CCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdf
MANOJ H internship ppt.pptx
1. Sri Srinivasa Educational and Charitable Trust®
SAPTHAGIRI COLLEGE OF ENGINEERING
(Affiliated to VTU, Belagavi, and Recognized by AICTE, New Delhi)
(Accredited by NAAC with “A” Grade), (Accredited by NBA)
(ISO 9001-2015 and 14001-2015 Certified Institute)
Bengaluru-560057, Karnataka, India.
DEPARTMENT OF ELECTRONICS & COMMUNICATION ENGINEERING
Internship presentation
On
Air quality Monitoring using Machine Learning
Under the guidance of:
Prof Shilpa V
Assistant Professor
Dept. of ECE
MANOJ H [1SG19EC052]
PRESENTED BY
1
3. INTRODUCTION
Air Quality is a crucial aspect of Environmental Monitoring and
Machine Learning has shown Great promise in improving accuracy
and efficiency of Air Quality Monitoring
Accuracy plays an important role in prediction. Although many
algorithms are available for this purpose, selecting the most accurate
one continues to be the fundamental task in getting the best results.
Machine Learning Algorithms can Analyze large dataset of air quality
and identify patterns that would be difficult for humans to detect
3
4. Training the algorithms, executing them, getting the results, comparing various
performance parameters of these algorithms and finally obtaining the most
accurate one is necessary for the System to be efficient
Air Quality Index (AQI) is a tool for effective communication of air quality
status to people can easily understand and take action.
4
5. OBJECTIVE
The main purpose of the prediction is to make advancement in technology
artificial intelligence based algorithms are being widely used for prediction purpose
especially for air quality forecasting.
A machine Learning approach takes into account in identifying sources of pollutants
Enhancing Existing Air quality models
5
6. Company profile
TAKE IT SMART (OPC) PVT.LTD is an Indian based engineering and
Software Company headquartered in Bangalore, Karnataka, India. It is both
product and service oriented software company.
All offices employ an experienced team of professionals, with an outstanding
track record of handling complex web & Apps. development projects.
The company was legally registered in the year 2021, but it made its humble
beginning in the year 2018 with a team of Two members.
6
8. WORKING
Machine Learning algorithms can be used to monitor air quality in real time by
analyzing data from sensors placed at different locations These algorithms
provide real time alerts when air quality level exceeds certain threshold levels
Linear Regression is one of the most popular machine learning algorithms . It is
a statistical method used for predictive analysis
8
9. WORKING
Logistic Regression can be used for various classification problems such as spam
detection. Diabetes prediction, if a given customer will purchase a particular
product or will they churn another competitor
Logistic Regression is one of the most simple and commonly used Machine
Learning algorithms for two-class classification. It is easy to implement and can be
used as the baseline for any binary classification problem.
Its basic fundamental concepts are also constructive in deep learning. Logistic
regression describes and estimates the relationship between one dependent binary
variable and independent variables.
9
12. METHODOLOGY
Preparing Data for Model Preparation
Three common evaluation metrics for regression problems:
Mean Absolute Error (MAE) is the mean of the absolute
value of the errors
ln∑i=ln|yi – y^i| ln ∑I = ln|yi –
y^i|
Mean Squared Error (MSE) is the mean of the squared
errors, MSE "punishes" larger errors, which tends to be
useful in the real world
ln ∑i=1(yi-y^i)2ln ∑i=ln(yi-y^i)2
Root Mean Squared Error (RMSE) is the square root of the
mean of the squared errors, RMSE is interpretable in the
"y" units ln ∑i=1(yi-y^i) 12
14. At higher SLP ,the PM2.5 values tend to raise beyond the acceptable level
14
15. Matplotlib Library was used for data visualization and there was repetition in the
dataset after index 700
visualization of data PM2.5 with NO Duplicates of data
15
16. CONCLUSION
Successful prediction of Air quality and Sources of pollutant
were identified by using various machine learning algorithms and
accuracy was compared
Linear regression gave an accuracy of 97% hence it was used and
able to predict the Air quality
16
17. b FUTURE SCOPE
In the coming years various sensors like ozone sensor and gas
sensors can be used to monitor air quality in real time by
analyzing data from sensors placed at different locations and with
the use of machine learning it can provide real time alerts when it
exceeds the threshold value
17