Early Stress Detection Research Articles

Early-Stage Detection of Biotic and Abiotic Stress on Plants by Chlorophyll Fluorescence Imaging Analysis.

Most agricultural land, as a result of climate change, experiences severe stress that significantly reduces agricultural yields. Crop sensing by imaging techniques allows early-stage detection of biotic or abiotic stress to avoid damage and significant yield losses. Among the top certified imaging techniques for plant stress detection is chlorophyll a fluorescence imaging, which can evaluate spatiotemporal leaf changes, permitting the pre-symptomatic monitoring of plant physiological status long before any visible symptoms develop, allowing for high-throughput assessment. Here, we review different examples of how chlorophyll a fluorescence imaging analysis can be used to evaluate biotic and abiotic stress. Chlorophyll a is able to detect biotic stress as early as 15 min after Spodoptera exigua feeding, or 30 min after Botrytis cinerea application on tomato plants, or on the onset of water-deficit stress, and thus has potential for early stress detection. Chlorophyll fluorescence (ChlF) analysis is a rapid, non-invasive, easy to perform, low-cost, and highly sensitive method that can estimate photosynthetic performance and detect the influence of diverse stresses on plants. In terms of ChlF parameters, the fraction of open photosystem II (PSII) reaction centers (qp) can be used for early stress detection, since it has been found in many recent studies to be the most accurate and appropriate indicator for ChlF-based screening of the impact of environmental stress on plants.

Photoplethysmographic Signal-Diffusive Dynamics as a Mental-Stress Physiological Indicator Using Convolutional Neural Networks

Stress is one of the primary triggers of serious pathologies (e.g., depression, obesity, heart attack). Prolonged exposure to it can lead to addictive substance consumption and even suicide, without ignoring other adverse side effects in the economic, work and family spheres. Early detection of stress would relax the pressure of medical practice exercised by the population affected and result in a healthier society with a more satisfying quality of life. In this work, a convolutional-neural-network (CNN) model is proposed to detect an individual’s stress state by analyzing the diffusive dynamics of the photoplethysmographic (PPG) signal. The characteristic (p,q)-planes of the 0–1 test serve as a framework to preprocess the PPG signals and feed the CNN with the dynamic information they supply to typify an individual’s stress level. The methodology follows CRISP-DM (Cross Industry Standard Process for Data Mining), which provides the typical steps in developing data-mining models. An adaptation of CRIPS-DM is applied, adding specific transitions between the usual stages of deep-learning models. The result is a CNN model whose performance amounts to 97% accuracy in diagnosing the stress level; it compares with other published results.

Drought affects both photosystems in Arabidopsis thaliana.

Drought is a major abiotic stress that impairs plant growth and development. Despite this, a comprehensive understanding of drought effects on the photosynthetic apparatus is lacking. In this work, we studied the consequences of 14-d drought treatment on Arabidopsis thaliana. We used biochemical and spectroscopic methods to examine photosynthetic membrane composition and functionality. Drought led to the disassembly of PSII supercomplexes and the degradation of PSII core. The light-harvesting complexes (LHCII) instead remain in the membrane but cannot act as an antenna for active PSII, thus representing a potential source of photodamage. This effect can also be observed during nonphotochemical quenching (NPQ) induction when even short pulses of saturating light can lead to photoinhibition. At a later stage, under severe drought stress, the PSI antenna size is also reduced and the PSI-LHCI supercomplexes disassemble. Surprisingly, although we did not observe changes in the PSI core protein content, the functionality of PSI is severely affected, suggesting the accumulation of nonfunctional PSI complexes. We conclude that drought affects both photosystems, although at a different stage, and that the operative quantum efficiency of PSII (ΦPSII ) is very sensitive to drought and can thus be used as a parameter for early detection of drought stress.

