Fitness Metrics Research Articles

Deep learning in marine bioacoustics: a benchmark for baleen whale detection

AbstractPassive acoustic monitoring (PAM) is commonly used to obtain year‐round continuous data on marine soundscapes harboring valuable information on species distributions or ecosystem dynamics. This continuously increasing amount of data requires highly efficient automated analysis techniques in order to exploit the full potential of the available data. Here, we propose a benchmark, which consists of a public dataset, a well‐defined task and evaluation procedure to develop and test automated analysis techniques. This benchmark focuses on the special case of detecting animal vocalizations in a real‐world dataset from the marine realm. We believe that such a benchmark is necessary to monitor the progress in the development of new detection algorithms in the field of marine bioacoustics. We ultimately use the proposed benchmark to test three detection approaches, namely ANIMAL‐SPOT, Koogu and a simple custom sequential convolutional neural network (CNN), and report performances. We report the performance of the three detection approaches in a blocked cross‐validation fashion with 11 site‐year blocks for a multi‐species detection scenario in a large marine passive acoustic dataset. Performance was measured with three simple metrics (i.e., true classification rate, noise misclassification rate and call misclassification rate) and one combined fitness metric, which allocates more weight to the minimization of false positives created by noise. Overall, ANIMAL‐SPOT performed the best with an average F metric of 0.83, followed by the custom CNN with an average fitness metric of 0.79 and finally Koogu with an average fitness metric of 0.59. The presented benchmark is an important step to advance in the automatic processing of the continuously growing amount of PAM data that are collected throughout the world's oceans. To ultimately achieve usability of developed algorithms, the focus of future work should be laid on the reduction of the false positives created by noise.

Wearable sensors for monitoring vital signals in sports and health: progress and perspective

Purpose This paper aims to concentrate on recent innovations in flexible wearable sensor technology tailored for monitoring vital signals within the contexts of wearable sensors and systems developed specifically for monitoring health and fitness metrics. Design/methodology/approach In recent decades, wearable sensors for monitoring vital signals in sports and health have advanced greatly. Vital signals include electrocardiogram, electroencephalogram, electromyography, inertial data, body motions, cardiac rate and bodily fluids like blood and sweating, making them a good choice for sensing devices. Findings This report reviewed reputable journal articles on wearable sensors for vital signal monitoring, focusing on multimode and integrated multi-dimensional capabilities like structure, accuracy and nature of the devices, which may offer a more versatile and comprehensive solution. Originality/value The paper provides essential information on the present obstacles and challenges in this domain and provide a glimpse into the future directions of wearable sensors for the detection of these crucial signals. Importantly, it is evident that the integration of modern fabricating techniques, stretchable electronic devices, the Internet of Things and the application of artificial intelligence algorithms has significantly improved the capacity to efficiently monitor and leverage these signals for human health monitoring, including disease prediction.

FitTrack BloodLink

FitTrack BloodLink is an innovative Android application designed to enhance users fitness tracking experience by seamlessly integrating it with life-saving blood donation and request functionalities. This comprehensive app automatically determines the user's starting point as their current location and sets the destination point upon finishing the run. Utilizing GPS tracking, FitTrack BloodLink monitors users routes throughout their runs, capturing essential fitness metrics like distance covered, calories burned, average speed, and total duration in real time. Additionally, users can register as blood donors through the app, making it easier for those needing donations. FitTrack BloodLink also includes a map feature displaying nearby blood donors, allowing users to view donor details and contact them directly via phone with a single click on the marker.

Validity arguments for creating a short motivation scale through adaptation of the Japanese motivated strategies for learning questionnaire

