E-Learning Readiness Assessment Using Machine Learning Methods

Assessing e-learning readiness is crucial for educational institutions to identify areas in their e-learning systems needing improvement and to develop strategies to enhance students' readiness. This paper presents an effective approach for assessing e-learning readiness by combining the ADKAR model and machine learning-based feature importance identification methods. The motivation behind using machine learning approaches lies in their ability to capture nonlinearity in data and flexibility as data-driven models. This study surveyed faculty members and students in the Economics faculty at Tlemcen University, Algeria, to gather data based on the ADKAR model's five dimensions: awareness, desire, knowledge, ability, and reinforcement. Correlation analysis revealed a significant relationship between all dimensions. Specifically, the pairwise correlation coefficients between readiness and awareness, desire, knowledge, ability, and reinforcement are 0.5233, 0.5983, 0.6374, 0.6645, and 0.3693, respectively. Two machine learning algorithms, random forest (RF) and decision tree (DT), were used to identify the most important ADKAR factors influencing e-learning readiness. In the results, ability and knowledge were consistently identified as the most significant factors, with scores of ability (0.565, 0.514) and knowledge (0.170, 0.251) using RF and DT algorithms, respectively. Additionally, SHapley Additive exPlanations (SHAP) values were used to explore further the impact of each variable on the final prediction, highlighting ability as the most influential factor. These findings suggest that universities should focus on enhancing students' abilities and providing them with the necessary knowledge to increase their readiness for e-learning. This study provides valuable insights into the factors influencing university students' e-learning readiness.

The Analytic Solutions of the Fractional-Order Model for the Spatial Epidemiology of the COVID-19 Infection

This paper provides a mathematical fractional-order model that accounts for the mindset of patients in the transmission of COVID-19 disease, the continuous inflow of foreigners into the country, immunization of population subjects, and temporary loss of immunity by recovered individuals. The analytic solutions, which are given as series solutions, are derived using the fractional power series method (FPSM) and the residual power series method (RPSM). In comparison, the series solution for the number of susceptible members, using the FPSM, is proportional to the series solution, using the RPSM for the first two terms, with a proportional constant of ψΓnα+1, where ψ is the natural birth rate of the baby into the susceptible population, Γ is the gamma function, n is the nth term of the series, and α is the fractional order as the initial number of susceptible individuals approaches the population size of Ghana. However, the variation in the two series solutions of the number of members who are susceptible to the COVID-19 disease begins at the third term and continues through the remaining terms. This is brought on by the nonlinear function present in the equation for the susceptible subgroup. The similar finding is made in the series solution of the number of exposed individuals. The series solutions for the number of deviant people, the number of nondeviant people, the number of people quarantined, and the number of people recovered using the FPSM are unquestionably almost identical to the series solutions for same subgroups using the RPSM, with the exception that these series solutions have initial conditions of the subgroup of the population size. It is observed that, in this paper, the series solutions of the nonlinear system of fractional partial differential equations (PDEs) provided by the RPSM are more in line with the field data than the series solutions provided by the FPSM.

XXII International Conference and School on Quantum Electronics: "Laser Physics and Applications”

The International School on Quantum Electronics "Laser Physics and Applications” was held for the first time as far back as 1980. Since then it has taken place biennially and has become an important international event in the field of laser physics and laser applications attracting participants from many countries, especially from south-eastern Europe. Traditionally, its program includes lectures delivered by prominent scientists dealing with investigations of basic physical phenomena, processes of interaction of laser radiation with matter and latest scientific results obtained in the research areas of quantum electronics and optics, as well as the technological practical applications of new ideas, devices, instruments and laser systems. Special attention is paid to the active participation of students and young scientists who have the opportunity to present their results and meet and share experience with outstanding professionals in their particular fields of research.The topics include the following:• Laser-matter interactions• Laser spectroscopy and metrology• Laser remote sensing and ecology• Lasers in biology and medicine• Laser systems and nonlinear optics• Alternative techniques for material synthesis and processingThe 22nd edition of the ICSQE was held as a virtual forum due to the restrictions related to COVID-19 pandemic from September 19th to 23rd, 2022. The Institute of Electronics, Bulgarian Academy of Sciences, located in Sofia, Bulgaria, hosted the conference organization. The Big Blue Button on-line system was used as a technical platform for the meeting. The technical sessions of the International School on Quantum Electronics included 22 invited talks (30 min + 5 min Q&A), a Mini-Symposium "Extreme light infrastructure”, 11 oral contributions (30 min + 5 min Q&A) and in total 51 poster presentations divided into 5 sessions (1 hour each). The platform was available 24 hours, allowing discussions in addition to the technical program. The total number of participants was 90 from 16 countries.The XXII International Conference and School on Quantum Electronics: "Laser Physics and Applications” was held by the financial support from the Bulgarian National Science Fund under Project No. KP-06-MNF/4, 20.07.2022.List of Committees, International Advisory Committee, Program Committee, Local Organizing Committee, Lecturers, Oral Presentations, Poster Presentations are available in this pdf.

