Daily Activity Monitoring Research Articles

Revolutionizing health monitoring: Integrating transformer models with multi-head attention for precise human activity recognition using wearable devices.

A daily activity routine is vital for overall health and well-being, supporting physical and mental fitness. Consistent physical activity is linked to a multitude of benefits for the body, mind, and emotions, playing a key role in raising a healthy lifestyle. The use of wearable devices has become essential in the realm of health and fitness, facilitating the monitoring of daily activities. While convolutional neural networks (CNN) have proven effective, challenges remain in quickly adapting to a variety of activities. This study aimed to develop a model for precise recognition of human activities to revolutionize health monitoring by integrating transformer models with multi-head attention for precise human activity recognition using wearable devices. The Human Activity Recognition (HAR) algorithm uses deep learning to classify human activities using spectrogram data. It uses a pretrained convolution neural network (CNN) with a MobileNetV2 model to extract features, a dense residual transformer network (DRTN), and a multi-head multi-level attention architecture (MH-MLA) to capture time-related patterns. The model then blends information from both layers through an adaptive attention mechanism and uses a SoftMax function to provide classification probabilities for various human activities. The integrated approach, combining pretrained CNN with transformer models to create a thorough and effective system for recognizing human activities from spectrogram data, outperformed these methods in various datasets - HARTH, KU-HAR, and HuGaDB produced accuracies of 92.81%, 97.98%, and 95.32%, respectively. This suggests that the integration of diverse methodologies yields good results in capturing nuanced human activities across different activities. The comparison analysis showed that the integrated system consistently performs better for dynamic human activity recognition datasets. In conclusion, maintaining a routine of daily activities is crucial for overall health and well-being. Regular physical activity contributes substantially to a healthy lifestyle, benefiting both the body and the mind. The integration of wearable devices has simplified the monitoring of daily routines. This research introduces an innovative approach to human activity recognition, combining the CNN model with a dense residual transformer network (DRTN) with multi-head multi-level attention (MH-MLA) within the transformer architecture to enhance its capability.

The Association Between Heart Rate Variability and Sleep Quality - a Narrative Review

Introduction Heart rate variability (HRV) serves as a non-invasive marker to assess autonomic nervous system (ANS) modulation on cardiac rhythm. Its link with sleep quality, particularly in the context of insomnia, posits HRV as a potential indicator of autonomic state variations during sleep disturbances. The prevalence of insomnia, affecting up to 20% of the general population, emphasizes the need to understand its extensive impact. Material and Methods For this review - 41 relevant titles from 1985 to 2024 were selected Analysis of the Literature: Recent studies highlight a bidirectional relationship between insomnia and ANS function, with increased sympathetic activity indicated by physiological and subjective measures in individuals with insomnia. The role of medications like beta-blockers in disrupting ANS and leading to sleep deprivation further connects measurable and perceived aspects of sleep quality, impacting health negatively. Moreover, HRV's application has expanded beyond professional athletics to daily activity and sleep quality monitoring by the general population, emphasizing its potential in evaluating stress and training intensity. Conclusion: The complex interplay between HRV, insomnia, and health outcomes necessitates further research. However, integrating HRV measurements into clinical and everyday monitoring may offer a promising avenue for improving sleep disorder management and enhancing quality of life.

Semantic representation and comparative analysis of physical activity sensor observations using MOX2-5 sensor in real and synthetic datasets: a proof-of-concept-study

