Online Machine Learning Research Articles

Push-sum Distributed Dual Averaging Online Convex Optimization With Bandit Feedback

Push-sum Distributed Dual Averaging Online Convex Optimization With Bandit Feedback

Exploring University Students' Self-Directed Learning in Online Learning

This qualitative case study aims to understand the situation of university students' SDL and identify the factors that help university students solve the problem of SDL in online learning. It involved seven participants who were selected according to the inclusion criteria. Using thematic analysis of the interview data, the researchers found that the university students' perceptions of the problems of SDL in online learning are: traditional teaching and learning limits SDL, lack of effective monitoring and evaluation of the SDL process, insufficient awareness of SDL, insufficient effective resources for SDL, methods of teaching SDL need to be improved, and inadequate online learning platform. Besides, reforming online teaching and learning models, building a mechanism for monitoring and evaluating SDL, strengthening university students' knowledge of SDL, improving online learning resources, improving methods of teaching SDL, and creating an online favorable atmosphere for university students are solutions to help university students solve the problem of SDL in online learning.

Analyzing Queueing Problems via Bandits With Linear Reward & Nonlinear Workload Fairness

Queueing models serve as important building blocks in many networking applications such as task scheduling in mobile edge computing nodes, traffic scheduling in networks, congestion control in Internet, etc. However, queueing theory often needs to make strong assumptions about the arrival process or service rewards at each queue. In addition, fairness in serving workload among all queues is of great importance in many applications. In this paper, we address how to optimize resource allocation among multiple queues with a fairness guarantee and without any a priori knowledge of these queues' parameters. To characterize queues with unknown parameters and the fairness requirement, we formulate an online learning model with a varying and continuous action space, as well as a nonlinear utility objective. We design an online learning algorithm to tackle the problem. We prove that our algorithm has a regret upper bound of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$O(\sqrt{T}\log T)$</tex-math></inline-formula> and our model has a regret lower bound of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\Omega (\sqrt{T})$</tex-math></inline-formula> , where <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$T$</tex-math></inline-formula> stands for the number of decision rounds. The asymptotic closeness of upper and lower bounds guarantees their near tightness and our algorithm's near optimality. We discuss our model's real-world applications in mobile edge computing, wireless networks, and crowdsourcing, and conduct simulations to validate our algorithm's effectiveness.

Digital learning in physiotherapy education: Exploring design approaches through meta-analysis

The implementation of internet-based educational designs to enhance teaching and learning could be advantageous for higher education. There is not much research on digital methods of learning in physiotherapy education. The investigation examines and assesses methods of online learning in an effort to raise the standard of physiotherapy education. An extensive meta-analysis and evaluation of both randomized and non-randomized tests are the proposed methods of the research. A map was made of the digital initiatives and research mentioned in the list. Learning impacts for similar interventions were determined by means of meta-analysis. Five cohort investigations and ten randomized controlled trials make up the total of 15 researches included in the evaluation. Blended learning, remote learning, and the flipped classroom methodology were all used in 14 studies. In all, seven of the fifteen pieces of content were referenced in the flipped classrooms have statistically significant effects on learning, according to a meta-analysis for interaction uses on useful skills. Based on the findings, integrating pedagogical approaches is equally, if not more, more efficient than a regular classroom instruction in obtaining learning objectives. Results in online education did not show any discernible variations from traditional classroom training. It has been found that space learning and integrated learning are just as effective as traditional teaching approaches, if not more so, in the field of physiotherapy education. The meta-analysis found that using student-made videos, flipped classrooms, and interactive websites improved students' learning. Larger controlled trials are needed to validate these results. Research ought to investigate the ways in which online learning models can make possible students' assimilation in pragmatic abilities and behaviors, facilitate their understanding of concepts, enhance their memory of contents, and cultivate methods of learning. Further, it needs to examine digital learning materials and information bases.

Flipping Childbirth Education.

