Online Learning Approach Research Articles

An Online Machine Learning Approach to Sentiment Analysis in Social Media

The online learning, is one that continuously adapts to arriving data, and gets updated incrementally instance by instance. In this paper, we compare the performance of different online machine learning algorithms for the task of sentiment analysis on challenging text datasets. We assess the models using a wide range of metrics, such as microF1, macroF1, accuracy, and running time. Our experiments have revealed that these online models provide a viable alternative to traditional offline machine learning in sentiment analysis, in fraction of the time.

MPC using an on-line TS fuzzy learning approach with application to autonomous driving

The control of complex nonlinear systems (such as autonomous vehicles) usually requires models which might be unavailable or inaccurate. In this paper, a novel data-driven Model Predictive Control (MPC) framework is proposed based on a data-driven approach to learn Takagi–Sugeno (TS) fuzzy models for nonlinear systems. To address the data TS modeling, we use the Evolving TS Fuzzy Ellipsoidal Information Granules (TS-EEFIG) approach to obtain a polytopic representation as well as a set of membership functions that allows to use efficient linear control tools to handle complex nonlinear systems. In particular, the formulated approach is applied for the autonomous driving control problem of a racing vehicle. The proposed control uses references provided by an external trajectory planner offering a high driving performance in racing mode. The control-estimation scheme is validated in a simulated racing environment based on a high fidelity vehicle model of a 1/10 scale RC car to show the potential of the proposed approach.

Adaptive Request Scheduling and Service Caching for MEC-Assisted IoT Networks: An Online Learning Approach

Multiaccess edge computing (MEC) is a new paradigm to meet the demand of resource-hungry and latency-sensitive services by enabling the placement of services and execution of computing tasks at the edge of radio access networks much closer to resource-constrained devices. However, how to serve more requests while reducing service latency by exploiting limited resources (storage capacities, CPU cycles, communication bandwidth) is still a critical issue in the multidevice MEC-assisted IoT networks, since the time-varying computing demands of devices and unavailability of future information make it difficult to determine where to handle computation tasks and which services to cache. In this article, we propose a twin-timescale framework to jointly optimize adaptive request scheduling (RS) and cooperative service caching (SC) in the multidevices and MEC-assisted networks, in order to explore request dynamic, MECs heterogeneity, service difference. To accommodate the unavailability of future information and unknown system dynamics, we, respectively, formulate RS and SC as partially observable Markov decision process (POMDP) problems. Then, we propose a deep reinforcement learning (DRL)-based online algorithm to improve the service latency reduction ratio and hit rate, which do not require <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">a priori</i> knowledge such as service popularity. Moreover, we give the optimal CPU cycles and communication bandwidth allocations in order to further minimize the average service latency. Extensive and trace-driven simulation results demonstrate the efficacy of the proposed approach.

Learning Experience with LearnwithEmma

The presence of Covid-19 was a game-changer in all the sectors that traditional learning, working, selling even living methods have changed from basic methods to something else to curb Covid-19. The impact was huge on most sectors due to the lack of experience in overcoming pandemics. One of the sectors that face the most struggle was educational institutions. For many years, face-to-face learning and teaching method have been in practice. While during Covid-19, everyone was forced to attend online classes as a precautious measure. Online learning is completely based on digital study without the physical presence of students or lecturers. Implementing such learning approaches gradually in education allows students to expose to both learning methods. Many subjects such as languages, and theory-based topics have been taught with an online learning approach; however, less attention was paid to mathematics. Therefore, this study aimed to examine students’ experience in learning Discrete Mathematics online through LearnwithEmma. LearnwithEmma is a learning platform that was designed for students in this study. During a month, students’ learning was assisted by an agent, Emma. Students were given a questionnaire that involved questions about their experience and their current understanding of the subject. Students opined that their performance significantly improved after learning via LearnwithEmma. About 77.2% strongly agreed that they excel in Mathematics after fully utilizing LearnwithEmma. Most of them agreed that they were able to perform better in their exam after using LearnwithEmma. 75.4% of the students agreed that they have scored better in their exams after using LearnwithEmma. 61.4% of the participants preferred to learn Discrete Mathematics through an online class compared to a traditional class. This study recommends that educators and researchers may enhance online learning by introducing new platforms such as LearnwithEmma or integrating other multimedia elements.

