Hybrid Learning Model Research Articles

Novel deep learning hybrid models (CNN-GRU and DLDL-RF) for the susceptibility classification of dust sources in the Middle East: a global source

Dust storms have many negative consequences, and affect all kinds of ecosystems, as well as climate and weather conditions. Therefore, classification of dust storm sources into different susceptibility categories can help us mitigate its negative effects. This study aimed to classify the susceptibility of dust sources in the Middle East (ME) by developing two novel deep learning (DL) hybrid models based on the convolutional neural network–gated recurrent unit (CNN-GRU) model, and the dense layer deep learning–random forest (DLDL-RF) model. The Dragonfly algorithm (DA) was used to identify the critical features controlling dust sources. Game theory was used for the interpretability of the DL model’s output. Predictive DL models were constructed by dividing datasets randomly into train (70%) and test (30%) groups, six statistical indicators being then applied to assess the DL hybrid model performance for both datasets (train and test). Among 13 potential features (or variables) controlling dust sources, seven variables were selected as important and six as non-important by DA, respectively. Based on the DLDL-RF hybrid model – a model with higher accuracy in comparison with CNN-GRU–23.1, 22.8, and 22.2% of the study area were classified as being of very low, low and moderate susceptibility, whereas 20.2 and 11.7% of the area were classified as representing high and very high susceptibility classes, respectively. Among seven important features selected by DA, clay content, silt content, and precipitation were identified as the three most important by game theory through permutation values. Overall, DL hybrid models were found to be efficient methods for prediction purposes on large spatial scales with no or incomplete datasets from ground-based measurements.

A Robust Framework Combining Image Processing and Deep Learning Hybrid Model to Classify Cardiovascular Diseases Using a Limited Number of Paper-Based Complex ECG Images.

Heart disease can be life-threatening if not detected and treated at an early stage. The electrocardiogram (ECG) plays a vital role in classifying cardiovascular diseases, and often physicians and medical researchers examine paper-based ECG images for cardiac diagnosis. An automated heart disease prediction system might help to classify heart diseases accurately at an early stage. This study aims to classify cardiac diseases into five classes with paper-based ECG images using a deep learning approach with the highest possible accuracy and the lowest possible time complexity. This research consists of two approaches. In the first approach, five deep learning models, InceptionV3, ResNet50, MobileNetV2, VGG19, and DenseNet201, are employed. In the second approach, an integrated deep learning model (InRes-106) is introduced, combining InceptionV3 and ResNet50. This model is developed as a deep convolutional neural network capable of extracting hidden and high-level features from images. An ablation study is conducted on the proposed model altering several components and hyperparameters, improving the performance even further. Before training the model, several image pre-processing techniques are employed to remove artifacts and enhance the image quality. Our proposed hybrid InRes-106 model performed best with a testing accuracy of 98.34%. The InceptionV3 model acquired a testing accuracy of 90.56%, the ResNet50 89.63%, the DenseNet201 88.94%, the VGG19 87.87%, and the MobileNetV2 achieved 80.56% testing accuracy. The model is trained with a k-fold cross-validation technique with different k values to evaluate the robustness further. Although the dataset contains a limited number of complex ECG images, our proposed approach, based on various image pre-processing techniques, model fine-tuning, and ablation studies, can effectively diagnose cardiac diseases.

Predicting ammonia nitrogen in surface water by a new attention-based deep learning hybrid model

