Hybrid Learning Model Research Articles

Analysis of Hybrid Learning Model Interest Selection for students using the Multi-Attribute Utility Theory Method Case Study: Mulia University

Hybrid learning is a learning method that combines or combines online learning with face-to-face learning (PTM). so that in its implementation, there are times when students and teaching staff meet face to face in class. However, in its implementation there are several obstacles, one of which is the number of students attending class and decreasing interest in learning, resulting in a poor final semester assessment. In connection with the problems faced, this research will try to measure interest in the hybrid learning model that has been implemented at Mulia University using the Multi-Attribute Utility Theory method, where this method is a decision-making method used to evaluate alternatives by considering several attributes. relevant and selecting the alternative that best meets the needs and preferences of the decision maker.

25 The Hybrid Learning Environment During Covid-19: A Case Study on IEP Implementation for a Student with Autism Spectrum Disorder

Objective:An effective support system for families with children with an Autism Spectrum Disorder (ASD) consists of multiple methods of educational and therapeutic delivery. Such methods are adapted to meet a family’s needs and needs of the time, like the COVID-19 pandemic. Individualized Educational Plan (IEP) are established by schools to support success in academics for children with ASD. IEPs can vary depending on the district and accessibility, thus, the effective implementation and communication between this support system is important for its success. The current case study examines academic and therapeutic outcomes of an IEP implementation during hybrid learning of a child with ASD and their family.Participants and Methods:Purposeful sampling identified a participant from a previous IRB approved study through the UNLV Educational Psychology program that interviewed parents on their remote learning experience. A qualitative case study was applied to further investigate student outcomes. Parent interview and the child’s progress report were coded and analyzed systematically. The identified family included correspondence from the mother (Lisa, 37) and her son (Noah, 9). Noah attended third grade at a Charter School and was diagnosed with ASD in 2019. His IEP included 80% in General Education (online) with Special Education assistance (in person; reading, writing, and mathematics) and Occupational (OT), Speech/Language (SLP), and Physical Therapy (PT) (hybrid).Results:Noah began hybrid learning in October 2020, with in-person learning two days a week and remote learning everyday for two to three hours each day. Progress report and interview were collected in April 2021 at the halfway point of his IEP implementation which described Noah’s current special education and therapy services goals/outcomes in March 2021. This included 11 goals that were observed and assessed in OT (2), PT(2), Reading (2), Writing (1), Math (2), and SLP (2). Noah progressed in 9 of 11 goals, with 1 being met and 8 classified as satisfactory by displaying some improvement in respective skills mid year. The remaining OT (2) goals showed no definitive conclusion. Lisa mentioned that lack of direct observation of particular skills and too many online classes to attend led to inconclusive outcomes. Lisa and Noah came across difficulties while engaging in OT online sessions encountering emotional stress when adjusting to the mode of delivery. Lisa expressed positive emotions when referring to the support system and described it as collaborative with adequate attention to multiple aspects of his development. She voiced understanding of her’s and other professionals’ role and the extent of their abilities in the context of the pandemic.Conclusions:Of the 11 IEP goals, there was adequate progress for the child amid hybrid learning. The parent preferred that OT be delivered in person as certain procedures require direct contact and affected outcomes. Hybrid learning has allowed for parents to directly access their children’s endeavors and heighten communication with professionals. This suggests that maintenance of IEP standards can be satisfactory in a hybrid learning model with adequate monitoring from parents and treatment teams for children with ASD.

Rainfall Forecasting with Hybrid and Machine Learning Models Based on Hyperparameter Optimization

Rainfall Forecasting with Hybrid and Machine Learning Models Based on Hyperparameter Optimization

