Rapid Learning Research Articles

Impact of virtual reality on performance among undergraduate healthcare professionals: A cross-sectional study

ABSTRACT In recent years, Virtual Reality (VR) has been increasingly used to train healthcare professionals. However, certain aspects of its application, such as the relationship between VR environments, training, and Sense of Presence (SoP), have yet to be explored. SoP impacts learners’ performances in certain learning situations, whereas in others, it does not. This study aimed to investigate the impact of VR, including SoP, on immersive mass incident simulation performances. A cross-sectional study was performed by immersing 83 undergraduate students (ambulance attendants, student nurses, and medical students) in a VR simulation. Questionnaires were administered before, during, and after the simulation to assess variables impacting non-technical skills. The results revealed that SoP was not associated with performance (P = 0.66). However, performance was associated with the learners’ perceptions of the VR environment (P = 0.008). Therefore, the impact of environmental perception on performance should be considered, allowing instructors to promote optimal training in VR. Moreover, SoP may impact performance in certain types of learning, like emotional skills training. Thus, VR should be chosen as a simulation modality to encourage reflexivity through rapid feedback and learning skills in the affective domain.

Usability of an Eye Drop Delivery Aid for Single-Dose Instillation: Results from a Market Research Study.

One of the challenges of treating chronic ocular diseases like vernal keratoconjunctivitis (VKC), glaucoma, and ocular surface disease is patient adherence to topical medication. To support correct eye drop instillation, a variety of delivery aids have been developed for both single-dose and conventional multi-dose containers. To evaluate Dropaid™ Single-dose, an eye drop delivery aid designed for single-dose containers, a usability study was conducted on 30 parents and caregivers of patients with VKC. After assessing the ability to squeeze a single eye drop from the single-dose container onto the eye of a pediatric medical dummy, the delivery aid was evaluated using an 11-point Likert scale on a variety of characteristics: from "very difficult" (-5) to "very easy" (+5). The majority of participants rated the task of opening the single-dose units (SDUs), preparing, and positioning the Dropaid™ Single-dose device as "very easy". When providing a single eye drop from the container, 87% of participants rated the Dropaid™ Single-dose device as either "very easy" or "easy", with a median rating score of +5.0 (interquartile range [IQR], 4.0-5.0). For general ease of use, 84% considered the delivery aid as either "very easy" or "easy", with a median score of +4.0 (IQR, 3.0-5.0). Most participants (93%) rated Dropaid™ Single-dose as either "very comfortable" or "comfortable" to hold, with a median score of +5.0 (IQR, 4.0-5.0). The Dropaid™ Single-dose delivery aid demonstrated rapid learning and ease of use across all stages of application, including opening the container, eye drop administration, and handling comfort. Although designed for use with single-dose containers to help eye drop instillation in patients with VKC, Dropaid™ Single-dose may provide a wider utility across a range of other ocular diseases such as glaucoma and dry eye.

Towards a sustainable edge computing framework for condition monitoring in decentralized photovoltaic systems

In recent times, the rapid advancements in technology have led to a digital revolution in urban areas, and new computing frameworks are emerging to address the current issues in monitoring and fault detection, particularly in the context of the growing renewable decentralized energy systems. This research proposes a novel framework for monitoring the condition of decentralized photovoltaic systems within a smart city infrastructure. The approach uses edge computing to overcome the challenges associated with costly processing through remote cloud servers. By processing data at the edge of the network, this concept allows for significant gains in speed and bandwidth consumption, making it suitable for a sustainable city environment. In the proposed edge-learning scheme, several machine learning models are compared to find the best suitable model achieving both high accuracy and low latency in detecting photovoltaic faults. Four light and rapid machine learning models, namely, CBLOF, LOF, KNN, ANN, are selected as best performers and trained locally in decentralized edge nodes. The overall approach is deployed in a smart solar campus with multiple distributed PV units located in the R&D platform Green & Smart Building Park. Several experiments were conducted on different anomaly scenarios, and the models were evaluated based on their supervision method, f1-score, inference time, RAM usage, and model size. The paper also investigates the impact of the type of supervision and the class of the model on the anomaly detection performance. The findings indicated that the supervised artificial neural network (ANN) had superior performance compared to other models, obtaining an f1-score of 80 % even in the most unfavorable conditions. The findings also showed that KNN was the most suitable unsupervised model for the investigated experiments achieving good f1-scores (100 %, 95 % and 92 %) in 3 out of 4 scenarios making it a good candidate for similar anomaly detection tasks.

