Hybrid Approach Of Learning Research Articles

Snow Distribution Patterns Revisited: A Physics‐Based and Machine Learning Hybrid Approach to Snow Distribution Mapping in the Sub‐Arctic

Snow Distribution Patterns Revisited: A Physics‐Based and Machine Learning Hybrid Approach to Snow Distribution Mapping in the Sub‐Arctic

Entropy generation and heatline visualization of magnetized thermal convection in an irregular enclosure filled with nanofluid and subject to non-uniform heating: FEM-machine learning hybrid approach

This investigation's primary objective is to analyze the fluid dynamics and heat transfer enhancement in an irregular enclosure. Several physical phenomena such as Alumina-water nanofluids, magnetic field, non-uniform heating and amplitude of non-uniform heating are taken into account. A thorough investigation using machine learning algorithms (MLAs) and computational fluid dynamics (CFD) is carried out. Initially, for CFD phase the coupled non-linear dimensionless governing equations of the considered problem are solved numerically by adapting a Finite Element method (FEM) using appropriate boundary conditions. The analysis considers a range of physical parameters, such as the Hartmann number (0–20), nanoparticle volume friction (0–0.04), Ryleigh number (103-105), offset temperature (0.1–1), frequency (1-10) and non-uniform heating amplitude (0.1–1). The numerical results are explicated in the form of streamlines, isotherms, heatlines structures. The impact of these factors on entropy generation is also explored. In addition, three popular MLAs, Random Forest (RF), Artificial Neural Network (ANN) and Support Vector Machine (SVM) were used to save the computational costs. The finding explore Hartmann number and nanoparticle volume friction has decreasing trend on total entropy production and heat transfer rate. The entropy production decreases up to 42.02 % for Hartman number and for nanoparticles it decreases 12.61 %. However, the non-uniform heating amplitude has opposite effect on irreversibility factor. Also, compared to other MLAs, the ANN model demonstrates more accurate predictions. The objective is to propose novel concept for enhancing the performance of cooling systems and optimizing energy utilization across diverse technical domain.

A lightweight hybrid model for the automatic recognition of uterine fibroid ultrasound images based on deep learning.

Uterine fibroids (UF) are the most frequent tumors in ladies and can pose an enormous threat to complications, such as miscarriage. The accuracy of prognosis may also be affected by way of doctor inexperience and fatigue, underscoring the want for automatic classification fashions that can analyze UF from a giant wide variety of images. A hybrid model has been proposed that combines the MobileNetV2 community and deep convolutional generative adversarial networks (DCGAN) into useful resources for medical practitioners in figuring out UF and evaluating its characteristics. Real-time automated classification of UF can aid in diagnosing the circumstance and minimizing subjective errors. The DCGAN science is utilized for superior statistics augmentation to create first-rate UF images, which are labeled into UF and non-uterine-fibroid (NUF) classes. The MobileNetV2 model then precisely classifies the photos based totally on this data. The overall performance of the hybrid model contrasts with different models. The hybrid model achieves a real-time classification velocity of 40 frames per second (FPS), an accuracy of 97.45%, and an F1 rating of 0.9741. By using this deep learning hybrid approach, we address the shortcomings of the current classification methods of uterine fibroid.

An effective data-driven machine learning hybrid approach for fault detection and classification in a standalone low-voltage DC microgrid

An effective data-driven machine learning hybrid approach for fault detection and classification in a standalone low-voltage DC microgrid

Optimizing Customer Interactions: A BERT and Reinforcement Learning Hybrid Approach to Chatbot Development

Optimizing Customer Interactions: A BERT and Reinforcement Learning Hybrid Approach to Chatbot Development

Deep learning hybrid model for analyzing and predicting the impact of imported malaria cases from Africa on the rise of Plasmodium falciparum in China before and during the COVID-19 pandemic.

