Embedded systems
Embedded systems are special-purpose computing systems embedded in application environments or in other computing systems and provide specialized support. The decreasing cost of processing power, combined with the decreasing cost of memory and the ability to design low-cost systems on chip, has led to the development and deployment of embedded computing systems in a wide range of application environments. Examples include network adapters for computing systems and mobile phones, control systems for air conditioning, industrial systems, and cars,
Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...
Batch -13.pptx lung cancer detection using transfer learning
1. Lung Cancer Detection using Transfer Learning
PRESENTED BY
M Harinath reddy (20BF1A04E3)
P Chandana (20BF1A04H7)
M Chandu Priya (20BF1A04E0)
N Vinay (20BF1A04E6)
M Venkata Subramanyam Sastry (20BF1A04D6)
S V COLLEGE OF ENGINEERING
(AUTONOMOUS)
Karkambadi Road, Tirupati
DEPARTMENT OF ELECTRONICS AND COMMUNICATION ENGINEERING
UNDER THE GUIDANCE OF
Mr.P.Rajesh,M.Tech(Ph.D)
Assistant Professor,
Department of ECE,
SVCE,Tirupati
3. ABSTRACT
•Lung cancer remains a significant global health concern, with early
detection playing a pivotal role in improving patient outcomes.
•This abstract presents a novel approach to lung cancer detection
through the application of transfer learning in medical imaging analysis.
•Transfer learning leverages pre-trained deep neural networks, fine-
tuning them on a dataset of lung images to enhance classification
accuracy.
•Transfer learning allows us to benefit from the feature extraction
capabilities of the pre-trained model.Our experimental results
demonstrate the effectiveness of transfer learning in lung cancer
detection and also high accuracy, sensitivity, and specificity.
4. EXISTING SYSTEM
•Existing system of lung cancer detection using machine learning
algorithms such as Support vector machines(SVM) have been shown
to be effective in detecting lung cancer in medical images.
•Support vector machine (SVM) is a supervised machine learning
algorithm that can be used for both classification and regression tasks.
•It is partict separates the data points into two or more classes.
• The algorithm is effective in handling high-dimensional feature
spaces and is particularly useful in scenarios with limited annotated
datasets.
5. DRAWBACKS OF EXISTING SYSTEM
•Need for large and high-quality datasets: SVM models are trained on
data, and the accuracy of the model depends on the quality and
quantity of the data.
•Overfitting: SVM models are prone to overfitting, which occurs when
the model learns the training data too well and is unable to generalize
to new data. This can lead to poor performance on real-world data.
•Continuous Model Updating: Medical knowledge evolves over time,
leading to changes in diagnostic criteria and practices. Machine learning
models need to be continuously updated to reflect the latest standards,
which can be resource-intensive.
6. DRAWBACKS OF EXISTING SYSTEM
•False Positives and False Negatives: SVM models can be trained
to be very accurate, but they are not perfect. There is always a risk
of false positives (i.e., the model predicts that a patient has cancer
when they do not) and false negatives (i.e., the model predicts that
a patient does not have cancer when they do) .
•Lack of interpretability: SVM models can be complex and
difficult to interpret, making it difficult to understand why the
system makes certain decisions..
8. PROPOSED SYSTEM
•The system is trained on a dataset that is split into three parts:
training set, validation set, and testing set.
•The dataset is split into training, validation, and testing sets. The
training set is typically the largest set, followed by the validation set
and the testing set.
• The training set is used to train the neural network model. The
validation set is used to evaluate the performance of the model
during training and to tune the hyperparameters. The testing set is
used to evaluate the final performance of the model.
•Data augmentation is a technique used to increase the size and
diversity of the training set.
9. PROPOSED SYSTEM
•So this can help to improve the performance of the model by
preventing overfitting.
•The neural network model is trained on the augmented training
set.
•The neural network learns to predict the segmentation masks and
class labels for the input images.
•Now ,the trained neural network is used to segment images into
different regions.Then the Features are extracted from the
segmented images.
•Finally the extracted features are used to classify the images into
different categories.
11. TOOLS USED
Python programming: Python is a high-level, general purpose
programming language used for readability , simplicity and versatility.
IDE : Pycharm , Jupyter notebook
Operating System : Windows 11 ,64-bit operating system.
Libraries used: numpy,pandas ,tensorflow, keras, open CV,matplotlib
Pre-trained models: VGG16,MobileNet, Inception or efficientnet