Background The coronavirus disease pandemic has substantially altered the mode of medical education, transitioning it from in-person to online. Online learning requires a strong motivational foundation to support self-directed studying. In our previous study, an adapted 31-item Japanese motivation measurement scale using the motivational section from the Japanese version of the Motivated Strategies for Learning Questionnaire (J-MSLQ) was developed. The present study aimed to collect evidence on the validity of the motivation section of the J-MSLQ and clarify whether further revision was necessary. Methods The motivation section of the J-MSLQ comprises a seven-point Likert scale survey containing 31 items. Of 127 fourth-year Japanese medical students invited to participate, 112 responded. Confirmatory factor analysis with structural equation modeling (SEM) was performed using R and R studio for all data analysis. Results The initial SEM model that incorporated all 31 items exhibited inadequate goodness of fit metrics: χ2 = 823.674 (p < 0.001), the comparative fit index (CFI) = 0.786, the root mean square error of approximation (RMSEA) = 0.093, the standardized root mean square residual (SRMR) = 0.112, the goodness of fit index (GFI) = 0.664, and the adjusted goodness of fit index (AGFI) = 0.602. We optimized the scale by eliminating 12 items with a Z test statistic < 10. Improvements in the goodness of fit metrics of the optimized SEM model were observed, demonstrating moderate model fit: χ2 = 205.602 (p < 0.001), CFI = 0.929, RMSEA = 0.080, SRMR = 0.063, GFI = 0.837, AGFI = 0.768. Conclusions A compact 18-item version of the motivation scale was developed and validated, which alleviated the respondent burden and enabled the researchers to collect data in a shorter time.

Elaboration of a Generalized Mixed Model for the wind speed distribution and an assessment of wind energy in Algerian Coastal regions and at the Capes

Understanding and evaluating wind energy involves various steps, including the observed temporal and directional variations in wind speed, choosing a suitable Probability Density Function (PDF) to describe wind regimes, and selecting an appropriate location for building wind farms. The wind speed data archived from nine meteorological stations along the northern coast of Algeria from 2017 to 2021 was used as a dataset to achieve these purposes. Zero-inflated mixed model (ZIMM) has been elaborated to model the wind speed regimes that combine two processes. The first process consists of mixing two PDFs that generate the counts data. The second process generates the residual zero-counts data. The estimation of ZIMM parameters is obtained with the Expectation–Maximization algorithm. ZIMM performances were evaluated at the selected sites using the commonly used goodness of fit (GOF) metrics: coefficient of determination (R2), root mean square error (RMSE), sum of square error (SSE), Kolmogorov–Smirnov (KS), Akaike information criterion (AIK), Bayesian Information Criterion (BIC), and compared with the widespread single PDFs: the two parameters Weibull, generalized extreme value (GEV) and Normal–Weibull mixed model. The datasets are used as input for assessing wind power and the feasibility of wind power plants in 24 Algerian Capes where the data is unavailable, using the Wind Atlas Analyses and Application Program (WAsP) and three different wind turbines, namely Nordex N50, Bonus B54, and Nordex N60. The results show significant variations in diurnal, monthly, and seasonal mean wind speed and power density. According to all GOF, the ZIMM PDF model outperforms conventional PDFs and the mixed model at the nine meteorological stations. The Bonus B54 wind turbine has the best capacity factor (Cp) with the lowest electrical production cost of all Algerian Capes, and the Cp exceeds 0.3 at 15 Capes from the 24 analyzed Capes. The highest Cp, about 0.467 with an annual electric production that reaches 4.09 GWh/year, is obtained at Cape Takouch with the lowest electrical production cost of 0.0414 $/kWh and 2.032 Kton/year of CO2 emission avoided.

Assessment of Motor Fitness Metrics among Athletes in Different Sports: An Original Research

Background. Motor fitness is one of the keys to athletes’ success and is the initial factor mixed with game-specific technique and tactics that has an impact on game performance. All athletes should incorporate these elements into their sport and game actions. Study purpose. The aim of this study was to evaluate differences in motor fitness metrics among university-level male athletes participating in various sports. Materials and methods. Sixty (60) male athletes, ranging in age from 18 to 25 years, were selected from six different sports: Athletics, Basketball, Cricket, Football, Handball, and Volleyball. Each group consisted of 10 athletes who had competed at the inter-university level. The research focused on six key fitness metrics: agility, speed, power, arm strength, abdominal muscle strength, and cardiovascular endurance. Appropriate testing methods and instruments were used to measure these parameters. Statistical analysis, including one-way ANOVA and post hoc LSD tests, was performed to identify significant differences between the groups. A significance level of 0.05 was set for the study. Results. The results showed statistically significant differences among the groups in agility (F(5,54) = 4.776, p<0.001), speed (F(5,54) = 5.602, p<0.000), and cardiovascular endurance (F(5,54) = 3.578, p<0.007). However, no significant differences were observed for power (F(5,54) = 2.079, p>0.082), arm strength (F(5,54) = 1.368, p>0.251), and abdominal muscle strength (F(5,54) = 1.947, p>0.102). According to the post hoc (LSD) test findings, each group’s agility, speed, and cardiovascular endurance parameters were compared to each other to check the significance level. Conclusions. In summary, the study has revealed that agility, speed, and cardiovascular endurance were significantly different among athletes in various sports, whereas power, arm strength, and abdominal muscle strength were not. The findings suggest that athletes and coaches should prioritize sport-specific fitness components to improve game performance.