Exploring the Potential of Proximal Remote Sensing in Plant Stress Phenotyping: A Comprehensive Review

The global challenge of feeding the world demands attention due to the projected population increase to 10.9 billion by 2050. Abiotic and biotic stressors, such as heat, drought, diseases, and pests, further compound the difficulties faced in achieving sufficient agricultural output. Early detection of crop stress is vital to mitigate yield loss and find appropriate agrotechnical solutions. However, the complex interactions between abiotic and biotic stressors and their impact on plant growth and yield present challenges in plant phenotyping and breeding. This review discusses recent advances in remote sensing technologies which offer promising solutions to overcome these challenges. Low-cost, reliable sensors and technologies facilitate data collection and interpretation, paving the way for proximal sensing and high-throughput phenotyping platforms. These automated platforms, equipped with imaging devices, enable non-destructive data collection and monitoring of plant properties over time. Optical methods like hyperspectral sensors, RGB imaging, remote sensing, and chlorophyll fluorescence contribute to the early identification of plant stress causes, facilitating the development of control strategies. By providing accurate and timely information on crop stress, these technologies offer essential support in enhancing agricultural productivity and ensuring food security for a growing global population.

Efficient Feature-Selection-Based Stacking Model for Stress Detection Based on Chest Electrodermal Activity.

Contemporary advancements in wearable equipment have generated interest in continuously observing stress utilizing various physiological indicators. Early stress detection can improve healthcare by lessening the negative effects of chronic stress. Machine learning (ML) methodologies have been modified for healthcare equipment to monitor user health situations utilizing sufficient user information. Nevertheless, more data are needed to make applying Artificial Intelligence (AI) methodologies in the medical field easier. This research aimed to detect stress using a stacking model based on machine learning algorithms using chest-based features from the Wearable Stress and Affect Detection (WESAD) dataset. We converted this natural dataset into a convenient format for the suggested model by performing data visualization and preprocessing using the RESP feature and feature analysis using the Z-score, SelectKBest feature, the Synthetic Minority Over-Sampling Technique (SMOTE), and normalization. The efficiency of the proposed model was estimated regarding accuracy, precision, recall, and F1-score. The experimental outcome illustrated the efficacy of the proposed stacking technique, achieving 0.99% accuracy. The results revealed that the proposed stacking methodology performed better than traditional methodologies and previous studies.

Application of Remote Sensing in Detecting and Monitoring Water Stress in Forests

In the context of climate change, the occurrence of water stress in forest ecosystems, which are solely dependent on precipitation, has exhibited a rising trend, even among species that are typically regarded as drought-tolerant. Remote sensing techniques offer an efficient, comprehensive, and timely approach for monitoring forests at local and regional scales. These techniques also enable the development of diverse indicators of plant water status, which can play a critical role in evaluating forest water stress. This review aims to provide an overview of remote sensing applications for monitoring water stress in forests and reveal the potential of remote sensing and geographic information system applications in monitoring water stress for effective forest resource management. It examines the principles and significance of utilizing remote sensing technologies to detect forest stress caused by water deficit. In addition, by a quantitative assessment of remote sensing applications of studies in refereed publications, the review highlights the overall trends and the value of the widely used approach of utilizing visible and near-infrared reflectance data from satellite imagery, in conjunction with classical vegetation indices. Promising areas for future research include the utilization of more adaptable platforms and higher-resolution spectral data, the development of novel remote sensing indices with enhanced sensitivity to forest water stress, and the implementation of modelling techniques for early detection and prediction of stress.

Analyzing Perceived Psychological and Social Stress of University Students: A Machine Learning Approach

The COVID-19 pandemic has worsened the psychological and social stress levels of university students due to physical illness, enhanced dependence on mobile devices and internet, a lack of social activities, and home confinement. Therefore, early stress detection is crucial for their successful academic performance and mental well-being. The advent of machine learning (ML)-based prediction models can have a crucial impact in predicting stress at its early stages and taking necessary steps for the well-being of individuals. This study aims to develop a reliable machine learning-based prediction model for perceived stress prediction and validate the model using real-world data collected through an online survey among 444 university students from different ethnicity. The machine learning models were built using supervised machine learning algorithms. Principal Component Analysis (PCA) and the chi-squared test were employed as feature reduction techniques. Moreover, Grid Search Cross-Validation (GSCV) and Genetic Algorithm (GA) were employed for hyperparameter optimization (HPO). According to the findings, around 11.26% of individuals were identified with high levels of social stress. In comparison, approximately 24.10% of people were found to be suffering from extremely high psychological stress, which is quite alarming for students' mental health. Furthermore, the prediction results of the ML models demonstrated the most remarkable accuracy (80.5%), precision (1.000), F1 score (0.890), and recall value (0.826). The Multilayer Perceptron model was shown to have the maximum accuracy when combined with PCA as a feature reduction approach and GSCV for HPO. The convenience sampling technique used in this study only considers self-reported data, which may have biased results and lack generalizability. Future research should consider a large sample of data and focus on tracking long-term impacts with coping strategies and interventions. The results of this study can be used to develop strategies to mitigate adverse effects of the overuse of mobile devices and promote student well-being during pandemics and other stressful situations.

