Stress Analysis Using Machine Learning

Stress is one of the major health issues of the world and one of the major reasons for committing suicide. Also, it leads to other mental health issues such as depression, anxiety etc., and damage to organs related to respiratory, cardiovascular and nervous systems. In recent years, stress has impacted many individuals due to the pandemic situation. Since the governments across the globe had started to impose lockdowns, the levels of stress significantly raised because of the disturbances led by covid infections, losing loved ones, continuous engagement with laptops and mobiles etc. It is also found that stress has not only disturbed the health condition but also disturbed the relationships and became a self-destruction component. This project is aimed to help those people to understand their stress and consult a psychologist at right time to overcome the situation. Though stress is an active area of research and achieved high performance of models, those were based on signal and speech which were computationally costlier and text-based research work using a state-of-the-art model called the BERT has achieved an f1-score i.e. 80.65%. This project focuses on text-domain and uses open-sourced Stress Analysis on Social Media dataset available on Kaggle which contains 3.6 K samples. In this project, both Machine Learning and Deep Learning Models were trained with 80% of the data and validated with 20% of the data. After, optimization and evaluation of several models, the best model has achieved a benchmark result of 83.74% f1-score on test data using a new network architecture i.e. combination of stacked Transformer Encoder layers with stacked Bi-directional-LSTM. In addition to this, an explainable AI has been implemented for an embedding layer to inspect input attributions in predicting the results. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

FPGA-Based Deep Learning Models for Analysing Corona Using Chest X-Ray Images

Coronavirus is a large family of viruses that affects humans and damages respiratory functions ranging from cold to more serious diseases such as ARDS and SARS. But the most recently discovered virus causes COVID-19. Isolation at home or hospital depends on one's health history and conditions. The prevailing disease that might get instigated due to the existence of the virus might lead to deterioration in health. Therefore, there is a need for early detection of the virus. Recently, many works are found to be observed with the deployment of techniques for the detection based on chest X-rays. In this work, a solution has been proposed that consists of a sample prototype of an AI-based Flask-driven web application framework that predicts the six different diseases including ARDS, bacteria, COVID-19, SARS, Streptococcus, and virus. Here, each category of X-ray images was placed under scrutiny and conducted training and testing using deep learning algorithms such as CNN, ResNet (with and without dropout), VGG16, and AlexNet to detect the status of X-rays. Recent FPGA design tools are compatible with software models in deep learning methods. FPGAs are suitable for deep learning algorithms to make the design as flexible, innovative, and hardware acceleration perspective. High-performance FPGA hardware is advantageous over GPUs. Looking forward, the device can efficiently integrate with the deep learning modules. FPGAs act as a challenging substitute podium where it bridges the gap between the architectures and power-related designs. FPGA is a better option for the implementation of algorithms. The design attains 121μW power and 89 ms delay. This was implemented in the FPGA environment and observed that it attains a reduced number of gate counts and low power. © 2022 Anupama Namburu et al.

Using CNN and YOLO Detect Face Mask and Social Distance Along With Temperature

The COVID-19 is an unparalleled crisis leading to huge number of problems. To reduce the spread of corona virus people are advised to wear masks when surrounded by people to protect themselves. This makes face recognition very difficult since certain parts of face are hidden. Many new algorithms are devised using convolutional architecture to make face recognition accurate as possible. This convolutional architecture has made it possible to extract even pixel details. Designed a binary face classifier which can detect any face present in the frame irrespective of its alignment beginning from RGB image of any size.The method involves training through fully convolutional networks it detects multiple facial images in a single frame and also proposes a model to detect social distance using visualisation deep learning network. CNN and YOLO algorithms are used to detect face mask and social distance between persons respectively. Arduino controller and LM35 sensor is used to detect body temperature which alerts if temperature is above predefined value.

Analysis and prediction of COVID-19 disease using CNN-ResNet algorithm

In this paper presents the deep learning diagnostic functions for chest x-rays and a COVID-Net-based image classifier for classifying chest x-ray images. In this article, we use model integration and transfer learning to classify chest x-rays in two ways: covid and non-covid. CNN can be used to make our result, which is more sensitive than radiologists in the detection and diagnosis of lung modules. According to the precision and loss value, choose the CNN model with good effect for the fusion and dynamically improve your weight ratio during the training process. This algorithm, using the RESNET50 model, is more sensitive than radiologists in screening and diagnosing lung modules.

Analysis of COVID-19 pandemic - Origin, global impact and Indian therapeutic solutions for infectious diseases

The first case of COVID-19 was reported in China in December 2019(ref. 1) and almost 213 countries have reported around 5,350,000 COVID-19 cases all over the world, with the mortality rate up to 3.4% as of May 23,2020. On March 11, 2020, the WHO (World Health Organization) declared COVID-19 as a global pandemic. Moving towards from epidemic to global pandemic situation just in two months, COVID-19 has caused tremendous adverse effects on people's well being and the economy all over the world. Scientists and researchers around the globe have a vested interest in researching and mitigating to handle the dire situation. This paper covers the COVID-19's origin, characteristics of the virus and reasons behind the outbreak, and precautionary measures that have to be followed to handle the critical situation. Several therapeutic solutions in the Indian healing tradition have been discussed to improve the immune system in order to equip ourselves to deal with the outbreak of COVID-19.

A Machine Learning Approach to Analyze COVID 2019

COVID 2019 is a family of Human Corona Virus and it is disrupting human lives across the world. It even started affecting countries other than China at higher rate of transmission. The origin of COVID 2019 is not yet clear and no scientific medication is available for cure. We analyzed the Corona dataset which is of more than 3000 X 5 dimensions by applying Time Series Analysis and Regression Models. We could predict the futuristic trend and further propose a design of the dataset for getting more insights of the pandemic unanswered questions. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.