Optimal Training Methods Research Articles

Training Leaders in Trauma Resuscitation: Teacher and Learner Perspectives on Ideal Methods.

IntroductionEffective leadership improves patient care during medical and trauma resuscitations. While dedicated training programs can improve leadership in trauma resuscitation, we have a limited understanding of the optimal training methods. Our objective was to explore learners’ and teachers’ perceptions of effective methods of leadership training for trauma resuscitation.MethodsWe performed a qualitative exploration of learner and teacher perceptions of leadership training methods using a modified grounded theory approach. We interviewed 28 participants, including attending physicians, residents, fellows, and nurses who regularly participated in trauma team activations. We then analyzed transcripts in an iterative manner to form codes, identify themes, and explore relationships between themes.ResultsBased on interviewees’ perceptions, we identified seven methods used to train leadership in trauma resuscitation: reflection; feedback; hands-on learning; role modeling; simulation; group reflection; and didactic. We also identified three major themes in perceived best practices in training leaders in trauma resuscitation: formal vs informal curriculum; training techniques for novice vs more senior learner; and interprofessional training. Participants felt that informal training methods were the most important part of training, and that a significant part of a training program for leaders in trauma resuscitation should use informal methods. Learners who were earlier in their training preferred more supervision and guidance, while learners who were more advanced in their training preferred a greater degree of autonomy. Finally, participants believed leadership training for trauma resuscitation should be multidisciplinary and interprofessional.ConclusionWe identified several important themes for training leaders in trauma resuscitation, including using a variety of different training methods, adapting the methods used based on the learner’s level of training, and incorporating opportunities for multidisciplinary and interprofessional training. More research is needed to determine the optimal balance of informal and formal training, how to standardize and increase consistency in informal training, and the optimal way to incorporate multidisciplinary and interprofessional learning into a leadership in trauma resuscitation training program.

PFedSim: An Efficient Federated Control Method for Clustered Training

To further promote the implementation and application of artificial intelligence technology under data silos, federated ecology has defined a set of standardized and systematic solutions from upstream data to downstream applications from a systematic perspective. As the core of the federated ecology, federated control can transform the abstract tasks of federated management into concrete execution rules. Clustered training is a common cooperation rule for the personalized federated training task of multi-party cooperation. However, it is difficult to generalize in large-scale cooperation scenarios because of increased data transmission pressure and server storage burden. Therefore, this paper designs a personalized federated control method based on similarity measures(pFedSim) so that the server can accurately distribute the cluster model to clients, thereby reducing the transmission cost. Compared with the existing clustered training method IFCA, pFedSim transfers the selection rights of cluster models from the client to the server. Model selection preference, accurate distribution of cluster models. Experiments show that in the personalized training task with s clusters, the method can obtain the same model level with 1/s data transmission. It is better than the current optimal clustering training method Macro-Acc increased by 2.25%.

Explainable Artificial Intelligence for Human-Machine Interaction in Brain Tumor Localization.

Primary malignancies in adult brains are globally fatal. Computer vision, especially recent developments in artificial intelligence (AI), have created opportunities to automatically characterize and diagnose tumor lesions in the brain. AI approaches have provided scores of unprecedented accuracy in different image analysis tasks, including differentiating tumor-containing brains from healthy brains. AI models, however, perform as a black box, concealing the rational interpretations that are an essential step towards translating AI imaging tools into clinical routine. An explainable AI approach aims to visualize the high-level features of trained models or integrate into the training process. This study aims to evaluate the performance of selected deep-learning algorithms on localizing tumor lesions and distinguishing the lesion from healthy regions in magnetic resonance imaging contrasts. Despite a significant correlation between classification and lesion localization accuracy (R = 0.46, p = 0.005), the known AI algorithms, examined in this study, classify some tumor brains based on other non-relevant features. The results suggest that explainable AI approaches can develop an intuition for model interpretability and may play an important role in the performance evaluation of deep learning models. Developing explainable AI approaches will be an essential tool to improve human–machine interactions and assist in the selection of optimal training methods.

