Professional Documents
Culture Documents
Review 1
Review 1
Name: Haricharan
Reg.No: 20BCE2728
B.Tech.
in
®
ABSTRACT:
Mental health prediction is one of the most essential parts of reducing the probability of
serious mental illness. Stress has always been an important and challenging issue,
especially in the case of students. Computer science has a advance to a great degree in a
last few years. It is to great degree large and multifaceted. It has been applied to wide
number of application creating to the basic needs of human society. In healthcare, vast
development have been made with the use of machine learning. Stress is a fatal disease
causing a considerable number of fatalities across the world. The machine learning enable
the prediction of the possibility of stress prediction in the under studies of students like,
graduate, hostler, financial issues and academic issues. In this paper we analyze the
performance of machine learning techniques to reduce the risk of stress prediction resulting
in early stage of the understudies students.The data set was collect from university, it
collected from more than 200 student’s data and the collected data is based upon the
educational status of the student and about their personal life . ML model like RF and
Decision tree model is implemented and comparison is done based upon the accuracy.
INTRODUCTION:
There are different types of sources of stress but three are commonly found in everyone
that’s are external stress, environmental stress, physical stress.
The Environment Stressor: The external stress can be occurred because by the
environment stressor, when the person is unable to respond to the external and internal
stimulus or situation it causes the stress. The examples includedisturbance in the
environment, crowding, cold and hot weather, traffic, high number of crimes in the
societies, pollution and pandemic viruses.
Social Stressor: Every individual lives in the society and interact with many people in
their day to day life. The external stressor can become the source of stress in the individual
life which includes- Hot and cold climate, natural disasters, criminal offence,
contamination, death. This kind stressors are happened by the earth and humans have no
control over these kinds of stressors.
The main software used in a typical Python machine learning pipeline can consist of
almost any combination of the following tools:
EXISTING SYSTEM
A decision tree is a supervised machine-learning algorithm so that means the data set
should be labelled. In KNN algorithm, the classification is done based on a set of rules. In
KNN Algorithm following steps are taken in the first step a tree will be constructed which
will have input features as its nodes. In the next step, it will select a feature from the input
features for predicting the output, which gives the highest information gain. Now use the
above steps for the creation of n values by making use of the features, which are not used
earlier.
OBJECTIVE:
The objective of the project is to develop a machine learning-based system for predicting
student stress levels in universities. By leveraging data from various sources such as
academic records, social interactions, and behavioral patterns, the system aims to identify
students at risk of experiencing high levels of stress. The primary goal is to provide timely
interventions and support mechanisms to mitigate stress-related issues, thereby promoting
the overall well-being and academic success of students. Through predictive analytics and
proactive measures, the project seeks to contribute to creating a healthier and more
supportive learning environment within the university community.
PROBLEM STATEMENT:
The problem statement of this project revolves around the pressing issue of student stress
in universities. Despite efforts to support student well-being, stress remains a significant
concern impacting academic performance and mental health. The project aims to address
this challenge by developing a machine learning-based system capable of predicting
student stress levels. By leveraging diverse data sources such as academic records, social
interactions, and behavioral patterns, the system will identify students at risk of
experiencing heightened stress. This predictive capability will enable timely interventions
and support mechanisms tailored to individual needs, fostering a healthier and more
resilient university community. Ultimately, the project seeks to alleviate the detrimental
effects of stress on students' academic success and overall well-being, enhancing the
quality of their educational experience.
LITERATURE SURVEY:
TITLE: Deep Learning for Time Averaged Wall Shear Stress Prediction In Left Main
Coronary Bifurcations
YEAR:2020
AUTHOR: RamtinGharleghi, GihanSamarasinghe, ArcotSowmya, Susann Beier
DESCRIPTION:
Analysing blood flow in coronary arteries has often been suggested in aiding the prediction
of cardiovascular disease (CVD) risk. Blood flow induced hemodynamic indices can
function as predictive measures in this pursuit and a fast method to calculate these may
allow patient specific treatment considerations for improved clinical outcomes in the
future. In vivo measurements of these metrics are not practical and thus computational fluid
dynamic simulations (CFD) are widely used to investigate blood flow conditions, but
require costly computation time for large scale studies such as patient specific
considerations in patients screened for CVD. This paper proposes a deep learning approach
to estimating the well-established hemodynamic risk indicator time average wall shear
stress (TAWSS) based on the vessel geometry. The model predicts TAWSS with good
accuracy, achieving cross validation results of average Mean Absolute error of 0.0407 Pa
and standard deviation of 0.002 Pa on a 127 patient CT angiography dataset, while being
several orders of magnitude faster than computational simulations, using the vessel radii,
angles between bifurcation (branching) vessels, curvature and other geometrical features.
