Training Approach Research Articles

Contribution of Lateral Bound and Triceps Dips Exercises to the Repulsion Results of Men in North Padang Lawas Regency

The proficiency in the sport of shot put is contingent upon the harmonious integration of strength, power, and technique. Notwithstanding its significance, athletes at Pembina Prestasi club in North Padang Lawas have demonstrated suboptimal outcomes, necessitating a targeted intervention to enhance their performance. The objective of study was to investigate the impact of lateral bound and tricep dip exercises on the performance of male athletes at Pembina Prestasi Club in the discipline of shot put. A pre-test and post-test experimental study was conducted on six male shot put athletes. The intervention comprised lateral bound and triceps dip exercises, conducted thrice weekly for 18 sessions over a six-week period. The efficacy of intervention was evaluated by measuring the participants' shot put performance before and after the intervention. The data were analyzed using descriptive statistics, normality tests, and paired sample t-tests. The results demonstrated a statistically significant enhancement in shot put performance subsequent to the intervention. The mean throwing distance increased from 6.40 meters to 7.74 meters, accompanied by a reduction in performance variability. The frequency distribution of performance categories exhibited a positive shift, with 66.33% of participants transitioning to the "Good" category following the intervention. A statistically significant difference was observed between the pre-test and post-test scores (p = 0.025). The implementation of lateral bound and tricep dip exercises effectively enhanced shot put performance among the studied athletes. The intervention not only improved throwing distances but also led to more consistent performances. Further research should explore these exercises with larger sample sizes and over extended periods. The integration of advanced technologies for more precise measurements and investigation of personalized training approaches based on individual athlete characteristics are recommended. Additionally, studies examining the long-term effects of these interventions and their applicability across different athlete demographics could further contribute to optimizing shot put.

USV formation navigation decision-making through hybrid deep reinforcement learning using self-attention mechanism

To address the challenging of balancing Unmanned Surface Vessel (USV) autonomous collision avoidance and formation maintenance in uncertain environments, a formation construction and navigation decision-making strategy based on Hybrid Deep Reinforcement Learning (HDRL) is proposed in this study. The novelty of this study is that: (1) A HDRL training approach is proposed, incorporating diverse DRL for virtual leader and followers, thereby significantly enhancing the decision-making adaptability of USVs formation. (2) The multi-head attention mechanism of decentralized Critic strategy is used to enhance the attentional focus of the HDRL algorithm towards different agents, thereby effectively improving convergence speed. (3) The method employs a meticulously designed hybrid reward function and incorporates the Optimal Reciprocal Collision Avoidance (ORCA) for speed selection, thereby providing optimal speed recommendations based on the current situation. It is worth emphasizing that the method exhibits exceptional performance in terms of success rate, navigation time, average reward value, and other relevant indicators within the simulation. Finally, the method is validated through the utilization of real-time navigation data in the Panama Canal, thereby substantiating the potential engineering applicability.

Case Method Teaching, Strategic Storytelling, and Social Change: A Pilot Evaluation of an Online Course to Address Colourism in Malaysia

Colourism is the discriminatory practice of favoring lighter skin over darker skin. It perpetuates social disparities and drives skin-lightening products (SLP) use globally, including in Malaysia. This study presents the results of an innovative 3 week online training course designed to equip health professionals and educators who work with youth in Malaysia with the knowledge and skills to combat colourism and the use of dangerous SLPs through strategic storytelling. We recruited a diverse group of learners ( N = 19) and assessed their knowledge and attitudes of colourism and use of SLP before and after the course. We also assessed student engagement and collected qualitative acceptability data. The course incorporated case method teaching, interactive case delivery, strategic storytelling methods, and team collaboration elements through digital platforms to facilitate course engagement and learning. Our findings indicate significant improvements in learners’ knowledge and concern regarding skin-shade discrimination and SLP usage pre- to post-course. Learners reported their intention to use strategic storytelling techniques for public health advocacy around colourism and use of SLPs. Qualitative learner feedback highlighted the positive aspects of the course, including its realism and the importance of collaborative learning with professionals from diverse fields to combat prevailing sociocultural issues. While this study offers valuable insights into the effectiveness of this innovative training approach, it also identifies areas of future improvements as suggested by learners, such as the need to increase content diversity, enhance communication channels, and extend time for discussion. This course provides a promising model for addressing colourism-related issues in Malaysia.

