Online Learning Framework Research Articles

An Online Transfer Learning Framework for Cell SOC Online Estimation of Battery Pack in Complex Application Conditions

An Online Transfer Learning Framework for Cell SOC Online Estimation of Battery Pack in Complex Application Conditions

Physics-Informed Online Learning for Temperature Prediction in Metal AM.

In metal additive manufacturing (AM), precise temperature field prediction is crucial for process monitoring, automation, control, and optimization. Traditional methods, primarily offline and data-driven, struggle with adapting to real-time changes and new process scenarios, which limits their applicability for effective AM process control. To address these challenges, this paper introduces the first physics-informed (PI) online learning framework specifically designed for temperature prediction in metal AM. Utilizing a physics-informed neural network (PINN), this framework integrates a neural network architecture with physics-informed inputs and loss functions. Pretrained on a known process to establish a baseline, the PINN transitions to an online learning phase, dynamically updating its weights in response to new, unseen data. This adaptation allows the model to continuously refine its predictions in real-time. By integrating physics-informed components, the PINN leverages prior knowledge about the manufacturing processes, enabling rapid adjustments to process parameters, geometries, deposition patterns, and materials. Empirical results confirm the robust performance of this PI online learning framework in accurately predicting temperature fields for unseen processes across various conditions. It notably surpasses traditional data-driven models, especially in critical areas like the Heat Affected Zone (HAZ) and melt pool. The PINN's use of physical laws and prior knowledge not only provides a significant advantage over conventional models but also ensures more accurate predictions under diverse conditions. Furthermore, our analysis of key hyperparameters-the learning rate and batch size of the online learning phase-highlights their roles in optimizing the learning process and enhancing the framework's overall effectiveness. This approach demonstrates significant potential to improve the online control and optimization of metal AM processes.

Fair Resource Allocation in Virtualized O-RAN Platforms

O-RAN systems in virtualized platforms (O-Cloud) offer performance boosts but also raise energy concerns. This paper assesses O-Cloud's energy costs and proposes energy-efficient policies for base station (BS) data loads and transport block (TB) sizes. These policies balance energy savings and performance fairly across servers and users. To handle the unknown and time-varying parameters affecting the policies, we develop a novel online learning framework with fairness guarantees that apply to the entire operation horizon of the system (long-term fairness).

The Framework of Online Learning Based on PBL-PL for College English Courses

The Framework of Online Learning Based on PBL-PL for College English Courses

Dynamic Environment Responsive Online Meta-Learning with Fairness Awareness

The fairness-aware online learning framework has emerged as a potent tool within the context of continuous lifelong learning. In this scenario, the learner’s objective is to progressively acquire new tasks as they arrive over time, while also guaranteeing statistical parity among various protected sub-populations, such as race and gender when it comes to the newly introduced tasks. A significant limitation of current approaches lies in their heavy reliance on the i.i.d (independent and identically distributed) assumption concerning data, leading to a static regret analysis of the framework. Nevertheless, it’s crucial to note that achieving low static regret does not necessarily translate to strong performance in dynamic environments characterized by tasks sampled from diverse distributions. In this article, to tackle the fairness-aware online learning challenge in evolving settings, we introduce a unique regret measure, FairSAR, by incorporating long-term fairness constraints into a strongly adapted loss regret framework. Moreover, to determine an optimal model parameter at each time step, we introduce an innovative adaptive fairness-aware online meta-learning algorithm, referred to as FairSAOML. This algorithm possesses the ability to adjust to dynamic environments by effectively managing bias control and model accuracy. The problem is framed as a bi-level convex-concave optimization, considering both the model’s primal and dual parameters, which pertain to its accuracy and fairness attributes, respectively. Theoretical analysis yields sub-linear upper bounds for both loss regret and the cumulative violation of fairness constraints. Our experimental evaluation of various real-world datasets in dynamic environments demonstrates that our proposed FairSAOML algorithm consistently outperforms alternative approaches rooted in the most advanced prior online learning methods.