Who Learns Fastest, Wins: Lean Startup and Discovery Driven Growth

Most entrepreneurial ventures fail. Most corporate ventures fail too, often more expensively. Against this backdrop, Lean Startup and Discovery-Driven Growth (DDG) are methods that emphasize rapid learning, resource parsimony, and an intense focus on validating assumptions as ways of reducing the cost and risk of failure. Lean Startup had its roots in and makes a contribution to entrepreneurship; Discovery-Driven Growth emerged instead from the study of corporate innovation efforts. Both acknowledge that planning methods based on low-uncertainty situations fall short when faced with high-uncertainty contexts. DDG suggests five design steps that interact: defining success, checking for realism, defining operations, documenting assumptions, and planning through checkpoints. Similar to Lean Startup, it emphasizes an experimental approach to learning. Different than Lean Startup, it is less prescriptive about the method and embraces wider uncertainties than Lean Startup's focus on product-market fit. In a context that has been described as an “innovation arms race,” both methods are a major advance over traditional planning processes because they both emphasize rapid learning. As is rapidly becoming clear, in more and more parts of the evolving digital economy, whoever learns the fastest wins.

A robot-aided visuomotor wrist training induces motor and proprioceptive learning that transfers to the untrained ipsilateral elbow

BackgroundLearning of a visuomotor task not only leads to changes in motor performance but also improves proprioceptive function of the trained joint/limb system. Such sensorimotor learning may show intra-joint transfer that is observable at a previously untrained degrees of freedom of the trained joint.ObjectiveHere, we examined if and to what extent such learning transfers to neighboring joints of the same limb and whether such transfer is observable in the motor as well as in the proprioceptive domain. Documenting such intra-limb transfer of sensorimotor learning holds promise for the neurorehabilitation of an impaired joint by training the neighboring joints.MethodsUsing a robotic exoskeleton, 15 healthy young adults (18–35 years) underwent a visuomotor training that required them to make continuous, increasingly precise, small amplitude wrist movements. Wrist and elbow position sense just-noticeable‐difference (JND) thresholds and spatial movement accuracy error (MAE) at wrist and elbow in an untrained pointing task were assessed before and immediately after, as well as 24 h after training.ResultsFirst, all participants showed evidence of proprioceptive and motor learning in both trained and untrained joints. The mean JND threshold decreased significantly by 30% in trained wrist (M: 1.26° to 0.88°) and by 35% in untrained elbow (M: 1.96° to 1.28°). Second, mean MAE in untrained pointing task reduced by 20% in trained wrist and the untrained elbow. Third, after 24 h the gains in proprioceptive learning persisted at both joints, while transferred motor learning gains had decayed to such extent that they were no longer significant at the group level.ConclusionOur findings document that a one-time sensorimotor training induces rapid learning gains in proprioceptive acuity and untrained sensorimotor performance at the practiced joint. Importantly, these gains transfer almost fully to the neighboring, proximal joint/limb system.

Hemorrhage Evaluation and Detector System for Underserved Populations: HEADS-UP

ObjectiveTo create a rapid, cloud-based, and deployable machine learning (ML) method named hemorrhage evaluation and detector system for underserved populations, potentially across the Mayo Clinic enterprise, then expand to involve underserved areas and detect the 5 subtypes of intracranial hemorrhage (IH). MethodsWe used Radiological Society of North America dataset for IH detection. We made 4 total iterations using Google Cloud Vertex AutoML. We trained an AutoML model with 2000 images, followed by 6000 images from both IH positive and negative classes. Pixel values were measured by the Hounsfield units, presenting a width of 80 Hounsfield and a level of 40 Hounsfield as the bone window. This was followed by a more detailed image preprocessing approach by combining the pixel values from each of the brain, subdural, and soft tissue window-based gray-scale images into R(red)-channel, G(green)-channel, and B(blue)-channel images to boost the binary IH classification performance. Four experiments with AutoML were applied to study the effects of training sample size and image preprocessing on model performance. ResultsOut of the 4 AutoML experiments, the best-performing model was the fourth experiment, where 95.80% average precision, 91.40% precision, and 91.40% recall were achieved. On the basis of this analysis, our binary IH classifier hemorrhage evaluation and detector system for underserved populations appeared both accurate and performed well. ConclusionHemorrhage evaluation and detector system for underserved populations is a rapid, cloud-based, deployable ML method to detect IH. This tool can help expedite the care of patients with IH in resource-limited hospitals.