Plasmodium falciparum cases are rising in China due to the imported malaria cases from African countries. The main goal of this study is to examine the impact of imported malaria cases in African countries on the rise of P. falciparum cases in China before and during the COVID-19 pandemic. A generalized regression model was used to investigate the association of time trends between imported malaria cases from 45 African countries and P. falciparum cases in 31 provinces of China from 2012 to 2018 before the COVID-19 pandemic and during the COVID-19 pandemic from October 2020 to May 2021. Based on the analysis, we proposed a statistical and deep learning hybrid approach to model the resurgence of malaria in China using monthly data of P. falciparum from 2004 to 2016. This study builds a hybrid model known as the ARIMA-GRU approach for modeling the P. falciparum cases in all provinces of China and the number of malaria deaths in China before and during the COVID-19 pandemic. The analysis showed an emerging link between the rise of imported malaria cases from Africa and P. falciparum cases in many provinces of China. Many imported malaria cases from Africa were P. falciparum cases. The proposed deep learning model achieved a high prediction accuracy score on the testing dataset of 96%. The study provided an analysis of the reduction of P. falciparum cases and deaths caused by imported P. falciparum cases during the COVID-19 pandemic due to the control measures regarding the limitation of international travel in China. The Chinese government has to prepare the imported malaria control measures after the normalization of international travel, to prevent the resurgence of malaria disease in China.

Feasibility Study of Numerical Calculation and Machine Learning Hybrid Approach for Renal Denervation Temperature Prediction

Transcatheter renal denervation (RDN) is a novel treatment to reduce blood pressure in patients with resistant hypertension using an energy-based catheter, mostly radio frequency (RF) current, by eliminating renal sympathetic nerve. However, several inconsistent RDN treatments were reported, mainly due to RF current narrow heating area, and the inability to confirm a successful nerve ablation in a deep area. We proposed microwave energy as an alternative for creating a wider ablation area. However, confirming a successful ablation is still a problem. In this paper, we designed a prediction method for deep renal nerve ablation sites using hybrid numerical calculation-driven machine learning (ML) in combination with a microwave catheter. This work is a first-step investigation to check the hybrid ML prediction capability in a real-world situation. A catheter with a single-slot coaxial antenna at 2.45 GHz with a balloon catheter, combined with a thin thermometer probe on the balloon surface, is proposed. Lumen temperature measured by the probe is used as an ML input to predict the temperature rise at the ablation site. Heating experiments using 6 and 8 mm hole phantom with a 41.3 W excited power, and 8 mm with 36.4 W excited power, were done eight times each to check the feasibility and accuracy of the ML algorithm. In addition, the temperature on the ablation site is measured for reference. Prediction by ML algorithm agrees well with the reference, with a maximum difference of 6 °C and 3 °C in 6 and 8 mm (both power), respectively. Overall, the proposed ML algorithm is capable of predicting the ablation site temperature rise with high accuracy.

Forecasting Equity using LSTM Value-at-Risk Estimation

A deep learning hybrid approach (LSTM-VaR) is proposed for risk-based stock value prediction by comparing the relationship and temporal sequence of stock value data. By utilizing time in its predictions, the model can improve accuracy and reduce volatility in stock price projections. It can anticipate changes in stock market indices and develop a reliable strategy for projecting future costs while calculating normal fluctuations of indices.

Intercultural Communicative Competence through CLIL and PBL hybrid approach: a Costa Rican perspective

This study explores the enhancement of intercultural communicative competence through content and language integrated learning and project-based learning hybrid approach of principles in English as a foreign language classroom at tertiary education in the Costa Rican context. The study conducted two pedagogical interventions for two semesters where learning principles from these approaches were combined to plan English language lessons while infusing intercultural matters of both foreign and local/home cultures. A quasi-experimental design was implemented in the Integrated English I and II courses offered at the National University of Costa Rica, Liberia campus. Participants were divided into control and experimental groups. Two Likert questionnaire scales were used to gather data. Quantitative data analysis was processed through descriptive and inferential statistics using SPSS. After the interventions, results supported the hypothesis that exposing participants to systematic intercultural hybrid methodology of principles promotes learners’ intercultural communicative competence.

