Professional Documents
Culture Documents
A SEMINAR REPORT
ON
Bachelor of Technology
IN
Submitted By:
Bharat Pareek
19ECTCS012
BHARAT PAREEK
19ECTCS012
Sincerely,
Bharat Pareek
19ECTCS012
Introduction------------------------------------------------------------------------------6
1. Types of machine learning algorithms ----------------------------------------------------6
a. Supervised learning-------------------------------------------------------------------6
b. Unsupervised learning-----------------------------------------------------------------7
c. Reinforcement learning----------------------------------------------------------------8
2. Applications of machine learning-----------------------------------------------------------9
3. Importance of machine learning in health care-----------------------------------------12
a. Machine learning in health care--------------------------------------------------12
4. Various machine learning Algorithms used in health care----------------------------15
a. Logistic Regression------------------------------------------------------------------15
b. Random Forest-----------------------------------------------------------------------16
c. SVM------------------------------------------------------------------------------------17
d. ANN------------------------------------------------------------------------------------18
e. Decision Tree-------------------------------------------------------------------------18
f. KNN------------------------------------------------------------------------------------18
g. Clustering Algorithms-------------------------------------------------------------19
5. Technologies-----------------------------------------------------------------------------------20
a. Cloud Computing-------------------------------------------------------------------20
b. Big Data Tools------------------------------------------------------------------------20
c. Programming Languages---------------------------------------------------------20
d. Data Visualization Tools-----------------------------------------------------------20
e. Deep Learning Frameworks------------------------------------------------------20
f. GPU Computing---------------------------------------------------------------------20
6. Limitations---------------------------------------------------------------------21
7. Conclusion----------------------------------------------------------------------23
Supervised learning
Supervised learning is a type of machine learning where the algorithm is trained on labelled
data, and it learns to make predictions based on that labelled data. In supervised learning, a
dataset is provided to the algorithm where each instance in the dataset is associated with a
corresponding target variable or label. The algorithm uses this labelled data to learn patterns
and relationships between the input features and target variable.
The goal of supervised learning is to develop a predictive model that can accurately predict
the target variable for new, unseen data. This is achieved through a training process where the
algorithm learns from the labelled data, and its performance is evaluated on a validation set.
Once the model is trained and validated, it can be used to make predictions on new data.
Examples of supervised learning include classification and regression problems. In
classification, the target variable is categorical, and the goal is to predict the class of a new
instance. For example, predicting whether an email is spam or not. In regression, the target
variable is continuous, and the goal is to predict a numerical value. For example, predicting
the price of a house based on its features.
Supervised learning is a widely used technique in many applications, including natural
language processing, image classification, and fraud detection. In healthcare, it has been used
for predicting disease outcomes, diagnosing diseases, and developing personalized
treatments.
Unsupervised learning
Unsupervised learning is a type of machine learning where the algorithm learns from
unlabelled data, without any pre-existing knowledge of what the output should be. In
unsupervised learning, the algorithm is presented with a dataset that does not have any
predefined labels, and it must identify patterns and relationships in the data by itself.
The main objective of unsupervised learning is to discover hidden structures in the data and
group similar data points together. This can be achieved through clustering or dimensionality
reduction techniques. In clustering, the algorithm groups data points that are similar to each
other into clusters. In dimensionality reduction, the algorithm reduces the number of features
in the dataset, while preserving as much of the relevant information as possible.
Unsupervised learning is useful in situations where there is no labelled data available, or
where the labelling of data is too costly or time-consuming. Examples of unsupervised
learning applications include anomaly detection, market segmentation, and recommendation
systems. In healthcare, unsupervised learning has been used to identify subgroups of patients
with similar disease characteristics, to detect patterns in medical imaging data, and to identify
clusters of genes with similar functions.
While unsupervised learning can be a powerful tool for discovering patterns in large and
complex datasets, it can also be challenging to interpret the results. Without predefined
labels, it may be difficult to determine whether the patterns identified by the algorithm are
relevant or not. Therefore, unsupervised learning is often used in combination with other
techniques, such as expert knowledge or supervised learning, to ensure the accuracy and
relevance of the results.
Reinforcement learning
Reinforcement learning is a type of machine learning where an agent learns to make
decisions by interacting with an environment and receiving feedback in the form of rewards
or penalties. In reinforcement learning, the agent learns through trial and error, exploring
different actions and observing their outcomes.