The widespread use of devices like mobile phones and wearables allows for automatic monitoring of human daily activities, generating vast datasets that offer insights into long-term human behavior. A structured and controlled data collection process is essential to unlock the full potential of this information. While wearable sensors for physical activity monitoring have gained significant traction in healthcare, sports science, and fitness applications, securing diverse and comprehensive datasets for research and algorithm development poses a notable challenge. In this proof-of-concept study, we underscore the significance of semantic representation in enhancing data interoperability and facilitating advanced analytics for physical activity sensor observations. Our approach focuses on enhancing the usability of physical activity datasets by employing a medical-grade (CE certified) sensor to generate synthetic datasets. Additionally, we provide insights into ethical considerations related to synthetic datasets. The study conducts a comparative analysis between real and synthetic activity datasets, assessing their effectiveness in mitigating model bias and promoting fairness in predictive analysis. We have created an ontology for semantically representing observations from physical activity sensors and conducted predictive analysis on data collected using MOX2-5 activity sensors. Until now, there has been a lack of publicly available datasets for physical activity collected with MOX2-5 activity monitoring medical grade (CE certified) device. The MOX2-5 captures and transmits high-resolution data, including activity intensity, weight-bearing, sedentary, standing, low, moderate, and vigorous physical activity, as well as steps per minute. Our dataset consists of physical activity data collected from 16 adults (Male: 12; Female: 4) over a period of 30–45 days (approximately 1.5 months), yielding a relatively small volume of 539 records. To address this limitation, we employ various synthetic data generation methods, such as Gaussian Capula (GC), Conditional Tabular General Adversarial Network (CTGAN), and Tabular General Adversarial Network (TABGAN), to augment the dataset with synthetic data. For both the authentic and synthetic datasets, we have developed a Multilayer Perceptron (MLP) classification model for accurately classifying daily physical activity levels. The findings underscore the effectiveness of semantic ontology in semantic search, knowledge representation, data integration, reasoning, and capturing meaningful relationships between data. The analysis supports the hypothesis that the efficiency of predictive models improves as the volume of additional synthetic training data increases. Ontology and Generative AI hold the potential to expedite advancements in behavioral monitoring research. The data presented, encompassing both real MOX2-5 and its synthetic counterpart, serves as a valuable resource for developing robust methods in activity type classification. Furthermore, it opens avenues for exploration into research directions related to synthetic data, including model efficiency, detection of generated data, and considerations regarding data privacy.

Development of a Dog Health Score Using an Artificial Intelligence Disease Prediction Algorithm Based on Multifaceted Data.

Detecting aberrant behaviors in dogs or observing emotional interactions between a dog and its owner may serve as indicators of potential canine diseases. However, dog owners typically struggle to assess or predict the health status of their pets independently. Consequently, there is a demand for a methodology enabling owners to evaluate their dogs' health based on everyday behavioral data. To address this need, we gathered individual canine data, including three months of standard daily activities (such as scratching, licking, swallowing, and sleeping), to train an AI model. This model identifies abnormal behaviors and quantifies each behavior as a numerical score, termed the "Health Score". This score is categorized into ten levels, where a higher score indicates a healthier state. Scores below 5 warrant medical consultation, while those above 5 are deemed healthy. We validated the baseline value of the Health Score against veterinarian diagnoses, achieving an 87.5% concordance rate. This validation confirms the reliability of the Health Score, which assesses canine health through daily activity monitoring, and is expected to significantly benefit dog owners who face challenges in determining the health status of their pets.

A dynamically stable self-healable wire based on mechanical-electrical coupling.

The rise in wearable electronics has witnessed the advancement of self-healable wires, which are capable of recovering mechanical and electrical properties upon structural damage. However, their highly fluctuating electrical resistances in the range of hundreds to thousands of ohms under dynamic conditions such as bending, pressing, stretching and tremoring may seriously degrade the precision and continuity of the resulting electronic devices, thus severely hindering their wearable applications. Here, we report a new family of self-healable wires with high strengths and stable electrical conductivities under dynamic conditions, inspired by mechanical-electrical coupling of the myelinated axon in nature. Our self-healable wire based on mechanical-electrical coupling between the structural and conductive components has significantly improved the electrical stability under dynamic scenarios, enabling precise monitoring of human health status and daily activities, even in the case of limb tremors from simulated Parkinson's disease. Our mechanical-electrical coupling strategy opens a new avenue for the development of dynamically stable electrodes and devices toward real-world wearable applications.

Passive Radar Sensing for Human Activity Recognition: A Survey.