Acquisition of Arabic Students with Hybrid and Receptive Learning Models

This study aimed to analyze the ability to acquire Arabic as a second language for students of the Islamic Economics and Business Faculty at IAIN Ponorogo through hybrid and sensory learning activities. This research is qualitative with a case study type. The research population totaled 176 students, with a sample of 20 students. The sampling technique was done by non-probability sampling with the snowball sampling method because the samples were taken based on the needs of this study. The research data is in the form of pronunciation of vocabulary sounds, Arabic spelling of letters, verbs, and nouns, the ability to understand the material being listened to, and the ability to read Arabic texts for FEBI IAIN Ponorogo students in odd semesters of 2022/2023 academic year. The student reading source used as research data is the book "Al-'Arabiyyah fī Dirāsah al-Mu'āmalāt." A book taught in the course "Arabic for Economics." Observation, interviews, and documentation carry out data collection techniques. Data analysis techniques with data reduction, data presentation, concluding, and verification. The results of the study show that the acquisition of Arabic as a second language by students of the Islamic Faculty of Economics and Business at IAIN Ponorogo in attending "Arabic for Economics" courses tends to differ from one another. They are entering the pre-production language acquisition phase. That is, they have not mastered many foreign vocabulary. This is due to the educational background taken before they entered university. Another influencing factor is the environment in which students live.

Early Childhood Social Skills Development Through Hyflex Learning (Flexible Hybrid)

Social skills need to be familiarized from an early age because children will carry these habits into adulthood. This study aims to find a learning model to develop social-emotional skills through hyflex learning. Face-to-face, hybrid (blended) learning should give early childhood flexibility to learn. HyFlex learning gives students choices about how they attend class through face-to-face, synchronous, and asynchronous technology. An alternative to achieving this goal is to develop a hybrid learning model that can be used to teach these early childhood social skills. The HyFlex Learning Model is a new form of learning in early childhood education. The selection of the model is based on the initial needs analysis in DKI Jakarta, where most ECCE educators need a learning model to develop children's social performance that can be applied during the Face-to-Face Meeting period to learning activities in PAUD which is limited in nature can be done optimally. The method used is research and development (Research and Development) which includes activities (1) researching and collecting information, including reading literature, observing classes, and preparing reports on development needs, (2) planning prototype components to be developed, (3) developing initial prototypes; (4) conduct limited trials, (5) revise, (6) test results, (7) revise product designs, (8) conduct field trials operationally, (9) make final revisions to the media, and (10) disseminate to various parties. The results of the model trial conducted obtained an assessment percentage of 83% with a decent assessment category, so this model is suitable for teaching Social Skills.

Deep Learning-Based Cross-Layer Power Allocation for Downlink Cell-Free Massive Multiple-Input–Multiple-Output Video Communication Systems

We propose a deep learning-based cross-layer power allocation method for asymmetric cell-free massive MIMO video communication systems. The proposed cross-layer approach considers physical layer channel state information (CSI) and the application layer rate distortion (RD) function, and it aims to enhance video quality in terms of peak signal-to-noise ratio (PSNR). Our study develops a decentralized deep neural network (DNN) model to capture intricate system patterns, enabling accurate and efficient power allocation decisions. The proposed cross-layer approach includes unsupervised and hybrid (supervised/unsupervised) learning models. The numerical results show that the hybrid method achieves convergence with just 50% of the iterations required by the unsupervised learning model and that it achieves a 1 dB gain in PSNR over the baseline physical layer scheme.

Slab arching degree identification and evaluation based on track dynamic inspection data

Due to structural deterioration and the external environment, the ballastless track is prone to slab arching during high-temperature periods. Arching will weaken the constraints between components, affect the smoothness of the line, and even endanger train safety in severe cases. Therefore, it is necessary to identify the arching in time and clarify the arching severity, which is of great significance for scientifically formulating maintenance plans and ensuring line stability. The existing research has established track geometry-based methods for arching identification, but they are difficult to recognize small arching and cannot quantitatively evaluate arching degree. To this end, this paper proposed a set of arching identification and evaluation methodology based on track dynamic inspection data. Combining the simulated and measured data, the time–frequency characteristics of car body vertical vibration caused by arching were finely extracted, and the arching-induced vibration index was established for identification. Then, a deep learning hybrid model for arching degree evaluation was proposed based on the analysis of the relationship between multiple feature indexes and arching gap height. The results showed that car body vibration could identify the arching defects with gap heights exceeding 1 mm, and the arching degree could be evaluated quantitatively based on multiple feature indexes. In practice, the proposed method can be used to detect arching of different degrees, assist maintenance decision-making, and help avoid the occurrence of serious failures.