A Machine Learning Hybrid Approach for Diagnosing Plants Bacterial and Fungal Diseases

Bacterial and Fungal diseases may affect the yield of stone fruit and cause damage to the Chlorophyll synthesis process, which is crucial for tree growth and fruiting. However, due to their similar visual shot-hole symptoms, novice agriculturalists and ordinary farmers usually cannot identify and differentiate these two diseases. This work investigates and evaluates the use of machine learning for diagnosing these two diseases. It aims at paving the way toward creating a generic deep learning-based model that can be embedded in a mobile phone application or in a web service to provide a fast, reliable, and cheap diagnosis for plant diseases which help reduce the excessive, unnecessary, or improper use of pesticides, which can harm public health and the environment. The dataset consists of hundreds of samples collected from stone fruit farms in the north of Jordan under normal field conditions. The image features were extracted using a CNN algorithm that was pre-trained with millions of images, and the diseases were identified using three machine learning classification algorithms: 1) K-nearest neighbour (KNN); 2) Stochastic Gradient Descent (SGD); and 3) Random Forests (RF). The resulting models were evaluated using 10-fold cross-validation, with CNN-KNN achieving the best AUC performance with a score of 98.5%. On the other hand, the CNN-SGD model performed best in Classification Accuracy (CA) with a score of 93.7%. The results shown in the Confusion Matrix, ROC, Lift, and Calibration curves also confirmed the validity and robustness of the constructed models.

Machine learning hybrid approach for the prediction of surface tension profiles of hydrocarbon surfactants in aqueous solution

HypothesisPredicting the surface tension (SFT)-log(c) profiles of hydrocarbon surfactants in aqueous solution is computationally non-trivial, and empirically challenging due to the diverse and complex architecture and interactions of surfactant molecules. Machine learning (ML), combining a data-based and knowledge-based approach, can provide a powerful means to relate molecular descriptors to SFT profiles. ExperimentsA dataset of SFT for 154 model hydrocarbon surfactants at 20–30 °C is fitted to the Szyszkowski equation to extract three characteristic parameters (Γmax,KL and critical micelle concentration (CMC)) which are correlated to a series of 2D and 3D molecular descriptors. Key (∼10) descriptors were selected by removing co-correlation, and employing a gradient-boosted regressor model to rank feature importance and carry out recursive feature elimination (RFE). The hyperparameters of each target-variable model were fine-tuned using a randomised cross-validated grid search, to improve predictive ability and reduce overfitting. FindingsThe ML models correlate favourably with test experimental data, with R2= 0.69–0.87, and the merits and limitations of the approach are discussed based on ‘unseen’ hydrocarbon surfactants. The incorporation of a knowledge-based framework provides an appropriate smoothing of the experimental data which simplifies the data-driven approach and enhances its generality. Open-source codes and a brief tutorial are provided.

The Viability of Blended Model in Undergraduate Medical Education in COVID-19 Pandemic

Introduction: With the new era of life threatening variants of Covid-19 the medical and dental education has been greatly compromised. Every school/college has to shift their educational setup to Blended model. Blended model can also be called as hybrid approach of learning or mixed mode of learning. It is an "insightful combination of Face to Face and Online opportunities for growth”. Objective: The aim of this study is to measure the viability of Blended Model through series of assessments by measuring the retention of the content after the teaching session in online and in face to face settings in Knowledge acquisition and knowledge retention test. Material & Method Methodology: This was a Quantitative Experimental study which was conducted in the Fatima Memorial college of Medicine and Dentistry Lahore. The participants were 66 of final year BDS students who voluntarily participated in the research project. Results: A total of 96 students participated in the study and it was found a significant difference between the two intervention groups regarding the mean scores of Knowledge acquisition and knowledge retention test. The PowerPoint group showed lower grades in Knowledge acquisition and knowledge retention test in comparison with Prezi group. The learning performances was evaluated from immediate learning responses in Knowledge acquisition and in long term learning retention in knowledge retention test showed that both the presentation software can be used as a presentation medium and students do learn from both but Prezi presentation software students are superior in learning performances from immediate learning to long term memory retention as compared to PowerPoint presentation software in online and in face to face settings. Conclusion: Blended model can help the medical teachers to teach the theoretical aspects of the curriculum via online and make easy schedules of student’s rotations for clinical clerkships. When it comes to clinical training, there is no shortcut or better way than face to face teaching strategy. Therefore blended learning is a viable method of teaching in this period of Covid-19. Keywords: Blended Model, Viability, Medical Education, Multimedia presentation, Covid-19

Deep learning for tilted-wave interferometry

Abstract The tilted-wave interferometer is an interferometrical measurement system for the accurate optical form measurement of optical aspheres and freeform surfaces. Its evaluation procedure comprises a high-dimensional inverse problem to reconstruct the form of the surface under test from measured data. Recent work has used a deep learning hybrid approach to solve the inverse problem successfully in a simulation environment. A quantification of the model uncertainty was incorporated using ensemble techniques. In this paper, we expand the application of the deep learning approach from simulations to measured data and show that it produces results similar to those of a state-of-the-art method in a real-world environment.

