Monitor Stress Levels Research Articles

Investigating the biological relevance of measuring gastrointestinal cortisol metabolite levels to assess stress responses in Atlantic salmon (Salmo salar L.) after an acute stress

Monitoring stress levels of farmed Atlantic salmon (Salmo salar) is important to ensure fish welfare and optimize farm operations. Feces could be a promising matrix for assessing stress responses in fish, based on their properties of low-invasive sampling and allowing repeated sampling over time. Meanwhile, elevated levels of cortisol metabolites (CMs) in feces indicate the increases in plasma cortisol levels (PLA) after exposure to acute stress. However, the dynamics of fecal CMs following acute stress in Atlantic salmon remain unclear. In this study, a confinement stress involving chasing and crowding was conducted to investigate the responses of gastrointestinal CMs to an acute stressor in Atlantic salmon. The post-smolts, with an average weight of 155.21 g, were sampled before and at 30 min, 1.5, 6, 12, 18, 24, 36, and 48 h after the onset of stress. Blood and gastrointestinal contents from the stomach, proximal intestine, and distal intestine of each fish were collected and subsequently analyzed, using competitive enzyme-linked immunosorbent assay (ELISA). The results demonstrated that the pre-stress level of PLA was low (4.28 ± 6.13 ng/ml) and reached a peak within 30 min following stress. The levels of CMs in gastrointestinal contents from stomach (SCMs), proximal intestine (PCMs), and distal intestine (DCMs) in pre-stress group were 0.82 ± 0.50, 18.31 ± 6.14 and 16.04 ± 6.69 ng/g, respectively. Gastrointestinal CMs increased significantly within 30 min and the peak levels of SCMs (3.51 ± 3.75 ng/g), PCMs (68.19 ± 23.71 ng/g) and DCMs (65.67 ± 23.37 ng/g) were found at 1.5 h post-stress. The significant increases in PCMs and DCMs post-stress validate the biological relevance of measuring intestinal CMs for assessing acute stress responses in Atlantic salmon. No significant difference was noted between PCMs and DCMs across all samples, suggesting that intestinal contents can serve as a suitable matrix compared with feces when measuring the responses of CMs to acute stress. The time lag between the peak of PLA levels and their reflection in the intestinal contents exceeded 1 h, indicating that using intestinal contents as a matrix to assess stress levels in fish can extend and delay the sampling window. This study highlights valuable guidance for determining the optimal times to utilize intestinal contents for measuring stress responses, providing further insights into the dynamics of fecal CM following acute stress.

Wireless-based portable device heart rate measurement as biomedical devices for stress detection

Stress can increase the heart rate, causing dangerous conditions that cause significant harm and even death. Therefore, managing stress well to control the heart rate is vital. Monitoring stress levels using biomedical devices is essential to prevent further damage to the individual. Regular monitoring facilitates the acquisition of individual stress levels through heart rate information. In this research, a MAX30100 sensor can produce Beats Per Minute (BPM) data, which show the stress experienced by a person during four daily activities (sitting, walking, running, and sleeping) and when watching a horror movie. This research underscores the potential of cost-effective wireless solutions to increase portability and facilitate real-time monitoring and remote surveillance. The researchers introduced an innovative methodology by reusing everyday consumer devices, initially intended for routine activities, to measure stress levels in a unique context—precisely in a controlled experiment involving a movie-watching scenario. The ultimate achievement of this research was creating a stationary heart rate monitoring device that is easy to access, easy to use, space-saving, and adept at effectively tracking stress indicators. BPM readings obtained from the MAX30100 sensor have scores similar to those obtained from the heart rate app. The researchers proposed the inclusion of other sensors, such as a photoplethysmograph, an electrocardiogram, and galvanic skin response, to provide a more holistic assessment of stress. Leveraging cloud technology for data storage enables long-term monitoring and in-depth analysis of stress patterns over time.