Since many childbirth education (CBE) courses have moved online, there is a need for a pedagogical design model for online learning. In this study, an online CBE course was flipped, user studies were conducted, and a pedagogical design model was developed. Flipped learning was chosen as it combines asynchronous and synchronous learning activities. The developed model was further strengthened by conducting a pilot study with public health nurses. User data were collected with questionnaires and analyzed using inductive thematic analysis. The results show that in informal learning settings, emphasis should be on which elements are asynchronous or synchronous and mandatory or voluntary. Additionally, time management and interaction between participants and their peers and the instructor should be considered for future training.

Online Submodular Maximization via Online Convex Optimization

We study monotone submodular maximization under general matroid constraints in the online setting. We prove that online optimization of a large class of submodular functions, namely, threshold potential functions, reduces to online convex optimization (OCO). This is precisely because functions in this class admit a concave relaxation; as a result, OCO policies, coupled with an appropriate rounding scheme, can be used to achieve sublinear regret in the combinatorial setting. We also show that our reduction extends to many different versions of the online learning problem, including the dynamic regret, bandit, and optimistic-learning settings.

Enhancing Online Learning: A Multimodal Approach for Cognitive Load Assessment

Online learning has become increasingly popular in recent years, but the frequent occurrence of cognitive overload has been notably impacting both the learning experience and effectiveness. Therefore, based on optimizing online learning, this study proposes a research framework for cognitive load assessment of online learning based on three modal data: electroencephalography (EEG), eye tracking, and face. Following this framework, a neural network was used to construct a cognitive load assessment model for online learning that integrates multimodal data. After validation, the assessment accuracy of the model reaches 91.52%. In addition, the results based on multimodal data analysis can be used as a reference for the development of learning resources and the optimization of online courses in intelligent online learning platforms. The assessment model constructed in this study can also be applied to the online learning platform, which is expected to realize prescription-adaptive online learning based on cognitive load assessment. Due to current research limitations, only specific thematic learning models have been explored. Future research will focus on model fine-tuning, complex learning scenarios and themes designing and expansion of research scale to enhance the model’s generalization capabilities.

Model Pembelajaran Online Maharah Al- Kalam di Pusat Kursus Bahasa Arab Pondok “ Takallam” Pare Kediri Jawa Timur

The selection of online learning models, especially for students, shows that the application of learning speaking skills is said to be unable to function perfectly without the formation of an active component and a linguistic environment. In addition, most of the Arabic language activists also have difficulty developing speaking skills due to space and time constraints. But in essence, language environments can be created not only through direct learning interactions, but also through distance learning programs. Therefore, one of the alternative learning methods that they can take to further develop their speaking skills is to take several online Arabic courses through informal learning institutions at the Takallam Institute of Arabic Language Course, Pare Kediri, East Java. The researcher used this research with descriptive and qualitative research types. This research was conducted at the Takallam Institute of Arabic Language Course in Pare Kediri, East Java. The subject of this research is a tutor or online class teacher at the Takallam Institute of Arabic Language Course at Pare Kediri, East Java. Meanwhile, the informants in this study were the director of the Takallam Institute of Arabic Language Course Institute Pare Kediri, East Java and participants of online class learning. The data collection methods that researchers use to obtain the data needed in writing this research, namely the method of observation, interviews and documentation. Test the validity of the data through source triangulation, technical triangulation, and temporal triangulation. While the data analysis technique was carried out in different stages, namely analysis before going into the field, data reduction, data presentation, and drawing conclusions. The results show that the online learning model of speaking skills at the Takallam Institute of Arabic Language Course in Pare Kediri, East Java, can run smoothly and inject the purpose of teaching speaking skills, meaning that participants can understand and practice speaking Arabic fluently. Learning speaking skills is carried out with the online maharah kalam learning model at the Takallam Institute Arabic Language Course Institute, Pare Kediri, East Java and is a type of direct learning model by applying the special "Takallam" method to improve speaking skills or mukalamah bil lughotil arabiyyah.