Secondary Frequency Control of Microgrids: An Online Reinforcement Learning Approach

In this article, we present a reinforcement learning-based scheme for secondary frequency control of lossy inverter-based microgrids. Compared with the existing methods in the literature, we relax the common restrictions on the system, i.e., being lossless, and the transmission lines and loads to have known constant impedances. The proposed secondary frequency control scheme does not require <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">a priori</i> information about system parameters and can achieve frequency synchronization within an ultimate bound in the presence of dominantly resistive and/or inductive line and load impedances, model parameter uncertainties, and time varying loads and disturbances. First, using Lyapunov theory, a feedback control is formulated based on the unknown dynamics of the microgrid. Next, a performance function is defined based on cumulative costs toward achieving convergence to the nominal frequency. The performance function is approximated by a critic neural network in real-time. An actor network is then simultaneously learning a parameterized approximation of the nonlinear dynamics and optimizing the approximated performance function obtained from the critic network. Furthermore, using the Lyapunov approach, the uniformly ultimate boundedness of the closed-loop frequency error dynamics and the networks' weight estimation errors are shown.

Digital Twin-Enabled Intelligent DDoS Detection Mechanism for Autonomous Core Networks

Existing distributed denial of service attack (DDoS) solutions cannot handle highly aggregated data rates; thus, they are unsuitable for Internet service provider (ISP) core networks. This article proposes a digital twin-enabled intelligent DDoS detection mechanism using an online learning method for autonomous systems. Our contributions are three-fold: we first design a DDoS detection architecture based on the digital twin for ISP core networks. We implemented a Yet Another Next Generation (YANG) model and an automated feature selection (AutoFS) module to handle core network data. We used an online learning approach to update the model instantly and efficiently, improve the learning model quickly, and ensure accurate predictions. Finally, we reveal that our proposed solution successfully detects DDoS attacks and updates the feature selection method and learning model with a true classification rate of ninety-seven percent. Our proposed solution can estimate the attack within approximately fifteen minutes after the DDoS attack starts.

TRENDS AND EFFECTS OF ONLINE EDUCATION

In this article, we have differentiated the positive changes of online learning, ways and styles of instructing online as well as physical and mental changes caused. This is often in any case a modern involvement for us to investigate online learning approach. In continuation to the move learning from confront to online, the first step is to have a full confirmation specialized bolster and organized inclining stage so that understudies can get all important bolster instantly. Taken a toll viability is the prime thought for online learning. Time administration on the other hand perhaps crucial for online learning. The classes must be kicked off and wrapped up inside a given timeline. Teaching method and engagement movement ought to be different from confront-to-confront educating. Online instructing in any case within the educator’s point of see should be enlivened, distant locks in, and movement based. Taking a healing center as a case, online learning like a benefit ICU whereas face to confront learning is to be a standard cabin back. To summarize, we’ve found underneath advantage and impediments all through the research: However online instruction framework could be an awesome help for learners and instruction industry in this widespread. Something else the learning may well be hindered for a long time which would have caused a more regrettable world.

Analyzing an Appropriate Blend of Face-to-Face, Offline and Online Learning Approaches for the In-Service Vocational Teacher's Training Program.

Blended learning approaches are considered as the most viable for the delivery of training to remote areas and accessing learners at a mass level. Blended learning is a combination of different learning approaches to facilitate the learners’ needs. The National Vocational and Technical Training Commission (NAVTTC) conducted an in-service vocational teachers’ training program through blended learning approaches in Pakistan. This study aimed to find the appropriate blend of face-to-face, online, and offline learning approaches for the training of in-service teachers in Pakistan. A mixed methods research approach was adopted. A survey collected data from 781 in-service vocational teachers who participated in training programs through blended learning approaches. The ANOVA test was applied to find the difference of the training participants’ attitude toward different modes of learning. It was found that trainees had more positive attitude toward a face-to-face learning approach than online and the online learning approach than offline learning. Semi-structured interviews were also conducted with training participants, admission and placement officers, and principals. They also endorsed that face-to-face learning approaches must be given more weight than online, and the online approach should have more weight than the offline approach. This study has practical implications for technical education and vocational training (TVET) institutes in developing countries such as Pakistan to design blended learning approaches for the training of in-service vocational teachers. Future research may be conducted on the effectiveness of in-service vocational education teachers through blended learning.

