Available courses

The demand for Machine Learning Engineers/AI specialists in the field of Medicine, Healthcare, and Public Health experiencing rapid growth.  

Start a career in Medical/Healthcare with the Techtern Applied ML in Medical Diagnosis and build a robust foundation for a great career


Problem Statement :

Can we accelerate the capacity and speed of medical professionals to diagnose diseases from X-rays and MRI brain scans? Achieving this capability can potentially minimize the cases of misdiagnosis, long wait times for patients, and clinic throughput


Aim :

This project portfolio consists of two projects designed to improve your mastery of ML-based mdeical diagnosis


In the first project, you will develop an ML model that detects disease conditions from chest X-rays.

A second project will improve your skill in developing models to identify, locate, and size tumors from MRI scans

 

Project Contents :

Dataset Information

Image pre-processing and Exploratory Data Analysis (EDA)

Modeling

Conclusion


What you will learn :

Application of Deep learning techniques for chest X-Ray Medical Diagnosis

Evaluation Techniques of Diagnostic Models

Brain Tumor Auto-Segmentation for Magnetic Resonance Imaging (MRI)


Heart failure prediction project focused on developing a full-stack deployable machine learning model to predict the onset of heart failure in patients.

This project includes the development of a core model and the implementation of a chatbot complete with a front and back end and API endpoints for serving the model to patients and the backend for sending notifications to doctors


According to the World Health Organization, 12 million deaths occur yearly due to heart disease. Load of cardiovascular disease is rapidly increasing all over the world in the past few years. Early detection of cardiac diseases can decrease the mortality rate and overall complications. However, it is not possible to monitor patients every day in all cases accurately and consultation with a patient for 24 hours by a doctor is not available since it requires more patience, time and expertise.

Our Heart Failure Prediction System is intended to assist patients in recognizing their heart state early and receiving treatment at an earlier stage, allowing them to avoid any serious conditions. We have designed this system using the Machine Learning model to predict the future possibility of heart disease by implementing the Logistic Regression algorithm.
The framework used in this project is Django. The Front End involves Html, CSS and JavaScript. The Back End involves MySQL Database. The Back End Language is Python

The user would need to register first to log into the system. For the system to predict if there is heart failure or not, the user would require to give inputs. The parameters include Age, Sex, Chest Pain Type, Resting BP, Cholesterol, Fasting BS, Resting ECG, Maximum Heart Rate, Exercise-induced Agina, Oldpeak, and the slope of the peak exercise ST segment. After the user provides all these inputs, the system will detect if there is any heart disease. The chatbot in the system will inform the user about the causes of heart failure, and the diagnosis test required. It will also provide links to nearby hospitals/clinics that specializes in heart disease. The user can also check out some free checkup camps.

The admin can log in using their credentials. They can view the users using the system. They can also add free checkup camp details. We have used Logistic Regression to develop this system. It is a significant machine learning algorithm because it can provide probabilities and classify new data using continuous and discrete datasets.

 

Advantages

  • The system is easy to maintain.
  • It is user-friendly.
  • Users can search for a doctor’s help at any point in time.
  • Very useful in case of emergency.
  • They can also look for free check-up camps.


Requirements:

Basic knowledge of python required


Learn how to organize and implement a classification model to predict if a patient is prone to heat failure.

You will work with dirty data and progressively transform it into clean data, learn to conduct simple feature engineering, and master 5 algorithms


Problem Statement :

With a plethora of medical data available and the rise of Data Science, a host of startups are taking up the challenge of attempting to create indicators for the foreseen diseases that might be contracted! Cardiovascular diseases (CVDs) are the number 1 cause of death globally, taking an estimated 17.9 million lives each year, which accounts for 31% of all deaths worldwide. Heart failure is a common event caused by CVDs. People with cardiovascular disease or who are at high cardiovascular risk (due to the presence of one or more risk factors such as hypertension, diabetes, hyperlipidemia or already established disease) need early detection and management wherein a machine learning model can be of great help. In this way, we try to solve and automate another problem that occurs in nature with a view to counter it and focus on the next problem with the help of AI techniques!

