Conventional Learning Techniques Research Articles

Fuzzy logical system for personalized vocal music instruction and psychological awareness in colleges using big data

Traditional psychological awareness relating to vocal musical instruction often disregards the impact of earlier experiences on music learning could result in a gap in meeting the needs of individual students. Conventional learning techniques of music related to psychological awareness for each individual has been focused on and addressed in this research. Technological upgrades in Fuzzy Logic (FL) and Big Data (BD) related to Artificial Intelligence (AI) are provided as a solution for the existing challenges and provide enhancement in personalized music education. The combined approach of BD-assisted Radial Basis Function is added with the Takagi Sugeno (RBF-TS) inference system, able to give personalized vocal music instruction recommendations and indulge psychological awareness among students. Applying Mel-Frequency Cepstral Coefficients (MFCC) is beneficial in capturing variant vocal characteristics as a feature extraction technique. The BD-assisted RBF can identify the accuracy of pitch differences and quality of tone, understand choices from students, and stimulate psychological awareness. The uncertainties are addressed by using the TS fuzzy inference system and delivering personalized vocal training depending on different student preference factors. With the use of multimodal data, the proposed RBF-TS approach can establish a fuzzy rule base in accordance with the personalized emotional elements, enhancing self-awareness and psychological well-being. Validation of the proposed approach using an Instruction Resource Utilization Rate (IRUR) gives significant improvements in engaging students, analyzing the pitching accuracy, frequency distribution of vocal music instruction, and loss function called Mean Square Error(MSE). The proposed research algorithm pioneers a novel solution using advanced AI algorithms addressing the research challenges in existing personalized vocal music education. It promises better student outcomes in the field of music education.

How a student becomes a teacher: learning and forgetting through spectral methods

In theoretical machine learning, the teacher–student paradigm is often employed as an effective metaphor for real-life tuition. A student network is trained on data generated by a fixed teacher network until it matches the instructor’s ability to cope with the assigned task. The above scheme proves particularly relevant when the student network is overparameterized (namely, when larger layer sizes are employed) as compared to the underlying teacher network. Under these operating conditions, it is tempting to speculate that the student ability to handle the given task could be eventually stored in a sub-portion of the whole network. This latter should be to some extent reminiscent of the frozen teacher structure, according to suitable metrics, while being approximately invariant across different architectures of the student candidate network. Unfortunately, state-of-the-art conventional learning techniques could not help in identifying the existence of such an invariant subnetwork, due to the inherent degree of non-convexity that characterizes the examined problem. In this work, we take a decisive leap forward by proposing a radically different optimization scheme which builds on a spectral representation of the linear transfer of information between layers. The gradient is hence calculated with respect to both eigenvalues and eigenvectors with negligible increase in terms of computational and complexity load, as compared to standard training algorithms. Working in this framework, we could isolate a stable student substructure, that mirrors the true complexity of the teacher in terms of computing neurons, path distribution and topological attributes. When pruning unimportant nodes of the trained student, as follows a ranking that reflects the optimized eigenvalues, no degradation in the recorded performance is seen above a threshold that corresponds to the effective teacher size. The observed behavior can be pictured as a genuine second-order phase transition that bears universality traits. Code is available at: https://github.com/Jamba15/Spectral-regularization-teacher-student/tree/master.

Enhancement of Mastery Physics Concept of Momentum and Impulse Among Class X High School Students by Implementing 8E Leaning Model

This research utilized the Physics at School application to utilize the Learning Cycle 8E model to explain students' conceptual mastery in class X SMA and identify any disparities in conceptual mastery for students in class X SMA. This kind of research uses a quantitative Nonequivalent Post-Test Control Group Design research design and a Quasi-Experimental research method. This research was performed at SMA Negeri 1 Teluk Kuantan. The aims of this research was to implement the Learning Cycle 8E model with assistance from the Physics at School program. In contrast, the second class uses conventional learning techniques as a control class. The data used in this research were concept mastery scores obtained from students who had learned physics using the Learning Cycle 8E model with assistance from the Physics at School program. Based on a descriptive and inferential examination of the data, it was found that the experimental class students' level of concept mastery increased by 73.08 points, while the control class was 69.70. Certainly, Learning Cycle 8E model, which is supported by the Physics at School application, has an impact on how well SMA Negeri 1 Teluk Kuantan children understand certain concepts.