Techno Medcare Glucose and Health Monitoring System Using IOT

Monitoring vital signs and stress levels plays a pivotal role in healthcare, yet challenges such as limited access to medical professionals, high consultation expenses, and infrastructure upkeep pose barriers to widespread monitoring. This paper proposes a streamlined solution by introducing an electronic health wearable capable of monitoring vital signs and glucose levels through IR sensors, alongside a stress monitoring headband. Additionally, the system integrates reminders for sedentary behavior and hydration, and features fall detection mechanisms using vibration motors and gyro sensors. To bolster accessibility, individuals can consult healthcare professionals via chat and video calls to review their health metrics. Moreover, appointments with doctors can be conveniently pre-scheduled, reducing consultation expenses and circumventing the need for extensive medical infrastructure. This approach offers a promising avenue for efficient and economical monitoring of vital signs and stress levels, thereby enhancing healthcare accessibility.

A Deep Learning-Based Platform for Workers' Stress Detection Using Minimally Intrusive Multisensory Devices.

The advent of Industry 4.0 necessitates substantial interaction between humans and machines, presenting new challenges when it comes to evaluating the stress levels of workers who operate in increasingly intricate work environments. Undoubtedly, work-related stress exerts a significant influence on individuals' overall stress levels, leading to enduring health issues and adverse impacts on their quality of life. Although psychological questionnaires have traditionally been employed to assess stress, they lack the capability to monitor stress levels in real-time or on an ongoing basis, thus making it arduous to identify the causes and demanding aspects of work. To surmount this limitation, an effective solution lies in the analysis of physiological signals that can be continuously measured through wearable or ambient sensors. Previous studies in this field have mainly focused on stress assessment through intrusive wearable systems susceptible to noise and artifacts that degrade performance. One of our recently published papers presented a wearable and ambient hardware-software platform that is minimally intrusive, able to detect human stress without hindering normal work activities, and slightly susceptible to artifacts due to movements. A limitation of this system is its not very high performance in terms of the accuracy of detecting multiple stress levels; therefore, in this work, the focus was on improving the software performance of the platform, using a deep learning approach. To this purpose, three neural networks were implemented, and the best performance was achieved by the 1D-convolutional neural network with an accuracy of 95.38% for the identification of two levels of stress, which is a significant improvement over those obtained previously.

Stress Detection in It Professionals by Image Processing and Machine Learning

Abstract: The project aims to leverage image processing and machine learning techniques for the detection of stress in IT professionals. The primary focus is on monitoring the emotional well-being of individuals who spend extended periods working in front of a computer, with the goal of identifying and alleviating stress to create a more conducive work environment. Key objectives include predicting stress based on observed symptoms, assessing stress levels in employees, and delivering pertinent information. Previous research in stress detection for IT professionals has employed machine learning and image processing, prioritizing secure monitoring through captured images of authenticated users. These systems analyze stress levels using standard conversion and image processing methods, incorporating live detection and periodic analysis. In contrast to earlier systems, they provide personalized counseling and solutions for managing both physical and mental stress levels, integrating surveys for regular assessments. Furthermore, existing systems may incorporate digital signal processing, taking into account factors such as Galvanic skin response, blood volume, pupil dilation, and skin temperature. Alternatively, they may rely on a variety of physiological signals and visual features to monitor stress levels during work.

402 Awardee Talk: Stress-Induced Dna Methylation Changes and Their Implications in Livestock Production

Abstract It is well known that pre- and post-natal stressors can impact livestock phenotype and performance. However, less is known about the molecular mechanisms responsible for the changes observed in individuals exposed to stress. A proposed mechanism is epigenetic modifications, such as DNA methylation (DNAm). Epigenetic marks are considered a bridge between the environment and genetics because the marks shift in response to environmental stimuli. Stress induced alterations of DNAm can result in changes in gene expression which could be the driver behind altered phenotype. “Omic” technologies have allowed the study of how DNAm patterns change in response to stressors in livestock species. Stressors such as weaning, transportation, and heat stress have altered DNAm patterns. These changes in methylation patterns have been associated with changes in immune function, growth, and behavior. Prenatal stressors have also modified DNAm patterns within the offspring, with some differences persisting later in life. These stress induced DNAm alterations can be transgenerational, potentially affecting livestock productivity and health over multiple generations. Not all alterations are negative; certain stress-induced modifications could allow animals to adapt better to stressors and changing conditions. These marks may indicate exposure of the animal to stress and the possible long-term effects on productivity. There is potential for using methylation patterns as a noninvasive way to monitor stress levels and assess animal welfare. Understanding how the methylome responds to stressors and how it contributes to performance will be beneficial for future selection decisions. More research is needed to identify management practices that might mitigate the negative impacts of stress induced DNAm changes and how the industry can take advantage of the role DNAm has in adapting to stressors and new environments. The epigenome will likely play a critical role in the livestock industry's future as the climate shifts and consumer demands focus more on animal welfare.