Examination of Students’ Academic Performance in Selected Mechanical Engineering Courses Prior-to-and-During COVID-19 Era

Advances in Information and Communications Technology (ICT) as well as the present challenges of COVID-19 have led to a new paradigm causing an absolute or partial transition from in-person classroom teaching-learning to online. There is little information available on research efforts that investigated the impact of an online learning approach on the academic performance of students in mechanical engineering-based courses. Therefore, the objective of this paper is the impact study of online learning mode as compared to in-person on academic performance of students in selected mechanical engineering courses in one of the Universities in South Pacific Islands prior-to-and-during COVID-19 Era. Data on grades obtained for 178 students that offered Fluid Mechanics, Thermodynamics, Heat Transfer, and Advanced Thermofluids (FTHA) courses were subjected to descriptive and non-parametric (Mann-Whitney and Kruskal-Wallis) statistical tests. Although descriptive analysis showed that online mode of instruction might influence a better academic performance in FTHA courses in comparison with in-person mode of instruction, the outcome of Mann-Whitney U and Kruskal-Wallis tests at specific p-values and corresponding z-values generally exhibited p-values higher than of 0.05, implying insignificant difference in performance between the two modes of learning investigated. Though the non-parametric statistical test results showed there was no significant difference in academic performance of students when online and in-person modes of learning were used, this, however, does not imply that a difference does not exist at all. Although the difference may be very trivial, descriptive analysis has shown that the online learning mode has at least exhibited better students’ academic performance when compared to in-person. It can be inferred from the foregoing that the online learning mode does not yield a negative response in respect of the performance of students who offered all four mechanical engineering courses. Based on the findings of this study, online is considered a reliable alternative to in-person or at least a suitable complement to in-person in the in-person-online hybrid mode during the ongoing COVID-19 era and other inevitable constraints in the future. Doi: 10.28991/esj-2022-SPER-017 Full Text: PDF

Fostering Nursing Staff Competence in Personal Protective Equipment Education during COVID-19: A Mobile-Video Online Learning Approach.

Nursing staff who are competent to use personal protective equipment (PPE) correctly can protect themselves while providing safe, high-quality care to patients. Under pandemic conditions, the ability to wear PPE correctly is essential in clinical practice, but the acquisition of correct PPE-wearing procedures is difficult for most staff in the absence of live practice drills. This study aimed to test the mobile video online learning approach by integrating PPE contexts into a digital learning system. We conducted an experiment to verify whether the mobile video online learning approach could effectively improve nursing staff’s learning achievement, learning anxiety, critical thinking skills, and learning self-efficacy. The study used a quasi-experimental design and was conducted with 47 nursing staff, divided into one group using a mobile video online learning approach and one group with a conventional learning approach. We used pre-and post-test examinations of learning achievements, learning anxiety, critical thinking, and learning self-efficacy. Results showed a significant effect of using the mobile video online learning method in helping nursing staff to decrease learning anxiety and improve knowledge about COVID-19 protection, increase learning achievement, critical thinking skills, and learning self-efficacy. These benefits are of interest to nursing workplace managers wishing to maintain professional standards during epidemics by improving the nursing staff’s PPE knowledge and self-efficacy concerning PPE.

Postdigital Possibilities and Impossibilities Behind the Screen: Visual Arts Educators in Conversation about Online Learning and Real-world Experiences

Abstract Through an ethnomethodological and dialogical encounter with Australian classrooms in the lived experience of two visual art (va) educators, the authors seek to learn how working between online and studio learning approaches shaped teacher perceptions of student learning during the outbreak of covid-19 in 2020 and 2021. The research has two phases. Phase 1 sees the two va educators create learning narratives. These narratives, reported in summary in the article, through both material and digital form became the baseline data. In Phase 2 these themes were reworked as conversational questions. These questions then became the stimulus for a critical reflective online video conversation between the two va educators. The resulting discussion around the borderlines looks beyond specific apps, platforms, or products that the teachers used, their successes and failures and examines the digital, non-digital, material, social relations and pedagogical realities and futures that may or may be possible in the context of the postdigital va secondary classroom. These educators have had little time to assess the shift from a strong and well researched studio-pedagogy to their virtual creative learning futures. The challenges of this shift are revealed through their personal experiences.

Online Learning for Chance-Constrained Observer of Leading Heavy-Duty Vehicle Power Capability

This paper proposes a stochastic observer for estimating power capability of a preceding heavy-duty vehicle, using its speed measurement and road slope information. A chance-constrained optimisation problem is formulated to take into consideration the uncertainties associated with measurement error in the speed and imperfect knowledge of the road slope. An online learning approach is proposed to solve the chance-constrained optimisation problem, which learns probability distribution of the measurements along the travelled distance. The effectiveness of the proposed observer is analysed in two case studies on real road topographies and compared with an existing deterministic leading vehicle observer. The results show that the proposed leading vehicle observer is robust against uncertainties.

