Model Of Learning System Research Articles

Classifying central serous chorioretinopathy subtypes with a deep neural network using optical coherence tomography images: a cross-sectional study

Central serous chorioretinopathy (CSC) is the fourth most common retinopathy and can reduce quality of life. CSC is assessed using optical coherence tomography (OCT), but deep learning systems have not been used to classify CSC subtypes. This study aimed to build a deep learning system model to distinguish CSC subtypes using a convolutional neural network (CNN). We enrolled 435 patients with CSC from a single tertiary center between January 2015 and January 2020. Data from spectral domain OCT (SD-OCT) images of the patients were analyzed using a deep CNN. Five-fold cross-validation was employed to evaluate the model’s ability to discriminate acute, non-resolving, inactive, and chronic atrophic CSC. We compared the performances of the proposed model, Resnet-50, Inception-V3, and eight ophthalmologists. Overall, 3209 SD-OCT images were included. The proposed model showed an average cross-validation accuracy of 70.0% (95% confidence interval [CI], 0.676–0.718) and the highest test accuracy was 73.5%. Additional evaluation in an independent set of 104 patients demonstrated the reliable performance of the proposed model (accuracy: 76.8%). Our model could classify CSC subtypes with high accuracy. Thus, automated deep learning systems could be useful in the classification and management of CSC.

Artificial Intelligence and Internet of Things (AI-IoT) Technologies in Response to COVID-19 Pandemic: A Systematic Review

The origin of the COVID-19 pandemic has given overture to redirection, as well as innovation to many digital technologies. Even after the progression of vaccination efforts across the globe, total eradication of this pandemic is still a distant future due to the evolution of new variants. To proactively deal with the pandemic, the health care service providers and the caretaker organizations require new technologies, alongside with improvements in existing related technologies, Internet of Things (IoT), Artificial Intelligence (AI), and Machine Learning in terms of infrastructure, efficiency, privacy, and security. This paper provides an overview of current theoretical and application prospects of IoT, AI, cloud computing, edge computing, deep learning techniques, blockchain technologies, social networks, robots, machines, privacy, and security techniques. In consideration of these prospects in intersection with COVID-19 pandemic, we reviewed the technologies within the broad umbrella of AI-IoT technologies in the most concise classification scheme. In this review, we illustrated that AI-IoT technological applications and innovations have most impacted the field of healthcare. The essential AI-IoT technologies found for healthcare were fog computing in IoT, deep learning, and blockchain. Furthermore, we highlighted several aspects of these technologies and their future impact with a novel methodology of using techniques from image processing, machine learning and differential system modeling.

Personalized feedback in digital learning environments: Classification framework and literature review

Digital learning technologies offer many opportunities to personalize instruction and learning in K-12 and higher education. In the last ten years, a growing body of research described personalized feedback implementations and investigated their effects on educational outcomes. Building on personalized education and adaptive learning systems models, this review provides an analytic framework to summarize key features of personalized feedback implementations and main empirical results. The systematic literature search resulted in 39 studies published in the last ten years. We found that scholars developed and investigated personalized feedback on the microscale, mesoscale, and macroscale of digital learning environments. However, the adaptive sources (To what is feedback adapted?) are mainly restricted to the current knowledge level and learning behavior data. Other interesting data sources for feedback adaptation remain underresearched, e.g., emotional state measures, progress measures, learning goals, or personality traits. Only a minority of the reviewed studies provided an empirical or theoretical rationale for assigning feedback messages to different types of students. Most studies report positive or at least mixed or neutral effects of personalized feedback on educational outcomes. This review discusses several implications for future directions in research on digitalized and personalized feedback. This study also adds to previous literature reviews on automatic and adaptive feedback that did not clearly distinguish task-adaptiveness and student-adaptiveness in digital feedback examples.

