Search

One of the most common themes that has come out of the transition to remote learning has been the lack of preparation provided to teachers to be able to teach in mediums outside of the traditional classroom as a part of their pre-service and in-service teacher preparation programs. For educators to be better prepared for the next short-term or long-term disruption that might occur, more teacher preparation programs need to include curriculum related to the provision of K-12 distance learning. [Extracted from the article]

Literature reviews as standalone papers serve various purposes; these include the development of new theories, the shaping of future research, the production or knowledge dissemination, and support of evidence-based practices. Review papers, as a foundational block of the research process, may promote further research with higher level of quality. However, in some cases, this methodological approach raises questions about their scientific rigor, trustworthiness, systematicity, and transparency. The main goal of this study is to assess transparency levels in previous review papers pertaining to blended learning in higher education. To complete this goal, this study collects and analyzes information about the report of methodological decisions and research activities in 40 review papers. As a result, in this descriptive review paper, we identify some patterns about the type of reviews and their transparency levels. Findings also demonstrate that most efforts (80%) remain focused on describing a phenomenon in the formats of narrative reviews (65%) and descriptive reviews (15%). These types of papers show low levels of transparency in their reporting process. Nevertheless, trends indicate in the last 5 years an increase in other types of published review papers such as critical, meta-analysis, and qualitative systematic reviews. This represents an important shift in the research domain. Finally, we argue that, regardless of its type, each review paper should have a minimum level of transparency in order to ensure trustworthiness in the research process. [ABSTRACT FROM AUTHOR]

In this paper we review selected significant developments in the use of digital technology in the teaching and learning of mathematics over the last five years. We focus on a number of important topics in this field, including the evolvement of STEAM and critical making as well as the process of redefining learning spaces in the transformation of the mathematics classroom. We also address the increasing use of computer algebra systems and dynamic geometry packages; and the issue of student collaboration online, especially using learning environments and social media. We briefly touch on artificial intelligence systems, including hyper-personalisation of learning, multimodality and videos. We include a brief discussion on the impact of COVID-19 on mathematics education, and lastly on the more theoretical perspective of the epistemology of digital technology and the construct of humans-with-media. We conclude the discussion with some possible concerns and mentioning some possible new topics for research in the field. [ABSTRACT FROM AUTHOR]

During COVID-19, universities across the globe experienced a rapid requirement to move to online learning and teaching provision. This rapid move has been explored as emergency remote education (ERE). This paper reviews and presents some emerging literature regarding ERE, demonstrating how this created an environment where technology-mediated abuse could arise within the university context. Intentional and unintentional forms of technology-mediated abuse, within a global context, are considered with account of how intersectional characteristics can impact. The paper concludes with a set of provocations explored within an example framework. The provocations are given to situate ways of thinking which are facilitative of safer and more respectful use of technological spaces. Both the provocations and example framework aim to be useful critical tools for program and module teams to adapt in higher education institutions within the online sphere. The phenomenon of ERE is an opportunity to consider what can be learned with regard to management of technology-mediated abuse. However, a focus on ERE presents limitations in the paper because of the smaller number of academic sources at this time, due to recency of the COVID-19 pandemic. [ABSTRACT FROM AUTHOR]

Accurate assessment of road conditions can effectively alleviate traffic congestion and guide people's travel plans, traffic control decisions of transportation departments, and formulation of traffic-related laws and regulations. This paper proposes a quantum particle swarm optimization (QPSO) and adaptive hybrid exponential smoothing with residual correction (AHES-RC) for the nonlinearity and randomness of traffic flow. In the proposed algorithm, the single–double-exponential smoothing method is mixed with adaptive weights to form AHES, a new method of mixing weights according to real-time traffic trend changes. After the residual correction of AHES is calculated by the extreme learning machine algorithm, the parameters of AHES-RC are optimized using QPSO to improve the prediction accuracy further. This paper comprehensively compares the QPSO-AHES-RC algorithm with other benchmark models through testing on 26 real-world data sets. The results show that the proposed algorithm can adaptive forecasting under various traffic conditions, yielding the best forecasting performance in terms of various forecast error metrics. Compared with advanced machine learning algorithms such as XGBoost and CatBoost, the mean RMSE and mean MAPE have been improved by over 20% on average. In addition, it is revealed that the real-time dynamic capture of traffic flow can effectively improve prediction accuracy. [ABSTRACT FROM AUTHOR]

With the rapid application of blended learning around the world, a large amount of literature has been accumulated. The analysis of the main research topics and development trends based on a large amount of literature is of great significance. To address this issue, this paper collected abstracts from 3772 eligible papers published between 2003 and 2021 from the Web of Science core collection. Through LDA topic modeling, abstract text content was analyzed, then 7 well-defined research topics were obtained. According to the topic development trends analysis results, the emphasis of topic research shifted from the initial courses about health, medicine, nursing, chemistry and mathematics to learning key elements such as learning outcomes, teacher factors, and presences. Among 7 research topics, the popularity of presences increased significantly, while formative assessment was a rare topic requiring careful intervention. The other five topics had no significant increase or decrease trends, but still accounted for a considerable proportion. Through word cloud analysis technology, the keyword characteristics of each stage and research focus changes of research were obtained. This study provides useful insights and implications for blended learning related research. [ABSTRACT FROM AUTHOR]

To counterbalance the abilities of global exploration and local exploitation of algorithm and enhance its comprehensive performance, a multi-objective particle swarm optimization with a competitive hybrid learning strategy (CHLMOPSO) is put forward. With regards to this, the paper first puts forward a derivative treatment strategy of personal best to promote the optimization ability of particles. Next, an adaptive flight parameter adjustment strategy is designed in accordance with the evolutionary state of particles to equilibrate the exploitation and exploration abilities of the algorithm. Additionally, a competitive hybrid learning strategy is presented. According to the outcomes of the competition, various particles decide on various updating strategies. Finally, an optimal angle distance strategy is proposed to maintain archive effectively. CHLMOPSO is compared with other algorithms through simulation experiments on 22 benchmark problems. The results demonstrate that CHLMOPSO has satisfactory performance. [ABSTRACT FROM AUTHOR]

