Muhammad Allah Rakha

Hadoop & Hadoop Ecosystem (Linux)

MARCH_24_2022

AAAA STARK INDUSTRY

• Hadoop Installation, Commands, Word-Count Example
• Follow the Hadoop-PDF instraction to installaion and more process.
• Hadoop is an open source software programming framework for storing a large amount of data and performing the computation. Its framework is based on Java programming with some native code in C and shell scripts.

Java and Linux and Hadoop

• hadoop-3.3.1
• openjdk-8-jdk
• openssh-server, openssh-client
• hadoop-3.3.1
• WordCount.java (file)

GitHub Link: Hadoop & Hadoop Ecosystem (Linux)

MPI and OpenMP (Linux)

MAY_8_2022

AAAA STARK INDUSTRY

• MPI and OpenMP program run in CPP programming language. Operating System: Linux

C++

• openmpi-bin
• mpich

GitHub Link: MPI and OpenMP (Linux)

NVIDIA CUDA Google Colab

MAY_10_2022

AAAA STARK INDUSTRY

• Deployment of NVIDIA-CUDA on Google Colab. With in examples codes (Vector Addition and Matrix Multiplication).
• Vector Addition CUDA
• Matrix Multiplication

GitHub Link: NVIDIA CUDA Google Colab

Perceptron Neural Network

MAY_11_2022

AAAA STARK INDUSTRY

• Artificial Natural Network Perceptron (Forward Pass and Back Propagation).
• Weights and Bias.
• Forward Pass: Net Input Function, Activation Function (Sigmoid).
• Threshold.
• Back Propagation: Binary Cross Entropy Loss, Computing Gradients/ Slopes/ Derivatives, Gradient Descent Step, Epoch.
• Write code to perform N number of epochs until the loss gets close to zero.
• Compute the loss after each epcoh using sklearn loss function.
• Try different values of alpha and see how it affects the training process.
• Once the perceptron gets trained, test the trained perceptron on testing data and report test accuracy, confusion matrix.

GitHub Link: Perceptron Neural Network

Text Classification NLP

MAY_12_2022

AAAA STARK INDUSTRY

• Data Set Load (Movies - TV)
• Train, Test and Encoder (Train and Validation)
• Count Vectors as features
• TF-IDF Vectors as features (Word level, N-Gram level, Character level)
• Text / NLP based features
• Naive Bayes Classifier (Accuray, Confusion Matrix, Precision, Recall Score, F1 Score)
• Linear Classifier (Accuray, Confusion Matrix, Precision, Recall Score, F1 Score)
• Word Density
• Rating Text
• Create Word Clouds

GitHub Link: Text Classification NLP

Word Association and Mutual Information NLP

MAY_13_2022

AAAA STARK INDUSTRY

• Encoding Character Detsets Checking
• Reading the Dataset (Dataset-CalheirosMoroRita-2017.csv)
• Cleaning Text Data (LowerText, Tokenize, UseLessWord-Remove, StopWord-Remove, PartOfSpeech, Lemmatize)
• Vader Lexicon (Positive, Negatives, Compound)
• Add the number of Characters and Words
• Gensim Module Vectors (Word2Vec, Doc2Vec)
• TF-IDF (Term Frequency - Inverse Document Frequency)
• Word Clouds
• Interpreting Mutual Information Scores
• Correlation-Matrix with Heatmap
• Bar Plot

GitHub Link: Word Association and Mutual Information NLP

Life Expectancy Predication

AUGUST_24_2021

AAAA STARK INDUSTRY

• Life expectancy refers to the average age a person is estimated to live and is an important factor to determine thepopulation health of any country. In the pre-modern world, Life expectancy was very less close to about 30 years but after19th Century life expectancy started to increase and it nearly doubled.
• The project tries to create a model based on data provided by the World Health Organization (WHO) to evaluate the lifeexpectancy for different countries in years. The data offers a timeframe from 2000 to 2015.