Safety enhancement for nonlinear systems via learning-based model predictive control with Gaussian process regression

This paper proposes a novel safe Gaussian process model predictive control scheme for discrete-time nonlinear systems subject to additive uncertainties. The scheme is implemented using an online learning framework that provides safety guarantees based on a nominal model, and employs Gaussian process regression (GPR) to learn the uncertainties to improve the control performance. The advantage of this framework lies in the ability to decouple safety and performance in the robust controller design. Furthermore, the inaccuracy measure given by GPR can be used to adaptively tighten the constraints, leading to the less conservative behaviors. A rigorous analysis of the constraint satisfaction, recursive feasibility and closed-loop stability is also presented. Two simulation examples, including a regulation problem of a nominally linear system and a tracking problem of a car whose model is nonlinear, are performed to verify the effectiveness of the proposed scheme.

Challenges of learning English in late adulthood: The case of online learning

Foreign language learning has been found effective in helping older people improve cognitive functioning and provide opportunities at psychological and social levels. This study examines the difficulties older adult English as a Foreign Language (EFL) learners and their instructors encounter within the online learning and instruction framework. To achieve this objective, seven EFL learners over 60 and two English teachers were included as participants in the study. The collection of qualitative data occurred over six weeks during an English course. The objective was achieved by submitting participants' weekly self-reflection reports, interviews with learners and instructors, and the researchers' observations. A content analysis was conducted to examine the qualitative data. The study's findings indicate that learners aged 60 and over have several cognitive and physical obstacles when participating in online English courses. Additionally, they rely on their previous learning habits, potentially impacting their overall learning experience. This study provides insights into the pedagogical implications of teaching English to older adults and recommendations for traditional face-to-face classroom instruction and online learning modalities.

Validating Foreign Language Classroom Anxiety Scale for High School Students

With the implementation of the Bilingual 2030 policy by the National Development Council in 2018, understanding the anxiety levels of junior and senior high school students in Taiwan regarding the English language has become crucial, especially in the context of online learning. This study reviewed the Foreign Language Classroom Anxiety Scale, modifying its factor structure and reducing the number of items to 19. The revised scale encompasses four factors: anxiety, self-efficacy, social comparison, and unwillingness to attend English classes. Data collected from 625 junior and senior high school students, within the framework of online learning, indicate the proposed scale's effectiveness and reliability in investigating English language anxiety among students. Additionally, the study offers insights into the impact of gender, grades, and the four identified factors.

Fair Resource Allocation in Virtualized O-RAN Platforms

O-RAN systems and their deployment in virtualized general-purpose computing platforms (O-Cloud) constitute a paradigm shift expected to bring unprecedented performance gains. However, these architectures raise new implementation challenges and threaten to worsen the already-high energy consumption of mobile networks. This paper presents first a series of experiments which assess the O-Cloud's energy costs and their dependency on the servers' hardware, capacity and data traffic properties which, typically, change over time. Next, it proposes a compute policy for assigning the base station data loads to O-Cloud servers in an energy-efficient fashion; and a radio policy that determines at near-real-time the minimum transmission block size for each user so as to avoid unnecessary energy costs. The policies balance energy savings with performance, and ensure that both of them are dispersed fairly across the servers and users, respectively. To cater for the unknown and time-varying parameters affecting the policies, we develop a novel online learning framework with fairness guarantees that apply to the entire operation horizon of the system (long-term fairness). The policies are evaluated using trace-driven simulations and are fully implemented in an O-RAN compatible system where we measure the energy costs and throughput in realistic scenarios.

