Diagnosis of placenta accreta spectrum using ultrasound texture feature fusion and machine learning.

INTRODUCTION: Placenta accreta spectrum (PAS) is an obstetric disorder arising from the abnormal adherence of the placenta to the uterine wall, often leading to life-threatening complications including postpartum hemorrhage. Despite its significance, PAS remains frequently underdiagnosed before delivery. This study delves into the realm of machine learning to enhance the precision of PAS classification. We introduce two distinct models for PAS classification employing ultrasound texture features. METHODS: The first model leverages machine learning techniques, harnessing texture features extracted from ultrasound scans. The second model adopts a linear classifier, utilizing integrated features derived from 'weighted z-scores'. A novel aspect of our approach is the amalgamation of classical machine learning and statistical-based methods for feature selection. This, coupled with a more transparent classification model based on quantitative image features, results in superior performance compared to conventional machine learning approaches. RESULTS: Our linear classifier and machine learning models attain test accuracies of 87 % and 92 %, and 5-fold cross validation accuracies of 88.7 (4.4) and 83.0 (5.0), respectively. CONCLUSIONS: The proposed models illustrate the effectiveness of practical and robust tools for enhanced PAS detection, offering non-invasive and computationally-efficient diagnostic tools. As adjunct methods for prenatal diagnosis, these tools can assist clinicians by reducing the need for unnecessary interventions and enabling earlier planning of management strategies for delivery.

An Interpretable Neonatal Lung Ultrasound Feature Extraction and Lung Sliding Detection System Using Object Detectors.

The objective of this study was to develop an interpretable system that could detect specific lung features in neonates. A challenging aspect of this work was that normal lungs showed the same visual features (as that of Pneumothorax (PTX)). M-mode is typically necessary to differentiate between the two cases, but its generation in clinics is time-consuming and requires expertise for interpretation, which remains limited. Therefore, our system automates M-mode generation by extracting Regions of Interest (ROIs) without human in the loop. Object detection models such as faster Region Based Convolutional Neural Network (fRCNN) and RetinaNet models were employed to detect seven common Lung Ultrasound (LUS) features. fRCNN predictions were then stored and further used to generate M-modes. Beyond static feature extraction, we used a Hough transform based statistical method to detect "lung sliding" in these M-modes. Results showed that fRCNN achieved a greater mean Average Precision (mAP) of 86.57% (Intersection-over-Union (IoU) = 0.2) than RetinaNet, which only displayed a mAP of 61.15%. The calculated accuracy for the generated RoIs was 97.59% for Normal videos and 96.37% for PTX videos. Using this system, we successfully classified 5 PTX and 6 Normal video cases with 100% accuracy. Automating the process of detecting seven prominent LUS features addresses the time-consuming manual evaluation of Lung ultrasound in a fast paced environment. Clinical impact: Our research work provides a significant clinical impact as it provides a more accurate and efficient method for diagnosing lung diseases in neonates.

Classification of lung pathologies in neonates using dual-tree complex wavelet transform.

INTRODUCTION: Undiagnosed and untreated lung pathologies are among the leading causes of neonatal deaths in developing countries. Lung Ultrasound (LUS) has been widely accepted as a diagnostic tool for neonatal lung pathologies due to its affordability, portability, and safety. However, healthcare institutions in developing countries lack well-trained clinicians to interpret LUS images, which limits the use of LUS, especially in remote areas. An automated point-of-care tool that could screen and capture LUS morphologies associated with neonatal lung pathologies could aid in rapid and accurate diagnosis. METHODS: We propose a framework for classifying the six most common neonatal lung pathologies using spatially localized line and texture patterns extracted via 2D dual-tree complex wavelet transform (DTCWT). We acquired 1550 LUS images from 42 neonates with varying numbers of lung pathologies. Furthermore, we balanced our data set to avoid bias towards a pathology class. RESULTS: Using DTCWT and clinical features as inputs to a linear discriminant analysis (LDA), our approach achieved a per-image cross-validated classification accuracy of 74.39% for the imbalanced data set. Our classification accuracy improved to 92.78% after balancing our data set. Moreover, our proposed framework achieved a maximum per-subject cross-validated classification accuracy of 64.97% with an imbalanced data set while using a balanced data set improves its classification accuracy up to 81.53%. CONCLUSION: Our work could aid in automating the diagnosis of lung pathologies among neonates using LUS. Rapid and accurate diagnosis of lung pathologies could help to decrease neonatal deaths in healthcare institutions that lack well-trained clinicians, especially in developing countries.

