2,875 results on '"LEARNING strategies"'
Search Results
2. Preprofessional Identity of Nutrition and Dietetics Students in Australia.
- Author
-
Cleary, Angela, Thompson, Courtney, Villani, Anthony, and Swanepoel, Libby
- Subjects
- *
QUALITATIVE research , *FOCUS groups , *HEALTH occupations students , *UNDERGRADUATES , *PROFESSIONAL identity , *DESCRIPTIVE statistics , *DIETETICS education , *DISCUSSION , *MOTIVATION (Psychology) , *DIETITIANS , *CURRICULUM planning , *CLINICAL competence , *CONCEPTUAL structures , *ABILITY , *COMMUNICATION , *LEARNING strategies , *SOCIAL support , *NUTRITION education , *VOCATIONAL guidance , *TRAINING - Abstract
This study aimed to explore the preprofessional identity of undergraduate nutrition and dietetic students to guide curriculum development to better support the expectations of students and promote career readiness in a changing profession. Qualitative focus group discussions in March, 2021. An Australian university. First-year students enrolled in the Bachelor of Nutrition (n = 50) or Bachelor of Dietetics (n = 58) at the University of the Sunshine Coast. Student sociodemographics, motivations for and influences on career choice and preprofessional identity, expectations of professional competency and practice, degree, and career expectations. Descriptive statistics were conducted, and focus group discussions were analyzed using the Framework Approach. Motivations and skills were consistent across both cohorts, centering on an interest in nutrition and respectful, professional conduct and communication. Expectations were similar across both degrees, with a focus on placement, real-world learning experiences, and staff support. Career expectations for both cohorts included business ownership. This research provided an understanding of students' preprofessional identity, which was similar for both nutrition and dietetics students. Motivations identified in this research can be used to inform activities across nutrition and dietetic programs that support career readiness. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
3. Improving mental dysfunction detection from EEG signals: Self-contrastive learning and multitask learning with transformers.
- Author
-
Basheer, Shakila, Aldehim, Ghadah, Alluhaidan, Ala Saleh, and Sakri, Sapiah
- Subjects
DATA augmentation ,TRANSFORMER models ,LEARNING ability ,LEARNING strategies ,MENTAL illness - Abstract
Existing works relied on subjective interviews in clinical settings, which does not detect mental health problems at early stages. With the advancement in learning strategies, research are trying to find a better way for detecting mental disorders and dysfunctions at early stages. EEG signal measurements is one of the prolific ways for identifying mental disorders and dysfunction in a non-invasive and ubiquitous way. However, the label scarcity and multiclass classification concerning EEG signal measurements has been a challenge for the research community that hinders the realization of automated mental dysfunction identification using EEG signals. Data imbalance is another issue that indirectly relates to the data scarcity issue. To tackle this challenge, we propose a novel Transformer-based Self-Contrastive and Multitask Learning (SCAM-Learning) framework for mental dysfunction classification using EEG signals. The SCAM-Learning framework uses Transformer networks, self-supervised contrastive learning paradigm, and multitask learning strategy to improve the classification performance. The multitask learning is accomplished by utilizing simple and complex data augmentation strategies to train the network for pretext task. The self-supervised contrastive learning helps in dealing with data and label scarcity issues. We also propose a novel cross contrastive loss that helps in improving interdependent correlation matrix for improving the classification performance. Our experimental results on a publicly available dataset reveal that the proposed method can achieve up to 11.89% performance gain in comparison to the existing state-of-the-art methods. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
4. Perspectives on remote learning of orthotic fabrication by certified hand therapists.
- Author
-
Schofield, Katherine A., Schwartz, Deborah A., and Bolch, Charlotte
- Subjects
ALLIED health education ,CROSS-sectional method ,SCALE analysis (Psychology) ,SATISFACTION ,AFFINITY groups ,COST analysis ,ORTHOPEDIC apparatus ,CERTIFICATION ,CONFIDENCE ,DESCRIPTIVE statistics ,ALLIED health personnel ,SURVEYS ,THEMATIC analysis ,STUDENTS ,PROFESSIONS ,ONLINE education ,HAND injury treatment ,RESEARCH methodology ,ABILITY ,CLINICAL competence ,LEARNING strategies ,MEDICAL equipment design ,TRAINING ,ACCESS to information ,TIME - Abstract
The COVID-19 pandemic caused disruption to continuing educational opportunities for hand therapists. In response, some courses were offered via online platforms, including virtual orthotic fabrication courses. It is important to determine the effectiveness and benefits of these courses for educating certified hand therapists and examine if remote learning of orthotic fabrication skills has continued merit and relevance. To investigate the value and effectiveness of orthotic fabrication courses taught in a virtual format. Cross-sectional, mixed methods survey study. A 31-item survey consisting of Likert-type, direct response, and open-ended questions about experiences and opinions of virtual orthotics courses was electronically delivered to certified hand therapists. Data analysis included descriptive and correlational statistics to highlight frequencies, ranges, and relationships between the participant demographics and opinions/experiences. Thematic analysis guided the coding of the qualitative data. A total of 459 responded, with a response rate of 9.7%. Most respondents had not participated in online courses on orthotic fabrication. Those that did reported high satisfaction but noted that clinical experience and knowledge from previous courses influenced this experience. Most participants felt that novice clinicians and students would not gain enough skills and confidence from online courses. However, participants with all levels of experience found the courses to be of value. Results suggest that while online learning of this skill set is valuable and effective, it is most beneficial for experienced clinicians. Disadvantages included the lack of instructor feedback necessary for hands-on skill development and the lack of peer interaction. Advantages included convenience of time, cost, accessibility, and the ability to revisit the topic as needed. Online learning of orthotic fabrication skills is a sustainable option for clinicians seeking to advance their skills. Nevertheless, it is not a substitute for initial training for novice hand therapists due to the lack of feedback and skill development. • Orthotic fabrication skills can be taught in a virtual format. • Advantages include time, cost, and the ability to access course material on demand. • Disadvantages include limited instructor feedback, peer interaction, and material access. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
5. Alternative predictive approach for low-cycle fatigue life based on machine learning and energy-based modeling.
- Author
-
Yu, Jinyeong, Lee, Seong Ho, Cheon, Seho, Park, Sung Hyuk, and Lee, Taekyung
- Subjects
MACHINE learning ,CYCLIC loads ,PREDICTION models ,AEROSPACE industries ,LEARNING strategies - Abstract
• The study introduces a hybrid ML/E model combining machine learning with an energy-based physical model. • The model offers a unified prediction for the LCF life of anisotropic Mg alloys. • It enhances prediction accuracy utilizing several ML strategies: loop learning, ε t−1 feature, optimum ANN architecture, and modified morrow model. • It outperforms the conventional coffin-manson model in both predictability and generalizability. Mg alloys are extremely valuable in the automotive and aerospace industries because of their lightweight properties and excellent machinability. The applications in these industries necessitate the accurate prediction of fatigue life under cyclic loading. However, this is challenging for many wrought Mg alloys owing to their pronounced plastic anisotropy. Conventional predictive methods such as the Coffin-Manson equation require manual parameter adjustment for different conditions, thus limiting their applicability. Accordingly, a novel predictive model for low-cycle fatigue (LCF) life that combines machine learning (ML) with an energy-based physical model, referred to as the hybrid ML/E model, is proposed herein. The hybrid ML/E model leverages a substantial hysteresis-loop dataset generated from LCF tests on a rolled AZ31 Mg alloy to effectively predict fatigue life. The proposed approach addresses the inherent challenges of small fatigue datasets, hysteresis-loop perception, and algorithm selection. The hybrid ML/E model demonstrates superior predictive accuracy and robustness in various loading directions, based on validation against conventional methods. The integration of ML and physical principles offers a unified framework for the LCF life prediction of anisotropic materials and represents a significant advancement for industrial applications. [Display omitted] [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
6. Improving data participation for the development of artificial intelligence in dermatology.
- Author
-
de Luzuriaga, Arlene Ruiz
- Subjects
- *
MEDICAL personnel , *ARTIFICIAL intelligence , *LEARNING strategies , *TRUST , *ALGORITHMS - Abstract
Artificial intelligence (AI) has the potential to significantly impact many aspects of dermatology. The visual nature of dermatology lends itself to innovations in this space. The robustness of AI algorithms depends on the quality, quantity, and variety of data on which it is trained and tested. Image collections can suffer from inconsistencies in image quality, underrepresentation of various anatomic sites and skin tones, and lack of benign counterparts leading to underperformance of algorithms in contexts other than one in which it is developed. Access to care, trust, rights, control, and transparency all play roles in the willingness of patients and health care providers and systems to collect, provide, and share data. Opportunities to improve data participation for the development of AI include the establishment of data hubs and public algorithms, federated learning strategies, development of renumeration ecosystems for patients and systems, and development of criteria and mechanisms for transparency. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