Supervised Hierarchical Online Hashing for Cross-modal Retrieval

Online cross-modal hashing has gained attention for its adaptability in processing streaming data. However, existing methods only define the hard similarity between data using labels. This results in poor retrieval performance, as they fail to exploit the semantic structure information of labels and miss the high-quality hash codes guided by the hierarchical relevance between labels. In addition, they ignore the bit-flipping problem, which leads to sub-optimal cross-modal retrieval performance. To address these issues, we propose Supervised Hierarchical Online Hashing (SHOH) for cross-modal retrieval. Our approach acquires hierarchical similarity via cross-layer affiliation of labels and explores its application to online hashing. We design a hierarchical similarity learning method in the online learning framework, which includes virtual center learning and hierarchical similarity embedding. Labels with soft similarity bridge the label hierarchy and cross-modal hash embedding. Furthermore, we propose a Weighted Retrieval Strategy (WRS) to mitigate the impact caused by bit-flipping errors. Extensive experiments and verification on hierarchical and non-hierarchical datasets demonstrate that SHOH preserves accurate inter-class distances and achieves performance improvements compared to state-of-the-art methods. The source code is available at https://github.com/HUST-IDSM-AI/SHOH .

Applications of Generative Artificial Intelligence in Online Learning and Ethical Governance Framework

Applications of Generative Artificial Intelligence in Online Learning and Ethical Governance Framework

Enhancing Student Learning Experiences Through Integrated Constructivist Pedagogical Models

This study investigates the use of constructive pedagogy models to effectively engage students and enhance their learning experiences in college courses. Meaningful Online Learning attributes was used to redesign a face-to-face course in Sultan Qaboos University in Oman. The contemporary landscape of higher education is marked by a dynamic shift towards optimizing pedagogical approaches to meet diverse learning needs and preferences and to effectively engage students and enhance their learning experiences. Within this context, this research delves into the exploration of constructive pedagogy models as a means to actively engage students and elevate their learning experiences in the realm of college courses. A mixed-method approach was employed to conduct an exploratory case study, which involved the use of various instruments and sources such as a pre-course survey, a focus group discussion, and an analysis of the course based on the Meaningful Online Learning framework. This study lies in providing guidelines for faculty to redesign their courses using constructive approaches, particularly emphasizing the MOL attributes and to improve the quality of their courses. The results unveiled a positive correlation between the incorporation of Meaningful Online Learning attributes into the course redesign and the improvement of students' learning experiences. Furthermore, students exhibited the acquisition of novel skills and knowledge through the adaptation of assignments and learning activities associated with the course. Educators in higher education have to enhance their courses based on the MOL principles to effectively engage students in learning process and to design active and constructive courses that contribute to enhance students’ learning success. The researcher recommends applying this approach and the obtained design principles to other courses for refinement purposes. Additionally, they suggest conducting a comparative study between a class with traditional pedagogy and a class with constructivist pedagogy. Implication of the finding of this study showed that it is important to design engaging learning experiences to gain students the required skill to compete globally and contribute effectively to their communities. That is, students are playing crucial roles in society’s development especially in sustainable development. Further investigation is needed to refine and enhance the obtained principles and to share best practices of designing meaningful learning using innovative pedagogy models.

EPOC: A 28-nm 5.3 pJ/SOP Event-driven Parallel Neuromorphic Hardware with Neuromodulation-based Online Learning.

Bio-inspired neuromorphic hardware with learning ability is highly promising to achieve human-like intelligence, particularly in terms of high energy efficiency and strong environmental adaptability. Though many customized prototypes have demonstrated learning ability, learning on neuromorphic hardware still lacks a bio-plausible and unified learning framework, and inherent spike-based sparsity and parallelism have not been fully exploited, which fundamentally limits their computational efficiency and scale. Therefore, we develop a unified, event-driven, and massively parallel multi-core neuromorphic online learning processor, namely EPOC. We present a neuromodulation-based neuromorphic online learning framework to unify various learning algorithms, and EPOC supports high-accuracy local/global supervised Spike Neural Network (SNN) learning with a low-memory-demand streaming single-sample learning strategy through different neuromodulator formulations. EPOC leverages a novel event-driven computation method that fully exploits spike-based sparsity throughout the forward-backward learning phases, and parallel multi-channel and multi-core computing architecture, bringing 9.9× time efficiency improvement compared with the baseline architecture. We synthesize EPOC in a 28-nm CMOS process and perform extensive benchmarking. EPOC achieves state-of-the-art learning accuracy of 99.2%, 98.2%, and 94.3% on the MNIST, NMNIST, and DVS-Gesture benchmarks, respectively. Local-learning EPOC achieves 2.9× time efficiency improvement compared with the global learning counterpart. EPOC operates at a typical clock frequency of 100 MHz, providing a peak 328 GOPS/51 GSOPS throughput and a 5.3 pJ/SOP energy efficiency.