Wearables and Their Potential to Transform Health Management: A Step towards Sustainable Development Goal 3

In the era of rapid technological advancement, wearables have emerged as a promising tool for enhancing health and well-being. The convergence of health and technology drives an unprecedented change in the approach to health and well-being management. This paper aims to provide a comprehensive understanding of the potential role of wearables in actualising health and well-being, thereby paving the way for a healthier and more sustainable future. Using the Affordance Theory lens, this paper delves into the transformative potential of wearables in health and well-being management, thereby promoting Sustainable Development Goal 3 to ensure healthy lives and well-being for all at all ages. The thematic analysis of online reviews on wearable devices captured through web scraping was carried out to explore the potential of these devices in the management of health and well-being. The paper explored how wearables, often integrated into everyday life, can monitor vital signs, track fitness metrics, and even provide therapeutic benefits for health and well-being. The findings reveal that wearables can empower individuals to take charge of their health by leveraging real-time data and personalised feedback, promoting a proactive and preventive approach to health management and resource-effective healthcare. Furthermore, the paper highlights how wearables can contribute to long-term health outcomes for the present generation without exerting excessive strain on the resources for future generations.

A PZT active sensing method for monitoring prestressing force based on the ultrasonic reflection coefficient

Prestress monitoring is key to ensuring the safety and longevity of post-tensioned prestressed structures. A new method of prestress monitoring, based on piezoceramic transducers, is proposed. Compared to traditional ultrasonic detection, we utilize piezoelectric (PZT) active sensing monitoring, eliminating the need for a specialized ultrasonic probe. First, a relationship model between the signal received energy and loading force is established based on the principle of ultrasonic reflection coefficient at the contact interface. On this basis, we overcome the low signal-to-noise ratio issue associated with the traditional method by employing the time reversal (TR) method. Next, the model parameters were fitted using experimental data. The values of the fitting evaluation metrics, SSE and RMSE, tend to be close to 0, while the R-squared value tends to be close to 1. This indicates the reliability of the model. Finally, the prestressing force validation tests are conducted through unloading tests. The average relative error between the measured and actual values across different paths ranges from 6.85% at the minimum to 15.61% at the maximum. Since the method is related to the proximity of the interface contact, it can be applied in other areas of civil engineering, such as assessing the adhesive strength of composite structures, crack development, and detecting axial stress.

Physical fitness metrics and their relationship to locomotor activity profiles among female international field hockey players across an Olympic cycle

ObjectivesThe study explored the correlations between physical fitness metrics and match locomotor activity profiles. Furthermore exploring the transformations of both fitness tests as well as match locomotor activities over an Olympic cycle. DesignObservational descriptive study. MethodsFitness testing (n = 24) and match locomotor activity (n = 102) profiles were collected. A Pearson's product-moment correlation and 95 % confidence intervals were calculated to determine relationships between metrics for each year. A mixed-effects model was used for repeated measures to identify differences in the physical fitness tests and match locomotor activity profiles between years. ResultsThe YoYo intermittent reocvery testest level 1 changed significantly (p < 0.0001) and accounted for 29 % of the variance in average speed (p < 0.001, rrm (59) = 0.54) Upper and lower body muscular strength, also improved, evidenced by the 3RM bench press (p < 0.0001), and a 28 % (2017–2019) increase in 3RM squat (p < 0.0001). Also pull-ups increased from 4.2 ± 2.8 pull-ups (2017) to 10.0 ± 3.1 pull-ups (2020) (p < 0.0001) and. countermovement jump height increased over the study duration (p < 0.0001). Match total distances remained unchanged, while average speed increased significantly (p < 0.0001). High-speed running distance (p < 0.0003) and sprint counts (p < 0.0001), showed significant improvements over the study period. ConclusionsThe study underscores noteworthy improvements in physical attributes and performance metrics over an Olympic cycle. Contributing valuable insights for enhancing athletic performance in hockey players competing in the Olympics.

Application of Northern Goshawk Back-Propagation Artificial Neural Network in the Prediction of Monohydroxycarbazepine Concentration in Patients with Epilepsy.