Detection of driver drowsiness level using a hybrid learning model based on ECG signals.

Fatigue has a considerable impact on the driver's vehicle and even the driver's own operating ability. An intelligent algorithm is proposed for the problem that it is difficult to classify the degree of drowsiness generated by the driver during the driving process. By studying the driver's electrocardiogram (ECG) during driving, two models were established to jointly classify the ECG signals as awake, stress, and fatigue or drowsiness states for drowsiness levels. Firstly, the deep learning method was used to establish the model_1 to predict the drowsiness of the original ECG, and model_2 was developed using the combination of principal component analysis (PCA) and weighted K-nearest neighbor (WKNN) algorithm to classify the heart rate variability characteristics. Then, the drowsiness prediction results of the two models were weighted according to certain rules, and the hybrid learning model combining dilated convolution and bidirectional long short-term memory network with PCA and WKNN algorithm was established, and the mixed model was denoted as DiCNN-BiLSTM and PCA-WKNN (DBPW). Finally, the validity of the DBPW model was verified by simulation of the public database. The experimental results show that the average accuracy, sensitivity and F1 score of the test model in the dataset containing multiple drivers are 98.79, 98.81, and 98.79 % respectively, and the recognition accuracy for drowsiness or drowsiness state is 99.33 %. Using the proposed algorithm, it is possible to identify driver anomalies and provide new ideas for the development of intelligent vehicles.

Can Clean Energy Stocks Predict Crude Oil Markets Using Hybrid and Advanced Machine Learning Models?

Can Clean Energy Stocks Predict Crude Oil Markets Using Hybrid and Advanced Machine Learning Models?

Dental Student Perceptions of Distance Education over Time: A Mixed-Methods Study.

Amid the COVID-19 pandemic, the transition to distance learning raised pertinent questions regarding advantages and challenges compared to traditional in-person learning. This study aimed to investigate dental students' perceptions of distance learning throughout the pandemic, examining its impact on their education. This study employed a convergent mixed-methods design. Three online surveys were conducted in 2020, 2021, and 2022 to collect quantitative data. Additionally, qualitative semi-structured interviews were carried out in 2022. Interviews were recorded and transcribed; then, thematic analysis was performed following an inductive approach. As perceived by the participants, distance learning entails advantages and challenges. Initially, they felt uncertainty and negativity about the new environment with distance learning. However, their perceptions shifted positively as they adapted, even after returning to hybrid and in-person modules. Furthermore, most participants felt that distance learning is better suited for didactic content. It was suggested that didactic courses contain approximately 25-50% of online methods. Distance learning has provided valuable opportunities to reinforce curricula and improve learning efficacy during the pandemic. Our findings suggest that a hybrid learning model that combines traditional and distance modules appears to be an effective approach for future dental education.

AN ANALYSIS OF STUDENTS’ LEARNING READINESS TOWARDS HYBRID LEARNING ACHIEVEMENT IN ENGLISH

ABSTRACT
 This study used a descriptive qualitative approach to analyze students' readiness for hybrid learning achievement in English. Data were collected through questionnaires and interviews. The study aimed to (1) assess the extent to which students of SMK N 7 Semarang were ready to adopt the hybrid learning model in English learning, (2) identify the factors that hindered the readiness of students of SMK N 7 Semarang in implementing the hybrid learning model in English learning, and (3) identify the factors that supported the readiness of students of SMK N 7 Semarang in implementing the hybrid learning model in English learning. The subjects of the study were students of class XI TFLM 1 SMK N 7 Semarang. The results of the study showed that (1) students of SMK N 7 Semarang had adequate readiness to adopt hybrid learning in English learning, with a readiness level of 65.57%, (2) factors that hindered students' readiness involved facility constraints, skills, and motivation in online learning, and (3) factors that supported students' readiness included guidance from teachers, support from parents, and cooperation among students. The study concluded that hybrid learning had the potential to improve the quality of English learning if students had a high level of learning readiness. Therefore, the recommendations from this study were that teachers and schools should provide adequate facilities, training, and encouragement to prepare students for hybrid learning.
 Keywords: Hybrid learning, Learning readiness, Learning achievement