Educational Board Game Design Based on Local Wisdom for Youth to Support Social Sustainability Learning

Social sustainability is the process of creating sustainable, successful places to offer prosperity by understanding what people need from where they live and work. In the 17 goals of the SDGs, social sustainability is reflected in the goals of the pillars of social development which include the goals of (1) no poverty, (2) no hunger, (3) healthy and prosperous life, (4) quality education, (5) gender equality. Adolescents who are the next generation must also begin to know the principles related to social sustainability. Besides, it is proven that people who play board games can absorb and memorize material more effectively than conventional learning techniques. This research resulted an educational board game design that collaborates on local wisdom performances from West Java as an adaptation of the Pagelaran Yogyakarta board game to generate revenue for solve social problems. The results obtained from the testing were an increase in the post-test score to 83.33 from the initial pre-test value of 52.38 and the average final result of the questionnaire on sustainability awareness was 3.19 from the initial average of 2.56. This indicates an increase in sustainability awareness, especially regarding social sustainability for adolescents from moderate to high levels.

Implementasi Strategi Pembelajaran pada Pembelajaran Bahasa Indonesia Kelas 3 SDN Cipondoh 3 Kota Tangerang

Indonesian is the language that our society uses to communicate, interact with other people. One of the important subjects taught is Indonesian at school. The problem with this research is that teachers use conventional learning techniques. The reason is that learning is not varied or interesting, it is still teacher-centered, and students still have difficulty understanding the concept of learning materials. Implementation of Indonesian language learning aims to find out strategies for learning Indonesian at SDN Cipondoh 3 Tangerang city. The research methodology which is a case study research takes a qualitative approach . This lesson was conducted in class 3 at SDN Cipondoh 3 Tangerang City. From the findings of this study it shoes that learning Indonesian in class 3 at SDN Cipondoh 3 Tangerang city is not optimal.

Perspectives of Medical Students on E-Learning in the Surgery Module

Objectives: The goal of this study was to explore medical students' perceptions, assess their experiences, and identify obstacles to e-learning during the COVID-19 pandemic, as well as to understand the factors behind its adoption and application as a learning means in the surgery module. Materials and Methods: Data were gathered from undergraduate medical students, at the University of Hail, KSA, in their surgery module using an electronic questionnaire. Subsequently, SPSS version 25.0 (IBM, Armonk, NY, USA) has been used for analysis. Results: The study included 72 students, with a participation rate of 85.7%. Students positively perceived technology (M = 4.024 ± 0.94 and P < 0.001). Most respondents (79.5%) claimed that e-learning required less time for studying than the conventional learning technique (M = 4.14 ± 1.052 and P < 0.001). They had positive perceptions of the implications of e-learning (M = 3.92 ± 0.89 and P < 0.001). Regarding the perception toward instructors, 53.9% admitted that when instructors use computer technologies, it adequately met their needs. The mean agreeability to online quizzes was high (M = 3.8264 ± 0.910). More than half preferred the blended style of learning. A-70.9% interested in using e-learning (M = 3.83 ± 1.278 and P < 0.001). There was no statistical difference among genders (P > 0.05). Conclusion: This study addresses the determinants behind the adoption and use of e-learning within the surgery module. Therefore, it will support the event of a rational approach to an effective application of e-learning and look at it as a positive initiative toward development and alteration.