369 Point-of-Care Ultrasound Escape Rooms: Innovative Game Based Training of Emergency Medicine Residents

Point-of-care ultrasound (POCUS) is an integral component of emergency medicine (EM) residency education, however optimal training methods are unclear. We identified a training gap in standard case based simulation: difficulty with assessment of learner image acquisition, interpretation, and integration of multiple POCUS applications as applied to the evaluation of a broad set of differential diagnoses for a single chief complaint. Game based learning has been shown to have a positive impact on a learner-centered education process.

Preliminary Assessment of Muscle Activity and Muscle Characteristics during Training with Powered Robotic Exoskeleton: A Repeated-Measures Study.

A variety of robotic exoskeletons have been developed for patients with spinal cord injuries. However, the optimal training method and period for using a robotic exoskeleton have been uncertain until now. The purpose of this study is to determine the minimum training period for using a robotic exoskeleton with minimal muscle activity by investigating the changes in muscle activity and muscle characteristics of healthy adults during robotic exoskeleton training. A total of 16 people participated in the study. The robotic exoskeleton locomotion training consisted of three 50-min sessions a week for 7 weeks. The assessment consisted of sitting, standing, wide standing, sit-to-stand, and stand-to-sit where muscle activity and muscle characteristics were measured during each motion. All measurements were performed in the first session and every five sessions. Participants showed decreased muscle activity up to 10 sessions of training in the standing position, and 15 sessions in sit-to-stand and stand-to-sit motions. Upper extremity muscles showed decreased muscle activity, tone, stiffness, and logarithmic decrement up to the 15th session. The study results show that at least 15 training sessions are required to use the robotic exoskeleton with minimal load on the musculoskeletal system, and longer training is required for patients with spinal cord injury.

Strength Training for Long-Distance Triathletes: Theory to Practice

ABSTRACTConcurrent training, commonly acknowledged as a training method where strength and endurance training are completed complementary to each other, is a strategy often implemented in endurance cyclists' and runners' programs to improve physiological determinants of success such as exercise economy. Although concurrent training methods and strategies have been examined to a large extent in endurance cyclists and runners, literature examining optimal concurrent training methods to improve physiological variables in long-distance triathletes is minimal, leaving optimal programming relatively unknown. This practical applications paper identifies and outlines current concepts and considerations regarding concurrent training for long-distance triathletes including mechanisms contributing to improved performance, muscle and movement patterns used, exercise selection, load, velocity of movement, scheduling, frequency, and duration of training. Common misconceptions related to concurrent training are also identified and practical considerations for the application of concurrent training for coaches, athletes, and other professionals to improve all 3 disciplines of triathlon are discussed.

Procedural training models among emergency medicine residency programs

ObjectiveOptimal training methods remain controversial for rarely performed emergency procedures. Previous research has failed to demonstrate the superiority or inferiority of live anesthetized animal models (LAA) as compared to other modalities. Most of the data on LAA use comes from military contexts; less information is available for civilian emergency medicine (EM) training. We sought to characterize the prevalence of LAA use among civilian EM residency programs and reasons for its use or discontinuation.MethodsSurvey study of program directors of EM residency programs accredited by the Accreditation Council for Graduate Medical Education. A 16-item questionnaire was electronically delivered to program directors, including program region, current and historical use of LAA, and attitudes regarding the optimal procedural training modalities.ResultsOf 179 survey recipients, 83 completed the survey (46.4%). Twelve programs (14.3%) currently use LAA, and 17 programs (20.5%) report previous LAA use. Reasons for discontinuing LAA use included ethical concerns, financial and logistical limitations, political pressures, and feeling that there were superior or equivalent alternative models available. Programs that currently use LAA were more likely to rank LAA as being the most preferable training modality while programs that do not currently use LAA were more likely to rank human cadavers as the most preferable modality.ConclusionDespite a lack of data showing educational outcomes-driven differences between LAA and alternative training models, LAA use is declining among civilian EM residencies. Despite this, disagreement exists among programs that do and do not use LAA regarding the most optimal procedural training.

