Fitness Monitoring Research Articles

The Principles of Hearable Photoplethysmography Analysis and Applications in Physiological Monitoring-A Review.

Not long ago, hearables paved the way for biosensing, fitness, and healthcare monitoring. Smart earbuds today are not only producing sound but also monitoring vital signs. Reliable determination of cardiovascular and pulmonary system information can explore the use of hearables for physiological monitoring. Recent research shows that photoplethysmography (PPG) signals not only contain details on oxygen saturation level (SPO2) but also carry more physiological information including pulse rate, respiration rate, blood pressure, and arterial-related information. The analysis of the PPG signal from the ear has proven to be reliable and accurate in the research setting. (1) Background: The present integrative review explores the existing literature on an in-ear PPG signal and its application. This review aims to identify the current technology and usage of in-ear PPG and existing evidence on in-ear PPG in physiological monitoring. This review also analyzes in-ear (PPG) measurement configuration and principle, waveform characteristics, processing technology, and feature extraction characteristics. (2) Methods: We performed a comprehensive search to discover relevant in-ear PPG articles published until December 2022. The following electronic databases: Institute of Electrical and Electronics Engineers (IEEE), ScienceDirect, Scopus, Web of Science, and PubMed were utilized to conduct the studies addressing the evidence of in-ear PPG in physiological monitoring. (3) Results: Fourteen studies were identified but nine studies were finalized. Eight studies were on different principles and configurations of hearable PPG, and eight studies were on processing technology and feature extraction and its evidence in in-ear physiological monitoring. We also highlighted the limitations and challenges of using in-ear PPG in physiological monitoring. (4) Conclusions: The available evidence has revealed the future of in-ear PPG in physiological monitoring. We have also analyzed the potential limitation and challenges that in-ear PPG will face in processing the signal.

Comparison of Exercise Capacity, Physical Activity Level and Peripheral Muscle Strength in Systemic Lupus Erythematosus Patients with Healthy Individuals

Abstract Background This study investigated physical activity, peripheral muscle strength, exercise capacity, sleep, fatigue, anxiety and depression in patients with systemic lupus erythematosus (SLE). Material and Methods Twenty-six patients with SLE, median age 32.5 (25–43) years, and 29 healthy individuals, median age 30 (23–32) years, were included. Exercise capacity (6-minute walk test (6MWT)), peripheral muscle strength (dynamometer), physical activity (Mi Band 4 smart band), fatigue (Fatigue Severity Scale (FSS)), anxiety and depression (Hospital Anxiety Depression scale (HAD)), quality of life (SLE-specific QOL scale (SLEQoL)) and sleep (Pittsburgh Sleep Quality Index (PSQI)) were assessed. Results Demographic characteristics were similar in both groups. 6MWT distance, peripheral muscle strength, physical activity level, SLEQoL and PSQI scores were significantly lower, while FSS and HAD scores were higher in patients with SLE (p<0.05). Moreover, pre-test and post-test heart rates, dyspnea and fatigue severity scores were higher in patients with SLE than in healthy individuals (p<0.05). Conclusion Patients with SLE had lower exercise capacity, muscle strength, physical activity, quality of life and sleep quality, along with more common fatigue, anxiety and depression. Strategies need to be developed to improve these symptoms in patients with SLE for a favourable outcome.

Design of a perceptron model-based physical fitness index monitoring system for sports training

Abstract The purpose of designing a sports training fitness index monitoring system is to grasp better the physical performance data of athletes in the training process to ensure training safety. In this paper, the principle of multilayer perceptron is explained based on the perceptron model, the optimal loss function of multilayer perceptron is solved by using the activation function and forward propagation algorithm, the sensor data collection module is constructed, and the physical fitness index monitoring system for sports training is built by this method. To verify the feasibility of the detection system in this paper, experimental analysis was conducted from three aspects: the distribution of physical fitness index monitoring information density, physical fitness index data and monitoring data accuracy. The index monitoring density distribution was between 0.11 and 2.09 from the monitoring information density. Regarding physical performance indicators, the average values of maximum oxygen uptake, heart rate, relative energy metabolism level, and exercise intensity were 41.02, 121.58, and 11.84, respectively. From the accuracy of indicator monitoring data, the accuracy of the system in this paper was 93.63%, which was 21.57 and 11.03 percentage points higher than that of GAN and MCNN algorithms, respectively. The physical fitness index monitoring system constructed based on the perceptron model can effectively realize the monitoring of physical fitness indexes, help trainers master the training rhythm, and improve the safety of sports training.

