Learning Problems Research Articles

Penerapan Model Discovery Learning Menggunakan Pendekatan Saintifik Untuk Meningkatkan Keaktifan Belajar IPA Peserta Didik Kelas V SDN 109/II Manggis Kabupaten Bungo

The learning process in the 2013 curriculum is carried out with students being the center of learning, so that students have a role to be able to be more active in the learning process. Natural Sciences (IPA) is learning content related to the process of searching for something systematically and in accordance with the results of discoveries. Science learning is not just about learning concepts, principles or mastery of knowledge in the form of facts, but in science it is known as the process of discovery. Based on the results of initial observations carried out at SDN 109/II Manggis Kab. Bungo on January 20 2022 obtained information related to the learning process in the science learning content in class V which was carried out at the school, which did not show that all students were actively involved in the learning process. The type of data used is Classroom Action Research (PTK) using qualitative and quantitative data. The subjects in this research were all students and teachers of class V at SDN 103/II Manggis, Bungo Regency, even semester of the 2023/2024 academic year. Data collection using interviews is a data collection technique carried out to obtain in-depth information from sources. Based on the results of the research, it shows that through the application of the Discovery Learning model with a Scientific Approach, it has a good impact on increasing students' learning activeness in science content, as can be seen from the increase in students' learning activeness in science from pre-action, namely by 23.07% until at the end of cycle II it increased to 84 .61%. Increasing students' learning activity occurs periodically from cycle I to cycle II by applying the Discovery Learning model syntax, namely stimulation, problem statement (problem identification), data collection, data processing, verification (proof) and generalization (drawing conclusions) and the Scientific Approach with the elements of observing, asking, collecting information/trying, reasoning/associating and communicating.

A Review on Rainfall Nowcasting Methodology using different ML and DL Models

Weather is influenced by several factors such as temperature, pressure, air movement, moisture/water vapor, and the Earth's rotation. Forecasting weather with high geographic precision is both challenging and computationally demanding. This study explores a nowcasting method for meteorological radar images. Building on the concept of an unsupervised representation problem in deep learning, next-frame prediction is an emerging area in computer vision where future images are predicted based on previous ones. This has numerous applications, including in robotics and autonomous driving. The paper reviews the latest next-frame prediction networks, categorizing them into two main approaches: machine learning and deep learning. It compares these strategies by discussing their respective advantages and disadvantages. Lastly, the paper outlines the most promising directions for future research.

Problems of Inclusive Learning in Fostering Entrepreneurial Motivation in Students with Disabilities: Systematic Literature Review (SLR)

Problems of Inclusive Learning in Fostering Entrepreneurial Motivation in Students with Disabilities: Systematic Literature Review (SLR)

An explainable dual-mode convolutional neural network for multivariate time series classification

Multivariate time series classification (MTSC) is a crucial machine learning problem prevalent across various real-life domains. Traditional deep learning approaches with high accuracy in MTSC are often criticized for their “black box” nature, offering no insight into their operational mechanisms or decision-making processes. Explainable artificial intelligence (XAI) becomes a key idea for dealing with such limitations in decision-sensitive areas. While some researchers have explored the interpretability of MTSC, the majority have focused on elucidating the relationship between variables over time, neglecting the intricate connections among different variables. To address the interpretability issue in MTSC, we introduce an explainable dual-mode convolutional neural network (XDM-CNN) designed specifically for MTSC. The proposed XDM-CNN framework comprises two modules: a classification module and an explanation module. The classification module can ensure exceptional classification performance by combining both one-dimensional and two-dimensional convolutional neural networks, while the explanation module can mine the underlying logical relationships among variables during the classification process by utilizing a synergy of visualization and quantification techniques. We validate our approach using 26 datasets sourced from the University of East Anglia (UEA) archive. The experimental results demonstrate that XDM-CNN not only exhibits excellent performance in classification accuracy, but also has strong explainability. By combining visual and numerical explanation, the hidden logical relationships among multivariate time series are explored and interpreted, providing human users with a decidable basis for classification decisions.

Application of Transformers in Cheminformatics.

By accelerating time-consuming processes with high efficiency, computing has become an essential part of many modern chemical pipelines. Machine learning is a class of computing methods that can discover patterns within chemical data and utilize this knowledge for a wide variety of downstream tasks, such as property prediction or substance generation. The complex and diverse chemical space requires complex machine learning architectures with great learning power. Recently, learning models based on transformer architectures have revolutionized multiple domains of machine learning, including natural language processing and computer vision. Naturally, there have been ongoing endeavors in adopting these techniques to the chemical domain, resulting in a surge of publications within a short period. The diversity of chemical structures, use cases, and learning models necessitate a comprehensive summarization of existing works. In this paper, we review recent innovations in adapting transformers to solve learning problems in chemistry. Because chemical data is diverse and complex, we structure our discussion based on chemical representations. Specifically, we highlight the strengths and weaknesses of each representation, the current progress of adapting transformer architectures, and future directions.