Hierarchical Episodic Control

Deep reinforcement learning is one of the research hotspots in artificial intelligence and has been successfully applied in many research areas; however, the low training efficiency and high demand for samples are problems that limit the application. Inspired by the rapid learning mechanisms of the hippocampus, to address these problems, a hierarchical episodic control model extending episodic memory to the domain of hierarchical reinforcement learning is proposed in this paper. The model is theoretically justified and employs a hierarchical implicit memory planning approach for counterfactual trajectory value estimation. Starting from the final step and recursively moving back along the trajectory, a hidden plan is formed within the episodic memory. Experience is aggregated both along trajectories and across trajectories, and the model is updated using a multi-headed backpropagation similar to bootstrapped neural networks. This model extends the parameterized episodic memory framework to the realm of hierarchical reinforcement learning and is theoretically analyzed to demonstrate its convergence and effectiveness. Experiments conducted in four-room games, Mujoco, and UE4-based active tracking highlight that the hierarchical episodic control model effectively enhances training efficiency. It demonstrates notable improvements in both low-dimensional and high-dimensional environments, even in cases of sparse rewards. This model can enhance the training efficiency of reinforcement learning and is suitable for application scenarios that do not rely heavily on exploration, such as unmanned aerial vehicles, robot control, computer vision applications, and so on.

Rapid runtime learning by curating small datasets of high-quality items obtained from memory.

We propose the "runtime learning" hypothesis which states that people quickly learn to perform unfamiliar tasks as the tasks arise by using task-relevant instances of concepts stored in memory during mental training. To make learning rapid, the hypothesis claims that only a few class instances are used, but these instances are especially valuable for training. The paper motivates the hypothesis by describing related ideas from the cognitive science and machine learning literatures. Using computer simulation, we show that deep neural networks (DNNs) can learn effectively from small, curated training sets, and that valuable training items tend to lie toward the centers of data item clusters in an abstract feature space. In a series of three behavioral experiments, we show that people can also learn effectively from small, curated training sets. Critically, we find that participant reaction times and fitted drift rates are best accounted for by the confidences of DNNs trained on small datasets of highly valuable items. We conclude that the runtime learning hypothesis is a novel conjecture about the relationship between learning and memory with the potential for explaining a wide variety of cognitive phenomena.

THE ROLE OF EARLY CHILDHOOD EDUCATION IN PROMOTING LONG-TERM ACADEMIC SUCCESS

This article provides a comprehensive review of the role of early childhood education(ECE) in promoting long-term academic success. Early childhood is a critical period of rapid brain development and learning, making high-quality educational experiences during this time crucial for future academic achievement.The article explores the theoretical foundations of ECE, examines the key componenets of effective early childhood programs, and synthesizes empirical research on the long-term impacts of ECE on academic outcomes.Moreover, this paper aims to demonstrate the role of ECE in promoting long-term academic success by examining the social, emotional, and cognitive development of children.

Early Gains in Motor Learning Measured Through Two Coordination Tests: A Retrospective Analysis of Gender Differences

Motor skills can be improved through rapid on-the-job training or slower multi-session learning. The objective of this study was to determine the rapid learning differences between male and female university students during the execution of two motor coordination tests. Available data from 716 female and 331 male college students were retrospectively analyzed. The female participants had a mean age (±SD) of 19.6 (±1.55) years, while the male participants recorded a mean age of 19.8 (±1.87) years. Data were collected using two motor coordination tests, each performed in triplicate. The statistical method used in this analysis was mixed-model ANOVA. The interaction effect of gender and number of attempts was statistically significant for both motor coordination tests (F=12.446; p<0.01; η2p=0.13 & F=11.169; p<0.01; η2p=0.01). Post-hoc testing showed that males performed better at the tasks in all three runs, and both genders improved their performance in subsequent trials. However, females showed a larger relative improvement from trial to trial than did males. The two coordination tests yield similar results. The observed differences in improvements in the coordination tests may be attributed to different motor learning strategies and cognitive processing between the sexes.