Personalized Deep Learning Model for Clinical Target Volume on Daily Cone Beam Computed Tomography in Breast Cancer Patients

PurposeHerein, we developed a deep learning algorithm to improve the segmentation of the clinical target volume (CTV) on daily cone-beam computed tomography (CBCT) scans in breast cancer radiotherapy. By leveraging the Intentional Deep Overfit Learning (IDOL) framework, we aimed to enhance personalized image-guided radiotherapy (IGRT) based on patient-specific learning. MethodsWe utilized 240 CBCT scans from 100 breast cancer patients and employed a two-stage training approach. The first stage involved training a novel general deep learning model (Swin UNETR, UNET, and SegResNET) on 90 patients. The second stage utilized intentional overfitting on the remaining 10 patients for patient-specific CBCT outputs. Quantitative evaluation was conducted using the Dice Similarity Coefficient (DSC), Hausdorff Distance (HD), mean surface distance (MSD), and independent samples t-test with expert contours on CBCT scans from the 1st to 15th fractions. ResultsIDOL integration significantly improved CTV segmentation, particularly with the Swin UNETR model (p-values <0.05). Using patient-specific data, IDOL enhanced the DSC, HD, and MSD metrics. The average DSC for the 15th fraction improved from 0.9611 to 0.9819, the average HD decreased from 4.0118 mm to 1.3935 mm, and the average MSD decreased from 0.8723 to 0.4603. Incorporating CBCT scans from the initial treatments and 1st to 3rd fractions further improved results, with an average DSC of 0.9850, an average HD of 1.2707 mm, and an average MSD of 0.4076 for the 15th fraction, closely aligned with physician-drawn contours. ConclusionCompared with a general model, our patient-specific deep learning-based training algorithm significantly improved CTV segmentation accuracy of CBCT scans in patients with breast cancer. This approach, coupled with continuous deep learning training using daily CBCT scans, demonstrated enhanced CTV delineation accuracy and efficiency. Future studies should explore the adaptability of the IDOL framework to diverse deep learning models, datasets, and cancer sites.

The effects of circuit training versus high-intensity interval training on the endurance of volleyball athletes: a randomized controlled trial

Despite its intermittent nature, volleyball places significance on a high aerobic capacity, particularly evident in multiset games that demand sustained high-performance levels. Various training approaches exist to enhance the endurance of volleyball athletes. Thus, the fundamental aim of this research is to examine the contrasting effects of utilizing high-intensity interval training (HIIT) and circuit training methods to enhance volleyball athletes' endurance. The study used an Experimental group that partook in a HIIT training regime, and a Contrast group that undertook a Circuit training program. Thirty male volleyball players aged between 17 and 22 years (M=19.14; SD±1.61) were purposefully selected for the study and split into Contrast and Experimental groups of 15 each. At the beginning and end of the intervention programs both groups underwent physiological assessments for Maximum Oxygen Consumption (VO2max), Heart Rate Recovery (HRR), Peak Inspiratory Flow (PIF), Peak Expiratory Flow (PEF), and Force Vital Capacity (FVC). As result a meaningful Time x Group interaction for the VO2max, HRR, PIF, PEF and FVC was observed. This represents a significant improvement in the treatment group (p &lt; 0.001). No material change was observed in the comparison group. Findings revealed that the HIIT training approach outperformed the circuit training method in enhancing volleyball athletes' endurance. Consequently, it is should be beneficial for volleyball players to incorporate HIIT into their standard training regimens. Keywords: VO2max; physiology; sport; exercise; aerobic capacity.

An Original Remote Digital Serious Game for Neonatal Resuscitation Training: New Opportunities from COVID-19 Era.