“Intelligent tutoring effects on induced emotions and cognitive load of learning-disabled learners”

Purpose This study addresses the learning requirements of learners with learning difficulties by monitoring their learning experience in an Intelligent Tutoring System. Intelligent Tutoring Systems were developed to enrich the teaching-learning process. Materials and Methods In the present work, the interface is designed and developed utilizing the potential of Artificial Intelligence to meet their individual needs. Designing an online learning platform for a learners with learning difficulties requires consideration of their learning problems and preferences. The interface was developed focusing on all the requirements of the LD learners. The objective of the present study is to monitor the learning experience in the form of induced emotions and cognitive load of the learners to determine the impact of learning. Results 83 learners were observed during various stage of learning. The results obtained through the Support Vector machine (SVM) classification technique showed the positive attitude towards intelligent tutoring. The analysis revealed that a total of 0.23% of learners were positively induced. Their learning experience was positive and effective. The cognition load on learners was minimum with single-mode instruction and least disturbed. Conclusions The system was improved based on preference feedback on design features. This helps in improving content design and creating device independent and responsive visual design. The fatigue effect analysis on cognitive load implied that multiple modes of instruction increased drowsiness. Single mode of instruction have a positive impact on the learning process and it reduces the cognitive load of the learners. Implications for Rehabilitation The user interface designed and developed for learners with Dyslexia, Dysgraphia and Dyscalculia has learning disabled-friendly features. These can be used to create a device-independent and responsive design. Learning experience is monitored along with the impact on cognitive load of the learners. The research helps in understanding the stimulation and response of learners with learning disability for different learning conditions. Most existing learning systems are limited to non-learning-disabled learners. The ITS developed during research presents a Universal learning design helpful for all learners with and without learning disability.

Pendekatan, Strategi dan Teknik Bimbingan Konseling dalam Mengatasi Permasalahan Sosial Remaja

This article aims to find out what approaches, strategies and techniques for guidance and counseling are good and correct in dealing with adolescent social problems. This research was conducted using qualitative methods, where researchers distributed forms containing questions to respondents. In this research, there were two respondents who were the targets of the research, namely high school students and guidance and counseling teachers. The data collection method that the researcher took was the method of non-participant observation and literature review, where the observer was outside the subject being studied and did not participate in the activities they carried out. This research measures all the domains that exist in students in dealing with personal, social, learning and career problems, and their relationship with how a teacher knows the behavior of each individual in the learning process. So that a teacher can direct his students to be able to face every problem. The results of this research explain that a student initially has a high level of trust in providing counseling to a counseling teacher at their respective school, but not all of these teachers have a good impact on students who do counseling. There are still many guidance and counseling teachers who do not know how to respond and how to communicate well with the students who are counseling with them. And then this creates a feeling of discomfort for students so that they no longer have a sense of trust in the guidance and counseling teacher.

Skeleton-aware Graph-based Adversarial Networks for Human Pose Estimation from Sparse IMUs

Recently, sparse-inertial human pose estimation (SI-HPE) with only a few IMUs has shown great potential in various fields. The most advanced work in this area achieved fairish results using only six IMUs. However, there are still two major issues that remain to be addressed. First, existing methods typically treat SI-HPE as a temporal sequential learning problem and often ignore the important spatial prior of skeletal topology. Second, there are far more synthetic data in their training data than real data, and the data distribution of synthetic data and real data is quite different, which makes it difficult for the model to be applied to more diverse real data. To address these issues, we propose “Graph-based Adversarial Inertial Poser (GAIP)”, which tracks body movements using sparse data from six IMUs. To make full use of the spatial prior, we design a multi-stage pose regressor with graph convolution to explicitly learn the skeletal topology. A joint position loss is also introduced to implicitly mine spatial information. To enhance the generalization ability, we propose supervising the pose regression with an adversarial loss from a discriminator, bringing the ability of adversarial networks to learn implicit constraints into full play. Additionally, we construct a real dataset that includes hip support movements and a synthetic dataset containing various motion categories to enrich the diversity of inertial data for SI-HPE. Extensive experiments demonstrate that GAIP produces results with more precise limb movement amplitudes and relative joint positions, accompanied by smaller joint angle and position errors compared to state-of-the-art counterparts. The datasets and codes are publicly available at https://cslinzhang.github.io/GAIP/ .