Physical Activity Pattern of Adults With Metabolic Syndrome Risk Factors: Time-Series Cluster Analysis.

Physical activity plays a crucial role in maintaining a healthy lifestyle, and wrist-worn wearables, such as smartwatches and smart bands, have become popular tools for measuring activity levels in daily life. However, studies on physical activity using wearable devices have limitations; for example, these studies often rely on a single device model or use improper clustering methods to analyze the wearable data that are extracted from wearable devices. This study aimed to identify methods suitable for analyzing wearable data and determining daily physical activity patterns. This study also explored the association between these physical activity patterns and health risk factors. People aged >30 years who had metabolic syndrome risk factors and were using their own wrist-worn devices were included in this study. We collected personal health data through a web-based survey and measured physical activity levels using wrist-worn wearables over the course of 1 week. The Time-Series Anytime Density Peak (TADPole) clustering method, which is a novel time-series method proposed recently, was used to identify the physical activity patterns of study participants. Additionally, we defined physical activity pattern groups based on the similarity of physical activity patterns between weekdays and weekends. We used the χ2 or Fisher exact test for categorical variables and the 2-tailed t test for numerical variables to find significant differences between physical activity pattern groups. Logistic regression models were used to analyze the relationship between activity patterns and health risk factors. A total of 47 participants were included in the analysis, generating a total of 329 person-days of data. We identified 2 different types of physical activity patterns (early bird pattern and night owl pattern) for weekdays and weekends. The physical activity levels of early birds were less than that of night owls on both weekdays and weekends. Additionally, participants were categorized into stable and shifting groups based on the similarity of physical activity patterns between weekdays and weekends. The physical activity pattern groups showed significant differences depending on age (P=.004) and daily energy expenditure (P<.001 for weekdays; P=.003 for weekends). Logistic regression analysis revealed a significant association between older age (≥40 y) and shifting physical activity patterns (odds ratio 8.68, 95% CI 1.95-48.85; P=.007). This study overcomes the limitations of previous studies by using various models of wrist-worn wearables and a novel time-series clustering method. Our findings suggested that age significantly influenced physical activity patterns. It also suggests a potential role of the TADPole clustering method in the analysis of large and multidimensional data, such as wearable data.

Clinical Applications of Otoacoustic Emission: A Review of the Indications in Aminu Kano Teaching Hospital Northern Nigerian

Context: An otoacoustic emission (OAE) is a low-level sound emitted by the cochlea either spontaneously or evoked by an auditory stimulus. Objectives: To determine cochlea status, specifically outer hair cells (OHC), and to determine the indications and utilization of Otoacoustic emission in Aminu Kano Teaching Hospital. Settings and Design: This was a 3 years retrospective analysis in which all patients that had Otoacoustic Emission in Aminu Kano Teaching Hospital from January 1, 2018 to December 31, 2021. Materials and Methods: The records were retrieved and the basic demographic data, indications, and findings were extracted and entered into the Excel spreadsheet. Statistical Analysis Used: Retrospective analysis of the indications of otoacoustic emission testing was done by analyzing the records of 146 patients. The data were extracted and analyzed using SPSS version 22.0 and the result presented in tables. Results: Hearing loss accounted for 37% of OAE testing done (55 patients). Hearing loss from febrile illness accounted for 12.3% (18 patients) and 12% resulted from congenital hearing loss (16 patients). Conclusion: OAEs continue to play an important role in routine audiological assessments with ever-expanding applications. There is, however, marked under-utilization of the investigation. Hopefully, the scope of applications will broaden to include hearing aid fitting and intraoperative monitoring, and using OAE as “acoustic fingerprints” becomes a reality. There is a need for more commitment by the ORL Surgeons.