7. Exploring clinicians' insertion experience with a new peripheral intravenous catheter in the emergency department.
- Author
-
Xu, Hui (Grace), Hyun, Areum, Kang, Evelyn, Marsh, Nicole, and Corley, Amanda
- Subjects
MEDICAL personnel ,QUALITATIVE research ,PATIENT safety ,BLOOD vessels ,INTERVIEWING ,CONTENT analysis ,FIELD notes (Science) ,HOSPITAL emergency services ,PATIENT care ,MEDICAL equipment ,PERIPHERAL central venous catheterization ,LEARNING strategies ,PSYCHOSOCIAL factors ,EMERGENCY nurses - Abstract
Hospitals frequently introduce new medical devices. However, the process of clinicians adapting to these new vascular access devices has not been well explored. The study aims to explore clinicians' experience with the insertion of a new guidewire peripheral intravenous catheter (PIVC) introduced in the emergency department (ED) setting. The study was conducted at two EDs in Queensland, Australia, utilising a qualitative explorative approach. Interviews were conducted with guidewire PIVC inserters, including ED doctors and nurses, and field notes were recorded by research nurses during insertions. Data analysis was performed using inductive content analysis, from which themes emerged. The study compiled interviews from 10 participants and field notes from 191 observation episodes. Five key themes emerged, including diverse experience, barriers related to the learning process, factors influencing insertion success, and recommendations to enhance clinicians' acceptance. These themes suggest that the key to successful adoption by clinicians lies in designing user-friendly devices that align with familiar insertion techniques, facilitating a smooth transfer of learning. Clinician adaptation to new devices is vital for optimal patient care. Emergency nurses and doctors prefer simplicity, safety, and familiarity when it comes to new devices. Providing comprehensive device training with diverse training resources, hands-on sessions, and continuous expert support, is likely to enhance clinician acceptance and the successful adoption of new devices in ED settings. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
8. Complex system anomaly detection via learnable temporal-spatial graph with degradation tendency segmentation.
- Author
-
Han, Qinfeng, Chen, Jinglong, Wang, Jun, and Feng, Yong
- Subjects
ANOMALY detection (Computer security) ,RELIABILITY in engineering ,ROCKET engines ,TIME series analysis ,LEARNING strategies - Abstract
To guarantee the safety and reliability of equipment operation, such as liquid rocket engine (LRE), carrying out system-level anomaly detection (AD) is crucial. However, current methods ignore the prior knowledge of mechanical system itself, and seldom unite the observations with the inherent relation in data tightly. Meanwhile, they neglect the weakness and nonindependence of system-level anomaly which is different from component fault. To overcome above limitations, we propose a separate reconstruction framework using worsened tendency for system-level AD. To prevent anomalous feature being attenuated, we first propose to divide single sample into two equal-length parts along the temporal dimension. And we maximize the mean maximum discrepancy (MMD) between feature segments to force encoders to learn normal features with different distributions. Then, to fully explore the multivariate time series, we model temporal-spatial dependence by temporal convolution and graph attention. Besides, a joint graph learning strategy is proposed to handle prior knowledge and data characteristics simultaneously. Finally, the proposed method is evaluated on two real multi-sensor datasets from LRE and the results demonstrate the effectiveness and potential of the proposed method on system-level AD. • A novel neural network based on segmenting and reconstructing temporal-spatial feature for system anomaly detection. • Segmenting operation is designed to overcome the weakness of anomaly, which is simple and universal for time series data. • A joint graph learning strategy and a novel temporal-spatial feature extraction module are proposed for multi-source data. • Experiments on two different real-world datasets are conducted and demonstrated the superiority of proposed method. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
9. Modeling and multi-objective optimal state-dependent control of a continuous double-bioreactor in series fermentation.
- Author
-
Wang, Juan, Zhao, Feiyan, Wang, Jichao, and Li, An
- Subjects
- *
NONLINEAR dynamical systems , *PARETO optimum , *LEARNING strategies , *FERMENTATION , *PARAMETERIZATION - Abstract
This paper models a continuous double-bioreactor in series fermentation of glycerol to 1,3-propanediol by a nonlinear dynamic system and formulates its process control by a multi-objective optimal control problem formulating the dilution rates as varying-coefficient state-dependent controls. Control parameterization and time scale transformation are firstly applied to transform the proposed optimal control problem into a large-scale parameter optimization problem, which is then solved by a novel numerical algorithm based on an improved dynamic neighborhood learning strategy and a classified pairwise competition mechanism. Numerical results suggest that the proposed algorithm has good diversity of solutions and convergence to the Pareto optimal front for complex multi-objective problems. Numerical comparisons indicate that the proposed control has the characters of shorter computation time, higher calculation accuracy, and poorer stability when compared to two closed-loop controls, and is better in system stability and improving mean productivity compared to two other open-loop controls. Simulation curves also show the potential application of double-bioreactor in series fermentation. [ABSTRACT FROM AUTHOR]
- Published
- 2025
- Full Text
- View/download PDF
10. Self-tuning framework to reduce the number of false positive instances using aggregation functions in ensemble classifier.
- Author
-
Gałka, Wojciech, Bazan, Jan G., Bentkowska, Urszula, Mrukowicz, Marcin, Drygaś, Paweł, Ochab, Marcin, Suszalski, Piotr, and Obara, Sebastian
- Subjects
MACHINE learning ,PHISHING ,LEARNING strategies ,ALGORITHMS ,POSTAL service - Abstract
In this contribution, the model which is dedicated to reducing the number of false positive instances is proposed. This is a self-tuning model using aggregation functions and time-series data periods. As a case study, the proposed model is tested in the context of phishing link detection. In the proposed model, well-known aggregation functions are applied to combine the confidence values of multiple Classification models for email phishing. The division of the dataset into multiple segments and subsets facilitates the implementation of incremental learning strategies. This approach enables the iterative enhancement of model performance through the training of new data while leveraging previously acquired knowledge. In our research, two datasets are considered, namely the existing PhiUSIIL phishing URL dataset as well as the dataset provided by the FreshMail company are applied. The proposed algorithm achieves a small number of expected false positives. This reduces the costs associated with manual analysis of such cases by domain experts (in the case of incorrect prediction as phishing mail). [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
11. Enhanced multi-strategy bottlenose dolphin optimizer for UAVs path planning.
- Author
-
Hu, Gang, Huang, Feiyang, Seyyedabbasi, Amir, and Wei, Guo
- Subjects
- *
BOTTLENOSE dolphin , *SWARM intelligence , *SHARKS , *LEARNING strategies - Abstract
A new enhanced multi-strategy bottlenose dolphin optimizer is proposed. • The superiority of the proposed algorithm is verified by comparing with efficient intelligent algorithms. • A three-dimensional path planning model for unmanned aerial vehicles with time, threat, height and smooth cost is studied. • The proposed algorithm is applied to solve the three-dimensional path planning problem for unmanned aerial vehicles. • The quality of the proposed algorithm based path planning results is better than other approaches. The path planning of unmanned aerial vehicle is a complex practical optimization problem, which is an important part of unmanned aerial vehicle technology. For constrained path planning problem, the traditional path planning methods can not deal with the complex constraint conditions well, and the classical nature-inspired algorithms will find the local optimal solution due to the lack of optimization ability. In this paper, an enhanced multi-strategy bottlenose dolphin optimizer is proposed to solve the unmanned aerial vehicle path planning problem under threat environments. Firstly, the introduction of fish aggregating device strategy that simulates the living habits of sharks enriches the behavioral diversity of the population. Secondly, random mixed mutation strategy and chaotic opposition-based learning strategy expand the exploration range of the algorithm in the solution space by disturbing the positions of some individuals and generating the opposite population respectively. Finally, after balancing the exploration and exploitation ability of the algorithm more reasonably through the mutation factor and energy factor, this paper proposes a new swarm intelligence algorithm. After verifying the adaptability and efficiency of the proposed algorithm through different types of test functions, this paper further highlights the advantages of the proposed algorithm in finding the optimal feasible path in the unmanned aerial vehicle path planning model based on four constraints. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
12. Active recall strategies associated with academic achievement in young adults: A systematic review.
- Author
-
Xu, Joy, Wu, Alyssa, Filip, Cosmina, Patel, Zinal, Bernstein, Sarah R., Tanveer, Rameen, Syed, Hiba, and Kotroczo, Tiffany
- Subjects
- *
YOUNG adults , *RETRIEVAL practice , *ACADEMIC achievement , *CONCEPT mapping , *LEARNING strategies , *TEAM learning approach in education - Abstract
Effective learning strategies are crucial to the development of academic skills and information retention, especially in post secondary education where increasingly complex subjects are explored. Active recall-based strategies have been identified as particularly effective for long-term learning. This systematic review investigates the effectiveness of various active recall-based learning strategies for improving academic performance and self-efficacy in higher education students. A systematic review of peer-reviewed articles was conducted with a priori criteria by searching PubMed, ScienceDirect, JSTOR, PsycInfo, and Web of Science databases. Search results were screened/extracted and reconciled by two independent authors with the use of a piloted screening tool. Included studies were assessed for quality and risk of bias using the GRADE Quality Assessment Tool for Quantitative Studies. Three overarching study strategies were extracted for further investigation including flashcards, practice testing or retrieval practice, and concept mapping. Within each category, three additional unique search strings were searched, screened, and extracted. A qualitative analysis of the studies was provided. Among the appraised articles, flashcards were found to be popular and correlated with higher GPA and test scores. Self-testing, retrieval practice, and concept mapping were also effective but under-utilized. Concept mapping was found to boost student confidence. Active recall strategies exhibit promise for effective learning and additional research in these developing field can support academic pursuits. • There are a range of learning strategies that students can implement to achieve stronger information retention skills, that they can apply to different facets of their life. • Significant active recall strategies reflected potential in technology-associated interventions, gamified learning experiences, and edutainment-based learning intervention. • Heterogeneity in included studies allude to inconsistent reports for certain associations of academic outcomes and learning strategies [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
13. Competency based medical education in nuclear cardiology: A tale of two axes.
- Author
-
Small, Gary R. and Chow, Benjamin J.W.