Physiological Signal Analysis and Stress Classification from VR Simulations Using Decision Tree Methods.

Stress is induced in response to any mental, physical or emotional change associated with our daily experiences. While short term stress can be quite beneficial, prolonged stress is detrimental to the heart, muscle tissues and immune system. In order to be proactive against these symptoms, it is important to assess the impact of stress due to various activities, which is initially determined through the change in the sympathetic (SNS) and parasympathetic (PNS) nervous systems. After acquiring physiological data wirelessly through captive electrocardiogram (ECG), galvanic skin response (GSR) and respiration (RESP) sensors, 21 time, frequency, nonlinear, GSR and respiration features were manually extracted from 15 subjects ensuing a baseline phase, virtual reality (VR) roller coaster simulation, color Stroop task and VR Bubble Bloom game. This paper presents a comprehensive physiological analysis of stress from an experiment involving a VR video game Bubble Bloom to manage stress levels. A personalized classification and regression tree (CART) model was developed using a novel Gini index algorithm in order to effectively classify binary classes of stress. A novel K-means feature was derived from 11 other features and used as an input in the Decision Tree (DT) algorithm, strong learners Ensemble Gradient Boosting (EGB) and Extreme Gradient Boosting (XGBoost (XGB)) embedded in a pipeline to classify 5 classes of stress. Results obtained indicate that heart rate (HR), approximate entropy (ApEN), low frequency and high frequency ratio (LF/HF), low frequency (LF), standard deviation (SD1), GSR and RESP all reduced and high frequency (HF) increased following the VR Bubble Bloom game phase. The personalized CART model was able to classify binary stress with 87.75% accuracy. It proved to be more effective than other related studies. EGB was able to classify binary stress with 100% accuracy, which outperformed every other related study. XGBoost and DT were able to classify five classes of stress with 72.22% using the novel K-means feature. This feature produced less error and better model performance in comparison to using all the features. Results substantiate that our proposed methods were more effective for stress classification than most related studies.

Motion Vector Extrapolation for Video Object Detection.

Despite the continued successes of computationally efficient deep neural network architectures for video object detection, performance continually arrives at the great trilemma of speed versus accuracy versus computational resources (pick two). Current attempts to exploit temporal information in video data to overcome this trilemma are bottlenecked by the state of the art in object detection models. This work presents motion vector extrapolation (MOVEX), a technique which performs video object detection through the use of off-the-shelf object detectors alongside existing optical flow-based motion estimation techniques in parallel. This work demonstrates that this approach significantly reduces the baseline latency of any given object detector without sacrificing accuracy performance. Further latency reductions up to 24 times lower than the original latency can be achieved with minimal accuracy loss. MOVEX enables low-latency video object detection on common CPU-based systems, thus allowing for high-performance video object detection beyond the domain of GPU computing.

Artificial intelligence and the work-health interface: A research agenda for a technologically transforming world of work.

The labor market is undergoing a rapid artificial intelligence (AI) revolution. There is currently limited empirical scholarship that focuses on how AI adoption affects employment opportunities and work environments in ways that shape worker health, safety, well-being and equity. In this article, we present an agenda to guide research examining the implications of AI on the intersection between work and health. To build the agenda, a full day meeting was organized and attended by 50 participants including researchers from diverse disciplines and applied stakeholders. Facilitated meeting discussions aimed to set research priorities related to workplace AI applications and its impact on the health of workers, including critical research questions, methodological approaches, data needs, and resource requirements. Discussions also aimed to identify groups of workers and working contexts that may benefit from AI adoption as well as those that may be disadvantaged by AI. Discussions were synthesized into four research agenda areas: (1) examining the impact of stronger AI on human workers; (2) advancing responsible and healthy AI; (3) informing AI policy for worker health, safety, well-being, and equitable employment; and (4) understanding and addressing worker and employer knowledge needs regarding AI applications. The agenda provides a roadmap for researchers to build a critical evidence base on the impact of AI on workers and workplaces, and will ensure that worker health, safety, well-being, and equity are at the forefront of workplace AI system design and adoption.

Mobile Health-Supported Virtual Reality and Group Problem Management Plus: Protocol for a Cluster Randomized Trial Among Urban Refugee and Displaced Youth in Kampala, Uganda (Tushirikiane4MH, Supporting Each Other for Mental Health).