Role of exercise physiologists in talent identification, training and monitoring performance in sports

Exercise Physiology is the branch of 'Sports Science', which involves the study of adaptation to exercise. Exercise physiologists monitor thephysical and physiological variables of the sports persons, which are used for talent identification, training, and evaluation of performance.Sports talent may be identified from young children when they show interest in sports. Proper nutrition and training during the growthand development phase of life help improve the athletes' performance. Training has to be formulated according to the principles ofperiodization to achieve the best possible performance. Long-term training and participating in competitions brought changes withinthe sports persons. Regular monitoring of athletes' anthropometric, physical fitness and physiological variables provides valuableinformation about their fitness, health, metabolic and cardio-respiratory status. This would enable the coaches to assess the currentstatus of the athletes and the degree of training adaptability and provide an opportunity to modify the training schedule accordinglyto achieve the desired performance. Exercise physiologists suggest optimal training strategies to enhance athletic performance. Thedemand for an athlete's success and fitness awareness within society increases the responsibility of exercise physiologists to optimizeathletes' sports performance, health, and safety.

EHealth and Smart Solutions framework for health monitoring in the course of the pandemic

Our main objective focusing on the different design principles for applications which can receiveand store various data from smart devices e.g., smart bands, smart watches, smart homes and could gainmore information about its users with some extent to their health. We would like to collect this information,store them, then create well understandable diagrams and show them to the user in a modern, responsiveenvironment. We placed great em- phasis on the architecture which holds the necessary features (scalabilityand extensibility). We have followed the standards, recommendations, and protocols during the designprocess. The result is an application framework which fulfills the duty of an XXI. century smart solutionsapplication that could monitor the health of people and even help to live a healthier life avoiding chronicdisorders e.g., obesity and/or diabetes. We focused on predicting and classifying on COVID-19 disease tooaccording to the collected information and research results. We achieved tihs project using our own deviceslike a Samsung Galaxy Watch 2 whch comes integrated Tizen OS and gave the opportunity to develop adata sending application on it. On the other hand we worked with smartbands like the Xiaomi Mi Band 6but it does not have programable OS so we needed to find a solution to collect data from it but his case isdiscussed in the paper later. We would like to implement this project live with the Clinic of our universityto get more real cases and data. We are working on a solution where everyone could have their own medicalassistant to predict and prevent healthcare issues.

Fitness bracelet for optimizing life

Relevance. Fitness bracelets allow you to monitor daily activity by pulse, saturation, stress level, pressure, sleep quality and a number of other indicators. However, there is no consensus on how to use it effectively. The priority should be considered the use of a fitness bracelet for the growth of quality of life, career achievements, etc. Such physical activity is optimal, in which intellectual performance has the greatest significance. The purpose of the study is to determine the optimal scenario for using a fitness bracelet, as well as to compare the most popular models on the market. Methods and organization of research. As a device for measuring intellectual productivity, the most common computer games were used: tetris, chess, lines, etc., having a numerical indicator of success. The level of intellectual performance first increases with the amount of physical activity, but after a certain value it drops. This point is conventionally called the inflection point. First there was the mi smart band 7 fitness bracelet, and then HUAWEI Band 7. The big advantage was storing all the data on a separate application in a smart background. This made it possible to compare the level of intellectual activity with all the indicators of the smartphone. We saw inflection points on all the charts. Personal values were shown on the example of the two most widespread bracelets. It turned out that the recorded levels of the number of steps per day, the number of calories, stress levels, sleep quality and others also pass through the inflection point. However, the values of these points differ for different models. For a new model, it is necessary to do such a study anew. The optimization of the daily routine, the mode of activity for the indicators found led to a change in the level of the game of chess, when the number of games won tripled, which seems to be more than an impressive incentive to use a fitness bracelet. Conclusions. Fitness bracelets allow you to monitor daily activity by pulse, concentration, stress level, pressure, sleep quality and a number of other indicators. The level of accuracy of the indicators is continuously increasing. This allows you to use fitness bracelets to optimize users' lives.