Continuous and unobtrusive monitoring of daily human activities in homes can potentially improve the quality of life and prolong independent living for the elderly and people with chronic diseases by recognizing normal daily activities and detecting gradual changes in their conditions. However, existing human activity recognition (HAR) solutions employ wearable and video-based sensors, which either require dedicated devices to be carried by the user or raise privacy concerns. Radar sensors enable non-intrusive long-term monitoring, while they can exploit existing communication systems, e.g., Wi-Fi, as illuminators of opportunity. This survey provides an overview of passive radar system architectures, signal processing techniques, feature extraction, and machine learning's role in HAR applications. Moreover, it points out challenges in wireless human activity sensing research like robustness, privacy, and multiple user activity sensing and suggests possible future directions, including the coexistence of sensing and communications and the construction of open datasets.

Fabrication of a tough, long-lasting adhesive hydrogel patch via the synergy of interfacial entanglement and adhesion group densification.

Adhesive hydrogels (AHs) are considered ideal materials for flexible sensors. However, the lack of effective energy dissipation networks and sparse surface polar groups in AHs lead to poor mechanical properties and interfacial adhesion, which limit their practical application. Herein, a tough, long-lasting adhesive and highly conductive nanocomposite hydrogel (PACPH) was fabricated via the synergy of interfacial entanglement and adhesion group densification. PACPH was obtained by the in situ polymerization of highly carboxylated cellulose nanocrystals (SCNCPA, surface pre-grafted polyacrylic acid chains, C-COOH = 11.5 mmol g-1) with the acrylic acid precursor. The unique tacticity of SCNCPA provides strong interface entanglement and multiple hydrogen bonds with the PACPH network, which further increases the energy dissipated during SCNCPA displacements, and enhances the mechanical properties of PACPH (tensile strength = 1.45 MPa, modulus = 332 kPa, and fracture toughness = 13.2 MJ m-3). Meanwhile, SCNCPA increases the density of surface polar groups in PAPCH and also acts as an anchor point to improve the adhesion strength (>2-3 times) of PACPH on various substrates. The combination of excellent mechanical, adhesive, and conductive properties of the PAPCH-integrated patches enables long-term monitoring of human daily activities and electrocardiogram (ECG) signals, verifying that PAPCH is a promising material platform for the further development of flexible sensors and other health management devices.

Graph Learning and Deep Neural Network Ensemble for Supporting Cognitive Decline Assessment

Cognitive decline represents a significant public health concern due to its severe implications on memory and general health. Early detection is crucial to initiate timely interventions and improve patient outcomes. However, traditional diagnosis methods often rely on personal interpretations or biases, may not detect the early stages of cognitive decline, or involve invasive screening procedures; thus, there is a growing interest in developing non-invasive methods benefiting also from the technological advances. Wearable devices and Internet of Things sensors can monitor various aspects of daily life together with health parameters and can provide valuable data regarding people’s behavior. In this paper, we propose a technical solution that can be useful for potentially supporting cognitive decline assessment in early stages, by employing advanced machine learning techniques for detecting higher activity fragmentation based on daily activity monitoring using wearable devices. Our approach also considers data coming from wellbeing assessment questionnaires that can offer other important insights about a monitored person. We use deep neural network models to capture complex, non-linear relationships in the daily activities data and graph learning for the structural wellbeing information in the questionnaire answers. The proposed solution is evaluated in a simulated environment on a large synthetic dataset, the results showing that our approach can offer an alternative as a support for early detection of cognitive decline during patient-assessment processes.

CASE STUDIES OF A SENOR-ENHANCED CARE COORDINATION MODEL TO ADDRESS OLDER ADULT HEALTH

Abstract Smart technologies hold enormous potential in the early detection of activity change that may indicate illness or functional decline among older adults. However, little research currently exists on the application of such technologies to community-dwelling older adults. Our program, Age-friendly Sustainable Smart and Equitable Technologies for Aging in Place (ASSETs for AIP) uses open-source smart home technologies and consumer-grade wearable devices to monitor community-dwelling older adults recently discharged from the Show-Me Home program. We employ a novel approach; pairing technology with a care coordination team, comprised of a registered nurse, occupational therapist, and a licensed social worker. This presentation will highlight the function of this team, and how they leverage sensor-generated health information to provide care coordination. Using a clinical interface that displays the sensor-generated health data, this team provides ongoing monitoring of daily activity to identify early changes in routine that may indicate the development of a health problem. As significant changes in health data present, our clinical team works with clients to understand the change and formulate a plan of action. For example, an unexplained spike in heart rate may lead the clinician to discuss recent activity, exertion, and potential modifications in routine for a client. An increase in middle-of-the night bathroom trips may indicate a health change, for the which the client will be coached in what to communicate to their provider. Case studies from our program will be discussed in this presentation, to highlight this model of sensor-enhanced care coordination.