Real-time stress detection and monitoring system using IoT-based physiological signals

Currently, medical experts use psychophysiological questionnaires to evaluate human stress levels during counseling or interviews. Typically, biochemical samples use urine, saliva, and blood samples to identify the effects of stress on the human body. This research explains that stress detection can be done by analyzing psychological signals and the importance of monitoring stress levels. The authors develop research on stress detection based on psychological signals. The system then processes the recorded data; the android application displays the calculation results. The database can also be accessed as a spreadsheet via a web application. The design of real-time stress detection and monitoring using internet of things (IoT) can work well.

The Impact of Smartwatch on Health and Fitness

The introduction of smartwatches has brought about a new era of health monitoring and management. These wearable devices have numerous sensors and features that enable users to track various health metrics, including heart rate, steps taken, sleep quality, and even stress levels. Smartwatches are changing the way people approach their health and wellness by providing real-time feedback and personalized insights. The impact of smartwatches on health has been significant. These devices have enabled users to take a proactive approach to their health by giving them access to a wealth of information about their bodies. Smartwatches can track and analyze data over time, providing users with insights into their health that they may not have been aware of before. For example, a smartwatch can alert users if their heart rate is consistently elevated or they are not getting enough sleep. One of the primary benefits of smartwatches is their ability to motivate users to be more active. With features such as step tracking and activity reminders, smartwatches encourage users to move more throughout the day. This increased activity can lead to a wide range of health benefits, including weight loss, improved cardiovascular health, and reduced risk of chronic diseases. Smartwatches can also help users manage their stress levels. Many devices come equipped with stress-tracking features that use sensors to measure changes in heart rate variability and other physiological indicators. By monitoring stress levels, users can identify triggers and take steps to reduce stress before it becomes overwhelming. Smartwatches are also having a significant impact on healthcare providers. With access to real-time health data, doctors can monitor their patients remotely and make more informed decisions about their care. This can lead to improved outcomes and reduced healthcare costs. However, there are also some concerns about the impact of smartwatches on health. Some experts worry that constant tracking and monitoring could lead to an unhealthy fixation on health metrics. Additionally, there are concerns about data privacy and security, particularly with the large amount of personal health data that these devices collect. In conclusion, smartwatches profoundly impact health by enabling users to take a proactive approach to their well-being. These devices have numerous benefits, including increased activity, stress management, and improved medication management. With the ability to monitor health data in real time, smartwatches are also transforming the healthcare industry. However, it is essential to address concerns about privacy and ensure that users do not become overly fixated on health metrics.

Skin Cortisol and Acoustic Activity: Potential Tools to Evaluate Stress and Welfare in Captive Cetaceans.

As people's focus broadens from animals on farms to zoos and aquaria, the field of welfare science and the public's concern for animal welfare continue to grow. In captive animals, stress and its causes are topics of interest in welfare issues, and the identification of an objective method that can be used to assess animals' stress as a physiological state is essential. Both behavioral and physiological parameters can be used as indicators in order to assess animal stress quantitatively. To validate this approach, acoustic activity and the sloughed scrape skin cortisol concentration were used to evaluate the animal welfare of captive beluga whales (Delphinapterus leucas). The acoustic activity (5 min at 10:00 am) of three captive D. leucas was routinely recorded by a transducer and analyzed using audio editing software. The calls were separated into three main categories: whistles, pulses, and combo calls. The sloughed scrape skin samples were collected non-invasively once a week from all three animals' fluke and/or flipper. Cortisol was extracted using a modified skin steroid extraction technique, and detected via commercially available enzyme immunoassays. The results showed that the cortisol concentration increased by varying levels when the whales encountered the same event. In addition, the number and distribution of the calls changed along with the events. This indicated that the changes in the cortisol concentration and acoustic behavior may have reflected the fluctuations in the environment and body condition. Therefore, the scrape cortisol measurement and acoustic recordings could be used to monitor stress levels in captive beluga whales. We recommend that aquaria consider incorporating skin scrape cortisol and acoustic activity monitoring into their standards for animal welfare.