The Development and Evaluation of a Training Monitoring System for Amateur Rugby Union

A training monitoring system (TMS) should be both attainable and scientifically grounded; however, the optimal method of monitoring training is not yet fully understood. The purpose of this study was to develop and evaluate an online TMS for amateur rugby union. The experimental approach to the problem consisted of five phases: (1) establishing the current training and training load (TL) monitoring practices of amateur rugby union teams, (2) designing and developing the TMS, (3) recruiting teams and subsequently introducing the TMS, (4) supporting the strength and conditioning (S&C) coaches using the TMS, and (5) evaluating the TMS. The findings of this study support the use of an online TMS as a useful and effective method of facilitating training prescription and design in an effort to reduce injury risk and enhance performance. The main barriers impeding player compliance are the lack of feedback on their data and evidence of its use in training design, coaching, and prescription. The effectiveness of the system is dependent on the extent to which the associated challenges are mitigated to ensure quality and consistent data. However, this study offers a method of monitoring training that can be effective while also establishing pitfalls to avoid for both practitioners and researchers alike.

An Optimized Training Method for GAN-Based Hyperspectral Image Classification

This letter explores how to apply a generative adversarial network (GAN) to the classification of hyperspectral images (HSIs) to obtain a smooth training process and better classification results. To this end, the ideas of the progressive growing GAN (PG-GAN) and Wasserstein generative adversarial network gradient penalty (WGAN-GP) are combined to propose a new method for HSI classification. PG-GAN is optimized from the training process of generating adversarial networks. It gradually increases the depth of the network and the size of the input image, making the training smoother. WGAN-GP is optimized in terms of the loss function. The gradient penalty method is used to solve the problems of vanishing gradient and exploding gradient, making the training more stable. Based on the combination of the two methods, a classifier is added to the model so that it can complete the HSI classification task. The proposed method is evaluated over two publicly available hyperspectral data sets, the Indian Pines and University of Pavia data sets. The results show that the proposed method can achieve good training results with only a small amount of labeled training data.

Overground Locomotor Training In Parkinson's Disease: Effects On Walking Economy And Performance Fatigability

Walking economy (WE) is a measure of metabolic energy expenditure relative to walking speed, and, when elevated, may contribute to decreased capacity and performance relative to sustained walking in people with Parkinson’s Disease (PD). Coupled with performance fatigability (PF), these factors may increase disability in this population. Although sustained walking underlies many daily activities and impacts physical activity for many people with PD, responses to walking-specific interventions to develop optimal training methods have not been fully investigated in this population. PURPOSE: Determine changes in WE, PF, and physiologic response during sustained walking following a task-specific, performance-based overground locomotor training program (OLT) in people with mild/moderate PD. METHODS: 7 males and 2 females (68.9 ± 7.1 years old, H&Y scores 1-3) completed a 12-week program of 24 OLT sessions lasting 45 - 60 minutes each. Subjects were coached through multiplanar movement drills based on components of the gait cycle emphasizing power, stability and stepping under aerobically challenging conditions (ClinicalTrials.gov. - NCT03864393). Walking performance was measured during an overground 10-minute walk test (10MWT) by total distance (TD) and PF (Δ speed/total distance). During the final 5 minutes of the 10MWT, average heart rate (HR), oxygen consumption (V̇O2), and carbon dioxide production (V̇CO2) were recorded using a portable metabolic system. These values were divided by the average speed in the final 5 minutes of the 10MWT to assess WE and physiologic response. RESULTS: There were moderate to large, significant effects for TD (925.77 ± 175.67 vs 1018.37 ± 133.83, p=0.019, d=0.59), PFS (1.11 ± 0.19 vs 0.98 ± 0.13, p=0.013, d=0.79) and HR/speed (76.46 ± 7.69 vs 71.49 ± 6.71 bpm/m/s, p=0.05, d=0.69). There were small, non-significant effects for V̇O2/speed (12.14 ± 1.99 vs 11.47 ± 2.89 mL/min/kg/m/s, d=0.34) and V̇CO2/speed (790.56 ± 196.8 vs 778.93 ± 197.94 mL/min/m/s, d=0.06). CONCLUSIONS: OLT improved WE and PFS during sustained walking. Despite a moderate effect, HR changes in response to OLT are difficult to interpret without additional measures of cardiorespiratory function. Larger and more mechanistic studies can provide further insight into this potential adaptation.