An Online Learning Approach for Cooperator Selection in CSS Under SSDF Attack

Cooperative spectrum sensing (CSS) can greatly improve sensing accuracy by combining the individual sensing results. However, it also faces spectrum sensing data falsification (SSDF) attack which degrades the cooperative sensing performance in practice. To deal with SSDF attack and reduce total energy consumption, it is recommended to select reliable secondary users (SUs) and SUs which have the best detection performance for cooperation. In this letter, an online learning based user selection algorithm is proposed according to the approximate ground truth about the licensed channel state, which addresses the practical problem that different users have different sensing capability and may launch SSDF attacks. In addition, the cooperator’s trust degree is updated in the online learning process. Simulation results indicate that the proposed SUs selection algorithm can quickly converge to a stable state in terms of collision probability and spectrum waste probability under highly unreliable conditions.

The Acquisition of Technical Terms using the Online Learning Approach among Aircraft Maintenance Learners

The Acquisition of Technical Terms using the Online Learning Approach among Aircraft Maintenance Learners

Can flipped classroom pedagogy offer promising perspectives for mathematics education on pandemic-related issues? A systematic literature review

Educators sometimes effect changes in education through the implementation of new ideas, and sometimes extraordinary circumstances force them to change their educational approaches, as during the COVID-19 crisis. Although we live in a digital age, the limited use of technology in education, particularly prior to the COVID-19 pandemic, and teachers’ insufficient experience with online or hybrid learning and teaching approaches resulted in several countries being unprepared for education during the pandemic. The flipped classroom (FC) is an innovative pedagogy with the potential to engage students in mathematics education using hybrid education combined with online and face-to-face learning, which is especially important during a pandemic. However, despite the high expectations surrounding this innovative approach, to date, no systematic literature review has discussed the opportunities and pitfalls of FCs in mathematics education regarding pandemic-related issues. In the present systematic review, we aim to bridge this gap and highlight the importance of flipping mathematics instruction during the pandemic and beyond. The results, which are based on textual analysis of 97 eligible articles, demonstrate that FC is a promising pedagogy that has numerous benefits for mathematics teaching and learning, although it is not a panacea for pandemic-related issues, as it also has several significant pitfalls. Overall, if the mechanism of mathematics education is to be crisis-ready, we should learn from experiences during the pandemic. In this regard, the current review contributes to research in mathematics education with the aim of gaining insight into successful implementations of FC pedagogy, not only during the pandemic but also beyond the crisis era of a pandemic.

An Online Learning Approach to Sequential User-Centric Selection Problems

This paper proposes a new variant of multi-play MAB model, to capture important factors of the sequential user-centric selection problem arising from mobile edge computing, ridesharing applications, etc. In the proposed model, each arm is associated with discrete units of resources, each play is associate with movement costs and multiple plays can pull the same arm simultaneously. To learn the optimal action profile (an action profile prescribes the arm that each play pulls), there are two challenges: (1) the number of action profiles is large, i.e., M^K, where K and M denote the number of plays and arms respectively; (2) feedbacks on action profiles are not available, but instead feedbacks on some model parameters can be observed. To address the first challenge, we formulate a completed weighted bipartite graph to capture key factors of the offline decision problem with given model parameters. We identify the correspondence between action profiles and a special class of matchings of the graph. We also identify a dominance structure of this class of matchings. This correspondence and dominance structure enable us to design an algorithm named OffOptActPrf to locate the optimal action efficiently. To address the second challenge, we design an OnLinActPrf algorithm. We design estimators for model parameters and use these estimators to design a Quasi-UCB index for each action profile. The OnLinActPrf uses OffOptActPrf as a subroutine to select the action profile with the largest Quasi-UCB index. We conduct extensive experiments to validate the efficiency of OnLinActPrf.

Student physiotherapists perceptions of online curriculum delivery during the COVID-19 pandemic