Sentiment analysis of scientific citations has received much attention in recent years because of the increased availability of scientific publications. Scholarly databases are valuable sources for publications and citation information where researchers can publish their ideas and results. Sentiment analysis of scientific citations aims to analyze the authors' sentiments within scientific citations. During the last decade, some review papers have been published in the field of sentiment analysis. Despite the growth in the size of scholarly databases and researchers' interests, no one as far as we know has carried out an in-depth survey in a specific area of sentiment analysis in scientific citations. This paper presents a comprehensive survey of sentiment analysis of scientific citations. In this review, the process of scientific citation sentiment analysis is introduced and recently proposed methods with the main challenges are presented, analyzed and discussed. Further, we present related fields such as citation function classification and citation recommendation that have recently gained enormous attention. Our contributions include identifying the most important challenges as well as the analysis and classification of recent methods used in scientific citation sentiment analysis. Moreover, it presents the normal process, and this includes citation context extraction, public data sources, and feature selection. We found that most of the papers use classical machine learning methods. However, due to limitations of performance and manual feature selection in machine learning, we believe that in the future hybrid and deep learning methods can possibly handle the problems of scientific citation sentiment analysis more efficiently and reliably. [ABSTRACT FROM AUTHOR]

From a design perspective, this paper offers a response to the impact, value, and application of a manuscript published by Philipsen et al. (Improving teacher professional development for online and blended learning: A systematic meta-aggregative review. Educational Technology and Research Development, 67, 1145–1174. https://doi.org/10.1007/s11423-019-09645-8, 2019). Philipsen et al. (2019) reviewed what constitutes an effective teacher professional development program (TPD) for online and blended learning (OBL), with our response focusing on its value and application in light of an emergency shift to digital to address a global pandemic. This paper also proceeds to examine limitations in previous research into the subject and future research opportunities to investigate important components that inform the design of a resilient and scalable TPD for OBL. [ABSTRACT FROM AUTHOR]

This paper provides a response to the work of Philipsen et al. (Educ Technol Res Dev 67:1145–1174, Philipsen et al., Educational Technology, Research and Development 67:1145–1174, 2019), from a critical pedagogy perspective. Here, critical pedagogy is defined from a post-colonial framework focused on liberation. From this perspective, the value of Philipsen et al.'s paper is in its implicit alignment with critical methodologies, including how liberatory ideas are embedded in the TPD for OBL framework. In a response to Philipsen et al.'s work, this paper provides advice on practical actions teachers can take to develop their ability to engage in critical pedagogy, both from the TPD for OBL lens and from an equity lens. This paper concludes with a discussion of the limitations of the meta-aggregative review, including the lack of an explicitly critical framework, and it provides suggestions for how the work could be improved, especially as regards a discussion of equity for teachers and students. Future research in this area should focus on methods for disrupting educational inequity regarding online and blended learning. [ABSTRACT FROM AUTHOR]

Renewable microgrids enhance security, reliability, and power quality in power systems by integrating solar and wind sources, reducing greenhouse gas emissions. This paper proposes a machine learning approach, leveraging Gaussian Process (GP) and Krill Herd Algorithm (KHA), for energy management in renewable microgrids with a reconfigurable structure based on remote switching of tie and sectionalizing. The method utilizes Gaussian Process (GP) for modeling hybrid electric vehicle (HEV) charging demand. To counteract HEV charging effects, two scenarios are explored: coordinated and intelligent charging. A novel optimization method inspired by the Krill Herd Algorithm (KHA) is introduced for the complex problem, along with a self-adaptive modification to tailor solutions to specific situations. Simulation on an IEEE microgrid demonstrates efficiency in both scenarios. The predictive model yields a remarkably low Mean Absolute Percentage Error (MAPE) of 1.02381 for total HEV charging demand. Results also reveal a reduction in microgrid operation cost in the intelligent charging scenario compared to coordinated charging. [ABSTRACT FROM AUTHOR]

In the contemporary digitalised knowledge society, work-integrated professional development is an important and continuous activity. Continuous professional development should preferably be a hybrid format, where academia collaborates with industry and the surrounding society in a multi-directed exchange of ideas. Continuous professional development is today conducted in a blend of workplace activities, and in technology enhanced online environments. A complex blend for professionals that at the same time are working full-time with their ordinary jobs. The need for a support model to navigate in these new digital learning spaces is obvious, where the support model also should include collaboration and a community of practice. A community where the members communicate regularly to improve their skills and knowledge in their common professional domain. The aim of this paper is to describe and analyse the development of a support model that involves these aspects. Findings confirm the necessity of the four steps in the earlier model, at the same time as they indicate the need for a fifth step facilitating the creation of Communities and Landscapes of Practice. The use of the model may support higher education institutions in creating beneficial conditions for hybrid work-integrated continuous professional development for industry. [ABSTRACT FROM AUTHOR]

Noising in X-ray imaging has been one of the biggest challenges that leads to insufficient and improper diagnosis. Despite the fact that X-rays are one of the most widespread and acceptable imaging techniques among the medical and scientific fraternity, still Gaussian and Poisson noise lead to a lot of image deterioration. Over the past few decades, several denoising techniques have been explored using traditional, hybrid and deep learning techniques which have been reported in this paper. Poisson noise was best removed by the application of bilateral filter with a maximum Peak Signal to Noise Ratio (PSNR) of 36.22 and for the removal of Gaussian noise, median filter proved to be unparalleled with a PSNR of 32.92 for the variance of 0.01, 31.4 for the variance of 0.04, 31.03 for the variance of 0.07, and 30.58 for the variance of 0.1 amongst the conventional filters. The Noise2Noise model employing the deep learning approach has given the best PSNR value of 34.38 amongst all the other alternatives for the images with gaussian noise. This paper serves as a comprehensive review for beginners working in this domain, that would aid them to select the best filter for the image pre-processing and noise removal. [ABSTRACT FROM AUTHOR]

The main goal of this research is to improve the personification of learning in higher education. The proposed flexible model for organizing blended and distance learning in higher education involves the creation of an individual learning path through testing students before the start of training. Based on the learning outcomes, the student is credited to the learning path. The training path consists of mandatory and additional modules for training; additional modules can be skipped after successfully passing the test, without studying these modules. The paper examines the composition of intelligent learning systems: student model, learning model and interface model. A student model is described, which contains the level of their knowledge, skills and abilities, the ability to learn, the ability to complete tasks (whether they know how to use the information received or not), personal characteristics (type, orientation) and other factors. The student's model is described by a mathematical formula. Thus, being described using logical rules, which have formed the basis for the software implementation of mixed and distance learning rules for lifelong learning courses. There is an interface model presented in the paper, and the results of the course of the proposed flexible model for the organization of mixed and distance learning "Digital Skills of a Modern Teacher in the Context of Distance Learning", as well as the face-to-face course "Digital Learning for Everyone" before the start of the pandemic which is close in its content to the course under study. Based on the results of the analysis, we introduced criteria for the effectiveness of the training course, proposed the weighting coefficients for evaluating the training course, carried out the assessment and drew conclusions. [ABSTRACT FROM AUTHOR]