Designing a Stress and Anxiety Support Tool to Help Young Adults with Autism in Daily Living

Abstract Individuals with autism may experience higher stress and anxiety levels for longer periods than their neurotypical peers. Traditional techniques to provide stress relief and anxiety management include support, which reminds people of how to face stressful situations. Some technological proposals supporting the user include strategies for detecting and monitoring stress levels. In this research, we conducted an iterative user-centered study aiming to understand how young adults with autism deal with stress in real-life situations. We proposed a set of five design principles that will serve as guidelines to develop assistive anxiety management technology for individuals with autism. We then developed a set of low-fi prototypes and selected SATORI, a support tool composed of three interfaces, to help young adults with autism autonomously manage the anxiety caused by stressful situations in their daily life. We evaluated our proposed design principles using SATORI with eight young adults with autism. The results show a positive perception of the design principles on what SATORI is based on, as participants perceived that SATORI could help them in their daily life to manage stress and channel anxiety.

Monitoring of Cortisol Levels in Hog Deer with Varying Environment Exposure

Hog deer (Axis porcinus) is one of the least studied animal species in Pakistan. It belongs to Order Artiodactyla and the family Cervidae. IUCN classified Axis porcinus as an endangered species in 2008. The present study was conducted to investigate the effects of varying environmental exposure, genders, and seasonal changes on captive hog deer (A. porcinus) at Lahore Zoo, Safari Zoo, and Jallo Park in Lahore, Pakistan. Non-invasive techniques were used to monitor stress levels in hog deer. For sample collection, four definite months belonging to two seasons’ winter and summer were considered. A total of 48 urine and faecal samples were collected from both male and female hog deer. Seasonal fluctuations have been found to have a significant impact on faecal and urinary cortisol levels. Higher cortisol levels were found in both male and female hog deer in the summer season at all three visited sites. Fluctuations in environmental exposure at three research sites had a significant impact on faecal and urinary cortisol levels. Higher levels of cortisol were found in both male and female hog deer at Jallo park and Lahore Zoo, as compared to Safari Zoo. It was concluded that lower cortisol levels at Safari Zoo might be due to better environmental conditions and more flexible enclosure size and interaction of various species of deer. Temperature affected hog deer cortisol levels in summer, as higher levels were measured in summer compared to winter. In addition, sex did not predict any stress levels in hog deer. It has been suggested that a large enclosure size can control levels of cortisol in hog deer.

Restraint Stress Delays the Recovery of Neurological Impairments and Exacerbates Brain Damages through Activating Endoplasmic Reticulum Stress-mediated Neurodegeneration/Autophagy/Apopotosis post Moderate Traumatic Brain Injury.