Python Libraries and Dataset

• Sklearn, Pandas, Plotly, Seaborn, Scipy, Pycounty_Convert, Matplotlib, Numpy. Life Expectancy Data (.csv)

GitHub Link: Life Expectancy Predication

Breast Cancer Analysis

AUGUST_25_2021

AAAA STARK INDUSTRY

• Breast cancer (BC) is one of the most common cancers among women worldwide, representing the majority of new cancercases and cancer-related deaths according to global statistics, making it a significant public health problem in today’ssociety.
• The dataset it is contains 596 rows and 32 columns of tumor shape and specifications. The tumor is classified as benign ormalignant based on its geometry and shape. Features are computed from a digitized image of a fine needle aspirate(FNA) of a breast mass, which is type of biopsy procedure. They describe characteristics of the cell nuclei present in theimage.

Python Libraries and Dataset

• Sklearn, Pandas, Subprocess, Matplotlib, Numpy. Data (.csv)

GitHub Link: Breast Cancer Analysis

Twitter Sentiment Analysis

AUGUST_26_2021

AAAA STARK INDUSTRY

• Sentiment analysis, also referred to as opinion mining or emotion extraction is the classification of emotions within atextual data.
• Twitter is a social media platform that has been mostly used by people to express emotions for particular events.
• We have collected tweets for a number of events, analyzed them using a number of Machine Learning algorithms like NaïveBayes, SVM, Random Forest classifier and LSTM and compared the results.

Project Pipeline

• Import Necessary Dependencies, Necessary Setting, Read and Load the Dataset, Pre-Process dataset, Split train andtest, Word2Vec, Tokenize Text, Label Encoder, Embedding layer, Build Model, Compile model, Callbacks, Train,Evaluate, Predict, Confusion Matrix, Classification Report, Accuracy Score and Save model.

Python Libraries and Dataset

• Sklearn, Keras, Pandas, Gensim, Seaborn, Scipy, NLTK, Matplotlib, Numpy, Pickle. Sentiment140 Dataset (.csv) whichconsists of 1,600,000 tweets

GitHub Link: Breast Cancer Analysis

Detecting Parkinson's Disease

MAR_2_2021

AAAA STARK INDUSTRY

• Parkinson’s disease is a progressive disorder of the central nervous system affecting movement and inducing tremors and stiffness. It is a neurodegenerative disorder affecting dopamine-producing neurons in the brain.

Python Libraries and Dataset

• Scikit-learn, Numpy, Pandas, and XGBoost

GitHub Link: Detecting Parkinson's Disease

Detecting Fake News

MAR_10_2021

AAAA STARK INDUSTRY

• A type of yellow journalism, fake news encapsulates pieces of news that may be hoaxes and is generally spread throughsocial media and other online media. This is often done to further or impose certain ideas and is often achieved withpolitical agendas. Such news items may contain false and/or exaggerated claims, and may end up being viralized byalgorithms, and users may end up in a filter bubble.

Python Libraries and Dataset

• TfidfVectorizer: TF (Term Frequency) and IDF (Inverse Document Frequency)

GitHub Link: Detecting Fake News

Customer Segmentation

APR_1_2021

AAAA STARK INDUSTRY

• Customer Segmentation is the process of division of customer base into several groups of individuals that share a similarityin different ways that are relevant to marketing such as gender, age, interests, and miscellaneous spending habits.
• Companies that deploy customer segmentation are under the notion that every customer has different requirements andrequire a specific marketing effort to address them appropriately.

R Libraries and Dataset

• K-Mean Clustring

GitHub Link: Customer Segmentation

Image Classification

MAR_18_2021

AAAA STARK INDUSTRY

• The classification problem is to categorize all the pixels of a digital image into one of the defined classes.
• Image classification is the most critical use case in digital image analysis.
• Image classification is an application of both supervised classification and unsupervised classification.