Pathophysiology describes and explains the physiological dysfunctions that occur in human diseases. Pathophysiology is content heavy, often leading to medical/biomedical science students adopting a surface approach to learning. To encourage more engagement, we developed clinical simulation practical classes using manikin patients. Students considered these were more effective than paper-based case studies. However, they found the first encounter with the manikins daunting. In addition, they did not have a strong sense of responsibility towards the outcome of their treatment choices largely because they recognized this as a simulated experience. Video is a powerful teaching tool to demonstrate situations that are difficult to explain in words, to see theory applied to practice or create enthusiasm and confidence in the viewer regarding the use of new practices. In this study, we evaluated the effectiveness of exposure to a video scenario, in which a high-fidelity manikin was used as the 'patient', before the students' own interactions with the manikin in later classes. Survey results suggested that the students felt more engaged with the case study. They felt the video helped them appreciate aspects of clinical communication and prepare for their time in the simulation laboratory interacting with the manikin. They saw the video as a useful addition to the written case study notes. Their criticisms were mainly around the production quality. This study supports the use of video scenarios as a valuable adjunct to the teaching of pathophysiology to medical/biomedical science students when using either paper- or simulation-based case studies. [ABSTRACT FROM AUTHOR]

Although university students use their digital devices for almost everything, current studies shows that students have difficulties with digital learning because they lack in self-regulated skills which in return lead to low performance. Self-regulated learning strategies (SRLS) are used assist students to learn efficiently. While many researchers have investigated SRLS towards academic outcomes such as grades, little is known about the use of SRLS towards non-academic outcomes that are also essential to assist university students' learning progression. Hence, there is a need to understand how best to utilise SRLS to drive positive non-academic outcomes in digital learning within a blended learning environment. The systematic review methodology follows PRISMA guidelines to explore the current literature. Different sources were searched using predefined search items. A total of 239 retrievals were found which were screened for duplication. A closer screening was done on the abstracts and titles of 239 papers after duplication removal. 28 full text papers were evaluated for eligibility. Finally, 14 papers were then selected for the review. Most of the papers included in the review were peer-reviewed articles published in social science and educational journals. List of self-regulated learning strategies and non-academic outcomes used in a blended learning environment in higher education institutions were identified. Majority of the 14 reviewed papers investigated metacognitive knowledge, resource management and motivational belief strategies towards learning performance whereas cognitive engagement strategies was the least researched. Results revealed that generally, SRLS positively correlate with non-academic outcomes. At the end of the review, research gap and the future direction are presented. [ABSTRACT FROM AUTHOR]

This paper aims to examine the current dynamics of the flipped classroom studies and to propose a direction for future research for the field. Using a bibliometric approach, we observe a sample of 1557 documents from the Scopus database to identify research activity on the flipped classroom. The keywords "flipped classroom" and "flipped learning" have been executed in the search query. We presented the earlier stage of research in the flipped classroom, the subsequent trends, publications status based on source title, country and institution and examined citations pattern of the publication. We also discuss the themes based on the occurrences and terms of the keywords, title and abstract of the documents. This paper also predicts the future study in the flipped classroom using Lotka's law. We found that the pattern distribution of the author's contribution fits with the law. We conclude by suggesting a few potential research directions on the flipped classroom. Research on flipped classroom focuses on approaches, strategies and effectiveness perceived by practitioners and learners with relatively less attention on author's contribution and the prediction on their future and sustainable contribution and networking in guaranteeing the survival and expansion of flipped classroom approach for the coming decades. [ABSTRACT FROM AUTHOR]

Time series forecasting models are gaining traction in many real-world domains as valuable decision support tools. Stock market analysis is a challenging domain, characterized by a complex multi-variate and time-evolving nature, with high volatility, and multiple correlations with exogenous factors. Autoregressive, machine learning, and deep learning models for temporal data have been adopted thus far to solve this task. However, they are usually limited to the analysis of a single data source or modality, and do not collectively deal with all the inherent challenges and complexities presented by stock market data. In this paper, inspired by the promising learning capabilities of hybrid ensemble methods, we propose a novel stacking ensemble approach for stock market prediction that jointly considers news headlines, multi-variate time series data, and multiple base models as predictors. By taking multiple factors into consideration, our model is able to learn historical patterns leveraging multiple data sources and models. Our experiments showcase the ability of our model to outperform popular baselines on next-day stock market trend prediction. A portfolio analysis reveals that our method is also able to yield potential gains or capital preservation capabilities when its predictions are exploited for trading decisions. [ABSTRACT FROM AUTHOR]

Present-day demand and supply of connectivity necessitate the rapid production of Microwave (MW) filter units. The production of these filters is then followed by the step of utmost importance in the assembly line, viz., the 'tuning of the filter', as tuning is crucial to meeting the selectivity requirements of the band. Since the advent of filters, tuning has always been done manually, and hence it is considered a bottleneck by experts in the field. Thus, the need to automate the system is highly implied. The goal of the current work is to outline various MW filter tuning techniques that have been advocated by the community of researchers. The limitations of the said research works and their comparative analysis are also encapsulated in tabular form in the present paper. The paper ends with the implementation of an Expert-Based Hybrid Deep Learning Algorithm to fully automate the filter tuning process. [ABSTRACT FROM AUTHOR]

In this paper, we propose a method for predicting epileptic seizures using a pre-trained model utilizing supervised contrastive learning and a hybrid model combining residual networks (ResNet) and long short-term memory (LSTM). The proposed training approach encompasses three key phases: pre-processing, pre-training as a pretext task, and training as a downstream task. In the pre-processing phase, the data is transformed into a spectrogram image using short time Fourier transform (STFT), which extracts both time and frequency information. This step compensates for the inherent complexity and irregularity of electroencephalography (EEG) data, which often hampers effective data analysis. During the pre-training phase, augmented data is generated from the original dataset using techniques such as band-stop filtering and temporal cutout. Subsequently, a ResNet model is pre-trained alongside a supervised contrastive loss model, learning the representation of the spectrogram image. In the training phase, a hybrid model is constructed by combining ResNet, initialized with weight values from the pre-trained model, and LSTM. This hybrid model extracts image features and time information to enhance prediction accuracy. The proposed method's effectiveness is validated using datasets from CHB-MIT and Seoul National University Hospital (SNUH). The method's generalization ability is confirmed through Leave-one-out cross-validation. From the experimental results measuring accuracy, sensitivity, and false positive rate (FPR), CHB-MIT was 91.90%, 89.64%, 0.058 and SNUH was 83.37%, 79.89%, and 0.131. The experimental results demonstrate that the proposed method outperforms the conventional methods. [ABSTRACT FROM AUTHOR]