BACKGROUND: Although mental health challenges disproportionately affect people in humanitarian contexts, most refugee youth do not receive the mental health support needed. Uganda is the largest refugee-hosting nation in Africa, hosting over 1.58 million refugees in 2022, with more than 111,000 living in the city of Kampala. There is limited information about effective and feasible interventions to improve mental health outcomes and mental health literacy, and to reduce mental health stigma among urban refugee adolescents and youth in low- and middle-income countries (LMICs). Virtual reality (VR) is a promising approach to reduce stigma and improve mental health and coping, yet such interventions have not yet been tested in LMICs where most forcibly displaced people reside. Group Problem Management Plus (GPM+) is a scalable brief psychological transdiagnostic intervention for people experiencing a range of adversities, but has not been tested with adolescents and youth to date. Further, mobile health (mHealth) strategies have demonstrated promise in promoting mental health literacy. OBJECTIVE: The aim of this study is to evaluate the feasibility and effectiveness of two youth-tailored mental health interventions (VR alone and VR combined with GMP+) in comparison with the standard of care in improving mental health outcomes among refugee and displaced youth aged 16-24 years in Kampala, Uganda. METHODS: A three-arm cluster randomized controlled trial will be implemented across five informal settlements grouped into three sites, based on proximity, and randomized in a 1:1:1 design. Approximately 330 adolescents (110 per cluster) are enrolled and will be followed for approximately 16 weeks. Data will be collected at three time points: baseline enrollment, 8 weeks following enrollment, and 16 weeks after enrollment. Primary (depression) and secondary outcomes (mental health literacy, attitudes toward mental help-seeking, adaptive coping, mental health stigma, mental well-being, level of functioning) will be evaluated. RESULTS: The study will be conducted in accordance with CONSORT (Consolidated Standards of Reporting Trials) guidelines. The study has received ethical approval from the University of Toronto (#40965; May 12, 2021), Mildmay Uganda Research Ethics Committee (MUREC-2021-41; June 24, 2021), and Uganda National Council for Science & Technology (SS1021ES; January 1, 2022). A qualitative formative phase was conducted using focus groups and in-depth, semistructured key informant interviews to understand contextual factors influencing mental well-being among urban refugee and displaced youth. Qualitative findings will inform the VR intervention, SMS text check-in messages, and the adaptation of GPM+. Intervention development was conducted in collaboration with refugee youth peer navigators. The trial launched in June 2022 and the final follow-up survey will be conducted in November 2022. CONCLUSIONS: This study will contribute to the knowledge of youth-tailored mental health intervention strategies for urban refugee and displaced youth living in informal settlements in LMIC contexts. Findings will be shared in peer-reviewed publications, conference presentations, and with community dissemination. TRIAL REGISTRATION: ClinicalTrials.gov NCT05187689; https://clinicaltrials.gov/ct2/show/NCT05187689. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/42342.

A Survey on Physiological Signal-Based Emotion Recognition.

Physiological signals are the most reliable form of signals for emotion recognition, as they cannot be controlled deliberately by the subject. Existing review papers on emotion recognition based on physiological signals surveyed only the regular steps involved in the workflow of emotion recognition such as pre-processing, feature extraction, and classification. While these are important steps, such steps are required for any signal processing application. Emotion recognition poses its own set of challenges that are very important to address for a robust system. Thus, to bridge the gap in the existing literature, in this paper, we review the effect of inter-subject data variance on emotion recognition, important data annotation techniques for emotion recognition and their comparison, data pre-processing techniques for each physiological signal, data splitting techniques for improving the generalization of emotion recognition models and different multimodal fusion techniques and their comparison. Finally, we discuss key challenges and future directions in this field.

Edge-preserving Image Synthesis for Unsupervised Domain Adaptation in Medical Image Segmentation.

Domain Adaptation is a technique to address the lack of massive amounts of labeled data in different application domains. Unsupervised domain adaptation is the process of adapting a model to an unseen target dataset using solely labeled source data and unlabeled target domain data. Though many image-spaces domain adaptation methods have been proposed to capture pixel-level domain-shift, such techniques may fail to maintain high-level semantic information for the segmentation task. For the case of biomedical images, fine details such as blood vessels can be lost during the image transformation operations between domains. In this work, we propose a model that adapts between domains using cycle-consistent loss while maintaining edge details of the original images by enforcing an edge-based loss during the adaptation process. We demonstrate the effectiveness of our algorithm by comparing it to other approaches on two eye fundus vessels segmentation datasets. We achieve 3.1 % increment in Dice score compared to the SOTA and  âˆ¼  7.02% increment compared to a vanilla CycleGAN implementation. Clinical relevance- The proposed adaptation scheme can provide better performance on unseen data for semantic segmentation, which is widely applied in computer-aided diagnosis. Such robust performance can reduce the reliance of a large amount of labeled data, which is a common problem in the medical domain.