Early detection of drought stress in tomato from spectroscopic data: A novel convolutional neural network with feature selection

The yield and quality of tomato (Solanum lycopersicum L.) crops are lower when the plants are exposed to drought stress. Drought stress can be prevented through timely irrigation if it is identified early. Thus, this study modified the one-dimensional spectrogram power net (1D-SP-Net) to formulate a 1D convolutional neural network with an embedded residual global context (ResGC) block; this network, called 1D-ResGC-Net, processes visible and near-infrared (Vis/NIR) spectroscopy data of tomato leaves to identify the early signs of drought stress. In evaluation experiments, the proposed 1D-ResGC-Net model outperformed partial least squares discriminant analysis (PLSDA) and random forest (RF) models. Gradient-weighted class activation mapping, variable importance in projection, and variable importance were used to identify the most important feature bands (i.e., those that were most strongly associated with drought stress) as output by the 1D-ResGC-Net, PLSDA, and RF, respectively. The 1D-ResGC-Net model achieved 90% accuracy when the 15 most important feature bands were used; by contrast, the PLSDA and RF models required more than 90 of the most important feature bands to reach 90% accuracy. When the number of input features is similar, the accuracy of 1D-SP-Net and 1D-ResGC-Net is very close. However, when the number of input features is reduced, the accuracy of 1D-SP-Net will be much lower than 1D-ResGC-Net. In summary, 1D-ResGC-Net offers greater accuracy at a lower cost.

Stress Detection Based on Naïve Bayes Algorithm

Abstract: Stress is a prevalent issue that affects individuals' mental and physical well-being, leading to various health problems. The use of machine learning (ML) has been gaining popularity as a tool for stress detection. ML techniques have shown promising results in identifying patterns and features from various physiological and behavioral data sources such as heart rate, blood pressure, and speech signals. The primary goal of stress detection using ML is to provide accurate, non-invasive, and costeffective methods for early stress detection and intervention. Overall, stress detection using ML holds great promise in providing an objective, efficient, and scalable approach for stress monitoring and intervention. Further research is required to address the challenges associated with data collection, feature extraction, and model generalization to diverse populations and contexts.

Stress Monitoring Device and its Future Direction

Stress and mental health have become a global concern as a result of the COVID-19 pandemic. This review highlights the technologies applied to stress monitoring with up-to -date literature on psychological and behavioural evaluation for stress detection. The working principle and potential of these stress identifiers, particularly physiological signals are explored. Researchers have been directing their interest in producing reliable and wearable devices to detect and prevent stress and panic attacks. The breakthrough of biochemical-near-infrared stress monitoring devices will facilitate medical practitioners in the early detection of stress and panic attacks. The review seeks to explore the types of methods used to detect stress as well as the pros and cons of the available technology while providing a new solution for future implications of stress monitoring detection devices.

A deep learning approach for assessing stress levels in patients using electroencephalogram signals

Stress can contribute to many health problems, such as high blood pressure, heart disease, obesity, and diabetes. Therefore, early stress detection is essential in preventing illness and health problems. This study proposes a music experimentation approach to identify stress levels among the subjects. In this experiment, we study 45 subjects in the age category of 13–21. The model architecture used in the study is EEGnet, a compact convolutional neural network with a Relu activation function. We experimented with the mother wavelet decomposition method with 0 to 60 Hz frequency electroencephalogram signals and frequency division in 5 bands. The mounting positions involved are frontal, temporal, partial, and central. Signals generated at the frontal and temporal position in band value of 8–16 Hz serve as the most prominent feature in an experiment. We have achieved an accuracy of 99.45% for the alpha band with deep learning EEGnet architecture