This paper reports a comprehensive review of literature on personalised learning in STEM and STEAM (or STE(A)M) education, which involves the disciplinary integration of Science, Technology, Engineering, and Mathematics, as well as Arts. The review covered the contexts of STE(A)M education where personalised learning was adopted, the objectives of personalised learning and research issues, and various aspects of practising personalisation. A total of 72 publications from 2011 to 2020 were collected from Scopus for review. The results reveal the widespread studies in this area across various countries/territories, levels of education, subject disciplines, and modes of education. The most common objective of personalised learning lied in catering for learning styles. The issue most frequently addressed focused on evaluating the effectiveness of technologies for personalised learning. Blended learning and learning analytics are the most popular means to achieve personalised learning. Among various aspects of learning, learning material is the one most frequently addressed. Also, the factors and criteria for personalising learning were summarised, which reveal the heterogeneous nature of learners who have their own learning ability, interest, style and progress. The results suggest more research on interdisciplinary and integrative approaches for STE(A)M learning to examine how personalisation can be applied effectively, as well as more investigation on integrating personalisation with the pedagogies and elements commonly introduced to STE(A)M education. [ABSTRACT FROM AUTHOR]

Although the use of educational technology to support online and distance learning is, arguably, a mature field (Broadbent and Poon [5]; Stephenson [23]), students' learning ultimately happens where the student is (Lave and Wenger [11]). This special issue responds to the growing interest in this theme as observed in a series of workshops, titled Learning Analytics Across Spaces (CrossLAK), organised at the International Conference on Learning Analytics and Knowledge in 2016 and 2017 (Martinez-Maldonado et al. [14]). This paper illustrates the potential of harnessing more sources of evidence about students' behaviour in more than one digital space to build more effective predictive analytics systems that can be used in blended classroom settings. 10 Kitto, K., Cross, S., Waters, Z., Lupton, M.: Learning analytics beyond the LMS: the connected learning analytics toolkit. [Extracted from the article]

Growing use of the internet in educational contexts has been prominent in recent years. In this survey paper, we describe how the internet is transforming the mathematics classroom and mathematics teacher education. We use as references several reviews of use of the internet in mathematics education settings made in recent years to determine how the field has evolved. We identify three domains in which new approaches are being generated by mathematic educators: principles of design of new settings; social interaction and construction knowledge; and tools and resources. The papers in this issue reflect different perspectives developed in the last decade in these three domains, providing evidence of the advances in theoretical frameworks and support in the generation of new meanings for old constructs such as 'tool', 'resources' or 'learning setting'. We firstly highlight the different ways in which the use of digital technologies generates new ways of thinking about mathematics and the settings in which it is learnt, and how mathematics teacher educators frame the new initiatives of initial training and professional development. In this survey paper, we identify trends for future research regarding theoretical and methodological aspects, and recognise new opportunities requiring further engagement. [ABSTRACT FROM AUTHOR]

Weatherby, Clark-Wilson, Cukurova and Luckin are up next, with the importance of boundary objects in industry-academia collaborations to support evidencing the efficacy of educational technology. Welcome to the September 2022 issue of I TechTrends i ! Educational robotics is the topic of the next paper by Socratous and Ioannou where they compare the effect of a structured versus an unstructured educational robotics curriculum on students' group metacognition during collaborative problem-solving. [Extracted from the article]

Flipped classroom (FC) approaches have gotten substantial attention in the last decade because they have a potential to stimulate student engagement as well as active and collaborative learning. The FC is generally defined as a strategy that fips the traditional education setting, i.e., the information transmission component of a traditional face-to-face lecture is moved out of class time. The FC relies on technology and is therefore suitable for online or blended learning, which were predominant forms of learning during the COVID-19 pandemic (March 2020-July 2021). In this paper we present a systematic literature review (SLR) of studies that covered online FC approaches in higher education during the pandemic. We analyzed 205 publications in total and 18 in detail. Our research questions were related to the main findings about the success of implementation of online FC and recommendations for future research. The findings indicated that those who had used FC approaches in face-to-face or blended learning environments more successfully continued to use them in online environments than those who had not used it before. The SLR opened possible questions for future research, such as the effectiveness of the FC for different courses and contexts, the cognitive and emotional aspects of student engagement, and students' data protection. It pointed to the need to examine different aspects of online delivery of the FC more comprehensively, and with more research rigor. [ABSTRACT FROM AUTHOR]

In recent years, intrusion detection systems (IDSs) have increasingly come to be regarded as a significant method due to their potential to develop into a key component that is necessary for the safety of computer networks. This work focuses on the usage of extreme learning machines, which are also known as ELMs, with the purpose of spotting prospective intrusions and assaults. The proposed method combines the self-adaptive differential evolution method for optimising network input weights and hidden node biases and multi-node probabilistic approach with the extreme learning machine for deriving network output weights. This body of work presents an innovative method of learning that can be put into practice in order to determine whether or not an incursion has taken place in the system that is the focus of the investigation that is being carried out by this body of work. A hybrid extreme learning machine is used in the execution of this strategy. When there is one thousand times more traffic on a network, the ability of regular IDS systems to detect malicious network intrusions is lowered by a factor of one hundred. This is because there are less opportunities to detect the intrusions. This is due to the fact that there are less probabilities to identify potential dangers. This paper lays the groundwork for a novel methodology for identifying malicious network breaches. The findings of the simulation demonstrated that putting into practice the approach that was proposed resulted in an improvement in the accuracy of the scenario's classification while it was being investigated. The implementation of the method seems to have produced the desired results. [ABSTRACT FROM AUTHOR]

This essay discusses a potential method for predicting the behavior of various physical processes and uses the COVID-19 outbreak to demonstrate its applicability. This study assumes that the current data set reflects the output of a dynamic system that is governed by a nonlinear ordinary differential equation. This dynamic system may be described by a Differential Neural Network (DNN) with time-varying weights matrix parameters. A new hybrid learning scheme based on the decomposition of the signal to be predicted. The decomposition considers the slow and fast components of the signal which is more natural to signals such as the ones corresponding to the number of infected and deceased patients who suffered of COVID 2019 sickness. The paper results demonstrate the recommended method offers competitive performance (70 days of COVID prediction) in comparison to similar studies. [ABSTRACT FROM AUTHOR]

Computer-assisted instructional programs such as intelligent tutoring systems are often used to support blended learning practices in K-12 education, as they aim to meet individual student needs with personalized instruction. While these systems have been shown to be effective under certain conditions, they can be difficult to integrate into pedagogical practices. In this paper, we introduce three group formation algorithms that leverage learning data from the adaptive intelligent tutoring system ALEKS to support pedagogical and collaborative learning practices with ALEKS. Each grouping method was devised for different use cases, but they all utilize a fine-grained multidimensional view of student ability measured across several hundred skills in an academic course. As such, the grouping algorithms not only identify groups of students, but they also determine what areas of ALEKS content each group should focus on. We then evaluate each of the three methods against two alternative baseline methods, which were chosen for their plausibility of being used in practice—one that groups students randomly and one that groups students based on a unidimensional course score. To evaluate these methods, we establish a set of practical metrics based on what we anticipate teachers would care about in practice. Evaluations were performed by simulating mock groupings of students at different time periods for real ALEKS algebra classes that occurred between 2017 and 2019. We show that each devised method obtains more favorable results on the specified metrics than the alternative methods under each use-case. Moreover, we highlight examples where our methods lead to more nuanced groupings than grouping based on a unidimensional measure of ability. [ABSTRACT FROM AUTHOR]

