AbubakarSarwar
Software Developer | Data Scientist | National University of Computer and Emerging Sciences
Karachi, Pakistan
Pinned Repositories
Amazon-S3-To-Redshift-Copier
A solution created to upload a CSV file into Redshift instance using the help of Python and S3.
Audio-Signal-Processing-for-Music-Applications
This repository holds all the codes/documentation/working/templates of how to process audio/music/song files using digital signal processing primitives. The Music files will range from .wav to .mp3 file. The repository will cover extracting low-level descriptors (freq, wavelength, duration.. etc) i.e easily extracted from an audio file, mid-level descriptors (harmony, rythm.. etc) i.e information general about music and high-level descriptors (genre, emotion, instrument.. etc) i.e relevant to the users.
Bank-Management-System
Cache-Management-Emulator
An application that allowed the analysis of the difference between running programs with and without cache.
Custom-Topology-Generation-and-Firewall-Policies-in-SDN
A python based application with GUI that allowed the user to create a customized topology for the SDN.
DeepPink-Analysis
A thorough analysis of the Deep Pink Chess Engine, and proposed upgrades to improve the final results.
Gender-Classification-of-Twitter-Account-Based-on-Tweets-UserBio
Instrument-Classification-of-IRMAS-Dataset
- The purpose of this research is to compare and contrast the different algorithm’s results over the IRMAS dataset. The dataset contains 4 different instruments Electric Guitar, Acoustic Guitar, Violin and Trumpet. The features extraction process is performed using the Librosa library and numerous features were extracted such as tempo, beat frames, mfcc etc. Feature selection was done by dimension reduction techniques such as Principal Component Analysis and L1 based feature selection. The method used to classify the instruments were a series of five classification algorithms(KNN, Naive Bayes, Random Forest, Decision Tree, Bagging) using three different approaches which consists of K-folds, Hold out and Leave one out. The results were then compared and contrasted with respect to accuracy.
Mail-Service-Using-Windows-Service
Unified
A web application created for students to help them in exchanging books and notes. Also, to allow them to find people for group study.
AbubakarSarwar's Repositories
AbubakarSarwar/Instrument-Classification-of-IRMAS-Dataset
- The purpose of this research is to compare and contrast the different algorithm’s results over the IRMAS dataset. The dataset contains 4 different instruments Electric Guitar, Acoustic Guitar, Violin and Trumpet. The features extraction process is performed using the Librosa library and numerous features were extracted such as tempo, beat frames, mfcc etc. Feature selection was done by dimension reduction techniques such as Principal Component Analysis and L1 based feature selection. The method used to classify the instruments were a series of five classification algorithms(KNN, Naive Bayes, Random Forest, Decision Tree, Bagging) using three different approaches which consists of K-folds, Hold out and Leave one out. The results were then compared and contrasted with respect to accuracy.
AbubakarSarwar/Custom-Topology-Generation-and-Firewall-Policies-in-SDN
A python based application with GUI that allowed the user to create a customized topology for the SDN.
AbubakarSarwar/Mail-Service-Using-Windows-Service
AbubakarSarwar/Amazon-S3-To-Redshift-Copier
A solution created to upload a CSV file into Redshift instance using the help of Python and S3.
AbubakarSarwar/Audio-Signal-Processing-for-Music-Applications
This repository holds all the codes/documentation/working/templates of how to process audio/music/song files using digital signal processing primitives. The Music files will range from .wav to .mp3 file. The repository will cover extracting low-level descriptors (freq, wavelength, duration.. etc) i.e easily extracted from an audio file, mid-level descriptors (harmony, rythm.. etc) i.e information general about music and high-level descriptors (genre, emotion, instrument.. etc) i.e relevant to the users.
AbubakarSarwar/Bank-Management-System
AbubakarSarwar/Cache-Management-Emulator
An application that allowed the analysis of the difference between running programs with and without cache.
AbubakarSarwar/DeepPink-Analysis
A thorough analysis of the Deep Pink Chess Engine, and proposed upgrades to improve the final results.
AbubakarSarwar/Gender-Classification-of-Twitter-Account-Based-on-Tweets-UserBio
AbubakarSarwar/Unified
A web application created for students to help them in exchanging books and notes. Also, to allow them to find people for group study.
AbubakarSarwar/Flight-Reservation-System
A web application to help users book a flight online.
AbubakarSarwar/Folder-Monitoring-System-Via-Windows-Service
AbubakarSarwar/Gang-of-Four-Design-Patterns
Implementation of Design Patterns such as Adapter, Bridge, Builder etc in C#
AbubakarSarwar/KNN-Classifier-Via-JAVA
AbubakarSarwar/librosa
Python library for audio and music analysis
AbubakarSarwar/Music-Emotion-Recognition
A Machine Learning Approach of Thayers Emotional Model to Plot a 2D Cartesian and Polar Planes using x-axis as Valence and y-axis as Arousal
AbubakarSarwar/Music-Genre-Classification
Classifying English Music (.mp3) files using Music Information Retrieval (MIR), Digital/Audio Signal Processing (DIP) and Machine Learning (ML) Strategies
AbubakarSarwar/USB-Device-Driver
A customized manual USB device driver that was installed in the kernel of Linux as a model.