Scribd
Upload
14 views30 pages

Minor Project

Uploaded by

ginni bhayana
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
14 views30 pages

Minor Project

Uploaded by

ginni bhayana
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 30

web based skin type

prediction system using


machine learning

INSTITUTE OF INFORMATION TECHNOLOGY &


MANAGEMENT NEW DELHI,110058
BATCH (2022-2025)

Submitted to: Submitted by:


Dr. Harmeet Malhotra Kashika Bhayana
BCA-V E
35321102022
Table of contents
Objective
Overview of machine learning
About Dataset
Result &
Discussion
Conclusion
Future scope
Objective
Skin type classification is a crucial aspect of skincare and dermatology.
Accurately identifying skin type (e.g., normal, oily, dry, combination) helps
individuals select appropriate skincare products and routines. This system
aims to leverage machine learning techniques to develop a web-based
application that can predict skin type based on user-provided information
about their skin characteristics. B y analyzing factors like skin texture,
oiliness, sensitivity, and other relevant parameters, the system can provide
personalized recommendations for skincare products and routines.
What is Machine Learning?
Machine learning (ML) is a f ield of study in artif icial
intelligence concerned with the development and study
of statistical algorithms that can learn from data and generalize to
unseen data and thus perform tasks without explicit instructions.
It is also known as subset of Artif icial Intelligence.
ML can find patterns and insights in large datasets
that might be difficult for humans to discover.
Types of Machine Learning
The types of Machine Learning are:-
1.Supervised Learning
2. Unsupervised Learning
3. Reinforcement Learning
Supervised Learning
Supervised learning is defined as when a model gets trained
on a “Labelled Dataset”.
Labelled datasets have both input and output parameters.
In Supervised Learning algorithms learn to map points
between inputs and correct outputs.
It has both training and validation datasets labelled.
Types of Supervised Learning
Supervised learning is categorised into Two types:
1. Regression
2.Classification
1.Regression: Regression algorithms are used if there is a
relationship between the input variable and the output variable.
It is used for the prediction of continuous variables, such as Weather
forecasting, Market Trends, etc.
2.Classification: Classification algorithms are used when the output
variable is categorical, which means there are two classes such as Yes-No,
Male-Female, True-false, etc.
Regression
The regression include some common algorithms that are:
1.Linear Regression
2. Decision Tree Regressor
3. Random Forest Regressor

Classification
The Classification include some common algorithms that are:
1.Logistic Regression
2. Decision Tree Classifier
3. Random Forest Classifier
Unsupervised Learning
Definition: Unsupervised learning algorithms are trained on data without
labeled responses. The goal is to identify patterns and relationships in the
data.
Applications: Commonly used for clustering (e.g., customer
segmentation) and association (e.g., market basket analysis).
Examples: K - means clustering, hierarchical clustering, and principal
component analysis (PCA).
Reinforcement Learning
Definition: In reinforcement learning, an agent learns to make
decisions by performing actions and receiving feedback in the
form of rewards or penalties.
Applications: Widely used in robotics, game playing, and
real-
time decision-making systems.
Examples: Q-learning, deep Q-networks (DQNs), and policy
gradient methods.
About Dataset
Skin type Prediction - This dataset is sourced from Kaggle.com
The dataset includes sample data for the first five entries, showcasing a variety of
ages, time spent outdoors, sleep duration, water intake, sunscreen usage frequency,
and skin types.
Dataset Summary
Total Entries: 12, 0 0 0
Total Columns: 6
Columns and Data Types
Age: Represents the age
of individuals in the
dataset
Time Spent Outdoors: Indicates the amount of time (in hours) individuals
spend outdoors.
Sleep Duration: Represents the duration of sleep (in hours) for individuals.
Water Intake: Measures the amount of water intake (in liters) by individuals.
Sunscreen Usage Frequency: Indicates the frequency of sunscreen usage, with
higher numbers representing more frequent use.
The steps involved in the process Machine
Learning algorithms are:
1.Aim
2. Gather Information of the dataset
3. Do the following steps:
- Data Manipulation
- Data Visualization
- Data Cleaning
4. Divide the columns into Independent and dependent
features
5. Train and Test Split
6. Standard Scaling
7. Model Building
8. Train model
9. Test
1.
Aim skin type prediction system using
The aim of the project is to develop a web-based
machine learning algorithms.

2. Importing the csv file


In cell[1]: The csv file is imported
3.Gathering Information
Cell[2]: To gather the information

4. Data Manipulation/visualization
It involves steps like-checking null values, duplicated values, outliers

cell[3]: To check the null values


cell[4]: To check the duplicated values cell[5]: To check the outliers
cell[5]:The outliers are checked

Note: Therefore, No manipulation is done in this


data as It does not contain any null or
duplicated values and outliers.
Representation of Boxplot for each
column

5.Multiclassification
Cell[11]:Classification of Categorical column into numerical to perform classification model
6. Division of Dependent & Independent features
cell[15]: The columns are divided into x and y , x represents the dependent features and
y represents the independent.

7. Train and Test split


Cell[19]: To divide the x into x train, x test and y into y train, y
test
multiclassification Logistic Regression

↑
score
Decision Tree Classifier

↑
score
Random forest classifier

↑
scor
e
K nearest neighbour (knn)

↑
score
Naive bayes

↑
score
Support vector Machine

↑
score
Accuracy table
The accuracy score table according to all classification models
Graphical representation
Visual graphical representation of accuracy according to all models
Prediction table
User Input prediction
Conclusion
In conclusion, the web-based skin type prediction system using machine learning
provides a promising solution for personalized skincare. B y utilizing advanced
machine learning algorithms, the system is capable of accurately predicting skin
types based on various user inputs, offering valuable insights into individual
skincare needs. This not only enhances user experience but also allows for more
tailored skincare recommendations, improving overall skin health. As technology
continues to evolve, the integration of machine learning in skincare applications
has the potential to revolutionize the way individuals approach skincare routines,
making them more efficient and scientifically driven. Further improvements and
refinements can expand the system's capabilities, ensuring even more accurate
predictions and recommendations..
Future scope
The future scope of the web-based skin type prediction system using machine learning is
vast and promising. Some potential areas for future development include:
Integration with IoT Devices: The system can be enhanced by integrating with wearable
devices or smart sensors to gather real-time data on skin conditions, such as moisture
levels, temperature, and U V exposure, allowing for more accurate and dynamic skin type
predictions.
Incorporation of More Data Variables: The system can be expanded to consider
additional factors such as lifestyle, diet, and genetic predispositions, which can influence
skin health and type, providing even more precise and personalized recommendations.
Real-Time Skin Condition Monitoring: B y incorporating image recognition and
computer vision technologies, the system could allow users to upload photos of their
skin and analyze changes over time, offering real-time skin condition monitoring.
ThanK

You might also like