Ammonia nitrogen (NH3–N) is closely related to the occurrence of cyanobacterial blooms and destruction of surface water ecosystems, and thus it is of great significance to develop predictive models for NH3–N. However, traditional models cannot fully consider the complex nonlinear relationship between NH3–N and various relative environmental parameters. The long short-term memory (LSTM) neural network can overcome this limitation. A new hybrid model BC-MODWT-DA-LSTM was proposed based on LSTM combining with the dual-stage attention (DA) mechanism and boundary corrected maximal overlap discrete wavelet transform (BC-MODWT) data decomposition method. By introducing attention mechanism, LSTM could selectively focus on the input data. BC-MODWT could decompose the input data into sublayers to determine the main swings and trends of the input feature series. The BC-MODWT-DA-LSTM hybrid model was superior to other studied models with lower average prediction errors. It could maintain NASH Sutcliffe efficiency coefficient (NSE) values above 0.900 under the lead time up to 7 days, and the area under the receiver operating characteristic (ROC) curve could reach 0.992. The hybrid model also had higher prediction accuracies at the peak spots, indicating that it was capable of early warning when sudden high NH3–N pollution occurred. The high forecasting accuracy of the suggested hybrid method proved that further improving LSTM model without introducing more complex topologies was a promising water quality prediction method.

Driver Identification Methods in Electric Vehicles, a Review

Driver identification is very important to realizing customized service for drivers and road traffic safety for electric vehicles and has become a research hotspot in the field of modern automobile development and intelligent transportation. This paper presents a comprehensive review of driver identification methods. The basic process of driver identification task is proposed as four steps, the advantages and disadvantages of different data sources for driver identification are analyzed, driver identification models are divided into three categories, and the characteristics and research progress of driver identification models are summarized, which can provide a reference for further research on driver identification. It is concluded that on-board sensor data in the natural driving state is objective and accurate and could be the main data source for driver identification. Emerging technologies such as big data, artificial intelligence, and the internet of things have contributed to building a deep learning hybrid model with high accuracy and robustness and representing an important gradual development trend of driver identification methods. Developing a driver identification method with high accuracy, real-time performance, and robustness is an important development goal in the future.

ПРОБЛЕМА АНОНИМНОСТИ ОБУЧАЮЩИХСЯ В ВИРТУАЛЬНОЙ УЧЕБНОЙ СРЕДЕ

This article focuses on one of the particular problems associated with the gradual transition to a hybrid model of learning in the context of the coronavirus pandemic, which is that students, who regularly use the Internet and other digital tools for everyday communication and entertainment, transfer their desire to remain anonymous to the virtual learning environment. The described empirical diagnostic study aims to compare students’ declared attitudes towards anonymity in virtual space with their actual actions in a partially digitized learning environment. It finds that students accustomed to digital inquiry tools and interaction channels transfer their desire for anonymity to the virtual learning environment and see many benefits in such anonymity, but state that it is impossible to apply the principle of anonymity to their learning processes. This contradiction points to the need for further research into this issue from psychological, social, cultural and philosophical perspectives.

A comparative study for landslide susceptibility assessment using machine learning algorithms based on grid unit and slope unit

Landslide susceptibility assessment is an important support for disaster identification and risk management. This study aims to analyze the application ability of machine learning hybrid models in different evaluation units. Three typical machine learning models, including random forest forest by penalizing attributes (FPA) and rotation forest were merged by random subspace algorithm. Twelve evaluation factors, including elevation, slope angle, slope aspect, roughness, rainfall, lithology, distance to rivers, distance to roads, normalized difference vegetation index, topographic wetness index, plan curvature, and profile curvature, were extracted from 155 landslides in Yaozhou District, Tongchuan City, China. Six landslide susceptibility maps were generated based on the slope units divided by curvature and 30 m resolution grid units. Multiple performance metrics showed that the RS-RF model based on slope units has excellent spatial prediction ability. At the same time, the method of slope unit division based on curvature is proved to be more suitable for the typical Loess tableland regions, which provides basis for the selection of evaluation units in landslide susceptibility assessment.