Aim :

  • Classify/predict whether a patient is prone to heart failure depends on multiple attributes.
  • It is a binary classification with multiple numerical and categorical features.
Dataset Attributes
  • Age: age of the patient [years]
  • Sex: sex of the patient [M: Male, F: Female]
  • ChestPainType: chest pain type [TA: Typical Angina, ATA: Atypical Angina, NAP: Non-Anginal Pain, ASY: Asymptomatic]
  • RestingBP: resting blood pressure [mm Hg]
  • Cholesterol : serum cholesterol [mm/dl]
  • FastingBS: fasting blood sugar [1: if FastingBS > 120 mg/dl, 0: otherwise]
  • RestingECG: resting electrocardiogram results [Normal: Normal, ST: having ST-T wave abnormality (T wave inversions and/or ST elevation or depression of > 0.05 mV), LVH: showing probable or definite left ventricular hypertrophy by Estes' criteria]
  • MaxHR: maximum heart rate achieved [Numeric value between 60 and 202]
  • ExerciseAngina: exercise-induced angina [Y: Yes, N: No]
  • Oldpeak : old peak = ST [Numeric value measured in depression]
  • ST_Slope: the slope of the peak exercise ST segment [Up: upsloping, Flat: flat, Down: downsloping]
  • HeartDisease: output class [1: heart disease, 0: Normal]

 
 
 

Project Contents :

  • Dataset Information
  • Exploratory Data Analysis (EDA)
  • Summary of EDA
  • Modeling
  • Conclusion

What you will learn :

  • Data Visualization
  • Data Scaling
  • Statistical Tests for Feature Engineering
  • Modeling and visualization of results for algorithms

 

Requirement :

Basic knowledge of Python required


Build your skills in the application of machine learning in healthcare and medical diagnostics.  This project will build your mastery of the key stages of analytics and predictive modeling in healthcare as you work with our project team to design, develop and implement a breast cancer diagnostic system


Problem Statement :

The application of machine learning approaches to medical diagnostics has grown explosively in recent years. The breast cancer diagnostics project enables participants to build intermediate-level skills in the application of data science and machine learning-based approaches to improving the quality and speed of medical diagnostics in patient care across the healthcare delivery spectrum

Aim :

This project aims to create mastery in candidates to build a model able to predict the diagnosis of breast cancer tissues as malignant or benign. Participants will learn how to combine biology, chemistry, physics, and data science to uncover insights or find previously hidden patterns  which in this case will be to predict whether a cancer cell is malignant or benign

Data for this project is drawn from digitized images of a fine needle aspirate (FNA) of a breast mass that describe characteristics of the cell nuclei present in the image

What you will learn :

  • Data Analytics toolset for health/medical diagnostics
  • Data Cleaning and Feature Engineering
  • Multiple Modeling Approaches for Medical data features
  • Model Performance Tunning
  • API-based model serving


This project features JIT-based training in Python and as such, candidates are not required to possess any skills in Python


Farm weed detection and management model complete with deployment


Leaf Detection System using OpenCV

  • Background/ Problem Statement

Computer Vision is a field of study that helps to develop techniques to recognize images and displays. It has different features like image recognition, object detection, image creation, etc.

We can detect objects present in an image like a human face, animal face, eyes, etc. We can use OpenCV to detect objects present in an image. OpenCV has many pre-trained models based on its features.

Our Leaf Detection System detects leaves from the image using Convolutional Neural Network (CNN) and OpenCV. It will also detect the type of leaf once it detects whether the image contains an image that is been provided.

  • Project Overview

In this system, the user will need to register first to log in to the system. With the credentials, they can log in to the system. The system will detect the leaf and the leaf type from an uploaded image. The user will just need to upload an image that contains a leaf in it.

This system will automatically detect the leaf from the image and once it finds the leaf it will further detect which type of leaf it is. The user will also be able to see the accuracy score.

The front end involves Html, CSS, and JavaScript and the back end involves Python. The framework used is Django and the database is MySQL. Here, we have implemented the OpenCV and CNN library. The dataset has been extracted from Kaggle.

  • Advantages
  • It is easy to maintain.
  • It is user-friendly.
  • The system can easily detect the leaf from the image.
  • It will also detect which type of leaf it is.
  • The user can also be able to see the accuracy score.
  • System Description

The system comprises 1 major module with their sub-modules as follows:

  • USER MODULE:
  • Sign Up
  • The user will need to register first to log in to the system.
  • Login
  • The user can log in with their username and password.
  • Start Detection:
  • The user will have to enter the image which has a leaf in it and it will detect the type of leaf after detection.

 

  • Project Life Cycle

            The waterfall model is a classical model used in the system development life cycle to create a system with a linear and sequential approach. It is termed a waterfall because the model develops systematically from one phase to another in a downward fashion. The waterfall approach does not define the process to go back to the previous phase to handle changes in requirements. The waterfall approach is the earliest approach that was used for software development.