0748 Using daily wearable cardio fitness and sleep data to predict obesity in early adolescence

Abstract Introduction Obesity, and its co-morbidities, is a serious health risk currently facing adolescents in the US, with increased risk for adult obesity and cardiovascular health problems. Sleep is crucial for energy restorative processes and insufficient sleep influences food intake and appetite regulation. Adolescents are at risk for poor/insufficient sleep, which could, therefore, contribute to obesity risk. Given multifactorial risk factors, there is a need to identify the most salient predictors of adolescent obesity. Predicting adolescent obesity using objective Fitbit data has not previously been investigated and is the aim of the current study. Methods We used data collected with the Fitbit Charge 2 device from 2491 participants (Year 2, Mean-age=11.95 years, SD=0.65, 49.5% female) in the Adolescent Brain Cognitive Development (ABCD) Study®. We trained machine learning models (Gradient Boosted Trees and Regularized Logistic Regression) to identify the most important measures that predict obesity (&amp;gt;95 BMI percentile). In addition to sleep (timing, efficiency, duration, and regularity across the week) and cardio fitness (step counts, resting heart rate) Fitbit measures, averaged across seven days, we included socio-demographic characteristics. We ran a grid search embedded in a 2x5 fold cross-validation and we evaluated the performance based on the area under the curve-AUC and accuracy-ACC metrics. Results 15% percent of the sample were classified as having obesity. Both classification models performed acceptably high, with the LogReg having better performance (AUC-LogReg=0.76, ACC=85%) than the GBT model (AUC-GBT=0.75, ACC=0.69). Shorter sleep duration, more day-to-day variability in sleep measures, low number of steps with low variability over the week, and higher resting heart rate, with high day-to-day variability, were important predictors. Sociodemographic factors (Hispanic/Latinx ethnicity, African American race, low access to food) were also important predictors. Conclusion Results show that there are socio-economic disparities in obesity risk and that shorter sleep duration and more variable sleep patterns, as detected with a wearable, are important predictors of obesity risk. Results highlight the clinical utility of wearable measures and the importance of continuous monitoring of sleep, physical activity, and cardio fitness in adolescents. Support (if any) NIH U01DA041022

Sensitivity analysis of numerical model parameters for optimized PEH responses

With the increasing popularity of wearable devices, typically employed in fitness and health monitoring, there is an evident need to extend their autonomy and replace the conventional power sources with environmentally friendly alternatives. Piezoelectric energy harvesting systems, optimized for collecting kinetic energy from random human motion and transduce it into electrical energy, represent a viable option for powering autonomous wearables. Since established analytical methods are unable to model the behaviour of piezoelectric harvesters with complex optimized geometries, suitable numerical models need to be employed for their design. This implies the need of a thorough study focused on the mechanical engineering design optimization purposes of how the finite element type and mesh density affect the uncoupled modal and coupled transient responses of a new class of optimised design configurations of the studied devices.

A CNN-SPEED-BASED GNSS/PDR INTEGRATED SYSTEM FOR SMARTWATCH

Abstract. In recent years, wearable devices such as smart bands and smartwatches have gained widespread popularity due to their ability to provide various health and fitness applications by detecting and analyzing the human body and motion information. However, the accuracy of location-based services can be limited, especially in urban areas and indoors. This study proposes a series of smartwatch Pedestrian Dead Reckoning (PDR) improvements based on 9 Degrees of Freedom (DOF) IMU orientation estimation, which includes the heading estimation of human movement and a novel pre-trained velocity regression model. The proposed system holds the potential to enhance positioning accuracy and augment navigation availability for smartwatch users, thus offering potential applications across various fields. This study makes significant contributions to the field of smartwatch navigation by proposing a GNSS/PDR fusion algorithm specifically designed for the consumer-grade IMU, magnetometer, and GNSS receiver built into Apple Watch, tracking varied roll and pitch of the sensor caused by hand swing, and integrating a CNN model to predict the 1-D speed and provide ZUPT information, offering improved accuracy and reliability.

Quantification of the Number of Steps in a School Recess by Means of Smart Bands: Proposal of Referential Values for Children and Adolescents.

