Fauzan Mohammed Portofolio

Image Classification

Classifying a leaf wether healthy or with a disease

This project uses Dataset from Botenical Society of America. The aim is to develop a model using images from a training dataset that can: 1) Accurately classify a given image from a testing dataset into different diseased categories or a healthy leaf; 2) Accurately distinguish between many diseases, sometimes more than one on a single leaf; 3) Deal with rare classes and novel symptoms; 4) Address depth perception—angle, light, shade, physiological age of the leaf; and 5) Incorporate expert knowledge in identification.

Cancer Prediction

Cancer Predictions using Deep Learning

The goal of the study was to identify both micro- and macro-metastases in digital images of lymph nodes. Because lymph node metastases occur in the majority of cancer types, this topic is very pertinent (e.g. breast, prostate, colon). Small glands called lymph nodes filter lymph, a fluid that travels through the lymphatic system. In order to distinguish metastatic cancer in small image patches extracted from larger digital pathology scans, deep learning models were used.

Name Entity Recognizer

NER

In this project, I delved into the capabilities of SpaCy’s Named Entity Recognition (NER) pipeline to identify and classify entities within textual data. SpaCy’s NER model can recognize a wide range of entities, including organizations, geopolitical entities, monetary values, and more. The model is trained on diverse web texts, such as blogs and news articles, making it robust in understanding various contexts

Breast Cancer Predictions

Predict Wether Cells are Either Bening of Mallicious.

A machine learning project employing both the KNeighbors Classifier and the Support Vector Machines Classifier, to predict whether a group of cells are cancerous or benign.The human body has about 100 trillion cells within it. And usually those cells behave in a certain way. However, occasionally, one of these 100 trillion cells, behave in a different way and keeps dividing and pushes the other cells around it out of the way. That cell stops observing the rules of the tissue within which it is located and begins to move out of its normal position and starts invading into the tissues around it and sometimes entering the bloodstream and becoming is called a metastasis. At the end the KNN model did better as compared to the SVM. This project was deployed via Heroku

Bank Note Analysis

Analysing Bank note to determine originality

This project uses Dataset from Kaggle. In this project, i took advantage of the data science pipeline and employed different supervised machine learning algorithms to classify a bank not as fake or genuine. in the end, I observed the best working model.

Fuel Efficiency

Fuel Efficiency Prediction

This project uses Dataset from Kaggle To create a model that can estimate miles per gallon (MPG), which is the most common indicator of a car's economy. The model was trained using three regression algorithms: Decision Tree, Random Forest, and XGBoost.

Compressive Strenght

Predicting Compressive Strength Of Concrete

This project uses Dataset from UCI Machine Learning Repository. A personal project predicting the strenght of concrete. Being a mechanical engineer, this is somewhat a domain understanding for me. Employed various regression models while also using KFold for proper intuition.

Data Science Professional Certificate Capstone Project

IBM

This project contains an end-to-end solution and a final report for the IBM data science professional certificate capstone project.

Netflix Recommendation Clone

Recommendation System

The recommendation system uses a combination of collaborative filtering and content-based filtering to make personalized recommendations to users. It takes into account the ratings and reviews that users have given to different movies, as well as the metadata associated with each movie (such as its genre, director, and cast).

Employee Acess Challenge

Amazon

The dataset is made up of historical data gathered between 2010 and 2020. Over time, employees are manually granted or denied access to resources. I developed an algorithm that used previous data to forecast denial/approval for an unknown group of employees.

Sales Predictions

Big Mart

This project uses Dataset from Kaggle. Big Mart is a big supermarket chain with stores all over the world. The management of the shop has set out a challenge to all data sciencetist to help them create a model that can predict sales per product for each store

Bank Loans

Loan Predictions

This project uses Dataset from UCI Machine Learning Repository. By using different supervised machine learnig algortithms to predict whether an individual is elegible for a loan or not

Object Recognition

Vehicle

The data contains features extracted from the silhouette of vehicles in different angles. Four "Corgie" model vehicles were used for the experiment: a double decker bus, Cheverolet van, Saab 9000 and an Opel Manta 400 cars. This particular combination of vehicles was chosen with the expectation that the bus, van and either one of the cars would be readily distinguishable, but it would be more difficult to distinguish between the cars. The purpose is to classify a given silhouette as one of three types of vehicle, using a set of features extracted from the silhouette. The vehicle may be viewed from one of many different angles.

Fauzan Mohammed

Projects