НАУКОВА АКТИВНІСТЬ НАУКОВО-ПЕДАГОГІЧНИХ ПРАЦІВНИКІВ УНІВЕРСИТЕТУ: РЕФЛЕКСІЇ ВПЛИВУ УМОВ СУЧАСНОСТІ

Contemporary global development conditions present a range of challenges and opportunities to academic experts in higher education institutions, who must navigate them with limited resources and varying circumstances. The study outlined in this article aims to investigate the factors that influence the scholarly engagement of academic personnel across different timeframes, encompassing both times of peace and conflict. The findings from the analysis underscore critical limitations and motivations that mold the scholarly conduct of university educators. During periods of tranquility, the principal barriers to scholarly engagement include substantial administrative and methodological workloads, as well as limited financial impetus. In times of military events, emotional fatigue and financial hurdles emerge as primary factors curbing the scholarly involvement of academic staff, particularly when coupled with excessive workloads. Moreover, the research results reveal that adaptable work environments, embracing hybrid learning models, also significantly contribute to scholarly involvement. The analysis brings to light the need for dedicated research time in scholarly activities, necessitating a harmonious balance between teaching, methodological commitments, administrative duties, and opportunities for profound research. An intriguing revelation is that young instructors prove most productive, emphasizing the critical role of their guidance and growth. The study's deductions emphasize the importance and imperative of streamlining university operations, particularly through the equitable allocation of workloads, prioritization of psychological and emotional well-being, and establishment of favorable circumstances for scholarly commitment, especially among emerging academics, across local, regional, and national domains. These findings establish a groundwork for crafting effective strategies aimed at sustaining academic experts and fostering scholarly engagement within universities amidst a backdrop of dynamic transformations. Keywords: scientific activity, academic professionals,university, war, peacetime, Covid-2019.

Multi-target meridians classification based on the topological structure of anti-cancer phytochemicals using deep learning

Ethnopharmacological relevanceTraditional Chinese medicine (TCM) meridian is the key theoretical guidance of prescription against tumor in clinical practice. However, there is no scientific and systematic verification of therapeutic action of herbs under meridians context. Several studies have determined the Chinese herbal medicine (CHM) phytochemicals for intrinsic attribute or meridians classification based on artificial intelligence (AI) tools. However, it is challenging to represent the complex molecular structures with large heterogeneity through the current technologies. In addition, the multiple correspondence between herbs and meridians has not been paid much attention. Aim of the studyWe aim to develop an AI framework to classify multi-target meridians through the topological structure of phytochemicals. Materials and methodsA total of 354 anti-cancer herbs, their corresponding TCM meridians and 5471 ingredient compounds were collected from public databases of CancerHSP, ETCM, and Hit 2.0. The statistical analysis of herbal and compound datasets, clustering analysis of the associated cancers, and correlational analysis of meridian tropism were preliminary conducted. Then a deep learning (DL) hybrid model named GRMC consisting of graph convolutional network (GCN) and recurrent neural network (RNN) was employed to generate the meridian multi-label sequences based on molecular graph. ResultsThe curing herbs against tumors have tight relationships to lung, liver, stomach, and spleen meridians. These herbs behave different properties in curing certain cancer. Certain cancer types have co-occurrence such as ovarian, bladder and cervical cancer. Compounds have multitarget meridians with characteristics of higher-order correlations. Compared with the other state-of-the-art algorithms on the datasets and previous methods dealing with conventional fixed fingerprints of herbal compounds, the proposed GRMC has superior overall performance on testing dataset with the one error of 0.183, hamming loss of 0.112, mean averaged accuracy (MAA) of 0.855, mean averaged precision (MAP) of 0.891, mean averaged recall (MAR) of 0.812, and mean averaged F1 score (MAF) of 0.849. ConclusionsThe proposed method can predict multi-targeted meridians through neural graph features in herbal compounds and outperforms several comparison methods. It could provide a basis for understanding the molecular scientific evidence of TCM meridians.

