approach, historical information-based acceleration coefficients, and selection operation. These strategies are embedded into the FPSO to enhance the levels of exploration and exploitation based on the fitness value of particles and their historical search status. In the FPSO, the transfer function is also added to transform the continuous search space into binary search space. Experimental validation and comparison with seven other metaheuristic algorithms on 24 datasets verify the effectiveness of the FPSO in eliminating irrelevant and redundant features.

Upaya Meningkatkan Minat Belajar Siswa Kelas IV Pada Pembelajaran IPS dengan Menggunakan Media Gambar di SDK Roworeke 2

This research aims to describe efforts to increase the learning interest of fourth grade students in learning social studies using image media at SDK Roworeke 2 East Ende. This type of research is qualitative, namely the researcher describes how to increase the learning interest of fourth grade students in social studies learning using image media at SDK Roworeke 2 Ende Timur through in-depth interviews with research information supported by observation and documentation processes. The research subjects were the principal, class IV teacher and 4 class IV students. The results of the research show that the teacher's strategy in using image media can increase the learning interest of fourth grade students learning social studies by using image media at SDK Roworeke 2 East Ende, namely; adapting the material to the images that will be used, designing the image media that will be used considering the limitations of the media, compiling steps in using image media, adjusting learning steps based on lesson plans, references and learning objectives that have been prepared previously

Development and validation of a rheumatoid arthritis case definition: a machine learning approach using data from primary care electronic medical records

BackgroundRheumatoid Arthritis (RA) is a chronic inflammatory disease that is primarily diagnosed and managed by rheumatologists; however, it is often primary care providers who first encounter RA-related symptoms. This study developed and validated a case definition for RA using national surveillance data in primary care settings.MethodsThis cross-sectional validation study used structured electronic medical record (EMR) data from the Canadian Primary Care Sentinel Surveillance Network (CPCSSN). Based on the reference set generated by EMR reviews by five experts, three machine learning steps: ‘bag-of-words’ approach to feature generation, feature reduction using a feature importance measure coupled with recursive feature elimination and clustering, and classification using tree-based methods (Decision Tree, Random Forest, and Extreme Gradient Boosting). The three tree-based algorithms were compared to identify the procedure that generated the optimal evaluation metrics. Nested cross-validation was used to allow evaluation and comparison and tuning of models simultaneously.ResultsOf 1.3 million patients from seven Canadian provinces, 5,600 people aged 19 + were randomly selected. The optimal algorithm for selecting RA cases was generated by the XGBoost classification method. Based on feature importance scores for features in the XGBoost output, a human-readable case definition was created, where RA cases are identified when there are at least 2 occurrences of text “rheumatoid” in any billing, encounter diagnosis, or health condition table of the patient chart. The final case definition had sensitivity of 81.6% (95% CI, 75.6–86.4), specificity of 98.0% (95% CI, 97.4–98.5), positive predicted value of 76.3% (95% CI, 70.1–81.5), and negative predicted value of 98.6% (95% CI, 98.0-98.6).ConclusionA case definition for RA in using primary care EMR data was developed based off the XGBoost algorithm. With high validity metrics, this case definition is expected to be a reliable tool for future epidemiological research and surveillance investigating the management of RA in CPCSSN dataset.