- Subjects
CURRICULUM ,MEDICAL education ,CARDIOLOGY ,SINGLE-photon emission computed tomography ,POSITRON emission tomography ,NUCLEAR medicine ,CLINICAL competence ,OUTCOME-based education ,LEARNING strategies ,NATIONAL competency-based educational tests - Abstract
Background: Across medical specialties, including nuclear cardiology, competency based medical education (CBME) changes the emphasis of learning from a time or experiential emphasis to a proficiency focused approached. Plotted on a learning-curve graph the emphasis on learning has shifted from the duration/ volume-based x-axis to the performance-based y-axis. Current status: It has proven difficult to establish y-axis -based standards within nuclear cardiology to assess learning. As such there is a paucity of data to verify current experiential training targets and only recently is data emerging that seeks to find CBME targets by which proficiency (y-axis units) can be evaluated. Initial reports from such CBME-oriented studies indicate that in current nuclear cardiology practice, the number of studies required to achieve competency is dependent upon the chosen measure of competency that is assessed (summed stress score versus % LV ischemia), the case mix, and the modality being learnt (PET versus SPECT). Recent findings have also suggested that prior levels of experiential training may be an underestimation of the number of supervised studies learners need to interpret before they achieve competency. Summary: Nuclear cardiology training has adopted the concept of CBME and is progressing toward a more modern approach to trainee assessment. This brief review provides the background, current requirements and insights into new developments in nuclear cardiology training. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
14. Evaluation of a community helpers' mental health and suicide awareness training programme for youth and young adults in Alberta, Canada.
- Author
-
Loitz, C.C., Arinde, F., Olaoye, F., Pilon, K., and Johansen, S.
- Subjects
- *
SUICIDE prevention , *HEALTH literacy , *MENTAL health , *SELF-efficacy , *DATA analysis , *QUALITATIVE research , *AFFINITY groups , *INTERVIEWING , *CONTENT analysis , *PROBLEM solving , *SURVEYS , *PRE-tests & post-tests , *INFORMATION needs , *ATTITUDES of medical personnel , *RESEARCH methodology , *FRIEDMAN test (Statistics) , *STATISTICS , *ABILITY , *COMMUNICATION , *BUSINESS networks , *HEALTH outcome assessment , *SOCIAL support , *LEARNING strategies , *COMMUNITY-based social services , *PATIENTS' attitudes , *SOCIAL stigma , *PATIENT aftercare , *TRAINING - Abstract
The Community Helpers Programme (CHP) is a peer-helping programme providing youth and young adults with tools to support their peers to problem solve and seek mental health and suicide prevention support. This study aims to evaluate the effectiveness of the provincial programme (primary outcomes = knowledge, self-efficacy; secondary outcome = awareness of stigma) and describe the experience of participants, coordinators, and others. The mixed methods evaluation included a longitudinal panel design outcome evaluation along with follow-up interviews. A series of three surveys collecting participant characteristics, knowledge, self-efficacy, and awareness of stigma at pre-training (T0), post-training (T1), and six-months follow-up (T2) were conducted. Mean group scores were calculated for completers (T0 and T1 completers and T0, T1, and T2 completers). Friedman tests were conducted to assess change over time and follow-up Wilcoxon Signed Rank tests determined the significance of changes in scores between each timepoint. Content analysis was conducted on qualitative data. Participants' knowledge of mental health, suicide, and available supports along with self-efficacy increased from T0 to T1, and declined at T2. Awareness of stigma was high at all timepoints. Themes from the qualitative analysis included skill and knowledge development facilitators (e.g., consideration of learner needs, passionate coordinators, engaged learning approaches), sustaining community helper connectedness (e.g., helpers' network, awareness of and communication with local resources), and role and impact of CHP (e.g., addressing stigma, success stories). This evaluation demonstrated that CHP was effective and offered feedback on experiences, including suggestions on CHP strengths and aspects to explore. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
15. Teaching cardiopulmonary resuscitation using virtual reality: A randomized study.
- Author
-
Alcázar Artero, P.M., Greif, R., Cerón Madrigal, J.J., Escribano, D., Pérez Rubio, M.T., Alcázar Artero, M.E., López Guardiola, P., Mendoza López, M., Melendreras Ruiz, R., and Pardo Ríos, M.
- Subjects
COMPUTER simulation ,CARDIOPULMONARY resuscitation ,RESEARCH ,TEACHING methods ,CONFIDENCE intervals ,VIRTUAL reality ,CROSS-sectional method ,GAMES ,COMPARATIVE studies ,LEARNING strategies ,RANDOMIZED controlled trials ,DESCRIPTIVE statistics ,STATISTICAL sampling ,EDUCATIONAL outcomes - Abstract
The main functions of healthcare professionals include training and health education. In this sense, we must be able to incorporate new technologies and serious game to the teaching cardiopulmonary resuscitation. a multicenter, comparative and cross-sectional study was carried out to assess the learning of resuscitation of a group that was trained with the use of serious gaming with virtual reality, as compared to a control group trained with conventional classroom teaching. the mean quality obtained in chest compressions for the virtual reality group was 86.1 % (SD 9.3), and 74.8 % (SD 9.5) for the control group [mean difference 11.3 % (95 % CI 6.6–16.0), p < 0.001]. Salivary Alpha-Amylase was 218.882 (SD 177.621) IU/L for the virtual reality group and 155.190 (SD 116.746) IU/L for the control group [mean difference 63.691 (95 % CI 122.998–4.385), p = 0.037]. using virtual reality and serious games can improve the quality parameters of chest compressions as compared to traditional training. • The European Resuscitation Council recommends training of the general population on basic life support. • The use of technology will help us to improve the training in cardiopulmonary resuscitation (CPR). • Serious games have been shown to allow students develop and apply their learning. • Healthcare professionals must be able to incorporate new technologies and be at the forefront of teaching innovation. • VR simulation has been proven to be an interesting training tool in cardiopulmonary resucitation. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
16. Perpetual or Subscription: Incumbent sales strategy with strategic consumers and social learning.
- Author
-
Wu, Cheng-Han, Chamnisampan, Netnapha, and Liao, Yan-Tong
- Subjects
SOCIAL learning ,CONSUMERS ,INCUMBENCY (Public officers) ,MARKETING software ,LEARNING strategies - Abstract
This study explores the impact of social learning on sales strategies for incumbent firms facing new entrants in the digital software market. Consumers rely on peer reviews to assess product quality, making it difficult to evaluate new products. The study considers two pricing strategies: perpetual and subscription. Results suggest that monopolizing the market is not always beneficial for the incumbent. The best strategy depends on the strength of social learning effects, with a subscription strategy being more effective when social learning effects are strong, and a perpetual strategy being more effective when they are weak. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
17. PhenoNet: A two-stage lightweight deep learning framework for real-time wheat phenophase classification.
- Author
-
Zhang, Ruinan, Jin, Shichao, Zhang, Yuanhao, Zang, Jingrong, Wang, Yu, Li, Qing, Sun, Zhuangzhuang, Wang, Xiao, Zhou, Qin, Cai, Jian, Xu, Shan, Su, Yanjun, Wu, Jin, and Jiang, Dong
- Subjects
- *
WHEAT , *GRAPHICS processing units , *DEEP learning , *IMAGE recognition (Computer vision) , *REMOTE sensing , *BACOPA monnieri , *LEARNING strategies - Abstract
The real-time monitoring of wheat phenology variations among different varieties and their adaptive responses to environmental conditions is essential for advancing breeding efforts and improving cultivation management. Many remote sensing efforts have been made to relieve the challenges of key phenophase detection. However, existing solutions are not accurate enough to discriminate adjacent phenophases with subtle organ changes, and they are not real-time, such as the vegetation index curve-based methods relying on entire growth stage data after the experiment was finished. Furthermore, it is key to improving the efficiency, scalability, and availability of phenological studies. This study proposes a two-stage deep learning framework called PhenoNet for the accurate, efficient, and real-time classification of key wheat phenophases. PhenoNet comprises a lightweight encoder module (PhenoViT) and a long short-term memory (LSTM) module. The performance of PhenoNet was assessed using a well-labeled, multi-variety, and large-volume dataset (WheatPheno). The results show that PhenoNet achieved an overall accuracy (OA) of 0.945, kappa coefficients (Kappa) of 0.928, and F1-score (F1) of 0.941. Additionally, the network parameters (Params), number of operations measured by multiply-adds (MAdds), and graphics processing unit memory required for classification (Memory) were 0.889 million (M), 0.093 Giga times (G), and 8.0 Megabytes (MB), respectively. PhenoNet outperformed eleven state-of-the-art deep learning networks, achieving an average improvement of 3.7% in OA, 5.1% in Kappa, and 4.1% in F1, while reducing average Params, MAdds, and Memory by 78.4%, 85.0%, and 75.1%, respectively. The feature visualization and ablation analysis explained that PhenoNet mainly benefited from using time-series information and lightweight modules. Furthermore, PhenoNet can be effectively transferred across years, achieving a high OA of 0.981 using a two-stage transfer learning strategy. Furthermore, an extensible web platform that integrates WheatPheno and PhenoNet and ensures that the work done in this study is accessible, interoperable, and reusable has been developed (https://phenonet.org/). [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