(1) Background: Regular physical activity has multiple benefits. Therefore, school recess is a key tool to provide opportunities for schoolchildren to engage in extracurricular physical activity, have fun, play and interact with their peers. The aim is to provide reference data to quantify the number of steps that children and adolescents perform in a school recess using smart bands according to age range and sex. (2) Method: A descriptive cross-sectional study was carried out in 494 schoolchildren aged 6 to 17 years (292 males and 202 females). Weight, standing height and waist circumference (WC) were evaluated. The body mass index (BMI) was calculated. The quantification of the number of steps during school recess was performed using a smart band. (3) Results: Percentiles were constructed for the number of steps (number of steps/recess). The cut-off points considered were <p25 (below average), p25 to p75 (average) and >p75 (above average). The median values in both sexes decreased as the age range increased. Youth who walked fewer steps during recess (<p25: below average) had elevated BMI and WC values relative to those who walked within average and above average. (4) Conclusion: The number of steps taken by schoolchildren during school recess decreases drastically with advancing age. The proposed reference values can be used to categorize schoolchildren according to the number of steps taken and to compare them among their peers. The results suggest their use and application in schools as a way of achieving the minimum physical activity recommendations.

Optoelectronic and Optomechanical Properties of Few-Atomic-Layer Black Phosphorus Nanoflakes as Revealed by In Situ TEM.

The optoelectronic signatures of free-standing few-atomic-layer black phosphorus nanoflakes are analyzed by in situ transmission electron microscopy (TEM). As compared to other 2D materials, the band gap of black phosphorus (BP) is related directly to multiple thicknesses and can be tuned by nanoflake thickness and strain. The photocurrent measurements with the TEM show a stable response to infrared light illumination and change of nanoflakes band gap with deformation while pressing them between two electrodes assembled in the microscope. The photocurrent spectra of an 8- and a 6-layer BP nanoflake samples are comparatively measured. Density functional theory (DFT) calculations are performed to identify the band structure changes of BP during deformations. The results should help to find the best pathways for BP smart band gap engineering via tuning the number of material atomic layers and programmed deformations to promote future optoelectronic applications.

The impact of sport-specific physical fitness change patterns on lower limb non-contact injury risk in youth female basketball players: a pilot study based on field testing and machine learning.

Background: In recent years, identifying players with injury risk through physical fitness assessment has become a hot topic in sports science research. Although practitioners have conducted many studies on the relationship between physical fitness and the likelihood of injury, the relationship between the two remains indeterminate. Consequently, this study utilized machine learning to preliminary investigate the relationship between individual physical fitness tests and injury risk, aiming to identify whether patterns of physical fitness change have an impact on injury risk. Methods: This study conducted a retrospective analysis by extracting the records of 17 young female basketball players from the sport-specific physical fitness monitoring and injury registration database in Fujian Province. Sports-specific physical fitness tests included physical performance, physiological, biochemical, and subjective perceived responses. The data for each player was standardized individually using Z-scores. Synthetic minority over-sampling techniques and edited nearest neighbor algorithms were used to sample the training set to address the negative impact of class imbalance on model performance. Feature extraction was performed on the dataset using linear discriminant analysis, and the prediction model was constructed using the cost-sensitive neural network. Results: The 10 replicate 5-fold stratified cross-validation showed that the lower limb non-contact injury prediction model based on the cost-sensitive neural network had achieved good discrimination and calibration (average Precision: 0.6360; average Recall: 0.8700; average F2-Score: 0.7980; average AUC: 0.8590; average Brier-score: 0.1020), which could be well applied in training practice. According to the attribution analysis, agility and speed were important physical attributes that affect youth female basketball players' non-contact lower limb injury risk. Specifically, there was enhance in the performance of the 1-min double under, accompanied by an increase in urinary ketone and urinary blood levels following the agility test. The 3/4 basketball court sprint performance improved, while urinary protein and RPE levels decreased after the speed test. Conclusion: The sport-specific physical fitness change pattern can impact the lower limb non-contact injury risk of young female basketball players in Fujian Province, specifically in terms of agility and speed. These findings will provide valuable insights for planning athletes' physical training programs, managing fatigue, and preventing injuries.