Online Learning-Based Surrogate Modeling of Stratospheric Airship Solar Array Output Power

The stratospheric airship is a type of aerostat that uses solar energy as its power source and can fly continuously for months or even years in near space. The rapid and accurate prediction of the output power of its solar array is the key to maintaining energy balance and extending flight time. This paper establishes an online learning model for predicting the output power of the solar array of stratospheric airships. The readings of radiometers arranged on the surface of the airship are used as features for training the model. The parameters of the model can be updated in real-time during the flight process without retraining the entire model. The effect of radiometer placement on the model accuracy was also analyzed. The results show that for the continuous flight of 40 days, the online learning model can achieve an accuracy of 88% after training with 10 days of flight data and the accuracy basically reaches its highest level after 20 days. In addition, placing the radiometers at the four corners of the array can achieve a higher prediction accuracy of 95%. The online model can also accurately identify and reflect the effect of module efficiency attenuation or damage and maintain high accuracy.

Intelligent femtosecond laser bone drilling via online monitoring and machine learning

In conventional spinal surgeries, mechanical and thermal injuries frequently usually arise due to improper handling, giving rise to a range of complications including infection, poor wound healing and bleeding. Femtosecond laser ablation offers a promising approach owing to high precision and low thermal damage. In this study, an intelligent femtosecond laser drilling method of human spinal bones has been proposed, and a machine learning method has been employed to determine the optimal laser processing window, ensuring high-quality outcomes. A neural network model has been developed to predict drilling quality, achieving an impressive accuracy rate exceeding 98 %, along with precision and recall rates of 100 % and 92.86 %, respectively. To further monitor the process, a fiber spectrometer and a thermal camera has been employed to monitor the focal status and bone temperature during laser processing to make sure the drilling is in a focal position and temperature in safe range. Subsequently, the drilling efficiency has been predicted using another neural network model within high-quality processing window for the maximum ablation processing parameter. The current research has demonstrated a direct, non-destructive and efficient method for intelligent laser spinal drilling.

Hybrid learning of predictive mobile-edge computation offloading under differently-aged network states

By offloading computationally demanding applications to edge servers, mobile edge computing (MEC) can alleviate the stringent hardware requirements and save energy consumption of resource-restrained devices. Mobile edge computation offloading (MECO, i.e., optimizing computation offloading and resource allocation) is critical to the performance of MEC. However, the existing study typically assumed the availability of all the network states for the upcoming time slot, not applicable in practical MECO with differently-aged network states (e.g., fast-changing practical wireless channels and instantly observable local task arrivals). This paper proposes a novel hybrid learning approach that optimizes the instantaneous local processing and predictive computation offloading decisions. We establish a new hybrid learning approach for instantaneous local processing and predictive computation offloading decisions by integrating the learning techniques of stochastic gradient descent (SGD) and online convex optimization (OCO). By decomposing the primal problems, the proposed approach can be implemented in a decentralized manner. We prove that the optimality loss resulting from the differently-aged network states can diminish with the decreasing stepsizes of SGD and OCO. Simulation results validate the asymptotic optimality and superiority of the proposed hybrid learning approach, as compared to state-of-the-art (e.g., based on OCO techniques).

Dynamic Industrial Optimization: A Framework Integrates Online Machine Learning for Processing Parameters Design

We develop the online process parameter design (OPPD) framework for efficiently handling streaming data collected from industrial automation equipment. This framework integrates online machine learning, concept drift detection and Bayesian optimization techniques. Initially, concept drift detection mitigates the impact of anomalous data on model updates. Data without concept drift are used for online model training and updating, enabling accurate predictions for the next processing cycle. Bayesian optimization is then employed for inverse optimization and process parameter design. Within OPPD, we introduce the online accelerated support vector regression (OASVR) algorithm for enhanced computational efficiency and model accuracy. OASVR simplifies support vector regression, boosting both speed and durability. Furthermore, we incorporate a dynamic window mechanism to regulate the training data volume for adapting to real-time demands posed by diverse online scenarios. Concept drift detection uses the EI-kMeans algorithm, and the Bayesian inverse design employs an upper confidence bound approach with an adaptive learning rate. Applied to single-crystal fabrication, the OPPD framework outperforms other models, with an RMSE of 0.12, meeting precision demands in production.