Background: The social restrictions imposed by the COVID-19 pandemic have disrupted traditional teaching methods and encouraged the development of innovative and safer approaches based on distance learning. Among these novel techniques, digital game-based learning (DGBL) is a method that facilitates learning through the efficient use of interactive software tailored to the user. Methods: In this work, we investigated the effectiveness of the DGBL methodology for remote training using a game-based digital learning software designed about remote neonatal resuscitation. The DGBL approach was validated in 52 anesthesiologist trainees and compared to a homogenous retrospective control group of pediatric trainees with the same prior knowledge, who followed an in-person training course using the digital serious game. Scores obtained during each game session are recorded and used to assess progress in knowledge of the flowchart, decision time, timing of assisted ventilation, and ability to check equipment. Results: The results confirmed the effectiveness of the remote training mode for each of the analyzed features, whereas no statistically significant advantages of using a supervised DGBL were found. Conclusion: In conclusion, the DGBL remote training approach is a valuable tool that can provide users with an interactive, effective, and enjoyable learning experience. Future developments will concern the implementation of multiplayer versions to stimulate interaction between users for the development of inter-professional and teamwork skills.

Antonym and Oppositeness: A Cognitive Training Approach of Thinking in English Writing in the AI Era

Antonym and Oppositeness: A Cognitive Training Approach of Thinking in English Writing in the AI Era

Perspectives of Nursing Home Staff: Application of Dementia Training Approaches.

Non-pharmacological strategies are prioritized to manage dementia-related symptoms in nursing homes (NHs). A multiple-case study design, embedded within a pragmatic trial, examined NH staff perspectives of applying a team-based (TB) or problem-based dementia training program to resident care. A purposive sample of staff was recruited from 23 NHs to participate in one-on-one interviews, which were analyzed using a rapid qualitative approach. Both approaches yielded staff who were able to apply their training to resident care. Staff described similarities in communication strategies, family interactions, recognizing sources of behaviors, providing comfort, and ensuring resident safety. In addition, staff demonstrated increased self-efficacy when caring for residents. Differences emerged for team collaboration, engaging residents, and managing behaviors. Among TB staff, training impacted how staff cared for residents and increased teamwork. Leaders may want to consider the benefits of each approach as they deliberate on which dementia care training to provide to their staff.

Facilitating Diversity and Accessibility in Microscopy through Educational Initiatives and Streamlined Training Approaches

Facilitating Diversity and Accessibility in Microscopy through Educational Initiatives and Streamlined Training Approaches

Privacy-preserving edge federated learning for intelligent mobile-health systems

Machine Learning (ML) algorithms are generally designed for scenarios in which all data is stored in one data center, where the training is performed. However, in many applications, e.g., in the healthcare domain, the training data is distributed among several entities, e.g., different hospitals or patients’ mobile devices/sensors. At the same time, transferring the data to a central location for learning is certainly not an option, due to privacy concerns and legal issues, and in certain cases, because of the communication and computation overheads. Federated Learning (FL) is the state-of-the-art collaborative ML approach for training an ML model across multiple parties holding local data samples, without sharing them. However, enabling learning from distributed data over such edge Internet of Things (IoT) systems (e.g., mobile-health and wearable technologies, involving sensitive personal/medical data) in a privacy-preserving fashion presents a major challenge mainly due to their stringent resource constraints, i.e., limited computing capacity, communication bandwidth, memory storage, and battery lifetime. In this paper, we propose a privacy-preserving edge FL framework for resource-constrained mobile-health and wearable technologies over the IoT infrastructure. We evaluate our proposed framework extensively and provide the implementation of our technique on Amazon’s AWS cloud platform based on the seizure detection application in epilepsy monitoring using wearable technologies.

Reconfigurable inverse design of phononic crystal sensor based on a deep learning accelerated evolution strategy

Phononic crystals offer valuable sensing capabilities due to their high sensitivity to changes in sound velocity of analytes. In this work, a reconfigurable inverse design approach of phononic crystal sensors is achieved using a deep learning accelerated evolution strategy. The training data is acquired through finite element method (FEM). Two multilayer perceptrons (MLP) are constructed and trained to predict the center frequency and bandwidth of a passband in the dispersion relation. Utilizing a two-step training approach enables rapid accuracy enhancements and swift reconstruction of network targets from NaCl to KCl solutions. The trained networks accelerate the optimization process, yielding a phononic crystal with good detection ability. Compared to FEM, invoking the trained networks can reduce optimization time by a factor of 105. The optimized and initial structures are both fabricated and experimentally tested. The robust linear relation between the resonant peak and the solution concentration indicates significant sensing value. The experimental results are in good agreement with the FEM simulations. In the detection of NaCl solution, the optimized phononic crystal sensor has a sensitivity increase of 375% and a Q-factor of 999%. Our research demonstrates that the data-driven deep learning network is a very powerful tool for the design and optimization of phononic crystal devices.