Hybrid deep learning and metaheuristic model based stroke diagnosis system using electroencephalogram (EEG)

Over the last few decades, there has been a significant increase in the average lifespan. Consequently, the number of elderly people suffering from strokes has also risen. As a result, strokes and their treatments have become crucial subjects of research, particularly for the application of machine learning. One of the primary factors in stroke treatment is the speed of response. Currently, both computed tomography (CT) and magnetic resonance imaging (MRI) are used to diagnose strokes. However, CT takes eight hours before an accurate diagnosis can be made, and MRI is expensive and not available in all hospitals. Therefore, there is a growing need for novel approaches to identifying strokes based on electroencephalogram (EEG) signals. In this paper, a hybrid model of deep learning and metaheuristic was developed in the offline stage to classify strokes. Since EEG data is a time series with frequencies, a hybrid model was deemed appropriate. This hybrid model combined a Convolutional Neural Network (CNN) with bidirectional Gated Recurrent Unit (BiGRU). The performance of this model surpassed that of other comparable models. Given the paramount importance of speed and accuracy in this work, the harmony search (HS) algorithm, which is specialized in handling frequencies, was used for feature selection. HS outperformed all similar algorithms when applied to the CNN-BiGRU hybrid model. Additionally, for the optimization of continuous hyperparameters, the multiverse optimization (MVO) algorithm was employed, which proved to be the most effective when compared to another similar algorithm for validation purposes. The new model, CNN-BiGRU-HS-MVO, was applied to analyze the data collected from Al Bashir Hospital using the MUSE-2 portable device, resulting in an impressive prediction accuracy of 99.991%. Moreover, it demonstrated an 11.08% improvement over the results from the paper titled “Predicting stroke severity with a 3-min recording from the Muse portable EEG study”. Furthermore, a decision support system was built on the cloud computing environment based on the hybrid model. This system allows for the diagnosis of patients anytime and from anywhere within minutes, with the authorized person receiving the diagnosis results through SMS notification.

Post-COVID craft education

This paper presents a hybrid model of teaching and learning that proposes new possibilities for exchang­ing tangible and intangible cross-cultural knowledge in textile craft education. The paper aims to demonstrate how online platforms can be used creatively to disseminate traditional craft knowledge and skills in new ways. The discussion centres on a unique virtual global studio between fashion and textile undergraduate students at the University of Technology Sydney and on an artisanal woodblock print studio, Tharangini, based in Bengaluru (Bangalore), India. The hybrid workshop was an adaptation of the studio in response to travel restrictions caused by the pandemic. The author argues that while the internet cannot replace the immersive cultural experience of studying in another country, digital platforms have a place alongside teaching to offer otherwise impossible opportunities. This paper explores a methodology for disseminating craft knowledge and skills across cultures through a combination of online and in-house practicum. Classes were structured around weekly Zoom sessions with Director Padmini Govind, where sustainable approaches to print production were disseminated through a suite of commissioned films and hand-carved woodblocks to explore on campus. The results show how this unique adaptation allowed students to interact with the artisan craft of woodblock printing in rich and varied ways, and it proposes that this novel hybrid model can be creatively adapted to future craft education in the 2020s.

Power Load Forecasting System Based on Deep Hybrid Learning Model

Accurate prediction of electricity demand is crucial to ensure the stability and dependability of local power grids. Numerous scholars have put forth comprehensive prediction systems; However, the majority of these models fail to capture the inherent global features present within the data. This study introduces a novel integrated prediction system that leverages the synergistic capabilities of Time Convolutional Network (TCN) and Long Short-Term Memory (LSTM) architectures, aiming to enhance the accuracy of short-term electric load forecasting. The initial step is to establish separate prediction models for LSTM and TCN, with a focus on electric load data. After combining the output results of these models, the reciprocal of the error square ratio was used as a weighting factor. By using this approach, the LSTM-TCN model for combined prediction is created. This research paper performs an exhaustive examination of the case study by employing authentic data sourced from the Australian Energy Management Authority. The study's findings support that the LSTM-TCN model outperforms both single prediction models and traditional network models in terms of performance. The results indicate that the LSTM-TCN model exhibits greater accuracy in predicting short-term energy demand.