A northern goshawk back-propagation artificial neural network (NGO-BPANN) model was established to predict monohydroxycarbazepine (MHD) concentration in patients with epilepsy. The data were collected from 108 Han Chinese patients with epilepsy on oxcarbazepine monotherapy. The results of 14 genotype variates were selected as the input layer in the first BPANN model, and the variables that had a more significant impact on the plasma concentration of MHD were retained. With demographic characteristics and clinical laboratory test results, the genotypes of SCN1A rs2298771 and SCN2A rs17183814 were used to construct the BPANN model. The BPANN model was comprehensively validated and used to predict the MHD plasma concentration of five patients with epilepsy in our hospital. The model demonstrated favorable fitness metrics, including a mean squared error of 0.00662, a gradient magnitude of 0.00753, an absence of validation tests amounting to zero, and a correlation coefficient of 0.980. Sex, BMI, and the genotype SCN1A rs2298771 were ranked highest by the absolute mean impact value (MIV), which is primarily associated with the concentration of MHD. The test group exhibited a range of - 20.84% to 31.03% bias between the predicted and measured values, with a correlation coefficient of 0.941 between the two. With BPANN, the MHD nadir concentration could be predicted precisely. The NGO-BPANN model exhibits exceptional predictive capability and can be a practical instrument for forecasting MHD concentration in patients with epilepsy. www.chiCTR-OOC-17012141 .

Physical and mental health in adolescence: novel insights from a transdiagnostic examination of FitBit data in the ABCD study

Adolescence is among the most vulnerable period for the emergence of serious mental illnesses. Addressing this vulnerability has generated interest in identifying markers of risk for symptoms and opportunities for early intervention. Physical fitness has been linked to psychopathology and may be a useful risk marker and target for early intervention. New wearable technology has made assessing fitness behavior more practical while avoiding recall and self-report bias. Still, questions remain regarding the clinical utility of physical fitness metrics for mental health, both transdiagnostically and along specific symptom dimensions. The current study includes 5007 adolescents (ages 10–13) who participated in the Adolescent Brain Cognitive Development (ABCD) study and additional sub-study that collected fitness data from wearable technology and clinical symptom measures. Physical fitness metrics included resting heart rate (RHR- an index of cardiovascular health), time spent sedentary (associated with increased inflammation and cardiovascular disease), and time spent in moderate physical activity (associated with increased neurogenesis, neuroplasticity, and healthy neurodevelopment). Self-report clinical symptoms included measures of psychosis-like experiences (PLE), internalizing symptoms, and externalizing symptoms. Increased RHR- lower cardiovascular fitness- related only to greater internalizing symptoms (t = 3.63). More sedentary behavior related to elevated PLE severity (t = 5.49). More moderate activity related to lower PLE (t = −2.69) and internalizing (t = −6.29) symptom severity. Wearable technology fitness metrics linked physical health to specific mental health dimensions, which emphasizes the utility of detailed digital health data as a marker for risk and the need for precision in targeting physical health behaviors to benefit symptoms of psychopathology.

Evaluation of Sort Recovery via Rmax.

Cell sorting performance can be evaluated in regard to the purity and recovery of the sorted fractions. The purity provides checks on sample quality, acquisition settings, gating strategy, and the sort decisions made by the instrument, but alone it is not sufficient to evaluate sorting performance. Recovery, defined here as the number of target particles sorted relative to the number of original target particles to be sorted, is a key metric of sort fitness and performance but is often neglected due to difficulties in its measurement. Both purity and recovery require re-sampling of the sorted fraction, but unlike determining purity, calculating recovery calls for the absolute counting of particles in the sorted fraction that comes with large errors, and may not be feasible for rare populations or precious samples. Here, we describe a recently developed metric and method for calculating sort recovery called Rmax, representing the maximum expected recovery for a particular set of instrument settings. Rmax calculation avoids re-sampling of the total sorted fraction and absolute counting, being instead based on the ratios of target and non-target populations in the original pre-sort sample and in the waste stream or center stream catch. The Rmax method is ideal to evaluate and troubleshoot the optimum drop-charge delay of the sorter or any instrument-related failures that will affect sort performance. It can be used as a daily quality control check but can be particularly useful to assess instrument fitness before single-cell or rare population sorts. Because the sorted fraction is not perturbed, we can calculate Rmax during the sort run. © 2024 The Authors. Current Protocols published by Wiley Periodicals LLC. Basic Protocol 1: Evaluating sorter setup with Rmax Basic Protocol 2: Finding the maximum Rmax: scanning over the drop charge delay Alternate Protocol: Finding the maximum Rmax for cells: scanning over the drop charge delay Basic Protocol 3: Estimating sorted cell number with Rmax.