Locality sensitive hashing scheme based on online-learning

Locally Sensitive Hashing (LSH) algorithms are classical algorithms commonly used on the c-Approximate Nearest Neighbor (c-ANN) search problem. When using Euclidean distance to measure sample similarity and solve the c-ANN problem, the traditional approach is to utilize the Exact Euclidean Locality Sensitive Hashing (E2LSH) algorithm based on the p-stable distribution. However, the uncertainty of the p-stable distribution causes the hash buckets constructed by the E2LSH algorithm to vary in queries. Therefore, this paper proposes the OLLSH algorithm based on the Weighted Majority algorithm in the Online-Learning framework, which selects the hash buckets with more stable query accuracy by weighted voting on the hash buckets generated by the E2LSH algorithm. Then, we conduct simulation experiments on synthetic dataset and four real data sets and conclude that the proposed OLLSH algorithm improves the accuracy compared to the original algorithm with the same memory usage.

Exploring the pros and cons of online courses for physiotherapists — a theoretical study

Physiotherapy, as a constantly evolving discipline, requires professionals to continually update their knowledge base to enhance patient care. To facilitate this growth, lifelong learning through supplementary educational courses plays a crucial role. The flexible online education has opened new opportunities for adult learners, including physiotherapists, to pursue further education while managing their daily commitments. This paper examines the conceptual framework of online learning in the context of physiotherapy education. It explores the advantages and disadvantages of online courses compared to traditional classroom methods. Online education is classified into three primary types: synchronous, asynchronous, and blended or hybrid courses. Synchronous courses involve real-time interaction with teachers, while asynchronous courses allow learners to access materials at their own convenience. Blended or hybrid courses combine online learning with face-to-face instruction. Advantages of online courses include accessibility, flexibility, cost-effectiveness, diverse learning resources, and the opportunity to build a global professional network. On the other hand, online courses lack continuous communication and interaction between teachers and learners, potentially hindering the learning experience. Learners must possess strong digital skills and self-study capabilities to succeed in online education.The study concludes that the choice between traditional and online education depends on specific course objectives and participant expectations. Regardless of the mode of education, the active participation and engagement of learners are crucial for professional success. As the field of physiotherapy education continues to evolve, ongoing research and innovation are vital to improve the overall learning experience and ensure optimal outcomes for lifelong learners in the healthcare field.

Integrating education for sustainable development into a sustainable-smart transdisciplinary learning framework

Education for Sustainable Development (ESD) has been gaining traction as a promising approach for addressing social challenges and driving positive change within society. The purpose of this article is to explore how ESD can be foregrounded to reframe and enrich an existing learning framework called the Interdisciplinary Collaborative Online Learning Framework (ICoL). The ICoL framework has been developed since 2020 using a Design-based Research methodology. Literature on ESD lacks exploration of practical implementation for interdisciplinary collaborative projects within communities. This article interrogates the question of how to integrate ESD within the ICoL learning framework. This study is explorative, and data are drawn from a review of the literature and student reflections. A qualitative, themed analysis of the data revealed a fifth learning design principle and a fourth structuring element towards a new learning framework, called the Sustainable-Smart Transdisciplinary Learning Framework.