BackgroundAs a result of the COVID-19 pandemic a rapid transformation from face-to-face curriculum delivery to an online teaching and learning environment, was adopted in a number of higher education institutions globally. Allied Health Profession courses such as physiotherapy, traditionally utilising an in person teaching model to prepare students for practice, needed to swiftly adopt new methods of delivery, involving both synchronous and asynchronous approaches. Understanding physiotherapy student perceptions of this transition is important to allow faculty to develop their delivery of online teaching and provide an evidence base for future course curricula.MethodsCross-sectional survey of UK higher education students studying either an undergraduate or post-graduate pre-registration degree in physiotherapy was conducted between October 2020 and February 2021. The survey investigated the student’s perception of the transition to either an online or hybrid model of learning during the COVID-19 pandemic. A mixed method approach was adopted allowing respondents to share their experiences and facilitate the exploration of questions which required in-depth thought.ResultsTwo hundred thirty-six respondents completed the questionnaire. Online learning was perceived to be a flexible (49%, n=116,CI 95% 43 to 55) and convenient (49, 116, 43 to 55) method of learning. Despite this, 79% of the students surveyed felt that the online learning experience had a negative impact on their understanding of the subject and were disadvantaged compared to traditional face-to-face teaching provision (mean 4.14 ± SD 1.06). Online physiotherapy delivery produced low student satisfaction, leaving respondents feeling disadvantaged. Decreased levels of engagement and the lack of ability to practice ‘hands-on’ skills were detrimental aspects of the online approach, with 55% (n=106) reporting they did not perceive the academic staff had the necessary skills to deliver effective online content.ConclusionsThe majority of UK physiotherapy students surveyed were dissatisfied and lacked engagement with an online learning approach within the curricula, compared with the traditional face-to-face delivery. Although several positives of both a synchronous and asynchronous delivery were highlighted, faculty must consider how they best deliver online learning content, making use of pedagogical strategies that will create as many learning and engagement opportunities as possible.

EXTERNAL EVALUATION OF SELF-DIRECTED LEARNING SKILLS: ONLINE EDUCATION

Self-isolation measures implemented during the Covid-19 pandemic resulted in a quick transition to online instruction. As a result, teachers and students must master online learning tools and technologies in educational institutions. In addition, the problems with online education are frequently reported in scholarly sources. Many participants in the educational process faced difficulties during this period. In our opinion, many difficulties in online education were caused by insufficient training of self- directed learning skills in students and corresponding skills in teachers. At the same time, this group of universal learning skills is a mandatory part of education in Russian schools. The skills of self-organization and self-control are included in the Russian federal state educational standards requirements. A considerable number of scientific publications are devoted to the formation of assessment skills in school children. At the same time, the problem of training self-directed learning skills in online classes has not been sufficiently studied. This article examines the results of an independent assessment of self-directed learning skills and training in online classes for both primary school students and primary school teachers. As a result of the study, the following skills were identified as important for teaching primary school online learners: Planning, Self-Monitoring, Self-assessment, and selecting effective approaches for online learning. Empirical data were collected as part of the study. From this, the following points can be made: Primary school teachers are not prepared for online teaching; time demands on teachers have increased due to the specifics of teacher self-monitoring under the new conditions. Consequently, students need to learn the following skills during online teaching: self-monitoring, use of automated assessment and monitoring tools, self- and peer-assessment in the digital educational environment, and planning. The empirical data obtained show the importance of training self-monitoring skills for online teaching. Therefore, the proposed recommendations for improving teacher training education programs in pedagogical universities and in the teacher professional development system have practical relevance and can be implemented through appropriate educational programs.

Agent based online learning approach for power flow control of electric vehicle fast charging station integrated with smart microgrid

AbstractIn stochastic power systems, electric vehicle (EV) fast charging stations (FCS) are rapidly being installed, while adversely impacts the distribution network. Due to this, the improper offline charging control policies for EVs may increase the voltage fluctuation and instability. To analyse these aspects, this paper investigates the problems associated with offline (dis)charging control for effective utilization of battery storage and grid power through different modes of operations. Further, the need to develop real‐time charging control is identified to mitigate the adverse impacts of FCS on the distribution network. Hence, an online controller using reinforcement learning (RL) is designed to distinguish the uncertainties in real‐time and to schedule the (dis)charging of an EV against the uncertainties based on travelling pattern. The RL based online controller uses deep neural network (DNN), where the agents are programmed to control the bi‐directional power flow (V2G/G2V). The effectiveness of the RL rewards controller is fulfilled by the different charging states of the battery. The performance of online (dis)charging controllers that utilize DNN to act at its optimal power flow set of points for all sessions are examined in the details. Finally, the effectiveness of online RL controller and hardware results have been realized using real time hardware‐in‐the loop simulator.

Penerapan Metode Blended Learning dalam Pembelajaran pada Masa Pandemi Covid-19

This study aims to analyze learning innovation, blended learning model as a strategy in learning during the covid 19 pandemi. This research method uses a literature review of journals. The analysis of this study concludes that blended learning is needed to improve the quality and quantity of learning. This learning model combines face-to-face and online learning approaches. With a mixed learning strategy, learning becomes flexible. The blended learning model can make it easier for participants to access learning materials and materials, increase learning motivation and participants' independence so that learning is more effective. This blended learning model can be applied as a learning model in educational institutions. To improve the quality of blended learning in learning, it is necessary to have adequate information technology infrastructure and student independence.