 

Requirement:

No previous knowledge required



Gain mastery of image processing-based models with this project. You will work in a project team to work from the ground up to develop a full-functioning model to automate the process of car damage inspection for insurance claims and reporting using Computer Vision based techniques and Deep Learning


Problem Scenario :

Insurance firms often rely on care damage photos after an accident to conduct damage inspection as input for claims processing. This process can be tedious and time-consuming. This project provides an approach to leverage the power and speed of machine learning to efficiently inspect, assess and report on vehicle damage in the event of an accident


Aim :

This project aims to create mastery in candidates to utilize the power of deep learning and Convolutional Neural Networks (CNN ) to speed up the process of damage detection and evaluation to classify the type of car, type and severty of damage, and the location of the damage


Participants in this project will work in core teams to collect data and learn to implement data augmentation to improve model performance


What you will learn :

Computer Vision Project Organization

Data Requirements Design and data collection

Image data pre-processing and data augmentation techniques

Convolutional Neural Networks Design and Implementation

Model inferencing architecture


Requirements:

This project features JIT-based training in Python  and image pre-processing and as such, candidates are not required to possess any skills in Python


Program Overview:

This is a 5-month industry agnostic program designed to get you ready as a full stack data scientist.

Working through 10 core cross-industry projects you will see your mastery of the tools, techniques, and underlying concepts of the domain grow. 

Highlights of this program:

  • Implement 10+ real-world projects drawn from multiple industry domains
  • Learn from actual industry experts
  • Receive sound mentoring and coaching to set you on the path to rewarding growth
  • Gain experience working with real project teams at Prognoz.Ai through your internship
  • Become ready on Day 1 for a great job as a data scientist


Requirements:

No Previous knowledge required


Prepare for a career in the NLP space through 5 core projects designed to accelerate your mastery to intermediate levels.


Problem Scenario :

Unstructured data(text) presents challenges that are not easily overcome using data science and machine learning techniques for structured data. Almost all organizations that interact with consumers or stakeholders, including patient care in hospitals generate tons of textual data that potentially hold game-changing insights for the organization. As a result, the demand for NLP professionals has steadily increased across all industry domains

Aim :

This project portfolio is designed to take participants from beginner to intermediate levels of mastery in using NLP to process and model unstructured data (text). Working through 5 projects, participants will gain mastery of the NLTK package and Transformers for data preprocessing, transformation, and analytics 

Participants in this project will work in core teams to clean text data and data transformation techniques to  improve model performance 


What you will learn :

Text data cleaning and preprocessing

Feature representation and context preservation

Implement sentiment analysis

Implement named Entity Recognition models

Implement multiple recommendation systems


Get started with Time Series Analysis. Through a series of projects, you will build mastery of time series data analytics and modeling.

 

Projects Aim :

  1. Understanding different terminologies involved in Time Series Analysis.
  2. Statistical concepts and their code implementation.
  3. Understanding of ARIMA & SARIMA models along with their order selection.
  4. Use of rolling & non-rolling methods for In - Sample & Out-of - Sample forecasting.
  5. Implementation & difference between forecast function & predict function of ARIMA & SARIMA models.
  6. Specific code snippets that can be recycled for any Time Series Analysis problem.

Project Contents :

  • Dataset Information
  • Exploratory Data Analysis (EDA)
  • Summary of EDA
  • Time Series Analysis
  • Modeling
  • Insights and Inferencing

What you will learn :

  • Statistical Tests for Time Series Analysis.
  • Order selection for ARIMA & SARIMA models.
  • In-sample and Out-of-sample forecasting using rolling and non-rolling methods.
  • Difference between forecast function and predict function of ARIMA & SARIMA.

Start a career in AI-assisted driving with the traffic signs detection systems project.  Apply deep neural nets and computer vision to detect, locate and provide drivers with early information on road signs to enable active safety on the road


Problem Scenario :

The safety of commuters and pedestrians often depends on the level of alertness of the driver and the related interpretation of road signs. Under impaired driving conditions, the risks associated with missing or misinterpreting road signs increase and can potentially impact safety adversely. Using computer vision and deep learning, we can implement a model to assist in the early detection and alerting of road signs


Aim :

This project aims to create mastery in candidates to utilize the power of deep learning, Convolutional Neural Networks (CNN ), and computer vision to build models that detect road signs with great skill. This is a basic component of self-driving cars

Participants in this project will work in core teams to collect data and learn to implement data augmentation to improve model performance


What you will learn :

Computer Vision Project Organization

Data Requirements Design and data collection

Image data pre-processing and data augmentation techniques

Convolutional Neural Networks Design and Implementation

Model inferencing architecture



Requirements:

This project features JIT-based training in Python  and image pre-processing and as such, candidates are not required to possess any skills in Python


Data cleaning training for Cohorts 2 and 3