Design and Development of Neuroevolutionary Algorithms for Cyber Security and Optimizing AI Models through Genetic Programming

Different methods have been created to make optimization processes more efficient and effective, which is a big step forward in the area of evolutionary optimization. This abstract talks about four well-known methods: Neuroevolution of Augmenting Topologies (NEAT), Genetic Algorithms (GAs), Genetic Programming (GP), and Advanced Neuroevolutionary Genetic Algorithm (ANGA). It focuses on important performance indicators like Fitness Metrics, Generalization, Efficiency and Speed, and Overall Performance. With scores of 90% in Fitness Metrics and 88% in Generalization, NEAT, a neuroevolutionary program, shows strong success in competitive tasks. With an 80% score, it does poorly in Efficiency and Speed, though. GAs are known for using a population-based method. They do very well in Efficiency and Speed (90%), but they do a little worse in Fitness Metrics and Generalization (89% and 85%, respectively). With a focus on updated computer programs, GP gets marks that are equal in Fitness Metrics, Generalization, and Efficiency and Speed (88%, 85%, and 85%, respectively). The new ANGA algorithm stands out as a top worker, doing exceptionally well in all tests. ANGA gets great marks of 93% in Fitness Metrics, 94% in Generalization, and 93% in Efficiency and Speed. This shows how well it can optimize everything. Overall Performance score of 97.78% shows how well it works as a whole, making ANGA a potential method for genetic optimization.

Colony level fitness analysis identifies a trade-off between population growth rate and dauer yield in Caenorhabditis elegans

BackgroundIn the evolution from unicellular to multicellular life forms, natural selection favored reduced cell proliferation and even programmed cell death if this increased organismal fitness. Could reduced individual fertility or even programmed organismal death similarly increase the fitness of colonies of closely-related metazoan organisms? This possibility is at least consistent with evolutionary theory, and has been supported by computer modelling. Caenorhabditis elegans has a boom and bust life history, where populations of nematodes that are sometimes near clonal subsist on and consume food patches, and then generate dauer larva dispersal propagules. A recent study of an in silico model of C. elegans predicted that one determinant of colony fitness (measured as dauer yield) is minimization of futile food consumption (i.e. that which does not contribute to dauer yield). One way to achieve this is to optimize colony population structure by adjustment of individual fertility.ResultsHere we describe development of a C. elegans colony fitness assay, and its use to investigate the effect of altering population structure on colony fitness after population bust. Fitness metrics measured were speed of dauer production, and dauer yield, an indirect measure of efficiency of resource utilization (i.e. conversion of food into dauers). We find that with increasing founder number, speed of dauer production increases (due to earlier bust) but dauer yield rises and falls. In addition, some dauer recovery was detected soon after the post-colony bust peak of dauer yield, suggesting possible bet hedging among dauers.ConclusionsThese results suggest the presence of a fitness trade-off at colony level between speed and efficiency of resource utilization in C. elegans. They also provide indirect evidence that population structure is a determinant of colony level fitness, potentially by affecting level of futile food consumption.

Psychometric properties of the Chinese version of the health behavior motivation scale: a translation and validation study.

This study's objectives were to translate the Health Behavior Motivation Scale (HBMS) into Chinese and verify the scale's validity and reliability among Chinese healthy adults. The HBMS scales were translated into Chinese based on Brislin's principles. The Chinese version of HBMS is created through translation, back translation, and cross-cultural adaptation. This investigation implemented the convenience sampling method to conduct a survey on 781 healthy respondents, utilizing the Chinese version of the HBMS and a general demographic questionnaire. We used AMOS (v28.0) and SPSS (v26.0) for statistical analysis. We employed test-retest reliability, split-half reliability, and internal consistency to assess the reliability of the translation questionnaire. Structure validity and content validity were used to assess validity. The Chinese version of the Health Behavior Motivation Scale (HBMS) had a Cronbach's alpha coefficient of 0.885, and the range of Cronbach's alpha values for each dimension was 0.820-0.885. The scale's test-retest reliability was 0.824, and its split-half reliability was 0.906. Five public factors with a cumulative variance contribution of 56.527% were retrieved from the exploratory factor analysis. Moreover, the factor loading value for each item exceeded 0.4.In confirmatory factor analysis, the indicators were reported as follows: χ2/df = 1.567, GFI = 0.900, CFI = 0.952, IFI = 0.952, TLI = 0.946, AGFI = 0.881, PGFI = 0.757, PNFI = 0.789, RMSEA = 0.039, and the results of the model fit metrics were within the reference range. The Chinese version of the HBMS exhibits strong discrimination, validity, and reliability. The tool effectively identifies the motivation of healthy people to engage in healthy behaviors. It can be used by healthcare practitioners to assist in the development of follow-up interventions to reduce the prevalence of chronic disease in older people and the incidence of chronic disease in populations of young and middle-aged people.