The purpose of this study was to conduct a three-way comparison of face-to-face, online, and blended teaching modalities in an undergraduate Child Development course to determine if there were differences in student academic outcomes and course satisfaction across modalities. Student academic outcomes were measured by three examinations, one research paper assignment, and the overall course total grade. Course satisfaction was measured by administering the Student Opinion Questionnaire (SOQ) across the three teaching modalities and the Constructivist On-Line Learning Environment Survey (COLLES) to online and blended modalities. Results indicated that students performed equally well on all three examinations, research paper, and the overall course total grade across three teaching modalities, allaying traditional reservations about online and blended teaching efficacy. The SOQ and COLLES analysis found students from the three modalities were equally satisfied with their learning experiences. A Two-Factor Model identifying Face-to-Face Interaction and Learn on Demand (Flexibility) as factors determining student academic outcomes was proposed. Implications, limitations, and future research direction were discussed. [ABSTRACT FROM AUTHOR]

A web application is a software system that provides an interface to its users through a web browser on any operating system (OS). Despite their growing popularity, web application security threats have become more diverse, resulting in more severe damage. Malware attacks, particularly SQLI attacks, are common in poorly designed web applications. This vulnerability has been known for more than two decades and is still a source of concern. Accordingly, different techniques have been proposed to counter SQLI attacks. However, the majority of them either fail to cover the entire scope of the problem. The structured query language injection (SQLI) attack is among the most harmful online application attacks and often happens when the attacker(s) alter (modify), remove (delete), read, and copy data from database servers. All facets of security, including confidentiality, data integrity, and data availability, can be impacted by a successful SQLI attack. This paper investigates common SQLI attack forms, mechanisms, and a method of identifying, detecting, and preventing them based on the existence of the SQL query. Here, we have developed a comprehensive framework for detecting and preventing the effectiveness of techniques that address specific issues following the essence of the SQLI attacks by using traditional Navies Bayes (NB), Decision Trees (DT), Support Vectors Machine (SVM), Random Forests (RF), Logistic Regression (LR), and Neural Networks Based on Multilayer Perceptron (MLP), and hybrid approach are used for our study. The machine learning (ML) algorithms were implemented using the Keras library, while the classical methods were implemented using the Tensor Flow-Learn package. For this proposed research work, we gathered 54,306 pieces of data from weblogs, cookies, session usage, and from HTTP (S) request files to train and test our model. The performance evaluation results for training set in metrics such as the hybrid approach (ANN and SVM) perform better accuracies in precision (99.05% and 99.54%), recall (99.65% and 99.61%), f1-score (99.35% and 99.57%), and training set (99.20% and 99.60%) respectively than other ML approaches. However, their training time is too high (i.e., 19.62 and 26.16 s respectively) for NB and RF. Accordingly, the NB technique performs poorly in accuracy, precision, recall, f1-score, training set evaluation metrics, and best in training time. Additionally, the performance evaluation results for test set in metrics such as hybrid approach (ANN and SVM) perform better accuracies in precision (98.87% and 99.20%), recall (99.13% and 99.47%), f1-score (99.00% and 99.33%) and test set (98.70% and 99.40%) respectively than other ML approaches. However, their test time is too high (i.e., 11.76 and 15.33 ms respectively). Accordingly, the NB technique performs poorly in accuracy, precision, recall, f1-score, test set evaluation metrics, and best in training time. Here, among the implemented ML techniques, SVM and ANN are weak learners. The achieved performance evaluation results indicated that the proposed SQLI attack detection and prevention mechanism has been improved over the previously implemented techniques in the theme. Finally, in this paper, we aimed to keep researchers up-to-date, with contributions, and recommendations to the understanding of the intersection between SQLI attacks and prevention in the artificial intelligence (AI) field. [ABSTRACT FROM AUTHOR]

Learning to rank (LTR) is the process of constructing a model for ranking documents or objects. It is useful for many applications such as Information retrieval (IR) and recommendation systems. This paper introduces a comparison between Offline and Online (LTR) for IR. It also proposes a novel Offline (1 + 1)-Simulated Annealing Strategy (SAS-Rank) and introduces the first Hybrid Online–Offline LTR techniques using SAS-Rank and ES-Rank with Online Dependent Click Model (DCM). SAS-Rank is a combination of Simulated Annealing method and Evolutionary Strategy. From the obtained experimental results, we can conclude that the Offline LTR techniques outperformed the well-known Online Dependent Click Model (DCM) technique. Moreover, the Hybrid Online–Offline SAS-Click outperformed the predictive ranking results on unseen data in most evaluation fitness metrics using LETOR 4 dataset compared to other approaches. On the other hand, Hybrid ES-Click is a competitive approach with SAS-Click in evolving ranking models for training and validation data. Regarding Offline LTR, the SAS-Rank outperformed the well-known ES-Rank which has been compared in previous studies with fourteen machine learning techniques. This research uses the best available Linear LTR approaches existing in the literature which are offline ES-Rank with Online DCM. The linear LTR approach output is a linear ranking model which can be represented as a vector of feature importance weights. This paper demonstrated the results and findings obtained using the LETOR 4 dataset, and Java Archive Package is provided for facilitating reproducible research. [ABSTRACT FROM AUTHOR]

The COVID-19 pandemic has forced a significant increase in the utilization of video-based e-learning platforms for programming education. These platforms never considered the essential attributes of student characteristics and learning preferences while designing such a problematic subject having high dropout and failure rates. The traditional e-learning environments deliver instructional videos to the learners by assuming all learners have a single learning preference. Moreover, existing learning style models need to address the recent requirements of e-learning paradigms. To address this issue, this paper presents a novel learning style model tailored for instructional video-based programming e-learning environments that map individual learning preferences with various video design patterns. An adaptive e-learning environment was employed to assess the effectiveness of the proposed model that leveraged a decision tree classifier to divide learners into four preferences. In a paired experimental design, 195 first-year undergraduate students were randomly assigned to one of three groups where learner scores and feedback were taken as evaluation metrics. The control group partook without instructional videos for the entire semester of six months. During the same period, experimental group-1 learned with a traditional video-based e-learning environment, and experimental group-2, with the proposed learning style model, enabled an adaptive e-learning environment. Based on the proposed decision tree learning model, it is understood that the intervention group showed significant improvements in knowledge acquisition, grade, and positive feedback compared to the other groups. Hence, the proposed model is highly recommended for traditional programming e-learning environments to deliver instructional videos based on learners' learning preferences. [ABSTRACT FROM AUTHOR]