Smartphone-Tracked Digital Markers of Momentary Subjective Stress in College Students: Idiographic Machine Learning Analysis

Stress is an important predictor of mental health problems such as burnout and depression. Acute stress is considered adaptive, whereas chronic stress is viewed as detrimental to well-being. To aid in the early detection of chronic stress, machine learning models are increasingly trained to learn the quantitative relation from digital footprints to self-reported stress. Prior studies have investigated general principles in population-wide studies, but the extent to which the findings apply to individuals is understudied. We aimed to explore to what extent machine learning models can leverage features of smartphone app use log data to recognize momentary subjective stress in individuals, which of these features are most important for predicting stress and represent potential digital markers of stress, the nature of the relations between these digital markers and stress, and the degree to which these relations differ across people. Student participants (N=224) self-reported momentary subjective stress 5 times per day up to 60 days in total (44,381 observations); in parallel, dedicated smartphone software continuously logged their smartphone app use. We extracted features from the log data (eg, time spent on app categories such as messenger apps and proxies for sleep duration and onset) and trained machine learning models to predict momentary subjective stress from these features using 2 approaches: modeling general relations at the group level (nomothetic approach) and modeling relations for each person separately (idiographic approach). To identify potential digital markers of momentary subjective stress, we applied explainable artificial intelligence methodology (ie, Shapley additive explanations). We evaluated model accuracy on a person-to-person basis in out-of-sample observations. We identified prolonged use of messenger and social network site apps and proxies for sleep duration and onset as the most important features across modeling approaches (nomothetic vs idiographic). The relations of these digital markers with momentary subjective stress differed from person to person, as did model accuracy. Sleep proxies, messenger, and social network use were heterogeneously related to stress (ie, negative in some and positive or zero in others). Model predictions correlated positively and statistically significantly with self-reported stress in most individuals (median person-specific correlation=0.15-0.19 for nomothetic models and median person-specific correlation=0.00-0.09 for idiographic models). Our findings indicate that smartphone log data can be used for identifying digital markers of stress and also show that the relation between specific digital markers and stress differs from person to person. These findings warrant follow-up studies in other populations (eg, professionals and clinical populations) and pave the way for similar research using physiological measures of stress.

Chlorophyll Fluorescence Imaging for Early Detection of Drought and Heat Stress in Strawberry Plants.

The efficiency of photosynthesis in strawberry plants is measured to maintain the quality and quantity of strawberries produced. The latest method used to measure the photosynthetic status of plants is chlorophyll fluorescence imaging (CFI), which has the advantage of obtaining plant spatiotemporal data non-destructively. This study developed a CFI system to measure the maximum quantum efficiency of photochemistry (Fv/Fm). The main components of this system include a chamber for plants to adapt to dark environments, blue LED light sources to excite the chlorophyll in plants, and a monochrome camera with a lens filter attached to capture the emission spectra. In this study, 120 pots of strawberry plants were cultivated for 15 days and divided into four treatment groups: control, drought stress, heat stress, and a combination of drought and heat stress, resulting in Fv/Fm values of 0.802 ± 0.0036, 0.780 ± 0.0026, 0.768 ± 0.0023, and 0.749 ± 0.0099, respectively. A strong correlation was found between the developed system and a chlorophyll meter (r = 0.75). These results prove that the developed CFI system can accurately capture the spatial and temporal dynamics resulting from the response of strawberry plants to abiotic stresses.

Mental Stress Detection Using a Wearable In-Ear Plethysmography.