A study on the effectiveness of self-assessment learning system of ideological and political education for college students

Ideology and political education can be strengthened through legal interventions to enhance the judiciary learner approach and instill values and culture in college students' programs. Traditional methods are employed for rapid learning in ideology teaching and politics and social instruction. A self-assessment learning system allows students to evaluate their progress and the significance of changed learning criteria. Democratizing the teaching system and transforming ideological education present challenges, but Internet Multi-Media (IMM) and Digital Virtual Technology (DVT) provides innovative solutions. IMM-DVT enables comparative explorations and better comprehension of ideological and political education. It facilitates understanding of unequal social interactions and promotes the political, economic, and social sciences as essential components of ideology. Collecting knowledge through media streams and enabling interactions in teaching and learning improves educational effectiveness. Innovative ideological and cultural education strategies help to measure political development and college students' ideas resulting from individual experiences. The college's coordination of social practice projects with the examination has led to improved evaluation results for the ideological and political theory course, along with enhanced social practice competence among the students.

Personalized Symmetrical and Asymmetrical Gait Generation of a Lower Limb Exoskeleton

Personal assistive devices for rehabilitation will be in increasing demand during the coming decades due to demographic change, i.e., an aging society. Among the elderly population, difficulty in walking is the most common problem. Even though there are commercially available lower-limb exoskeleton systems, the coordination between user and device still needs to be improved to achieve versatile personalized gaits. To tackle this issue, an advanced EXOskeleton framework for Versatile personalized gaIt generation with a Seamless user-exo interface (called “EXOVIS”) is proposed in this study. The main control of the framework uses adaptive bio-inspired modular neural mechanisms. These mechanisms include decoupled central pattern generators (CPGs) with Hebbian-based synaptic plasticity and adaptive CPG post-processing networks with error-based learning. The control method facilitates the rapid online learning of personalized walking gaits described by the walking frequency as well as hip, knee, and ankle joint patterns. The method is verified on a real lower-limb exoskeleton system with six degrees of freedom (DOFs) on different subjects under static and dynamic conditions such as flat terrain and a split-belt treadmill. The results show that the proposed method can not only automatically learn to generate personalized symmetrical gaits, but also asymmetrical gaits, which have not been explicitly shown by other approaches so far.

On Electrochemically Driven Phase Change and Accelerated Test Protocols in Solid Oxide Cells

The aim of this talk is to address three fundamental questions in solid oxide fuel cells and solid oxide electrolysis cells:(1) Whether or not the oxygen reduction reaction is indeed the limiting step in solid oxide cells and how to quantify it definitely?(2) What is the origin for the so-called “electrochemically driven phase transformation and how to translate the understanding to achieve a high-performance and highly stable electrode?(3) How to develop reliable accelerated test protocols and what’s the physical process that was accelerated?Quantifying electrode polarization in fuel cells and electrolyzers is of significant importance. It, however, remains difficult because of the substantial overlap of polarizations from both negative and positives electrodes either in a dc or an ac measurement. This challenge leads to a compelling gap in our scientific understanding of electrode phenomena and designing high-performance and durable electrochemical devices. In this talk, we will describe a reproducible method to quantify the polarization of an individual electrode of a solid oxide cell. This method is generic and can be applied readily to other electrochemical cells.We will then address the greater phase transformation of an oxygen electrode during operation when compared to thermally annealed powders. Theoretical analysis suggests that the presence of a reduced oxygen partial pressure at the interface between the oxygen electrode and the electrolyte is the origin for the phase change in an oxygen electrode. Guided by the theory, an addition of the electronic conduction in the interface layer leads to the significant suppression of phase change, while improving cell performance and performance stability.Reliable accelerated test protocols are needed for solid oxide fuel cell research to facilitate rapid learning on key durability issues, identify potential modes of failure expeditiously, and eventually predict the calendar lifetime of an electrochemical cell. In this work, solid oxide fuel cells operated at a constant current density were compared to cells undergoing accelerated measurements, which are composed of intermittent current injection to the cell. A general accelerated test profile was developed by cycling a solid oxide fuel cell from open circuit to a predetermined operating current density that is the same as the current density during a steady-state operation, to accelerate the local redox environment. Up to 1,320,000 cycles were generated in this work. The cell degradation was accelerated by nearly 10×, suggesting the feasibility of using this protocol for acceleration test to predict life performance of solid oxide fuel cells.Finally, we will present a theoretical model that underlies those three questions and can be used to address stability and durability issues in solid oxide fuel cells and solid oxide electrolysis cells.