Differentiation of Physical Training for Athletes Aged 10-12 in Kickboxing: Potential and Research Perspectives

Martial arts hold a prominent position in the array of sports disciplines, characterized by an extensive range of techniques, severe performance standards in competitive settings, impactful actions, unpredictability of outcomes, and substantial physical contact. Within this framework, the implementation of a personalized approach to physical training for children in the 10-12 age group becomes essential. This strategy encompasses an inclusive evaluation of each young athlete's unique physiological, biomechanical, and psychological traits. Such a holistic approach not only facilitates their well-rounded development but also minimizes the likelihood of injuries.&#x0D; From an educational perspective, this technique covers not only the physical aspects of training, but also emphasizes the development of academic and social skills, using methods that stimulate interest, self-motivation and positive self-esteem in athletes. It is important to use personalized training strategies that take into account the different learning styles and needs of each child, which contributes to the better integration of kickboxing techniques and the development of the necessary skills. Special attention is paid to the development of training programs that meet the individual needs and capabilities of each child, ensuring harmonious physical, psychological and social development at this key stage of their life.&#x0D; In conducting a systematic review of contemporary scholarly literature addressing physical training, the efficacy of assorted methodological approaches in the differentiation of training across various sports disciplines, such as fencing, the military- sports complex all-around, sports games, volleyball, and rowing, has been substantiated. However, there is a notable deficiency in scholarly focus on exploring the application of these differentiated physical training approaches within martial arts, especially in terms of specific physical fitness metrics for athletes in these disciplines. This research gap highlights the imperative for additional investigation and the creation of refined training strategies tailored to martial arts practitioners. These strategies should be designed to expertly integrate the distinct physical and physiological traits of these athletes.

Spring-Mass Characteristics in Runners Before and After a 56-km Road Ultramarathon.

Ultramarathons are a unique model to study the effects of systemic fatigue in athletes. This investigation applied the spring-mass template to study runners before and 2days after a road ultramarathon to characterize the effects of fatigue on systemic gait patterns. Overground kinetics were captured 7days before and 2days after the event in 14 runners. Traditional kinetic and spring-mass parameters were calculated, along with nonlinear regression-derived parameters and spring-mass model fit metrics. After the ultramarathon, vertical force magnitudes and loading rates were unchanged, but impact peaks increased (1.88 ± 0.08-1.95 ± 0.10 bodyweight). Ground contact times were modestly shorter (-3 ± 1ms), resulting in increased leg stiffness (10.0 ± 0.5-10.3 ± 0.5kN/m) with equivocal vertical stiffnesses. The deviation from the modeled spring-mass kinetics also increased (171.3 ± 15.0-181.4 ± 16.5N). Overall, the systemic mechanical behaviors of the runners persisted despite the fatigue and stress induced by a road ultramarathon. These findings support previous observations that runners maintain gross mechanical behavior when fatigued with small compensatory changes in spatiotemporal and traditional spring-mass characteristics. However, these findings also suggest that the variability within that gross behavior may increase after stress, suggesting new opportunities for quantifying those deviations.

A Comparison of Critical Speed and Critical Power in Runners Using Stryd Running Power.