Recommendation Learning System Model for Children with Autism

Autism spectrum disorder (ASD), is a neurological developmental disorder. It affects how people communicate and interact with others, as well as how they behave and learn. The symptoms and signs appear when a child is very young. Derived with increased usage of machine learning procedure in the medicinal analysis investigations. In this paper, our objective is to find out the most significant attributes and automate the process using classification techniques and pattern clustering using K-means clustering. We have analyzed ASD datasets of children towards determining the best performance of classifier for these binary datasets considering recall, precision, accuracy and classification errors. For this purpose only we use classifier along with a training model with the deep learning technique. In this deep neural network the different types of patterns have been obtained, and then the entire autism dataset has been trained using this classification technique. After that, the group of patterns has been formed using K- means clustering technique. Then these grouped patterns have been sent to the stochastic gradient descent (SGD) for obtaining the classification with enhanced accuracy, and after this, the regression process is done, then by this classified output, the recommendation learning system model is given for autism affected children. The need for recommendation for ASD is due to slow functioning of the brain and change in personal characteristic of the affected children, so it is necessary for recommendation learning model in ASD.

FEATURES OF CONTENT PRESENTATION IN MULTI-SCENARIO SYSTEMS

When software is developed, it is assumed that it can be used by different groups of users. The difference between these groups may be not only in the level of technical qualifications, but also in physiological and psychological differences, features of hardware, software, environment, and so on. Lead to the need of creation of the universal interface that can suit all users. Due to the fact that all users are different, this problem has no solution and in fact the interface corresponds to the property "least inconvenient" instead of "most convenient". The problem of adapting software and hardware to the conditions of use is solved by each team of developers with their own methods, but the approach to analyzing the problem and solutions is almost the same and comes down to building scenarios for the use of hardware and software. The article represent a general approach to the creation of multi-scenario systems for various purposes - electronic educational systems, hardware educational systems for the visually impaired, medical diagnostic systems. The following problems of development were solved in the article: adaptive intelligent interface, architecture and structure of adaptive intelligent interface and algorithms of functioning of adaptive system interface agents. The presented examples of hardware and software solutions, and the visualization of the model of the adaptive learning system will allow to develop own algorithms for the implementation of multi-scenario systems.

DenseNet-CNN Architectural Model for Detection of Abnormality in Acute Pulmonary Edema

Acute pulmonary edema (EPA) is a condition of emergency respiratory distress that results from the sudden and rapid build-up of fluid into the lungs. Rapid screening of EPA patients is necessary so that radiologists can make the prognosis as early as possible. In addition, reliance on the expert's knowledge of reasoning also hinders the diagnostic process. This research proceeded by developing an architectural model for machine learning systems with a deep learning approach. With the concept of representative learning, the denseNet-CNN algorithm connects each layer to another utilizing a feed-forward. The data used is Image CXR-14 that is specifically labeled pulmonary edema pathology. Each CXR-14 image is 1024 × 1024 in size with a value of 8 bits grayscale. The architectural model development consists of several stages: the preparation stage, data resampling, data training, and data testing. Optimizer parameters used are Adam's optimizer, a learning rate of 0.0001, weight decay = 1e-5, and the loss used is binary cross-entropy. The resulting mean of AUROC analysis showed that the sensitivity value of the 10% dataset was 71.493%, and the specificity value of 10.011% was obtained at the second hold of the k-fold cross-validation method after holdout validation so that the resulting model was valid. The detection system developed from the denseNet-CNN model is to expectedly help radiologists identify abnormalities in CXR images quickly, precisely, and consistently. The development of the denseNet CNN model is in the form of a heatmap visualization by localizing the features one is watching. With localization in the heat map form, pathological abnormalities detection of PEA is easier to do and recognize.

Call for Papers on Machine Learning and Earth System Modeling

Contributions are invited to a new journal special collection on the use of new machine learning methodologies and applications of machine learning to Earth system modeling.