UAV-YOLO: Small Object Detection on Unmanned Aerial Vehicle Perspective.

Object detection, as a fundamental task in computer vision, has been developed enormously, but is still challenging work, especially for Unmanned Aerial Vehicle (UAV) perspective due to small scale of the target. In this study, the authors develop a special detection method for small objects in UAV perspective. Based on YOLOv3, the Resblock in darknet is first optimized by concatenating two ResNet units that have the same width and height. Then, the entire darknet structure is improved by increasing convolution operation at an early layer to enrich spatial information. Both these two optimizations can enlarge the receptive filed. Furthermore, UAV-viewed dataset is collected to UAV perspective or small object detection. An optimized training method is also proposed based on collected UAV-viewed dataset. The experimental results on public dataset and our collected UAV-viewed dataset show distinct performance improvement on small object detection with keeping the same level performance on normal dataset, which means our proposed method adapts to different kinds of conditions.

STRUCTURE OPTIMIZATION OF DEEP BELIEF NETS IN THE APPLICATIONS OF IMAGE RECOGNITION.

Deep belief network (DBN) has become one of the most important models in deep learning, however, the un-optimized structure leads to wasting too much training resources. To solve this problem and to investigate the connection of depth and accuracy of DBN, an optimization training method that consists of two steps is proposed. Firstly, by using mathematical and biological tools, the significance of supervised training is analyzed, and a theorem, that is on reconstruction error and network energy, is proved. Secondly, based on conclusions of step one, this paper proposes to optimize the structure of DBN (especially hidden layer numbers). Thirdly, this method is applied in two image recognition experiments, and results show increased computing efficiency and accuracies in both tasks.

Determining the Optimal Training Method for Older Adults Using GPS Technology

Abstract Date Presented 04/05/19 This study explored the optimal training method for using GPS. Sixty older adults with no GPS experience were assigned to a video tutorial group, one-to-one training, or control. Results indicate that the one-to-one training significantly improved performance compared to the other conditions. Results are discussed in terms of being significant for the promotion of healthy aging, OT, and the importance of using hands-on training when teaching older adults to use technology. Primary Author and Speaker: Michael Coleman Additional Authors and Speakers: Anne Dickerson

The primary accreditation. The ways of the problems solving related to the preparation of graduates of medical universities

The article is devoted to the study problems associated with the education of graduates of medical universities. The aim of the study is to explore possible ways to optimize the training of students for the practical exam in the simulation center, taking into account their educational needs A questionnaire was developed to assess students ‘attitude to choosing the optimal method of training, including questions about the socio-demographic characteristics of the respondents, the most difficult practical exam stations, the choice of the optimal method of training and the level of students’ involvement into the process of self education for the exam during the 6th year. Statistical data processing was performed using the SPSS 20.0 software package (SPSS Inc., Chicago, IL, USA). The study included 100 students randomly selected from among those enrolled in the 6th year of the medical faculty of the NWSMU. I.I. Mechnikov. Data analysis showed that the most difficult stations are “Providing emergency medical care” and “Emergency states”. The “training with a teacher in a simulation center” had the highest rating from all proposed education methods. Neither the socio-demographic characteristics nor the form of funding for education had an effect on this choice. Despite of fears related to the complexity of these stations, the number of people trying to master them was 40%. Conclusions. 1. The most difficult for students are the skills of providing emergency medical care. This choice was not influenced by gender, age or experience in the health care system. 2. It is necessary to make changes in the curricula of medical students in accordance with the requirements of the professional standard of the district physician, whose work functions include the provision of emergency medical care. 3. The involvement of teachers into the process of preparing students for emergency and urgent care should begin at the 5th year and be systematic. 4. It is necessary to motivate students to systematic self-study of materials on the methodology for providing emergency and urgent care presented on the website of the Methodological Center for Accreditation.