Based on accumulating evidence, patients recovering from mild and moderate traumatic brain injury (TBI) often experience increased sensitivity to stressful events. However, few studies have assessed on the effects and pathophysiological mechanisms of stress on TBI. In the current study, using a mouse model of moderate TBI, we investigated whether restraint stress (RS) regulates secondary neurodegeneration and neuronal cell death, which are commonly associated with neurological dysfunctions. Our data showed that RS significantly reduced body weight recovery, delayed the recovery of neurological functions (motor function, cognitive function and anxiety-like behavior) and exacerbated the brain lesion volume after moderate TBI. Immunofluorescence results indicated that moderate TBI-induced cell insults and blood-brain barrier leakage were aggravated by RS. Further Western blotting experiments showed that RS activated endoplasmic reticulum (ER) stress excessively after moderate TBI and decreased the number of NeuN-positive cells, but increased the number of CHOP/NeuN-co-positive cells by performing immunostaining in the injured cortex after moderate TBI. Moreover, RS increased the ratios of CHOP/Aβ and CHOP/p-Tau co-positive cells in the injured cortex after moderate TBI. However, blocking ER stress with the classic ER stress inhibitor salubrinal remarkably decreased apoptosis and the levels of autophagy-related proteins in the mouse model of moderate TBI plus RS. Collectively, RS delays the recovery of neurological function and deteriorates morphological damage by excessively activating ER stress-mediated neurodegeneration, apoptosis and autophagy after moderate TBI. Thus, monitoring stress levels in patients recovering from non-severe TBI may merit consideration in the future.

On-Line Control of Stresses in the Power Unit Pressure Elements Taking Account of Variable Heat Transfer Conditions

Coal-fired power units, now balancing power shortages in the power system, must be characterised by increasingly higher flexibility of operation. This means faster start-ups and the capacity for frequent decreases and increases in the power output. These processes cause large temperature gradients in elements of the power unit and the turbine and lead to an increase in the stress level. At such an operating regime it is impossible to ensure safety based on start-up characteristics only—it becomes necessary to constantly monitor stress levels in critical areas of machinery and equipment elements. The stress level in turbine elements can be monitored on-line using algorithms based on Green’s functions and Duhamel’s integral. This paper presents examples of modifications of stress calculations in turbine valves and casings during start-ups. By modifying basic algorithms, it is possible to take into account the impact of the variability of heat transfer coefficients on the thermal stress level. Additionally, individual Green’s functions and correction factors were determined for specific stages of start-ups. Due to modifications, it is possible to obtain satisfactory agreement with the results obtained from FEM-based calculations for the entire heating process. Equations are also given that enable estimation of values of the heat transfer coefficient in turbine valves. The proposed modification of the algorithm will substantially improve the accuracy of stress modelling in transient states of the turbine operation. On-line stress monitoring will enable an increase in the flexibility of the power unit operation and facilitate operational control, ensuring safety of individual elements at the same time. The stress values calculated in the on-line mode can also be used to estimate fatigue life consumption and forecast the residual lifetime of individual components.

Grip Force on Steering Wheel as a Measure of Stress.

Driver performance is crucial for road safety. There is a relationship between performance and stress such that too high or too low stress levels (usually characterized by stressful or careless driving, respectively) impair driving quality. Therefore, monitoring stress levels can improve the overall performance of drivers by providing either an alert or intervention when stress levels are sub-optimal. Commonly used stress measures suffer from several shortcomings, such as time delays in indication and invasiveness of sensors. Grip force is a relatively new measure that shows promising results in measuring stress during psychomotor tasks. In driving, grip force sensor is non-invasive and transparent to the end user as drivers must continuously grip the steering wheel. The aim of the current research is to examine whether grip force can be used as a useful measure of stress in driving tasks. Twenty-one participants took part in a field experiment in which they were required to brake the vehicle in various intensities. The effects of the braking intensity on grip force, heart rate, and heart rate variability were analyzed. The results indicate a significant correlation between these three parameters. These results provide initial evidence that grip force can be used to measure stress in driving tasks. These findings may have several applications in the field of stress and driving research as well as in the vehicle safety domain.

Rapid Screening of Glucocorticoid Receptor (GR) Effectors Using Cortisol-Detecting Sensor Cells.

Cortisol, a stress hormone, plays key roles in mediating stress and anti-inflammatory responses. As abnormal cortisol levels can induce various adverse effects, screening cortisol and cortisol analogues is important for monitoring stress levels and for identifying drug candidates. A novel cell-based sensing system was adopted for rapid screening of cortisol and its functional analogues under complex cellular regulation. We used glucocorticoid receptor (GR) fused to a split intein which reconstituted with the counterpart to trigger conditional protein splicing (CPS) in the presence of targets. CPS generates functional signal peptides which promptly translocate the fluorescent cargo. The sensor cells exhibited exceptional performance in discriminating between the functional and structural analogues of cortisol with improved sensitivity. Essential oil extracts with stress relief activity were screened using the sensor cells to identify GR effectors. The sensor cells responded to peppermint oil, and L-limonene and L-menthol were identified as potential GR effectors from the major components of peppermint oil. Further analysis indicated L-limonene as a selective GR agonist (SEGRA) which is a potential anti-inflammatory agent as it attenuates proinflammatory responses without causing notable adverse effects of GR agonists.