Python Libraries and Dataset

• Keras, TensorFlow, Matplotlib, Numpy. CIFAR-10 (dataset)

GitHub Link: Image Classification

Convolutional Neural Networks

MAR_19_2021

AAAA STARK INDUSTRY

• Convolutional Neural Networks, like neural networks, are made up of neurons with learnable weights and biases. Eachneuron receives several inputs, takes a weighted sum over them, pass it through an activation function and responds withan output.
• The whole network has a loss function and all the tips and tricks that we developed for neural networks still apply onConvolutional Neural Networks.

Python Libraries and Dataset

• Keras, TensorFlow, Matplotlib, Numpy. CIFAR-10 (dataset)

GitHub Link: Convolutional Neural Networks

Web Scraping Site (https://www.thestar.com.my)

AUGUST_20_2021

AAAA STARK INDUSTRY

• The Star | Malaysia News: National Regional and World News
• The website was recognized in 2014 as one of the best in Asia by the World Association of Newspapers and NewsPublishers (WAN-IFRA).
• Simply build a web scraper to collect all the review information from all the web pages of this site, and store it in a dataframe.

Python Libraries and Dataset

• Pandas, Urlopen, Request, BeautifulSoup, Numpy. Thestar_database (.csv)

GitHub Link: Web Scraping Site (https://www.thestar.com.my)

Netflix Data Visualization

AUGUST_23_2021

AAAA STARK INDUSTRY

• Netflix’s strategy is focused on data analysis. The goal is to improve data visualization tools to provide relevantinformation, in real time, on the state of the environment. This is intended for all departments and businesses. Equippingthe entire company enables all stakeholders to be assisted in their decision-making or creative process.

Python Libraries and Dataset

• Sklearn, Pandas, , Seaborn, Plotly, Matplotlib, Numpy. Netflix Titles (.csv)

GitHub Link: Netflix Data Visualization

World Happiness Report

AUGUST_22_2021

AAAA STARK INDUSTRY

• The World Happiness Report is a landmark survey of the state of global happiness. The report continues to gain globalrecognition as governments, organizations and civil society increasingly use happiness indicators to inform their policy-making decisions. Leading experts across fields – economics, psychology, survey analysis, national statistics, health, publicpolicy and more – describe how measurements of well-being can be used effectively to assess the progress of nations.The reports review the state of happiness in the world today and show how the new science of happiness explainspersonal and national variations in happiness.

Python Libraries and Dataset

• Pandas, Seaborn, Matplotlib, Numpy. World Happiness Report/World Happiness Report 2021 (.csv)

GitHub Link: World Happiness Report

Framingham Heart Study-Cohort (FHS-Cohort)

AUGUST_21_2021

AAAA STARK INDUSTRY

• The Framingham Heart Study (FHS) has conducted seminal research defining cardiovascular disease (CVD) risk factors andfundamentally shaping public health guidelines for CVD prevention over the past five decades.
• This dataset comprises of predictors such as cholesterol, age, diabetes, and family history that are used to predict theonset of heart disease in a patient.

Python Libraries and Dataset

• Pandas, Seaborn, Matplotlib, Numpy. Framingham (.csv)

GitHub Link: Framingham Heart Study-Cohort (FHS-Cohort)

Personal Portfolio Website (AAAASTARK)

June_4_2021

AAAA STARK INDUSTRY

• Personal Website of AAAASTARK & MUHAMMA ALLAH RAKHA. The Personal Portfolio website is developed by using the ReactJS and with Django Python Framework. This website is made for Rusume, Books, Services, Project, and information about AAAASTARK.