Post-mortem digital forensics analysis of the Zepp Life android application

This paper studies the post-mortem digital forensic artifacts left by the Android ZeppLife (formerly MiFit) mobile application when used in conjunction with a Xiaomi MiBand 6. The MiBand 6 is a low-cost smart band device with several sensors that allow for health and activity monitoring, collecting metrics such as heart rate, blood oxygen saturation level, and step count. The device communicates via Bluetooth Low Energy with the ZeppLife application, which displays its data, provides some controls, and acts as a bridge to the Internet.We study, from a digital forensics perspective, the Android version of the mobile application in a rooted smartphone. For this purpose, we analyze the data repositories, namely its databases and XML files, and correlate the data on the smartphone with the corresponding usage of the Mi Band device. The paper also presents two open-source scripts we have developed to ease the task of forensic practitioners dealing with ZeppLife/MiBand 6: ZL_std and ZL_autopsy. The former refers to a Python 3 script that extracts high-level views of Zepp Life data through the command-line, whereas the latter is a module that integrates ZL_std functionalities within the popular open-source Autopsy digital forensic software. Data stored on the Android companion device of a MiBand 6 might include GPS coordinates, events and alarms, and biometric data such as heart rate, sleep time, and fitness activity, which can be valuable digital forensic artifacts.

HearFit+: Personalized Fitness Monitoring via Audio Signals on Smart Speakers

Fitness can help to strengthen muscles, increase resistance to diseases, and improve body shape. Nowadays, a great number of people choose to exercise at home/office rather than at the gym due to lack of time. However, it is difficult for them to get good fitness effects without professional guidance. Motivated by this, we propose the first personalized fitness monitoring system, HearFit+, using smart speakers at home/office. We explore the feasibility of using acoustic sensing to monitor fitness. We design a fitness detection method based on Doppler shift and adopt the short time energy to segment fitness actions. Based on deep learning, HearFit+ can perform fitness classification and user identification at the same time. Combined with incremental learning, users can easily add new actions. We design 4 evaluation metrics (i.e., duration, intensity, continuity, and smoothness) to help users to improve fitness effects. Through extensive experiments including over 9,000 actions of 10 types of fitness from 12 volunteers, HearFit+ can achieve an average accuracy of 96.13% on fitness classification and 91% accuracy for user identification. All volunteers confirm that HearFit+ can help improve the fitness effect in various environments.

Sensing the Environment with Sensors: A Smart Wearable Band for Obstacle Detection for the Visually Impaired

Abstract: Even after numerous remedies have been suggested, the issue of improving the mobility of individuals with visual impairments remains today. A clever wearable is described in this article. A sonar is an ultrasonic instrument that can produce a band for the user to recognize obstacles. Wearable technology such as ultrasonic sensors and tactile input is used in smart bands to help blind or visually disabled individuals navigate their surroundings. Vibration and auditory signals or messages can be used to tell the user of their position, adjacent barriers, and other crucial information. This technology can significantly improve the freedom of visually impaired people who are blind or visually impaired, allowing them to move more boldly and easily through new situations.

Barriers and Facilitators to Telehealth Timed Up and Go (TUG) Assessment in an Underserved Urban Stroke Population (P6-5.013)

<h3>Objective:</h3> To eliminate barriers and facilitate remote assessment of a standardized mobility outcome measure for stroke patients in a telehealth-based study to facilitate physical activity and rehabilitation at home through fitness monitoring and feedback. <h3>Background:</h3> Telehealth for assessment &amp; intervention for individuals with neurological conditions has grown since the CoVid-19 pandemic. Our stroke patients are from an underserved urban community with social, personal, and environmental barriers that would impact success of a telehealth program. <h3>Design/Methods:</h3> Patients (n= 6 to date) with minor stroke discharged home from acute hospitalization were recruited. Evaluation by the interdisciplinary team determined patient safety for discharge home (6Clicks Mobility Score=46.15(9.12)). A neurologist evaluated the patient through telehealth and information from 1 month monitoring period was reviewed with an infographic guided discussion to enhance self-efficacy. Physical therapy team members executed two TUG trials and determined real-time reliability. The assessors followed a standardized script including a flowsheet with video demonstrations of camera set-up, testing materials and TUG demonstration. Patients provided feedback regarding instruction mode and suggested improvements. The Theoretical Domains Framework (TDF) mapped identified barriers/facilitators, analyzed, and interpreted the results. Intertester reliability for TUG and TUG/physical mobility measure correlation were performed. <h3>Results:</h3> The flowsheet, video demonstration, and client feedback eliminated patient barriers in knowledge, environmental context and resources domains. Memory, attention, and decision process barriers were facilitated by flexible patient scheduling and phone call reminders. Professional role/identity barriers were eliminated by optimizing each interprofessional team member’s skill set. Patient selection criteria during hospitalization eliminated the barrier to beliefs about consequences. Beliefs about capability barriers were mitigated by intertester reliability (r²=0.98) during telehealth TUG assessment and correlation with remote monitored average daily step counts (r²=−0.52). <h3>Conclusions:</h3> TDF identified facilitators to telehealth TUG assessment in an urban underserved stroke community with resource and environmental constraints and should be utilized to promote equity in health care. <b>Disclosure:</b> Clare Bassile has nothing to disclose. Ms. McIntyre has nothing to disclose. Miss Powell has nothing to disclose. Ms. Sareen has nothing to disclose. Ms. Karsos has nothing to disclose. Dr. Naqvi has nothing to disclose.