Education Model for Paediatric Palliative Care

Introduction: Meeting the palliative care needs of children and their families is complex and challenging. For countries such as Australia, whose relatively small paediatric palliative care population is dispersed across a very large geographical area, one challenge is maintaining a skilled workforce in regional, rural, and remote areas, where, when compared to major cities, there are fewer resources, and the workforce is often transient. Methods: The Quality of Care Collaborative Australia (QuoCCA) Pop-up Model of Education was used to provide palliative care education to health professionals across three geographical locations and facilities, to facilitate a 2,500-km transfer of a child with complex palliative care needs from a tertiary hospital to the remote family home on Country. Results: Each Pop-Up provided effective education to facilitate the successful transfer of the child to the next hospital location. Over 18 months, three Pop-Ups occurred. Relational learning and real-time problem solving enabled health professionals to build confidence and capacity to successfully transfer the child from the regional hospital to the remote family home. Implications: The QuoCCA Education Pop-up Model is a feasible method to deliver timely access to speciality education. The model can be successfully applied in multiple settings. Keywords: paediatric, palliative care, integrated health care delivery, learning, rural, education models.

Deep deductive reasoning is a hard deep learning problem

Deep Deductive Reasoning refers to the training and then executing of deep learning systems to perform deductive reasoning in the sense of formal, mathematical logic. We discuss why this is an interesting and relevant problem to study, and explore how hard it is as a deep learning problem. In particular, we present some of the progress made on this topic in recent years, understand some of the theoretical limitations that can be assessed from existing literature, and discuss negative results we have obtained regarding improving on the state of the art.

MRME-Net: Towards multi-semantics learning and long-tail problem of efficient event detection from social messages

Discovering trending social events (e.g., major meetings, political scandals, natural disasters, etc.) from social messages is vital because it emphasizes important events and can help people comprehend the world. However, the heterogeneous semantics enrichment, severe long-tail problems, and sparse text contents of social messages pose great challenges to event detection, often leading to limited generalization ability and accuracy. In this paper, we propose a novel Multi-Relational Meta-Enhanced Network (MRME-Net) architecture to learn social events. First, we model social messages into a multi-relational message graph, incorporating abundant meta-semantics along with various meta-relations. Second, we present a multi-relational graph attention network based on Sophia by using a dual-step message aggregation mechanisms to capture the local features of neighboring messages and global semantics of mutiple relations and ultimately learn social message embeddings. We use Sophia optimizer to reduce the massive time and cost of training. Third, in order to address the long-tail problem, we introduce a locally-adapted meta-learning framework in social event detection for the first time and propose a novel META-TAILENH embedding enhancement strategy to refine tail node embeddings in multi-relational graph. Eventually, we conduct the detection of social events according to the hierarchical clustering algorithm. Extensive experiments have been carried out to evaluate MRME-Net on the MAVEN and Twitter dataset, revealing a notable improvement of 3 %–13 %, 4 %–20 % and 6 %–30 % increases on NMI, AMI and ARI in the social event detection task.

AIGO-DTI: Predicting Drug-Target Interactions Based on Improved Drug Properties Combined with Adaptive Iterative Algorithms.

Artificial intelligence-based methods for predicting drug-target interactions (DTIs) aim to explore reliable drug candidate targets rapidly and cost-effectively to accelerate the drug development process. However, current methods are often limited by the topological regularities of drug molecules, making them difficult to generalize to a broader chemical space. Additionally, the use of similarity to measure DTI network links often introduces noise, leading to false DTI relationships and affecting the prediction accuracy. To address these issues, this study proposes an Adaptive Iterative Graph Optimization (AIGO)-DTI prediction framework. This framework integrates atomic cluster information and enhances molecular features through the design of functional group prompts and graph encoders, optimizing the construction of DTI association networks. Furthermore, the optimization of graph structure is transformed into a node similarity learning problem, utilizing multihead similarity metric functions to iteratively update the network structure to improve the quality of DTI information. Experimental results demonstrate the outstanding performance of AIGO-DTI on multiple public data sets and label reversal data sets. Case studies, molecular docking, and existing research validate its effectiveness and reliability. Overall, the method proposed in this study can construct comprehensive and reliable DTI association network information, providing new graphing and optimization strategies for DTI prediction, which contribute to efficient drug development and reduce target discovery costs.