Development of convolutional neural network and its application in image classification: a survey

In recent years, convolutional neural networks (CNNs) have been widely used in various computer visual recognition tasks and have achieved good results compared with traditional methods. Image classification is one of the basic and important tasks of visual recognition, and the CNN architecture applied to other visual recognition tasks (such as object detection, object localization, and semantic segmentation) is generally derived from the network architecture in image classification. We first summarize the development history of CNNs and then analyze the architecture of various deep CNNs in image classification. Furthermore, not only the innovation of the network architecture is beneficial to the results of image classification, but also the improvement of the network optimization method or training method has improved the result of image classification. We also analyze each of these methods’ effect. The experimental results of various methods are compared. Finally, the development of future CNNs is prospected.

Improved Real-Time Optical Diagnosis of Colorectal Polyps Following a Comprehensive Training Program

The optimal training method for endoscopic characterization of colorectal polyps using narrow-band imaging is uncertain, and sessile serrated lesions (SSLs) optical diagnosis data are lacking. We aimed to evaluate a comprehensive training program for real-time optical diagnosis of colorectal polyps, including SSLs. We performed a single-institution prospective study of 15 endoscopists trained with the Workgroup Serrated Polyps and Polyposis classification system. After the first phase of in vivo optical diagnosis, their performances were evaluated. After re-education for insufficient competency, they began the second phase. The learning curves and performance on 2 preservation and incorporation of valuable endoscopic innovations benchmarks were assessed. A total of 7294 polyps, including 486 SSLs, were diagnosed in real-time. The overall accuracy improved from 73.5% in the first phase to 77.1% in the second. The accuracy with high confidence was 79.4% and 85.1% in the first and second phases, respectively. In the first and second phases, the negative predictive values for diminutive neoplastic polyps were 82.1% and 92.5%, respectively, and concordances of the surveillance intervals were 80.7% and 89.7%, respectively. Eight endoscopists achieved the preservation and incorporation of valuable endoscopic innovations benchmarks after the second phase compared with none after the first. In contrast, the high confidence rate decreased from 74.6% to 70.2% as training progressed. A comprehensive training program for real-time optical diagnosis significantly improved performance and reduced individual variability in less-experienced endoscopists. ClinicalTrials.gov no: NCT02516748.

Attentional bias modification reduces clinical depression and enhances attention toward happiness

Difficulty in clinical antidepressant treatment leads to the pursuit of alternative treatments, such as cognitive-behavior therapy (CBT). CBT combined with regular antidepressants have indicated an optimal therapeutic effect in clinic. Attentional bias is important in the occurrence and remission of depression, however, few studies have explored the effect of attentional bias modification (ABM) on depression, and inconsistent results have been obtained due to the heterogeneity in the targeted populations, training tasks, strategies, and materials. Hence, the current study aimed to explore the therapeutic effect of ABM on depression in clinical depression.Study I was designed to explore the optimal training methods regarding task (dot-probe vs. cue-target), material (faces vs. self-referent words), and strategy (mixed ABM toward positive and away from negative stimuli vs. positive ABM toward positive stimuli) in unselected undergraduates once daily for 10 days (N = 309). Study II was carried out to observe the effect of 10 days ABM toward positive and away from negative faces (based on Study I) on clinical depression (N = 32). Depression level was assessed via a self-reporting questionnaire and a structured interview, while attentional bias was tested by cue-target task and attention to positive and negative inventory (APNI).In unselected undergraduates (Study I), two strategies significantly reduced the self-reporting depression scores: mixed ABM toward positive stimuli and away from negative stimuli with emotional faces, and positive ABM toward positive materials only with self-referent words. In patients with major depressive disorder (MDD) (Study II), the mixed ABM with emotional faces resulted in enhanced attentional bias toward happy materials in the cue-target task and APNI, which predicted a delayed depression reduction in clinical depression at the one-month follow-up investigation.Our finding confirms the literature and broadens the knowledge with the evidence of the optimal therapeutic effect of ABM combined with regular antidepressants in clinical depression. The findings that a quick enhancement in positive attentional bias, predicting a later therapeutic effect on clinical depression reduction, indicate a potential mechanism that could underlie the therapeutic process of ABM in depression. The findings that two training strategies are effective in depression reduction suggest that different strategies should be utilized to treat different types of depression. This study offers a potential way to cure depression and could be further practiced in clinic.