An extended community of inquiry framework supporting students in online and digital education

ABSTRACT In response to the COVID-19 pandemic, universities across the world were forced to move from a classroom-based delivery model to an online learning model which heavily disrupted the learning process for students. Despite proactive efforts for academic staff to embrace online teaching tools and techniques, the pressing urgency with which solutions were implemented raised concerns about the competence of academic staff to deliver online education effectively, the capabilities of digital tools and technologies required for different topics, and the quality of students’ learning experiences. Within a university postgraduate setting, this research adopts the Community of Inquiry (CoI) framework to explore the social presence, teaching presence, and cognitive presence as essential elements facilitating the educational experiences of 100 students within an online learning environment. The findings expand current literature by proposing a revised CoI framework, the Digital Community of Inquiry Framework, to highlight an additional need, that of ‘self-presence’.

Students' Self-Directed Learning Readiness with the Online Learning Model

This research aims to reveal the level of Students' Self-Directed Learning Readiness with the Online Learning Model. The research was conducted on students of the Arabic Language Education Study Program, Faculty of Islamic Religion, University of Muhammadiyah Malang with 66 respondents selected using purposive techniques. Research data was collected through a questionnaire with the Self-Directed Learning Readiness Scale (SDLRS) instrument developed by Guglielmino, and was analyzed using the SPSS Windows Release 7.5.1 program. The research results show that the level of students' Self-Directed Learning readiness with online learning model is in the average category with the score of 223.6, which means that students have the ability to successfully study independently, but are less ready to face challenges and solve problems independently.

The Impact of Online Learning Models on Educational Implementation and Issue Analysis

When compared to in-person settings, despite the fact that online platforms provide flexible access, there are major pedagogical constraints that limit the ability to maintain student engagement and motivation. With the exponential growth in online education, comprehensively evaluating the efficacy and persistent barriers that constrain learner outcomes is imperative. This paper provides an in-depth analysis of the evolution of online learning models, ideal frameworks, resultant transformations in teaching methodologies and learning processes, key challenges like uneven motivation and academic performance, and potential solutions. The findings reveal that despite expanding access and flexibility, fully online models hamper engagement and achievement due to transactional designs, social isolation, and motivation declines. However, emerging blended, multimedia and learner-driven personalization showcase the potential to match offline results by balancing experience, outcomes and access if challenges are addressed. Recommendations encompass competency analytics, teacher retraining in online best practices, tailor-made content, modernized platforms and inclusive upgrades to enhance user experience. Comparative research on motivation factors and skill building across settings can guide universal designs to fulfill online learning's global promise for equitable and rewarding access at scale.

Students’ Perceptions on Online Teaching and Learning in Higher Education

Virtual environments allow teachers to approach the teaching process inclusively and creatively, to facilitate the effective transfer of learning and to support student learning with new technologies regardless of various barriers. The hereby study evaluates the students’ views concerning the virtual delivery of courses during their learning process taking into consideration their former face-to-face teaching-learning experience. It was based on the theoretical part which included typical aspects of online teaching and learning are presented and the most recent studies in this area are reviewed. Following previous research, we aim to develop an innovative model of successful online teaching and learning in higher education. A questionnaire-based research methodology was designed for 355 students at a university in the North-Eastern region of Romania. The questionnaire with closed-ended items was used for assessing students’ attitudes on the online teaching activity. The results indicate students’ preference for online courses, as well as a number of significant differences, depending on the study specialisation or form of education. Any future changes to online teaching and learning in universities should also take into account students’ and teachers’ views on this particular issue. Such an approach should allow us to see whether and how effective the use of virtual teaching environments can be for both students and teachers in higher education (HE).