The goal of reinforcement learning is to develop a policy that maximizes the cumulative
reward obtained by the agent over time. The policy is a function that maps the state of the
environment to an action. The agent starts in a given state, takes an action based on the
policy, and observes the new state and the reward associated with that action. The policy is
updated based on the observed state, action, and reward, with the goal of improving the
policy over time.
Reinforcement learning has been applied to a wide range of problems, including game
playing, robotics, and autonomous driving. In healthcare, reinforcement learning has been
used for developing personalized treatment plans for chronic diseases, optimizing drug
dosages, and controlling medical devices.
One of the key challenges of reinforcement learning is the trade-off between exploration and
exploitation. The agent needs to explore the environment to discover new actions that can
lead to higher rewards, but it also needs to exploit the actions that have already been learned
to maximize the cumulative reward. Balancing exploration and exploitation is critical for
achieving good performance in reinforcement learning.
Reinforcement learning is a promising approach for developing intelligent systems that can
learn to make decisions and adapt to changing environments. However, it also poses
challenges in terms of scalability, interpretability, and safety, which need to be addressed to
ensure its practical application in healthcare and other domains.
1. Image Recognition
Image recognition is one of the most common applications of machine learning. It is used to
identify objects, persons, places, digital images, etc. The popular use case of image
recognition and face detection is Automatic friend tagging suggestion
Facebook provides us a feature of auto friend tagging suggestion. Whenever we upload a
photo with our Facebook friends, then we automatically get a tagging suggestion with name,
and the technology behind this is machine learning's face detection and recognition
algorithm.
It is based on the Facebook project named "Deep Face," which is responsible for face
recognition and person identification in the picture.
2. Speech Recognition
While using Google, we get an option of "Search by voice," it comes under speech
recognition, and it's a popular application of machine learning.
Speech recognition is a process of converting voice instructions into text, and it is also
known as "Speech to text", or "Computer speech recognition." At present, machine learning
algorithms are widely used by various applications of speech recognition. Google assistant,
Siri, Cortana, and Alexa are using speech recognition technology to follow the voice
instructions.
Bharat Pareek 19ECTCS012 9
3. Traffic prediction
If we want to visit a new place, we take help of Google Maps, which shows us the correct
path with the shortest route and predicts the traffic conditions
It predicts the traffic conditions such as whether traffic is cleared, slow-moving, or heavily
congested with the help of two ways
Real Time location of the vehicle form Google Map app and sensors
Average time has taken on past days at the same time.
Everyone who is using Google Map is helping this app to make it better. It takes information
from the user and sends back to its database to improve the performance.
4. Product recommendations
Machine learning is widely used by various e-commerce and entertainment companies such
as Amazon, Netflix, etc., for product recommendation to the user. Whenever we search for
some product on Amazon, then we started getting an advertisement for the same product
while internet surfing on the same browser and this is because of machine learning.
Google understands the user interest using various machine learning algorithms and suggests
the product as per customer interest.
As similar, when we use Netflix, we find some recommendations for entertainment series,
movies, etc., and this is also done with the help of machine learning.
5. Self-driving cars:
One of the most exciting applications of machine learning is self-driving cars. Machine
learning plays a significant role in self-driving cars. Tesla, the most popular car
manufacturing company is working on self-driving car. It is using unsupervised learning
method to train the car models to detect people and objects while driving.
Figure 6 SVM
Figure 10 Clustering
These algorithms can be used in various applications in healthcare, such as predicting patient
outcomes, classifying patients into different disease categories, identifying optimal
Technologies
In addition to the technologies specific to healthcare, there are several more general
technologies that are commonly used in machine learning applications, including:
1.) Cloud Computing
Cloud computing platforms such as Amazon Web Services (AWS) and Microsoft Azure
provide scalable, on-demand computing resources that can be used for training and running
machine learning models.
Limitations
While machine learning has shown great promise in healthcare, there are also several
limitations that need to be considered. Here are ten limitations of machine learning in
healthcare:
1.) Data quality
Machine learning models require high-quality data to be effective, but healthcare data can
often be incomplete, inconsistent, or inaccurate.
3.) Bias
Machine learning models can be biased if the training data is biased, which can result in
disparities in healthcare outcomes for different populations.
5.) Overfitting
Machine learning models can sometimes be too complex and overfit to the training data,
which can lead to poor performance on new data.
9.) Interpretability
Machine learning models can be difficult to interpret, which can make it challenging to
explain their predictions to patients or other stakeholders.