AI inspired EEG-based spatial feature selection method using multivariate empirical mode decomposition for emotion classification.

Classification of human emotions based on electroencephalography (EEG) is a very popular topic nowadays in the provision of human health care and well-being. Fast and effective emotion recognition can play an important role in understanding a patient’s emotions and in monitoring stress levels in real-time. Due to the noisy and non-linear nature of the EEG signal, it is still difficult to understand emotions and can generate large feature vectors. In this article, we have proposed an efficient spatial feature extraction and feature selection method with a short processing time. The raw EEG signal is first divided into a smaller set of eigenmode functions called (IMF) using the empirical model-based decomposition proposed in our work, known as intensive multivariate empirical mode decomposition (iMEMD). The Spatio-temporal analysis is performed with Complex Continuous Wavelet Transform (CCWT) to collect all the information in the time and frequency domains. The multiple model extraction method uses three deep neural networks (DNNs) to extract features and dissect them together to have a combined feature vector. To overcome the computational curse, we propose a method of differential entropy and mutual information, which further reduces feature size by selecting high-quality features and pooling the k-means results to produce less dimensional qualitative feature vectors. The system seems complex, but once the network is trained with this model, real-time application testing and validation with good classification performance is fast. The proposed method for selecting attributes for benchmarking is validated with two publicly available data sets, SEED, and DEAP. This method is less expensive to calculate than more modern sentiment recognition methods, provides real-time sentiment analysis, and offers good classification accuracy.

Survey to Assess Perceived Causes of Stress, Its Manifestations and Coping Strategies Among Dental College Students in Maharashtra During COVID-19 Lockdown

Various studies across the globe have emphasized the importance of monitoring stress levels among students pursuing professional courses, especially medical and dental students. The pandemic caused by the novel Corona virus affected the lives of people and economies of almost all nations in a manner no one could have ever fathomed. Unexpected and unprecedented changes have occurred in the way we work, study, interact, travel and many aspects of the way we humans lead our lives.The period of lockdown was a difficult period for everyone, more so for the youth, as they were forced to remain indoors, now no longer being able to physically interact with their friends,go to college, visit malls, socialize, pursue pass-times and hobbies or generally have a life that the younger generation is used to.Academic activities initially came to a standstill before shifting to online mode which was new to both, teachers and students. The objective of the current questionnaire-based study was to find out the perceived stress levels during the COVID-19 lockdown among the students and how capable they think they are to cope with these testing times. This survey was undertaken among the students from first to final year of a dental college in Nasik, Maharashtra in the first phase of lockdown in India from 22 Mar 2020 to 14 April 2020. A pretested self-administered questionnaire using Google forms was used for the data collection after getting approval from the Institutional Ethical Committee. Students from all the four years reported being stressed and academic factors were one of the most important stressors. During the lockdown, portion completion, delay in academic activities, uncertainties of the disease and the impending exams were the main causes of anxiety and stress. Continuous student engagement during the period and the availability of a staff to discuss and talk out a problem helped in a big way.It is suggested that mental health of college students should be monitored during such unusual circumstances as the pandemic. The introduction of stress management education into the curriculum could prove useful to the students to help them deal with any such situation in the future.