Bayesian Physics Informed Neural Networks for real-world nonlinear dynamical systems

Understanding real-world dynamical phenomena remains a challenging task. Across various scientific disciplines, machine learning has advanced as the go-to technology to analyze nonlinear dynamical systems, identify patterns in big data, and make decision around them. Neural networks are now consistently used as universal function approximators for data with underlying mechanisms that are incompletely understood or exceedingly complex. However, neural networks alone ignore the fundamental laws of physics and often fail to make plausible predictions. Here we integrate data, physics, and uncertainties by combining neural networks, physics informed modeling, and Bayesian inference to improve the predictive potential of traditional neural network models. We embed the physical model of a damped harmonic oscillator into a fully-connected feed-forward neural network to explore a simple and illustrative model system, the outbreak dynamics of COVID-19. Our Physics Informed Neural Networks seamlessly integrate data and physics, robustly solve forward and inverse problems, and perform well for both interpolation and extrapolation, even for a small amount of noisy and incomplete data. At only minor additional cost, they self-adaptively learn the weighting between data and physics. They can serve as priors in a Bayesian Inference, and provide credible intervals for uncertainty quantification. Our study reveals the inherent advantages and disadvantages of Neural Networks, Bayesian Inference, and a combination of both and provides valuable guidelines for model selection. While we have only demonstrated these different approaches for the simple model problem of a seasonal endemic infectious disease, we anticipate that the underlying concepts and trends generalize to more complex disease conditions and, more broadly, to a wide variety of nonlinear dynamical systems.

Relevant mathematical modelling efforts for understanding COVID-19 dynamics: an educational challenge.

The purpose of the work described in this paper is to emphasize the importance of using mathematical models and mathematical modelling in order to be able to understand and to learn possible behaviours in epidemic situations such as that of the COVID-19 pandemic, besides suggesting modelling techniques with which to evaluate certain sanitary decisions and policies which do, in fact, affect society as a whole. The mathematical tools that are used derive from nonlinear systems of difference equations (possibly viable at a high school level, using spreadsheets or adequate software) as well as nonlinear systems of ordinary differential equations (therefore using mathematical tools and software well within the reach of undergraduate students of many courses). This purpose is accomplished by motivating students and learners to study existing SIR-type models and modifying them in order to have a fully understandable translation of dynamics for infectious diseases such as COVID-19 in several different realistic scenarios, that is to say, situations that consider social distancing policies, widespread vaccination programmes, as well as possible and even probable results when in the presence of negationist postures and attitudes. Several modelling choices referring to real-life situations are shown and explored. These models are analysed and discussed, implicitly proposing similar attitudes and evaluations in learning environments. Conclusions are drawn, stimulating further work using the described mathematical tools and resources. Supplementary Information: The online version contains supplementary material available at 10.1007/s11858-022-01447-2.

Analyzing Commodity Prices in the Context of COVID-19, High Inflation, and the Ukrainian War: An Interview with James Hamilton

The following interview with Prof. James Hamilton was conducted in September 2022 by Dr. Fredj Jawadi with the assistance of Professor Adonis Yatchew in association with the 6th International Workshop on Financial Markets and Nonlinear Dynamics (FMND) held in Paris, France. The interview includes 20 questions related to commodity price dynamics. The aim of the discussion was, first, to help readers gain a better understanding of the factors driving commodity price volatility during the COVID-19 pandemic. Second, we analyzed commodity reactions to the ongoing Ukrainian war. Third, we examined the impact of changes in commodity prices on the economy as a whole and on inflation in particular. Finally, we discussed projections related to the dynamics of commodity prices in the future and the impact on the energy transition process. We hope that this interview will give readers clearer insights into the causes and consequences of commodity price changes and their evolution over time.