This bypasses costly computational simulations and allows large scale population studies
as required for meaningful CVD risk prediction.
TITLE: A Deep Learning Approach Replacing the Finite Difference Method for In
situ Stress Prediction
YEAR:2020
AUTHOR: WenliGao, Xinming Lu, Yanjun Peng, And Liang Wu
DESCRIPTION:
In the domain of geotechnical engineering analysis, fast Lagrangian analysis based on the
finite difference method is the most commonly used numerical analysis method. It is a
classical numerical algorithm applied to calculate the in situ stress. In this paper, we
propose a deep learning (DL) architecture called the enhance-and-split feature capsule
network embedded in fully convolutional neural networks (ES-Caps-FCN) to predict the
in situ stress for a strain-softening model when using the finite difference method for the
numerical computation. Experiments indicate that this novel approach is stable and
convergent. Compared with some classical prediction methods including linear regression
analysis and a deep neural network, the mean squared error of our proposed algorithm is
as low as 0.059866%, which is lower than the 0.616676% of the deep neural network
prediction algorithm and the 0.978495% of the conventional machine learning algorithm.
Additionally, the calculation efficiency of fully trained deep learning models is superior to
that of the conventional finite difference method. Therefore, DL is a feasible and promising
fast and accurate surrogate for the finite difference method for solving the in situ stress.
DESCRIPTION:
While accurately predicting mood and wellbeing could have a number of important clinical
benefits, traditional machine learning (ML) methods frequently yield low performance in
this domain. We posit that this is because a one-size-fits-all machine learning model is
inherently ill-suited to predicting outcomes like mood and stress, which vary greatly due
to individual differences. Therefore, we employ Multitask Learning (MTL) techniques to
train personalized ML models which are customized to the needs of each individual, but
still leverage data from across the population. Three formulations of MTL are compared:
i) MTL deep neural networks, which share several hidden layers but have final layers
unique to each task; ii) Multi-task Multi-Kernel learning, which feeds information across
tasks through kernel weights on feature types; and iii) a Hierarchical Bayesian model in
which tasks share a common Dirichlet Process prior. We offer the code for this work in
open source. These techniques are investigated in the context of predicting future mood,
stress, and health using data collected from surveys, wearable sensors, smartphone logs,
and the weather. Empirical results demonstrate that using MTL to account for individual
differences provides large performance improvements over traditional machine learning
methods and provides personalized, actionable insights.
YEAR:2019
AUTHOR: FaridRazzak, Fei Yi, Yang Yang, HuiXiong
DESCRIPTION:
Since the financial crisis in late 2008-2009, several global regulatory authorities have
mandated stress-testing exercises to evaluate the potential capital shortfalls & systemic
impacts that large banks may face during adverse economic conditions. Thus, having the
ability to analyze economic conditions & banking performance profiles together to
determine relationships among their respective features may provide insights for
stresstesting tasks. In this paper, we propose an Integrated Multimodal Bank Stress Test
Prediction (IMBSTP) model framework consisting of a two-stages; (1) economic
conditions estimator to approximate joint representation among the exogenous factors
using generative models, (2) bank capital & loss forecaster to project stresstest measures
based on dimensional & temporal features selected from the exogenous economic
conditions & banking performance profiles using a dual-attention recurrent neural network.
Extensive experimentation is performed on historical economic conditions & consolidated
financial statements of U.S. bank holdings companies to show the effectiveness of our
approach when compared to state-of-the-art baseline methods.
YEAR:2019
AUTHOR: MahyaMirbagheri, Ata Jodeiri, NaserHakimi, VahidZakeri,
SeyedKamaledinSetarehdan
DESCRIPTION:
Stress is known as one of the major factors threatening human health. A large number of
studies have been performed in order to either assess or relieve stress by analyzing the brain
and heart-related signals. In this study, signals produced by functional Near-Infrared
Spectroscopy (fNIRS) of the brain recorded from 10 healthy volunteers are employed to
assess the stress induced by the Montreal Imaging Stress Task by means of a deep learning
system. The proposed deep learning system consists of two main parts: First, the one-
dimensional convolutional neural network is employed to build informative feature maps.
Then, a stack of deep fully connected layers is used to predict the stress existence
probability. Experiment results showed that the trained fNIRS model performs stress
classification by achieving 88.52 ± 0.77% accuracy. Employment of the proposed deep
learning system trained on the fNIRS measurements leads to higher stress classification
accuracy than the existing methods proposed in fNIRS studies in which the same
experimental procedure has been employed. The proposed method suggests better stability
with lower variation in prediction. Furthermore, its low computational cost opens up the
possibility to be applied in real-time stress assessment.