A federated bidirectional connection broad learning scheme for secure data sharing in Internet of Vehicles

Data sharing in Internet of Vehicles (IoV) makes it possible to provide personalized services for users by service providers in Intelligent Transportation Systems (ITS). As IoV is a multi-user mobile scenario, the reliability and efficiency of data sharing need to be further enhanced. Federated learning allows the server to exchange parameters without obtaining private data from clients so that the privacy is protected. Broad learning system is a novel artificial intelligence technology that can improve training efficiency of data set. Thus, we propose a federated bidirectional connection broad learning scheme (FeBBLS) to solve the data sharing issues. Firstly, we adopt the bidirectional connection broad learning system (BiBLS) model to train data set in vehicular nodes. The server aggregates the collected parameters of BiBLS from vehicular nodes through the federated broad learning system (FedBLS) algorithm. Moreover, we propose a clustering FedBLS algorithm to offload the data sharing into clusters for improving the aggregation capability of the model. Some simulation results show our scheme can improve the efficiency and prediction accuracy of data sharing and protect the privacy of data sharing.

THE INFLUENCE OF THINK PAIR SHARE (TPS) AS A COOPERATIVE LEARNING MODEL IN IMPROVING HEALTH INFORMATION MANAGEMENT STUDENTS’ SKILL AT DELI HUSADA DELI TUA HEALTH INSTITUTE ON TOEFL TEST

TOEFL is categorized as a Norm-Referenced Test because scores are associated based on tiered counts or has percentage stages. Based on an initial survey, the biggest difficulty of TOEFL is known having high difficulty level. Think Pair Share (TPS) as a cooperative learning model for more effective learning system in providing and improving communication skills both orally and written within the scope of academic understanding through TOEFL. The application of TPS is expected to increase student's TOEFL score, learning quality and provide the opportunity to find out strategies on TOEFL success and further develop students’ skill. TPS is a type of cooperative learning designed in the form of discussion that can improve thinking skills, communication skills and encourage student participation in class. This research is aimed to improve the ability of Health Information Management students in facing TOEFL test by applying the cooperative learning model Think Pair Share (TPS). After applying the model, it found that the average score of students' TOEFL scores as well has increased from previously 56.93 to 83.68. This can be seen during the English learning process in the classroom. In learning by using Think Pair Share (TPS) model, students are required to discuss simple and effective ways to solve TOEFL questions with their friends by expressing the result of his thoughts.

Construction of a quality model for machine learning systems

Nowadays, systems containing components based on machine learning (ML) methods are becoming more widespread. In order to ensure the intended behavior of a software system, there are standards that define necessary qualities of the system and its components (such as ISO/IEC 25010). Due to the different nature of ML, we have to re-interpret existing qualities for ML systems or add new ones (such as trustworthiness). We have to be very precise about which quality property is relevant for which entity of interest (such as completeness of training data or correctness of trained model), and how to objectively evaluate adherence to quality requirements. In this article, we present how to systematically construct quality models for ML systems based on an industrial use case. This quality model enables practitioners to specify and assess qualities for ML systems objectively. In addition to the overall construction process described, the main outcomes include a meta-model for specifying quality models for ML systems, reference elements regarding relevant views, entities, quality properties, and measures for ML systems based on existing research, an example instantiation of a quality model for a concrete industrial use case, and lessons learned from applying the construction process. We found that it is crucial to follow a systematic process in order to come up with measurable quality properties that can be evaluated in practice. In the future, we want to learn how the term quality differs between different types of ML systems and come up with reference quality models for evaluating qualities of ML systems.

Developing Blended Learning Teaching Model through Online Social Media Platform as Learning’s Support

Technology develops rapidly and it affects the technology development at physical, health, and recreation education study program of IKIP Budi Utomo as this year they uses combination learning approach. Students can study anywhere, anytime, and with whomever. To support the current availability of the facilities, the lecturers are required to develop various learning plan models which are easy and comprehensive; one of them is Blended Learning Model. The objective of this research is to develop blended learning model teaching scenario plan and develop blended learning application using social media as the media to ease the teaching and learning process. Online social media were chosen as the basic platform to distribute learning materials and communicate online because of the determinations of usage affordability, effectiveness, and familiarity. The development of blended learning scenario and application used ADDIE Model because it was a general/common learning system model and one of product development models. There is evaluation in each step of ADDIE model. Evaluation is done through validation process and the collected data were analyzed using percentage technique, they are: per item data tabulation and whole data tabulation. Based on the research result, it could be concluded that the percentage of Blended Learning Teaching Scenario developed was considered as appropriate and able to improve the students’ comprehension significantly.