Failure of Digital Device Performance in Monitoring Physical Exercise in a Pilot Study in Sedentary Persons with HIV.

Digital devices have gained popularity in the last 10 years as a tool for exercise prescription, the monitoring of daily physical activity, and nutrition for the management of a health-related parameter. Therefore, the aim of this study was to assess the effectiveness of the use of digital devices to monitor exercise data in sedentary persons with HIV who exercise following an individualized activity pacing (AP) protocol on cardiorespiratory fitness body composition, blood lipid profile, and psychological parameters. Twenty-four PLWH were enrolled in an 18-week randomized, open-label, pilot AP exercise protocol. All participants were monitored by a Health Band connected to a mobile app that transmitted the data to a server. At week 3, they were randomized either in an experimental group (EG), in which an open device configuration enabled them to receive training data feedback (n = 12), or continued with no data feedback (control group, n = 12). The primary endpoint was improvement from the baseline of 15% of steady-state oxygen consumption (V˙O2) during a 6-min walking test. Technical issues occurred when pairing the health band with the app, which prevented EG participants from regularly receiving data feedback, and with data transmission to the server, which enabled only 40% monitoring of the total training days. Consequently, the study outcomes could not be compared between the two groups, and participants also lost confidence in the study. However, 19 out of 24 participants completed the AP program. Overall, only 6 (32%) improved steady-state V˙O2, with no significant changes at W18 from the baseline. Significant reductions were observed of BMI (p = 0.040), hip circumference (p = 0.027), and total-(p = 0.049) and HDL-cholesterol (p = 0.045). The failure of digital device performance substantially affected study procedures, monitoring, and participants' engagement, and likely limited the potential benefits of the AP exercise program.

Associations between patient reported fatigue and remotely monitored activity in patients with prostate cancer receiving androgen deprivation therapy.

593 Background: Androgen deprivation therapy (ADT) is commonly used for the management of prostate cancer (PCa). Despite its benefits, ADT can lead to a range of side effects that have prominent determents on patient quality of life, specifically fatigue. Fatigue is a multidimensional symptom that influences a patient’s psychological and physical well-being, including the inability to perform daily activities due to lack of energy. This analysis evaluates associations between patient-reported fatigue and remotely monitored objective activity in PCa patients. Methods: This is a secondary analysis ofa multi-site observational cohort study (DigiPRO) among men diagnosed with advanced PCa, initiating ADT within 6 months, conducted between 12/2020 and 4/2023. Eligible patients wore an activity monitor (Fitbit Charge HR 4) continuously for the 12-week study and completed NIH PROMIS fatigue surveys via REDCap, which included Likert-scale questions (8 items, range 1-5 (worse)) about fatigue severity and interference, at baseline, 4, 8, and 12 weeks. PROMIS scores were converted to standardized T-scores (mean 50: SD: 10). Pearson correlation coefficients were calculated, and multivariable logistic regression models were fit to evaluate associations between activity and fatigue T-scores. Results: 40 patients were included in the analysis (median age: 70 yrs, range 51-85; 37% Black or African American/63% White, 10% Hispanic/90% non-Hispanic White). 11 patients reported high levels of fatigue (T-Score>60) at least once over the course of the study and 20% of patients experienced an increase > 5 T-score points from baseline, indicating clinically meaningful deterioration. Higher fatigue T-scores were negatively correlated with higher daily step counts (r=-0.6, p=0.003) and calories expended (r=-0.5, p=0.002) and positively correlated with increased sedentary time (r=0.5, p=0.002) at baseline. Lower baseline step counts were significantly associated with any occurrence of worsening patient fatigue over the study period (OR: 2.08, 95% CI 1.12-3.8, per 1000 step decrease, p=0.02) after adjusting for age and race. Patients who reported worsening fatigue had a mean step count of 3,426 compared to 5,664 steps/day among those who reported stable or improving fatigue (p=0.02). Conclusions: Findings from this analysis suggest that objective measures of daily activityare correlated with patient-reported fatigue and predict worsening fatigue over time. Routine collection and monitoring of patient-reported fatigue and daily activity during ADT may help identify patients at increased risk for worsening fatigue. More research is needed to determine the role of wearable activity monitors as potential interventions and for real time monitoring to help manage fatigue and other symptoms during ADT. Clinical trial information: NCT04575402 .