They analyzed self-reported survey data from 572 undergraduate students from a teacher education university in Southwest China, and found that relatedness had effects on perceived learning gains and satisfaction mediated by online self-regulated learning. The COVID-19 pandemic has greatly impacted students' opportunities to learn worldwide. It is important to think about and promote teacher wellbeing in a more holistic way (both negative and positive), which benefit both student and teacher learning. Currently, there are many theories and principles for better engaging students in online environments (Chiu et al., [4]; Ryan & Deci, [9]); however, teachers may not able to execute the theoretical ideas in teaching. [Extracted from the article]

Community college student perceptions of remote learning shifts due to COVID-19 are reported next by Christopher Prokes and Jacqueline Housel. Following Siyam and Hussain, Torrey Trust and colleagues explore why educators are motivated to learn about new technologies, such as augmented reality (AR), virtual reality (VR) and 3D printers, what they already know about these tools, and what they want to know. The original papers begin with a technoethical audit of Google by Daniel G. Krutka, Ryan M. Smits, and Troy A. Willhelm which addresses ethical, legal, democratic, economic, technological, and pedagogical concerns educators, students, and community members should consider. [Extracted from the article]

An efficient carbon trading market can effectively curb excessive carbon emissions and thus slow down the pace of global warming, which heightens the necessity of improving the accuracy of carbon price forecasting. In order to overcome the weakness of previous prediction model that always trained data in one-way neural networks and propagated the data sequentially, this paper proposes a novel hybrid learning paradigm WPD-ISSA-BiLSTM combining wavelet packet decomposition (WPD), improved sparrow search algorithm (ISSA), and Bi-directional long short-term memory network for deep feature exploration of carbon prices. Firstly, WPD decomposes and reconstructs the original carbon price series into several independent subseries. Then, the input features of the all subseries are filtered with random forest to select the best input features for the prediction model. Finally, a Bi-directional long short-term memory network optimized by the ISSA is employed to deeply delineate the intrinsic evolutionary trends of carbon prices, and the prediction results of all subseries are superimposed on each other to obtain the final carbon price prediction results. The actual carbon emission trading prices are collected as input to the model, and the experimental results show that the RMSE values of the proposed model are 0.2516 and 0.2962 under the mild and severe volatility scenarios, respectively. The proposed model has superiority and robustness compared to the comparison model and several existing models and better understands the intrinsic correlation between historical carbon price data. The results of this study can provide meaningful references for the carbon market development and emission reduction pathways. [ABSTRACT FROM AUTHOR]

This research investigates the relationship between self-regulated learning awareness, procrastination, and learning behaviors in a blended learning environment. Participants included 179 first-grade university students attending a blended learning-style class that used a learning management system. Data were collected using questionnaires on participants' self-regulated learning awareness, academic behavior awareness for procrastination, and a datalog on the timeliness of their report submissions to quantify learning behaviors. Participants answered both pre- and post-class questionnaires. As regards learning behaviors, report and 1-min paper submission time values were collected using the learning management system. The results revealed that internal value, self-regulation, and procrastination are fundamental elements that enhance the awareness of time management for planned learning. Positive time management awareness promotes the submission of the 1-min paper report within the deadline and of the regular report early. [ABSTRACT FROM AUTHOR]

The use of writing in science classrooms is important to facilitate students' conceptual understanding of science concepts. They analyzed student and instructor feedback from surveys and interviews from science courses in university. They also found that students' problem-solving beliefs could directly influence students' STEM career perceptions. They found that informal STEM project-learning activities improve their STEM perceptions. [Extracted from the article]

This paper reflects on the findings of Borup et al. (Educ Technol Res Dev 63:161–184, 2015) regarding the efficiency and affect of text and video feedback in the context of the rapid shift to online education due to the COVID-19 pandemic. Based on reports of diminished mental wellness, increased depression, and anxiety among learners and instructors, this paper offers ideas on how to apply the findings from Borup et al. (Educ Technol Res Dev 63:161–184, 2015) from a combination of practice, research, design, and inclusion perspectives to ensure emotional support, mental wellness, and social presence during times of crisis, even at the expense of efficiency of instruction. [ABSTRACT FROM AUTHOR]

Digitization of schools has increased significantly in recent years and is generating a massive innovation boost in education. This development is accompanied by an increased demand for new digital educational objects for schools. The resources required for creating such objects (expert knowledge from teaching contexts versus technological knowledge and infrastructures) are distributed among different groups of actors from digital economy and educational practice. Therefore, the production of such new objects requires new forms of cooperation in the education sector. This article discusses such a hybrid collaboration between a software developer and the teachers of two pilot schools for the creation of interactive learning software. We examine this collaborative relationship in light of different bodies of knowledge that both groups of actors bring to the relationship and that need to be reconciled. We also examine the ways in which the organizational boundaries between schools and companies are temporarily blurred, and the distribution of costs and benefits between the participating groups of actors. By looking at the various dimensions of the cooperative commercial production of these digital objects as well as their (prototypical) experimental stage, the paper analyses the digital transformation of teaching as an innovative social process, structured by economic and educational rationalities. [ABSTRACT FROM AUTHOR]

In recent years, the pandemic situation has forced the education system to shift from traditional teaching to online teaching or blended learning. The ability to monitor remote online examinations efficiently is a limiting factor to the scalability of this stage of online evaluation in the education system. Human Proctoring is the most used common approach by either asking learners to take a test in the examination centers or by monitoring visually asking learners to switch on their camera. However, these methods require huge labor, effort, infrastructure, and hardware. This paper presents an automated AI-based proctoring system- 'Attentive system' for online evaluation by capturing the live video of the examinee. Our Attentive system includes four components to estimate the malpractices such as face detection, multiple person detection, face spoofing, and head pose estimation. Attentive Net detects the faces and draws bounding boxes along with confidences. Attentive Net also checks the alignment of the face using the rotation matrix of Affine Transformation. The face net algorithm is combined with Attentive-Net to extract landmarks and facial features. The process for identifying spoofed faces is initiated only for aligned faces by using a shallow CNN Liveness net. The head pose of the examiner is estimated by using the SolvePnp equation, to check if he/she is seeking help from others. Crime Investigation and Prevention Lab (CIPL) datasets and customized datasets with various types of malpractices are used to evaluate our proposed system. Extensive Experimental results demonstrate that our method is more accurate, reliable and robust for proctoring system that can be practically implemented in real time environment as Automated proctoring System. An improved accuracy of 0.87 is reported by authors with the combination of Attentive Net, Liveness net and head pose estimation. [ABSTRACT FROM AUTHOR]