Examining the Setting of Significant Learning Events during the Engineering School-to-Work Transition

The school-to-work transition is a critical time for engineers that involves rapid learning across multiple fronts, but relatively little is known about the setting (i.e., how, where, and with whom) of significant learning experiences during this time. The purpose of the study is to examine the setting of significant learning events for recent engineering graduates. We used a multi-case study in which 12 recent engineering graduates responded to weekly reflective journal prompts for the first twelve weeks of their transition from school to work. Participants described significant learning events through a series of open-ended questions. We used both deductive and inductive coding to identify the setting of the event in terms of how, where, and with whom engineers engaged in learning at work. The findings highlight the emergent, social nature of workplace learning and point to critical differences across school and work. To better prepare students for professional practice, engineering educators should consider how they might create learning environments that promote effective transfer of knowledge and skills.

Starting a robotic thoracic surgery program: From wedge resection to sleeve lobectomy in six months. Initial conclusions

IntroductionRobot-assisted thoracic surgery (RATS) is a rapidly expanding technique. In our study, we aimed to analyze the results of the process to adopt robotic surgery in our Department of Thoracic Surgery. MethodsThis is an intention-to-treat analysis of a series of consecutive patients operated on using the RATS approach in our hospital from January 2021 to March 2022. Data were registered for patient characteristics, type of surgery, operative times, conversion rate, chest tube duration, length of hospital stay and complications.The IBM SPSS® statistical software was used for the statistical analysis. A cumulative sum analysis of the operating time was performed to define the learning curve. ResultsDuring the study period, 51 patients underwent robotic surgery, including pulmonary and non-pulmonary interventions. In addition, 15 patients (29.4%) underwent non-pulmonary interventions: one pleural (2%), 2 diaphragmatic (3.9%), and 12 mediastinal (23.5%). Among the mediastinal surgeries, one conversion was necessary (8.3%) for a complex vascular malformation, and 11 were completed by RATS, including 7 (58.3%) thymomas, 3 (25%) pleuro-pericardial cysts, and one (8.3%) neurogenic tumor. Mean operative time was 141 min (104–178), mean chest tube duration was 0.9 days (0–2), and mean length of stay was 1.45 days (1–2).Thirty-six patients underwent lung surgery (70.6%). The complete RATS resections (34; 94.4%) included: 3 wedge resections (11.1%), 2 segmentectomies (3.7%), 28 lobectomies (81.5%), and one sleeve lobectomy (3.7%). Mean surgery time was 194.56 min (141–247), chest tube duration was 3.92 days (1–8), and length of stay was 4.6 days (1–8). Complications occurred in 4 patients (11.1%). No 90-day mortalities were registered. ConclusionsThe implementation of RATS was achieved with good clinical results and operative times for all indications. A rapid learning curve was accomplished in short time. Previous VATS experience, patient selection, team training and program continuity are fundamental to successfully develop a RATS program.

Development and Application of a Reference Manual for Diagnosis and Rational Use of Antimicrobial Agents for Outpatient Primary Care (Digestive System Part): A Delphi Study.

To establish a concise and easy-to-understand reference manual for outpatient primary care providers, promoting correct diagnosis of digestive system diseases and rational antimicrobial use. The establishment of the manual encompassed two processes: the development of a draft manual and the validation of the manual. The development process was based on a literature review and expert discussion. The manual comprises portions for disease diagnosis and rationality of antimicrobial use. The validation process employed a two-round Delphi technique, collecting consensus through paper-based or mail-based communications. The response of the Delphi group was assessed by the level of authority and commitment of the panelists and the degree of agreement among them. Furthermore, the manual was preliminarily applied among primary care physicians. A total of 29 panelists completed the Delphi working process. They were authoritative in their professional fields with authority coefficients of 0.813 and 0.818 for the two portions of the manual, respectively. The level of commitment of the panelists was measured by response rates, which were 100.00% and 96.67% for Round 1 and 2. After two rounds, a consensus was achieved with the consensus rates for the two portions of the manual being greater than 65% and 70%, respectively. Kendall W-tests had P-values < 0.001 in both rounds. This reference manual provides 200 diagnostic indicators for 29 common digestive diseases and recommendations for the rational use of antimicrobial agents for 13 categories of digestive diseases. The primary care physicians who used the reference manual reported high satisfaction and frequent usage. Based on a collective consensus of professionals, a reference manual has been established, to provide a concise and easy-to-understand guide specifically for physicians and pharmacists in outpatient primary care. It could facilitate rapid learning to improve the accuracy of diagnosis and treatment for digestive disorders.