Needs Analysis on the Development of Integrated GITTW Hybrid Learning Model in the Learning of Biology at Senior High School

The rapid development of technology in the era of globalization affects the world of education. As a result, learning must be able to adapt by utilizing technology. in line with this, there are problems in learning biology such as the lack of understanding a biological concepts, learning motivation and learning independence of students. As the consequency, the learning outcomes is declining. This study aims to determine the needs and potentials of teachers and students in learning biology as the basis for developing an Integrated GITTW (Group Investigation and Think Talk Write) Hybrid Learning Model strategy in Biology learning. This research is a descriptive type with the research subjects of teachers and students of grade X science at Senior High School in the city of Surabaya. Data were collected through observation, documentation, questionnaires and interviews. The results of the study reveal that teachers and students need the learning innovations by utilizing learning technology. The integration of technology in learning makes it easier for students to obtain information from various media and learning resources. The hybrid learning model integrated with the GITTW strategy with Moodle-based media makes learning more effective, efficient, and interesting and according to students' interests in using media such as smartphones and laptops. Through the model that will be developed, learning problems in comprehending biological concepts, learning activities and motivations as well as students' learning independence that are lacking in biology learning are expected to be resolved. Based on this fact, it is necessary to develop a hybrid learning model that integrates the GITTW strategy in biology learning.

EFEKTIVITAS MODEL PEMBELAJARAN HYBRID DALAM KETERAMPILAN MENULIS CERPEN SISWA KELAS XI SMAIT AL USWAH BANGIL

Some students find writing short stories difficult and boring. One way to improve writing skills is to use a hybrid learning model. It is a type of learning that combines various methods to help learn new information. Hybrid learning is a learning model that combines traditional face-to-face and online learning resources. This allows for smarter learning experiences for both students and teachers. The purpose of this study was to test the effectiveness of the hybrid learning model in the short story writing skills of class XI SMAIT Al Uswah Bangil. This type of research uses a pre-experimental design with one group pretest-posttest. Collecting data in this study using a questionnaire. The results of data analysis using the different test, namely the Paired sample t-test, found that the p value was 0.000 <α 0.05, which means that the results of the study showed that the hybrid learning model proved effective in short story writing skills for class XI students at SMAIT Al Uswah Bangil.

Enhanced Deep Learning Hybrid Model of CNN Based on Spatial Transformer Network for Facial Expression Recognition

One of the most common approaches through which people communicate is facial expressions. A large number of features documented in the literature were created by hand, with the goal of overcoming specific challenges such as occlusions, scale, and illumination variations. These classic methods are then applied to a dataset of facial images or frames in order to train a classifier. The majority of these studies perform admirably on datasets of images shot in a controlled environment, but they struggle with more difficult datasets (FER-2013) that have higher image variation and partial faces. The nonuniform features of the human face as well as changes in lighting, shadows, facial posture, and direction are the key obstacles. Techniques of deep learning have been studied as a set of methodologies for gaining scalability and robustness on new forms of data. In this paper, we look at how well-known deep learning techniques (e.g. GoogLeNet, AlexNet) perform when it comes to facial expression identification, and propose an enhanced hybrid deep learning model based on STN for facial emotion recognition, which gives the best feature extraction and classification in one go and maximizes the accuracy for a large number of samples on FERG, JAFFE, FER-2013, and CK+ datasets. It is capable of focusing on the main parts of the face and attaining extensive development over preceding fashions on the FERG, JAFFE, CK+ datasets, and the more challenging one namely FER-2013.