Control-free and efficient integrated photonic neural networks via hardware-aware training and pruning

Integrated photonic neural networks (PNNs) are at the forefront of AI computing, leveraging light’s unique properties, such as large bandwidth, low latency, and potentially low power consumption. Nevertheless, the integrated optical components are inherently sensitive to external disturbances, thermal interference, and various device imperfections, which detrimentally affect computing accuracy and reliability. Conventional solutions use complicated control methods to stabilize optical devices and chip, which result in high hardware complexity and are impractical for large-scale PNNs. To address this, we propose a training approach to enable control-free, accurate, and energy-efficient photonic computing without adding hardware complexity. The core idea is to train the parameters of a physical neural network towards its noise-robust and energy-efficient region. Our method is validated on different integrated PNN architectures and is applicable to solve various device imperfections in thermally tuned PNNs and PNNs based on phase change materials. A notable 4-bit improvement is achieved in micro-ring resonator-based PNNs without needing complex device control or power-hungry temperature stabilization circuits. Additionally, our approach reduces the energy consumption by tenfold. This advancement represents a significant step towards the practical, energy-efficient, and noise-resilient implementation of large-scale integrated PNNs.

Developing a tablet-based brain-computer interface and robotic prototype for upper limb rehabilitation.

The current study explores the integration of a motor imagery (MI)-based BCI system with robotic rehabilitation designed for upper limb function recovery in stroke patients. We developed a tablet deployable BCI control of the virtual iTbot for ease of use. Twelve right-handed healthy adults participated in this study, which involved a novel BCI training approach incorporating tactile vibration stimulation during MI tasks. The experiment utilized EEG signals captured via a gel-free cap, processed through various stages including signal verification, training, and testing. The training involved MI tasks with concurrent vibrotactile stimulation, utilizing common spatial pattern (CSP) training and linear discriminant analysis (LDA) for signal classification. The testing stage introduced a real-time feedback system and a virtual game environment where participants controlled a virtual iTbot robot. Results showed varying accuracies in motor intention detection across participants, with an average true positive rate of 63.33% in classifying MI signals. The study highlights the potential of MI-based BCI in robotic rehabilitation, particularly in terms of engagement and personalization. The findings underscore the feasibility of BCI technology in rehabilitation and its potential use for stroke survivors with upper limb dysfunctions.

Sensorimotor Challenges in Minimally Invasive Surgery: A Theoretically-Oriented Review.

This review surveys the literature on sensorimotor challenges impacting performance in laparoscopic minimally invasive surgery (MIS). Despite its well-known benefits for patients, achieving proficiency in MIS can be challenging for surgeons due to many factors including altered visual perspectives and fulcrum effects in instrument handling. Research on these and other sensorimotor challenges has been hindered by imprecise terminology and the lack of a unified theoretical framework to guide research questions in the field. We conducted a systematic survey of the MIS literature, focusing on studies investigating sensorimotor challenges affecting laparoscopic performance. To provide a common foundation for cross-study comparisons, we propose a standardized taxonomy that distinguishes between different experimental paradigms used in the literature. We then show how the computational motor learning perspective provides a unifying theoretical framework for the field that can facilitate progress and motivate future research along clearer, hypothesis-driven lines. The survey identified diverse sensorimotor perturbations in MIS, which can be effectively categorized according to our proposed taxonomy. Studies investigating monitor-, camera-, and tool-based perturbations were systematically analyzed, elucidating their impact on surgical performance. We also show how the computational motor learning perspective provides deeper insights and potential strategies to mitigate challenges. Sensorimotor challenges significantly impact MIS, necessitating a systematic, empirically informed approach. Our proposed taxonomy and theoretical framework shed light on the complexities involved, paving the way for more structured research and targeted training approaches to enhance surgical proficiency. Understanding the sensorimotor challenges inherent to MIS can guide the design of improved training curricula and inform the configuration of setups in the operating room to enhance surgeon performance and ultimately patient outcomes. This review offers key insights for surgeons, educators, and researchers in surgical performance and technology development.