The Process of Digital Transformation in Education During the COVID-19 Pandemic

Purpose: This document seeks to delve into the digital transformation of education during the COVID-19 pandemic, aiming to provide a comprehensive understanding of this evolving phenomenon's purpose and significance.
 
 Design/Methodology/Approach: The research approach undertaken is characterized by a non-experimental, documentary, exploratory, and descriptive study methodology, which involves an extensive examination of existing literature and data to gain insights into the digital transformation in education during the pandemic.
 
 Findings: The study's key findings revolve around the consensus in existing literature regarding the swift acceleration of the transformation of education from traditional face-to-face classes to virtual learning environments. It also highlights the implications of this transformation, particularly in reshaping teaching models and advocating for a hybrid approach encompassing both face-to-face and virtual learning.
 
 Research, Practical & Social implications: The implications of this research extend to informing educational institutions about the need for digital adaptation, guiding policymakers in supporting adaptable learning models, and empowering educators with a deeper understanding of the changing educational landscape. Moreover, it considers the broader societal impact, including equity and access issues in education.
 
 Originality/Value: This research is unique in its contribution to understanding the profound impact of the COVID-19 pandemic on education. It emphasizes the significance of adaptability and hybrid learning models while providing a foundation for future educational research and policy development.

Hybrid Learning Models for IMU-Based HAR with Feature Analysis and Data Correction.

This paper proposes a novel approach to tackle the human activity recognition (HAR) problem. Four classes of body movement datasets, namely stand-up, sit-down, run, and walk, are applied to perform HAR. Instead of using vision-based solutions, we address the HAR challenge by implementing a real-time HAR system architecture with a wearable inertial measurement unit (IMU) sensor, which aims to achieve networked sensing and data sampling of human activity, data pre-processing and feature analysis, data generation and correction, and activity classification using hybrid learning models. Referring to the experimental results, the proposed system selects the pre-trained eXtreme Gradient Boosting (XGBoost) model and the Convolutional Variational Autoencoder (CVAE) model as the classifier and generator, respectively, with 96.03% classification accuracy.

Iraqi EFL University Instructors' Attitudes Towards the Hybrid Learning Model in the Teaching and Learning Process

This paper describes the process of developing and validating a self-assessment survey that measures "technology pedagogical topic knowledge" among preservice instructors studying to teach English as a foreign language (EFL). The questionnaire, called "Technological Pedagogical Content Knowledge" )TPACK(, the study aims to provide an assessment tool for preservice foreign language instructors towards the hybrid learning model. The tool used a questionnaire survey. "The sample of the study consist of (30) instructors" (10 male and 20 female) from Baghdad and Tikrit Universities. The results indicate that instructors have superior content, pedagogical, and pedagogical content knowledge, but inferior technical and technological content knowledge. This might be attributed to the lack of digital classroom technology and information assistance in their educational institutions. In general, EFL instructors have favorable opinions on hybrid learning.

Hybrid Learning through Lecture Capture: Exploring Perspectives and Overcoming Challenges with Blackboard Encore Technology

The COVID-19 pandemic has resulted in significant disruptions in higher education. Despite UK universities returning to in-person teaching, many international students still face travel restrictions imposed by their home countries, resulting in remote learning for many students at the beginning of the 2022–2023 academic year. To ensure a seamless academic transition for all students, a British university has implemented a hybrid learning model that utilizes lecture capture technology, specifically Blackboard Encore Streaming, to provide face-to-face and remote students with access to the same learning experience. This paper presents the findings from two online focus groups with students (n = 18) and two staff reflections, which aimed to explore the perspectives of teachers and students on the new Encore Streaming feature. The results indicate that both teachers and students value the hybrid approach, with remote students appreciating the flexibility and convenience of this approach more than face-to-face students. However, the study also reveals significant discrepancies in teacher attention and student participation opportunities between remote and face-to-face students, attributed to pedagogical and technological barriers. The study highlights the crucial role of teachers in orchestrating the hybrid classroom to ensure equal learning opportunities for all students and identifies areas where teachers require support, such as training, staff time, and technology support.