A Hybrid DNN Model for Travel Time Estimation from Spatio-Temporal Features

Due to recent advances in the Vehicular Internet of Things (VIoT), a large volume of traffic trajectory data has been generated. The trajectory data is highly unstructured and pre-processing it is a very cumbersome task, due to the complexity of the traffic data. However, the accuracy of traffic flow learning models depends on the quantity and quality of preprocessed data. Hence, there is a significant gap between the size and quality of benchmarked traffic datasets and the respective learning models. Additionally, generating a custom traffic dataset with required feature points in a constrained environment is very difficult. This research aims to harness the power of the deep learning hybrid model with datasets that have fewer feature points. Therefore, a hybrid deep learning model that extracts the optimal feature points from the existing dataset using a stacked autoencoder is presented. Handcrafted feature points are fed into the hybrid deep neural network to predict the travel path and travel time between two geographic points. The chengdu1 and chengdu2 standard reference datasets are used to realize our hypothesis of the evolution of a hybrid deep neural network with minimal feature points. The hybrid model includes the graph neural networks (GNN) and the residual networks (ResNet) preceded by the stacked autoencoder (SAE). This hybrid model simultaneously learns the temporal and spatial characteristics of the traffic data. Temporal feature points are optimally reduced using Stacked Autoencoder to improve the accuracy of the deep neural network. The proposed GNN + Resnet model performance was compared to models in the literature using root mean square error (RMSE) loss, mean absolute error (MAE) and mean absolute percentile error (MAPE). The proposed model was found to perform better by improving the travel time prediction loss on chengdu1 and chengdu2 datasets. An in-depth comprehension of the proposed GNN + Resnet model for predicting travel time during peak and off-peak periods is also presented. The model’s RMSE loss was improved up to 22.59% for peak hours traffic data and up to 11.05% for off-peak hours traffic data in the chengdu1 dataset.

ANALISIS PEMBELAJARAN HIBRIDA SELAMA PANDEMI DI SMPN 13 MALANG

This research is motivated by government regulations regarding the implementation of education during pandemic since 2020 which regulates distance learning. The various obstacles in implementing distance education require learning models that are in accordance with the needs of teachers and students in offline learning and during learning. This is necessary in order to develop the potential of teachers and students as well as improve the quality of independent learning in accordance with the objectives of independent learning by the Ministry of Education and Culture.
 In addition, this study aims to provide an overview of the implementation of learning in speaking skills at SMPN 13 Malang using a hybrid learning model. This study used descriptive qualitative method. Data collection techniques in this study used interviews, observation, and documentation. Data analysis techniques lead to inductive data analysis which includes data collection, data presentation, and drawing conclusions.
 The results of this study indicate learning activities, inhibiting and supporting factors in implementing hybrid learning. Based on these constraints, teachers are expected to be able to improve and correct the shortcomings that exist in the hybrid learning model so that learning activities are more fun and interactive for students during the pandemic.

A hybrid learning model for efficient classification of Land Use and land change from satellite images

With Deep Learning (DL) outperforming previous Machine Learning (ML) techniques in classifying images, the remote sensing community has recently shown an increased interest in using these algorithms to classify Land Use and Land Cover (LULC) using multispectral and hyperspectral data. Land Use (LU) and Land Cover (LC) are two types of cartographic data that are used to develop smart cities and monitor the environment. LULC classification can benefit greatly from successfully applying remote sensing Image Classification (IC) using high spatial resolution data. The acquisition of spatiotemporal data for LULC classification has been made more accessible because of recent improvements in spatial analysis and Deep Learning (DL) technology. Considering the quality of Deep Neural Networks (DNN) in related Computer Vision (CV) tasks and the enormous volume of remotely sensed data accessible, DL methods appear to be particularly promising for modelling many remote sensing problems. However, there are several issues with ground-truth, resolution, and the nature of data that have a significant impact on categorization performance. We propose a Reversible Residual Network (RAVNet), a hybrid residual attention sensitive segmentation approach, to precisely categorize LULC in this study. The suggested network is based on the VNet model, which extracts relevant information by mixing low-level and high-level Feature Maps (FM). The attention-aware features change adaptively to the integration of residual modules. Our system was tested on the National Agriculture Imagery Program (NAIP) dataset, and the findings demonstrate that our architecture is competitive against other learning models.