Toward a Precision Science of Word Learning: Understanding Individual Vocabulary Pathways.

Toddlers vary widely in the rate at which they develop vocabulary. This variation predicts later language development and school success at the group level; however, we cannot determine which children with slower vocabulary development in the second year will continue to have difficulty. In this article, I argue that this is because we lack theoretical understanding of how multiple processes operate as a system to create individual children's pathways to word learning. I discuss the difficulties children face when learning even a single concrete noun, the multiple general cognitive processes that support word learning, and some evidence of rapid development in the second year. I present work toward a formal model of the word learning system and how this system changes over time. The long-term goal of this work is to understand how individual children's strengths and weaknesses create unique vocabulary pathways that enable us to predict outcomes and identify effective interventions.

Reactor Coolant Pump Leakage Estimation of PWR Based on Broad Learning System

Loss-of-coolant accident (LOCA) of reactor coolant pump is considered as a critical issue in pressurized water reactor (PWR) accident analysis. Much work focus on the detection of LOCA, while little work has been done on leakage quantity estimation. In this paper, a reactor coolant leakage estimation model is proposed based on broad learning system (BLS) model which takes the advantages of the flatted structure and incremental learning. Considering that larger leakage is more concerned, the BLS model is improved by a weighted loss function. Dropout layer and white noise are added to improve the robustness of the model. This model is designed to estimate the coolant leakage in an online manner with high precision. The proposed model is evaluated on real leakage data of a reactor coolant pump. Experiments show that, with similar accuracy, the proposed model is significantly faster than the state-of-art deep neural networks.

Multilevel Design in the Implementation of Blended Learning in Nonformal Education Unit

CLC as one of the non-formal educational institutions affected by the COVID 19 outbreak must organize online teaching and learning activities under government instructions as an effort to prevent transmission of the COVID 19 pandemic. Lack of experience in conducting online learning makes institutions confused about running the learning process due to educators and managers' limited ability to implement online education. It is necessary to study more deeply what learning strategies CLCs should carry out during the pandemic period. The approach used in this study was a mixed-method with 10 CLC respondents spread across West Java. From the findings in the field, learning at CLC during the pandemic was still ongoing. Tutor only used message applications for delivering learning material and evaluation process. They do not even implement it in the online learning management system. For this reason, CLC can pilot a multilevel blended learning system model. The implementation of the model system starts from institutional management, program management, to learning management by tutors.

Estimating Submicron Aerosol Mixing State at the Global Scale With Machine Learning and Earth System Modeling

AbstractThis study integrates machine learning and particle‐resolved aerosol simulations to develop emulators that predict submicron aerosol mixing state indices from the Earth system model (ESM) simulations. The emulators predict aerosol mixing state using only quantities that are predicted by the ESM, including bulk aerosol species concentrations, which do not by themselves carry mixing state information. We used PartMC‐MOSAIC as the particle‐resolved model and NCAR's CESM as the ESM. We trained emulators for three different mixing state indices for submicron aerosol in terms of chemical species abundance (χa), the mixing of optically absorbing and nonabsorbing species (χo), and the mixing of hygroscopic and nonhygroscopic species (χh). Our global mixing state maps show considerable spatial and seasonal variability unique to each mixing state index. Seasonal averages varied spatially between 13% and 94% for χa, between 38% and 94% for χo, and between 20% and 87% for χh with global annual averages of 67%, 68%, and 56%, respectively. High values in one index can be consistent with low values in another index depending on the grouping of species and their relative abundance, meaning that each mixing state index captures different aspects of the population mixing state. Although a direct validation with observational data has not been possible yet, our results are consistent with mixing state index values derived from ambient observations. This work is a prototypical example of using machine learning emulators to add information to ESM simulations.