Data-driven hierarchical learning approach for multi-point servo control of Pan–Tilt–Zoom cameras

Pan–Tilt–Zoom (PTZ) cameras, with their significant features of free rotation and zoom, are widely used in areas such as border security, ecological conservation, emergency management, and the military. PTZ cameras can achieve automatic monitoring of a selected area through multiple servo operations, known as multi-point servo control. However, due to the deficiencies in the servo control Software Development Kit (SDK), hardware wear, and interference from complex external environments, the multi-point servo control process generates significant errors. This paper proposes a precise multi-point servo control framework based on Deep Reinforcement Learning (DRL) to address this issue. The complexity of real-world environments necessitates a reward function design that fully considers various factors, for which we propose the directional gravity reward function. Due to the instability during the training process, prolonged trial-and-error interactions between the agent and the equipment can cause irreversible damage to the devices. This framework employs a phased training approach, where the agent learns sequentially from offline, off-policy, and on-policy data, reducing direct interaction with the equipment while enhancing the agent’s overall performance. Additionally, real-time and accurate device status can be obtained by performing feature matching on images from adjacent time frames, which is crucial for the system’s operation. Evaluation results indicate that our proposed precise multi-point servo control framework significantly outperforms other methods in 4-point servo control tasks in both virtual and real-world scenarios. Additionally, the operational process fully considers safety issues.

Analysis of the effectiveness and user experience of employing virtual reality to enhance the efficacy of occupational safety and health learning for electrical workers and graduate students

IntroductionThe integration of engineering approaches in education and training is pivotal for reducing workplace incidents. Effective safety education increases workers' awareness of potential risks and fosters a robust Occupational Safety and Health (OSH) culture. Virtual reality (VR) offers immersive experiences that enhance the efficacy of safety training. MethodThis study evaluated VR's effectiveness through two experiments that demonstrated improved learning capacities. The first study employed quantitative methods and quasi-experiments with electrical sector technical support professionals. The second study used a qualitative approach with scenario case studies involving graduate students. ResultsThe quantitative study revealed significant improvements in OSH understanding among electrical workers, highlighting VR-based training's superiority over traditional methods. The qualitative study found positive outcomes in VR usability and user experience among graduate students, affirming VR's effectiveness in OSH education. ConclusionVR has proven to be an effective and efficient training tool for both graduate students and experienced workers. It significantly advances skills, knowledge, and proficiency in electrical engineering by providing realistic, immersive, and tailored learning experiences. As VR technology continues to evolve, its role in shaping the future of electrical technical education and training appears increasingly promising.

Video Gaming in Older People: What Are the Implications for Cognitive Functions?

Mild cognitive impairment impacts a sizable segment of the older population, and often evolves into dementia within a few years. At this stage, subjects may benefit from non-pharmacological therapies that can delay or stop the progression of the mild cognitive impairment into dementia and are crucial for improvement in the subject's quality of life, while also being easily accessible and safe for use. Many research studies have shown that a variety of exercises, including cognitive training, have the potential to enhance or optimize cognitive function and general well-being. Recently, many authors have suggested video games as a promising approach for cognitive training and neurorehabilitation in older people, thanks to their increasing motivation and training effects through immersion in stimulating environments. Under this premise, our narrative review's objective is to discuss and summarize the body of existing material on the role of video games in improving cognitive performance, daily life activities, and depression symptoms in older individuals with different levels of cognitive decline. From the papers reviewed, it emerged that older subjects trained with video games showed a significant improvement in cognitive functions, sleep quality, and psychiatric symptoms, positioning video games as an intriguing and useful tool.

Remotely-delivered exercise training program for improving physical and cognitive functions among older adults with multiple sclerosis: Protocol for an NIH stage-I randomized controlled trial