18. Mitigating Bias in Aesthetic Quality Control Tasks: An Adversarial Learning Approach.
- Author
-
Bernovschi, Denis, Giacomini, Alex, Rosati, Riccardo, and Romeo, Luca
- Subjects
AESTHETICS ,PRODUCT quality ,LEARNING strategies ,PREDICTION models ,QUALITY control - Abstract
Aesthetic quality control (AQC) is an essential step in smart factories to ensure that product quality meets the desired standards. This operation includes assessing factors such as color, texture, and shape. In the context of AQC, bias can arise when the criteria used to evaluate the aesthetics of a product are subjective and influenced by personal preferences. Bias can also occur due to the background or other objective factors like the geometry of the material. This work will focus on applying an adversarial learning strategy to a pre-trained DL architecture for improving the generalization performance of a predictive model tailored explicitly for solving AQC task classification. Experimental results on a benchmark AQC dataset highlighted the robustness of the proposed methodology for learning only relevant components related to quality classes rather than other confusing traits, enabling the mitigation of the identified bias. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
19. Riemannian SPD learning to represent and characterize fixational oculomotor Parkinsonian abnormalities.
- Author
-
Olmos, Juan, Manzanera, Antoine, and Martínez, Fabio
- Subjects
- *
PARKINSON'S disease , *RIEMANNIAN manifolds , *DEEP brain stimulation , *LEARNING strategies , *NEURODEGENERATION , *HUMAN abnormalities - Abstract
Parkinson's disease (PD) is the second most common neurodegenerative disorder, mainly characterized by motor alterations. Despite multiple efforts, there is no definitive biomarker to diagnose, quantify, and characterize the disease early. Recently, abnormal fixational oculomotor patterns have emerged as a promising disease biomarker with high sensitivity, even at early stages. Nonetheless, the complex patterns and potential correlations with the disease remain largely unexplored, among others, because of the limitations of standard setups that only analyze coarse measures and poorly exploit the associated PD alterations. This work introduces a new strategy to represent, analyze and characterize fixational patterns from non-invasive video analysis, adjusting a geometric learning strategy. A deep Riemannian framework is proposed to discover potential oculomotor patterns aimed at withstanding data scarcity and geometrically interpreting the latent space. A convolutional representation is first built, then aggregated onto a symmetric positive definite matrix (SPD). The latter encodes second-order statistics of deep convolutional features and feeds a non-linear hierarchical architecture that processes SPD data by maintaining them into their Riemannian manifold. The complete representation discriminates between Parkinson and Healthy (Control) fixational observations, even at PD stages 2.5 and 3. Besides, the proposed geometrical representation exhibit capabilities to statistically differentiate observations among Parkinson's stages. The developed tool demonstrates coherent results from explainability maps back-propagated from output probabilities. • A strategy that pools convolutional representations into Riemannian representations. • A digital biomarker to quantify Parkinson's Disease from ocular fixation videos. • An explainability strategy that highlights regions over eye video sequences. • The approach reveals remarkable performance on an extra dataset [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
20. Students experienced near peer-led simulation in physiotherapy education as valuable and engaging: a mixed methods study.
- Author
-
Granger, Catherine L, Smart, Aiden, Donald, Karen, McGinley, Jennifer L, Stander, Jessica, Kelly, David, Fini, Natalie, Whish-Wilson, Georgina A, and Parry, Selina M
- Subjects
TEACHER-student relationships ,AFFINITY groups ,SCHOOL environment ,FOCUS groups ,CONFIDENCE ,RESEARCH methodology ,HEALTH occupations students ,PHYSICAL therapy ,SIMULATION methods in education ,CURRICULUM ,EVIDENCE-based medicine ,EXPERIENCE ,PRE-tests & post-tests ,LEARNING strategies ,PHYSICAL therapy education ,STUDENTS ,QUESTIONNAIRES ,STUDENT attitudes - Abstract
What is the student experience of near peer-led simulation in physiotherapy education from the perspectives of students (near peer learners and near peer teachers)? What are their expectations, perceptions and engagement in this as a teaching and learning activity? Are there any short-term benefits? Convergent mixed-methods study. From a graduate entry Doctor of Physiotherapy course, 111 first-year and 20 second-year students participated. Near peer-led simulation was delivered within first-year cardiorespiratory, musculoskeletal and neurological physiotherapy curricula and as a precursor to second-year clinical placements. First-year students were near peer learners. Second-year students were near peer teachers and the simulated patients. Focus groups, pre/post-simulation questionnaires and direct observation. Data were triangulated and presented in overall themes. Five themes emerged: near peer-led simulation improved the students' confidence and the opportunity to make mistakes in a supportive and safe environment was valued; peer feedback was an integral part of the learning process that enriched the learning experience; the authenticity and realism created seriousness, promoted engagement and facilitated perceived knowledge transfer; there were benefits for learning for both peer learners and peer teachers; and the anticipation and emotional impact was evident. Near peer-led simulation was viewed by students as a valuable and engaging activity. Students perceived a broad range of benefits on their learning, especially from peer feedback (giving and receiving) on their performance, and had increased confidence following simulation. Peer-led simulation is an authentic and valuable component of entry-to-practice physiotherapy education. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
21. Analysis of the Impact Process Innovation and Collaboration on Competitiveness in Small and Medium-sized Enterprises: A Case Study in Colombia.
- Author
-
Henríquez-Calvo, Laura, Díaz-Martínez, Karina, Chang-Muñoz, Eduardo Antonio, Guarín-García, Andrés Felipe, Portnoy, Ivan, and Ramírez, Javier Alfonso
- Subjects
TECHNOLOGICAL innovations ,SMALL business ,LEARNING strategies ,RANK correlation (Statistics) ,ARTIFICIAL neural networks - Abstract
Our goal is to understand process innovation activities, constraints, and challenges. Collaboration and Research and Development (R&D) are vital for innovation, but many Small- and Medium-size Enterprises (SMEs) need to improve on these, necessitating focused efforts. Innovation is linked to growth, productivity, and capacity, demanding new offerings and process improvement. Surveying 56 Colombian exporting SMEs with a 19-question survey, we employed Artificial Neural Network (ANN) models and Spearman correlation for predicting Process Innovation. Scrutinizing requisite activities and their impact is essential for economic growth, allowing SMEs to enhance performance through market-driven innovation. Collaboration with research institutions and suppliers is pivotal, highlighting its importance for process innovation. Process-focused firms emphasize process innovation, while Colombian exporting SMEs prioritize it for competitiveness. Technological learning shapes strategies, and SMEs leverage market innovation. We identified links between R&D/innovation (R&D+I) and export behavior. Innovation aids internationalization despite Colombia's innovation gap. Enterprises invest in R&D+I and external collaboration, while SMEs focus on efficiency. Prospective research should explore interconnections in innovation facets, harnessing machine learning. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
22. Screen-time: ensuring excellence in online teaching.
- Author
-
Larsson, Martina, Shad, Nadia, Hulbert, Rebecca, Roueché, Alice, and Macaulay, Chloe
- Subjects
ONLINE education ,SCHOOL environment ,TEACHING methods ,CURRICULUM ,SCREEN time ,LEARNING strategies ,CLINICAL medicine ,EXCELLENCE ,MEDICAL education ,CLINICAL education ,TEACHER development ,EDUCATIONAL outcomes - Abstract
Online and virtual learning grew exponentially during the coronavirus pandemic in all areas, including medical education. It is now a well-established part of clinical teaching. This raises questions about which learning content should be delivered online; how it should be delivered and, crucially, how to engage learners in the online environment. We summarise a range of approaches and key considerations to enable appropriate clinical content to be delivered online and propose a number of teaching modalities for use within medical education. Preparation, including faculty training and development, is key to the ongoing effectiveness and success of online learning. We provide an online learning checklist and suggest ground rules to consider when approaching online teaching. Furthermore, we summarise a number of online platforms, applications and resources that aim to enhance learner engagement and encourage you to explore, innovate and reflect on your online teaching journey as an educator. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
23. An Interdisciplinary and Immersive Real-Time Learning Experience in Adolescent Nutrition Education Through Augmented Reality Integrated With Science, Technology, Engineering, and Mathematics.
- Author
-
Kalimuthu, Ilavarasi, Karpudewan, Mageswary, and Baharudin, Siti Mastura
- Subjects
- *
AUGMENTED reality , *NUTRITION education , *LEARNING strategies , *ENGINEERING , *MATHEMATICS , *INTERPROFESSIONAL relations , *TECHNOLOGY , *SCIENCE - Published
- 2023
- Full Text
- View/download PDF
24. Virtual reality for shoulder arthroplasty education.
- Author
-
Ahmed, Abdulaziz, Goel, Danny, and Lohre, Ryan
- Subjects
COMPUTER simulation ,HOSPITAL medical staff ,VIRTUAL reality ,INTERNSHIP programs ,LEARNING strategies ,TOTAL shoulder replacement - Abstract
Simulation provides an effective learning strategy to offset real-world training. Immersive virtual reality (IVR) is a form of simulation that incorporates unique software and hardware to create interactive, 3-dimensional (3D) virtual worlds to practice surgical procedures. In shoulder arthroplasty, IVR has shown consistent improvements in both technical skill and knowledge acquisition relative to traditional learning formats for trainees. The purpose of this review is to describe the current availability and application of IVR for shoulder arthroplasty education, and to describe future uses. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
25. Knowledge and practice of infection control during radiology procedures among radiography undergraduates in Sri Lanka.
- Author
-
Weerakoon, Bimali Sanjeevani and Chandrasiri, Nishadi Rangana
- Subjects
TEACHING methods ,HEALTH occupations students ,CROSS-sectional method ,ALLIED health education ,RADIOLOGIC technologists ,CROSS infection ,INFECTION control ,MEDICAL protocols ,UNDERGRADUATES ,LEARNING strategies ,QUESTIONNAIRES ,DESCRIPTIVE statistics ,DEMOGRAPHY - Abstract
Copyright of Journal of Medical Imaging & Radiation Sciences is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
- Published
- 2023
- Full Text
- View/download PDF
26. Physics-informed neural networks with parameter asymptotic strategy for learning singularly perturbed convection-dominated problem.