Although running traditionally relies on critical speed (CS) as an indicator of critical intensity, portable inertial measurement units offer a potential solution for estimating running mechanical power to assess critical power (CP) in runners. The purpose of this study was to determine whether CS and CP differ when assessed using the Stryd device, a portable inertial measurement unit, and if 2 running bouts are sufficient to determine CS and CP. On an outdoor running track, 10 trained runners (V˙O2max, 59.0 [4.2]mL·kg-1·min-1) performed 3 running time trials (TT) between 1200 and 4400m on separate days. CS and CP were derived from 2-parameter hyperbolic speed-time and power-time models, respectively, using 2 (CS2TT and CP2TT) and 3 (CS3TT and CP3TT) TTs. Subsequently, runners performed constant-intensity running for 800m at their calculated CS3TT and CP3TT. Running at the calculated CS3TT speed (3.88 [0.44]m·s-1) elicited an average Stryd running power (271 [28]W) not different from the calculated CP3TT (270 [28]; P = .940; d = 0.02), with excellent agreement between the 2 values (intraclass correlation coefficient = .980). The CS2TT (3.97 [0.42]m·s-1) was not higher than CS3TT (3.89 [0.44]m·s-1; P = .178; d = 0.46); however, CP2TT (278 [29] W) was greater than CP3TT (P = .041; d = 0.75). The running intensities at CS and CP were similar, supporting the use of running power (Stryd) as a metric of aerobic fitness and exercise prescription, and 2 trials provided a reasonable, albeit higher, estimate of CS and CP.

Hybrid Simulated Annealing‐Evaporation Rate‐Based Water Cycle Algorithm Application for Medical Image Enhancement

Visualizing medical images is difficult due to artifacts, poor local contrast, low soft tissue contrast, excessive noise levels, and a wide dynamic range. This has created a serious problem for physicians, resulting in unapproachable and inaccurate disease diagnoses. To circumvent this problem, this research proposes a medical image enhancement (MIE) approach based on the hybrid simulated annealing‐evaporation rate‐based water cycle algorithm (SA‐ERWCA). The ERWCA enhances distorted medical images by finding the best optimal solution for the transformation parameters according to the fitness function. The fitness function consists of three objective measurements, namely, entropy, number of edges, and sum of edge intensities. Due to its high potential for finding a globally optimal solution, SA is applied solely to determine the optimized initial population of the ERWCA, thereby enhancing its convergence characteristics. To simply put, the main objective of SA is to avoid premature convergence of the ERWCA. Thus, blending SA and ERWCA produces better‐quality medical images. The performance of the proposed algorithm was compared to histogram equalization (HE), low contrast stretching (LCS), contrast‐limited adaptive histogram equalization (CLAHE), particle swarm optimization (PSO), accelerated PSO (APSO), and the water cycle algorithm (WCA). Along with the objective function fitness, seven full reference (FR) image quality assessment (IQA) metrics were implemented to evaluate image quality and compare performance. The findings of the present study showed that the proposed strategy outperforms all of the compared methods in terms of objective function fitness and perceptual visual IQA metrics such as the Harr wavelet‐based perceptual similarity index (HaarPSI), visual signal‐to‐noise ratio (VSNR), and information content weighted structural similarity index measure (IW‐SSIM). The suggested technique also exhibited better stability and faster convergence time to the optimum solution. Furthermore, the proposed approach outperformed others by avoiding premature convergence to the best solution and providing excellent optimization results with acceptable computational efficiency.

Evolving interpretable decision trees for reinforcement learning

In recent years, reinforcement learning (RL) techniques have achieved great success in many different applications. However, their heavy reliance on complex deep neural networks makes most RL models uninterpretable, limiting their application in domains where trust and security are important. To address this challenge, we propose MENS-DT-RL, an algorithm capable of constructing interpretable models for RL via the evolution of decision tree (DT) models. MENS-DT-RL uses a multi-method ensemble algorithm to evolve univariate DTs, guiding the process with a fitness metric that prioritizes interpretability and consistent high performance. Three different initializations for the MENS-DT-RL are proposed, including the use of Imitation Learning (IL) techniques, and a novel pruning approach that reduces solution size without compromising performance. To evaluate the proposed approach, we compare it with other models from the literature on three benchmark tasks from the OpenAI Gym library, as well as on a fertilization problem inspired by real-world crop management. To the best of our knowledge, the proposed scheme is the first to solve the Lunar Lander benchmark with both interpretability and a high confidence rate (90% of episodes are successful), as well as the first to solve the Mountain Car environment with a tree of only 7 nodes. On the real-world task, the proposed MENS-DT-RL is able to produce solutions with the same quality as deep RL policies, with the added bonus of interpretability. We also analyze the best solutions found by the algorithm and show that they are not only interpretable but also diverse in their behavior, empowering the end user with the choice of which model to apply. Overall, the findings show that the proposed approach is capable of producing high-quality transparent models for RL, achieving interpretability without losing performance.