Optimizing Symptom Based Testing Strategies for Pandemic Mitigation

In this paper, a predictive-control-based approach is proposed for pandemic mitigation with multiple control inputs. Using previous results on the dynamical modeling of symptom-based testing, the testing intensity is introduced as a new manipulable input to the control system model in addition to the stringency of non-pharmaceutical measures. The control objective is the minimization of the severity of interventions, while the main constraints are the bounds on the daily number of hospitalized people and on the total number of available tests. For the control design and simulation, a nonlinear dynamical model containing 14 compartments is used, where the effect of vaccination is also taken into consideration. The computation results clearly show that the optimization-based design of testing intensity significantly reduces the stringency of the measures to be introduced to reach the control goal and fulfill the prescribed constraints.

Probabilities of Risk Due to Random Aerosol Displacement and Aleatory Social Distancing

With the apparition of Corona Virus Disease (Covid-19 in short) a plethora of mechanisms have emerged in order to protect people. One of them is the well-known social distancing that is a global protocol that has emerged in 2020 in order to be applied in pandemic times. The protocol persists to date event when people have got the vaccine because the mutation of virus and the risk to be infected again. Commonly these distances have been established to be in the range of distances between 1.5 and 2.0 meters, that in a first instance would guarantee a common and healthy interaction among people. Although very little information on the calculation of this is known, this paper proposes a theory by the which the social distancing might be strongly dependent on stochastic events, so that this study deepens the origin with respect the true or approximated value of social distancing. Simulations and estimations are presented. © 2021 IEEE.

A Modified Iterative Algorithm for Numerical Investigation of HIV Infection Dynamics

The human immunodeficiency virus (HIV) mainly attacks CD4+ T cells in the host. Chronic HIV infection gradually depletes the CD4+ T cell pool, compromising the host’s immunological reaction to invasive infections and ultimately leading to acquired immunodeficiency syndrome (AIDS). The goal of this study is not to provide a qualitative description of the rich dynamic characteristics of the HIV infection model of CD4+ T cells, but to produce accurate analytical solutions to the model using the modified iterative approach. In this research, a new efficient method using the new iterative method (NIM), the coupling of the standard NIM and Laplace transform, called the modified new iterative method (MNIM), has been introduced to resolve the HIV infection model as a class of system of ordinary differential equations (ODEs). A nonlinear HIV infection dynamics model is adopted as an instance to elucidate the identification process and the solution process of MNIM, only two iterations lead to ideal results. In addition, the model has also been solved using NIM and the fourth order Runge–Kutta (RK4) method. The results indicate that the solutions by MNIM match with those of RK4 method to a minimum of eight decimal places, whereas NIM solutions are not accurate enough. Numerical comparisons between the MNIM, NIM, the classical RK4 and other methods reveal that the modified technique has potential as a tool for the nonlinear systems of ODEs.

A Comprehensive Comparison of the Performance of Metaheuristic Algorithms in Neural Network Training for Nonlinear System Identification

Many problems in daily life exhibit nonlinear behavior. Therefore, it is important to solve nonlinear problems. These problems are complex and difficult due to their nonlinear nature. It is seen in the literature that different artificial intelligence techniques are used to solve these problems. One of the most important of these techniques is artificial neural networks. Obtaining successful results with an artificial neural network depends on its training process. In other words, it should be trained with a good training algorithm. Especially, metaheuristic algorithms are frequently used in artificial neural network training due to their advantages. In this study, for the first time, the performance of sixteen metaheuristic algorithms in artificial neural network training for the identification of nonlinear systems is analyzed. It is aimed to determine the most effective metaheuristic neural network training algorithms. The metaheuristic algorithms are examined in terms of solution quality and convergence speed. In the applications, six nonlinear systems are used. The mean-squared error (MSE) is utilized as the error metric. The best mean training error values obtained for six nonlinear systems were 3.5×10−4, 4.7×10−4, 5.6×10−5, 4.8×10−4, 5.2×10−4, and 2.4×10−3, respectively. In addition, the best mean test error values found for all systems were successful. When the results were examined, it was observed that biogeography-based optimization, moth–flame optimization, the artificial bee colony algorithm, teaching–learning-based optimization, and the multi-verse optimizer were generally more effective than other metaheuristic algorithms in the identification of nonlinear systems.

Data-driven prediction of COVID-19 cases in Germany for decision making.