Influence of preterm birth on physical fitness in early childhood

ABSTRACT Evidence suggests that preterm birth is associated with an impaired physical fitness later in life, but whether these effects are already visible since early childhood remains unknown. We aimed to compare the physical fitness of preterm preschoolers with that of children born at term. Children aged three to six years and born preterm (<35 weeks) were recruited from a Neonatal Intensive Care Unit, and children born at term (>37 weeks) were included as controls. A variety of physical fitness indicators (strength, cardiorespiratory fitness, agility, flexibility and balance) were assessed with the PREFIT battery and the adapted sit and reach test. Physical activity levels were measured through the PrePAQ questionnaire. A total of 98 preterm children (gestational age 32.4 ± 2.3 weeks, age 5.1 ± 0.8 years) and 74 controls (gestational age 39.9 ± 1.0 weeks, age 4.8 ± 0.9 years) were analysed. Despite no significant differences in physical activity levels (p > 0.05), preterm children showed an overall poorer physical fitness compared to controls. Specifically, preterm children had an impaired handgrip strength (−13.95%, p < 0.001), lower-limb muscle strength (−12.67%, p = 0.003), agility (−14.9%, p = 0.001), cardiorespiratory fitness (−12.73% p = 0.005) and flexibility (−17.04%, p = 0.001) compared to controls. An inverse dose–response association was observed between the level of prematurity and physical fitness, with very preterm children (gestational age ≤32 weeks) presenting the poorest fitness levels. In summary, prematurity seems to impair physical fitness since early childhood, which might support the need for promoting preventive strategies (e.g. fitness monitoring and applying exercise interventions). Highlights Preterm children present an impaired physical fitness compared with peers born at term since early childhood (3–6 years), as reflected by lower muscle strength, agility, flexibility and cardiorespiratory fitness. A greater impairment of physical fitness in observed in children born very preterm (≤32 weeks of gestation). These findings might support the implementation of preventive strategies (e.g. fitness monitoring and exercise training) in preterm children since early childhood.

Construction and Application of LSTM-Based Prediction Model for Tunnel Surrounding Rock Deformation

Tunnel surrounding rock deformation is a significant issue in tunnel construction and maintenance and has garnered attention from both domestic and international scholars. Traditional methods of predicting tunnel surrounding rock deformation involve fitting monitoring and measuring data, which is a laborious and resource-intensive process with low accuracy when predicting data with significant fluctuations. A deep learning approach can improve monitoring efficiency and accuracy while reducing labor costs. In this study, taking an actual tunnel project as an example, a long short-term memory (LSTM) network model was constructed based on the recurrent neural network algorithm with deep learning to model and analyze the tunnel monitoring and measurement data, and the model was used to analyze and predict the vault settlement of the tunnel. LSTM is a type of artificial neural network architecture that is commonly used in deep learning applications for sequence prediction tasks, such as natural language processing, speech recognition, and time-series forecasting. In predicting data with smaller fluctuations, the maximum error is 4.76 mm, the minimum error is 0.03 mm, the root mean square error is 2.64, and the coefficient of determination is 0.98. In predicting data with larger fluctuations, the maximum error is 8.32 mm, the minimum error is 0.13 mm, the root mean square error is 4.42, and the coefficient of determination is 0.88. The average error of the LSTM network model is 2.16 mm. With the growth of the prediction period, the prediction results become more and more stable and closer to the actual vault settlement, which provides a reliable reference for introducing the LSTM prediction method with deep learning to tunnel construction and promoting tunnel construction safety.