Interactive Segmentation Using U-Net with Weight Map and Dynamic User Interactions.

Interactive segmentation has recently attracted attention for specialized tasks where expert input is required to further enhance the segmentation performance. In this work, we propose a novel interactive segmentation framework, where user clicks are dynamically adapted in size based on the current segmentation mask. The clicked regions form a weight map and are fed to a deep neural network as a novel weighted loss function. To evaluate our loss function, an interactive U-Net (IU-Net) model which applies both foreground and background user clicks as the main method of interaction is employed. We train and validate on the BCV dataset, while testing on spleen and colon cancer CT images from the MSD dataset to improve the overall segmentation accuracy in comparison to the standard U-Net using our weighted loss function. Applying dynamic user click sizes increases the overall accuracy by 5.60% and 10.39% respectively by utilizing only a single user interaction.

Multi-Level Classification of Lung Pathologies in Neonates using Recurrence Features.

The use of Lung Ultrasound (LUS) as a tool to diagnose and monitor lung diseases in neonates has increased in urban hospitals. LUS's main advantages compared to chest CT or X-rays is that it is less expensive, more accessible, and does not expose the patient to radiation. Performing LUS on neonates and diagnosing the LUS images require highly trained medical professional and clinicians. While availability of such specialists in general is not an issue in urban areas, there is lack of such personnel in rural and remote communities. Hence, an automated computer-aided screening approach as a first level diagnosis assistance in such scenarios might be of significant value. Many of the image morphologies used by clinicians in diagnosing the LUS have strong recurrence characteristics. Building upon this knowledge, in this paper, we propose a feature extraction method designed to quantify such recurrent features for classification of LUS images into 6 common neonatal lung conditions. These conditions were normal lung, chronic lung disease (CLD), transient tachypnea of the newborn (TTN), pneumothorax (PTX), respiratory distress syndrome (RDS), and consolidation (CON) that could be pneumonia or atelectasis. The proposed method extracts virtual scanlines from the LUS images and converts them into signals. Then using recurrence quantification analysis (RQA), features were extracted and fed to pattern classifiers. Using a simple linear classifier the proposed features can achieve a classification accuracy of 69.3% without clinical features and 77.6% with clinical features. Clinical Relevance- Development of an automated computer-aided screening tool for first level diagnosis assistance in neonatal LUS pathologies. Such a tool will be of significant value in rural and remote medical communities.

Skin lesion segmentation using a semi-supervised U-NetSC model with an adaptive loss function.

Skin lesion segmentation is a crucial step in cancer detection. Deep learning has shown promising results for lesion segmentation. However, the performance of these models depends on accessing lots of training samples with pixel-level annotations. Employing a semi-supervised approach reduces the need for a large number of annotated samples. Accordingly, a semi-supervised strategy is proposed based on the high correlation of segmentation and classification tasks. The U - N et Segmentation and Classification model (U-NetSC) is a unified architecture containing segmentation and classification modules. The classification module uses feature maps from the last layer of the segmentation model to increase the collaboration of two tasks. U-NetSC can be trained with only class-level or both class-level and pixel-level ground truth using an adaptive loss function. U-NetSC achieves ~2%, ~ 2%, ~ 3%, and ~ 1 % improvement in Jaccard Index, Dice coefficient, precision, and accuracy, respectively, in comparison with a supervised attention-gated U-Net model. Clinical relevance - The paper proposes an automatic skin lesion segmentation model in a semi-supervised manner. Training the segmentation model is based on a combination of class-level and pixel-level information without requiring a large number of labeled samples.

Affective State Recognition with Convolutional Autoencoders.

The aim of this study was to create a robust generalizable model to classify person's affective state based on physiological signals obtained using wearable sensor devices. Traditional machine learning methods require manual feature extraction from time sequences. Deep learning methods, such as Convolutional Neural Networks (CNN), can automatically extract features from time sequences. However, CNN models can be prone to overfitting, especially when the dataset is small. We apply a novel idea of using unsupervised convolutional autoencoders to automatically extract features from time-series data that are then fed to supervised classifier to classify people's affective state. We achieve almost 3% accuracy increase over traditional CNN model using all physio data from WESAD dataset, 2% increase using chest only physio data, and 8% increase using wrist only physio data while classifying neutral, stress, and amusement states. Code to reproduce the results can be found at https://github.com/srovins/wesad Clinical Relevance- A high-performing affective state recognition system can be utilized for various medical applications, ranging from patient monitoring to cognitive therapy.