- Author
-
Cao, Fujun, Gao, Fei, Guo, Xiaobin, and Yuan, Dongfang
- Subjects
- *
SINGULAR perturbations , *TRANSPORT equation , *PARTIAL differential equations , *BOUNDARY value problems , *LEARNING strategies , *BOUNDARY layer (Aerodynamics) , *HEAT equation - Abstract
Physics-informed neural networks (PINN) have proven their effectiveness in solving partial differential equations (PDEs). Nevertheless, existing networks cannot model finely detailed signals and therefore fail to represent a signal's spatial and temporal derivatives. Traditional PINN are unable to approximate solutions of singularly perturbed boundary value problems that have solutions exhibiting sharp boundary layers and steep gradients with sufficient accuracy. A new asymptotic parameter PINN (PAPINN) is proposed to solve singular perturbation-dominated problems. This approach approximates the smooth solution by optimizing the neural network with large perturbation parameters, which are then used as initial values of the neural network with small perturbation parameters to approximate the singular solution. The method avoids the disadvantages of uncertainty of random parameters and manual setting of initial weights, and gives the network better initial weights. It offers a feasible deep learning approach for solving the singular perturbation problem without requiring a priori boundary layer information. By solving numerical examples of convection-diffusion equations originating from magnetic fluids, the accuracy and convergence efficiency of this method are compared with those of PINN and gPINN. The results show that the method can effectively approximate the large gradient solution of the convection-dominated diffusion equation with an accuracy of order 10 − 3 and has better convergence speed and stability than PINN and gPINN. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
27. Doubly robust logistic regression for image classification.
- Author
-
Song, Zihao, Wang, Lei, Xu, Xiangjian, and Zhao, Weihua
- Subjects
- *
IMAGE recognition (Computer vision) , *PRINCIPAL components analysis , *SUPERVISED learning , *CALCULUS of tensors , *LOGISTIC regression analysis , *LEARNING strategies - Abstract
• A doubly robust classification method is proposed by TRPCA and minimum distance criterion. • We apply the TRPCA of third-order tensor to the input by the low tubal rank with its tensor nuclear norm. • Our procedure is a data driven and adaptive supervised learning method. The growing prevalence of image data in engineering and medical applications motivates the need for classification performance that are robust against outliers. To facilitate efficient and data-driven classification and recovery method, in this paper, we propose a novel supervised learning strategy based on the robust principal component analysis for third-order tensor and minimum distance criterion L 2 E for logistic regression, which is named as doubly robust logistic regression. Our work applies the ADMM method to obtain updating algorithm, and its global convergence is established even though L 2 E loss function is non-convex. We also extend the estimation procedure to the case of incomplete observation in input matrix. The numerical experiments demonstrate the advantages of combining the logistic L 2 E with tensor robust principal component analysis which can not only increase the accuracy of classification but also improve the recovery accuracy of noisy image. Three real data analysis are further used to examine the outperformance of our proposed method over the stat-of-art. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
28. The Value of the Pediatric Urgent Care in Pediatric Resident Education.
- Author
-
Marsh, Melanie C., George, Adia, Daley, Melissa, Welter, Jacqueline, Berkemeyer, Andrea, Ndiaye, Mariane Cindy, and Reed, Suzanne
- Subjects
HOSPITAL emergency services ,HOSPITAL medical staff ,COURSE evaluation (Education) ,HEALTH services accessibility ,ATTITUDES of medical personnel ,RESEARCH methodology ,SELF-evaluation ,PEDIATRICS ,MANN Whitney U Test ,LEARNING strategies ,CONCEPTUAL structures ,T-test (Statistics) ,CLINICAL competence ,AUTONOMY (Psychology) ,DESCRIPTIVE statistics ,THEMATIC analysis ,NEEDS assessment ,DATA analysis software ,MEDICAL education ,EDUCATIONAL attainment - Abstract
OBJECTIVE: Pediatric urgent care (UC) is a growing field and may provide unique learning opportunities for pediatric residents. We aimed to assess whether a UC rotation could be feasible and meaningful and help fill educational gaps. METHODS: Within our current X + Y rotational model, we used Kern's 6-step approach for curriculum development to create a longitudinal UC educational experience for postgraduate year 2 (PGY2) pediatric residents. We assessed progress toward achieving our aim by using a mixed-methods approach matched to Kirkpatrick's levels of learning, including program annual evaluations, self-assessed UC competencies, and 360 milestone evaluations. RESULTS: A total of 14 PGY2s participated in our yearlong longitudinal rotation without duty hour violations or deviations from well child care. Thematic analysis revealed concepts of autonomy, procedural access, and intentionality of education. Residents showed statistical improvement in 4/10 milestones and 26/27 self-assessed performance items. Of 14 residents, 6 scored ≥4 on all milestones by the end of the year. CONCLUSIONS: Our curriculum demonstrates a valuable role for the pediatric UC in the procedural and clinical education of pediatric residents. Practical implications and assessment tools of such a curriculum may be valuable for others interested in integrating this learning experience into their current educational model. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
29. Multiple-instance ensemble for construction of deep heterogeneous committees for high-dimensional low-sample-size data.
- Author
-
Zhou, Qinghua, Wang, Shuihua, Zhu, Hengde, Zhang, Xin, and Zhang, Yudong
- Subjects
- *
DEEP learning , *CASCADE connections , *LEARNING strategies - Abstract
Deep ensemble learning, where we combine knowledge learned from multiple individual neural networks, has been widely adopted to improve the performance of neural networks in deep learning. This field can be encompassed by committee learning, which includes the construction of neural network cascades. This study focuses on the high-dimensional low-sample-size (HDLS) domain and introduces multiple instance ensemble (MIE) as a novel stacking method for ensembles and cascades. In this study, our proposed approach reformulates the ensemble learning process as a multiple-instance learning problem. We utilise the multiple-instance learning solution of pooling operations to associate feature representations of base neural networks into joint representations as a method of stacking. This study explores various attention mechanisms and proposes two novel committee learning strategies with MIE. In addition, we utilise the capability of MIE to generate pseudo-base neural networks to provide a proof-of-concept for a "growing" neural network cascade that is unbounded by the number of base neural networks. We have shown that our approach provides (1) a class of alternative ensemble methods that performs comparably with various stacking ensemble methods and (2) a novel method for the generation of high-performing "growing" cascades. The approach has also been verified across multiple HDLS datasets, achieving high performance for binary classification tasks in the low-sample size regime. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
30. Drone-based RGBT tiny person detection.
- Author
-
Zhang, Yan, Xu, Chang, Yang, Wen, He, Guangjun, Yu, Huai, Yu, Lei, and Xia, Gui-Song
- Subjects
- *
MINIATURE objects , *RESCUE work , *LEARNING strategies , *DRONE aircraft , *DETECTORS , *THERMOGRAPHY - Abstract
RGBT person detection benefits numerous vital applications like surveillance, search, and rescue. Meanwhile, drones can capture images holding broad perspectives and large searching regions per frame, which can notably improve the efficacy of large-scale search and rescue missions. In this work, we leverage the advantages of drone-based vision for RGBT person detection. The drone-based RGBT person detection task brings interesting challenges to existing cross-modality object detectors, e.g. , tiny sizes of objects, modality-space imbalance, and position shifts. Observing that there is a lack of data and customized detectors for drone-based RGBT person detection, we contribute two new datasets and design a novel detector. The data contribution is two-fold. For one, we construct the first large-scale drone-based RGBT person detection benchmark RGBTDronePerson, which contains 6,125 pairs of RGBT images and 70,880 instances. Images are captured in various scenes and under various illumination and weather conditions. For another, we annotate the VTUAV tracking dataset and obtain its object detection version, named VTUAV-det. To tackle the challenges raised by this task, we propose a Quality-aware RGBT Fusion Detector (QFDet). Firstly, we design a Quality-aware Learning Strategy (QLS) to provide sufficient supervision for tiny objects while focusing on high-quality samples, in which a Quality-Aware Factor (QAF) is designed to measure the quality. Moreover, a Quality-aware Cross-modality Enhancement module (QCE) is proposed to predict a QAF map for each modality, which not only indicates the reliability of each modality but also highlights regions where objects are more likely to appear. Our QFDet remarkably boosts the detection performance over tiny and small objects, surpassing the strong baseline on mAP 50 tiny by 6.57 points on RGBTDronePerson and mAP s by 3.80 points on VTUAV-det. The datasets, codes, and pre-trained models are available at https://nnnnerd.github.io/RGBTDronePerson/. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
31. An exploration of communication skills development for student diagnostic radiographers using simulation-based training with a standardised patient: UK-based focus-group study.
- Author
-
Adamson, H.K., Chaka, B., Hizzett, K., Williment, J., and Hargan, J.