CIM: A Novel Clustering-based Energy-Efficient Data Imputation Method for Human Activity Recognition

Human activity recognition (HAR) is an important component in a number of health applications, including rehabilitation, Parkinson’s disease, daily activity monitoring, and fitness monitoring. State-of-the-art HAR approaches use multiple sensors on the body to accurately identify activities at runtime. These approaches typically assume that data from all sensors are available for runtime activity recognition. However, data from one or more sensors may be unavailable due to malfunction, energy constraints, or communication challenges between the sensors. Missing data can lead to significant degradation in the accuracy, thus affecting quality of service to users. A common approach for handling missing data is to train classifiers or sensor data recovery algorithms for each combination of missing sensors. However, this results in significant memory and energy overhead on resource-constrained wearable devices. In strong contrast to prior approaches, this paper presents a clustering-based approach (CIM) to impute missing data at runtime. We first define a set of possible clusters and representative data patterns for each sensor in HAR. Then, we create and store a mapping between clusters across sensors. At runtime, when data from a sensor are missing, we utilize the stored mapping table to obtain most likely cluster for the missing sensor. The representative window for the identified cluster is then used as imputation to perform activity classification. We also provide a method to obtain imputation-aware activity prediction sets to handle uncertainty in data when using imputation. Experiments on three HAR datasets show that CIM achieves accuracy within 10% of a baseline without missing data for one missing sensor when providing single activity labels. The accuracy gap drops to less than 1% with imputation-aware classification. Measurements on a low-power processor show that CIM achieves close to 100% energy savings compared to state-of-the-art generative approaches.

Daily Activity of Individuals With an Amputation Above the Knee as Recorded From the Nonamputated Limb and the Prosthetic Limb

Introduction: Mobility restriction following limb loss might lead to a sedentary lifestyle, impacting health. Daily activity monitoring of amputees has focused on prosthetic steps, neglecting overall activity. Purpose: To assess daily activity in individuals with an established amputation and to explore the amount of activity recorded from the prosthesis as compared to the overall activity. Methods: Individuals with a unilateral transfemoral amputation or knee disarticulation who had used a prosthesis in daily life for >1 year and could walk 100 m (unsupported or single aided) were recruited. Descriptive information and prosthetic mobility were collected. Two activPAL™ accelerometers were attached to the nonamputated thigh and the prosthesis, respectively. The mean daily activity over 7 days was compared between the nonamputated limb and the prosthesis. Results: Thirty-nine participants (22 men/17 women; mean age 54 [14.5] years) with amputation mainly due to trauma (59%) or tumor (28%) were included. Overall, participants took 6,125 steps and spent 10.2 hr sedentary, 5.0 hr upright, and 8.7 hr laying per day. Compared to recordings from the nonamputated limb, 85% of sit-to-stand transitions (32/38), 73% of steps (4,449/6,125), and 68% of walking time (1.0/1.5 hr) were recorded from the prosthesis. Recordings seemed to be less adequate for incidental prosthetic steps than for walks. Conclusions: Sedentary behavior accounted for most of the day demonstrating the importance to encourage physical activity among established prosthetic users. The prosthesis is used for daily activity to a great extent. However, noted pitfalls in the recordings call for further refinement of the measurements.