BackgroundOlder adults with multiple sclerosis (MS) present with low physical activity participation, cognitive and ambulatory dysfunctions, and compromised quality of life (QOL). ObjectiveWe propose a NIH Stage-I, randomized controlled trial (RCT) that examines the feasibility and efficacy of a 16-week theory-based, remotely-delivered, exercise training program for improving cognitive and physical functions in older adults with MS who have moderate mobility disability without severe cognitive impairment. MethodsThis Stage-I study utilizes a parallel-group RCT design. Participants (N = 50; age ≥ 50 years) will be randomly assigned into exercise training (combined aerobic and resistance exercise) or active control (flexibility and stretching) conditions. The conditions will be undertaken within a participant's home/community over a 16-week period, and monitored remotely and supported by Zoom-based chats guided by social cognitive theory (SCT) via a behavioral coach. Participants will receive training manuals and equipment, one-on-one behavioral coaching, action-planning calendars, self-monitoring logs, and SCT-based newsletters. The primary outcomes include feasibility (e.g., recruitment and retention rates), exercise behavior and physical activity; other outcomes include physical function (lower-extremity function, mobility, walking), cognition (processing speed, learning and memory, executive function), MS symptoms, QOL, and vascular function. We will collect outcome data at baseline (Week 0), post-intervention (Week 16), and follow-up (Week-32). Data analysis will follow intent-to-treat principles using linear mixed-effects models. DiscussionThis Stage-I trial adopts an innovative approach for exercise training via telerehabilitation and is convenient and accessible for older adults with MS. If successful, the study will provide foundations for future research using remotely-delivered exercise intervention for managing the consequences of aging with MS.Trial Registration Number:NCT05930821

Validation of a novel, low-fidelity virtual reality simulator and an artificial intelligence assessment approach for peg transfer laparoscopic training

Simulators are widely used in medical education, but objective and automatic assessment is not feasible with low-fidelity simulators, which can be solved with artificial intelligence (AI) and virtual reality (VR) solutions. The effectiveness of a custom-made VR simulator and an AI-based evaluator of a laparoscopic peg transfer exercise was investigated. Sixty medical students were involved in a single-blinded randomised controlled study to compare the VR simulator with the traditional box trainer. A total of 240 peg transfer exercises from the Fundamentals of Laparoscopic Surgery programme were analysed. The experts and AI-based software used the same criteria for evaluation. The algorithm detected pitfalls and measured exercise duration. Skill improvement showed no significant difference between the VR and control groups. The AI-based evaluator exhibited 95% agreement with the manual assessment. The average difference between the exercise durations measured by the two evaluation methods was 2.61 s. The duration of the algorithmic assessment was 59.47 s faster than the manual assessment. The VR simulator was an effective alternative practice compared with the training box simulator. The AI-based evaluation produced similar results compared with the manual assessment, and it could significantly reduce the evaluation time. AI and VR could improve the effectiveness of basic laparoscopic training.

Social Story Intervention for Training Expected Behaviors among Preschool Children: A Systematic Review and Meta-Analysis.

Promoting appropriate behaviors in early childhood is crucial for children's future development. This systematic review aimed to explore the efficacy of social story (SS) intervention in teaching expected behaviors among preschool children. A structured search strategy was applied to five online electronic databases. The references were systematically screened in accordance with the PRISMA statements. Randomized or non-randomized controlled studies, as well as single-subject studies, in which SSs served as a behavioral training approach for children aged 2 to 6 years were included. Information related to study design, characteristics of the participants, target behaviors, and implementation of SS intervention was extracted. A meta-analysis was performed using the random-effects model, where similar outcomes were evaluated by similar intervention across multiple studies. Twenty-one studies were identified for qualitative analysis, while two studies formed the basis of the meta-analysis. SS interventions were employed to teach a variety of behaviors among typically developing children as well as those with various disabilities, such as autism, developmental delay, hearing impairments, attention deficit hyperactivity disorder, or other disabilities. The target behaviors included oral health practices, peer interaction, staying on-task, self-regulation, sleep habits, and controlling aggressive behavior during group activities. The SSs were used either alone or combined with other strategies, such as positive reinforcement, music therapy, role play, group discussion, video self-modeling, immediate practices, or additional audio commentary. Most studies reported improvements in appropriate behaviors and/or reductions in unfavorable behaviors. The meta-analysis indicated that children practiced more toothbrushing steps when using SS interventions compared to conventional oral health instruction (Z = 3.60, MD = 0.66, 95%CI 0.30 to 1.02, p < 0.001). SS interventions have the potential to teach target behaviors, particularly toothbrushing behaviors, among preschool children. More well-designed randomized controlled trials are warranted to determine the efficacy of SS interventions among children with various developmental profiles.