Prioritization, Incentives, and Resource Use for Sustainable Dentistry: The EU PRUDENT Project.

The EU PRUDENT project aims to enhance the financing of oral health systems through novel evidence and implementation of better financing solutions together with citizens, patients, providers, and policy makers. The multicountry nature of the project offers unique windows of opportunity for rapid learning and improving within and across various contexts. PRUDENT is anticipated to strengthen capacities for better oral care financing in the EU and worldwide.

Deep Dyna-Q for Rapid Learning and Improved Formation Achievement in Cooperative Transportation

Nowadays, academic research, disaster mitigation, industry, and transportation apply the cooperative multi-agent concept. A cooperative multi-agent system is a multi-agent system that works together to solve problems or maximise utility. The essential marks of formation control are how the multiple agents can reach the desired point while maintaining their position in the formation based on the dynamic conditions and environment. A cooperative multi-agent system closely relates to the formation change issue. It is necessary to change the arrangement of multiple agents according to the environmental conditions, such as when avoiding obstacles, applying different sizes and shapes of tracks, and moving different sizes and shapes of transport objects. Reinforcement learning is a good method to apply in a formation change environment. On the other hand, the complex formation control process requires a long learning time. This paper proposed using the Deep Dyna-Q algorithm to speed up the learning process while improving the formation achievement rate by tuning the parameters of the Deep Dyna-Q algorithm. Even though the Deep Dyna-Q algorithm has been used in many applications, it has not been applied in an actual experiment. The contribution of this paper is the application of the Deep Dyna-Q algorithm in formation control in both simulations and actual experiments. This study successfully implements the proposed method and investigates formation control in simulations and actual experiments. In the actual experiments, the Nexus robot with a robot operating system (ROS) was used. To confirm the communication between the PC and robots, camera processing, and motor controller, the velocities from the simulation were directly given to the robots. The simulations could give the same goal points as the actual experiments, so the simulation results approach the actual experimental results. The discount rate and learning rate values affected the formation change achievement rate, collision number among agents, and collisions between agents and transport objects. For learning rate comparison, DDQ (0.01) consistently outperformed DQN. DQN obtained the maximum −170 reward in about 130,000 episodes, while DDQ (0.01) could achieve this value in 58,000 episodes and achieved a maximum −160 reward. The application of an MEC (model error compensator) in the actual experiment successfully reduced the error movement of the robots so that the robots could produce the formation change appropriately.

Making a Grand Contribution: Fostering Learner Self‐Efficacy is the Key to Rapid Learning Performance Gains

Making a Grand Contribution: Fostering Learner Self‐Efficacy is the Key to Rapid Learning Performance Gains

Movement during the acquisition of a visual landmark may be necessary for rapid learning in ants.

We conducted laboratory experiments using Japanese carpenter ants (Camponotus japonicus) to investigate whether movement during visual learning can influence the learning performance of ant foragers. We performed three different experiments. In the first experiment, the ants could move freely in a straight maze during the visual learning. The ants in the experiments two and three were fixed to a certain position during the visual learning training. A distinct difference between these two experiments was that the ants in one experiment could perceive an approaching visual stimulus during the training, although they were fixed. After training phases, a Y-maze test was performed. One arm of the Y-maze had a visual stimulus presented to the ants during the training. We found that the ants in the first experiment showed rapid learning and correctly selected the landmark arm. However, the ants in the experiments two and three did not exhibit any preference for the chosen arm. Interestingly, we found differences in the time spent around a certain location in the Y-maze between the experiments two and three. These results suggest that movement during visual learning may influence the rapid learning of ant foragers.