UNDERAGE CITIZENS MONITORING APPLICATIONS - A REVIEW OF THE STATE OF THE ART AND GUIDELINES FOR FUTURE IMPLEMENTATIONS

Children's safety is a constant concern, both for parents and the institutions in which they are entrusted with care. There are several dangers and situations that can jeopardize children's safety. It is, therefore, important to have constant monitoring and preventive monitoring. This need, together with the technological means available nowadays, opens the way to the development of applications that allow better safety and monitoring of children's daily activities. The aim is to keep parents informed about where their children are and if there is anything they should be worried about. In this context, an analysis of the state of the art was carried out to identify the functionalities currently available to users of applications with this purpose. Through this analysis, essential functionalities were identified, such as real-time location on the map, location history, marking of safe areas and sending alerts. On the other hand, technological advances in various areas mean that there is room and opportunity to add value to what already exists and to contribute to answering existing problems. Therefore, in this article, besides the state of the art previously mentioned, it is also presented implementation lines for new mobile applications that may be developed in the future. The contributions of this article are, on the one hand to present what currently exists in terms of mobile applications to support the monitoring of children and on the other to propose lines of new features that current technology can provide in new applications.

Daily physical activity monitoring in older adults with metastatic prostate cancer on active treatment: Feasibility and associations with toxicity

IntroductionPhysical activity may be associated with cancer treatment toxicity, but generalizability to geriatric oncology is unclear. As many older adults have low levels of physical activity and technology use, this area needs further exploration. We evaluated the feasibility of daily step count monitoring and the association between step counts and treatment-emergent symptoms. Materials and MethodsAdults aged 65+ starting treatment (chemotherapy, enzalutamide/abiraterone, or radium-223) for metastatic prostate cancer were enrolled in a prospective cohort study. Participants reported step counts (measured via smartphone) and symptoms (Edmonton Symptom Assessment Scale) daily for one treatment cycle (i.e., 3–4 weeks). Embedded semi-structured interviews were performed upon completion of the study. The feasibility of daily monitoring was evaluated with descriptive statistics and thematic analysis. The predictive validity of a decline in daily steps (compared to pre-treatment baseline) for the emergence of symptoms was examined using sensitivity and positive predictive value (PPV). Associations between a 15% decline in steps and the emergence of moderate (4–6/10) to severe (7–10/10) symptoms and pain in the next 24 h were assessed using logistic regression. ResultsOf 90 participants, 47 engaged in step count monitoring (median age = 75, range = 65–88; 52.2% participation rate). Daily physical activity monitoring was found to be feasible (94% retention rate; 90.5% median response rate) with multiple patient-reported benefits including increased self-awareness and motivation to engage in physical activity. During the first treatment cycle, instances of a 15% decline in steps were common (n = 37, 78.7%), as was the emergence of moderate to severe symptoms overall (n = 40, 85.1%) and pain (n = 26, 55.3%). The predictive validity of a 15% decline in steps on the emergence of moderate to severe symptoms was good (sensitivity = 81.8%, 95% confidence interval [CI] = 68.7–95.0; PPV = 73.0%, 95% CI = 58.7–87.3), although the PPV for pain was poor (sensitivity = 77.8%, 95% CI = 58.6–97.0; PPV = 37.8%, 95% CI = 22.2–53.5). In the regression models, changes in daily physical activity were not associated with symptoms or pain. DiscussionChanges in physical activity had modest ability to predict moderate to severe symptoms overall. Although participation was suboptimal, daily activity monitoring in older adults with cancer appears feasible and may have other uses such as improving physical activity levels. Further studies are warranted.

Feasibility of daily physical activity monitoring and associations with treatment toxicity in older adults with metastatic prostate cancer.