Loss-optimal classification trees: a generalized framework and the logistic case

Classification trees are one of the most common models in interpretable machine learning. Although such models are usually built with greedy strategies, in recent years, thanks to remarkable advances in mixed-integer programming (MIP) solvers, several exact formulations of the learning problem have been developed. In this paper, we argue that some of the most relevant ones among these training models can be encapsulated within a general framework, whose instances are shaped by the specification of loss functions and regularizers. Next, we introduce a novel realization of this framework: specifically, we consider the logistic loss, handled in the MIP setting by a piece-wise linear approximation, and couple it with ℓ1\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\ell _1$$\\end{document}-regularization terms. The resulting optimal logistic classification tree model numerically proves to be able to induce trees with enhanced interpretability properties and competitive generalization capabilities, compared to the state-of-the-art MIP-based approaches.

Ship-Radiated Noise Separation in Underwater Acoustic Environments Using a Deep Time-Domain Network

Ship-radiated noise separation is critical in both military and economic domains. However, due to the complex underwater environments with multiple noise sources and reverberation, separating ship-radiated noise poses a significant challenge. Traditionally, underwater acoustic signal separation has employed blind source separation methods based on independent component analysis. Recently, the separation of underwater acoustic signals has been approached as a deep learning problem. This involves learning the features of ship-radiated noise from training data. This paper introduces a deep time-domain network for ship-radiated noise separation by leveraging the power of parallel dilated convolution and group convolution. The separation layer employs parallel dilated convolution operations with varying expansion factors to better extract low-frequency features from the signal envelope while preserving detailed information. Additionally, we use group convolution to reduce the expansion of network size caused by parallel convolution operations, enabling the network to maintain a smaller size and computational complexity while achieving good separation performance. The proposed approach is demonstrated to be superior to the other common networks in the DeepShip dataset through comprehensive comparisons.

Simultaneous Determination of Four Catechins in Black Tea via NIR Spectroscopy and Feature Wavelength Selection: A Novel Approach.

As a non-destructive, fast, and cost-effective technique, near-infrared (NIR) spectroscopy has been widely used to determine the content of bioactive components in tea. However, due to the similar chemical structures of various catechins in black tea, the NIR spectra of black tea severely overlap in certain bands, causing nonlinear relationships and reducing analytical accuracy. In addition, the number of NIR spectral wavelengths is much larger than that of the modeled samples, and the small-sample learning problem is rather typical. These issues make the use of NIRS to simultaneously determine black tea catechins challenging. To address the above problems, this study innovatively proposed a wavelength selection algorithm based on feature interval combination sensitivity segmentation (FIC-SS). This algorithm extracts wavelengths at both coarse-grained and fine-grained levels, achieving higher accuracy and stability in feature wavelength extraction. On this basis, the study built four simultaneous prediction models for catechins based on extreme learning machines (ELMs), utilizing their powerful nonlinear learning ability and simple model structure to achieve simultaneous and accurate prediction of catechins. The experimental results showed that for the full spectrum, the ELM model has better prediction performance than the partial least squares model for epicatechin (EC), epicatechin gallate (ECG), epigallocatechin (EGC), and epigallocatechin gallate (EGCG). For the feature wavelengths, our proposed FIC-SS-ELM model enjoys higher prediction performance than ELM models based on other wavelength selection algorithms; it can simultaneously and accurately predict the content of EC (Rp2 = 0.91, RMSEP = 0.019), ECG (Rp2 = 0.96, RMSEP = 0.11), EGC (Rp2 = 0.97, RMSEP = 0.15), and EGCG (Rp2 = 0.97, RMSEP = 0.35) in black tea. The results of this study provide a new method for the quantitative determination of the bioactive components of black tea.

A novel deep machine learning algorithm with dimensionality and size reduction approaches for feature elimination: thyroid cancer diagnoses with randomly missing data.

Thyroid cancer incidences endure to increase even though a large number of inspection tools have been developed recently. Since there is no standard and certain procedure to follow for the thyroid cancer diagnoses, clinicians require conducting various tests. This scrutiny process yields multi-dimensional big data and lack of a common approach leads to randomly distributed missing (sparse) data, which are both formidable challenges for the machine learning algorithms. This paper aims to develop an accurate and computationally efficient deep learning algorithm to diagnose the thyroid cancer. In this respect, randomly distributed missing data stemmed singularity in learning problems is treated and dimensionality reduction with inner and target similarity approaches are developed to select the most informative input datasets. In addition, size reduction with the hierarchical clustering algorithm is performed to eliminate the considerably similar data samples. Four machine learning algorithms are trained and also tested with the unseen data to validate their generalization and robustness abilities. The results yield 100% training and 83% testing preciseness for the unseen data. Computational time efficiencies of the algorithms are also examined under the equal conditions.