Development of an ontological model of the distance learning system

An ontological model of the distance learning system has been built, which captures and structures the knowledge common to this subject area. This allows it to be used repeatedly within the subject area as the basis of a single model of knowledge, which ensures logical consistency between the individual ontologies when combined. An ontology has been formed to build a single information space of the distance learning system. This single information space allows you to navigate the developed knowledge base. Requirements of semantic search and acquisition of new knowledge are realized by means of initial ontology and are transferred in the form of updating in uniform information space. Information hierarchies for designing an intellectual model of distance learning process using elements of the methodology of object-oriented approach are constructed. The application of the ontological approach is a very effective way to design an intellectual model of the distance learning process. Based on the theory of system analysis and synthesis of organizational management, as well as on methodologies for automating the design of information technology processes and systems, a method of creating a single information space for the implementation of operational management of higher education. An ontological method of modeling information systems based on multidimensional models is proposed for use. The tools of this method allow you to develop an infographic model of any information system that will fully reflect the pragmatics of the system under study, and thus eliminate the use of any additional methods for its creation.

Big Data Curriculum Design and Teaching Practice Based on Smart Learning Environment

This article proposes a smart learning system model based on big data. The system model is based on a big data architecture, combined with an adaptive general learning model, and provides information assistance and technical support for learners and teachers to learn through education big data and learning analysis technology. And based on the overall design framework, a learning early warning system model based on multi-modal data and an intervention mechanism process model are proposed. Experimental research shows that the intelligent learning system model can solve teaching resource management and the construction and application of various online courses. Help schools improve teaching quality, improve teaching efficiency, simplify teaching management, and promote teaching reform.

Revealing deep interaction patterns of team learning processes through video-based interactive analysis

New tools provide new lenses for a better understanding of how learning occurs within the team setting. A better understanding of team learning will enable human resource development (HRD) professionals to more effectively develop an enhanced level of performance in the workplace. Since teams represent complex learning systems, traditional questionnaires that take a static 'snapshot' of the reality and interviews that capture retrospective member memories fail to reflect the dynamics or the holistic nature of teamwork. Deeper patterns of the dynamics of team learning will provide the foundation for more generalisable theories. We argue that a better understanding of team learning in HRD will grow when scholars generate new models of team learning systems based on new ways of measuring team behaviour that capture the complex interactions among members. In this paper, we propose that video-based interaction analysis can offer more opportunities. We discuss the current research methods issues, profile the current state of the scholarship of team learning, and recommended a new data collection/analysis approach: video-based interactive analysis (VIA).

Multidomain Feature Fusion for Varying Speed Bearing Diagnosis Using Broad Learning System

Bearing is one of the most critical mechanical components in rotating machinery. To identify the running status of bearing effectively, a variety of possible fault vibration signals are recorded under multiple speeds. However, the acquired vibration signals have different characteristics under different speeds and environment interference, which may lead to different diagnosis results. In order to improve the fault diagnosis reliability, a multidomain feature fusion for varying speed bearing diagnosis using broad learning system is proposed. First, a multidomain feature fusion is adopted to realize the unified form of vibration characteristics at different speeds. Time‐domain and frequency‐domain features are extracted from the different speeds vibration signals. Then, the broad learning system is employed with the fused features for classification. Our experimental results suggest that, compared with other machine learning models, the proposed broad learning system model, which makes full use of the fused feature, can improve the diagnosis performance significantly in terms of both accuracy and robustness analysis.

Mathematics of Climate Modeling: Challenges and Perspectives

Climate modeling is a complex and interdisciplinary field that relies on mathematics, physics, computer science, and other disciplines to simulate the Earth's climate system. This paper provides an overview of the mathematical foundations, challenges, and perspectives on advancements in climate modeling. It discusses the importance of mathematics in climate modeling, including the use of differential equations, numerical methods, and statistical techniques. The paper also examines the challenges faced by climate modelers, such as uncertainty and sensitivity analysis, model complexity, and parameterization of physical processes. Furthermore, it explores the potential advancements in climate modeling, including the integration of machine learning, high-performance computing, and Earth system models. Case studies and applications of climate modeling, such as regional climate modeling, climate change projections, and impact assessments, are presented to demonstrate the relevance and importance of these models in understanding and addressing climate change. Overall, this paper highlights the critical role of mathematics in advancing climate modeling and its implications for climate science and policy.