With the rapid growth in multimedia collections around the world, video forensics faces new obstacles in recognizing human actions under video surveillance systems, human-computer interaction, etc. that requires multiple activity recognition systems. Due to issues such as background clutter, partial occlusion, scaling, viewpoint, lighting, and appearance, recognizing human activities from video sequences or still images is a difficult process. In the literature, there are a variety of Deep Learning methods that can be employed to solve the problems of unethical human action recognition which are effective in learning low-level temporal and spatial features but struggle from learning high-level features that affect the feature learning capability of the model. Due to this problem, deep learning methods suffer from poor performance and learning ability. From digital forensic perspective, deep analysis of video has become a prerequisite in human action recognition methods concerning to cyber-crime investigation and prevention. In this paper, we propose a Deep Learning based hybrid model for unethical human action recognition using two-stream inflated 3D ConvNet (I3D) and spatio-temporal attention (STA) modules. The I3D model improves the performance of 3D CNN architecture by inflating 2D convolution kernels into 3D kernels and STA increases the learning capability by giving attention to each frame's spatial and temporal information. To test the capability of our model, we have built a multi-action dataset using the subset of diverse datasets like Weizmann, HMDB51, UCF-101, NPDI, and UCF-Crime then compared our proposed model with existing models using unique and multi-action datasets to show better performance capability. [ABSTRACT FROM AUTHOR]

Fish diseases in aquaculture pose a significant threat to nutrient security and the fishing industry's income. However, identifying infectious fish can be challenging due to the lack of necessary infrastructure. To prevent the spread of diseases, it is crucial to identify infectious fish promptly. This paper proposes a machine learning technique based on Artificial Neural Networks (ANN) for fish disease identification and classification. We introduce a novel hybrid algorithm called Black Widow Optimization Algorithm with Mayfly Optimization Algorithm (BWO-MA) for solving global optimization problems. The proposed approach aims to develop a BWO-MA with an ANN-based diagnostic model for the earlier detection of fish diseases. We compare our proposed method with existing machine learning techniques and demonstrate that the BWO-MA-based ANN architecture achieves better performance. Our comprehensive analysis shows that the proposed method achieves state-of-the-art performance. The combination of Artificial Neural Networks (ANN) with the Black Widow Optimization Algorithm and with the Mayfly Optimization Algorithm (BWO-MA) achieved a high accuracy rate of 96.439% in detecting and classifying fish diseases. [ABSTRACT FROM AUTHOR]

A decision-making system is one of the most important tools in data mining. The data mining field has become a forum where it is necessary to utilize users' interactions, decision-making processes and overall experience. Nowadays, e-learning is indeed a progressive method to provide online education in long-lasting terms, contrasting to the customary head-to-head process of educating with culture. Through e-learning, an ever-increasing number of learners have profited from different programs. Notwithstanding, the highly assorted variety of the students on the internet presents new difficulties to the conservative one-estimate fit-all learning systems, in which a solitary arrangement of learning assets is specified to the learners. The problems and limitations in well-known recommender systems are much variations in the expected absolute error, consuming more query processing time, and providing less accuracy in the final recommendation. The main objectives of this research are the design and analysis of a new transductive support vector machine-based hybrid personalized hybrid recommender for the machine learning public data sets. The learning experience has been achieved through the habits of the learners. This research designs some of the new strategies that are experimented with to improve the performance of a hybrid recommender. The modified one-source denoising approach is designed to preprocess the learner dataset. The modified anarchic society optimization strategy is designed to improve the performance measurements. The enhanced and generalized sequential pattern strategy is proposed to mine the sequential pattern of learners. The enhanced transductive support vector machine is developed to evaluate the extracted habits and interests. These new strategies analyze the confidential rate of learners and provide the best recommendation to the learners. The proposed generalized model is simulated on public datasets for machine learning such as movies, music, books, food, merchandise, healthcare, dating, scholarly paper, and open university learning recommendation. The experimental analysis concludes that the enhanced clustering strategy discovers clusters that are based on random size. The proposed recommendation strategies achieve better significant performance over the methods in terms of expected absolute error, accuracy, ranking score, recall, and precision measurements. The accuracy of the proposed datasets lies between 82 and 98%. The MAE metric lies between 5 and 19.2% for the simulated public datasets. The simulation results prove the proposed generalized recommender has a great strength to improve the quality and performance. [ABSTRACT FROM AUTHOR]

Decomposition hybrid structure learning algorithms (DHSLAs), which combine the idea of divide and conquer with hybrid algorithms to reduce the computational complexity, are used to learn Bayesian network (BN) structure. Nevertheless, it's hard to learn highly accurate BN structures using DHSLAs based on data alone in some cases. First, accurate divisions for the whole domain are difficult to obtain because of the effect on network density and substructures tend to be poorly learned because of the large search space. In addition, using data alone, it is difficult to distinguish Markov equivalence classes. At this point, utilizing expert knowledge is an effective way. However, existing algorithms have not been studied to integrate expert knowledge into DHSLAs. Therefore, in this paper, we propose the first structure learning algorithm for using expert knowledge in DHSLAs called Decomposition Hybrid Structure Learning Algorithm with Expert Knowledge (DHSLA-EK). In the DHSLA-EK, we incorporate domain knowledge and structural knowledge with confidence into the DHSLA by constructing prior subdomains in the decomposition stage and by forming a novel scoring function in the subdomain structure learning stage. Extensive experiments on four benchmark networks indicate that the proposed algorithm can effectively improve the learning effect of the DHSLA. [ABSTRACT FROM AUTHOR]

The research described in this paper focused on the issue of describing and understanding how mathematical discussion develops in a hybrid learning environment, and how students participate in it. The experimental plan involved several classes working in parallel, with pupils and teachers interacting both in their real classrooms and in a digital environment with other pupils and teachers. The research was based on a rich set of data collected from the M@t.abel 2020 project, which was developed in Italy during the Covid health crisis. Based on Complementary Accounts Methodology, the data analysis presented in this paper involved specialists from the fields of mathematics education and inclusive education. In the study we considered the complexity of learning and the different elements that have an impact on students' activity and participation, when they are engaged in mathematical discussions within the multilevel-digital environment that emerged due to the pandemic. These parallel analyses showed that 'mathematical discussion in the classroom' is a complex (and sometimes chaotic) phenomenon wherein different factors interweave. A complementary approach assists in developing a global vision for this dynamic phenomenon and in highlighting local episodes that are crucial in this interplay of factors. It is precisely in these episodes that the role of the teacher is fundamental: these episodes appear as catalysts for the different variables, with the teacher acting as mediator. [ABSTRACT FROM AUTHOR]