BACKGROUND: The COVID-19 pandemic has led to a high interest in mathematical models describing and predicting the diverse aspects and implications of the virus outbreak. Model results represent an important part of the information base for the decision process on different administrative levels. The Robert-Koch-Institute (RKI) initiated a project whose main goal is to predict COVID-19-specific occupation of beds in intensive care units: Steuerungs-Prognose von Intensivmedizinischen COVID-19 Kapazitäten (SPoCK). The incidence of COVID-19 cases is a crucial predictor for this occupation. METHODS: We developed a model based on ordinary differential equations for the COVID-19 spread with a time-dependent infection rate described by a spline. Furthermore, the model explicitly accounts for weekday-specific reporting and adjusts for reporting delay. The model is calibrated in a purely data-driven manner by a maximum likelihood approach. Uncertainties are evaluated using the profile likelihood method. The uncertainty about the appropriate modeling assumptions can be accounted for by including and merging results of different modelling approaches. The analysis uses data from Germany describing the COVID-19 spread from early 2020 until March 31st, 2021. RESULTS: The model is calibrated based on incident cases on a daily basis and provides daily predictions of incident COVID-19 cases for the upcoming three weeks including uncertainty estimates for Germany and its subregions. Derived quantities such as cumulative counts and 7-day incidences with corresponding uncertainties can be computed. The estimation of the time-dependent infection rate leads to an estimated reproduction factor that is oscillating around one. Data-driven estimation of the dark figure purely from incident cases is not feasible. CONCLUSIONS: We successfully implemented a procedure to forecast near future COVID-19 incidences for diverse subregions in Germany which are made available to various decision makers via an interactive web application. Results of the incidence modeling are also used as a predictor for forecasting the need of intensive care units.

Solution of a nonlinear fractional COVID-19 model

Purpose: The purpose of this study is to obtain an analytical solution for a nonlinear system of the COVID-19 model for susceptible, exposed, infected, isolated and recovered. Design/methodology/approach: The Laplace decomposition method and the differential transformation method are used. Findings: The obtained analytical results are useful on two fronts: first, they would contribute to a better understanding of the dynamic spread of the COVID-19 disease and help prepare effective measures for prevention and control. Second, researchers would benefit from these results in modifying the model to study the effect of other parameters such as partial closure, awareness and vaccination of isolated groups on controlling the pandemic. Originality/value: The approach presented is novel in its implementation of the nonlinear system of the COVID-19 model © 2022, Emerald Publishing Limited.

Analysis of epidemic spread dynamics using a PDE model and COVID-19 data from Hamilton County OH USA

We study the spatiotemporal dynamics of an epidemic spread using a compartmentalized PDE model. The model is validated using COVID-19 data from Hamilton County, Ohio, USA. The model parameters are estimated using a month of recorded data and then used to forecast the infection spread over the next ten days. The model is able to accurately estimate the key dynamic characteristics of COVID-19 spread in the county. Additionally, a stability analysis indicates that the model is robust to disturbances and perturbations which, for instance, could be used to represent the effects of super spreader events. We also use the modeling framework to analyse and discuss the impact of Non-pharmaceutical interventions (NPIs) for mitigation of infection. Our results suggest that such models can yield useful short and medium term predictive characterization of an epidemic spread in a restricted geographical region and also help formulate effective NPIs for mitigation. The results also signify the importance of further research into the accurate analytical representation of specific NPIs and hence their dampening effects on an infection spread. Copyright © 2021 The Authors.

Analysis of Neural Network and Statistical Models Used for Forecasting of a Disease Infection Cases

More than a year has passed since the coronavirus 2 (SARS-CoV2) pandemic began, and no one has been able to forecast the infection cases of the disease with high accuracy. Nowadays, a lot of studies are devoted to finding out the pattern of infection spreading and forecasting cases of infection. But models used in those studies have large errors in forecasts, and this makes it more challenging to discover the pattern of infection spreading. The choice of appropriate models may vary from country to country. The increase of the number of infection cases is one of the global challenges nowadays not only for virusologists and medicians, but also for data analytics. In our paper, we analyze errors in the forecast in the list of the top 10 countries affected by disease on January 1, 2021 using the following the neural network models, linear and non-linear classical statistical models, and also classical epidemiological SIR model. The other part of our computational experiment is devoted to forecasting the dates of the peak values of time series. It is shown on time series for the regions most affected by pandemics that neural network models allow to forecast this date with high accuracy. We also discover the possible field of application of such algorithms in other fields. © 2021 IEEE.