This study presents an ear-mounted photoplethysmography (PPG) system that is designed to detect mental stress. Mental stress is a prevalent condition that can negatively impact an individual's health and well-being. Early detection and treatment of mental stress are crucial for preventing related illnesses and maintaining overall wellness. The study used data from 14 participants that were collected in a controlled environment. The participants were subjected to stress-inducing tasks such as the Stroop color-word test and mathematical calculations. The raw PPG signal was then preprocessed and transformed into scalograms using continuous wavelet transform (CWT). A convolutional neural network classifier was then used to classify the transformed signals as stressed or non-stressed. The results of the study show that the PPG system achieved high levels of accuracy (92.04%) and F1-score (90.8%). Furthermore, by adding white Gaussian noise to the raw PPG signals, the results were improved even more, with an accuracy of 96.02% and an F1-score of 95.24%. The proposed ear-mounted device shows great promise as a reliable tool for the early detection and treatment of mental stress, potentially revolutionizing the field of mental health and well-being.

A blockchain-based secure Internet of medical things framework for stress detection

With the aid of advancing technologies, the healthcare sector is improving more swiftly than ever, yet there are still many unexplored areas and there is always potential for improvement. Deep Learning (DL), blockchain and the Internet of Medical Things (IoMT), three of the most revolutionary technologies, have aided replace conventional practice employed in the healthcare industry with more sophisticated and efficient procedures. In this research, we propose DON-B-STRESSED (DBS), an innovative framework which integrates DL, blockchain and IoMT technologies to provide a method for the early detection of stress in users donning IoMT devices. Long-term stress, indeed, is well-known to have profound consequences on human wellbeing; hence the need for automated solutions for continual stress monitoring. DON-B-STRESSED stands for DON a Blockchain-based, Secure, Timely, REliable System for StrEss Detection: the premise behind this is that if the above-mentioned technologies can be combined, a system that employs IoMT for users' data collection, DL to properly predict patients' stress levels, and smart contracts deployed on blockchain to ensure secure transactions and health checks, the well-known concerns of harmful effects of long-term stress might be avoided. By using multimodal data from both a chest- and a wrist-worn IoMT device, we have developed a tailored, secure, accurate yet fast real-time system for the early detection of stress signs. The DL part has been evaluated on WESAD, a publicly available dataset for wearable stress and affect detection, reaching an accuracy of more than 99% with LOSO generalization scheme. Furthermore, the scalability and reliability of DON-B-STRESSED are shown by comparison with the findings of past research.

Paper-Based Multiplex Sensors for the Optical Detection of Plant Stress.

The rising population and the ongoing climate crisis call for improved means to monitor and optimise agriculture. A promising approach to tackle current challenges in food production is the early diagnosis of plant diseases through non-invasive methods, such as the detection of volatiles. However, current devices for detection of multiple volatiles are based on electronic noses, which are expensive, require complex circuit assembly, may involve metal oxides with heating elements, and cannot easily be adapted for some applications that require miniaturisation or limit front-end use of electronic components. To address these challenges, a low-cost optoelectronic nose using chemo-responsive colorimetric dyes drop-casted onto filter paper has been developed in the current work. The final sensors could be used for the quantitative detection of up to six plant volatiles through changes in colour intensities with a sub-ppm level limit of detection, one of the lowest limits of detection reported so far using colorimetric gas sensors. Sensor colouration could be analysed using a low-cost spectrometer and the results could be processed using a microcontroller. The measured volatiles could be used for the early detection of plant abiotic stress as early as two days after exposure to two different stresses: high salinity and starvation. This approach allowed a lowering of costs to GBP 1 per diagnostic sensing paper. Furthermore, the small size of the paper sensors allows for their use in confined settings, such as Petri dishes. This detection of abiotic stress could be easily achieved by exposing the devices to living plants for 1 h. This technology has the potential to be used for monitoring of plant development in field applications, early recognition of stress, implementation of preventative measures, and mitigation of harvest losses.

A Comparison and Introduction of Novel Solar Panel’s Fault Diagnosis Technique Using Deep-Features Shallow-Classifier through Infrared Thermography

Solar photovoltaics (PV) are susceptible to environmental and operational stresses due to their operation in an open atmosphere. Early detection and treatment of stress prevents hotspots and the total failure of solar panels. In response, the literature has proposed several approaches, each with its own limitations, such as high processing system requirements, large amounts of memory, long execution times, fewer types of faults diagnosed, failure to extract relevant features, and so on. Therefore, this research proposes a fast framework with the least memory and computing system requirements for the six different faults of a solar panel. Infrared thermographs from solar panels are fed into intense and architecturally complex deep convolutional networks capable of differentiating one million images into 1000 classes. Features without backpropagation are calculated to reduce execution time. Afterward, deep features are fed to shallow classifiers due to their fast training time. The proposed approach trains the shallow classifier in approximately 13 s with 95.5% testing accuracy. The approach is validated by manually extracting thermograph features and through the transfer of learned deep neural network approaches in terms of accuracy and speed. The proposed method is also compared with other existing methods.