Interpretable Artificial Intelligence through Locality Guided Neural Networks.

In current deep learning architectures, each of the deeper layers in networks tends to contain hundreds of unorganized neurons which makes it hard for humans to understand how they interact with each other. By organizing the neurons using correlation as the criteria, humans can observe how clusters of neighbouring neurons interact with each other. Research in Explainable Artificial Intelligence (XAI) aims to all alleviate the black-box nature of current AI methods and make them understandable by humans. In this paper, we extend our previous algorithm for XAI in deep learning, called Locality Guided Neural Network (LGNN). LGNN preserves locality between neighbouring neurons within each layer of a deep network during training. Motivated by Self-Organizing Maps (SOMs), the goal is to enforce a local topology on each layer of a deep network such that neighbouring neurons are highly correlated with each other. Our algorithm can be easily plugged into current state of the art Convolutional Neural Network (CNN) models to make the neighbouring neurons more correlated. A cluster of neighbouring neurons activating for a class makes the network both quantitatively and qualitatively more interpretable when visualized, as we show through our experiments. This paper focuses on image processing with CNNs, but can theoretically be applied to any type of deep learning architecture. In our experiments, we train VGG and WRN networks for image classification on CIFAR100 and Imagenette. Our experiments analyse different perceptible clusters of activations in response to different input classes.

Contrastive Self-Supervised Learning for Stress Detection from ECG Data.

In recent literature, ECG-based stress assessment has become popular due to its proven correlation to stress and increased accessibility of ECG data through commodity hardware. However, most ECG-based stress assessment models use supervised learning, relying on manually-annotated data. Limited research is done in the area of self-supervised learning (SSL) approaches that leverage unlabelled data and none that utilize contrastive SSL. However, with the dominance of contrastive SSL in domains such as computer vision, it is essential to see if the same excellence in performance can be obtained on an ECG-based stress assessment dataset. In this paper, we propose a contrastive SSL model for stress assessment using ECG signals based on the SimCLR framework. We test our model on two ECG-based stress assessment datasets. We show that our proposed solution results in a 9% improvement in accuracy on the WESAD dataset and 3.7% on the RML dataset when compared with SOTA ECG-based SSL models for stress assessment. The development of more accurate stress assessment models, particularly those that employ non-invasive data such as ECG for assessment, leads to developments in wearable technology and the creation of better health monitoring applications in areas such as stress management and relaxation therapy.

Efficient and Scalable Object Localization in 3D on Mobile Device.

Two-Dimensional (2D) object detection has been an intensely discussed and researched field of computer vision. With numerous advancements made in the field over the years, we still need to identify a robust approach to efficiently conduct classification and localization of objects in our environment by just using our mobile devices. Moreover, 2D object detection limits the overall understanding of the detected object and does not provide any additional information in terms of its size and position in the real world. This work proposes an object localization solution in Three-Dimension (3D) for mobile devices using a novel approach. The proposed method works by combining a 2D object detection Convolutional Neural Network (CNN) model with Augmented Reality (AR) technologies to recognize objects in the environment and determine their real-world coordinates. We leverage the in-built Simultaneous Localization and Mapping (SLAM) capability of Google's ARCore to detect planes and know the camera information for generating cuboid proposals from an object's 2D bounding box. The proposed method is fast and efficient for identifying everyday objects in real-world space and, unlike mobile offloading techniques, the method is well designed to work with limited resources of a mobile device.

Interpreting Uncertainty in Model Predictions for Covid-19 Diagnosis.

COVID-19, due to its accelerated spread has brought in the need to use assistive tools for faster diagnosis in addition to typical lab swab testing. Chest X-Rays for COVID cases tend to show changes in the lungs such as ground glass opacities and peripheral consolidations which can be detected by deep neural networks. However, traditional convolutional networks use point estimate for predictions, lacking in capture of uncertainty, which makes them less reliable for adoption. There have been several works so far in predicting COVID positive cases with chest X-Rays. However, not much has been explored on quantifying the uncertainty of these predictions, interpreting uncertainty, and decomposing this to model or data uncertainty. To address these needs, we develop a visualization framework to address interpretability of uncertainty and its components, with uncertainty in predictions computed with a Bayesian Convolutional Neural Network. This framework aims to understand the contribution of individual features in the Chest-X-Ray images to predictive uncertainty. Providing this as an assistive tool can help the radiologist understand why the model came up with a prediction and whether the regions of interest captured by the model for the specific prediction are of significance in diagnosis. We demonstrate the usefulness of the tool in chest x-ray interpretation through several test cases from a benchmark dataset.