Trustworthy Precision Medicine: An Interpretable Approach to Detecting Anomalous Behavior of IoT Devices.

The growing integration of Internet of Things (IoT) technology within the healthcare sector has revolutionized healthcare delivery, enabling advanced personalized care and precise treatments. However, this raises significant challenges, demanding robust, intelligible, and effective monitoring mechanisms. We propose an interpretable machine-learning approach to the trustworthy and effective detection of behavioral anomalies within the realm of medical IoT. The discovered anomalies serve as indicators of potential system failures and security threats. Essentially, the detection of anomalies is accomplished by learning a classifier from the operational data generated by smart devices. The learning problem is dealt with in predictive association modeling, whose expressiveness and intelligibility enforce trustworthiness to offer a comprehensive, fully interpretable, and effective monitoring solution for the medical IoT ecosystem. Preliminary results show the effectiveness of our approach.

Joint learning of reward machines and policies in environments with partially known semantics

We study the problem of reinforcement learning for a task encoded by a reward machine. The task is defined over a set of properties in the environment, called atomic propositions, and represented by Boolean variables. One unrealistic assumption commonly used in the literature is that the truth values of these propositions are accurately known. In real situations, however, these truth values are uncertain since they come from sensors that suffer from imperfections. At the same time, reward machines can be difficult to model explicitly, especially when they encode complicated tasks. We develop a reinforcement-learning algorithm that infers a reward machine that encodes the underlying task while learning how to execute it, despite the uncertainties of the propositions' truth values. In order to address such uncertainties, the algorithm maintains a probabilistic estimate about the truth value of the atomic propositions; it updates this estimate according to new sensory measurements that arrive from exploration of the environment. Additionally, the algorithm maintains a hypothesis reward machine, which acts as an estimate of the reward machine that encodes the task to be learned. As the agent explores the environment, the algorithm updates the hypothesis reward machine according to the obtained rewards and the estimate of the atomic propositions' truth value. Finally, the algorithm uses a Q-learning procedure for the states of the hypothesis reward machine to determine an optimal policy that accomplishes the task. We prove that the algorithm successfully infers the reward machine and asymptotically learns a policy that accomplishes the respective task.

Improving Thinking Skills Through Usul Al-Fiqh Learning: An Action Research on Prospective Islamic Religious Education Teachers

As part of the study of Islamic law, ushul fiqh demands that one be able to practically handle religious issues by using the ulama's defined principles of Islamic law. Applying Islamic legal theory practically calls for critical thinking abilities. Therefore, this research aims to find a learning formulation in Ushul fiqh that integrates efforts to improve thinking skills. To achieve this goal, action research was chosen as a research design which was carried out in three research stages, namely pre action, implementation action and post action. This design was chosen considering that the context of this research is oriented towards finding solutions to learning problems. This research involved 35 prospective Islamic religious education teachers who took Ushul Fiqh courses from one of the government-owned Islamic universities, which is quite popular in Indonesia. Data was collected through surveys and semi-structured interviews which were analyzed using a descriptive quantitative approach and qualitative with content analysis. This research produced seven stages as learning formulations that need to be implemented in the ushul fiqh learning process. The study concludes that the proposed seven steps effectively elevate students' thinking skills to the Higher Order Thinking Skills (HOTS) level while applying usul al-fiqh principles. The findings suggest a promising pedagogical approach for cultivating advanced thinking skills within the context of Islamic law education. The main contribution of this study is to present a practical methodological guide regarding the steps for teaching usul fiqh, which is oriented toward improving students' thinking skills.

Analisis Penyebab dan Strategi Pencegahan Perilaku Menyontek pada Siswa/i di SMP Negeri 35 Medan

This research aims to find out the causes and strategies for preventing cheating among students at SMP Negeri 35 Medan. This research uses qualitative research methods using books and journals as additional references. This research was conducted by SMP N 35 Pecut Sei Tuan, North Sumatra. The results of the research show that cheating behavior still often occurs among students at SMP Negeri 35 Medan. This is motivated by the lack of concern from teachers, schools and parents regarding learning problems, especially cheating behavior, and also because there is pressure on students to get good grades. Thus, it has a negative impact on students' academic and moral development. Therefore, it is necessary to carry out various strategies including group guidance, and collaboration with subject teachers and homeroom teachers, individual guidance, and learning counseling in reducing students' cheating behavior at school.