Developing a Basketball Learning Model Using the Teaching Game for Understanding (TGfU) Approach to Improve the Effectiveness of HOTS in Elementary Schools

Study purpose. The researcher realizes that not all physical education teachers in elementary schools provide basketball lessons and some teachers still use conventional learning techniques. This study aims to determine the effectiveness of a basketball learning model with the TGfU approach to increase HOTS and reduce bullying.&#x0D; Materials and methods. This study used a quantitative approach to test the validity of the content and constructs as well as the effectiveness of the learning model. The experimental subjects in this study were fifth-grade students totaling 165 respondents from 5 elementary schools in Central Java, Indonesia. Data analysis of small-scale trials used Explanatory Factor Analysis (EFA) path analysis, and that of large-scale trials used Confirmatory Factor Analysis (CFA) path analysis. The paired-samples t-test was used to analyze the effectiveness of HOTS and the reduction of bullying.&#x0D; Results. The result of this study is a basketball learning model that utilizes the TGfU approach to increase HOTS and reduce bullying behavior in the form of a guidebook.&#x0D; Conclusions. The developed model can increase HOTS and reduce bullying and will affect students’ cognitive, affective and psychomotor learning outcomes. So that the learning model is easy, safe, and makes students more enthusiastic about learning.

An Adaptive Firefly Optimization (AFO) with Multi-Kernel SVM (MKSVM) Classification for Big Data Dimensionality Reduction

The data's dimensionality had already risen sharply in the last several decades. The "Dimensionality Curse" (DC) is a problem for conventional learning techniques when dealing with "Big Data (BD)" with a higher level of dimensionality. A learning model's performance degrades when there is a numerous range of features present. "Dimensionality Reduction (DR)" approaches are used to solve the DC issue, and the field of "Machine Learning (ML)" research is significant in this regard. It is a prominent procedure to use "Feature Selection (FS)" to reduce dimensions. Improved learning effectiveness such as greater classification precision, cheaper processing costs, and improved model comprehensibility are all typical outcomes of this approach that selects an optimal portion of the original features based on some relevant assessment criteria. An "Adaptive Firefly Optimization (AFO)" technique based on the "Map Reduce (MR)" platform is developed in this research. During the initial phase (mapping stage) the whole large "DataSet (DS)" is first subdivided into blocks of contexts. The AFO technique is then used to choose features from its large DS. In the final phase (reduction stage), every one of the fragmentary findings is combined into a single feature vector. Then the "Multi Kernel Support Vector Machine (MKSVM)" classifier is used as classification in this research to classify the data for appropriate class from the optimal features obtained from AFO for DR purposes. We found that the suggested algorithm AFO combined with MKSVM (AFO-MKSVM) scales very well to high-dimensional DSs which outperforms the existing approach "Linear Discriminant Analysis-Support Vector Machine (LDA-SVM)" in terms of performance. The evaluation metrics such as Information-Ratio for Dimension-Reduction, Accuracy, and Recall, indicate that the AFO-MKSVM method established a better outcome than the LDA-SVM method.

Improving students' pronouncing of Friction Consonants through dubbing Video at the first grade of SMA Negeri 1 Way Jepara

The current study aimed to find out whether the use of dubbing video technique could improve students' achievement of pronouncing the Friction consonants. It was conducted at the first grade students of SMAN 1 Way Jepara, in the academic year 2021/2022. The study was a quantitative approach with the design of true experimental where two classes (experimental and control classes) were involved (X IPA 1 and 2), each of which consisted of 30 students. The data were collected through the pretest and the post test in the form of friction consonants list for students to pronounce. The gain scores of both classes were compared using SPSS software 22. The results showed that i) dubbing video technique significantly improved the students' achievement of pronouncing friction consonants with significant level 0.05, and ii) there was statistically significant difference achievement of friction consonants between the students taught through dubbing technique and those through conventional learning method without dubbing video technique. The result showed that the students taught with dubbing video techniques had better achievement than those with conventional learning techniques. This suggests that dubbing technique facilitates students to improve their achievement of pronouncing friction consonant sounds.