- Subjects
ROLE playing ,OCCUPATIONAL roles ,FOCUS groups ,INDIVIDUAL development ,HEALTH occupations students ,RADIOLOGIC technologists ,SIMULATION methods in education ,ALLIED health education ,LEARNING strategies ,RESPONSIBILITY ,THEMATIC analysis ,PATIENT care ,EMOTIONS ,COMMUNICATION education ,VIDEO recording ,REFLECTION (Philosophy) - Abstract
Copyright of Journal of Medical Imaging & Radiation Sciences is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
- Published
- 2023
- Full Text
- View/download PDF
32. Management challenges in primary and secondary postpartum haemorrhage.
- Author
-
Taylor, Naomi and Brazel, Nicholas
- Subjects
MEDICAL quality control ,POSTPARTUM hemorrhage ,MEDICAL care ,LEARNING strategies ,QUALITY assurance ,WOMEN'S health ,COMORBIDITY - Abstract
In this review article we will cover the management of both primary and secondary postpartum haemorrhage. Detailed national guidance on the management of primary PPH has been in place since 1998. Despite this, multiple MBRRACE-UK reports have consistently found significant scope for improvement in the care delivered to women. The recurrent nature of the themes highlighted in the reports is equally sobering, which suggests a failure to learn from these tragic cases. The first part of this paper will provide practical steps that can be taken to embed the learning from successive MBRRACE-UK reports into our day-to-day clinical practice. The second part of this paper will provide an overview of the literature on secondary postpartum haemorrhage. Secondary PPH is associated with significant maternal morbidity. Despite this, there is a lack of randomised controlled trials to inform the management of these women, and the long-term sequalae associated with both the condition and its management is unknown. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
33. Development, Feasibility, and Initial Evaluation of an Active Learning Module for Teaching Pediatric ECG Interpretation and Entrustable Professional Activities to Clinical Medical StudentsTagedEnd.
- Author
-
Holland, Jennifer E., Rohwer, James K., O'Connor, Julia M., Wahlberg, Kramer J., DeSarno, Michael, Hopkins, William E., and Flyer, Jonathan N.
- Subjects
PROFESSIONAL practice ,PILOT projects ,NATIONAL competency-based educational tests ,ANALYSIS of variance ,MEDICAL students ,MANN Whitney U Test ,LEARNING strategies ,PEDIATRIC cardiology ,EDUCATIONAL tests & measurements ,ELECTROCARDIOGRAPHY ,EDUCATIONAL technology ,DESCRIPTIVE statistics ,RESEARCH funding ,CURRICULUM planning ,NEEDS assessment ,TRUST - Abstract
The article focuses on the development, feasibility, and initial evaluation of an Active Learning Module (PACE) designed for teaching pediatric ECG interpretation and Entrustable Professional Activities (EPAs) to clinical medical students. The innovative module, created by and for students, demonstrated feasibility, high satisfaction, increased ECG competency, and integration with general pediatrics EPAs and outlines the educational approach, participant details, and results.
- Published
- 2023
- Full Text
- View/download PDF
34. Multi-phase iterative learning control for high-order systems with arbitrary initial shifts.
- Author
-
Chen, Dongjie, Xu, Ying, Lu, Tiantian, and Li, Guojun
- Subjects
- *
ITERATIVE learning control , *LINEAR differential equations , *LEARNING strategies - Abstract
Aiming at the second-order tracking system with arbitrary initial shifts, this paper presents a multi-phase iterative learning control strategy. Firstly, utilizing the form of solution of the second-order non-homogeneous linear differential equation with constant coefficients and the initial shifts, we can select the appropriate control gain to ensure that the second-order systems are stable and reach the stable output after a fixed time. Secondly, on the premise that the second-order systems have reached the fixed output, two methods are proposed for rectifying the fixed shift, namely, shifts rectifying control and varied trajectory control. Theoretical analysis shows that the multi-stage iterative learning control strategy proposed in this paper can ensure that the second-order systems achieve complete tracking in the specified interval. Finally, the simulation examples affirm the validation of the designed algorithms. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
35. Discovering the ultralow thermal conductive A2B2O7-type high-entropy oxides through the hybrid knowledge-assisted data-driven machine learning.
- Author
-
Zhang, Ying, Ren, Ke, Wang, William Yi, Gao, Xingyu, Yuan, Ruihao, Wang, Jun, Wang, Yiguang, Song, Haifeng, Liang, Xiubing, and Li, Jinshan
- Subjects
THERMAL conductivity ,PHASE transitions ,MACHINE learning ,PHONON scattering ,OXIDES ,CHARGE transfer ,LEARNING strategies - Abstract
• The hybrid knowledge-assisted data-driven machine learning strategy is utilized to discover A 2 B 2 O 7 -type HEOs with low thermal conductivity through screening 17 rare-earth (RE = Sc, Y, la– Lu) solutes optimized A-site. • The best candidates are addressed and validated among the smart-designed 6188 (5RE 0.2) 2 Zr 2 O 7 HEOs by severe lattice distortion and local phase transformation. • Strong multi-phonon scattering and weak interatomic interactions should be utilized as key property parameters to screen the advanced multi-component HEOs with low thermal conductivity. Lattice engineering and distortion have been considered one kind of effective strategies for discovering advanced materials. The instinct chemical flexibility of high-entropy oxides (HEOs) motivates/accelerates to tailor the target properties through phase transformations and lattice distortion. Here, a hybrid knowledge-assisted data-driven machine learning (ML) strategy is utilized to discover the A 2 B 2 O 7 -type HEOs with low thermal conductivity (κ) through 17 rare-earth (RE = Sc, Y, La–Lu) solutes optimized A-site. A designing routine integrating the ML and high throughput first principles has been proposed to predict the key physical parameter (KPPs) correlated to the targeted κ of advanced HEOs. Among the smart-designed 6188 (5RE 0.2) 2 Zr 2 O 7 HEOs, the best candidates are addressed and validated by the principles of severe lattice distortion and local phase transformation, which effectively reduce κ by the strong multi-phonon scattering and weak interatomic interactions. Particularly, (Sc 0.2 Y 0.2 La 0.2 Ce 0.2 Pr 0.2) 2 Zr 2 O 7 with predicted κ below 1.59 Wm
−1 K−1 is selected to be verified, which matches well with the experimental κ = 1.69 Wm−1 K−1 at 300 K and could be further decreased to 0.14 Wm−1 K−1 at 1473 K. Moreover, the coupling effects of lattice vibrations and charges on heat transfer are revealed by the cross-validations of various models, indicating that the weak bonds with low electronegativity and few bonding charge density and the lattice distortion (r *) identified by cation radius ratio (r A / r B) should be the KPPs to decrease κ efficiently. This work supports an intelligent designing strategy with limited atomic and electronic KPPs to accelerate the development of advanced multi-component HEOs with properties/performance at multi-scales. [ABSTRACT FROM AUTHOR]- Published
- 2024
- Full Text
- View/download PDF
36. Materials genome strategy for metallic glasses.
- Author
-
Lu, Zhichao, Zhang, Yibo, Li, Wenyue, Wang, Jinyue, Liu, Xiongjun, Wu, Yuan, Wang, Hui, Ma, Dong, and Lu, Zhaoping
- Subjects
METALLIC glasses ,MACHINE learning ,LEARNING strategies - Abstract
• A timely overview of key advances in materials genome strategy for metallic glasses (MGs) was presented. • Current challenges of high-throughput techniques and data-driven machine learning strategies for MGs were discussed in depth. • Future opportunities and perspectives for materials genome strategy-assisted design of MGs were proposed and surmised. Metallic glasses (MGs) have attracted extensive attention in the past decades due to their unique chemical, physical and mechanical properties promising for a wide range of engineering applications. A thorough understanding of their structure-property relationships is the key to the development of novel MGs with desirable performance. New strategies, as proposed by Materials Genome Initiative (MGI), construct a new paradigm for high-throughput materials discovery and design, and are being increasingly implemented in the search of new MGs. While a few reports have summarized the application of high-throughput and/or machine learning techniques, a comprehensive assessment of materials genome strategies for developing MGs is still missing. Herein, this paper aims to present a timely overview of key advances in this fascinating subject, as well as current challenges and future opportunities. A holistic approach is used to cover the related topics, including high-throughput preparation and characterization of MGs, and data-driven machine learning strategies for accelerating the development of novel MGs. Finally, future research directions and perspectives for MGI-assisted design of MGs are also proposed and surmised. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
37. From degrade to upgrade: Learning a self-supervised degradation guided adaptive network for blind remote sensing image super-resolution.
- Author
-
Xiao, Yi, Yuan, Qiangqiang, Jiang, Kui, He, Jiang, Wang, Yuan, and Zhang, Liangpei
- Subjects
- *
SOURCE code , *LEARNING strategies , *HIGH resolution imaging , *REMOTE sensing - Abstract
Over the past few years, single image super-resolution (SR) has become a hotspot in the remote sensing area, and numerous methods have made remarkable progress in this fundamental task. However, they usually rely on the assumption that images suffer from a fixed known degradation process, e.g., bicubic downsampling. To save us from performance drop when real-world distribution deviates from the naive assumption, blind image super-resolution for multiple and unknown degradations has been explored. Nevertheless, the lack of a real-world dataset and the challenge of reasonable degradation estimation hinder us from moving forward. In this paper, a self-supervised degradation-guided adaptive network is proposed to mitigate the domain gap between simulation and reality. Firstly, the complicated degradations are characterized by robust representations in embedding space, which promote adaptability to the downstream SR network with degradation priors. Specifically, we incorporated contrastive learning to blind remote sensing image SR, which guides the reconstruction process by encouraging the positive representations (relevant information) while punishing the negatives. Besides, an effective dual-wise feature modulation network is proposed for feature adaptation. With the guide of degradation representations, we conduct modulation on feature and channel dimensions to transform the low-resolution features into the desired domain that is suitable for reconstructing high-resolution images. Extensive experiments on three mainstream datasets have demonstrated our superiority against state-of-the-art methods. Our source code can be found at https://github.com/XY-boy/DRSR • A simple and effective self-supervised degradation representation learning strategy is proposed. • The learned representations can promote cross-domain super-resolution generalization. • A dual-wise modulation network is established for effective feature adaption. • Our method achieves favorable performance on various remote sensing datasets. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