MODULES
• Data collection
• Data pre-processing
• Feature extraction
• Classification
• Performance evaluation
DATA COLLECTION:
In the initial phase of our project titled "Predicting Student Stress," we focus on data
collection. This crucial step involves sourcing and refining datasets essential for our
predictive model. We prioritize datasets encompassing previous academic records and
indicators of student well-being. Evaluation of datasets, including those available on
platforms like Kaggle, guides our selection process. Integration of the chosen dataset into
our predictive model lays the groundwork for accurate stress level predictions, marking the
commencement of our project's implementation phase.
FORMATTING
You may not have chosen the details in a format that suits you for working with.
The data may also be in in an electronic database and you would like it to be in a
spreadsheet, or the information may be in a proprietary file format and you would like it
to be in an electronic database or folder.
CLEANING
Cleaning data is the eradication or restoration of unfinished or empty data. There may
also be incomplete occurrences of data which do not carry the information that you think
you'd like to lever may need to eliminate these occurrences. In addition, there are
attributes which carry sensitive information and that the attributes are likely to be omitted.
DATA-PRE PROCESSING:
Data pre-processing is a part of machine learning, which involves transforming raw data
into a more coherent format. Raw data is usually, inconsistent or incomplete and usually
contains many errors. The data pre-processing involves checking out for missing values,
looking for categorical values, splitting the dataset into training and test set and finally
do a feature scaling to limit the range of variables so that they can be compared on
common environs. In this paper we have used is null() method for checking null values
and lable Encoder() for converting the categorical data into numerical data
FEATURE EXTRACTION:
A new method to detect malicious Android applications through machine learning techniques by
analyzing the extracted permissions from the application itself. Features used to classify are the
presence of tags uses-permission and uses feature into the manifest as well as the number of
permissions of each application. These features are the permission requested individually and the
«usesfeature» tag.the possibility of detection malicious Android applications based on permissions
and 20 features from Android application packages.
MODULE DIAGRAM:
ALGORITHM USED:
• Random forest algorithm
One of the most important features of the Random Forest Algorithm is that it can handle
the data set containing continuous variables as in the case of regression and categorical
variables as in the case of classification. It performs better results for classification
problems.
Step 1: In Random forest n number of random records are taken from the data set having k
number of records.
CONCLUSION
Students are the victim of massive amounts of stress and this is increasing at an alarming rate
with the ever growing competition on the educational grounds. This surfaces other problems such
as peer pressure, parental expectations, health issues and many more. The tender minds of the
studentswouldbe subjected to these parameters and they won't be able to cope up well without the
right guidance. Our work is an aid which helps in predicting the stress levels due to various
parameters considered through a survey and it also lists as to whether the students are stress free
or stressful and the range of their stress levels. This is accurately done with the RF & Decision tree
classification algorithm. This Machine Learning model holds an accuracy of 94%. Not just
identifying the parameters and measuring the stress levels, our work tops this up by giving each
student the appropriate solution for his or her grief. The student can incorporate the solution and
work towards maintaining his or her mental equilibrium.
REFERENCES:
5. Liu, David, and Mark Ulrich. "Listen to Your Heart: Stress Prediction Using Consumer Heart
Rate Sensors." Online] 2014.
6. Subhani, Ahmad Rauf, WajidMumtaz, Mohamed Naufal Bin Mohamed Saad, NidalKamel, and
Aamir Saeed Malik. "Machine learning framework for the detection of mental stress at multiple
levels." IEEE Access 5 (2017): 13545-13556.
8. Adnan, Nadia, et al. "University students stress level and brainwave balancing index:
Comparison between early and end of study semester." Research and Development (SCOReD),
2012 IEEE Student Conference on. IEEE, 2012.
9. U Srinivasulu Reddy, Aditya vivekThota, Adharun,” Machine learning Techniques for Stress
prediction in working employee” 2018 IEEE International Conference on computational
intelligence and computing research.
10. Senthiil, P. V., VS AakashSirusshti, and T. Sathish. "Equivalent stress prediction of automobile
structural member using feaann technique." International Journal of Mechanical and Production
Engineering Research and Development 9.2 (2019): 757-768.
11. G. Mikelsons, M. Smith, A. Mehrotra, M. Musolesi, “Towards deep learning models for
psychological state prediction using smartphone data: Challenges and opportunities, 2017.
12. R. Wang, G. Harari, P. Hao, X. Zhou, and A. T. Campbell. SmartGPA: how smartphones can
assess and predict academic performance of college students. In UbiComp’15, 2015.