Long non-coding RNA(lncRNA) is one of the non-coding RNAs longer than 200 nucleotides and it has no protein encoding function. LncRNA plays a key role in many biological processes. Studying the RNA-binding protein (RBP) binding sites on the lncRNA chain helps to reveal epigenetic and post-transcriptional mechanisms, to explore the physiological and pathological processes of cancer, and to discover new therapeutic breakthroughs. To improve the recognition rate of RBP binding sites and reduce the experimental time and cost, many calculation methods based on domain knowledge to predict RBP binding sites have emerged. However, these prediction methods are independent of nucleotides and do not take into account nucleotide statistics. In this paper, we use a high-order statistical-based encoding scheme, then the encoded lncRNA sequences are fed into a hybrid deep learning architecture named AC-Caps. It consists of a joint processing layer(composed of attention mechanism and convolutional neural network) and a capsule network. The AC-Caps model was evaluated using 31 independent experimental data sets from 12 lncRNA-binding proteins. In experiments, our method achieves excellent performance, with an average area under the curve (AUC) of 0.967 and an average accuracy (ACC) of 92.5%, which are 0.014, 2.3%, 0.261, 28.9%, 0.189, and 21.8% higher than HOCCNNLB, iDeepS, and DeepBind, respectively. The results show that the AC-Caps method can reliably process the large-scale RBP binding site data on the lncRNA chain, and the prediction performance is better than existing deep-learning models. The source code of AC-Caps and the datasets used in this paper are available at https://github.com/JinmiaoS/AC-Caps. [ABSTRACT FROM AUTHOR]

Historical data in climatology is important for recognizing patterns and discovering trends. However, data gaps often occur in some weather station time series. This paper presents a framework consisting of machine learning techniques combined with triangulation methods to identify missing meteorological data. Our approach is based on using data from neighboring weather stations as input for triangulation methods in combination with machine learning techniques. The current focus of the proposed framework is on filling missing temperature data and it was applied in ten different regions of Brazil, each with a different climatic configuration. Furthermore, a statistical study was conducted to estimate the best configuration which showed that a popular mathematical triangulation model combined with neural networks produced the most satisfactory results in predicting missing data, outperforming the results of traditional triangulation methods. [ABSTRACT FROM AUTHOR]

Since performance of traditional classification methods is extremely dependent on the number of labeled samples and, to gather ground-truth information of hyperspectral images from the earth's surface is an expensive and time-consuming process. Semisupervised classification is extensively utilized for hyperspectral images to deal with the issue of restricted training samples by combining the power of labeled and unlabeled data. In this paper, a unique semisupervised classification technique depends on a deep learning based hybrid framework (DL-HF) is described in order to utilize the more information as feasible in order to complete the hyperspectral classification issues. To begin, the proposed semisupervised based method DL-HF uses mainly two arrangements for pre labeling of unlabeled data: the neighboring samples create local arrangement based on neighborhood weighted information, and the most similar training data samples perform global arrangement based on deep learning. Then, to expand the training set, a few unlabeled samples along with superior confidence have been chosen. Finally, using the revised training data, self-arrangement which is based on the self-features developed through deep learning used to extract spectral as well as spatial features and generate a classified map. Evaluation results confirmed that the classification effects of proposed DL-HF algorithm are significantly better in contrast to other competing classification schemes on two benchmark hyperspectral datasets: AVIRIS Indian pines and AVIRIS salina valley dataset, in terms of Overall Accuracy (OA), Average Accuracy (AA) and kappa coefficient (k). The overall classification accuracy achieved is more than 94% which is superior to other related classification methods. [ABSTRACT FROM AUTHOR]

The efficient allocation of resources is a critical challenge in the context of Narrowband IoT(NB-IoT) networks. This paper presents the Hybrid Namib Antenna Beetle optimization with Refraction Reverse Learning (HNAB-RRL) algorithm, which combines the Namib Antenna Beetle Optimization (NAB) and Beetle Antenna Search (BAS) Optimization algorithms with the Refraction Reverse Learning (RRL) algorithm to optimize resource allocation. The HNAB-RRL algorithm is designed to allocate available resources to multiple users efficiently and optimally. The algorithm takes into account factors such as signal-to-noise ratio, data rate, and available bandwidth to allocate resources to each user. The NAB and BAS algorithms are used to explore the search space and identify candidate solutions. These algorithms use a combination of local and global search strategies to find optimal solutions. The NAB algorithm focuses on finding the best combination of subcarriers and timeslots, while the BAS algorithm optimizes the allocation of power to the subcarriers. The RRL algorithm refines and optimizes the candidate solutions identified by the NAB and BAS algorithms. This machine learning technique learns from previous resource allocation decisions to improve future allocations. The algorithm takes into account factors such as user requirements, available resources, and previous allocation decisions to make optimal resource allocation decisions. The HNAB-RRL algorithm continuously updates the RRL algorithm with new resource allocation decisions to improve future allocations, leading to higher network throughput and better performance overall. The experimentation results revealed that the proposed HNAB-RRL model requires less time to run, provides better group fairness, and enhances performance while reducing high complexity. The achieved throughput is 105 Kbit/s, which is higher than existing methods such as E-CORA, fusion, and greedy algorithms. Overall, the HNAB-RRL algorithm provides a powerful and effective approach to resource allocation in NB-IoT networks, combining the strengths of multiple optimization techniques to find the best possible solutions. [ABSTRACT FROM AUTHOR]

Efficient resource management approaches have become a fundamental challenge for distributed systems, especially dynamic environment systems such as cloud computing data centers. These approaches aim at load-balancing or minimizing power consumption. Due to the highly dynamic nature of cloud workloads, traditional time series and machine learning models fail to achieve accurate predictions. In this paper, we propose novel hybrid VTGAN models. Our proposed models not only aim at predicting future workloads but also predicting the workload trend (i.e., the upward or downward direction of the workload). Trend classification could be less complex during the decision-making process in resource management approaches. Also, we study the effect of changing the sliding window size and the number of prediction steps. In addition, we investigate the impact of enhancing the features used for training using the technical indicators, Fourier transforms, and wavelet transforms. We validate our models using a real cloud workload dataset. Our results show that VTGAN models outperform traditional deep learning and hybrid models, such as LSTM/GRU and CNN-LSTM/GRU, concerning cloud workload prediction and trend classification. Our proposed model records an upward prediction accuracy ranging from 95.4 % to 96.6 % . [ABSTRACT FROM AUTHOR]