Python Libraries and Web Deployment

• Asgiref
• Dj-Database-Url
• Django
• Django-Crispy-Forms
• Gunicorn
• Django-Heroku
• Psycopg2
• Pytz
• Sqlparse
• Whitenoise
• For Deployment (Heroku & Heroku CLI, Git & GitHub)

Website Link: Peronal Portfolio Website (AAAASTARK)

GitHub Link: Peronal Portfolio Website (AAAASTARK)

AAAA STARK DESKTOP APPLICATION

JULY_30_2021

AAAA STARK INDUSTRY

• AAAA STARK desktop application is make, the based of AAAA STARK website of module visualization. The database is online. We use the Programming Language and Programming FrameWork for this project development.
• Language: HTML & CSS & JAVASCRIPT & NODEJS & MYSQL DATABASE
• FrameWork: ELECTRON JS

Electron Libraries and NodeJs Libraries

• Electron
• MySQL Database
• Sequelize
• Electron-Forge Package
• Electron-Forge Make
• Electron-Forge Publish
• Electron-Squirrel-Startup
• Electron-Squirrel-Startup
• Electron-Forge/Cli
• Electron-Forge/Maker-Deb
• Electron-Forge/Maker-Rpm
• Electron-Forge/Maker-Squirrel
• Electron-Forge/Maker-Zip

AAAA STARK MOBILE APPLICATION

AUGUST_20_2021

AAAA STARK INDUSTRY

• AAAA STARK moblie application is make, the based of AAAA STARK website of module visualization. The database is online. We use the Programming Language and Programming FrameWork for this project development.
• Language: JAVA & HTML & CSS & JAVASCRIPT & NODEJS
• FrameWork: CORDOVA
• Database: MYSQL

Cordova Libraries and Java Libraries

• Cordova
• Cordova-Android
• Cordova-Plugin-Whitelist
• Keytool
• Jarsigner
• Zipalign

SOLAR SYSTEM 3D

JULY_26_2021

AAAA STARK INDUSTRY

• 3D Solar System is make, the based of 3D Module Blue Visualization. We use the Programming Language and Programming FrameWork for this project development.
• Language: HTML & CSS & JAVASCRIPT & NODEJS
• FrameWork: ELECTRON JS

Electron Libraries and NodeJs Libraries

• Electron
• Electron-Builder
• Electron-Forge Package
• Electron-Forge Make
• Electron-Forge Publish
• Electron-Squirrel-Startup
• Electron-Squirrel-Startup
• Electron-Forge/Cli
• Electron-Forge/Maker-Deb
• Electron-Forge/Maker-Rpm
• Electron-Forge/Maker-Squirrel
• Electron-Forge/Maker-Zip

Human Resource Management System (AAAASTARK)

November_15_2021

AAAA STARK INDUSTRY

• Human Resource Management System (HRMS) Website Application. Employee Dashboard. Information mange to relative Managing to the employee records and some more personal details. In hrms system is only employee dashboard.

Python Libraries and Web Deployment

• Asgiref
• Certifi
• Charset-Normalizer
• Dj-Database-Url
• Dj-Static
• Django
• Django-Crispy-Forms
• Django-Heroku
• Gunicorn
• Idna
• Jinja2
• MarkupSafe
• Mysql-Connector
• Mysql-Connector-Python
• Protobuf
• Psycopg2
• Python-Decouple
• Pytz
• Requests
• Requests-Toolbelt
• Sqlparse
• Static3
• Urllib3
• Whitenoise
• Django
• For Deployment (Heroku & Heroku CLI, Git & GitHub

Website Link: Human Resource Management System (AAAASTARK)

GitHub Link: Human Resource Management System (AAAASTARK)

Todo Website (AAAASTARK)

MAY_1_2021

AAAA STARK INDUSTRY

• The todo website is developed by using the Django Python Framework. In which enter your todo plains and remove yourplains at any time you want to. Backed we use the database of Django SQLite Python.

Python Libraries and Web Deployment

• asgiref==3.3.4
• Django==3.2
• django-crispy-forms==1.11.2
• gunicorn==20.1.0
• pytz==2021.1
• sqlparse==0.4.1
• whitenoise==5.2.0
• For Deployment (Heroku & Heroku CLI, Git & GitHub

Website Link: Todo Website (AAAASTARK)

GitHub Link: Todo Website (AAAASTARK)

Human Resource Management System HRMS

JAN_10_2021

AAAA STARK INDUSTRY

• The project build for Employee Dashbord. Manage the all requard of employee and staff.
• Only admin access provieded to Administration Office.