A type-3 logic fuzzy system: Optimized by a correntropy based Kalman filter with adaptive fuzzy kernel size

In this study, a self-organizing interval type-3 fuzzy logic system (SO-IT3FLS) with a new learning algorithm is presented. An adaptive kernel size using fuzzy systems is introduced to improve the robustness of conventional correntropy based Kalman filters against non-Gaussian noise. The maximum correntropy Kalman filter (MCKF) and maximum correntropy unscented Kalman filter (MCUKF) with the proposed adaptive fuzzy kernel size are reformulated to optimize both rule and antecedent parameters, respectively. In addition to the rule parameters, the proposed membership function (MF) parameters and the level of α -cuts are also optimized. Five simulation examples with real-world data sets are given for examination. The simulations show that the introduced SO-IT3FLS and learning algorithm result in better accuracy in contrast to the other kind of fuzzy neural networks and conventional learning techniques. Furthermore, it is verified that the robustness of the proposed learning method against non-Gaussian noise is improved in contrast to the conventional Kalman filter, maximum correntropy Kalman filter and unscented Kalman filter.

Recalling the Definitions with a Mind Mapping and SelfLearning Technique: A Comparative Study in Undergraduate Students

Around 13.34% weightage is given to the definitions of university exams in nursing.1Nursing educatorsneed to help the students in memorizing terms, so that students can write the correct concept in the exameffectively.Aim: To assess the comparison of mind mapping and self-learning techniques in recalling thedefinition. Design : A comparative approach was used to understand the difference between the knowledgeof self-learning group and mind mapping group . Total 5 definitions were used from the nursing foundationtextbook .To obtain baseline data, subjects completed a short test and it is randomly allocated to two groups:‘self -learning’ and ‘mind map’. After a one hour of study period short test was taken. Recalling wasmeasured after a week later. Setting: Symbiosis College of Nursing, Symbiosis International University,India. Subjects : 48 First year Bachelor Nursing Students. Results: Mean score in Mind mapping groupwere 5.87 and 5 in session one and two . For self-learning group, the mean effect was 6.21and 4.67 in the firstand second sessions. Hence Mind mapping technique proven to be more effective than Self learning methodin recalling the definition. Two sample t-test for comparison of effect of Mind mapping vs self-learningmethod.t-values for this comparison were –0.76 and 0.62 . Corresponding p-values were 0.45 and 0.54 andthe p-value &lt; 0.05 , so the null hypothesis is rejected. Conclusion: mind maps were proved affectivity as away of recalling the definitions in the second session. Students need to be encouraged to adopt this approachmore than the other conventional learning techniques.

Strategi Dalam Pembelajaran Bahasa Indonesia Di Sekolah Dasar Daerah Terpencil Nusa Tenggara Timur (NTT)

Bahasa is one of the important materials taught in Indonesian schools for the important roles in our daily lives. The aim of this study is to determine the effectiveness of learning in a remote island in Flores. The method used is qualitative descriptive with a naturalistic approach and case study. This research was conducted in several places in a remote area on the island of Flores, East Nusa Tenggara. The result shows that Bahasa language learning in the remote area of Flores island is not maximal enough. Primary school teachers are still applying the conventional learning techniques and they do not want to be role models for the teaching-learning process.

THE USE OF MIND MAPPING TO TEACH READING COMPREHENSION

The research was aimed at finding out the impact of using mind mapping toward students’ reading comprehension. This study was classified as a quasi experimental research design using two intact classes as an experimental and control group. The experimental group was treated using mind-mapping technique, while the control group was subjected to conventional learning technique. The sample of this study was the first year students of Nabi’ Nubu’ Islamic Senior High School. The instrument of this study employed reading test for students in both groups. The reading tests were distributed in the pre-test and post-test. The data analysis used descriptive and inferential statistic. The data were met the normal and homogeneous data. The result of the study showed that the mean scores of the experimental group (71.76) was higher than the control group (60.24) after treatment was given. Thus, the use of mind mapping has a significant effect towards students’ reading comprehension. It indicated that the technique can be an alternative technique to teach reading comprehension.