BANDT: A Border-Aware Network With Deformable Transformers for Visual Tracking

Siamese trackers that predict a tracking box over a regular grid of feature maps based on the sliding-window paradigm have recently drawn widespread attention in the tracking community. However, the sliding-window paradigm lacks the exploration to characterize the explicit border features of the tracking object for accurate box prediction. Furthermore, Siamese trackers do not use an online learning process to improve the model’s discriminative power and a deformable transformer to explore the rich temporal context from the successive frames. To overcome these issues, we propose a border-aware network with deformable transformers (BANDT), which contains classification and regression branches for tracking. The proposed BANDT tracker introduces a border-alignment operation to capture the “border features" from the extreme points of the object’s border to improve the point features of the sliding-window paradigm. The BANDT tracker implements a deformable transformer consisting of an encoder and a decoder to enhance the target representations within a discriminative online learning framework. Specifically, the introduced encoder of the deformable transformer enhances the target representations, while the decoder highlights the potential tracking location. The proposed tracker achieves state-of-the-art performance on seven public datasets. In particular, it achieves 69.6% overlap success and 90.0% precision scores on the UAV123 dataset.

RecON: Online learning for sensorless freehand 3D ultrasound reconstruction.

Sensorless freehand 3D ultrasound (US) reconstruction based on deep networks shows promising advantages, such as large field of view, relatively high resolution, low cost, and ease of use. However, existing methods mainly consider vanilla scan strategies with limited inter-frame variations. These methods thus are degraded on complex but routine scan sequences in clinics. In this context, we propose a novel online learning framework for freehand 3D US reconstruction under complex scan strategies with diverse scanning velocities and poses. First, we devise a motion-weighted training loss in training phase to regularize the scan variation frame-by-frame and better mitigate the negative effects of uneven inter-frame velocity. Second, we effectively drive online learning with local-to-global pseudo supervisions. It mines both the frame-level contextual consistency and the path-level similarity constraint to improve the inter-frame transformation estimation. We explore a global adversarial shape before transferring the latent anatomical prior as supervision. Third, we build a feasible differentiable reconstruction approximation to enable the end-to-end optimization of our online learning. Experimental results illustrate that our freehand 3D US reconstruction framework outperformed current methods on two large, simulated datasets and one real dataset. In addition, we applied the proposed framework to clinical scan videos to further validate its effectiveness and generalizability.

Online decision making for trading wind energy

We propose and develop a new algorithm for trading wind energy in electricity markets, within an online learning and optimization framework. In particular, we combine a component-wise adaptive variant of the gradient descent algorithm with recent advances in the feature-driven newsvendor model. This results in an online offering approach capable of leveraging data-rich environments, while adapting to the nonstationary characteristics of energy generation and electricity markets, also with a minimal computational burden. The performance of our approach is analyzed based on several numerical experiments, showing both better adaptability to nonstationary uncertain parameters and significant economic gains.

An online learning framework for self-adaptive dynamic thermal modeling of building envelopes

Modeling dynamic thermal behavior plays a crucial role for developing effective energy management strategies of buildings. In this work, we introduce an improved framework for online training of the GP-integrated 3R-2C model for building envelopes using a modified Ensemble Kalman filter (EnKF) algorithm. The framework combines the R-C model for defining physical constraints with Gaussian process (GP) predictor to capture time-varying thermal dynamics. This modified EnKF algorithm is designed based on Bayesian estimation theory and adapted for online learning, which eliminates the need for offline data collection and training. Numerical experiments using varied synthetic datasets were conducted to evaluate the effectiveness of the proposed framework. The results show that this framework significantly outperforms conventional schemes using the augmented EnKF algorithm: its relative deviations from benchmark results are only half of those achieved by the conventional ones. Importantly, this framework can gradually improve itself and be adapted to the incidental variations in heat transfer characteristics of building surfaces. Furthermore, it is highly flexible, which can be extended to deal with various thermal modeling problems through the utilization of different R-C models and configurations of GP predictors or machine learning techniques.