Advance control strategies using image processing, UAV and AI in agriculture: a review

PurposeThe purpose of this paper is to provide an overview of smart agriculture systems and monitor and identify the technologies which can be used for deriving traditional agriculture system to modern agriculture system. It also provides the reader a broad area to work for the advancement in the field of agriculture and also explains the use of advanced technologies such as spectral imaging, robotics and artificial intelligence (AI) in the field of agriculture.Design/methodology/approachSmart uses of modern technologies were reviewed in the field of agriculture, which helps to monitor stress levels of plants and perform operations according to requirements. Operations can be irrigation, pests spray, monitoring crops, monitoring yield production, etc. Based on the literature review, a smart agriculture system is suggested. The parameters studied were spectral image processing, AI, unmanned aerial vehicle (UAVs) (fixed and rotatory), water or soil moisture, nutrients and pesticides.FindingsThe use of autonomous vehicles and AI techniques has been suggested through which the agriculture system becomes much more efficient. The world will switch to the smart agriculture system in the upcoming era completely. The authors conclude that autonomous vehicle in the field of science is time-saving and health efficient for both plants and workers in the fields. The suggested system increases the productivity of crops and saves the assets as well.Originality/valueThis review paper discusses the various contemporary technologies used in the field of agriculture and it will help future researchers to build on this research. This paper reveals that the UAVs along with multispectral, hyperspectral or red, green and blue camera (depends on the need) and AI are more suitable for the advancement of agriculture and increasing yield rate.

Fecal Glucocorticoid Metabolite Concentration as a Tool for Assessing Impacts of Interventions in Humboldt Penguins (Spheniscus humboldti)

It is currently unknown if current guidelines for collecting and interpreting blood corticosterone in flying birds can be extrapolated to penguins. It is also difficult to collect blood quickly without causing stress to a penguin. Therefore, immunoreactive fecal glucocorticoid metabolites (FGCMs) may be the most practical and minimally invasive way of monitoring the stress levels of penguins. This study investigated the reliability of FGCMs for monitoring stress levels in captive Humboldt Penguins (Spheniscus humboldti) at Jurong Bird Park, Singapore. Humboldt Penguin feces were randomly sampled and pooled from the exhibit for 2 months. The penguins were restrained and transported on three separate occasions to simulate stressful events. The feces were analyzed using an enzyme immunoassay to measure corticosterone levels. There were significant increases lasting 3 to 7 days in the FGCM levels after a stressful event. This method was then used to test whether accelerometer vests used for behavior quantification caused stress responses in these birds. There was no significant difference in FGCMs between time periods with and without the accelerometer vests. The results indicated that FGCMs can be an accurate indication of capture-, restraint-, and transport-related stress in Humboldt Penguins, and that accelerometer vests do not appear to cause stress.

Machine Learning Based Stress Monitoring in Older Adults Using Wearable Sensors and Cortisol as Stress Biomarker

The objective of this work is to evaluate the effectiveness of a wearable physiological stress monitoring system in distinguishing between stressed and non-stressed state in older adults using machine learning techniques. This system utilizes EDA and BVP signal to detect occurrence of stress as indicated by salivary cortisol measurement which is a reliable objective measure of physiological stress. Data of 19 healthy older adults (11 female and 8 male) with mean age 73.15 ± 5.79 were used for this study. EDA and BVP signals were recorded using a finger tip sensor during the Trier Social Stress Test, which is a well known experimental protocol to reliably induce stress in humans in a social setting. 39 statistical measures of the peak characteristic of EDA and BVP signal were extracted. A supervised feature selection algorithm is used to select important features as an input to the machine learning model. Four machine learning algorithms were evaluated based on their performance in classifying between stressed and non-stressed states. Results indicate that the logistic regression performed the best among Random Forest, κ-NN, and Support Vector Machine achieving an macro-average and micro-average f1-score of 0.87 and 0.95 respectively and an AUC score of 0.81. We also evaluated the effectiveness of a novel deep learning Long Short-Term Memory (LSTM) based classifier in distinguishing between stressed and non-stressed state. Results on test data shows that LSTM based classifier achieved an improvement of 6.7% and 2% in terms of macro-average f1-score and micro-average f1-score respectively. Also the AUC score for LSTM classifier is found to be 0.9 which is about 11% higher than the best performing logistic regression model. This work can be used to design a convenient unobtrusive wearable device to monitor stress levels in older adults in their home environment, thereby facilitating aging in place and improving the quality of life.