12055 Background: Accelerometry research suggests physical activity may be associated with treatment toxicity, but generalizability to geriatric oncology is unclear. As many older adults have low levels of physical activity and technology use, further exploration is warranted. This study explores the feasibility of daily physical activity monitoring and the association between step counts and symptoms. Methods: Older adults aged 65+ starting treatment (chemotherapy, enzalutamide/abiraterone, or Radium-223) for metastatic prostate cancer were enrolled in a prospective cohort study. Participants reported step counts (measured via smartphone and a free commercial app) and symptoms (Edmonton Symptom Assessment Scale (ESAS)) daily for their first treatment cycle (~1 month). The feasibility of daily monitoring was assessed with descriptive statistics and thematic analysis. The association between a 15% decline in steps (compared to pre-treatment baseline) and the emergence of moderate-to-severe symptoms and pain (ESAS ≥4) in the next 24 hours was assessed using logistic regression. The utility of a 15% step count decline in predicting the development of moderate-to-severe symptoms and pain was evaluated using sensitivity and positive predictive value (PPV). Results: Of 90 participants, 47 engaged in step count monitoring (mean age 75y; 52.2% participation rate). Daily physical activity monitoring was found to be feasible (90.5% median response rate; 94% retention rate) with numerous patient-reported benefits including increased self-awareness and motivation to engage in physical activity. During the first treatment cycle, instances of a 15% decline in steps were common (n=37, 78.7%), as was the emergence of moderate-to-severe symptoms overall (n=40, 85.1%) and pain (n=26, 55.3%). Overall, daily physical activity did not appear to be significantly predictive of symptoms (OR=1.8, 95% CI=0.42-7.74) overall or pain (OR=0.95, 95% CI=0.22-3.81). Predictive validity estimates revealed reasonable sensitivity for both moderate to severe symptoms overall (sensitivity=88.8%, 95% CI=68.7-95.0; PPV=73.0%, 95% CI=58.7-87.3) but poor PPV for pain (sensitivity=77.8%, 95% CI=58.6-97.0; PPV=37.8%, 95% CI=22.2-53.5). Conclusions: Despite recent studies framing physical activity changes as predictive of toxicity, PPV was only poor to fair. However, daily activity monitoring in older cancer patients appears feasible and may have other uses. Clinical trial information: NCT04193657 .

Real-time monitoring of honeybee colony daily activity and bee loss rates can highlight the risk posed by a pesticide

Information on honeybee foraging performance and especially bee loss rates at the colony level are crucial for evaluating the magnitude of effects due to pesticide exposure, thereby ensuring that protection goals for honeybee colonies are met (i.e. threshold of acceptable effects). However, current methods for monitoring honeybee foraging activity and mortality are very approximate (visual records) or are time-limited and mostly based on single cohort analysis. We therefore assess the potential of bee counters, that enable a colony-level and continuous monitoring of bee flight activity and mortality, in pesticide risk assessment.After assessing the background activity and bee loss rates, we exposed colonies to two concentrations of sulfoxaflor (a neurotoxic insecticide) in sugar syrup: a concentration that was considered to be field realistic (0.59 μg/ml) and a higher concentration (2.36 μg/ml) representing a worst-case exposure scenario. We did not find any effect of the field-realistic concentration on flight activity and bee loss rates. However, a two-fold decrease in daily flight activity and a 10-fold increase in daily bee losses were detected in colonies exposed to the highest sulfoxaflor concentration as compared to before exposure. When compared to the theoretical trigger values associated with the specific protection goal of 7 % colony-size reduction, the observed fold changes in daily bee losses were often found to be at risk for colonies. In conclusion, the real-time and colony-level monitoring of bee loss rates, combined with threshold values indicating at which levels bee loss rates threaten the colony, have great potential for improving regulatory pesticide risk assessments for honeybees under field conditions.

149 Case Study: The Impact of a Fogging System on Dairy Cow Comfort in Cows Housed in a Barn with Tunnel Ventilation and an Automatic Milking System

Abstract Fogging systems control microclimatic parameters of barns to provide immediate cooling to dairy cows during heat stress conditions. However, the benefits of implementing a fogging system to cow comfort behaviors have not been thoroughly investigated in lactating cows. Therefore, the objective of this case study was to evaluate cow comfort behaviors and milk productivity in cows managed in a tunnel-ventilated barn in a commercial dairy farm that uses an automatic milk system. Sixty Holstein lactating dairy cows (45-90 days in milk; DIM) were monitored and housed in group pens (6 pens; n = 10 cows/pen). Four weeks before the fogging system installation, cows had pedometers (IceQube, IceRobotics, Inc., United Kingdom) and SCR rumination collars (SCR by Allflex; Israel) placed for continuous daily activity and rumination levels monitoring, respectively. Productivity information was acquired using automatic robotic milking technology (Lely Astronaut A5; Iowa, United States), and all variables were measured until four weeks after fogger system installation. Activity behavior (lying duration, daily step count, and number of transitions) and productivity (daily milk yield and milk speed) were evaluated before (PRE; 20-day pre-installation period), during (DURING; 2-day period), and after fogger installation (POST; 35-day post-installation period). Data were analyzed using PROC GLM in SAS 9.4 with cow as the experimental unit and temperature-humidity index (THI) included in the model as a covariate. Overall, cows spent more time lying (P < 0.01) in the POST period versus PRE and DURING. Cows performed fewer daily transitions between lying and standing (P < 0.01) in the POST versus PRE period, but no differences were detected (P = 0.67) among the step counts observed PRE, DURING, and POST fogger installation. Average milk speed and average milk yield were decreased (P < 0.01) in the POST period compared with the PRE and DURING periods. Temperature-humidity index significantly influenced (P < 0.01) lying time but did not have an effect on any other variables measured. In summary, installation of a fogger system in a commercial tunnel-ventilated barn improved cow comfort behaviors in lactating cows managed with an automated robotic milking system but did not offer immediate production performance benefits.