Incorporating perceptual decision-making training into high-intensity interval training for Australian football umpires

ABSTRACTExisting methods for developing decision–making skill for Australian football umpires separate the physical and perceptual aspects of their performance. This study aimed to determine the efficacy of incorporating video-based decision-making training during high-intensity interval training sessions, specific for Australian football umpires. 20 amateur Australian football umpires volunteered to participate in a randomised control trial. Participants completed an 8-week training intervention in a conditioning only (CON; n=7), combined video-based training and conditioning (COM; n=7), or separated conditioning and video-based training (SEP; n=6) group. Preliminary and post-testing involved a Yo-Yo Intermittent Recovery Test (Yo-YoIR1), and 10x300m run test with an Australian football specific video-based decision-making task. Overall, changes in decision-making accuracy following the intervention were unclear between groups. SEP was possibly beneficial compared to COM in Yo-YoIR1 performance, whereas CON was likely beneficial compared to COM in 10x300m sprint performance. There was no additional benefit to completing video-based training, whether combined with, or separate to physical training, suggesting that this was not an optimal training method. For video-based training to be an effective decision-making tool, detailed feedback should be incorporated into training. It is recommended that longer conditioning and video-based training interventions be implemented to determine training effectiveness.

Determining optimal artificial neural network training method in predicting the performance and emission parameters of a biodiesel-fueled diesel generator

Artificial neural network (ANN) methods were employed and suggested in modeling the emissions and performance of a diesel generator fueled with waste cooking oil derived biodiesel during steady-state operation. These papers are generally built on determining optimal network structure, but the modelling accuracy of an ANN is also highly dependent on employed training method. In modeling, operating conditions and fuel blend ratio were used as the inputs while the performance and emission parameters were the outputs. The modeling results obtained by conventional ANNs that were trained by back propagation (BP) learning algorithm, radial basis function (RBF), and extreme learning machine (ELM) were compared with experimental results and each other. The accuracy of the estimations by ELM was above 95% for all the output parameters except for specific fuel consumption and thermal efficiency. Moreover, ELM performed better than BP and RBF with lower mean relative error (MRE) in case where the emissions were estimated. The ELM provided correlation coefficients of 0.987, 0.950 and 0.996 for unburned hydrocarbons (HCs), nitrogen oxides (NOx) and smoke opacity (SO), respectively, while for BP, they were 0.973, 0.818, 0.993, and for RBF, 0.975, 0.640 and 0.981. The most suitable training function for each emission and performance parameters of diesel generator was determined based on obtained accuracies.

An Optimal Method of Training the Specific Lower Limb Muscle Group Using an Exoskeletal Robot.

This paper suggests a novel method of strengthening specific muscle groups in the lower limb during a functional movement. When the foot of an user wearing an exoskeletal robot follows a given path, the contribution of each muscle group to generate the motion changes along the path of the trajectory. The efficiency of muscle training, which is defined as the ratio of the work of a specific muscle group to that of all groups, can be maximized by changing the training load along the path. Based on a musculoskeletal model, the contribution of each muscle group along the path can be calculated as a function of its position. When a specific muscle group is chosen for exercise or rehabilitation, the efficiency of training can be maximized by setting high load where its contribution is high and low load where its contribution is low. By doing so, the user can exercise longer with the same amount of energy consumption. The EXOWheel that features a lower limb exoskeleton is employed to verify the method and the hamstring muscle group is selected as the specific muscle group. Three healthy subjects participate in the experiment, and electromyogram sensors are employed to monitor the muscle power. The results indicate that the efficiency of the hamstring muscle group for a given circular foot path under the optimal training load is 46.2% compared with 32.5% with a constant load and it means the 42% higher efficiency of the specific muscle group training.