38. A new variable shape parameter strategy for RBF approximation using neural networks.
- Author
-
Nassajian Mojarrad, Fatemeh, Han Veiga, Maria, Hesthaven, Jan S., and Öffner, Philipp
- Subjects
- *
RADIAL basis functions , *MESHFREE methods , *LEARNING strategies , *INTERPOLATION - Abstract
The choice of the shape parameter highly effects the behaviour of radial basis function (RBF) approximations, as it needs to be selected to balance between the ill-conditioning of the interpolation matrix and high accuracy. In this paper, we demonstrate how to use neural networks to determine the shape parameters in RBFs. In particular, we construct a multilayer perceptron (MLP) trained using an unsupervised learning strategy, and use it to predict shape parameters for inverse multiquadric and Gaussian kernels. We test the neural network approach in RBF interpolation tasks and in a RBF-finite difference method in one and two-space dimensions, demonstrating promising results. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
39. An extended physics informed neural network for preliminary analysis of parametric optimal control problems.
- Author
-
Demo, Nicola, Strazzullo, Maria, and Rozza, Gianluigi
- Subjects
- *
PARTIAL differential equations , *STOKES equations , *SUPERVISED learning , *PHYSICS , *LEARNING strategies - Abstract
In this work we propose an application of physics informed supervised learning strategies to parametric partial differential equations. Indeed, even if the latter are indisputably useful in many research fields, they can be computationally expensive most of all in a real-time and many-query setting. Thus, our main goal is to provide a physics informed learning paradigm to simulate parametrized phenomena in a small amount of time. The physics information will be exploited in many ways, in the loss function (standard physics informed neural networks), as an augmented input (extra feature employment) and as a guideline to build an effective structure for the neural network (physics informed architecture). These three aspects, combined together, will lead to a faster training phase and to a more accurate parametric prediction. The methodology has been tested for several equations and also in an optimal control framework. • Adaptation of PINNs to parametric problems in real-time and many-query scenarios. • Employment of an additional PINN-based strategy to reduce the cost of the training. • Application to the optimal control framework for Poisson and Stokes equations. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
40. Mutation Management for Evolutionary Small-Moves Approach in Pickup and Delivery Problem.
- Author
-
Baturina, Xenia, Shalamov, Viacheslav, Muravyov, Sergey, and Filchenkov, Andrey
- Subjects
MACHINE learning ,REINFORCEMENT learning ,LEARNING strategies ,TRANSPORTATION industry - Abstract
This paper focuses on the Pickup and Delivery Problem in the transportation and logistics industry. The study utilizes evolutionary programming methods and small-moves mutation management to develop algorithms for optimizing vehicle routes. The research investigates the effectiveness of various mutations and strategies by comparing them to existing solutions. During the study, existing mutations and strategies were analyzed and new strategies and mutations were developed. A comprehensive comparison of these strategies and mutations was conducted. By incorporating various reinforcement learning algorithms as strategies, an average reduction in route length by 81% was achieved, surpassing the results of previous studies, which exceeded the results of previous studies by more than 7%. Code is available at https://github.com/xeniabaturina/pdp_python. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
41. Systematic Review of Easy-to-Learn Behavioral Interventions for Dietary Changes Among Young Adults.
- Author
-
Moore, Dustin M., Madrid, Isabella, and Lindsay, Karen L.
- Subjects
- *
PREVENTION of chronic diseases , *FOOD habits , *TEACHING methods , *SYSTEMATIC reviews , *LEARNING strategies , *HUMAN services programs , *ELIGIBILITY (Social aspects) , *BEHAVIOR modification - Abstract
Improving the diet quality of young adults may support chronic disease prevention. The approaches used and efficacy of promoting small dietary behavior changes through easy-to-learn (ETL) interventions (requiring no more than 1 hour to teach the behavior) among young adults have not yet been systematically reviewed. Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, 2 independent electronic searches across 6 databases were conducted to identify any articles describing ETL interventions among young adults (aged 18–35 years) and reporting dietary intake outcomes. Among 9,538 articles identified, 9 studies met eligibility criteria. Five studies reported significant improvement in the selected dietary outcome. Of these, 3 studies used an implementation intentions approach, in which participants were given or asked to write out a simple dietary behavior directive and carry it on their person. Less than half of included studies were rated as positive for overall quality. The available evidence suggests that ETL interventions targeting the dietary behaviors of young adults may be effective in improving dietary intake. Limitations of included studies were lack of follow-up after the intervention period and low generalizability. Further dietary intervention studies targeting young adults should systematically evaluate the efficacy of ETL intervention approaches among diverse samples. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
42. BCE-Net: Reliable building footprints change extraction based on historical map and up-to-date images using contrastive learning.
- Author
-
Liao, Cheng, Hu, Han, Yuan, Xuekun, Li, Haifeng, Liu, Chao, Liu, Chunyang, Fu, Gui, Ding, Yulin, and Zhu, Qing
- Subjects
- *
CONVOLUTIONAL neural networks , *HISTORICAL maps , *FOOTPRINTS , *HISTORIC buildings , *LEARNING strategies - Abstract
Automatic and periodic recompiling of building databases with up-to-date high-resolution images has become a critical requirement for rapidly developing urban environments. However, the architecture of most existing approaches for change extraction attempts to learn features related to changes but ignores objectives related to buildings. This inevitably leads to the generation of significant pseudo-changes, due to factors such as seasonal changes in images and the inclination of building façades. To alleviate the above-mentioned problems, we developed a contrastive learning approach by validating historical building footprints against single up-to-date remotely sensed images. This contrastive learning strategy allowed us to inject the semantics of buildings into a pipeline for the detection of changes, which is achieved by increasing the distinguishability of features of buildings from those of non-buildings. In addition, to reduce the effects of inconsistencies between historical building polygons and buildings in up-to-date images, we employed a deformable convolutional neural network to learn offsets intuitively. In summary, we formulated a multi-branch building extraction method that identifies newly constructed and removed buildings, respectively. To validate our method, we conducted comparative experiments using the public Wuhan University building change detection dataset and a more practical dataset named SI-BU that we established. Our method achieved F1 scores of 93.99% and 70.74% on the above datasets, respectively. Moreover, when the data of the public dataset were divided in the same manner as in previous related studies, our method achieved an F1 score of 94.63%, which surpasses that of the state-of-the-art method. Code and datasets are available at https://vrlab.org.cn/~hanhu/projects/bcenet. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
43. A perspective on the synergistic potential of artificial intelligence and product-based learning strategies in biobased materials education.
- Author
-
Marquez, Ronald, Barrios, Nelson, Vera, Ramon E., Mendez, Maria E., Tolosa, Laura, Zambrano, Franklin, and Li, Yali
- Subjects
ARTIFICIAL intelligence ,LANGUAGE models ,LEARNING strategies ,CHEMICAL engineering education ,ENGINEERING education ,DEEP learning ,ELECTRONIC publications - Abstract
The integration of product-based learning strategies in Materials in Chemical Engineering education is crucial for students to gain the skills and competencies required to thrive in the emerging circular bioeconomy. Traditional materials engineering education has often relied on a transmission teaching approach, in which students are expected to passively receive information from instructors. However, this approach has shown to be inadequate under the current circumstances, in which information is readily available and innovative tools such as artificial intelligence and virtual reality environments are becoming widespread (e.g., metaverse). Instead, we consider that a critical goal of education should be to develop aptitudes and abilities that enable students to generate solutions and products that address societal demands. In this work, we propose innovative strategies, such as product-based learning methods and GPT (Generative Pre-trained Transformer) artificial intelligence text generation models, to modify the focus of a Materials in Chemical Engineering course from non-sustainable materials to sustainable ones, aiming to address the critical challenges of our society. This approach aims to achieve two objectives: first to enable students to actively engage with raw materials and solve real-world challenges, and second, to foster creativity and entrepreneurship skills by providing them with the necessary tools to conduct brainstorming sessions and develop procedures following scientific methods. The incorporation of circular bioeconomy concepts, such as renewable resources, waste reduction, and resource efficiency into the curriculum provides a framework for students to understand the environmental, social, and economic implications in Chemical Engineering. It also allows them to make informed decisions within the circular bioeconomy framework, benefiting society by promoting the development and adoption of sustainable technologies and practices. [Display omitted] • Integrating sustainability into Chemical Engineering education is a significant challenge. • Alternatives to improve teaching in Chemical Engineering shifting to a cognitive, constructivist, product-based approach. • Integrating new technologies such as digital platforms and AI platforms fosters learning and collaboration in experiential courses. • GPT models and AI image generators can help students interact and visualize to acquire knowledge in biobased materials courses. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
44. Dynamic event-triggered controller design for nonlinear systems: Reinforcement learning strategy.
- Author
-
Wang, Zichen, Wang, Xin, and Pang, Ning
- Subjects
- *
REINFORCEMENT learning , *NONLINEAR systems , *LEARNING strategies , *BACKSTEPPING control method , *LYAPUNOV stability , *STABILITY theory - Abstract
The current investigation aims at the optimal control problem for discrete-time nonstrict-feedback nonlinear systems by invoking the reinforcement learning-based backstepping technique and neural networks. The dynamic-event-triggered control strategy introduced in this paper can alleviate the communication frequency between the actuator and controller. Based on the reinforcement learning strategy, actor–critic neural networks are employed to implement the n-order backstepping framework. Then, a neural network weight-updated algorithm is developed to minimize the computational burden and avoid the local optimal problem. Furthermore, a novel dynamic-event-triggered strategy is introduced, which can remarkably outperform the previously studied static-event-triggered strategy. Moreover, combined with the Lyapunov stability theory, all signals in the closed-loop system are strictly proven to be semiglobal uniformly ultimately bounded. Finally, the practicality of the offered control algorithms is further elucidated by the numerical simulation examples. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