Online Arabic Language Teaching Model Based on Collaborative Learning in Indonesian Senior High Schools

This research focuses on the implementation of online/virtual Arabic language learning at Darul Quran Senior High School in Mojokerto, utilizing the collaborative-based learning model known as "The Group Process Model" in the maharah kitabah (Arabic writing skills). Employing the 5M scientific approach and active learning, the study aims to elucidate: (1) the collaborative-based online learning model for maharah kitabah, (2) the application of this learning model, and (3) its impact on improving students' writing skills. Through a descriptive qualitative approach, data were gathered using interviews, observations, and documentation. Analysis involved data reduction, presentation, and drawing conclusions. Findings revealed the preparation of E-learning Moddle, WAG, and Zoom applications, alongside various learning tools such as syllabi, lesson plans, and online learning guides to support collaborative learning and its assessment. The application of the online Arabic Writing Skill model followed a structured approach, including introductory, core, and closing activities, supplemented by assignments and initial activities using the WAG application and Zoom meetings. Students accessed course materials and assignments via the school's E-learning Moddle. The collaborative learning model in Arabic Writing Skill demonstrated enhanced student outcomes and collaborative problem-solving skills in the classroom.

An In-Depth Literature Review of Remote, Online, and Hybrid Learning with Case Studies of Successful and Failed Attempts

This literature review traces the historical development and changing educational delivery modalities to examine the evolution, application, and effects of remote, online, and hybrid learning models. It offers a theoretical framework outlining important educational ideas and techniques, concentrating on how different learning styles are considered within these paradigms and their difficulties and advantages. The paper emphasizes how significant technology developments have influenced remote learning, especially when combining synchronous and asynchronous learning techniques in hybrid models. Effective course design, learner engagement, technology infrastructure, faculty training, and institutional support are all factors that contribute to successful implementation. The study also contains case studies demonstrating successful and failed implementation initiatives, emphasizing the techniques, instructional approaches, technological integrations employed, and results and outcomes obtained. The analysis suggests best practices and suggestions for educators, institutions, and legislators to improve the effective implementation of various learning models, address possible issues, and offer enough faculty and student support. This thorough literature analysis provides insights into the dynamic interaction between pedagogy, technology, and institutional support in distant, online, and hybrid learning, serving as a significant resource in education and learning.

Online Convex Optimization with Switching Cost and Delayed Gradients

We consider the online convex optimization (OCO) problem with quadratic and linear switching cost when at time t only gradient information for functions f T , T &lt; t is available. For L-smooth and µ-strongly convex objective functions, we propose an algorithm (OMGD) with a competitive ratio of at most 4(L+5)+ 16(L+5)/µ for the quadratic switching cost, and also show the bound to be order-wise tight in terms of L, µ. In addition, we show that the competitive ratio of any online algorithm is at least maxΩ(L),Ω( L/√µ ) when the switching cost is quadratic. For the linear switching cost, the competitive ratio of the OMGD algorithm is shown to depend on both the path length and the squared path length of the problem instance, in addition to L, µ, and is shown to be order-wise, the best competitive ratio any online algorithm can achieve.

Brave New World: Navigating New Paradigms in the Educational Landscape for the Evolving Learner in a Rapidly Changing Era

This literature review explores the significant transformations in the educational landscape prompted by technological advancements and changing learner profiles in the digital era. The review examines the evolution of learner profiles, highlighting the shift towards multisensory learning, digital fluency, and a preference for interactive, personalized learning experiences. It delves into integrating innovative technologies such as virtual reality (VR), augmented reality (AR), and blockchain in education and discusses their implications for teaching and learning. The review also considers the impact of neuroscience on educational practices, emphasizing the importance of understanding brain functioning and neuroplasticity in developing effective teaching strategies. The unprecedented shift to online and blended learning models, accelerated by the COVID-19 pandemic, is analyzed for its long-term effects on educational delivery and pedagogy. Additionally, the review addresses the growing emphasis on interdisciplinary learning, sustainability, mental health, and well-being within educational curricula. The implications of these transformative trends for educators, policymakers, and learners are discussed, highlighting the need for adaptive and responsive approaches to education in the face of rapid technological and societal changes. The review concludes with reflections on the future trajectory of education, anticipating continued technical integration, evolving pedagogical theories, and an increased focus on preparing learners for global challenges and lifelong learning.