Principal component based support vector machine (PC-SVM): a hybrid technique for software defect detection.

Defects are the major problems in the current situation and predicting them is also a difficult task. Researchers and scientists have developed many software defects prediction techniques to overcome this very helpful issue. But to some extend there is a need for an algorithm/method to predict defects with more accuracy, reduce time and space complexities. All the previous research conducted on the data without feature reduction lead to the curse of dimensionality. We brought up a machine learning hybrid approach by combining Principal component Analysis (PCA) and Support vector machines (SVM) to overcome the ongoing problem. We have employed PROMISE (CM1: 344 observations, KC1: 2109 observations) data from the directory of NASA to conduct our research. We split the dataset into training (CM1: 240 observations, KC1: 1476 observations) dataset and testing (CM1: 104 observations, KC1: 633 observations) datasets. Using PCA, we find the principal components for feature optimization which reduce the time complexity. Then, we applied SVM for classification due to very native qualities over traditional and conventional methods. We also employed the GridSearchCV method for hyperparameter tuning. In the proposed hybrid model we have found better accuracy (CM1: 95.2%, KC1: 86.6%) than other methods. The proposed model also presents higher evaluation in the terms of other criteria. As a limitation, the only problem with SVM is there is no probabilistic explanation for classification which may very rigid towards classifications. In the future, some other method may also introduce which can overcome this limitation and keep a soft probabilistic based margin for classification on the optimal hyperplane.

An expert-model and machine learning hybrid approach to predicting human-agent negotiation outcomes in varied data

We present the results of a machine-learning approach to the analysis of several human-agent negotiation studies. By combining expert knowledge of negotiating behavior compiled over a series of empirical studies with neural networks, we show that a hybrid approach to parameter selection yields promise for designing more effective and socially intelligent agents. Specifically, we show that a deep feedforward neural network using a theory-driven three-parameter model can be effective in predicting negotiation outcomes. Furthermore, it outperforms other expert-designed models that use more parameters, as well as those using other techniques (such as linear regression models or boosted decision trees). In a follow-up study, we show that the most successful models change as the dataset size increases and the prediction targets change, and show that boosted decision trees may not be suitable for the negotiation domain. We anticipate these results will have impact for those seeking to combine extensive domain knowledge with more automated approaches in human-computer negotiation. Further, we show that this approach can be a stepping stone from purely exploratory research to targeted human-behavioral experimentation. Through our approach, areas of social artificial intelligence that have historically benefited from expert knowledge and traditional AI approaches can be combined with more recent proven-effective machine learning algorithms.

A review of learning theories and models underpinning technology-enhanced learning artefacts

PurposeVarious technology-enhanced learning software and tools exist where technology becomes the main driver for these developments at the expense of pedagogy. The literature reveals the missing balance between technology and pedagogy in the continuously evolving technology-enhanced learning domain. Consequently, e-learners struggle to realise the pedagogical value of such e-learning artefacts. This paper aims to understand the different pedagogical theories, models and frameworks underpinning current technology-enhanced learning artefacts to pave the way for designing more effective e-learning artefacts.Design/methodology/approachTo achieve this goal, a review is conducted to survey the most influential pedagogical theories, models and frameworks. To carry out this review, five major bibliographic databases have been searched, which has led to identifying a large number of articles. The authors selected 34 of them for further analysis based on their relevance to our research scope. The authors critically analysed the selected sources qualitatively to identify the most dominant learning theories, classify them and map them onto the key characteristics, criticism, approaches, models and e-learning artefacts.FindingsThe authors highlighted the significance of pedagogies underpinning e-learning artefacts. Furthermore, the authors presented the common and special aspects of each theory to support our claim, which is developing a hybrid pedagogical approach. Such a hybrid approach remains a necessity to effectively guide learners and allow them to achieve their learning outcomes using e-learning artefacts.Originality/valueThe authors found that different pedagogical approaches complement rather than compete with each other. This affirms our recommended approach to adopt a hybrid approach for learning to meet learners' requirements. The authors also found that a substantive consideration for context is inevitable to test our evolving understanding of pedagogy.