45. Dual-stream correlation exploration for face anti-Spoofing.
- Author
-
Liu, Yongluo, Wu, Lifang, Li, Zun, and Wang, Zhuming
- Subjects
- *
HUMAN facial recognition software , *LEARNING strategies - Abstract
• The different correlations are beneficial to the face anti-spoofing (FAS). • The metric correlation between liveness features improves generalization of FAS. • Liveness and content features learning fosters the discrimination of FAS. Face anti-spoofing (FAS) is an important technology to ensure the security of face recognition system. Previous methods generally focus on the representation of the spoof patterns. However, the hidden correlations between living and spoofing faces are ignored, making the generation and discrimination of face anti-spoofing less effective. In this paper, we propose a novel Dual-Stream Correlation Exploration method (DSCE) to simultaneously model the correlation between content and liveness features for the performance improvement. Specifically, DSCE devises two novel modules: the spoof cue generation module and the source face reconstruction module, at two streams respectively. The former one introduces pseudo negative feature to extend the diversity of attack types, and adopts a metric learning strategy to learn the correlation among liveness features. The latter one integrates liveness and content features to explores the potential relationship between the both features through source face reconstruction. Last, DSCE adaptively combines spoof cues and reconstructed faces to comprehensively consider the importance of different correlations for face anti-spoofing. Comprehensive experimental results on both intra-dataset testing and cross-dataset testing clearly demonstrate the high discrimination and generalization of DSCE. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
46. Educators' experiences of teaching and learning in radiography during COVID-19: A single-site South African study.
- Author
-
Mulla, Fathima, Lewis, Shantel, Britton, Shonelle, and Hayre, Christopher M.
- Subjects
TEACHING methods ,COVID-19 ,WORK ,COLLEGE teacher attitudes ,RADIOGRAPHY ,LEARNING strategies ,EXPERIENTIAL learning ,CLINICAL education - Published
- 2023
- Full Text
- View/download PDF
47. Three-step learning strategy for designing 15Cr ferritic steels with enhanced strength and plasticity at elevated temperature.
- Author
-
Hu, Xiaobing, Chen, Yiming, Lu, Jianlin, Xing, Chen, Zhao, Jiajun, Wu, Qingfeng, Jia, Yuhao, Li, Junjie, Wang, Zhijun, and Wang, Jincheng
- Subjects
FERRITIC steel ,LEARNING strategies ,HIGH temperatures ,LAVES phases (Metallurgy) ,TENSILE strength - Abstract
● Development of a three-step learning strategy for alloy design with high efficiency, transparency and interpretation. ● Realization of the trade-off between strength and plasticity at elevated temperature. ● Identification and validation of key factors influencing the content and distribution of Laves phase in ferrite steels. ● Extraction of composition-structure-property linkage by adaptive learning and local-interpolation learning. ● Development of new 15Cr ferrite steels that have low cost and excellent mechanical properties at 650 °C. 15Cr ferrite steels are urgently required in advanced Ultra-supercritical power plants but meet design challenges in balancing excellent strength and plasticity at high temperatures. We developed a three-step learning strategy based on mutually driven machine learning and purposeful experiments to complete this multi-objective task. Compared with traditional adaptive learning and local-interpolation learning, this step-by-step modular manner provides good transparency and interpretability of the information flow, which is ensured by identifying essential factors from an exquisitely prepared composition-microstructure dataset, and learning valuable knowledge about the composition-property relationship. The requirement of only two groups of experiments indicates the low cost and high efficiency of the strategy. Performing the strategy, we found that Ti is another key element affecting the Laves phase besides Mo and W, and their effects on ultimate tensile strength (UTS) and elongation were also uncovered. Importantly, several low-cost steels free of Co were successfully designed, and the best steel exhibited 156%, 31%, and 62% higher UTS and elongation at 650 °C than the typical 9Cr, 15Cr, and 20Cr steels, respectively. Based on the advantages and success of the strategy in terms of alloy improvement, we believe the strategy suits other multi-objective design tasks in more materials systems. [Display omitted] [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
48. Adaptive parameter learning and neural network control for uncertain permanent magnet linear synchronous motors.
- Author
-
Su, Xinyi, Yang, Xiaofeng, and Xu, Yunlang
- Subjects
- *
SYNCHRONOUS electric motors , *PERMANENT magnets , *INTELLIGENT control systems , *ROBUST control , *LEARNING strategies - Abstract
• Focusing on the intelligent control of a permanent magnet linear synchronous motor (PMLSM) with unknown parameters, nonlinearities, and disturbances. • Constructing an augmented neural network (NN) with a friction model and a force ripple model. • Presenting a new estimation-error-based learning law with suppressed chattering in learned parameters. • Proposing an adaptive robust control method composed of the new learning strategy and an adaptive sliding mode controller. This work aims to achieve accurate parameter estimation and intelligent control of a permanent magnet linear synchronous motor (PMLSM) with unknown parameters, nonlinearities, and disturbances. To address it, we propose a novel adaptive control method composed of a new estimation error-based learning strategy and a neural network (NN)-based adaptive sliding mode controller. An augmented NN with a friction model and a force ripple model is constructed to handle the uncertainties in PMLSM. The proposed learning law that contains leakage terms driven by estimation errors calculates the unknown parameter and NN's weights online. Especially the gain of the discontinuous term in the learning law is adjusted by the presented update law to reduce the chattering of learned parameters. The controller handles the residual error and external disturbance. Different from the existing methods, the proposed one needs no boundary information of uncertainties in both the controller and parameter-learning strategy. The proposed method is finite-time semi-global uniformly and ultimately bounded (FTSGUUB), which is analyzed by designing a Lyapunov function. Finally, numerical simulations are carried out to validate the parameter learning and control accuracy of the proposed method. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
49. Multi-Contrast MRI Acceleration with K-Space Progressive Learning and Image-Space Self-to-Peer Aggregation.
- Author
-
Xing, X., Yu, L., Zhu, L., Xing, L., and Liu, L.
- Subjects
- *
BRAIN tumors , *IMAGE sensors , *LEARNING strategies , *MAGNETIC resonance imaging , *RADIATION - Abstract
Multi-contrast MRI plays a vital role in accurate target delineation and treatment response evaluation during radiotherapy. This work aims to optimize multi-contrast MRI by integrating features across different contrasts and utilizing an easily obtained modality to guide high-quality reconstruction of target modalities from noisy and sparse samples. We propose a novel multi-contrast MRI reconstruction framework, which cascades a k-space learning network and an image space aggregation network to exploit features in both sensor and image domains. To deal with the imbalanced magnitudes of different frequency components in k-space, we propose a Low-to-High Frequency Progressive (LHFP) learning strategy. The network first recovers the low-frequency component and then emphasizes the high-frequency learning by reducing the loss weight of the low-frequency component. The low-high frequency boundary is adaptively estimated by a mask predictor module, which is optimized together with the k-space learning network. The network-learned k-space data are reconstructed to images and fed into the image domain network for further enhancement. To capture global dependencies in the image domain, we propose a transformer-based Self-to-Peer Aggregation (SPA) method to integrate features from multi-contrast MRI and improve the joint reconstruction accuracy. We evaluate our method on a multi-contrast MRI dataset, which contains both T1-weighted (T1WI) and T2-weighted (T2WI) MRI of brain tumor patients. We conduct experiments on two settings: 1) T1WI-guided 4-fold acceleration of the T2WI MRI, with only the reconstruction accuracy of T2WI evaluated; 2) T1WI-guided 4-fold acceleration of the T2WI MRI with low-field noise, where both reconstruction accuracies of T1WI and T2WI are evaluated. Our method leads to a peak-signal-to-noise (PSNR) improvement of 9.69 dB, 16.94 dB, and 11.16 dB for the T2WI 4X acceleration, T1WI low-field denoising, and low-field T2WI 4X acceleration, respectively. Moreover, our method significantly outperforms existing multi-contrast MRI reconstruction methods (K-DCNN, MINet, MTrans, MCCA). Through dual domain learning of k-space and image features, high-quality multi-contrast MRI can be obtained from noisy and sparse samples to support radiation treatment planning and follow-up. By exploiting global feature dependencies across different contrasts, improved robustness to noise and under-sampling artifacts can be achieved. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
50. Explicit Aspect Annotation via Transfer and Active Learning.
- Author
-
Maroua, Boudabous and Anna, Pappa
- Subjects
ACTIVE learning ,TRANSFER of training ,ANNOTATIONS ,LEARNING strategies ,ELECTRONIC equipment ,DEEP learning - Abstract
We present a semi-supervised annotation process for identifying and labelling explicit aspects of an initially unlabelled corpus. Firstly, we employ cross-domain learning to pre-annotate the initial data, deliberately excluding domain-related input features to ensure effective learning transfer. Then, we apply an active learning strategy to enhance the pre-annotation performance and enrich the learning data. We adjust the strategy to sequence labeling and address class imbalance. We evaluate this process using two unlabelled datasets in French, consisting of user opinions on beauty products and electronic devices, respectively. The results show an improved F1-score achieved by increasing and correcting 30% of the training dataset. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.