An Interpretable Object Detection-Based Model For The Diagnosis Of Neonatal Lung Diseases Using Ultrasound Images.

Over the last few decades, Lung Ultrasound (LUS) has been increasingly used to diagnose and monitor different lung diseases in neonates. It is a noninvasive tool that allows a fast bedside examination while minimally handling the neonate. Acquiring a LUS scan is easy, but understanding the artifacts concerned with each respiratory disease is challenging. Mixed artifact patterns found in different respiratory diseases may limit LUS readability by the operator. While machine learning (ML), especially deep learning can assist in automated analysis, simply feeding the ultrasound images to an ML model for diagnosis is not enough to earn the trust of medical professionals. The algorithm should output LUS features that are familiar to the operator instead. Therefore, in this paper we present a unique approach for extracting seven meaningful LUS features that can be easily associated with a specific pathological lung condition: Normal pleura, irregular pleura, thick pleura, A- lines, Coalescent B-lines, Separate B-lines and Consolidations. These artifacts can lead to early prediction of infants developing later respiratory distress symptoms. A single multi-class region proposal-based object detection model faster-RCNN (fRCNN) was trained on lower posterior lung ultrasound videos to detect these LUS features which are further linked to four common neonatal diseases. Our results show that fRCNN surpasses single stage models such as RetinaNet and can successfully detect the aforementioned LUS features with a mean average precision of 86.4%. Instead of a fully automatic diagnosis from images without any interpretability, detection of such LUS features leave the ultimate control of diagnosis to the clinician, which can result in a more trustworthy intelligent system.

Trends in Heart-Rate Variability Signal Analysis.

Heart rate variability (HRV) is the rate of variability between each heartbeat with respect to time. It is used to analyse the Autonomic Nervous System (ANS), a control system used to modulate the body's unconscious action such as cardiac function, respiration, digestion, blood pressure, urination, and dilation/constriction of the pupil. This review article presents a summary and analysis of various research works that analyzed HRV associated with morbidity, pain, drowsiness, stress and exercise through signal processing and machine learning methods. The points of emphasis with regards to HRV research as well as the gaps associated with processes which can be improved to enhance the quality of the research have been discussed meticulously. Restricting the physiological signals to Electrocardiogram (ECG), Electrodermal activity (EDA), photoplethysmography (PPG), and respiration (RESP) analysis resulted in 25 articles which examined the cause and effect of increased/reduced HRV. Reduced HRV was generally associated with increased morbidity and stress. High HRV normally indicated good health, and in some instances, it could signify clinical events of interest such as drowsiness. Effective analysis of HRV during ambulatory and motion situations such as exercise, video gaming, and driving could have a significant impact toward improving social well-being. Detection of HRV in motion is far from perfect, situations involving exercise or driving reported accuracy as high as 85% and as low as 59%. HRV detection in motion can be improved further by harnessing the advancements in machine learning techniques.

Physiological Signal Analysis and Classification of Stress from Virtual Reality Video Game.

Stress can affect a person's performance and health positively and negatively. A lot of the relaxation methods have been suggested to reduce the amount of stress. This study used virtual reality (VR) video games to alleviate stress. Physiological signals captured from Electrocardiogram (ECG), galvanic skin response (GSR), and respiration (RESP) were used to determine if the subject was stressed or relaxed. Time and frequency domain features were then extracted to evaluate stress levels. Frequency domain methods such as low-frequency (LF), high-frequency (HF), LF-HF ratio (LF/HF) are considered the most effective for HRV analysis, Poincare plots are moré discerning visually and shares a 81% correlation with LF/HF ratio. GSR is associated with EDA activity, which only increases due to stress. Stress and relax were classified using Linear Discriminant Analysis (LDA), Decision Tree, Support Vector machine (SVM), Gradient Boost (GB), and Naive Bayes. GB performed the best with an accuracy of 85% after 5 fold cross validation with 100 iterations, which is admirable from a small dataset with 50 samples.