A Hybrid Approach of Learning and Model-Based Channel Prediction for Communication Relay UAVs in Dynamic Urban Environments

This letter presents the trajectory planning of small unmanned aerial vehicles (UAVs) for a communication relay mission in an urban environment. In particular, we focus on predicting the communication strength between air and ground nodes accurately to allow relay UAVs to maximize the communication performance improvement of networked nodes. In urban environments, this prediction is not easily achievable even with good mathematical models as each model is characterized by a series of parameters which are not trivial to obtain or estimate apriori and can vary during the mission. To address the difficulty, this work proposes to integrate a learning-based measurement technique with a probabilistic communication channel model. This hybrid approach is able to predict communication model parameters based on signal strength data that UAVs observe during the mission online, thus achieving better performance compared with the model-based approach in an urban environment. The predicted parameters are based on four discrete urban environment types. Numerical simulations validate the performance and benefit of the proposed approach.

Deep reinforcement learning for cognitive sonar

Current developments in cognitive sonar have leveraged explicit semantic representations such as ontologies to develop cognitive agents that enable adaptation of sonar settings to optimize behaviors such as waveform selection during active tracking. However, such cognitive systems based on explicit knowledge representations can be time-and-labor intensive to update in operation and limited in ultimate performance. In other applications, such as computer Go, breakthrough performance was achieved by going beyond learning from all prior games and actions of experts to allowing the algorithm to compete with itself to develop and learn from the outcome of new approaches. This hybrid approach of learning from experts and then learning via self-competition is vital for sonar applications such as active antisubmarine warfare (ASW) because ground-truthed performance data are sparse and may not display optimal solutions. Here, we discuss our application of reinforcement learning to active ASW in a simulated environment based on computational-acoustics models, including an assessment of the goal states and performance metrics we have used. The fidelity of the simulated environment is discussed in terms of the interaction with reinforcement learning and the impact on generalization from learning in simulated environments to application in real environments. [Work supported by ARiA IR&D.]

A physically based and machine learning hybrid approach for accurate rainfall-runoff modeling during extreme typhoon events

Accurate rainfall-runoff modeling during typhoon events is an essential task for natural disaster reduction. In this study, a novel hybrid model which integrates the outputs of physically based hydrologic modeling system into support vector machine is developed to predict hourly runoff discharges in Chishan Creek basin in southern Taiwan. Seven storms (with a total of 1200 data sets) are used for model calibration (training) and validation. Six statistical indices (mean absolute error, root mean square error, correlation coefficient, error of time to peak discharge, error of peak discharge, and coefficient of efficiency) are employed to assess prediction performance. Overall, superiority of the present approach especially for a longer (6-h) lead time prediction is revealed through a systematic comparison among three individual methods (i.e., the physically based hydrologic model, artificial neural network, and support vector machine) as well as their two hybrid combinations. Besides, our analysis and in-depth discussions further clarify the roles of physically based and data-driven components in the proposed framework.

A topic sentence-based instance transfer method for imbalanced sentiment classification of Chinese product reviews

The increasing interest in sentiment classification of product reviews is due to its potential application for improving e-commerce services and quality of the products. However, in realistic e-commerce environments, the review-related data are imbalanced, and this leads to a problem in which minority class information tends to be ignored during the training phase of a classification model. To address this problem, we propose a topic sentence-based instance transfer method to process imbalanced Chinese product reviews by using an auxiliary dataset (source dataset). The proposed method incorporates a rule and supervised learning hybrid approach to identify a topic sentence of each product review and adds the feature set of the topic sentence to the feature space of sentiment classification. Next, to measure the transferability of instances in source dataset, a greedy algorithm based on information gain of top-N common features is used to select common features. Then, a common feature-based cosine similarity of instances between source dataset and target dataset is introduced to select the transferable instances. Furthermore, a synthetic minority over-sampling technique (Smote) based method is adopted to overcome feature space inconsistency between the source dataset and target dataset. Finally, we immigrate the instances selected in source dataset into target dataset to form a new dataset for the training of classification model. Two datasets collected from Jingdong and Dangdang are the target dataset and source dataset. The experimental results verify that, considering the ability of generalization, our proposed method helps a support vector machine (SVM) to outperform other classification methods, such as the J48, Naive Bayes, Random Forest and Random Committee methods, when applied to datasets produced by resampling and Smote.