Assessing Physical Activity Levels among Chinese College Students by BMI, HR, and Multi-Sensor Activity Monitors.

In a laboratory experiment, 100 college students, 18-25 years old, wore the SenseWear Pro3 Armband™ (SWA; BodyMedia, Inc., Pittsburg, PA, USA) and performed 7 different physical activities. EE was measured by indirect calorimetry, while body motion and accelerations were measured with an SWA accelerometer. Special attention was paid to the analysis of unidirectional and three-directional accelerometer output. Seven physical activities were recorded and distinguished by SWA, and different physical activities demonstrated different data features. The mean values of acceleration ACz (longitudinal accel point, axis Z) and VM (vector magnitude) were significantly different (p = 0.000, p < 0.05) for different physical activities, whereas no significant difference was found in one single physical activity with varied speeds (p = 0.9486, p > 0.05). When all physical activities were included in a correlation regression analysis, a strong linear correlation between the EE and accelerometer reporting value was found. According to the correlation analysis, sex, BMI, HR, ACz, and VM were independent variables, and the EE algorithm model demonstrated a high correlation coefficient R2 value of 0.7. The predictive energy consumption model of physical activity based on multi-sensor physical activity monitors, BMI, and HR demonstrated high accuracy and can be applied to daily physical activity monitoring among Chinese collegiate students.

SEMG Signal-Based Lower Limb Movements Recognition Using Tunable Q-Factor Wavelet Transform and Kraskov Entropy

BackgroundThe recognition of lower limb movement has a wide range of applications in rehabilitation training, wearable exoskeleton control, and human activity monitoring. Surface electromyography (sEMG) signals can directly reflect the intention of human movement and can be used as the source of lower limb movement recognition. Literature reports have shown that extracting features from sEMG signals is the core of human movement recognition based on sEMG signals. However, how to effectively extract features from the sEMG signal of the lower limbs affected by body gravity is a difficult problem for the recognition of lower limb movement based on the sEMG signal. ObjectivesThe main objective of this paper is to propose an efficient lower limb movement recognition model based on sEMG signals to accurately recognize the four lower limb movements. Methods and resultsWe proposed a novel method of lower limbs movements recognition based on tunable Q-factor wavelet transform (TQWT) and Kraskov entropy (KrEn). Firstly, the sEMG signals of four different lower limb movements from twenty subjects were recorded by seven wearable sEMG signal sensors, and the recorded sEMG signals were denoised by multi-scale principal component analysis (MSPCA). Then, the denoised sEMG signal is decomposed into multiple sub-band signals by TQWT and the KrEn feature is extracted from each sub-band signal. Next, the representative features are selected from the extracted KrEn features by the minimum redundancy maximum relevance (mRMR) feature selection method. Finally, the four lower limb movements are recognized by three machine learning classifiers. Besides, to improve the recognition performance, a majority voting (MV) technology is proposed for the post-processing of decision flow. Experimental results show that the combination of TQWT, KrEn, and MV technology achieved the average recognition accuracy of 98.42% using the linear discriminant analysis (LDA) classifier. ConclusionThe method proposed in this paper can recognize lower limb movements with high accuracy. Compared with existing methods, this method is more advanced and accurate, indicating that it has great application potential in rehabilitation training, wearable exoskeleton control, and daily activity monitoring.