A deep hybrid learning model for detection of cyber attacks in industrial IoT devices

A deep hybrid learning model for detection of cyber attacks in industrial IoT devices

Brain Tumor Classification and Detection Using Hybrid Deep Tumor Network

Brain tumor (BTs) is considered one of the deadly, destructive, and belligerent disease, that shortens the average life span of patients. Patients with misdiagnosed and insufficient medical treatment of BTs have less chance of survival. For tumor analysis, magnetic resonance imaging (MRI) is often utilized. However, due to the vast data produced by MRI, manual segmentation in a reasonable period of time is difficult, which limits the application of standard criteria in clinical practice. So, efficient and automated segmentation techniques are required. The accurate early detection and segmentation of BTs is a difficult and challenging task in biomedical imaging. Automated segmentation is an issue because of the considerable temporal and anatomical variability of brain tumors. Early detection and treatment are therefore essential. To detect brain cancers or tumors, different classical machine learning (ML) algorithms have been utilized. However, the main difficulty with these models is the manually extracted features. This research provides a deep hybrid learning (DeepTumorNetwork) model of binary BTs classification and overcomes the above-mentioned problems. The proposed method hybrid GoogLeNet architecture with a CNN model by eliminating the 5 layers of GoogLeNet and adding 14 layers of the CNN model that extracts features automatically. On the same Kaggle (Br35H) dataset, the proposed model key performance indicator was compared to transfer learning (TL) model (ResNet, VGG-16, SqeezNet, AlexNet, MobileNet V2) and different ML/DL. Furthermore, the proposed approach outperformed based on a key performance indicator (Acc, Recall, Precision, and F1-Score) of BTs classification. Additionally, the proposed methods exhibited high classification performance measures, Accuracy (99.51%), Precision (99%), Recall (98.90%), and F1-Score (98.50%). The proposed approaches show its superiority on recent sibling methods for BTs classification. The proposed method outperformed current methods for BTs classification using MRI images.

110 DEVELOPMENT AND DELIVERY OF A MULTI-DISCIPLINARY HYBRID EDUCATION PROGRAM IN SYNCOPE AND RELATED DISORDERS DURING THE COVID-19 PANDEMIC

Abstract Background Syncope and related disorders is an important area for training of all health professionals. During the COVID-19 pandemic, we adapted the delivery of our annual face-to-face certified program to a 9-month hybrid program. Here, we describe the development, delivery, and evaluation of such new program. Methods A pre-existing curriculum was modified to incorporate online content, online lecture delivery and interactive group learning, in addition to individual practical placements in a syncope management unit, in line with government and hospital infection control guidance at the time. Monthly content included video consultant case presentations, ECG analysis and interpretation, and instructional videos of diagnostic testing and relevant technologies. A comprehensive online week-long lecture program was developed. Results The lecture week included 30 clinical lectures, 10 clinical case presentations and 10 ‘how to’ practical videos for testing/monitoring procedures. Further learning over zoom incorporated learner case presentations in a small group format. At the completion of the course the leaners attended a final online half day of lectures and completed the multi choice question examination. Conclusion “Thank you so much for putting together such a fantastic week of training.” “The quality and expertise of the speakers was outstanding.” “I have taken a huge amount away to incorporate into my practice and local unit.” The above learner feedback is consistent with our aim to deliver a high-quality specialist program for those interested in advancing the management of syncope and related disorders. Over time, this specialist training will aid the development of regional syncope management units across Ireland. The benefits of a hybrid learning model include multiple options to cater for all categories of learners, thus suggesting it is the cornerstone of future learning modalities.

Methodology of Designing Digital Services for the Educational Market

The article discusses methodological aspects and practical experience in designing digital services for the educational market. There are defined basic requirements for the creation of digital services, their properties and characteristics. Based on the theoretical analysis, it is proved that the most promising way of designing digital services, which determines their configuration and user capabilities, is the platform approach. The analysis of the available educational platforms is carried out, their advantages and disadvantages are shown. The authors present a digital services designing methodology of their own, worked out with the help of the progressive Agile and Waterfall methodologies. The paper gives an example of the developed methodology approbation within the project of the Citadel Education online learning platform, focused on the implementation of adaptive educational programs with the possibility of choosing individual trajectories. This research is brand new, as it systematizes theoretical ideas about the creation of digital services with specific product characteristics and develops a methodological base for the creation of customized and technological educational services that meet today’s user needs. The results of the study are of particular interest in the context of foreign educational platforms withdrawal from the Russian market and may be useful for university leaders, who solve the problems of improving educational programs competitiveness, implementing hybrid learning models, and managing the portfolio of training courses.