Python Libraries and Web Deployment

• Asgiref
• Certifi
• Charset-Normalizer
• Dj-Database-Url
• Dj-Static
• Django
• Django-Crispy-Forms
• Django-Heroku
• Gunicorn
• Idna
• Jinja2
• MarkupSafe
• Mysql-Connector
• Mysql-Connector-Python
• Protobuf
• Psycopg2
• Python-Decouple
• Pytz
• Requests
• Requests-Toolbelt
• Sqlparse
• Static3
• Urllib3
• Whitenoise
• Django

GitHub Link: Human Resource Management System HRMS

Top Password Security System

DEC_25_2020

AAAA STARK INDUSTRY

• The project base in three different Algorithm base. 1: Cryptography 2: Caesar Cipher 3: Vigenere Cipher. The OOP(C++)language use in this project building.
• When user enter a password in the type of character. Then these algorithm are process of Ciphertext into Plaintext orPlaintext into Ciphertext

C++ Libraries and Algorithm

• Iostream, Fstream, Cstream, String, Cstring, Cmath, Stdlib.h, Conio.h (Libraries)
• Caesar Cipher, Cryptography, Vigenère Cipher (Algorithm)

Explanation Video Link: Top Password Security System

GitHub Link: Top Password Security System

Job Scheduling Problem

JAN_12_2021

AAAA STARK INDUSTRY

• Jоb Sсheduling is а methоd used tо set аnd аdjust jоb рlасement аims tо get the biggest рrоfit thаt саn be run by а system in ассоrdаnсe with сertаin рrоvisiоn. The intended рrоvisiоn is in the fоrm оf dividing the sсhedule ассоrding tо the set time limit оr deаdline whiсh is the time tо соmрlete the jоb.
• Sсheduling саn be interрreted аs аllосаting а number оf resоurсes (resоurсes) tо рerfоrm а number оf tаsks оr орerаtiоns within а сertаin рeriоd оf time аnd is а deсisiоn-mаking рrосess whоse rоle is very imроrtаnt in the mаnufасturing аnd serviсe industries, nаmely аllосаting existing resоurсes.
• Ассоrding tо the definitiоn аbоve, it саn be соnсluded thаt sсheduling is аn аllосаtiоn рrосess thаt is саrried оut tо dо wоrk within а сertаin рeriоd оf time. Just like jоb sсheduling, the divisiоn оf tаsks tо be саrried оut must be seen frоm the time needed аnd the рrоfit generаted tо асhieve орtimаl results.

C Libraries and Algorithm

• Stdio.h, Stdlib.h (Libraries)
• Greedy Approach (Algorithm)

GitHub Link: Job Scheduling Problem

Digital House System Simulation (IOT/IOE) Packet Tracer 7.2 Version

JAN_20_2020

AAAA STARK INDUSTRY

• The technology has been growing from day to day in human life. The necessity for the development of technology is to lead human life comfortably. The basic need of human to lead his/her life comfortably is home. A home with updated latest technology which means a digital house. One is needed to create a digital house when electronic devices are switched on and off. Digital house development is achieved by simulation via testing system, network setup and wireless home gatewa computer network equipment required by a digital house network cisco packet tracer using Internet Thing (IoT)/IoE command.
• Including various smart objects which are used for implementing digital house automation such as windows, fans, lights, doors, lawn sprinklers web cams and various sensors etc. The Home Gateway via IOT server are used for controlling the objects and sensors, which are providing programming environment for controlling objects that are connected and provide control mechanisms through the registration of Home Gateway via IOT server (smart devices).

Aim and Scope

• Living home that includes smart objects with specific functions is called smart home. I.e. aimed to improve safety, comfort and efficiency.
• Safe House System. The control every things of home using smart devices.

GitHub Link: Digital House System Simulation (IOT/IOE) Packet Tracer 7.2 Version