A Multi-Stage Early Stress Detection Model with Time Delay Subject to a Person’s Stress

Stress is the body’s response to something that requires action or attention. In general, anything that poses a real challenge or threat to a person’s well-being can cause stress. Stress can slow down a person’s well-being activities. Often, you might not know whether you are stressed, if you are under too much stress, or when it is time to seek help. This paper presents a mathematical model with time delay subject to a person’s stress for early stress detection to assess whether a person is stress-free, has stress but is undetected, or has stress in any specific state such as minor, moderate, or severe stress. Being more alert to the effects of stress and reducing the uncertainty of undetected stress, or better, preventing it, may help people, especially teens, manage it more effectively and cope better, even a person happens to be stressed. The model can be extended to study the effects of multiple stress factors in light of the prolonged COVID-19 pandemic on people’s mental stress.

Early Identification of Plant Drought Stress Responses: Changes in Leaf Reflectance and Plant Growth Promoting Rhizobacteria Selection-The Case Study of Tomato Plants

Drought is a worldwide problem, especially in arid and semi-arid regions. Detection of drought stress at the initial stages, before visible signs, to adequately manage irrigation and crop fertilization to avoid crop yield loss, is a desire of most farmers. Here, we evaluated the response of tomato plants to water scarcity, through changes in leaf reflectance due to modification in leaf pigments’ content, which translates into differences in spectral reflectance indices (SRI) values. Our methodology is innovative, as we were able to easily calculate and identify several SRIs for the early detection of drought stress “invisible” responses. We used a handheld spectro-radiometer to obtain SRI values from leaves of tomato plants growing under two different water regimes for 37 days. In an ensemble of 25 SRIs, we identified 12 that showed a consistent trend of significant differences between treatments along the experiment and within these, NDVI, SR, ZMI, Ctr2, GM1, and GM2 were already significantly different between treatments at day 7 after the start of the experiment and Ctr1 at day 9; although, no signs of damage were visible. Therefore, our results pinpoint these SRIs as promising proxies for the early detection of “invisible” responses to drought onset. We also analyzed the relationship between the monitored SRIs and plant morphological parameters measured during the experiment, highlighting a relationship between GM1 and plant height and leaf number. Finally, we observed a high abundance of putative beneficial bacteria among isolates collected from the tomato water-limited rhizo-environment at the terminus of the experiment, suggesting the active recruitment or selection of Plant Growth Promoting Rhizobacteria by tomato roots as a response to drought. Our work may be adapted into an easy protocol, of rapid execution, to be used in small-scale fields for early drought stress detection.

Early Detection of Wireworm (Coleoptera: Elateridae) Infestation and Drought Stress in Maize Using Hyperspectral Imaging

The objective of our research was to test hyperspectral imaging as a method for early detection and discrimination of biotic and abiotic stress in maize. We investigated the individual and combined effects of wireworm feeding and drought stress on leaf spectral responses and on various morphological and physiological traits of maize plants, selecting two hybrids with different tolerance to drought. Physiological parameters were determined at three time points (14, 21 and 28 days after adding wireworms and changing watering regime), along with hyperspectral imaging. Most of the differences in physiological characteristics between treatments were detected on day 21, when drought was the main cause of the negative physiological outcome, while the presence of wireworms only caused lower relative chlorophyll content, resulting in lower combined stress damage in some treatments. The morphological data showed greater wireworm damage to hybrid ZP341 and a greater negative effect of combined stress on hybrid FuturiXX. Hyperspectral imaging detected pest infestation and drought stress before they were detected by classical methods, with the highest overall accuracy on day 14 (84.7%) and the lowest on day 28 (67%). It can therefore be used as a method for early detection of wireworm infestation and/or drought in maize.