Using MOOC and Gamification Hybrid Learning Models in Rural Public Schools in Thailand

Using MOOC and Gamification Hybrid Learning Models in Rural Public Schools in Thailand

Forecasting Premium Motor Spirit (PMS) and Energy Commodities Prices Using Machine Learning Techniques: A Review

The instability of Premium Motor Spirit (PMS/Petrol) and other energy commodities prices, occasioned by volatile and dynamic movement of prices has been found to affect the cost of production in Nigeria. As a result, this paper studies current literature on the applications of machine learning techniques in forecasting PMS (Petrol) and other energy commodities prices. The review has been done through an electronic search of the published papers in the last 4 years (2019-2022). A total number of twenty-nine (29) publications on PMS (Petrol) and other energy commodities prices forecasting using machine learning models were selected for the study to identify research gaps and future works. This paper covers a summary of reviewed published papers on forecasting PMS (Petrol) and other energy commodities prices using machine learning techniques, semantic analysis of algorithms used, and the taxonomy of the models adopted in the published papers. The results showed that there are studies that presented the application of machine learning models in forecasting the prices of PMS (Petrol) and other energy commodities in other countries. However, very few of them have proposed the construction of machine learning models for forecasting PMS (Petrol) and other energy commodities prices in Nigeria. This leads to the need to develop new models, especially deep learning hybrid models.

Research on public opinion sentiment classification based on attention parallel dual-channel deep learning hybrid model

The research on sentiment classification of online public opinion is helpful to the management and control of online public opinions. In the matter of the problems of previous sentiment analysis research that it is difficult to well capture text sentiment features and to identify words ambiguity, an Attention Parallel Dual-channel Deep Learning Hybrid Model (ADDHM) is proposed. Bidirectional Encoder Representations from Transformers (BERT) is applied to extract semantic features and training text vector representation. Convolutional Neural Network (CNN) and Bidirectional Long Short-term Memory (BiLSTM), introducing the attention mechanism, form a dual-channel model to extract text semantic features so as to enrich the words meaning and improve the classification level. Microblog public opinion is taken as an experiment case and hyperparameters are adjusted to find the optimal hyperparameter combination. Six comparison models are selected to verify the validity of ADDHM on four data sets. The classification accuracy of the proposed model on the four experimental data sets are respectively 96.68%, 88.86%, 89.64% and 92.72%, which are superior to the comparison model, and the ROC curve performance of the model is also the best. The performance of ADDHM is significantly different from that of the comparison models. ADDHM can effectively optimize the expression of text features and enhance the capacity of extracting text sentiment feature. It has better classification effect and is more befitting for sentiment classification of online public opinion comments.

Classification of vein pattern recognition using hybrid deep learning

Recognition of finger vein patterns is essential technique that analyses the finger vein patterns to enable accurate authentication of an individual. A proper, accurate and quick learning of patterns is essentially required for improving the classification pattern. It is essential in developing an intelligent algorithm to effectively study and classify the patterns. In this paper, we develop an improved deep learning hybrid model for feature extraction and classification. A dimensional reduction deep neural network (DR-DNN) model has included a dimensional reduction model for extracting the essential features by reducing the dimensionality of feature datasets. A convolutional neural network (CNN) helps in classifying the benign vein patterns from the malignant vein patterns. The effectiveness is compared against existing deep learning classifiers to measure how effective the deep learning model is used for classifying finger vein patterns for biometric authentication. The results shows that the proposed method achieves an accuracy rate of 97.16% for the proposed method, where the other existing methods including CNN, Recurrent Neural Network (RNN) and Deep Neural Nets (DNN) has an accuracy rate of 86%, 80.66% and 88.31%, respectively.