Adaptive Trajectory Tracking During Motorized and FES-Induced Biceps Curls via Integral Concurrent Learning

A common rehabilitative technique for those with neuro-muscular disorders is functional electrical stimulation (FES) induced exercise such as FES-induced biceps curls. FES has been shown to have numerous health benefits, such as increased muscle mass and retraining of the nervous system. Closed-loop control of a motorized FES system presents numerous challenges since the system has nonlinear and uncertain dynamics and switching is required between motor and FES control, which is further complicated by the muscle having an uncertain control effectiveness. An additional complication of FES systems is that high gain feedback from traditional robust controllers can be uncomfortable to the participant. In this paper, data-based, opportunistic learning is achieved by implementing an integral concurrent learning (ICL) controller during a motorized and FES-induced biceps curl exercise. The ICL controller uses adaptive feedforward terms to augment the FES controller to reduce the required control input. A Lyapunov-based analysis is performed to ensure exponential trajectory tracking and opportunistic, exponential learning of the uncertain human and machine parameters. In addition to improved tracking performance and robustness, the potential of learning the specific dynamics of a person during a rehabilitative exercise could be clinically significant. Preliminary simulation results are provided and demonstrate an average position error of 0.14 ± 1.17 deg and an average velocity error of 0.004 ± 1.18 deg/s.

AdaLinUCB: Opportunistic Learning for Contextual Bandits

In this paper, we propose and study opportunistic contextual bandits - a special case of contextual bandits where the exploration cost varies under different environmental conditions, such as network load or return variation in recommendations. When the exploration cost is low, so is the actual regret of pulling a sub-optimal arm (e.g., trying a suboptimal recommendation). Therefore, intuitively, we could explore more when the exploration cost is relatively low and exploit more when the exploration cost is relatively high. Inspired by this intuition, for opportunistic contextual bandits with Linear payoffs, we propose an Adaptive Upper-Confidence-Bound algorithm (AdaLinUCB) to adaptively balance the exploration-exploitation trade-off for opportunistic learning. We prove that AdaLinUCB achieves O((log T)^2) problem-dependent regret upper bound, which has a smaller coefficient than that of the traditional LinUCB algorithm. Moreover, based on both synthetic and real-world dataset, we show that AdaLinUCB significantly outperforms other contextual bandit algorithms, under large exploration cost fluctuations.

Advancing learning through smart learning analytics: a review of case studies

Purpose Smart learning analytics (Smart LA) – i.e. the process of collecting, analyzing and interpreting data on how students learn – has great potentials to support opportunistic learning and offer better – and more personalized – learning experiences. The purpose of this paper is to provide an overview of the latest developments and features of Smart LA by reviewing relevant cases. Design/methodology/approach The paper studies several representative cases of Smart LA implementation, and highlights the key features of Smart LA. In addition, it discusses how instructors can use Smart LA to better understand the efforts their students make, and to improve learning experiences. Findings Ongoing research in Smart LA involves testing across various learning domains, learning sensors and LA platforms. Through the collection, analysis and visualization of learner data and performance, instructors and learners gain more accurate understandings of individual learning behavior and ways to effectively address learner needs. As a result, students can make better decisions when refining their study plans (either by themselves or in collaboration with others), and instructors obtain a convenient monitor of student progress. In summary, Smart LA promotes self-regulated and/or co-regulated learning by discovering opportunities for remediation, and by prescribing materials and pedagogy for remedial instruction. Originality/value Characteristically, Smart LA helps instructors give students effective and efficient learning experiences, by integrating the advanced learning analytics technology, fine-grained domain knowledge and locale-based information. This paper discusses notable cases illustrating the potential of Smart LA.

Opportunistic (L)earning in the Mobile Knowledge Society

This paper discusses the concept of opportunistic collaboration within the emerging mobile knowledge society. The paper illustrates how opportunistic collaboration can be applied to the areas of learning and earning by demonstrating how to transform a traditional unemployment agency into an Opportunistic Collaboration Agency based on an entrepreneurial supply-support network structured in the form of a prosumer manifold. The OCA pattern provides ways to capture the dynamics of entrepreneurial work-relations in the emerging ’work-portfolio society’, increase the transparency of the entire value chain of economic activities, and create prosumer value loops that can support multi-dimensional bartering and increase the opportunities for marginalized groups of people to create value together. The paper ends by demonstrating how to use the OCA pattern to transform a traditional educational institution into an Opportunistic Learning Activity Broker that could help to bridge the gap between formal and informal learning.

Opportunistic (L)earning in the Mobile Knowledge Society

This paper discusses the concept of opportunistic collaboration within the emerging mobile knowledge society. The paper illustrates how opportunistic collaboration can be applied to the areas of learning and earning by demonstrating how to transform a traditional unemployment agency into an Opportunistic Collaboration Agency based on an entrepreneurial supply-support network structured in the form of a prosumer manifold. The OCA pattern provides ways to capture the dynamics of entrepreneurial work-relations in the emerging ’work-portfolio society’, increase the transparency of the entire value chain of economic activities, and create prosumer value loops that can support multi-dimensional bartering and increase the opportunities for marginalized groups of people to create value together. The paper ends by demonstrating how to use the OCA pattern to transform a traditional educational institution into an Opportunistic Learning Activity Broker that could help to bridge the gap between formal and informal learning.