An Empirical Evaluation of Deep Learning for Network Anomaly Detection

Deep learning has been widely studied in many technical domains such as image analysis and speech recognition, with its benefits that effectively deal with complex and high-dimensional data. Our preliminary experiments show a high degree of non-linearity from the network connection data, which explains why it is hard to improve the performance of identifying network anomalies by using conventional learning methods (e.g., Adaboosting, SVM, and Random Forest). In this study, we design and examine deep learning models constructed based on Fully Connected Networks (FCNs), Variational AutoEncoder (VAE), and Sequence-to-Sequence (Seq2Seq) structures. For the extensive evaluation, we employ a broad range of the public datasets with unique characteristics. Our experimental results confirm the feasibility of deep learning-based network anomaly detection, with the improved performance compared to the conventional learning techniques. In particular, the detection model based on Seq2Seq with LSTM is highly promising, consistently yielding over 99% of accuracy to identify network anomalies from the entire datasets employed in the evaluation.

THE EFFECT OF PROBLEM BASED LEARNING MODEL AND MATHEMATIC-LOGICAL INTELLIGENCE TOWARD MATHEMATICS LEARNING ACHIEVEMENT

This study aims to find out the difference between the model of problem-based learning and the mathematical-logical intelligence towards mathematics learning achievement. This study is a true experimental with specific design of post-test only control group design. The population of this study are all fourth grade students of primary schools in Bajawa sub district. Meanwhile, the sample in this study is determined through random sampling. The result of analysis, it is gained that the learning achievement which used problem based learning model is higher than the mathematics learning achievement of the students with the conventional learning technique. The calculation from two ways ANAVA results in Fobs 1.793 with sig = 0.184, there is no significant effect of learning interaction model and mathematic-logical intelligence. Since there is no interaction, it also means that there is no significant effect of problem based learning collaborated with mathematic-logical intelligence to the students’ learning achievement.

Efektifitas Mind Mapping Dalam Pembelajaran Kosakata Bahasa Jepang Pada Pemelajar Tingkat Dasar

Article clarified the research entitled 「「初級学習者における日本語の語彙学習においてのマイ ンド・マッピングの効果」which were translated as "The Effectiveness of Mind Mapping In JapaneseVocabulary Learning for A Basic Level Learners". In previous studies, mind mapping was tested on reading skill, but for this research it was focused on vocabulary with the assumption that the language learners usually got difficulties in learning both languages. Technique of mind mapping was tested on a two-semester student to find out the effectiveness of its techniques in learning Japanese vocabulary. This research used experimental methods. This design involved two groups of subjects. One group, as experimental group, was given the mind mapping learning technique, and the other group (the control group) was treated with the conventional learning techniques. Data were taken in two ways, the quantitative method was using instrument in the forms of pre test and post test on both sample class. The qualitative method applied interview to complete the descriptive data analysis. Then, the pre test and post test data were analyzed by measuring the normality of data and test-t to know to what extent the effectiveness of mind mapping techniques was successfully applied to the sample. To strengthen those results, the outcomes of interview was transcribed to see the sample’s responses in line with mind mapping techniques to the study of Japanese vocabulary. The research result indicates that mind mapping technique is proven more effective in learning Japanese vocabulary compared to the conventional way.

Prediction of protein-protein interactions using one-class classification methods and integrating diverse biological data

Summary This research addresses the problem of prediction of protein-protein interactions (PPI) when integrating diverse kinds of biological information. This task has been commonly viewed as a binary classification problem (whether any two proteins do or do not interact) and several different machine learning techniques have been employed to solve this task. However the nature of the data creates two major problems which can affect results. These are firstly imbalanced class problems due to the number of positive examples (pairs of proteins which really interact) being much smaller than the number of negative ones. Secondly the selection of negative examples can be based on some unreliable assumptions which could introduce some bias in the classification results.Here we propose the use of one-class classification (OCC) methods to deal with the task of prediction of PPI. OCC methods utilise examples of just one class to generate a predictive model which consequently is independent of the kind of negative examples selected; additionally these approaches are known to cope with imbalanced class problems. We have designed and carried out a performance evaluation study of several OCC methods for this task, and have found that the Parzen density estimation approach outperforms the rest. We also undertook a comparative performance evaluation between the Parzen OCC method and several conventional learning techniques, considering different scenarios, for example varying the number of negative examples used for training purposes. We found that the Parzen OCC method in general performs competitively with traditional approaches and in many situations outperforms them. Finally we evaluated the ability of the Parzen OCC approach to predict new potential PPI targets, and validated these results by searching for biological evidence in the literature.

점증적 학습 퍼지 신경망을 이용한 적응 분류 모델

분류 시스템은 데이터 전처리 모듈, 학습모듈, 의사결정모듈로 구성되어 있으며 지능형시스템의 중요한 구성요소로 활용되어왔다. 특히 학습모듈은 사전정보를 제공하므로 분류를 위한 핵심 역할을 수행하여 왔다. 기존의 학습을 위한 기법은 주로 승자독점방식으로 데이터를 처리하므로 경계가 불명확한 대부분의 실세계 응용에 적합하지 못하다. 또한 학습 알고리즘에 필요한 데이터를 한꺼번에 준비해야 하지만 이는 일반적으로 가능하지 않은 경우가 많다. 이를 위하여 본 논문에서는 점증적 학습 퍼지신경망, FNN-I,를 이용한 적응 분류모델을 설계한다. 이 모델에서는 유용하게 정보를 표현하기 위하여 퍼지이론을 도입하고 계속적으로 모여지는 데이터를 가지고 점증적으로 학습할 수 있는 알고리즘을 제시한다. 제안된 모델을 컴퓨터 바이러스 분류를 위한 실제 데이터에 적용하여 점증적으로 학습할 수 있고 효과적으로, 새로운 바이러스 데이터를 분류할 수 있음을 보인다. The design of a classification system generally involves data acquisition module, learning module and decision module, considering their functions and it is often an important component of intelligent systems. The learning module provides a priori information and it has been playing a key role for the classification. The conventional learning techniques for classification are based on a winner take all fashion which does not reflect the description of real data where boundarues might be fuzzy Moreover they need all data for the learning of its problem domain. Generally, in many practical applications, it is not possible to prepare them at a time. In this paper, we design an adaptive classification model using incremental training fuzzy neural networks, FNN-I. To have a more useful information, it introduces the representation and membership degree by fuzzy theory. And it provides an incremental learning algorithm for continuously gathered data. We present tie experimental results on computer virus data. They show that the proposed system can learn incrementally and classify new viruses effectively.

Selective presentation learning for neural network forecasting of stock markets

This paper proposes a selective presentation learning technique for improving the learnability and predictability of large changes by back-propagation neural networks. Daily stock prices are predicted as a complicated real-world problem, taking non-numerical factors such as political and international events into account. Training data corresponding to large changes of prediction-target time series are presented more often, and network learning is stopped at the point that has the maximal profit. When this technique is applied to daily stock-price prediction, the prediction error on large-change data was reduced by 11%, and the network's ability to make profits through experimental stock-trading was improved by 67% to 81%, in comparison with results obtained using conventional learning techniques.

Computer-assisted instruction: MR imaging of the knee.

Computer-assisted education offers a unique method of learning that is complementary to conventional learning techniques. The regional anatomy of musculoskeletal magnetic resonance (MR) imaging lends itself well to discrete learning modules on the computer. This article describes a computer-assisted educational program for MR imaging of the knee. The program is divided into four sections: MR imaging physics, anatomy, pathology, and a quiz. The program has cross-references between the sections that allow comparison of normal versus pathologic findings, review of specified pathologic entities, and self-testing of comprehension. The student can progress through the program in a linear or nonlinear fashion at his or her own pace. All images in the program were digitally acquired with an MR imager and transferred directly to the computer used to develop the program. The program is available throughout the radiology department on a local area network and in the medical school library on stand-alone units. The program is currently being used at a medical school as a supplement to the recently implemented problem-based learning curriculum and for resident education.